From 8de1e9b01b03d2805f58aa490ea5bf0df003bc80 Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@nvidia.com>
Date: Wed, 22 Sep 2021 11:28:50 +0300
Subject: net/mlx5: Add uid field to UAR allocation structures

Add uid field to mlx5_ifc_alloc_uar_in_bits and
mlx5_ifc_dealloc_uar_out_bits structs.

This field will be used by FW to manage UAR according to uid.

Signed-off-by: Meir Lichtinger <meirl@nvidia.com>
Reviewed-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f3638d09ba77..96f5fb2af811 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -7569,7 +7569,7 @@ 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];
@@ -8416,7 +8416,7 @@ 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];
-- 
cgit v1.2.3


From d2c8a1554c10d5e0443b1f97f480d7dacd55cf55 Mon Sep 17 00:00:00 2001
From: Meir Lichtinger <meirl@nvidia.com>
Date: Wed, 22 Sep 2021 11:28:51 +0300
Subject: IB/mlx5: Enable UAR to have DevX UID

UID field was added to alloc_uar and dealloc_uar PRM command, to specify
DevX UID for UAR. This change enables firmware validating user access to
its own UAR resources.

For the kernel allocated UARs the UID will stay 0 as of today.

Signed-off-by: Meir Lichtinger <meirl@nvidia.com>
Reviewed-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/cmd.c              | 26 +++++++++++++
 drivers/infiniband/hw/mlx5/cmd.h              |  2 +
 drivers/infiniband/hw/mlx5/main.c             | 55 +++++++++++++++------------
 drivers/net/ethernet/mellanox/mlx5/core/uar.c | 14 +++----
 include/linux/mlx5/driver.h                   |  2 -
 5 files changed, 66 insertions(+), 33 deletions(-)

(limited to 'include/linux/mlx5')

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/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/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/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e23417424373..1b8bae246b28 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1005,8 +1005,6 @@ 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);
-- 
cgit v1.2.3


From 5249001d69a223811ad654884c6115d55158fd51 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@nvidia.com>
Date: Wed, 1 Sep 2021 19:05:02 +0300
Subject: net/mlx5: Bridge, mark reg_c1 when pushing VLAN

On ingress VLAN push also assign value 0x7FE to reg_c1 tunnel id+opts
bits (tunnel id 0, which is not a valid tunnel id, and option 0x7FE which
was reserved by one of previous patches in the series). In following patch
the reg value is matched on egress miss to restore the packet to its
original state by removing the VLAN before passing it to the software data
path.

Signed-off-by: Vlad Buslov <vladbu@nvidia.com>
Reviewed-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 .../net/ethernet/mellanox/mlx5/core/esw/bridge.c   | 40 +++++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/esw/bridge_priv.h  |  1 +
 include/linux/mlx5/eswitch.h                       |  9 +++++
 3 files changed, 49 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 8361dfc0bf1a..439b67b4380f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -465,8 +465,10 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char
 		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 
 	if (vlan && vlan->pkt_reformat_push) {
-		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
+			MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 		flow_act.pkt_reformat = vlan->pkt_reformat_push;
+		flow_act.modify_hdr = vlan->pkt_mod_hdr_push_mark;
 	} else if (vlan) {
 		MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria,
 				 outer_headers.cvlan_tag);
@@ -845,6 +847,33 @@ mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_
 	vlan->pkt_reformat_pop = NULL;
 }
 
+static int
+mlx5_esw_bridge_vlan_push_mark_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {};
+	struct mlx5_modify_hdr *pkt_mod_hdr;
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_1);
+	MLX5_SET(set_action_in, action, offset, 8);
+	MLX5_SET(set_action_in, action, length, ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS);
+	MLX5_SET(set_action_in, action, data, ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN);
+
+	pkt_mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, 1, action);
+	if (IS_ERR(pkt_mod_hdr))
+		return PTR_ERR(pkt_mod_hdr);
+
+	vlan->pkt_mod_hdr_push_mark = pkt_mod_hdr;
+	return 0;
+}
+
+static void
+mlx5_esw_bridge_vlan_push_mark_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw)
+{
+	mlx5_modify_header_dealloc(esw->dev, vlan->pkt_mod_hdr_push_mark);
+	vlan->pkt_mod_hdr_push_mark = NULL;
+}
+
 static struct mlx5_esw_bridge_vlan *
 mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *port,
 			    struct mlx5_eswitch *esw)
@@ -864,6 +893,10 @@ mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *por
 		err = mlx5_esw_bridge_vlan_push_create(vlan, esw);
 		if (err)
 			goto err_vlan_push;
+
+		err = mlx5_esw_bridge_vlan_push_mark_create(vlan, esw);
+		if (err)
+			goto err_vlan_push_mark;
 	}
 	if (flags & BRIDGE_VLAN_INFO_UNTAGGED) {
 		err = mlx5_esw_bridge_vlan_pop_create(vlan, esw);
@@ -882,6 +915,9 @@ err_xa_insert:
 	if (vlan->pkt_reformat_pop)
 		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
 err_vlan_pop:
+	if (vlan->pkt_mod_hdr_push_mark)
+		mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw);
+err_vlan_push_mark:
 	if (vlan->pkt_reformat_push)
 		mlx5_esw_bridge_vlan_push_cleanup(vlan, esw);
 err_vlan_push:
@@ -908,6 +944,8 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
 
 	if (vlan->pkt_reformat_pop)
 		mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw);
+	if (vlan->pkt_mod_hdr_push_mark)
+		mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw);
 	if (vlan->pkt_reformat_push)
 		mlx5_esw_bridge_vlan_push_cleanup(vlan, esw);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
index 52964a82d6a6..878311fe950a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -49,6 +49,7 @@ struct mlx5_esw_bridge_vlan {
 	struct list_head fdb_list;
 	struct mlx5_pkt_reformat *pkt_reformat_push;
 	struct mlx5_pkt_reformat *pkt_reformat_pop;
+	struct mlx5_modify_hdr *pkt_mod_hdr_push_mark;
 };
 
 struct mlx5_esw_bridge_port {
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 4ab5c1fc1270..97afcea39a7b 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -130,11 +130,20 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 #define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET)
 #define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET)
 #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */
+#define ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT
 /* 0x7FF is a reserved mapping */
 #define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \
 				       ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT)
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK
+/* 0x7FE is a reserved mapping for bridge ingress push vlan mark */
+#define ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN (ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT - 1)
+#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN ((ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN << \
+					   ESW_TUN_OPTS_BITS) | \
+					  ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN)
+#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK \
+	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
+		ESW_TUN_OPTS_OFFSET + 1)
 
 u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From 3663ad34bc707fc85492f4d83a313f5df84718d4 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 19 Aug 2021 16:18:57 +0300
Subject: net/mlx5: Shift control IRQ to the last index

Control IRQ is the first IRQ vector. This complicates handling of
completion irqs as we need to offset them by one.
in the next patch, there are scenarios where completion and control EQs
will share the same irq. for example: functions with single IRQ. To ease
such scenarios, we shift control IRQ to the end of the irq array.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/infiniband/hw/mlx5/odp.c                   |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  9 +++++----
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h |  2 --
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c  | 10 +++++-----
 include/linux/mlx5/driver.h                        |  2 ++
 5 files changed, 13 insertions(+), 11 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index d0d98e584ebc..81147d774dd2 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -1559,6 +1559,7 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
 
 	eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int;
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_IB_NUM_PF_EQE,
 	};
 	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 605c8ecc3610..792e0d6aa861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -632,6 +632,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_NUM_CMD_EQE,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD,
 	};
@@ -644,6 +645,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL);
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = MLX5_NUM_ASYNC_EQE,
 	};
 
@@ -653,6 +655,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 		goto err2;
 
 	param = (struct mlx5_eq_param) {
+		.irq_index = MLX5_IRQ_EQ_CTRL,
 		.nent = /* TODO: sriov max_vf + */ 1,
 		.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST,
 	};
@@ -806,8 +809,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 	ncomp_eqs = table->num_comp_eqs;
 	nent = MLX5_COMP_EQ_SIZE;
 	for (i = 0; i < ncomp_eqs; i++) {
-		int vecidx = i + MLX5_IRQ_VEC_COMP_BASE;
 		struct mlx5_eq_param param = {};
+		int vecidx = i;
 
 		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
 		if (!eq) {
@@ -953,9 +956,7 @@ static int set_rmap(struct mlx5_core_dev *mdev)
 		goto err_out;
 	}
 
-	vecidx = MLX5_IRQ_VEC_COMP_BASE;
-	for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE;
-	     vecidx++) {
+	for (vecidx = 0; vecidx < eq_table->num_comp_eqs; vecidx++) {
 		err = irq_cpu_rmap_add(eq_table->rmap,
 				       pci_irq_vector(mdev->pdev, vecidx));
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index abd024173c42..8116815663a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -8,8 +8,6 @@
 
 #define MLX5_COMP_EQS_PER_SF 8
 
-#define MLX5_IRQ_EQ_CTRL (0)
-
 struct mlx5_irq;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 763c83a02380..a66144b54fc8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -194,15 +194,14 @@ static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 	snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx);
 }
 
-static void irq_set_name(char *name, int vecidx)
+static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 {
-	if (vecidx == 0) {
+	if (vecidx == pool->xa_num_irqs.max) {
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx);
 		return;
 	}
 
-	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d",
-		 vecidx - MLX5_IRQ_VEC_COMP_BASE);
+	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx);
 }
 
 static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
@@ -217,7 +216,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 		return ERR_PTR(-ENOMEM);
 	irq->irqn = pci_irq_vector(dev->pdev, i);
 	if (!pool->name[0])
-		irq_set_name(name, i);
+		irq_set_name(pool, name, i);
 	else
 		irq_sf_set_name(pool, name, i);
 	ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh);
@@ -440,6 +439,7 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx,
 	}
 pf_irq:
 	pool = irq_table->pf_pool;
+	vecidx = (vecidx == MLX5_IRQ_EQ_CTRL) ? pool->xa_num_irqs.max : vecidx;
 	irq = irq_pool_request_vector(pool, vecidx, affinity);
 out:
 	if (IS_ERR(irq))
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e23417424373..0ca719c00824 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -59,6 +59,8 @@
 
 #define MLX5_ADEV_NAME "mlx5_core"
 
+#define MLX5_IRQ_EQ_CTRL (U8_MAX)
+
 enum {
 	MLX5_BOARD_ID_LEN = 64,
 };
-- 
cgit v1.2.3


From f891b7cdbdcda116fd26bbd706f91bd58567aa17 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Sun, 1 Aug 2021 12:08:49 +0300
Subject: net/mlx5: Enable single IRQ for PCI Function

Prior to this patch the driver requires two IRQs to function properly,
one required IRQ for control and at least one required IRQ for IO.

This requirement can be relaxed to one as the driver now allows
sharing of IRQs, so control and IO EQs can share the same irq.

This is needed for high scale amount of VFs.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 26 +++++++++++++++++------
 include/linux/mlx5/eq.h                           |  1 -
 2 files changed, 19 insertions(+), 8 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index a66144b54fc8..830444f927d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -196,6 +196,12 @@ static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 
 static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 {
+	if (!pool->xa_num_irqs.max) {
+		/* in case we only have a single irq for the device */
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_combined%d", vecidx);
+		return;
+	}
+
 	if (vecidx == pool->xa_num_irqs.max) {
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx);
 		return;
@@ -204,6 +210,11 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
 	snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx);
 }
 
+static bool irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
+{
+	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
+}
+
 static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 {
 	struct mlx5_core_dev *dev = pool->dev;
@@ -215,7 +226,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i)
 	if (!irq)
 		return ERR_PTR(-ENOMEM);
 	irq->irqn = pci_irq_vector(dev->pdev, i);
-	if (!pool->name[0])
+	if (!irq_pool_is_sf_pool(pool))
 		irq_set_name(pool, name, i);
 	else
 		irq_sf_set_name(pool, name, i);
@@ -385,6 +396,9 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx,
 	if (IS_ERR(irq) || !affinity)
 		goto unlock;
 	cpumask_copy(irq->mask, affinity);
+	if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max &&
+	    cpumask_empty(irq->mask))
+		cpumask_set_cpu(0, irq->mask);
 	irq_set_affinity_hint(irq->irqn, irq->mask);
 unlock:
 	mutex_unlock(&pool->lock);
@@ -577,6 +591,8 @@ void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev)
 
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table)
 {
+	if (!table->pf_pool->xa_num_irqs.max)
+		return 1;
 	return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min;
 }
 
@@ -592,19 +608,15 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev)
 	if (mlx5_core_is_sf(dev))
 		return 0;
 
-	pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-		 MLX5_IRQ_VEC_COMP_BASE;
+	pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + 1;
 	pf_vec = min_t(int, pf_vec, num_eqs);
-	if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE)
-		return -ENOMEM;
 
 	total_vec = pf_vec;
 	if (mlx5_sf_max_functions(dev))
 		total_vec += MLX5_IRQ_CTRL_SF_MAX +
 			MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev);
 
-	total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1,
-					  total_vec, PCI_IRQ_MSIX);
+	total_vec = pci_alloc_irq_vectors(dev->pdev, 1, total_vec, PCI_IRQ_MSIX);
 	if (total_vec < 0)
 		return total_vec;
 	pf_vec = min(pf_vec, total_vec);
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index cea6ecb4b73e..ea3ff5a8ced3 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -4,7 +4,6 @@
 #ifndef MLX5_CORE_EQ_H
 #define MLX5_CORE_EQ_H
 
-#define MLX5_IRQ_VEC_COMP_BASE 1
 #define MLX5_NUM_CMD_EQE   (32)
 #define MLX5_NUM_ASYNC_EQE (0x1000)
 #define MLX5_NUM_SPARE_EQE (0x80)
-- 
cgit v1.2.3


From 8208461d3912e3e97e31bcbd4ce716e4a251a5dd Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Fri, 8 Oct 2021 15:24:27 +0300
Subject: net/mlx5: Add ifc bits to support optional counters

Adding bth_opcode field and the relevant bits. This field will be used
to capture and count congestion notification packets (CNP).

Adding source_vhca_port support bit.
This field will be used to check the capability to use the
source_vhca_port as a match criteria in cases of dual port.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 96f5fb2af811..34254dbe7117 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -342,7 +342,7 @@ 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];
@@ -393,6 +393,14 @@ 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];
@@ -539,7 +547,7 @@ 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];
@@ -756,7 +764,15 @@ 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];
 
-- 
cgit v1.2.3


From b8dfed636fc6239396c3a2ae5f812505906cf215 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Fri, 8 Oct 2021 15:24:28 +0300
Subject: net/mlx5: Add priorities for counters in RDMA namespaces

Add additional flow steering priorities in the RDMA namespace.
This allows adding flow counters to count filtered RDMA traffic and then
continue processing in the regular RDMA steering flow.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 54 +++++++++++++++++++----
 include/linux/mlx5/device.h                       |  2 +
 include/linux/mlx5/fs.h                           |  2 +
 3 files changed, 50 insertions(+), 8 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fe501ba88bea..71a08f84d49d 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))),
 	}
 };
@@ -2215,6 +2247,12 @@ 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/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 66eaf0aa7f69..ed0230ff9422 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1456,6 +1456,8 @@ 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/fs.h b/include/linux/mlx5/fs.h
index 0106c67e8ccb..f2c3da2006d9 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -83,6 +83,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_RX,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
+	MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS,
+	MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS,
 };
 
 enum {
-- 
cgit v1.2.3


From 4b2c5fa9c9902ce34ecea6711558d9af96351b31 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Wed, 21 Jul 2021 16:14:12 +0300
Subject: net/mlx5: Add layout to support default timeouts register

Add needed structures and defines for DTOR (default timeouts register).
This will be used to get timeouts values from FW instead of hard coded
values in the driver code thus enabling support for slower devices which
need longer timeouts.

Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/device.h   |  4 +++-
 include/linux/mlx5/driver.h   |  1 +
 include/linux/mlx5/mlx5_ifc.h | 37 ++++++++++++++++++++++++++++++++++++-
 3 files changed, 40 insertions(+), 2 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 66eaf0aa7f69..109cc8106d16 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -577,7 +577,9 @@ struct mlx5_init_seg {
 	__be32			rsvd1[120];
 	__be32			initializing;
 	struct health_buffer	health;
-	__be32			rsvd2[880];
+	__be32			rsvd2[878];
+	__be32			cmd_exec_to;
+	__be32			cmd_q_init_to;
 	__be32			internal_timer_h;
 	__be32			internal_timer_l;
 	__be32			rsvd3[2];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 0ca719c00824..ccbd87fbd3bf 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -156,6 +156,7 @@ enum {
 	MLX5_REG_MIRC		 = 0x9162,
 	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
+	MLX5_REG_DTOR            = 0xC00E,
 };
 
 enum mlx5_qpts_trust_state {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 993204a6c1a1..b8bff5109656 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1306,7 +1306,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vhca_resource_manager[0x1];
 
 	u8         hca_cap_2[0x1];
-	u8         reserved_at_21[0x2];
+	u8         reserved_at_21[0x1];
+	u8         dtor[0x1];
 	u8         event_on_vhca_state_teardown_request[0x1];
 	u8         event_on_vhca_state_in_use[0x1];
 	u8         event_on_vhca_state_active[0x1];
@@ -2807,6 +2808,40 @@ struct mlx5_ifc_dropped_packet_logged_bits {
 	u8         reserved_at_0[0xe0];
 };
 
+struct mlx5_ifc_default_timeout_bits {
+	u8         to_multiplier[0x3];
+	u8         reserved_at_3[0x9];
+	u8         to_value[0x14];
+};
+
+struct mlx5_ifc_dtor_reg_bits {
+	u8         reserved_at_0[0x20];
+
+	struct mlx5_ifc_default_timeout_bits pcie_toggle_to;
+
+	u8         reserved_at_40[0x60];
+
+	struct mlx5_ifc_default_timeout_bits health_poll_to;
+
+	struct mlx5_ifc_default_timeout_bits full_crdump_to;
+
+	struct mlx5_ifc_default_timeout_bits fw_reset_to;
+
+	struct mlx5_ifc_default_timeout_bits flush_on_err_to;
+
+	struct mlx5_ifc_default_timeout_bits pci_sync_update_to;
+
+	struct mlx5_ifc_default_timeout_bits tear_down_to;
+
+	struct mlx5_ifc_default_timeout_bits fsm_reactivate_to;
+
+	struct mlx5_ifc_default_timeout_bits reclaim_pages_to;
+
+	struct mlx5_ifc_default_timeout_bits reclaim_vfs_pages_to;
+
+	u8         reserved_at_1c0[0x40];
+};
+
 enum {
 	MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN                 = 0x1,
 	MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR  = 0x2,
-- 
cgit v1.2.3


From 5945e1adeab527ec96c75a786213c146d4d482a4 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@mellanox.com>
Date: Thu, 7 Oct 2021 18:00:27 +0300
Subject: net/mlx5: Read timeout values from init segment

Replace hard coded timeouts with values stored in firmware's init
segment. Timeouts are read from init segment during driver load. If init
segment timeouts are not supported then fallback to hard coded defaults
instead. Also move pre initialization timeouts which cannot be read from
firmware to the new mechanism.

Signed-off-by: Amir Tzin <amirtz@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c      | 18 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c | 96 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h | 28 +++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     | 38 +++++----
 include/linux/mlx5/driver.h                        |  5 +-
 6 files changed, 161 insertions(+), 26 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 63032cd6efb1..a151575be51f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -17,7 +17,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
-		fw_reset.o qos.o
+		fw_reset.o qos.o lib/tout.o
 
 #
 # Netdev basic
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 4dc3a822907a..f71ec4d9d68e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -45,6 +45,7 @@
 
 #include "mlx5_core.h"
 #include "lib/eq.h"
+#include "lib/tout.h"
 
 enum {
 	CMD_IF_REV = 5,
@@ -225,9 +226,13 @@ static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
 
 static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 {
-	unsigned long poll_end = jiffies + msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC + 1000);
+	struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd);
+	u64 cmd_to_ms = mlx5_tout_ms(dev, CMD);
+	unsigned long poll_end;
 	u8 own;
 
+	poll_end = jiffies + msecs_to_jiffies(cmd_to_ms + 1000);
+
 	do {
 		own = READ_ONCE(ent->lay->status_own);
 		if (!(own & CMD_OWNER_HW)) {
@@ -925,15 +930,18 @@ static void cmd_work_handler(struct work_struct *work)
 {
 	struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work);
 	struct mlx5_cmd *cmd = ent->cmd;
-	struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd);
-	unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
+	bool poll_cmd = ent->polling;
 	struct mlx5_cmd_layout *lay;
+	struct mlx5_core_dev *dev;
+	unsigned long cb_timeout;
 	struct semaphore *sem;
 	unsigned long flags;
-	bool poll_cmd = ent->polling;
 	int alloc_ret;
 	int cmd_mode;
 
+	dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD));
+
 	complete(&ent->handling);
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -1073,7 +1081,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
 
 static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 {
-	unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC);
+	unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD));
 	struct mlx5_cmd *cmd = &dev->cmd;
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
new file mode 100644
index 000000000000..ee266e0d122a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include <linux/mlx5/driver.h>
+#include "lib/tout.h"
+
+struct mlx5_timeouts {
+	u64 to[MAX_TIMEOUT_TYPES];
+};
+
+static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = {
+	[MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000,
+	[MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000,
+	[MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2,
+	[MLX5_TO_FW_INIT_MS] = 2000,
+	[MLX5_TO_CMD_MS] = 60000
+};
+
+static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type)
+{
+	dev->timeouts->to[type] = val;
+}
+
+static void tout_set_def_val(struct mlx5_core_dev *dev)
+{
+	int i;
+
+	for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++)
+		tout_set(dev, tout_def_sw_val[i], i);
+}
+
+int mlx5_tout_init(struct mlx5_core_dev *dev)
+{
+	dev->timeouts = kmalloc(sizeof(*dev->timeouts), GFP_KERNEL);
+	if (!dev->timeouts)
+		return -ENOMEM;
+
+	tout_set_def_val(dev);
+	return 0;
+}
+
+void mlx5_tout_cleanup(struct mlx5_core_dev *dev)
+{
+	kfree(dev->timeouts);
+}
+
+/* Time register consists of two fields to_multiplier(time out multiplier)
+ * and to_value(time out value). to_value is the quantity of the time units and
+ * to_multiplier is the type and should be one off these four values.
+ * 0x0: millisecond
+ * 0x1: seconds
+ * 0x2: minutes
+ * 0x3: hours
+ * this function converts the time stored in the two register fields into
+ * millisecond.
+ */
+static u64 tout_convert_reg_field_to_ms(u32 to_mul, u32 to_val)
+{
+	u64 msec = to_val;
+
+	to_mul &= 0x3;
+	/* convert hours/minutes/seconds to miliseconds */
+	if (to_mul)
+		msec *= 1000 * int_pow(60, to_mul - 1);
+
+	return msec;
+}
+
+static u64 tout_convert_iseg_to_ms(u32 iseg_to)
+{
+	return tout_convert_reg_field_to_ms(iseg_to >> 29, iseg_to & 0xfffff);
+}
+
+static bool tout_is_supported(struct mlx5_core_dev *dev)
+{
+	return !!ioread32be(&dev->iseg->cmd_q_init_to);
+}
+
+void mlx5_tout_query_iseg(struct mlx5_core_dev *dev)
+{
+	u32 to;
+
+	if (!tout_is_supported(dev))
+		return;
+
+	to = ioread32be(&dev->iseg->cmd_q_init_to);
+	tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_FW_INIT_MS);
+
+	to = ioread32be(&dev->iseg->cmd_exec_to);
+	tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_CMD_MS);
+}
+
+u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type)
+{
+	return dev->timeouts->to[type];
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
new file mode 100644
index 000000000000..7e6fc61c5b45
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef MLX5_TIMEOUTS_H
+#define MLX5_TIMEOUTS_H
+
+enum mlx5_timeouts_types {
+	/* pre init timeouts (not read from FW) */
+	MLX5_TO_FW_PRE_INIT_TIMEOUT_MS,
+	MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS,
+	MLX5_TO_FW_PRE_INIT_WAIT_MS,
+
+	/* init segment timeouts */
+	MLX5_TO_FW_INIT_MS,
+	MLX5_TO_CMD_MS,
+
+	MAX_TIMEOUT_TYPES
+};
+
+struct mlx5_core_dev;
+int mlx5_tout_init(struct mlx5_core_dev *dev);
+void mlx5_tout_cleanup(struct mlx5_core_dev *dev);
+void mlx5_tout_query_iseg(struct mlx5_core_dev *dev);
+u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type);
+
+#define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS)
+
+# endif /* MLX5_TIMEOUTS_H */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 65313448a47c..b4893eac6ed6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -60,6 +60,7 @@
 #include "devlink.h"
 #include "fw_reset.h"
 #include "lib/mlx5.h"
+#include "lib/tout.h"
 #include "fpga/core.h"
 #include "fpga/ipsec.h"
 #include "accel/ipsec.h"
@@ -176,11 +177,6 @@ static struct mlx5_profile profile[] = {
 	},
 };
 
-#define FW_INIT_TIMEOUT_MILI		2000
-#define FW_INIT_WAIT_MS			2
-#define FW_PRE_INIT_TIMEOUT_MILI	120000
-#define FW_INIT_WARN_MESSAGE_INTERVAL	20000
-
 static int fw_initializing(struct mlx5_core_dev *dev)
 {
 	return ioread32be(&dev->iseg->initializing) >> 31;
@@ -193,8 +189,6 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
 	unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili);
 	int err = 0;
 
-	BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL);
-
 	while (fw_initializing(dev)) {
 		if (time_after(jiffies, end)) {
 			err = -EBUSY;
@@ -205,7 +199,7 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
 				       jiffies_to_msecs(end - warn) / 1000);
 			warn = jiffies + msecs_to_jiffies(warn_time_mili);
 		}
-		msleep(FW_INIT_WAIT_MS);
+		msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT));
 	}
 
 	return err;
@@ -975,25 +969,34 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot)
 	if (mlx5_core_is_pf(dev))
 		pcie_print_link_status(dev->pdev);
 
+	err = mlx5_tout_init(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed initializing timeouts, aborting\n");
+		return err;
+	}
+
 	/* wait for firmware to accept initialization segments configurations
 	 */
-	err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL);
+	err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT),
+			   mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL));
 	if (err) {
-		mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n",
-			      FW_PRE_INIT_TIMEOUT_MILI);
-		return err;
+		mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n",
+			      mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT));
+		goto err_tout_cleanup;
 	}
 
 	err = mlx5_cmd_init(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed initializing command interface, aborting\n");
-		return err;
+		goto err_tout_cleanup;
 	}
 
-	err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0);
+	mlx5_tout_query_iseg(dev);
+
+	err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0);
 	if (err) {
-		mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n",
-			      FW_INIT_TIMEOUT_MILI);
+		mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n",
+			      mlx5_tout_ms(dev, FW_INIT));
 		goto err_cmd_cleanup;
 	}
 
@@ -1062,6 +1065,8 @@ err_disable_hca:
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
+err_tout_cleanup:
+	mlx5_tout_cleanup(dev);
 
 	return err;
 }
@@ -1080,6 +1085,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot)
 	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_cleanup(dev);
+	mlx5_tout_cleanup(dev);
 
 	return 0;
 }
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ccbd87fbd3bf..fb06e8870aee 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -66,10 +66,6 @@ enum {
 };
 
 enum {
-	/* one minute for the sake of bringup. Generally, commands must always
-	 * complete and we may need to increase this timeout value
-	 */
-	MLX5_CMD_TIMEOUT_MSEC	= 60 * 1000,
 	MLX5_CMD_WQ_MAX_NAME	= 32,
 };
 
@@ -755,6 +751,7 @@ struct mlx5_core_dev {
 		u32 qcam[MLX5_ST_SZ_DW(qcam_reg)];
 		u8  embedded_cpu;
 	} caps;
+	struct mlx5_timeouts	*timeouts;
 	u64			sys_image_guid;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
-- 
cgit v1.2.3


From fbfa97b4d79f26042f188b84959065213e9d3e99 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 18 Aug 2021 13:21:30 +0300
Subject: net/mlx5: Disable roce at HCA level

Currently, when a user disables roce via the devlink param, this change
isn't passed down to the device.
If device allows disabling RoCE at device level, make use of it. This
instructs the device to skip memory allocations related to RoCE
functionality which otherwise is done by the device.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 25 ++++++++++++++++++++++-
 include/linux/mlx5/driver.h                       |  9 ++++----
 include/linux/mlx5/mlx5_ifc.h                     |  3 ++-
 4 files changed, 33 insertions(+), 7 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index a85341a41cd0..1c98652b244a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -454,7 +454,8 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	bool new_state = val.vbool;
 
-	if (new_state && !MLX5_CAP_GEN(dev, roce)) {
+	if (new_state && !MLX5_CAP_GEN(dev, roce) &&
+	    !MLX5_CAP_GEN(dev, roce_rw_supported)) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 75d284272119..47d92fb459ed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -558,15 +558,38 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 		MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
+	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
+/* Cached MLX5_CAP_GEN(dev, roce) can be out of sync this early in the
+ * boot process.
+ * In case RoCE cap is writable in FW and user/devlink requested to change the
+ * cap, we are yet to query the final state of the above cap.
+ * Hence, the need for this function.
+ *
+ * Returns
+ * True:
+ * 1) RoCE cap is read only in FW and already disabled
+ * OR:
+ * 2) RoCE cap is writable in FW and user/devlink requested it off.
+ *
+ * In any other case, return False.
+ */
+static bool is_roce_fw_disabled(struct mlx5_core_dev *dev)
+{
+	return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) ||
+		(!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce));
+}
+
 static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	void *set_hca_cap;
 	int err;
 
-	if (!MLX5_CAP_GEN(dev, roce))
+	if (is_roce_fw_disabled(dev))
 		return 0;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fb06e8870aee..7c8b5f06c2cd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1251,11 +1251,12 @@ static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev)
 {
 	struct devlink *devlink = priv_to_devlink(dev);
 	union devlink_param_value val;
+	int err;
 
-	devlink_param_driverinit_value_get(devlink,
-					   DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
-					   &val);
-	return val.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+						 &val);
+	return err ? MLX5_CAP_GEN(dev, roce) : val.vbool;
 }
 
 #endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b8bff5109656..c614ad1da44d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1588,7 +1588,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_tis_per_sq[0x5];
 
 	u8         ext_stride_num_range[0x1];
-	u8         reserved_at_3a1[0x2];
+	u8         roce_rw_supported[0x1];
+	u8         reserved_at_3a2[0x1];
 	u8         log_max_stride_sz_rq[0x5];
 	u8         reserved_at_3a8[0x3];
 	u8         log_min_stride_sz_rq[0x5];
-- 
cgit v1.2.3


From 2ec16ddde1fa31a83aee04320b248e94348d9152 Mon Sep 17 00:00:00 2001
From: Rongwei Liu <rongweil@nvidia.com>
Date: Thu, 16 Sep 2021 10:46:17 +0300
Subject: net/mlx5: Introduce new device index wrapper

Downstream patches.

Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c       | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lag.c              | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c       | 2 +-
 include/linux/mlx5/driver.h                                | 5 +++++
 6 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
index 86e079310ac3..ae52e7f38306 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c
@@ -24,7 +24,7 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv)
 
 	if (mlx5_core_is_pf(priv->mdev)) {
 		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn);
+		attrs.phys.port_number = mlx5_get_dev_index(priv->mdev);
 		if (MLX5_ESWITCH_MANAGER(priv->mdev)) {
 			mlx5e_devlink_get_port_parent_id(priv->mdev, &ppid);
 			memcpy(attrs.switch_id.id, ppid.id, ppid.id_len);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 20af557ae30c..7f9b96d9537e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -36,7 +36,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16
 		return NULL;
 
 	mlx5_esw_get_port_parent_id(dev, &ppid);
-	pfnum = PCI_FUNC(dev->pdev->devfn);
+	pfnum = mlx5_get_dev_index(dev);
 	external = mlx5_core_is_ecpf_esw_manager(dev);
 	if (external)
 		controller_num = dev->priv.eswitch->offloads.host_number + 1;
@@ -149,7 +149,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	pfnum = PCI_FUNC(dev->pdev->devfn);
+	pfnum = mlx5_get_dev_index(dev);
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index ca7e31a1a431..3e5a7d74020b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2798,7 +2798,7 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw)
 	int id;
 
 	/* Only 4 bits of pf_num */
-	pf_num = PCI_FUNC(esw->dev->pdev->devfn);
+	pf_num = mlx5_get_dev_index(esw->dev);
 	if (pf_num > max_pf_num)
 		return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index ca5690b0a7ab..f35c8ba48aac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -688,7 +688,7 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev,
 				 struct mlx5_core_dev *dev,
 				 struct net_device *netdev)
 {
-	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
+	unsigned int fn = mlx5_get_dev_index(dev);
 
 	if (fn >= MLX5_MAX_PORTS)
 		return;
@@ -718,7 +718,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev,
 static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev,
 			       struct mlx5_core_dev *dev)
 {
-	unsigned int fn = PCI_FUNC(dev->pdev->devfn);
+	unsigned int fn = mlx5_get_dev_index(dev);
 
 	if (fn >= MLX5_MAX_PORTS)
 		return;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 13891fdc607e..e1bb3acf45e6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -323,7 +323,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_
 		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
 		return -EOPNOTSUPP;
 	}
-	if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) {
+	if (new_attr->pfnum != mlx5_get_dev_index(dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
 		return -EOPNOTSUPP;
 	}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7c8b5f06c2cd..aecc38b90de5 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1243,6 +1243,11 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev)
 	return MLX5_CAP_GEN(dev, native_port_num);
 }
 
+static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev)
+{
+	return PCI_FUNC(dev->pdev->devfn);
+}
+
 enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
-- 
cgit v1.2.3


From 1021d0645d593ea86193c5fc371e33e5b208e14d Mon Sep 17 00:00:00 2001
From: Rongwei Liu <rongweil@nvidia.com>
Date: Tue, 12 Oct 2021 10:40:52 +0300
Subject: net/mlx5: Use native_port_num as 1st option of device index

Using "native_port_num" can support more NICs.

Fallback to PCIe IDs if "native_port_num" query fails.

Signed-off-by: Rongwei Liu <rongweil@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 include/linux/mlx5/driver.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5')

diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index aecc38b90de5..cf508685abca 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1245,7 +1245,12 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev)
 
 static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev)
 {
-	return PCI_FUNC(dev->pdev->devfn);
+	int idx = MLX5_CAP_GEN(dev, native_port_num);
+
+	if (idx >= 1 && idx <= MLX5_MAX_PORTS)
+		return idx - 1;
+	else
+		return PCI_FUNC(dev->pdev->devfn);
 }
 
 enum {
-- 
cgit v1.2.3


From 425a563acb1d1872c0036fbcb644247640edbbc6 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Sun, 23 May 2021 13:34:28 +0300
Subject: net/mlx5: Introduce port selection namespace

Add new port selection flow steering namespace. Flow steering rules in
this namespaceare are used to determine the physical port for egress
packets.

Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c  |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 26 +++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h |  7 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/fw.c      |  6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c    |  1 +
 include/linux/mlx5/device.h                       | 15 +++++++++++++
 include/linux/mlx5/fs.h                           |  1 +
 include/linux/mlx5/mlx5_ifc.h                     | 25 ++++++++++++++++++++--
 8 files changed, 78 insertions(+), 4 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 7db8df64a60e..caefdb7dfefe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -969,6 +969,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_NIC_TX:
 	case FS_FT_RDMA_RX:
 	case FS_FT_RDMA_TX:
+	case FS_FT_PORT_SEL:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fe501ba88bea..8d8696f7c3f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2191,6 +2191,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 		if (steering->fdb_root_ns)
 			return &steering->fdb_root_ns->ns;
 		return NULL;
+	case MLX5_FLOW_NAMESPACE_PORT_SEL:
+		if (steering->port_sel_root_ns)
+			return &steering->port_sel_root_ns->ns;
+		return NULL;
 	case MLX5_FLOW_NAMESPACE_SNIFFER_RX:
 		if (steering->sniffer_rx_root_ns)
 			return &steering->sniffer_rx_root_ns->ns;
@@ -2596,6 +2600,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev)
 	steering->fdb_root_ns = NULL;
 	kfree(steering->fdb_sub_ns);
 	steering->fdb_sub_ns = NULL;
+	cleanup_root_ns(steering->port_sel_root_ns);
 	cleanup_root_ns(steering->sniffer_rx_root_ns);
 	cleanup_root_ns(steering->sniffer_tx_root_ns);
 	cleanup_root_ns(steering->rdma_rx_root_ns);
@@ -2634,6 +2639,21 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering)
 	return PTR_ERR_OR_ZERO(prio);
 }
 
+#define PORT_SEL_NUM_LEVELS 3
+static int init_port_sel_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *prio;
+
+	steering->port_sel_root_ns = create_root_ns(steering, FS_FT_PORT_SEL);
+	if (!steering->port_sel_root_ns)
+		return -ENOMEM;
+
+	/* Create single prio */
+	prio = fs_create_prio(&steering->port_sel_root_ns->ns, 0,
+			      PORT_SEL_NUM_LEVELS);
+	return PTR_ERR_OR_ZERO(prio);
+}
+
 static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering)
 {
 	int err;
@@ -3020,6 +3040,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_PORT_SELECTION(dev, ft_support)) {
+		err = init_port_sel_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) &&
 	    MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) {
 		err = init_rdma_rx_root_ns(steering);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 98240badc342..79d37530afb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -97,7 +97,8 @@ enum fs_flow_table_type {
 	FS_FT_SNIFFER_TX	= 0X6,
 	FS_FT_RDMA_RX		= 0X7,
 	FS_FT_RDMA_TX		= 0X8,
-	FS_FT_MAX_TYPE = FS_FT_RDMA_TX,
+	FS_FT_PORT_SEL		= 0X9,
+	FS_FT_MAX_TYPE = FS_FT_PORT_SEL,
 };
 
 enum fs_flow_table_op_mod {
@@ -129,6 +130,7 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace	*rdma_rx_root_ns;
 	struct mlx5_flow_root_namespace	*rdma_tx_root_ns;
 	struct mlx5_flow_root_namespace	*egress_root_ns;
+	struct mlx5_flow_root_namespace	*port_sel_root_ns;
 	int esw_egress_acl_vports;
 	int esw_ingress_acl_vports;
 };
@@ -341,7 +343,8 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 	(type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) :		\
 	(type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) :		\
 	(type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) :      \
-	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_TX != FS_FT_MAX_TYPE))\
+	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \
+	(BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\
 	)
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index f4f8993eac17..1037e3629e7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -149,6 +149,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	if (err)
 		return err;
 
+	if (MLX5_CAP_GEN(dev, port_selection_cap)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION);
+		if (err)
+			return err;
+	}
+
 	if (MLX5_CAP_GEN(dev, hca_cap_2)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2);
 		if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 47d92fb459ed..f8446395163a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1416,6 +1416,7 @@ static const int types[] = {
 	MLX5_CAP_TLS,
 	MLX5_CAP_VDPA_EMULATION,
 	MLX5_CAP_IPSEC,
+	MLX5_CAP_PORT_SELECTION,
 };
 
 static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 109cc8106d16..347167c18802 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1185,6 +1185,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_GENERAL_2 = 0x20,
+	MLX5_CAP_PORT_SELECTION = 0x25,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1342,6 +1343,20 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap)
 
+#define MLX5_CAP_PORT_SELECTION(mdev, cap) \
+	MLX5_GET(port_selection_cap, \
+		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap)
+
+#define MLX5_CAP_PORT_SELECTION_MAX(mdev, cap) \
+	MLX5_GET(port_selection_cap, \
+		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap)
+
+#define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \
+	MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap)
+
+#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \
+	MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap)
+
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 0106c67e8ccb..259fcc168340 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -83,6 +83,7 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_RX,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL,
 	MLX5_FLOW_NAMESPACE_RDMA_TX,
+	MLX5_FLOW_NAMESPACE_PORT_SEL,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c614ad1da44d..db1d9c69c1fa 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -767,6 +767,18 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8         reserved_at_20c0[0x5f40];
 };
 
+struct mlx5_ifc_port_selection_cap_bits {
+	u8         reserved_at_0[0x10];
+	u8         port_select_flow_table[0x1];
+	u8         reserved_at_11[0xf];
+
+	u8         reserved_at_20[0x1e0];
+
+	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection;
+
+	u8         reserved_at_400[0x7c00];
+};
+
 enum {
 	MLX5_FDB_TO_VPORT_REG_C_0 = 0x01,
 	MLX5_FDB_TO_VPORT_REG_C_1 = 0x02,
@@ -1515,7 +1527,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         uar_4k[0x1];
 	u8         reserved_at_241[0x9];
 	u8         uar_sz[0x6];
-	u8         reserved_at_248[0x2];
+	u8         port_selection_cap[0x1];
+	u8         reserved_at_248[0x1];
 	u8         umem_uid_0[0x1];
 	u8         reserved_at_250[0x5];
 	u8         log_pg_sz[0x8];
@@ -3164,6 +3177,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
+	struct mlx5_ifc_port_selection_cap_bits port_selection_cap;
 	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
 	struct mlx5_ifc_debug_cap_bits debug_cap;
@@ -10434,9 +10448,16 @@ struct mlx5_ifc_dcbx_param_bits {
 	u8         reserved_at_a0[0x160];
 };
 
+enum {
+	MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0,
+	MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT,
+};
+
 struct mlx5_ifc_lagc_bits {
 	u8         fdb_selection_mode[0x1];
-	u8         reserved_at_1[0x1c];
+	u8         reserved_at_1[0x14];
+	u8         port_select_mode[0x3];
+	u8         reserved_at_18[0x5];
 	u8         lag_state[0x3];
 
 	u8         reserved_at_20[0x14];
-- 
cgit v1.2.3


From e7e2519e3632396a25031b7e828ed35332e5dd07 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Tue, 6 Jul 2021 17:48:26 +0300
Subject: net/mlx5: Add support to create match definer

Introduce new APIs to create and destroy flow matcher
for given format id.

Flow match definer object is used for defining the fields and
mask used for the hash calculation. User should mask the desired
fields like done in the match criteria.

This object is assigned to flow group of type hash. In this flow
group type, packets lookup is done based on the hash result.

This patch also adds the required bits to create such flow group.

Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c   |  57 +++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h   |   4 +
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c  |  46 ++++
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.h  |   5 +
 .../ethernet/mellanox/mlx5/core/steering/fs_dr.c   |  15 ++
 include/linux/mlx5/fs.h                            |   8 +
 include/linux/mlx5/mlx5_ifc.h                      | 272 +++++++++++++++++++--
 7 files changed, 380 insertions(+), 27 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index caefdb7dfefe..2c82dc118460 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -185,6 +185,20 @@ static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master,
 	return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
 }
 
+static int
+mlx5_cmd_stub_destroy_match_definer(struct mlx5_flow_root_namespace *ns,
+				    int definer_id)
+{
+	return 0;
+}
+
+static int
+mlx5_cmd_stub_create_match_definer(struct mlx5_flow_root_namespace *ns,
+				   u16 format_id, u32 *match_mask)
+{
+	return 0;
+}
+
 static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns,
 				   struct mlx5_flow_table *ft, u32 underlay_qpn,
 				   bool disconnect)
@@ -909,6 +923,45 @@ static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
 	mlx5_cmd_exec_in(dev, dealloc_modify_header_context, in);
 }
 
+static int mlx5_cmd_destroy_match_definer(struct mlx5_flow_root_namespace *ns,
+					  int definer_id)
+{
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type,
+		 MLX5_OBJ_TYPE_MATCH_DEFINER);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, definer_id);
+
+	return mlx5_cmd_exec(ns->dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns,
+					 u16 format_id, u32 *match_mask)
+{
+	u32 out[MLX5_ST_SZ_DW(create_match_definer_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_match_definer_in)] = {};
+	struct mlx5_core_dev *dev = ns->dev;
+	void *ptr;
+	int err;
+
+	MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.opcode,
+		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.obj_type,
+		 MLX5_OBJ_TYPE_MATCH_DEFINER);
+
+	ptr = MLX5_ADDR_OF(create_match_definer_in, in, obj_context);
+	MLX5_SET(match_definer, ptr, format_id, format_id);
+
+	ptr = MLX5_ADDR_OF(match_definer, ptr, match_mask);
+	memcpy(ptr, match_mask, MLX5_FLD_SZ_BYTES(match_definer, match_mask));
+
+	err = mlx5_cmd_exec_inout(dev, create_match_definer, in, out);
+	return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+}
+
 static const struct mlx5_flow_cmds mlx5_flow_cmds = {
 	.create_flow_table = mlx5_cmd_create_flow_table,
 	.destroy_flow_table = mlx5_cmd_destroy_flow_table,
@@ -923,6 +976,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = {
 	.packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc,
 	.modify_header_alloc = mlx5_cmd_modify_header_alloc,
 	.modify_header_dealloc = mlx5_cmd_modify_header_dealloc,
+	.create_match_definer = mlx5_cmd_create_match_definer,
+	.destroy_match_definer = mlx5_cmd_destroy_match_definer,
 	.set_peer = mlx5_cmd_stub_set_peer,
 	.create_ns = mlx5_cmd_stub_create_ns,
 	.destroy_ns = mlx5_cmd_stub_destroy_ns,
@@ -942,6 +997,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
 	.packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc,
 	.modify_header_alloc = mlx5_cmd_stub_modify_header_alloc,
 	.modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc,
+	.create_match_definer = mlx5_cmd_stub_create_match_definer,
+	.destroy_match_definer = mlx5_cmd_stub_destroy_match_definer,
 	.set_peer = mlx5_cmd_stub_set_peer,
 	.create_ns = mlx5_cmd_stub_create_ns,
 	.destroy_ns = mlx5_cmd_stub_destroy_ns,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
index 5ecd33cdc087..220ec632d35a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h
@@ -97,6 +97,10 @@ struct mlx5_flow_cmds {
 
 	int (*create_ns)(struct mlx5_flow_root_namespace *ns);
 	int (*destroy_ns)(struct mlx5_flow_root_namespace *ns);
+	int (*create_match_definer)(struct mlx5_flow_root_namespace *ns,
+				    u16 format_id, u32 *match_mask);
+	int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns,
+				     int definer_id);
 };
 
 int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 8d8696f7c3f5..873efde0d458 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3250,6 +3250,52 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
 
+int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer)
+{
+	return definer->id;
+}
+
+struct mlx5_flow_definer *
+mlx5_create_match_definer(struct mlx5_core_dev *dev,
+			  enum mlx5_flow_namespace_type ns_type, u16 format_id,
+			  u32 *match_mask)
+{
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_definer *definer;
+	int id;
+
+	root = get_root_namespace(dev, ns_type);
+	if (!root)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	definer = kzalloc(sizeof(*definer), GFP_KERNEL);
+	if (!definer)
+		return ERR_PTR(-ENOMEM);
+
+	definer->ns_type = ns_type;
+	id = root->cmds->create_match_definer(root, format_id, match_mask);
+	if (id < 0) {
+		mlx5_core_warn(root->dev, "Failed to create match definer (%d)\n", id);
+		kfree(definer);
+		return ERR_PTR(id);
+	}
+	definer->id = id;
+	return definer;
+}
+
+void mlx5_destroy_match_definer(struct mlx5_core_dev *dev,
+				struct mlx5_flow_definer *definer)
+{
+	struct mlx5_flow_root_namespace *root;
+
+	root = get_root_namespace(dev, definer->ns_type);
+	if (WARN_ON(!root))
+		return;
+
+	root->cmds->destroy_match_definer(root, definer->id);
+	kfree(definer);
+}
+
 int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
 				 struct mlx5_flow_root_namespace *peer_ns)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 79d37530afb3..7711db245c63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -49,6 +49,11 @@
 #define FDB_TC_MAX_PRIO 16
 #define FDB_TC_LEVELS_PER_PRIO 2
 
+struct mlx5_flow_definer {
+	enum mlx5_flow_namespace_type ns_type;
+	u32 id;
+};
+
 struct mlx5_modify_hdr {
 	enum mlx5_flow_namespace_type ns_type;
 	union {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
index 230e920e3845..2632d5ae9bc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c
@@ -625,6 +625,19 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n
 	mlx5dr_action_destroy(modify_hdr->action.dr_action);
 }
 
+static int
+mlx5_cmd_dr_destroy_match_definer(struct mlx5_flow_root_namespace *ns,
+				  int definer_id)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlx5_cmd_dr_create_match_definer(struct mlx5_flow_root_namespace *ns,
+					    u16 format_id, u32 *match_mask)
+{
+	return -EOPNOTSUPP;
+}
+
 static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
 				  struct mlx5_flow_table *ft,
 				  struct fs_fte *fte)
@@ -727,6 +740,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = {
 	.packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc,
 	.modify_header_alloc = mlx5_cmd_dr_modify_header_alloc,
 	.modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc,
+	.create_match_definer = mlx5_cmd_dr_create_match_definer,
+	.destroy_match_definer = mlx5_cmd_dr_destroy_match_definer,
 	.set_peer = mlx5_cmd_dr_set_peer,
 	.create_ns = mlx5_cmd_dr_create_ns,
 	.destroy_ns = mlx5_cmd_dr_destroy_ns,
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 259fcc168340..7a43fec63a35 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -98,6 +98,7 @@ enum {
 
 struct mlx5_pkt_reformat;
 struct mlx5_modify_hdr;
+struct mlx5_flow_definer;
 struct mlx5_flow_table;
 struct mlx5_flow_group;
 struct mlx5_flow_namespace;
@@ -258,6 +259,13 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 						 void *modify_actions);
 void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
 				struct mlx5_modify_hdr *modify_hdr);
+struct mlx5_flow_definer *
+mlx5_create_match_definer(struct mlx5_core_dev *dev,
+			  enum mlx5_flow_namespace_type ns_type, u16 format_id,
+			  u32 *match_mask);
+void mlx5_destroy_match_definer(struct mlx5_core_dev *dev,
+				struct mlx5_flow_definer *definer);
+int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer);
 
 struct mlx5_pkt_reformat_params {
 	int type;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index db1d9c69c1fa..8f41145bc6ef 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -94,6 +94,7 @@ enum {
 enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
+	MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
 	MLX5_OBJ_TYPE_PSV = 0xff03,
@@ -1731,7 +1732,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         flex_parser_id_outer_first_mpls_over_gre[0x4];
 	u8         flex_parser_id_outer_first_mpls_over_udp_label[0x4];
 
-	u8	   reserved_at_6e0[0x10];
+	u8         max_num_match_definer[0x10];
 	u8	   sf_base_id[0x10];
 
 	u8         flex_parser_id_gtpu_dw_2[0x4];
@@ -1746,7 +1747,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8	   reserved_at_760[0x20];
 	u8	   vhca_tunnel_commands[0x40];
-	u8	   reserved_at_7c0[0x40];
+	u8         match_definer_format_supported[0x40];
 };
 
 struct mlx5_ifc_cmd_hca_cap_2_bits {
@@ -5666,6 +5667,236 @@ struct mlx5_ifc_query_fte_in_bits {
 	u8         reserved_at_120[0xe0];
 };
 
+struct mlx5_ifc_match_definer_format_0_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         metadata_reg_c_0[0x20];
+
+	u8         metadata_reg_c_1[0x20];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_dmac_15_0[0x10];
+	u8         outer_ethertype[0x10];
+
+	u8         reserved_at_180[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         outer_ip_frag[0x1];
+	u8         outer_qp_type[0x2];
+	u8         outer_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         outer_l3_type[0x2];
+	u8         outer_l4_type[0x2];
+	u8         outer_first_vlan_type[0x2];
+	u8         outer_first_vlan_prio[0x3];
+	u8         outer_first_vlan_cfi[0x1];
+	u8         outer_first_vlan_vid[0xc];
+
+	u8         outer_l4_type_ext[0x4];
+	u8         reserved_at_1a4[0x2];
+	u8         outer_ipsec_layer[0x2];
+	u8         outer_l2_type[0x2];
+	u8         force_lb[0x1];
+	u8         outer_l2_ok[0x1];
+	u8         outer_l3_ok[0x1];
+	u8         outer_l4_ok[0x1];
+	u8         outer_second_vlan_type[0x2];
+	u8         outer_second_vlan_prio[0x3];
+	u8         outer_second_vlan_cfi[0x1];
+	u8         outer_second_vlan_vid[0xc];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         inner_ipv4_checksum_ok[0x1];
+	u8         inner_l4_checksum_ok[0x1];
+	u8         outer_ipv4_checksum_ok[0x1];
+	u8         outer_l4_checksum_ok[0x1];
+	u8         inner_l3_ok[0x1];
+	u8         inner_l4_ok[0x1];
+	u8         outer_l3_ok_duplicate[0x1];
+	u8         outer_l4_ok_duplicate[0x1];
+	u8         outer_tcp_cwr[0x1];
+	u8         outer_tcp_ece[0x1];
+	u8         outer_tcp_urg[0x1];
+	u8         outer_tcp_ack[0x1];
+	u8         outer_tcp_psh[0x1];
+	u8         outer_tcp_rst[0x1];
+	u8         outer_tcp_syn[0x1];
+	u8         outer_tcp_fin[0x1];
+};
+
+struct mlx5_ifc_match_definer_format_22_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         outer_ip_src_addr[0x20];
+
+	u8         outer_ip_dest_addr[0x20];
+
+	u8         outer_l4_sport[0x10];
+	u8         outer_l4_dport[0x10];
+
+	u8         reserved_at_160[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         outer_ip_frag[0x1];
+	u8         outer_qp_type[0x2];
+	u8         outer_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         outer_l3_type[0x2];
+	u8         outer_l4_type[0x2];
+	u8         outer_first_vlan_type[0x2];
+	u8         outer_first_vlan_prio[0x3];
+	u8         outer_first_vlan_cfi[0x1];
+	u8         outer_first_vlan_vid[0xc];
+
+	u8         metadata_reg_c_0[0x20];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         outer_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_23_bits {
+	u8         reserved_at_0[0x100];
+
+	u8         inner_ip_src_addr[0x20];
+
+	u8         inner_ip_dest_addr[0x20];
+
+	u8         inner_l4_sport[0x10];
+	u8         inner_l4_dport[0x10];
+
+	u8         reserved_at_160[0x1];
+	u8         sx_sniffer[0x1];
+	u8         functional_lb[0x1];
+	u8         inner_ip_frag[0x1];
+	u8         inner_qp_type[0x2];
+	u8         inner_encap_type[0x2];
+	u8         port_number[0x2];
+	u8         inner_l3_type[0x2];
+	u8         inner_l4_type[0x2];
+	u8         inner_first_vlan_type[0x2];
+	u8         inner_first_vlan_prio[0x3];
+	u8         inner_first_vlan_cfi[0x1];
+	u8         inner_first_vlan_vid[0xc];
+
+	u8         tunnel_header_0[0x20];
+
+	u8         inner_dmac_47_16[0x20];
+
+	u8         inner_smac_47_16[0x20];
+
+	u8         inner_smac_15_0[0x10];
+	u8         inner_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_29_bits {
+	u8         reserved_at_0[0xc0];
+
+	u8         outer_ip_dest_addr[0x80];
+
+	u8         outer_ip_src_addr[0x80];
+
+	u8         outer_l4_sport[0x10];
+	u8         outer_l4_dport[0x10];
+
+	u8         reserved_at_1e0[0x20];
+};
+
+struct mlx5_ifc_match_definer_format_30_bits {
+	u8         reserved_at_0[0xa0];
+
+	u8         outer_ip_dest_addr[0x80];
+
+	u8         outer_ip_src_addr[0x80];
+
+	u8         outer_dmac_47_16[0x20];
+
+	u8         outer_smac_47_16[0x20];
+
+	u8         outer_smac_15_0[0x10];
+	u8         outer_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_format_31_bits {
+	u8         reserved_at_0[0xc0];
+
+	u8         inner_ip_dest_addr[0x80];
+
+	u8         inner_ip_src_addr[0x80];
+
+	u8         inner_l4_sport[0x10];
+	u8         inner_l4_dport[0x10];
+
+	u8         reserved_at_1e0[0x20];
+};
+
+struct mlx5_ifc_match_definer_format_32_bits {
+	u8         reserved_at_0[0xa0];
+
+	u8         inner_ip_dest_addr[0x80];
+
+	u8         inner_ip_src_addr[0x80];
+
+	u8         inner_dmac_47_16[0x20];
+
+	u8         inner_smac_47_16[0x20];
+
+	u8         inner_smac_15_0[0x10];
+	u8         inner_dmac_15_0[0x10];
+};
+
+struct mlx5_ifc_match_definer_bits {
+	u8         modify_field_select[0x40];
+
+	u8         reserved_at_40[0x40];
+
+	u8         reserved_at_80[0x10];
+	u8         format_id[0x10];
+
+	u8         reserved_at_a0[0x160];
+
+	u8         match_mask[16][0x20];
+};
+
+struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         vhca_tunnel_id[0x10];
+	u8         obj_type[0x10];
+
+	u8         obj_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_general_obj_out_cmd_hdr_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         obj_id[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_create_match_definer_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr;
+
+	struct mlx5_ifc_match_definer_bits obj_context;
+};
+
+struct mlx5_ifc_create_match_definer_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+};
+
 enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS    = 0x0,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
@@ -8139,6 +8370,11 @@ struct mlx5_ifc_create_flow_group_out_bits {
 	u8         reserved_at_60[0x20];
 };
 
+enum {
+	MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_TCAM_SUBTABLE  = 0x0,
+	MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT     = 0x1,
+};
+
 enum {
 	MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS     = 0x0,
 	MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS   = 0x1,
@@ -8160,7 +8396,9 @@ struct mlx5_ifc_create_flow_group_in_bits {
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x4];
+	u8         group_type[0x4];
+	u8         reserved_at_90[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -8175,7 +8413,10 @@ struct mlx5_ifc_create_flow_group_in_bits {
 
 	u8         end_flow_index[0x20];
 
-	u8         reserved_at_140[0xa0];
+	u8         reserved_at_140[0x10];
+	u8         match_definer_id[0x10];
+
+	u8         reserved_at_160[0x80];
 
 	u8         reserved_at_1e0[0x18];
 	u8         match_criteria_enable[0x8];
@@ -10671,29 +10912,6 @@ struct mlx5_ifc_dealloc_memic_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
-struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
-	u8         opcode[0x10];
-	u8         uid[0x10];
-
-	u8         vhca_tunnel_id[0x10];
-	u8         obj_type[0x10];
-
-	u8         obj_id[0x20];
-
-	u8         reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_general_obj_out_cmd_hdr_bits {
-	u8         status[0x8];
-	u8         reserved_at_8[0x18];
-
-	u8         syndrome[0x20];
-
-	u8         obj_id[0x20];
-
-	u8         reserved_at_60[0x20];
-};
-
 struct mlx5_ifc_umem_bits {
 	u8         reserved_at_0[0x80];
 
-- 
cgit v1.2.3


From 58a606dba708f114e7f412b5c3024027e8a73e34 Mon Sep 17 00:00:00 2001
From: Maor Gottlieb <maorg@nvidia.com>
Date: Tue, 3 Aug 2021 10:04:41 +0300
Subject: net/mlx5: Introduce new uplink destination type

The uplink destination type should be used in rules to steer the
packet to the uplink when the device is in steering based LAG mode.

Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c             | 8 +++++++-
 include/linux/mlx5/mlx5_ifc.h                                | 1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 87d65f6b5310..7841ef6c193c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -235,6 +235,9 @@ const char *parse_fs_dst(struct trace_seq *p,
 	const char *ret = trace_seq_buffer_ptr(p);
 
 	switch (dst->type) {
+	case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
+		trace_seq_printf(p, "uplink\n");
+		break;
 	case MLX5_FLOW_DESTINATION_TYPE_VPORT:
 		trace_seq_printf(p, "vport=%u\n", dst->vport.num);
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 2c82dc118460..750b21124a1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -577,8 +577,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
 				id = dst->dest_attr.ft->id;
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_UPLINK:
 			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
-				id = dst->dest_attr.vport.num;
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id_valid,
 					 !!(dst->dest_attr.vport.flags &
@@ -586,6 +586,12 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
+				if (type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) {
+					/* destination_id is reserved */
+					id = 0;
+					break;
+				}
+				id = dst->dest_attr.vport.num;
 				if (extended_dest &&
 				    dst->dest_attr.vport.pkt_reformat) {
 					MLX5_SET(dest_format_struct, in_dests,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 8f41145bc6ef..09e43019d877 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1766,6 +1766,7 @@ enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE   = 0x1,
 	MLX5_FLOW_DESTINATION_TYPE_TIR          = 0x2,
 	MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6,
+	MLX5_FLOW_DESTINATION_TYPE_UPLINK       = 0x8,
 
 	MLX5_FLOW_DESTINATION_TYPE_PORT         = 0x99,
 	MLX5_FLOW_DESTINATION_TYPE_COUNTER      = 0x100,
-- 
cgit v1.2.3


From cf6a8b1b24d675afc35a01cccd081160014a0125 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Tue, 12 Oct 2021 13:26:30 +0300
Subject: RDMA/mlx5: Remove iova from struct mlx5_core_mkey

iova is already stored in ibmr->iova, no need to store it here.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c            |  1 -
 drivers/infiniband/hw/mlx5/mr.c              | 16 ++++++++--------
 drivers/infiniband/hw/mlx5/odp.c             |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/mr.c |  1 -
 drivers/vdpa/mlx5/core/resources.c           |  1 -
 include/linux/mlx5/driver.h                  |  1 -
 6 files changed, 12 insertions(+), 16 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index e95967aefe78..00ad24044c3a 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 	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);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3be36ebbf67a..6815500cfdaa 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -911,12 +911,13 @@ 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 +975,10 @@ 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;
 }
@@ -1088,7 +1088,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr,
 	wr->pd = mr->ibmr.pd;
 	wr->mkey = mr->mmkey.key;
 	wr->length = mr->mmkey.size;
-	wr->virt_addr = mr->mmkey.iova;
+	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 +1341,7 @@ 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 +1388,7 @@ 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;
 
@@ -1763,7 +1763,7 @@ 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->ibmr.iova = iova;
 	mr->mmkey.size = new_umem->length;
 	mr->page_shift = order_base_2(page_size);
 	mr->umem = new_umem;
@@ -1834,7 +1834,7 @@ 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);
 	}
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index d0d98e584ebc..d119ba3101a3 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) ||
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 174f71ed5280..d239d559994f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -52,7 +52,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 
 	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);
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index 15e266d0e27a..14d4314cdc29 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -215,7 +215,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk
 
 	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);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e23417424373..669904f9986e 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -364,7 +364,6 @@ enum {
 };
 
 struct mlx5_core_mkey {
-	u64			iova;
 	u64			size;
 	u32			key;
 	u32			pd;
-- 
cgit v1.2.3


From 062fd731e51ee29ba745b2fd1c7ac87dd460d4ca Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Tue, 12 Oct 2021 13:26:31 +0300
Subject: RDMA/mlx5: Remove size from struct mlx5_core_mkey

mkey->size is already stored in ibmr->length, no need to store it here.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c            | 1 -
 drivers/infiniband/hw/mlx5/mr.c              | 5 ++---
 drivers/net/ethernet/mellanox/mlx5/core/mr.c | 1 -
 drivers/vdpa/mlx5/core/resources.c           | 1 -
 include/linux/mlx5/driver.h                  | 1 -
 5 files changed, 2 insertions(+), 7 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 00ad24044c3a..8f6e1350cd37 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 	mkey->key = mlx5_idx_to_mkey(
 			MLX5_GET(create_mkey_out, out, mkey_index)) | key;
 	mkey->type = MLX5_MKEY_INDIRECT_DEVX;
-	mkey->size = MLX5_GET64(mkc, mkc, len);
 	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size);
 	init_waitqueue_head(&mkey->wait);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 6815500cfdaa..1b1367c87a6b 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -975,7 +975,6 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 
 	mr->ibmr.pd = pd;
 	mr->umem = umem;
-	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, iova);
@@ -1087,7 +1086,7 @@ 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->length = mr->ibmr.length;
 	wr->virt_addr = mr->ibmr.iova;
 	wr->access_flags = mr->access_flags;
 	wr->page_shift = mr->page_shift;
@@ -1764,7 +1763,7 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd,
 
 	mr->ibmr.length = new_umem->length;
 	mr->ibmr.iova = iova;
-	mr->mmkey.size = new_umem->length;
+	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);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index d239d559994f..b5dd44944265 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -52,7 +52,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	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);
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index 14d4314cdc29..d3d8b8b4e377 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -215,7 +215,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk
 
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	mkey->size = MLX5_GET64(mkc, mkc, len);
 	mkey->key |= mlx5_idx_to_mkey(mkey_index);
 	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	return 0;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 669904f9986e..ff1e991314e2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -364,7 +364,6 @@ enum {
 };
 
 struct mlx5_core_mkey {
-	u64			size;
 	u32			key;
 	u32			pd;
 	u32			type;
-- 
cgit v1.2.3


From c64674168b6a2f293e92caf33c917ccf10886801 Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Tue, 12 Oct 2021 13:26:32 +0300
Subject: RDMA/mlx5: Remove pd from struct mlx5_core_mkey

There is no read of mkey->pd, only write. Remove it.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c            | 1 -
 drivers/infiniband/hw/mlx5/mr.c              | 3 ---
 drivers/net/ethernet/mellanox/mlx5/core/mr.c | 3 ---
 drivers/vdpa/mlx5/core/resources.c           | 3 ---
 include/linux/mlx5/driver.h                  | 1 -
 5 files changed, 11 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 8f6e1350cd37..5322d787c094 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 	mkey->key = mlx5_idx_to_mkey(
 			MLX5_GET(create_mkey_out, out, mkey_index)) | key;
 	mkey->type = MLX5_MKEY_INDIRECT_DEVX;
-	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size);
 	init_waitqueue_head(&mkey->wait);
 
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 1b1367c87a6b..9d7f1cadaa76 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -975,7 +975,6 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 
 	mr->ibmr.pd = pd;
 	mr->umem = umem;
-	mr->mmkey.pd = to_mpd(pd)->pdn;
 	mr->page_shift = order_base_2(page_size);
 	set_mr_fields(dev, mr, umem->length, access_flags, iova);
 
@@ -1708,7 +1707,6 @@ 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;
 }
 
@@ -1753,7 +1751,6 @@ 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) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index b5dd44944265..6e99fd166f98 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -41,7 +41,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 {
 	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);
@@ -50,10 +49,8 @@ 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->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);
 
 	mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key);
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index d3d8b8b4e377..72b2d80e75b0 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -203,7 +203,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk
 {
 	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);
@@ -213,10 +212,8 @@ 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->key |= mlx5_idx_to_mkey(mkey_index);
-	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	return 0;
 }
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index ff1e991314e2..f0ce7d4dc4ff 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -365,7 +365,6 @@ enum {
 
 struct mlx5_core_mkey {
 	u32			key;
-	u32			pd;
 	u32			type;
 	struct wait_queue_head wait;
 	refcount_t usecount;
-- 
cgit v1.2.3


From 83fec3f12a5904b62330fd1a89af6d892afc387e Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Tue, 12 Oct 2021 13:26:33 +0300
Subject: RDMA/mlx5: Replace struct mlx5_core_mkey by u32 key

In mlx5_core and vdpa there is no use of mlx5_core_mkey members except
for the key itself.

As preparation for moving mlx5_core_mkey to mlx5_ib, the occurrences of
struct mlx5_core_mkey in all modules except for mlx5_ib are replaced by
a u32 key.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/mr.c                    | 21 ++++++++++++++-------
 drivers/infiniband/hw/mlx5/odp.c                   |  2 +-
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   |  6 +++---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  2 +-
 .../ethernet/mellanox/mlx5/core/diag/rsc_dump.c    | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/trap.c  |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_common.c    |  6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 13 ++++++-------
 .../net/ethernet/mellanox/mlx5/core/fpga/conn.c    | 10 +++++-----
 .../net/ethernet/mellanox/mlx5/core/fpga/core.h    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/mr.c       | 22 ++++++++++------------
 .../mellanox/mlx5/core/steering/dr_icm_pool.c      | 10 +++++-----
 .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 11 +++++------
 .../mellanox/mlx5/core/steering/dr_types.h         |  2 +-
 drivers/vdpa/mlx5/core/mlx5_vdpa.h                 |  8 ++++----
 drivers/vdpa/mlx5/core/mr.c                        |  8 ++++----
 drivers/vdpa/mlx5/core/resources.c                 |  8 ++++----
 drivers/vdpa/mlx5/net/mlx5_vnet.c                  |  2 +-
 include/linux/mlx5/driver.h                        | 14 ++++++--------
 21 files changed, 82 insertions(+), 81 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 9d7f1cadaa76..e2f020472ae2 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -104,8 +104,14 @@ static int
 mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_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
@@ -133,7 +139,7 @@ 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 +266,11 @@ 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 +297,7 @@ 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 +665,7 @@ 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) {
@@ -2326,7 +2333,7 @@ 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;
@@ -2345,7 +2352,7 @@ 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,
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index d119ba3101a3..a654367af056 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -909,7 +909,7 @@ 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;
 
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 f9cf9fb31547..02db3148240a 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 03a7a4ce5cd5..7761daa25f63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -665,7 +665,7 @@ 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 09c8b71b186c..63076d0e8b63 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -234,8 +234,7 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 }
 
 static int mlx5e_create_umr_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;
@@ -455,7 +454,7 @@ 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)
@@ -487,7 +486,7 @@ 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) {
@@ -574,7 +573,7 @@ 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;
@@ -607,7 +606,7 @@ 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);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -1991,7 +1990,7 @@ 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/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/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 6e99fd166f98..f099a087400e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -35,9 +35,8 @@
 #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;
@@ -50,33 +49,32 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 		return err;
 
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index);
-	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 b20e8aabb861..6c67185c05c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -1275,7 +1275,7 @@ 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/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 72b2d80e75b0..9800f9bec225 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -198,7 +198,7 @@ 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)] = {};
@@ -213,17 +213,17 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk
 		return err;
 
 	mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index);
-	mkey->key |= mlx5_idx_to_mkey(mkey_index);
+	*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/driver.h b/include/linux/mlx5/driver.h
index f0ce7d4dc4ff..bd99f713720b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -650,7 +650,7 @@ 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;
@@ -1021,13 +1021,11 @@ 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);
-- 
cgit v1.2.3


From 4123bfb0b28b77b944360be8c758b1a0974e96ad Mon Sep 17 00:00:00 2001
From: Aharon Landau <aharonl@nvidia.com>
Date: Tue, 12 Oct 2021 13:26:34 +0300
Subject: RDMA/mlx5: Move struct mlx5_core_mkey to mlx5_ib

Move mlx5_core_mkey struct to mlx5_ib, as the mlx5_core doesn't use it
at this point.

Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/devx.c    |  2 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h | 25 +++++++++++++++++++------
 drivers/infiniband/hw/mlx5/mr.c      | 12 +++++-------
 drivers/infiniband/hw/mlx5/odp.c     |  8 ++++----
 include/linux/mlx5/driver.h          | 13 -------------
 5 files changed, 29 insertions(+), 31 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 5322d787c094..d07a21a13ac0 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1293,7 +1293,7 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 				     void *in, void *out)
 {
 	struct mlx5_ib_devx_mr *devx_mr = &obj->devx_mr;
-	struct mlx5_core_mkey *mkey;
+	struct mlx5_ib_mkey *mkey;
 	void *mkc;
 	u8 key;
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bf20a388eabe..8f754c52d469 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -619,6 +619,19 @@ 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;
+	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 +650,7 @@ 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;
@@ -713,12 +726,12 @@ static inline bool is_dmabuf_mr(struct mlx5_ib_mr *mr)
 
 struct mlx5_ib_mw {
 	struct ib_mw		ibmw;
-	struct mlx5_core_mkey	mmkey;
+	struct mlx5_ib_mkey	mmkey;
 	int			ndescs;
 };
 
 struct mlx5_ib_devx_mr {
-	struct mlx5_core_mkey	mmkey;
+	struct mlx5_ib_mkey	mmkey;
 	int			ndescs;
 };
 
@@ -1579,7 +1592,7 @@ 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 +1601,14 @@ 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 e2f020472ae2..5afc3e965c28 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;
@@ -100,9 +99,8 @@ 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;
 
@@ -116,7 +114,7 @@ mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey,
 
 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)
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index a654367af056..7ab0a9b752f6 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -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;
@@ -797,7 +797,7 @@ 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)
+static int get_indirect_num_descs(struct mlx5_ib_mkey *mmkey)
 {
 	struct mlx5_ib_mw *mw;
 	struct mlx5_ib_devx_mr *devx_mr;
@@ -831,7 +831,7 @@ 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;
@@ -1703,8 +1703,8 @@ 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/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index bd99f713720b..70b6aff4940a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -357,19 +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 {
-	u32			key;
-	u32			type;
-	struct wait_queue_head wait;
-	refcount_t usecount;
-};
-
 #define MLX5_24BIT_MASK		((1 << 24) - 1)
 
 enum mlx5_res_type {
-- 
cgit v1.2.3


From cb464ba53c0cb497dcb4a3daaf4fad4b75291863 Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Mon, 11 Oct 2021 13:14:28 +0300
Subject: net/mlx5: Extend health buffer dump

Enhance health buffer to include:
 - assert_var5: expose the 6'th assert variable.
 - time: error's time-stamp in seconds (epoch time).
 - rfr: Recovery Flow Requiered. When set, indicates that the error
        cannot be recovered without flow involving reset.
 - severity: error's severity value, ranging from emergency to debug.
Expose them in the health buffer dump (dmesg and devlink fw reporter).

Health buffer in dmesg:
mlx5_core 0000:08:00.0: print_health_info:425:(pid 912): Health issue observed, firmware internal error, severity(3) ERROR:
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[0] 0x08040700
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[1] 0x00000000
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[2] 0x00000000
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[3] 0x00000000
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[4] 0x00000000
mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[5] 0x00000000
mlx5_core 0000:08:00.0: print_health_info:432:(pid 912): assert_exit_ptr 0x00aaf800
mlx5_core 0000:08:00.0: print_health_info:434:(pid 912): assert_callra 0x00aaf70c
mlx5_core 0000:08:00.0: print_health_info:436:(pid 912): fw_ver 16.32.492
mlx5_core 0000:08:00.0: print_health_info:437:(pid 912): time 1634819758
mlx5_core 0000:08:00.0: print_health_info:438:(pid 912): hw_id 0x0000020d
mlx5_core 0000:08:00.0: print_health_info:439:(pid 912): rfr 0
mlx5_core 0000:08:00.0: print_health_info:440:(pid 912): severity 3 (ERROR)
mlx5_core 0000:08:00.0: print_health_info:441:(pid 912): irisc_index 9
mlx5_core 0000:08:00.0: print_health_info:442:(pid 912): synd 0x1: firmware internal error
mlx5_core 0000:08:00.0: print_health_info:444:(pid 912): ext_synd 0x802b
mlx5_core 0000:08:00.0: print_health_info:445:(pid 912): raw fw_ver 0x102001ec

Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 73 +++++++++++++++++++++---
 include/linux/mlx5/device.h                      | 14 +++--
 include/linux/mlx5/mlx5_ifc.h                    | 10 +++-
 3 files changed, 82 insertions(+), 15 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 6a4dd7f78958..538ef392f54c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -36,6 +36,7 @@
 #include <linux/vmalloc.h>
 #include <linux/hardirq.h>
 #include <linux/mlx5/driver.h>
+#include <linux/kern_levels.h>
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/mlx5.h"
@@ -74,6 +75,11 @@ enum  {
 	MLX5_SENSOR_FW_SYND_RFR		= 5,
 };
 
+enum {
+	MLX5_SEVERITY_MASK		= 0x7,
+	MLX5_SEVERITY_VALID_MASK	= 0x8,
+};
+
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev)
 {
 	return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7;
@@ -98,12 +104,19 @@ static bool sensor_pci_not_working(struct mlx5_core_dev *dev)
 	return (ioread32be(&h->fw_ver) == 0xffffffff);
 }
 
+static int mlx5_health_get_rfr(u8 rfr_severity)
+{
+	return rfr_severity >> MLX5_RFR_BIT_OFFSET;
+}
+
 static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
-	u32 rfr = ioread32be(&h->rfr) >> MLX5_RFR_OFFSET;
 	u8 synd = ioread8(&h->synd);
+	u8 rfr;
+
+	rfr = mlx5_health_get_rfr(ioread8(&h->rfr_severity));
 
 	if (rfr && synd)
 		mlx5_core_dbg(dev, "FW requests reset, synd: %d\n", synd);
@@ -366,18 +379,52 @@ static const char *hsynd_str(u8 synd)
 	}
 }
 
+static const char *mlx5_loglevel_str(int level)
+{
+	switch (level) {
+	case LOGLEVEL_EMERG:
+		return "EMERGENCY";
+	case LOGLEVEL_ALERT:
+		return "ALERT";
+	case LOGLEVEL_CRIT:
+		return "CRITICAL";
+	case LOGLEVEL_ERR:
+		return "ERROR";
+	case LOGLEVEL_WARNING:
+		return "WARNING";
+	case LOGLEVEL_NOTICE:
+		return "NOTICE";
+	case LOGLEVEL_INFO:
+		return "INFO";
+	case LOGLEVEL_DEBUG:
+		return "DEBUG";
+	}
+	return "Unknown log level";
+}
+
+static int mlx5_health_get_severity(u8 rfr_severity)
+{
+	return rfr_severity & MLX5_SEVERITY_VALID_MASK ?
+	       rfr_severity & MLX5_SEVERITY_MASK : LOGLEVEL_ERR;
+}
+
 static void print_health_info(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
-	char fw_str[18];
-	u32 fw;
+	u8 rfr_severity;
+	int severity;
 	int i;
 
 	/* If the syndrome is 0, the device is OK and no need to print buffer */
 	if (!ioread8(&h->synd))
 		return;
 
+	rfr_severity = ioread8(&h->rfr_severity);
+	severity  = mlx5_health_get_severity(rfr_severity);
+	mlx5_core_err(dev, "Health issue observed, %s, severity(%d) %s:\n",
+		      hsynd_str(ioread8(&h->synd)), severity, mlx5_loglevel_str(severity));
+
 	for (i = 0; i < ARRAY_SIZE(h->assert_var); i++)
 		mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i,
 			      ioread32be(h->assert_var + i));
@@ -386,15 +433,16 @@ static void print_health_info(struct mlx5_core_dev *dev)
 		      ioread32be(&h->assert_exit_ptr));
 	mlx5_core_err(dev, "assert_callra 0x%08x\n",
 		      ioread32be(&h->assert_callra));
-	sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
-	mlx5_core_err(dev, "fw_ver %s\n", fw_str);
+	mlx5_core_err(dev, "fw_ver %d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev));
+	mlx5_core_err(dev, "time %u\n", ioread32be(&h->time));
 	mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
+	mlx5_core_err(dev, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
+	mlx5_core_err(dev, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
 	mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index));
 	mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd),
 		      hsynd_str(ioread8(&h->synd)));
 	mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
-	fw = ioread32be(&h->fw_ver);
-	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw);
+	mlx5_core_err(dev, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
 }
 
 static int
@@ -443,6 +491,7 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 	struct health_buffer __iomem *h = health->health;
+	u8 rfr_severity;
 	int err;
 	int i;
 
@@ -473,9 +522,19 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
 		return err;
 	err = devlink_fmsg_u32_pair_put(fmsg, "assert_callra",
 					ioread32be(&h->assert_callra));
+	if (err)
+		return err;
+	err = devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time));
 	if (err)
 		return err;
 	err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id));
+	if (err)
+		return err;
+	rfr_severity = ioread8(&h->rfr_severity);
+	err = devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity));
+	if (err)
+		return err;
+	err = devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity));
 	if (err)
 		return err;
 	err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index",
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 347167c18802..f8a0bbb42c3b 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -541,19 +541,21 @@ struct mlx5_cmd_layout {
 	u8		status_own;
 };
 
-enum mlx5_fatal_assert_bit_offsets {
-	MLX5_RFR_OFFSET = 31,
+enum mlx5_rfr_severity_bit_offsets {
+	MLX5_RFR_BIT_OFFSET = 0x7,
 };
 
 struct health_buffer {
-	__be32		assert_var[5];
-	__be32		rsvd0[3];
+	__be32		assert_var[6];
+	__be32		rsvd0[2];
 	__be32		assert_exit_ptr;
 	__be32		assert_callra;
-	__be32		rsvd1[2];
+	__be32		rsvd1[1];
+	__be32		time;
 	__be32		fw_ver;
 	__be32		hw_id;
-	__be32		rfr;
+	u8		rfr_severity;
+	u8		rsvd2[3];
 	u8		irisc_index;
 	u8		synd;
 	__be16		ext_synd;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 09e43019d877..6d292b5b8992 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -4149,13 +4149,19 @@ struct mlx5_ifc_health_buffer_bits {
 
 	u8         assert_callra[0x20];
 
-	u8         reserved_at_140[0x40];
+	u8         reserved_at_140[0x20];
+
+	u8         time[0x20];
 
 	u8         fw_version[0x20];
 
 	u8         hw_id[0x20];
 
-	u8         reserved_at_1c0[0x20];
+	u8         rfr[0x1];
+	u8         reserved_at_1c1[0x3];
+	u8         valid[0x1];
+	u8         severity[0x3];
+	u8         reserved_at_1c8[0x18];
 
 	u8         irisc_index[0x8];
 	u8         synd[0x8];
-- 
cgit v1.2.3


From 5a1023deeed02a2078bcc11eec1c4be31e85892d Mon Sep 17 00:00:00 2001
From: Aya Levin <ayal@nvidia.com>
Date: Wed, 13 Oct 2021 09:45:22 +0300
Subject: net/mlx5: Add periodic update of host time to firmware

Firmware logs its asserts also to non-volatile memory. In order to
reduce drift between the NIC and the host, the driver sets the host
epoch-time to the firmware every hour.

Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 30 ++++++++++++++++++++++++
 include/linux/mlx5/driver.h                      |  2 ++
 include/linux/mlx5/mlx5_ifc.h                    | 12 ++++++++++
 3 files changed, 44 insertions(+)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index c35a27255232..64f1abc4dc36 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -752,6 +752,31 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev)
 	spin_unlock_irqrestore(&health->wq_lock, flags);
 }
 
+#define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60)
+static void mlx5_health_log_ts_update(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	u32 out[MLX5_ST_SZ_DW(mrtc_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtc_reg)] = {};
+	struct mlx5_core_health *health;
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+	u64 now_us;
+
+	health = container_of(dwork, struct mlx5_core_health, update_fw_log_ts_work);
+	priv = container_of(health, struct mlx5_priv, health);
+	dev = container_of(priv, struct mlx5_core_dev, priv);
+
+	now_us =  ktime_to_us(ktime_get_real());
+
+	MLX5_SET(mrtc_reg, in, time_h, now_us >> 32);
+	MLX5_SET(mrtc_reg, in, time_l, now_us & 0xFFFFFFFF);
+	mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MRTC, 0, 1);
+
+	queue_delayed_work(health->wq, &health->update_fw_log_ts_work,
+			   msecs_to_jiffies(MLX5_MSEC_PER_HOUR));
+}
+
 static void poll_health(struct timer_list *t)
 {
 	struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer);
@@ -834,6 +859,7 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev)
 	spin_lock_irqsave(&health->wq_lock, flags);
 	set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags);
 	spin_unlock_irqrestore(&health->wq_lock, flags);
+	cancel_delayed_work_sync(&health->update_fw_log_ts_work);
 	cancel_work_sync(&health->report_work);
 	cancel_work_sync(&health->fatal_report_work);
 }
@@ -849,6 +875,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
 
+	cancel_delayed_work_sync(&health->update_fw_log_ts_work);
 	destroy_workqueue(health->wq);
 	mlx5_fw_reporters_destroy(dev);
 }
@@ -874,6 +901,9 @@ int mlx5_health_init(struct mlx5_core_dev *dev)
 	spin_lock_init(&health->wq_lock);
 	INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work);
 	INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work);
+	INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update);
+	if (mlx5_core_is_pf(dev))
+		queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0);
 
 	return 0;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 3f4c0f2314a5..f617dfbcd9fd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -134,6 +134,7 @@ enum {
 	MLX5_REG_MCIA		 = 0x9014,
 	MLX5_REG_MFRL		 = 0x9028,
 	MLX5_REG_MLCR		 = 0x902b,
+	MLX5_REG_MRTC		 = 0x902d,
 	MLX5_REG_MTRC_CAP	 = 0x9040,
 	MLX5_REG_MTRC_CONF	 = 0x9041,
 	MLX5_REG_MTRC_STDB	 = 0x9042,
@@ -440,6 +441,7 @@ struct mlx5_core_health {
 	struct work_struct		report_work;
 	struct devlink_health_reporter *fw_reporter;
 	struct devlink_health_reporter *fw_fatal_reporter;
+	struct delayed_work		update_fw_log_ts_work;
 };
 
 struct mlx5_qp_table {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 6d292b5b8992..746381eccccf 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10358,6 +10358,17 @@ struct mlx5_ifc_pddr_reg_bits {
 	union mlx5_ifc_pddr_reg_page_data_auto_bits page_data;
 };
 
+struct mlx5_ifc_mrtc_reg_bits {
+	u8         time_synced[0x1];
+	u8         reserved_at_1[0x1f];
+
+	u8         reserved_at_20[0x20];
+
+	u8         time_h[0x20];
+
+	u8         time_l[0x20];
+};
+
 union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_bufferx_reg_bits bufferx_reg;
 	struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout;
@@ -10419,6 +10430,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_mirc_reg_bits mirc_reg;
 	struct mlx5_ifc_mfrl_reg_bits mfrl_reg;
 	struct mlx5_ifc_mtutc_reg_bits mtutc_reg;
+	struct mlx5_ifc_mrtc_reg_bits mrtc_reg;
 	u8         reserved_at_0[0x60e0];
 };
 
-- 
cgit v1.2.3


From 46ae40b94d8826591472798114a723cc7feac7a7 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Thu, 12 Aug 2021 11:53:34 +0300
Subject: net/mlx5: Let user configure io_eq_size param

Currently, each I/O EQ is taking 128KB of memory. This size
is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the size of I/O EQs.

For example, to reduce I/O EQ size to 64, execute:
$ devlink resource set pci/0000:00:0b.0 path /io_eq_size/ size 64
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst          | 12 +++++
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/devlink.h  | 11 +++++
 .../net/ethernet/mellanox/mlx5/core/devlink_res.c  | 56 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  3 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |  3 ++
 include/linux/mlx5/driver.h                        |  4 --
 7 files changed, 85 insertions(+), 6 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c

(limited to 'include/linux/mlx5')

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 4e4b97f7971a..4e6020570292 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -46,6 +46,18 @@ parameters.
 
 The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
 
+Resources
+=========
+
+.. list-table:: Driver-specific resources implemented
+   :widths: 5 5 5 85
+
+   * - Name
+     - Description
+   * - ``comp_eq_size``
+     - Control the size of I/O completion EQs.
+       * The default value is 1024, and the range is between 64 and 4096.
+
 Info versions
 =============
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index bdb271b604d9..79c15ee62cde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -16,7 +16,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
-		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
+		diag/fw_tracer.o diag/crdump.o devlink.o devlink_res.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 30bf4882779b..4192f23b1446 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -6,6 +6,13 @@
 
 #include <net/devlink.h>
 
+enum mlx5_devlink_resource_id {
+	MLX5_DL_RES_COMP_EQ = 1,
+
+	__MLX5_ID_RES_MAX,
+	MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1,
+};
+
 enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
@@ -31,6 +38,10 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev);
 int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id,
 				  enum devlink_trap_action *action);
 
+void mlx5_devlink_res_register(struct mlx5_core_dev *dev);
+void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev);
+size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id);
+
 struct devlink *mlx5_devlink_alloc(struct device *dev);
 void mlx5_devlink_free(struct devlink *devlink);
 int mlx5_devlink_register(struct devlink *devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
new file mode 100644
index 000000000000..3beedfb8534a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */
+
+#include "devlink.h"
+#include "mlx5_core.h"
+
+enum {
+	MLX5_EQ_MIN_SIZE = 64,
+	MLX5_EQ_MAX_SIZE = 4096,
+	MLX5_COMP_EQ_SIZE = 1024,
+};
+
+static int comp_eq_res_register(struct mlx5_core_dev *dev)
+{
+	struct devlink_resource_size_params comp_eq_size;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	devlink_resource_size_params_init(&comp_eq_size, MLX5_EQ_MIN_SIZE,
+					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
+	return devlink_resource_register(devlink, "io_eq_size", MLX5_COMP_EQ_SIZE,
+					 MLX5_DL_RES_COMP_EQ,
+					 DEVLINK_RESOURCE_ID_PARENT_TOP,
+					 &comp_eq_size);
+}
+
+void mlx5_devlink_res_register(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = comp_eq_res_register(dev);
+	if (err)
+		mlx5_core_err(dev, "Failed to register resources, err = %d\n", err);
+}
+
+void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev)
+{
+	devlink_resources_unregister(priv_to_devlink(dev), NULL);
+}
+
+static const size_t default_vals[MLX5_ID_RES_MAX + 1] = {
+	[MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE,
+};
+
+size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	u64 size;
+	int err;
+
+	err = devlink_resource_size_get(devlink, id, &size);
+	if (!err)
+		return size;
+	mlx5_core_err(dev, "Failed to get param. using default. err = %d, id = %u\n",
+		      err, id);
+	return default_vals[id];
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 792e0d6aa861..4dda6e2a4cbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -19,6 +19,7 @@
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
 #include "mlx5_irq.h"
+#include "devlink.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -807,7 +808,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	ncomp_eqs = table->num_comp_eqs;
-	nent = MLX5_COMP_EQ_SIZE;
+	nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_COMP_EQ);
 	for (i = 0; i < ncomp_eqs; i++) {
 		struct mlx5_eq_param param = {};
 		int vecidx = i;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f8446395163a..96fdbc0c87bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -922,6 +922,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
 
+	mlx5_devlink_res_register(dev);
+
 	return 0;
 
 err_sf_table_cleanup:
@@ -957,6 +959,7 @@ err_devcom:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_devlink_res_unregister(dev);
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index f617dfbcd9fd..47c07f95bbe1 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -797,10 +797,6 @@ struct mlx5_db {
 	int			index;
 };
 
-enum {
-	MLX5_COMP_EQ_SIZE = 1024,
-};
-
 enum {
 	MLX5_PTYS_IB = 1 << 0,
 	MLX5_PTYS_EN = 1 << 2,
-- 
cgit v1.2.3


From a6cb08daa3b459e3dab1d98c67cb8c931f4d81a5 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 13 Oct 2021 09:57:54 +0300
Subject: net/mlx5: Let user configure event_eq_size param

Event EQ is an EQ which received the notification of almost all the
events generated by the NIC.
Currently, each event EQ is taking 512KB of memory. This size is not
needed in most use cases, and is critical with large scale. Hence,
allow user to configure the size of the event EQ.

For example to reduce event EQ size to 64, execute::
$ devlink resource set pci/0000:00:0b.0 path /event_eq_size/ size 64
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst          |  4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/devlink.h  |  1 +
 .../net/ethernet/mellanox/mlx5/core/devlink_res.c  | 26 +++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  2 +-
 include/linux/mlx5/eq.h                            |  1 -
 5 files changed, 31 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 4e6020570292..5b77863f9c88 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -57,6 +57,10 @@ Resources
    * - ``comp_eq_size``
      - Control the size of I/O completion EQs.
        * The default value is 1024, and the range is between 64 and 4096.
+   * - ``event_eq_size``
+     - Control the size of the asynchronous control events EQ.
+       * The default value is 4096, and the range is between 64 and 4096.
+
 
 Info versions
 =============
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 4192f23b1446..674415fd0b3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -8,6 +8,7 @@
 
 enum mlx5_devlink_resource_id {
 	MLX5_DL_RES_COMP_EQ = 1,
+	MLX5_DL_RES_ASYNC_EQ,
 
 	__MLX5_ID_RES_MAX,
 	MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
index 3beedfb8534a..549d23745942 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
@@ -7,6 +7,7 @@
 enum {
 	MLX5_EQ_MIN_SIZE = 64,
 	MLX5_EQ_MAX_SIZE = 4096,
+	MLX5_NUM_ASYNC_EQE = 4096,
 	MLX5_COMP_EQ_SIZE = 1024,
 };
 
@@ -23,13 +24,35 @@ static int comp_eq_res_register(struct mlx5_core_dev *dev)
 					 &comp_eq_size);
 }
 
+static int async_eq_resource_register(struct mlx5_core_dev *dev)
+{
+	struct devlink_resource_size_params async_eq_size;
+	struct devlink *devlink = priv_to_devlink(dev);
+
+	devlink_resource_size_params_init(&async_eq_size, MLX5_EQ_MIN_SIZE,
+					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
+	return devlink_resource_register(devlink, "event_eq_size",
+					 MLX5_NUM_ASYNC_EQE, MLX5_DL_RES_ASYNC_EQ,
+					 DEVLINK_RESOURCE_ID_PARENT_TOP,
+					 &async_eq_size);
+}
+
 void mlx5_devlink_res_register(struct mlx5_core_dev *dev)
 {
 	int err;
 
 	err = comp_eq_res_register(dev);
 	if (err)
-		mlx5_core_err(dev, "Failed to register resources, err = %d\n", err);
+		goto err_msg;
+
+	err = async_eq_resource_register(dev);
+	if (err)
+		goto err;
+	return;
+err:
+	devlink_resources_unregister(priv_to_devlink(dev), NULL);
+err_msg:
+	mlx5_core_err(dev, "Failed to register resources, err = %d\n", err);
 }
 
 void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev)
@@ -39,6 +62,7 @@ void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev)
 
 static const size_t default_vals[MLX5_ID_RES_MAX + 1] = {
 	[MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE,
+	[MLX5_DL_RES_ASYNC_EQ] = MLX5_NUM_ASYNC_EQE,
 };
 
 size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 4dda6e2a4cbc..31e69067284b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -647,7 +647,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = MLX5_IRQ_EQ_CTRL,
-		.nent = MLX5_NUM_ASYNC_EQE,
+		.nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_ASYNC_EQ),
 	};
 
 	gather_async_events_mask(dev, param.mask);
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index ea3ff5a8ced3..11161e427608 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -5,7 +5,6 @@
 #define MLX5_CORE_EQ_H
 
 #define MLX5_NUM_CMD_EQE   (32)
-#define MLX5_NUM_ASYNC_EQE (0x1000)
 #define MLX5_NUM_SPARE_EQE (0x80)
 
 struct mlx5_eq;
-- 
cgit v1.2.3


From 554604061979d656bbbec50f101526349cd5aa5f Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Mon, 16 Aug 2021 08:41:08 +0300
Subject: net/mlx5: Let user configure max_macs param

Currently, max_macs is taking 70Kbytes of memory per function. This
size is not needed in all use cases, and is critical with large scale.
Hence, allow user to configure the number of max_macs.

For example, to reduce the number of max_macs to 1, execute::
$ devlink dev param set pci/0000:00:0b.0 name max_macs value 1 \
              cmode driverinit
$ devlink dev reload pci/0000:00:0b.0

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 Documentation/networking/devlink/mlx5.rst         |  4 ++
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 69 +++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c    | 18 ++++++
 include/linux/mlx5/mlx5_ifc.h                     |  2 +-
 4 files changed, 92 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5')

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 5b77863f9c88..d467e770906e 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -14,8 +14,12 @@ Parameters
 
    * - Name
      - Mode
+     - Validation
    * - ``enable_roce``
      - driverinit
+   * - ``max_macs``
+     - driverinit
+     - The range is between 1 and 2^31. Only power of 2 values are supported.
 
 The ``mlx5`` driver also implements the following driver-specific
 parameters.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 1c98652b244a..fc78c745ead1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -752,6 +752,68 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink)
 	mlx5_devlink_eth_param_unregister(devlink);
 }
 
+static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	/* At least one unicast mac is needed */
+	if (val.vu32 == 0) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0");
+		return -EINVAL;
+	}
+	/* Check if its power of 2 or not */
+	if (!is_power_of_2(val.vu32)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only power of 2 values are supported for max_macs");
+		return -EOPNOTSUPP;
+	}
+
+	if (ilog2(val.vu32) >
+	    MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param max_uc_list_param =
+	DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_max_uc_list_validate);
+
+static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
+		return 0;
+
+	err = devlink_param_register(devlink, &max_uc_list_param);
+	if (err)
+		return err;
+
+	value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list);
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+					   value);
+	return 0;
+}
+
+static void
+mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
+		return;
+
+	devlink_param_unregister(devlink, &max_uc_list_param);
+}
+
 #define MLX5_TRAP_DROP(_id, _group_id)					\
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				\
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \
@@ -815,11 +877,17 @@ int mlx5_devlink_register(struct devlink *devlink)
 	if (err)
 		goto traps_reg_err;
 
+	err = mlx5_devlink_max_uc_list_param_register(devlink);
+	if (err)
+		goto uc_list_reg_err;
+
 	if (!mlx5_core_is_mp_slave(dev))
 		devlink_set_features(devlink, DEVLINK_F_RELOAD);
 
 	return 0;
 
+uc_list_reg_err:
+	mlx5_devlink_traps_unregister(devlink);
 traps_reg_err:
 	mlx5_devlink_auxdev_params_unregister(devlink);
 auxdev_reg_err:
@@ -830,6 +898,7 @@ auxdev_reg_err:
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
+	mlx5_devlink_max_uc_list_param_unregister(devlink);
 	mlx5_devlink_traps_unregister(devlink);
 	mlx5_devlink_auxdev_params_unregister(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 96fdbc0c87bf..079ee9e8da10 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -484,10 +484,23 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 }
 
+static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(dev);
+	union devlink_param_value val;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &val);
+	return err ? 0 : val.vu32;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
+	u32 max_uc_list;
 	int err;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
@@ -561,6 +574,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
 
+	max_uc_list = max_uc_list_get_devlink_param(dev);
+	if (max_uc_list)
+		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list,
+			 ilog2(max_uc_list));
+
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 746381eccccf..97465d00de9d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1603,7 +1603,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         ext_stride_num_range[0x1];
 	u8         roce_rw_supported[0x1];
-	u8         reserved_at_3a2[0x1];
+	u8         log_max_current_uc_list_wr_supported[0x1];
 	u8         log_max_stride_sz_rq[0x5];
 	u8         reserved_at_3a8[0x3];
 	u8         log_min_stride_sz_rq[0x5];
-- 
cgit v1.2.3


From 6b3671746a8a3aa05316b829e1357060f35009c1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 26 Oct 2021 08:29:39 -0700
Subject: net/mlx5: remove the recent devlink params

revert commit 46ae40b94d88 ("net/mlx5: Let user configure io_eq_size param")
revert commit a6cb08daa3b4 ("net/mlx5: Let user configure event_eq_size param")
revert commit 554604061979 ("net/mlx5: Let user configure max_macs param")

The EQE parameters are applicable to more drivers, they should
be configured via standard API, probably ethtool. Example of
another driver needing something similar:

https://lore.kernel.org/all/1633454136-14679-3-git-send-email-sbhatta@marvell.com/

The last param for "max_macs" is probably fine but the documentation
is severely lacking. The meaning and implications for changing the
param need to be stated.

Link: https://lore.kernel.org/r/20211026152939.3125950-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/devlink/mlx5.rst          | 20 ------
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c  | 69 -------------------
 drivers/net/ethernet/mellanox/mlx5/core/devlink.h  | 12 ----
 .../net/ethernet/mellanox/mlx5/core/devlink_res.c  | 80 ----------------------
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  5 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c     | 21 ------
 include/linux/mlx5/driver.h                        |  4 ++
 include/linux/mlx5/eq.h                            |  1 +
 include/linux/mlx5/mlx5_ifc.h                      |  2 +-
 10 files changed, 9 insertions(+), 207 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c

(limited to 'include/linux/mlx5')

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index d467e770906e..4e4b97f7971a 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -14,12 +14,8 @@ Parameters
 
    * - Name
      - Mode
-     - Validation
    * - ``enable_roce``
      - driverinit
-   * - ``max_macs``
-     - driverinit
-     - The range is between 1 and 2^31. Only power of 2 values are supported.
 
 The ``mlx5`` driver also implements the following driver-specific
 parameters.
@@ -50,22 +46,6 @@ parameters.
 
 The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD``
 
-Resources
-=========
-
-.. list-table:: Driver-specific resources implemented
-   :widths: 5 5 5 85
-
-   * - Name
-     - Description
-   * - ``comp_eq_size``
-     - Control the size of I/O completion EQs.
-       * The default value is 1024, and the range is between 64 and 4096.
-   * - ``event_eq_size``
-     - Control the size of the asynchronous control events EQ.
-       * The default value is 4096, and the range is between 64 and 4096.
-
-
 Info versions
 =============
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 79c15ee62cde..bdb271b604d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -16,7 +16,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \
 		lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \
-		diag/fw_tracer.o diag/crdump.o devlink.o devlink_res.o diag/rsc_dump.o \
+		diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \
 		fw_reset.o qos.o lib/tout.o
 
 #
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index fc78c745ead1..1c98652b244a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -752,68 +752,6 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink)
 	mlx5_devlink_eth_param_unregister(devlink);
 }
 
-static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id,
-					     union devlink_param_value val,
-					     struct netlink_ext_ack *extack)
-{
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
-
-	/* At least one unicast mac is needed */
-	if (val.vu32 == 0) {
-		NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0");
-		return -EINVAL;
-	}
-	/* Check if its power of 2 or not */
-	if (!is_power_of_2(val.vu32)) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Only power of 2 values are supported for max_macs");
-		return -EOPNOTSUPP;
-	}
-
-	if (ilog2(val.vu32) >
-	    MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) {
-		NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range");
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static const struct devlink_param max_uc_list_param =
-	DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
-			      NULL, NULL, mlx5_devlink_max_uc_list_validate);
-
-static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink)
-{
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
-	union devlink_param_value value;
-	int err;
-
-	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
-		return 0;
-
-	err = devlink_param_register(devlink, &max_uc_list_param);
-	if (err)
-		return err;
-
-	value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list);
-	devlink_param_driverinit_value_set(devlink,
-					   DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
-					   value);
-	return 0;
-}
-
-static void
-mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink)
-{
-	struct mlx5_core_dev *dev = devlink_priv(devlink);
-
-	if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported))
-		return;
-
-	devlink_param_unregister(devlink, &max_uc_list_param);
-}
-
 #define MLX5_TRAP_DROP(_id, _group_id)					\
 	DEVLINK_TRAP_GENERIC(DROP, DROP, _id,				\
 			     DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \
@@ -877,17 +815,11 @@ int mlx5_devlink_register(struct devlink *devlink)
 	if (err)
 		goto traps_reg_err;
 
-	err = mlx5_devlink_max_uc_list_param_register(devlink);
-	if (err)
-		goto uc_list_reg_err;
-
 	if (!mlx5_core_is_mp_slave(dev))
 		devlink_set_features(devlink, DEVLINK_F_RELOAD);
 
 	return 0;
 
-uc_list_reg_err:
-	mlx5_devlink_traps_unregister(devlink);
 traps_reg_err:
 	mlx5_devlink_auxdev_params_unregister(devlink);
 auxdev_reg_err:
@@ -898,7 +830,6 @@ auxdev_reg_err:
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
-	mlx5_devlink_max_uc_list_param_unregister(devlink);
 	mlx5_devlink_traps_unregister(devlink);
 	mlx5_devlink_auxdev_params_unregister(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
index 674415fd0b3a..30bf4882779b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h
@@ -6,14 +6,6 @@
 
 #include <net/devlink.h>
 
-enum mlx5_devlink_resource_id {
-	MLX5_DL_RES_COMP_EQ = 1,
-	MLX5_DL_RES_ASYNC_EQ,
-
-	__MLX5_ID_RES_MAX,
-	MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1,
-};
-
 enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE,
@@ -39,10 +31,6 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev);
 int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id,
 				  enum devlink_trap_action *action);
 
-void mlx5_devlink_res_register(struct mlx5_core_dev *dev);
-void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev);
-size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id);
-
 struct devlink *mlx5_devlink_alloc(struct device *dev);
 void mlx5_devlink_free(struct devlink *devlink);
 int mlx5_devlink_register(struct devlink *devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
deleted file mode 100644
index 549d23745942..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c
+++ /dev/null
@@ -1,80 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */
-
-#include "devlink.h"
-#include "mlx5_core.h"
-
-enum {
-	MLX5_EQ_MIN_SIZE = 64,
-	MLX5_EQ_MAX_SIZE = 4096,
-	MLX5_NUM_ASYNC_EQE = 4096,
-	MLX5_COMP_EQ_SIZE = 1024,
-};
-
-static int comp_eq_res_register(struct mlx5_core_dev *dev)
-{
-	struct devlink_resource_size_params comp_eq_size;
-	struct devlink *devlink = priv_to_devlink(dev);
-
-	devlink_resource_size_params_init(&comp_eq_size, MLX5_EQ_MIN_SIZE,
-					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
-	return devlink_resource_register(devlink, "io_eq_size", MLX5_COMP_EQ_SIZE,
-					 MLX5_DL_RES_COMP_EQ,
-					 DEVLINK_RESOURCE_ID_PARENT_TOP,
-					 &comp_eq_size);
-}
-
-static int async_eq_resource_register(struct mlx5_core_dev *dev)
-{
-	struct devlink_resource_size_params async_eq_size;
-	struct devlink *devlink = priv_to_devlink(dev);
-
-	devlink_resource_size_params_init(&async_eq_size, MLX5_EQ_MIN_SIZE,
-					  MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY);
-	return devlink_resource_register(devlink, "event_eq_size",
-					 MLX5_NUM_ASYNC_EQE, MLX5_DL_RES_ASYNC_EQ,
-					 DEVLINK_RESOURCE_ID_PARENT_TOP,
-					 &async_eq_size);
-}
-
-void mlx5_devlink_res_register(struct mlx5_core_dev *dev)
-{
-	int err;
-
-	err = comp_eq_res_register(dev);
-	if (err)
-		goto err_msg;
-
-	err = async_eq_resource_register(dev);
-	if (err)
-		goto err;
-	return;
-err:
-	devlink_resources_unregister(priv_to_devlink(dev), NULL);
-err_msg:
-	mlx5_core_err(dev, "Failed to register resources, err = %d\n", err);
-}
-
-void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev)
-{
-	devlink_resources_unregister(priv_to_devlink(dev), NULL);
-}
-
-static const size_t default_vals[MLX5_ID_RES_MAX + 1] = {
-	[MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE,
-	[MLX5_DL_RES_ASYNC_EQ] = MLX5_NUM_ASYNC_EQE,
-};
-
-size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id)
-{
-	struct devlink *devlink = priv_to_devlink(dev);
-	u64 size;
-	int err;
-
-	err = devlink_resource_size_get(devlink, id, &size);
-	if (!err)
-		return size;
-	mlx5_core_err(dev, "Failed to get param. using default. err = %d, id = %u\n",
-		      err, id);
-	return default_vals[id];
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 31e69067284b..792e0d6aa861 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -19,7 +19,6 @@
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
 #include "mlx5_irq.h"
-#include "devlink.h"
 
 enum {
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
@@ -647,7 +646,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 
 	param = (struct mlx5_eq_param) {
 		.irq_index = MLX5_IRQ_EQ_CTRL,
-		.nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_ASYNC_EQ),
+		.nent = MLX5_NUM_ASYNC_EQE,
 	};
 
 	gather_async_events_mask(dev, param.mask);
@@ -808,7 +807,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 
 	INIT_LIST_HEAD(&table->comp_eqs_list);
 	ncomp_eqs = table->num_comp_eqs;
-	nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_COMP_EQ);
+	nent = MLX5_COMP_EQ_SIZE;
 	for (i = 0; i < ncomp_eqs; i++) {
 		struct mlx5_eq_param param = {};
 		int vecidx = i;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 079ee9e8da10..f8446395163a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -484,23 +484,10 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx)
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP);
 }
 
-static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev)
-{
-	struct devlink *devlink = priv_to_devlink(dev);
-	union devlink_param_value val;
-	int err;
-
-	err = devlink_param_driverinit_value_get(devlink,
-						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
-						 &val);
-	return err ? 0 : val.vu32;
-}
-
 static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 {
 	struct mlx5_profile *prof = &dev->profile;
 	void *set_hca_cap;
-	u32 max_uc_list;
 	int err;
 
 	err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL);
@@ -574,11 +561,6 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx)
 	if (MLX5_CAP_GEN(dev, roce_rw_supported))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev));
 
-	max_uc_list = max_uc_list_get_devlink_param(dev);
-	if (max_uc_list)
-		MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list,
-			 ilog2(max_uc_list));
-
 	return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE);
 }
 
@@ -940,8 +922,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
 
-	mlx5_devlink_res_register(dev);
-
 	return 0;
 
 err_sf_table_cleanup:
@@ -977,7 +957,6 @@ err_devcom:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
-	mlx5_devlink_res_unregister(dev);
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 47c07f95bbe1..f617dfbcd9fd 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -797,6 +797,10 @@ struct mlx5_db {
 	int			index;
 };
 
+enum {
+	MLX5_COMP_EQ_SIZE = 1024,
+};
+
 enum {
 	MLX5_PTYS_IB = 1 << 0,
 	MLX5_PTYS_EN = 1 << 2,
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index 11161e427608..ea3ff5a8ced3 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -5,6 +5,7 @@
 #define MLX5_CORE_EQ_H
 
 #define MLX5_NUM_CMD_EQE   (32)
+#define MLX5_NUM_ASYNC_EQE (0x1000)
 #define MLX5_NUM_SPARE_EQE (0x80)
 
 struct mlx5_eq;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 97465d00de9d..746381eccccf 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1603,7 +1603,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         ext_stride_num_range[0x1];
 	u8         roce_rw_supported[0x1];
-	u8         log_max_current_uc_list_wr_supported[0x1];
+	u8         reserved_at_3a2[0x1];
 	u8         log_max_stride_sz_rq[0x5];
 	u8         reserved_at_3a8[0x3];
 	u8         log_min_stride_sz_rq[0x5];
-- 
cgit v1.2.3


From 50f477fe9933193e960785f1192be801d7cd307a Mon Sep 17 00:00:00 2001
From: Ben Ben-Ishay <benishay@nvidia.com>
Date: Thu, 2 Jul 2020 17:22:45 +0300
Subject: net/mlx5e: Rename lro_timeout to packet_merge_timeout

TIR stands for transport interface receive, the TIR object is
responsible for performing all transport related operations on
the receive side like packet processing, demultiplexing the packets
to different RQ's, etc.
lro_timeout is a field in the TIR that is used to set the timeout for lro
session, this series introduces new packet merge type, therefore rename
lro_timeout to packet_merge_timeout for all packet merge types.

Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h        | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/tir.c    | 6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c   | 2 +-
 include/linux/mlx5/mlx5_ifc.h                       | 6 +++---
 5 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index a3a4fece0cac..26e3f413386a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -265,7 +265,7 @@ struct mlx5e_params {
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
 	bool tx_dim_enabled;
-	u32 lro_timeout;
+	u32 packet_merge_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
 	struct mlx5e_xsk *xsk;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 3cbb596821e8..2b2b3c5cdbd5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -173,7 +173,7 @@ struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params)
 
 	lro_param = (struct mlx5e_lro_param) {
 		.enabled = params->lro_en,
-		.timeout = params->lro_timeout,
+		.timeout = params->packet_merge_timeout,
 	};
 
 	return lro_param;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index de936dc4bc48..857ea0979159 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -82,9 +82,9 @@ void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
 	if (!lro_param->enabled)
 		return;
 
-	MLX5_SET(tirc, tirc, lro_enable_mask,
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO |
-		 MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO);
+	MLX5_SET(tirc, tirc, packet_merge_mask,
+		 MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO |
+		 MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
 		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8);
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index f3dec58026d9..0e7a8afeb9bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4404,7 +4404,7 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
 			params->lro_en = !slow_pci_heuristic(mdev);
 	}
-	params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+	params->packet_merge_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
 	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 746381eccccf..21c0fd478afa 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3361,8 +3361,8 @@ enum {
 };
 
 enum {
-	MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO  = 0x1,
-	MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO  = 0x2,
+	MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO  = BIT(0),
+	MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO  = BIT(1),
 };
 
 enum {
@@ -3387,7 +3387,7 @@ struct mlx5_ifc_tirc_bits {
 
 	u8         reserved_at_80[0x4];
 	u8         lro_timeout_period_usecs[0x10];
-	u8         lro_enable_mask[0x4];
+	u8         packet_merge_mask[0x4];
 	u8         lro_max_ip_payload_size[0x8];
 
 	u8         reserved_at_a0[0x40];
-- 
cgit v1.2.3


From 7025329d208cae45937d2a0910786a45b9981475 Mon Sep 17 00:00:00 2001
From: Ben Ben-Ishay <benishay@nvidia.com>
Date: Wed, 9 Sep 2020 17:36:39 +0300
Subject: net/mlx5: Add SHAMPO caps, HW bits and enumerations

This commit adds SHAMPO bit to hca_cap and SHAMPO capabilities structure,
SHAMPO related HW spec hardware fields and enumerations.
SHAMPO stands for: split headers and merge payload offload.
SHAMPO new fields:
WQ:
 - headers_mkey: mkey that represents the headers buffer, where the packets
   headers will be written by the HW.

 - shampo_enable: flag to verify if the WQ supports SHAMPO feature.

 - log_reservation_size: the log of the reservation size where the data of
   the packet will be written by the HW.

 - log_max_num_of_packets_per_reservation: log of the maximum number of
   packets that can be written to the same reservation.

 - log_headers_entry_size: log of the header entry size of the headers buffer.

 - log_headers_buffer_entry_num: log of the entries number of the headers buffer.

RQ:
 - shampo_no_match_alignment_granularity: the HW alignment granularity
   in case the received packet doesn't match the current session.

 - shampo_match_criteria_type: the type of match criteria.

 - reservation_timeout: the maximum time that the HW will hold the
   reservation.

mlx5_ifc_shampo_cap_bits, the capabilities of the SHAMPO feature:
 - shampo_log_max_reservation_size: the maximum allowed value of the field
   WQ.log_reservation_size.

 - log_reservation_size: the minimum allowed value of the field
   WQ.log_reservation_size.

 - shampo_min_mss_size: the minimum payload size of packet that can open
   a new session or be merged to a session.

 - shampo_max_log_headers_entry_size: the maximum allowed value of the field
   WQ.log_headers_entry_size

Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c   |  6 +++
 drivers/net/ethernet/mellanox/mlx5/core/main.c |  1 +
 include/linux/mlx5/device.h                    |  4 ++
 include/linux/mlx5/mlx5_ifc.h                  | 56 ++++++++++++++++++++++++--
 4 files changed, 64 insertions(+), 3 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 1037e3629e7e..2d8406fab844 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -269,6 +269,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, shampo)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f8446395163a..a92a92a52346 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1417,6 +1417,7 @@ static const int types[] = {
 	MLX5_CAP_VDPA_EMULATION,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_PORT_SELECTION,
+	MLX5_CAP_DEV_SHAMPO,
 };
 
 static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index f8a0bbb42c3b..0d30a6184e1d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1186,6 +1186,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_VDPA_EMULATION = 0x13,
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
+	MLX5_CAP_DEV_SHAMPO = 0x1d,
 	MLX5_CAP_GENERAL_2 = 0x20,
 	MLX5_CAP_PORT_SELECTION = 0x25,
 	/* NUM OF CAP Types */
@@ -1431,6 +1432,9 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_IPSEC(mdev, cap)\
 	MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap)
 
+#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\
+	MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap)
+
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
 	MLX5_CMD_STAT_INT_ERR			= 0x1,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 21c0fd478afa..f1c134af5fcf 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1350,7 +1350,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_b0[0x1];
 	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
-	u8         reserved_at_b3[0xd];
+	u8         reserved_at_b3[0x7];
+	u8         shampo[0x1];
+	u8         reserved_at_bb[0x5];
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
@@ -1893,7 +1895,21 @@ struct mlx5_ifc_wq_bits {
 	u8         reserved_at_139[0x4];
 	u8         log_wqe_stride_size[0x3];
 
-	u8         reserved_at_140[0x4c0];
+	u8         reserved_at_140[0x80];
+
+	u8         headers_mkey[0x20];
+
+	u8         shampo_enable[0x1];
+	u8         reserved_at_1e1[0x4];
+	u8         log_reservation_size[0x3];
+	u8         reserved_at_1e8[0x5];
+	u8         log_max_num_of_packets_per_reservation[0x3];
+	u8         reserved_at_1f0[0x6];
+	u8         log_headers_entry_size[0x2];
+	u8         reserved_at_1f8[0x4];
+	u8         log_headers_buffer_entry_num[0x4];
+
+	u8         reserved_at_200[0x400];
 
 	struct mlx5_ifc_cmd_pas_bits pas[];
 };
@@ -3169,6 +3185,20 @@ struct mlx5_ifc_roce_addr_layout_bits {
 	u8         reserved_at_e0[0x20];
 };
 
+struct mlx5_ifc_shampo_cap_bits {
+	u8    reserved_at_0[0x3];
+	u8    shampo_log_max_reservation_size[0x5];
+	u8    reserved_at_8[0x3];
+	u8    shampo_log_min_reservation_size[0x5];
+	u8    shampo_min_mss_size[0x10];
+
+	u8    reserved_at_20[0x3];
+	u8    shampo_max_log_headers_entry_size[0x5];
+	u8    reserved_at_28[0x18];
+
+	u8    reserved_at_40[0x7c0];
+};
+
 union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap;
 	struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2;
@@ -3187,6 +3217,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_tls_cap_bits tls_cap;
 	struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
 	struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap;
+	struct mlx5_ifc_shampo_cap_bits shampo_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -3363,6 +3394,7 @@ enum {
 enum {
 	MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO  = BIT(0),
 	MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO  = BIT(1),
+	MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO    = BIT(2),
 };
 
 enum {
@@ -3569,6 +3601,18 @@ enum {
 	MLX5_RQC_STATE_ERR  = 0x3,
 };
 
+enum {
+	MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_BYTE    = 0x0,
+	MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE  = 0x1,
+	MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_PAGE    = 0x2,
+};
+
+enum {
+	MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_NO_MATCH    = 0x0,
+	MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED    = 0x1,
+	MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_FIVE_TUPLE  = 0x2,
+};
+
 struct mlx5_ifc_rqc_bits {
 	u8         rlky[0x1];
 	u8	   delay_drop_en[0x1];
@@ -3601,7 +3645,13 @@ struct mlx5_ifc_rqc_bits {
 	u8         reserved_at_c0[0x10];
 	u8         hairpin_peer_vhca[0x10];
 
-	u8         reserved_at_e0[0xa0];
+	u8         reserved_at_e0[0x46];
+	u8         shampo_no_match_alignment_granularity[0x2];
+	u8         reserved_at_128[0x6];
+	u8         shampo_match_criteria_type[0x2];
+	u8         reservation_timeout[0x10];
+
+	u8         reserved_at_140[0x40];
 
 	struct mlx5_ifc_wq_bits wq;
 };
-- 
cgit v1.2.3


From eaee12f046924eeb1210c7e4f3b326603ff1bd85 Mon Sep 17 00:00:00 2001
From: Khalid Manaa <khalidm@nvidia.com>
Date: Wed, 9 Jun 2021 12:27:32 +0300
Subject: net/mlx5e: Rename TIR lro functions to TIR packet merge functions

This series introduces new packet merge type, therefore rename lro
functions to packet merge to support the new merge type:
- Generalize + rename mlx5e_build_tir_ctx_lro to
  mlx5e_build_tir_ctx_packet_merge.
- Rename mlx5e_modify_tirs_lro to mlx5e_modify_tirs_packet_merge.
- Rename lro bit in mlx5_ifc_modify_tir_bitmask_bits to packet_merge.
- Rename lro_en in mlx5e_params to packet_merge_type type and combine
  packet_merge params into one struct mlx5e_packet_merge_param.

Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 14 ++++++-
 .../net/ethernet/mellanox/mlx5/core/en/params.c    | 21 +++-------
 .../net/ethernet/mellanox/mlx5/core/en/params.h    |  6 ---
 drivers/net/ethernet/mellanox/mlx5/core/en/rss.c   | 23 +++++------
 drivers/net/ethernet/mellanox/mlx5/core/en/rss.h   |  7 ++--
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.c    | 25 ++++++------
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.h    |  5 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en/tir.c   | 10 ++---
 drivers/net/ethernet/mellanox/mlx5/core/en/tir.h   |  6 +--
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  4 +-
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    |  6 +--
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 46 ++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  5 +--
 .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c  |  7 ++--
 include/linux/mlx5/mlx5_ifc.h                      |  2 +-
 15 files changed, 95 insertions(+), 92 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 26e3f413386a..8c3e7464b30f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -242,6 +242,17 @@ enum mlx5e_priv_flag {
 
 #define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
 
+enum packet_merge {
+	MLX5E_PACKET_MERGE_NONE,
+	MLX5E_PACKET_MERGE_LRO,
+	MLX5E_PACKET_MERGE_SHAMPO,
+};
+
+struct mlx5e_packet_merge_param {
+	enum packet_merge type;
+	u32 timeout;
+};
+
 struct mlx5e_params {
 	u8  log_sq_size;
 	u8  rq_wq_type;
@@ -259,13 +270,12 @@ struct mlx5e_params {
 	bool tunneled_offload_en;
 	struct dim_cq_moder rx_cq_moderation;
 	struct dim_cq_moder tx_cq_moderation;
-	bool lro_en;
+	struct mlx5e_packet_merge_param packet_merge;
 	u8  tx_min_inline_mode;
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
 	bool tx_dim_enabled;
-	u32 packet_merge_timeout;
 	u32 pflags;
 	struct bpf_prog *xdp_prog;
 	struct mlx5e_xsk *xsk;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 2b2b3c5cdbd5..15f441a1b80c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -87,7 +87,8 @@ bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params,
 	u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk),
 				 mlx5e_rx_get_linear_frag_sz(params, NULL));
 
-	return !params->lro_en && linear_frag_sz <= PAGE_SIZE;
+	return params->packet_merge.type == MLX5E_PACKET_MERGE_NONE &&
+		linear_frag_sz <= PAGE_SIZE;
 }
 
 bool mlx5e_verify_rx_mpwqe_strides(struct mlx5_core_dev *mdev,
@@ -164,19 +165,8 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 		mlx5e_rx_is_linear_skb(params, xsk) :
 		mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk);
 
-	return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0;
-}
-
-struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params)
-{
-	struct mlx5e_lro_param lro_param;
-
-	lro_param = (struct mlx5e_lro_param) {
-		.enabled = params->lro_en,
-		.timeout = params->packet_merge_timeout,
-	};
-
-	return lro_param;
+	return is_linear_skb || params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO ?
+		mlx5e_get_linear_rq_headroom(params, xsk) : 0;
 }
 
 u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
@@ -485,10 +475,11 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev,
 
 static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 {
+	bool lro_en = params->packet_merge.type == MLX5E_PACKET_MERGE_LRO;
 	bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) &&
 		MLX5_CAP_GEN(mdev, relaxed_ordering_write);
 
-	return ro && params->lro_en ?
+	return ro && lro_en ?
 		MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 879ad46d754e..e9593f5f0661 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -11,11 +11,6 @@ struct mlx5e_xsk_param {
 	u16 chunk_size;
 };
 
-struct mlx5e_lro_param {
-	bool enabled;
-	u32 timeout;
-};
-
 struct mlx5e_cq_param {
 	u32                        cqc[MLX5_ST_SZ_DW(cqc)];
 	struct mlx5_wq_param       wq;
@@ -125,7 +120,6 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
 u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev,
 			  struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk);
-struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params);
 
 /* Build queue parameters */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index b8b481b335cf..c1cdd8c2e37a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -127,7 +127,7 @@ mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt)
 
 static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 				enum mlx5_traffic_types tt,
-				const struct mlx5e_lro_param *init_lro_param,
+				const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				bool inner)
 {
 	struct mlx5e_rss_params_traffic_type rss_tt;
@@ -161,7 +161,7 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss,
 	rqtn = mlx5e_rqt_get_rqtn(&rss->rqt);
 	mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn,
 				    rqtn, rss->inner_ft_support);
-	mlx5e_tir_builder_build_lro(builder, init_lro_param);
+	mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 	rss_tt = mlx5e_rss_get_tt_config(rss, tt);
 	mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner);
 
@@ -198,14 +198,14 @@ static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types
 }
 
 static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss,
-				 const struct mlx5e_lro_param *init_lro_param,
+				 const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				 bool inner)
 {
 	enum mlx5_traffic_types tt, max_tt;
 	int err;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -297,7 +297,7 @@ int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 
 int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 		   bool inner_ft_support, u32 drop_rqn,
-		   const struct mlx5e_lro_param *init_lro_param)
+		   const struct mlx5e_packet_merge_param *init_pkt_merge_param)
 {
 	int err;
 
@@ -305,12 +305,12 @@ int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 	if (err)
 		goto err_out;
 
-	err = mlx5e_rss_create_tirs(rss, init_lro_param, false);
+	err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, false);
 	if (err)
 		goto err_destroy_rqt;
 
 	if (inner_ft_support) {
-		err = mlx5e_rss_create_tirs(rss, init_lro_param, true);
+		err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, true);
 		if (err)
 			goto err_destroy_tirs;
 	}
@@ -372,7 +372,7 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
  */
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_lro_param *init_lro_param,
+			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 			  bool inner, u32 *tirn)
 {
 	struct mlx5e_tir *tir;
@@ -381,7 +381,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 	if (!tir) { /* TIR doesn't exist, create one */
 		int err;
 
-		err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner);
+		err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner);
 		if (err)
 			return err;
 		tir = rss_get_tir(rss, tt, inner);
@@ -419,7 +419,8 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss)
 			       mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err);
 }
 
-int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param)
+int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
+				     struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	struct mlx5e_tir_builder *builder;
 	enum mlx5_traffic_types tt;
@@ -429,7 +430,7 @@ int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_p
 	if (!builder)
 		return -ENOMEM;
 
-	mlx5e_tir_builder_build_lro(builder, lro_param);
+	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 
 	final_err = 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d522a10dadf3..c6b216416344 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -17,7 +17,7 @@ struct mlx5e_rss *mlx5e_rss_alloc(void);
 void mlx5e_rss_free(struct mlx5e_rss *rss);
 int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 		   bool inner_ft_support, u32 drop_rqn,
-		   const struct mlx5e_lro_param *init_lro_param);
+		   const struct mlx5e_packet_merge_param *init_pkt_merge_param);
 int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev,
 			   bool inner_ft_support, u32 drop_rqn);
 int mlx5e_rss_cleanup(struct mlx5e_rss *rss);
@@ -30,13 +30,14 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		       bool inner);
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
-			  const struct mlx5e_lro_param *init_lro_param,
+			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 			  bool inner, u32 *tirn);
 
 void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns);
 void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
-int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param);
+int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
+				     struct mlx5e_packet_merge_param *pkt_merge_param);
 int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       const u8 *key, const u8 *hfunc,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 13056cb9757d..142953847996 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -34,7 +34,7 @@ struct mlx5e_rx_res {
 /* API for rx_res_rss_* */
 
 static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
-				     const struct mlx5e_lro_param *init_lro_param,
+				     const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 				     unsigned int init_nch)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
@@ -49,7 +49,7 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res,
 		return -ENOMEM;
 
 	err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn,
-			     init_lro_param);
+			     init_pkt_merge_param);
 	if (err)
 		goto err_rss_free;
 
@@ -275,7 +275,7 @@ struct mlx5e_rx_res *mlx5e_rx_res_alloc(void)
 }
 
 static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
-				      const struct mlx5e_lro_param *init_lro_param)
+				      const struct mlx5e_packet_merge_param *init_pkt_merge_param)
 {
 	bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT;
 	struct mlx5e_tir_builder *builder;
@@ -306,7 +306,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true);
@@ -336,7 +336,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res,
 		mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn,
 					    mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt),
 					    inner_ft_support);
-		mlx5e_tir_builder_build_lro(builder, init_lro_param);
+		mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param);
 		mlx5e_tir_builder_build_direct(builder);
 
 		err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true);
@@ -437,7 +437,7 @@ static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res)
 
 int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 		      enum mlx5e_rx_res_features features, unsigned int max_nch,
-		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 		      unsigned int init_nch)
 {
 	int err;
@@ -447,11 +447,11 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 	res->max_nch = max_nch;
 	res->drop_rqn = drop_rqn;
 
-	err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch);
+	err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch);
 	if (err)
 		goto err_out;
 
-	err = mlx5e_rx_res_channels_init(res, init_lro_param);
+	err = mlx5e_rx_res_channels_init(res, init_pkt_merge_param);
 	if (err)
 		goto err_rss_destroy;
 
@@ -645,7 +645,8 @@ int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix)
 	return err;
 }
 
-int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param)
+int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
+					struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	struct mlx5e_tir_builder *builder;
 	int err, final_err;
@@ -655,7 +656,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 	if (!builder)
 		return -ENOMEM;
 
-	mlx5e_tir_builder_build_lro(builder, lro_param);
+	mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param);
 
 	final_err = 0;
 
@@ -665,7 +666,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 		if (!rss)
 			continue;
 
-		err = mlx5e_rss_lro_set_param(rss, lro_param);
+		err = mlx5e_rss_packet_merge_set_param(rss, pkt_merge_param);
 		if (err)
 			final_err = final_err ? : err;
 	}
@@ -673,7 +674,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param
 	for (ix = 0; ix < res->max_nch; ix++) {
 		err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder);
 		if (err) {
-			mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n",
+			mlx5_core_warn(res->mdev, "Failed to update packet merge state of direct TIR %#x for channel %u: err = %d\n",
 				       mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err);
 			if (!final_err)
 				final_err = err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 4a15942d79f7..d09f7d174a51 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -25,7 +25,7 @@ enum mlx5e_rx_res_features {
 struct mlx5e_rx_res *mlx5e_rx_res_alloc(void);
 int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev,
 		      enum mlx5e_rx_res_features features, unsigned int max_nch,
-		      u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param,
+		      u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param,
 		      unsigned int init_nch);
 void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res);
 void mlx5e_rx_res_free(struct mlx5e_rx_res *res);
@@ -57,7 +57,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt,
 				     u8 rx_hash_fields);
-int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param);
+int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res,
+					struct mlx5e_packet_merge_param *pkt_merge_param);
 
 int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch);
 int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index 857ea0979159..a1afb8585e37 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -70,16 +70,16 @@ void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
 	MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support);
 }
 
-void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
-				 const struct mlx5e_lro_param *lro_param)
+void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder,
+					  const struct mlx5e_packet_merge_param *pkt_merge_param)
 {
 	void *tirc = mlx5e_tir_builder_get_tirc(builder);
 	const unsigned int rough_max_l2_l3_hdr_sz = 256;
 
 	if (builder->modify)
-		MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1);
+		MLX5_SET(modify_tir_in, builder->in, bitmask.packet_merge, 1);
 
-	if (!lro_param->enabled)
+	if (pkt_merge_param->type == MLX5E_PACKET_MERGE_NONE)
 		return;
 
 	MLX5_SET(tirc, tirc, packet_merge_mask,
@@ -87,7 +87,7 @@ void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
 		 MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO);
 	MLX5_SET(tirc, tirc, lro_max_ip_payload_size,
 		 (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8);
-	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout);
+	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, pkt_merge_param->timeout);
 }
 
 static int mlx5e_hfunc_to_hw(u8 hfunc)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
index e45149a78ed9..857a84bcd53a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -18,7 +18,7 @@ struct mlx5e_rss_params_traffic_type {
 };
 
 struct mlx5e_tir_builder;
-struct mlx5e_lro_param;
+struct mlx5e_packet_merge_param;
 
 struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify);
 void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder);
@@ -27,8 +27,8 @@ void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder);
 void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn);
 void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn,
 				 u32 rqtn, bool inner_ft_support);
-void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder,
-				 const struct mlx5e_lro_param *lro_param);
+void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder,
+					  const struct mlx5e_packet_merge_param *pkt_merge_param);
 void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 				 const struct mlx5e_rss_params_hash *rss_hash,
 				 const struct mlx5e_rss_params_traffic_type *rss_tt,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 25926e581d18..5a46b6e1b9da 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1952,8 +1952,8 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 			return -EOPNOTSUPP;
 		if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params))
 			return -EINVAL;
-	} else if (priv->channels.params.lro_en) {
-		netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n");
+	} else if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+		netdev_warn(netdev, "Can't set legacy RQ with HW-GRO/LRO, disable them first\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 81ebf281cdb4..ad0d234632a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -411,7 +411,7 @@ static int flow_get_tirn(struct mlx5e_priv *priv,
 			 u32 rss_context, u32 *tirn)
 {
 	if (fs->flow_type & FLOW_RSS) {
-		struct mlx5e_lro_param lro_param;
+		struct mlx5e_packet_merge_param pkt_merge_param;
 		struct mlx5e_rss *rss;
 		u32 flow_type;
 		int err;
@@ -426,8 +426,8 @@ static int flow_get_tirn(struct mlx5e_priv *priv,
 		if (tt < 0)
 			return -EINVAL;
 
-		lro_param = mlx5e_get_lro_param(&priv->channels.params);
-		err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn);
+		pkt_merge_param = priv->channels.params.packet_merge;
+		err = mlx5e_rss_obtain_tirn(rss, tt, &pkt_merge_param, false, tirn);
 		if (err)
 			return err;
 		eth_rule->rss = rss;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0e7a8afeb9bd..0c039906a1fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2222,17 +2222,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs)
 	chs->num = 0;
 }
 
-static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
+static int mlx5e_modify_tirs_packet_merge(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rx_res *res = priv->rx_res;
-	struct mlx5e_lro_param lro_param;
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
-
-	return mlx5e_rx_res_lro_set_param(res, &lro_param);
+	return mlx5e_rx_res_packet_merge_set_param(res, &priv->channels.params.packet_merge);
 }
 
-static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro);
+static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_packet_merge);
 
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
 			 struct mlx5e_params *params, u16 mtu)
@@ -3351,16 +3348,25 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 	}
 
 	new_params = *cur_params;
-	new_params.lro_en = enable;
 
-	if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
-		if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) ==
-		    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL))
-			reset = false;
+	if (enable)
+		new_params.packet_merge.type = MLX5E_PACKET_MERGE_LRO;
+	else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)
+		new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE;
+	else
+		goto out;
+
+	if (!(cur_params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO &&
+	      new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)) {
+		if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
+			if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) ==
+			    mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL))
+				reset = false;
+		}
 	}
 
 	err = mlx5e_safe_switch_params(priv, &new_params,
-				       mlx5e_modify_tirs_lro_ctx, NULL, reset);
+				       mlx5e_modify_tirs_packet_merge_ctx, NULL, reset);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3687,7 +3693,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		goto out;
 	}
 
-	if (params->lro_en)
+	if (params->packet_merge.type == MLX5E_PACKET_MERGE_LRO)
 		reset = false;
 
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
@@ -4144,8 +4150,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 	struct net_device *netdev = priv->netdev;
 	struct mlx5e_params new_params;
 
-	if (priv->channels.params.lro_en) {
-		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+	if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) {
+		netdev_warn(netdev, "can't set XDP while HW-GRO/LRO is on, disable them first\n");
 		return -EINVAL;
 	}
 
@@ -4402,9 +4408,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	    params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		/* No XSK params: checking the availability of striding RQ in general. */
 		if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL))
-			params->lro_en = !slow_pci_heuristic(mdev);
+			params->packet_merge.type = slow_pci_heuristic(mdev) ?
+				MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO;
 	}
-	params->packet_merge_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
+	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
 	rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
@@ -4693,7 +4700,6 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	enum mlx5e_rx_res_features features;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -4711,9 +4717,9 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
 	features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP;
 	if (priv->channels.params.tunneled_offload_en)
 		features |= MLX5E_RX_RES_FEATURE_INNER_FT;
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 0684ac6699b2..5230e0422cae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -793,7 +793,6 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup)
 static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -808,9 +807,9 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
 		return err;
 	}
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 3b8d8ada1a01..84297cc1b509 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -67,7 +67,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev,
 		MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE :
 		MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE;
 
-	params->lro_en = false;
+	params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 	params->tunneled_offload_en = false;
 }
@@ -356,7 +356,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
 static int mlx5i_init_rx(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5e_lro_param lro_param;
 	int err;
 
 	priv->rx_res = mlx5e_rx_res_alloc();
@@ -371,9 +370,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 		goto err_destroy_q_counters;
 	}
 
-	lro_param = mlx5e_get_lro_param(&priv->channels.params);
 	err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0,
-				priv->max_nch, priv->drop_rq.rqn, &lro_param,
+				priv->max_nch, priv->drop_rq.rqn,
+				&priv->channels.params.packet_merge,
 				priv->channels.params.num_channels);
 	if (err)
 		goto err_close_drop_rq;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index f1c134af5fcf..0bb78c04336c 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -6707,7 +6707,7 @@ struct mlx5_ifc_modify_tir_bitmask_bits {
 	u8         reserved_at_3c[0x1];
 	u8         hash[0x1];
 	u8         reserved_at_3e[0x1];
-	u8         lro[0x1];
+	u8         packet_merge[0x1];
 };
 
 struct mlx5_ifc_modify_tir_out_bits {
-- 
cgit v1.2.3


From d7b896acbdcb3ef5dab1fd2f33ba5a8da6ba1dda Mon Sep 17 00:00:00 2001
From: Ben Ben-Ishay <benishay@nvidia.com>
Date: Tue, 14 Jul 2020 14:40:32 +0300
Subject: net/mlx5e: Add support to klm_umr_wqe

This commit adds the needed definitions for using the klm_umr_wqe.
UMR stands for user-mode memory registration, is a mechanism to alter
address translation properties of MKEY by posting WorkQueueElement
aka WQE on send queue.
MKEY stands for memory key, MKEY are used to describe a region in memory that
can be later used by HW.
KLM stands for {Key, Length, MemVa}, KLM_MKEY is indirect MKEY that enables
to map multiple memory spaces with different sizes in unified MKEY.
klm_umr_wqe is a UMR that use to update a KLM_MKEY.
SHAMPO feature uses KLM_MKEY for memory registration of his header buffer.

Signed-off-by: Ben Ben-Ishay <benishay@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h | 24 +++++++++++++++++++++++-
 include/linux/mlx5/device.h                  |  1 +
 2 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8c3e7464b30f..98b56d8bddb8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -152,6 +152,25 @@ struct page_pool;
 #define MLX5E_UMR_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
 
+#define MLX5E_KLM_UMR_WQE_SZ(sgl_len)\
+	(sizeof(struct mlx5e_umr_wqe) +\
+	(sizeof(struct mlx5_klm) * (sgl_len)))
+
+#define MLX5E_KLM_UMR_WQEBBS(klm_entries) \
+	(DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_BB))
+
+#define MLX5E_KLM_UMR_DS_CNT(klm_entries)\
+	(DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_DS))
+
+#define MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size)\
+	(((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm))
+
+#define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\
+	ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT)
+
+#define MLX5E_MAX_KLM_PER_WQE(mdev) \
+	MLX5E_KLM_ENTRIES_PER_WQE(MLX5E_TX_MPW_MAX_NUM_DS << MLX5_MKEY_BSF_OCTO_SIZE)
+
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
 
 #define mlx5e_dbg(mlevel, priv, format, ...)                    \
@@ -217,7 +236,10 @@ struct mlx5e_umr_wqe {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
-	struct mlx5_mtt                inline_mtts[0];
+	union {
+		struct mlx5_mtt inline_mtts[0];
+		struct mlx5_klm inline_klms[0];
+	};
 };
 
 enum mlx5e_priv_flag {
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0d30a6184e1d..c920e5932368 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -290,6 +290,7 @@ enum {
 	MLX5_UMR_INLINE			= (1 << 7),
 };
 
+#define MLX5_UMR_KLM_ALIGNMENT 4
 #define MLX5_UMR_MTT_ALIGNMENT 0x40
 #define MLX5_UMR_MTT_MASK      (MLX5_UMR_MTT_ALIGNMENT - 1)
 #define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT
-- 
cgit v1.2.3


From f97d5c2a453e26071e3b0ec12161de57c4a237c4 Mon Sep 17 00:00:00 2001
From: Khalid Manaa <khalidm@nvidia.com>
Date: Tue, 19 May 2020 15:45:38 +0300
Subject: net/mlx5e: Add handle SHAMPO cqe support

This patch adds the new CQE SHAMPO fields:
- flush: indicates that we must close the current session and pass the SKB
         to the network stack.

- match: indicates that the current packet matches the oppened session,
         the packet will be merge into the current SKB.

- header_size: the size of the packet headers that written into the headers
               buffer.

- header_entry_index: the entry index in the headers buffer.

- data_offset: packets data offset in the WQE.

Also new cqe handler is added to handle SHAMPO packets:
- The new handler uses CQE SHAMPO fields to build the SKB.
  CQE's Flush and match fields are not used in this patch, packets are not
  merged in this patch.

Signed-off-by: Khalid Manaa <khalidm@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 205 ++++++++++++++++++++----
 include/linux/mlx5/device.h                     |  23 ++-
 3 files changed, 194 insertions(+), 35 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8431cdd8006c..c95b6b65c4de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -943,6 +943,7 @@ struct mlx5e_priv {
 struct mlx5e_rx_handlers {
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe;
 	mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe;
+	mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe_shampo;
 };
 
 extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 397a4e769076..68759c8fd31e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -62,10 +62,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 				   u16 cqe_bcnt, u32 head_offset, u32 page_idx);
 static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
+static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = {
 	.handle_rx_cqe       = mlx5e_handle_rx_cqe,
 	.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.handle_rx_cqe_mpwqe_shampo = mlx5e_handle_rx_cqe_mpwrq_shampo,
 };
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
@@ -185,8 +187,9 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq,
 			mlx5e_read_mini_arr_slot(wq, cqd, cqcc);
 
 		mlx5e_decompress_cqe_no_hash(rq, wq, cqcc);
-		INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
-				mlx5e_handle_rx_cqe, rq, &cqd->title);
+		INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
+				mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe,
+				rq, &cqd->title);
 	}
 	mlx5e_cqes_update_owner(wq, cqcc - wq->cc);
 	wq->cc = cqcc;
@@ -206,8 +209,9 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
 	mlx5e_read_title_slot(rq, wq, cc);
 	mlx5e_read_mini_arr_slot(wq, cqd, cc + 1);
 	mlx5e_decompress_cqe(rq, wq, cc);
-	INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
-			mlx5e_handle_rx_cqe, rq, &cqd->title);
+	INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
+			mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe,
+			rq, &cqd->title);
 	cqd->mini_arr_idx++;
 
 	return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1;
@@ -448,13 +452,13 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 static inline void
 mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 		      struct mlx5e_dma_info *dma_info,
-		      int offset_from, u32 headlen)
+		      int offset_from, int dma_offset, u32 headlen)
 {
 	const void *from = page_address(dma_info->page) + offset_from;
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
 	unsigned int len = ALIGN(headlen, sizeof(long));
 
-	dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len,
+	dma_sync_single_for_cpu(pdev, dma_info->addr + dma_offset, len,
 				DMA_FROM_DEVICE);
 	skb_copy_to_linear_data(skb, from, len);
 }
@@ -820,8 +824,8 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp)
 
 	if (tcp_ack) {
 		tcp->ack                = 1;
-		tcp->ack_seq            = cqe->lro_ack_seq_num;
-		tcp->window             = cqe->lro_tcp_win;
+		tcp->ack_seq            = cqe->lro.ack_seq_num;
+		tcp->window             = cqe->lro.tcp_win;
 	}
 }
 
@@ -847,7 +851,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		tcp = ip_p + sizeof(struct iphdr);
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 
-		ipv4->ttl               = cqe->lro_min_ttl;
+		ipv4->ttl               = cqe->lro.min_ttl;
 		ipv4->tot_len           = cpu_to_be16(tot_len);
 		ipv4->check             = 0;
 		ipv4->check             = ip_fast_csum((unsigned char *)ipv4,
@@ -867,7 +871,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
 		tcp = ip_p + sizeof(struct ipv6hdr);
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 
-		ipv6->hop_limit         = cqe->lro_min_ttl;
+		ipv6->hop_limit         = cqe->lro.min_ttl;
 		ipv6->payload_len       = cpu_to_be16(payload_len);
 
 		mlx5e_lro_update_tcp_hdr(cqe, tcp);
@@ -1237,7 +1241,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	}
 
 	/* copy header */
-	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, head_wi->offset,
+			      headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -1433,6 +1438,30 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = {
 };
 #endif
 
+static void
+mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		    u32 data_bcnt, u32 data_offset)
+{
+	net_prefetchw(skb->data);
+
+	while (data_bcnt) {
+		u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt);
+		unsigned int truesize;
+
+		if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
+			truesize = pg_consumed_bytes;
+		else
+			truesize = ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
+
+		mlx5e_add_skb_frag(rq, skb, di, data_offset,
+				   pg_consumed_bytes, truesize);
+
+		data_bcnt -= pg_consumed_bytes;
+		data_offset = 0;
+		di++;
+	}
+}
+
 static struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				   u16 cqe_bcnt, u32 head_offset, u32 page_idx)
@@ -1458,20 +1487,9 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		frag_offset -= PAGE_SIZE;
 	}
 
-	while (byte_cnt) {
-		u32 pg_consumed_bytes =
-			min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
-		unsigned int truesize =
-			ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz));
-
-		mlx5e_add_skb_frag(rq, skb, di, frag_offset,
-				   pg_consumed_bytes, truesize);
-		byte_cnt -= pg_consumed_bytes;
-		frag_offset = 0;
-		di++;
-	}
+	mlx5e_fill_skb_data(skb, rq, di, byte_cnt, frag_offset);
 	/* copy header */
-	mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, head_offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -1525,6 +1543,123 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 	return skb;
 }
 
+static struct sk_buff *
+mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
+			  struct mlx5_cqe64 *cqe, u16 header_index)
+{
+	struct mlx5e_dma_info *head = &rq->mpwqe.shampo->info[header_index];
+	u16 head_offset = head->addr & (PAGE_SIZE - 1);
+	u16 head_size = cqe->shampo.header_size;
+	u16 rx_headroom = rq->buff.headroom;
+	struct sk_buff *skb = NULL;
+	void *hdr, *data;
+	u32 frag_size;
+
+	hdr		= page_address(head->page) + head_offset;
+	data		= hdr + rx_headroom;
+	frag_size	= MLX5_SKB_FRAG_SZ(rx_headroom + head_size);
+
+	if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) {
+		/* build SKB around header */
+		dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE);
+		prefetchw(hdr);
+		prefetch(data);
+		skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size);
+
+		if (unlikely(!skb))
+			return NULL;
+
+		/* queue up for recycling/reuse */
+		page_ref_inc(head->page);
+
+	} else {
+		/* allocate SKB and copy header for large header */
+		skb = napi_alloc_skb(rq->cq.napi,
+				     ALIGN(head_size, sizeof(long)));
+		if (unlikely(!skb)) {
+			rq->stats->buff_alloc_err++;
+			return NULL;
+		}
+
+		prefetchw(skb->data);
+		mlx5e_copy_skb_header(rq->pdev, skb, head,
+				      head_offset + rx_headroom,
+				      rx_headroom, head_size);
+		/* skb linear part was allocated with headlen and aligned to long */
+		skb->tail += head_size;
+		skb->len  += head_size;
+	}
+	return skb;
+}
+
+static void
+mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index)
+{
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+	u64 addr = shampo->info[header_index].addr;
+
+	if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) {
+		shampo->info[header_index].addr = ALIGN_DOWN(addr, PAGE_SIZE);
+		mlx5e_page_release(rq, &shampo->info[header_index], true);
+	}
+	bitmap_clear(shampo->bitmap, header_index, 1);
+}
+
+static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
+{
+	u16 data_bcnt		= mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size;
+	u16 header_index	= be16_to_cpu(cqe->shampo.header_entry_index);
+	u32 wqe_offset		= be32_to_cpu(cqe->shampo.data_offset);
+	u16 cstrides		= mpwrq_get_cqe_consumed_strides(cqe);
+	u32 data_offset		= wqe_offset & (PAGE_SIZE - 1);
+	u32 cqe_bcnt		= mpwrq_get_cqe_byte_cnt(cqe);
+	u16 wqe_id		= be16_to_cpu(cqe->wqe_id);
+	u32 page_idx		= wqe_offset >> PAGE_SHIFT;
+	struct mlx5e_rx_wqe_ll *wqe;
+	struct sk_buff *skb = NULL;
+	struct mlx5e_dma_info *di;
+	struct mlx5e_mpw_info *wi;
+	struct mlx5_wq_ll *wq;
+
+	wi = &rq->mpwqe.info[wqe_id];
+	wi->consumed_strides += cstrides;
+
+	if (unlikely(MLX5E_RX_ERR_CQE(cqe))) {
+		trigger_report(rq, cqe);
+		rq->stats->wqe_err++;
+		goto mpwrq_cqe_out;
+	}
+
+	if (unlikely(mpwrq_is_filler_cqe(cqe))) {
+		struct mlx5e_rq_stats *stats = rq->stats;
+
+		stats->mpwqe_filler_cqes++;
+		stats->mpwqe_filler_strides += cstrides;
+		goto mpwrq_cqe_out;
+	}
+
+	skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index);
+
+	if (unlikely(!skb))
+		goto free_hd_entry;
+
+	di = &wi->umr.dma_info[page_idx];
+	mlx5e_fill_skb_data(skb, rq, di, data_bcnt, data_offset);
+
+	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
+	napi_gro_receive(rq->cq.napi, skb);
+free_hd_entry:
+	mlx5e_free_rx_shampo_hd_entry(rq, header_index);
+mpwrq_cqe_out:
+	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
+		return;
+
+	wq  = &rq->mpwqe.wq;
+	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
+	mlx5e_free_rx_mpwqe(rq, wi, true);
+	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
+}
+
 static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 {
 	u16 cstrides       = mpwrq_get_cqe_consumed_strides(cqe);
@@ -1617,8 +1752,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 
 		mlx5_cqwq_pop(cqwq);
 
-		INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
-				mlx5e_handle_rx_cqe, rq, cqe);
+		INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq,
+				mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo,
+				rq, cqe);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 out:
@@ -1822,15 +1958,24 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool
 		rq->post_wqes = mlx5e_post_rx_mpwqes;
 		rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
 
-		rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe;
 		if (mlx5_fpga_is_ipsec_device(mdev)) {
 			netdev_err(netdev, "MPWQE RQ with Innova IPSec offload not supported\n");
 			return -EINVAL;
 		}
-		if (!rq->handle_rx_cqe) {
-			netdev_err(netdev, "RX handler of MPWQE RQ is not set\n");
-			return -EINVAL;
+		if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) {
+			rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe_shampo;
+			if (!rq->handle_rx_cqe) {
+				netdev_err(netdev, "RX handler of SHAMPO MPWQE RQ is not set\n");
+				return -EINVAL;
+			}
+		} else {
+			rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe;
+			if (!rq->handle_rx_cqe) {
+				netdev_err(netdev, "RX handler of MPWQE RQ is not set\n");
+				return -EINVAL;
+			}
 		}
+
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
 		rq->wqe.skb_from_cqe = xsk ?
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index c920e5932368..56bcf95d4ab7 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -800,10 +800,23 @@ struct mlx5_cqe64 {
 	u8		tls_outer_l3_tunneled;
 	u8		rsvd0;
 	__be16		wqe_id;
-	u8		lro_tcppsh_abort_dupack;
-	u8		lro_min_ttl;
-	__be16		lro_tcp_win;
-	__be32		lro_ack_seq_num;
+	union {
+		struct {
+			u8	tcppsh_abort_dupack;
+			u8	min_ttl;
+			__be16	tcp_win;
+			__be32	ack_seq_num;
+		} lro;
+		struct {
+			u8	reserved0:1;
+			u8	match:1;
+			u8	flush:1;
+			u8	reserved3:5;
+			u8	header_size;
+			__be16	header_entry_index;
+			__be32	data_offset;
+		} shampo;
+	};
 	__be32		rss_hash_result;
 	u8		rss_hash_type;
 	u8		ml_path;
@@ -873,7 +886,7 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe)
 
 static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe)
 {
-	return (cqe->lro_tcppsh_abort_dupack >> 6) & 1;
+	return (cqe->lro.tcppsh_abort_dupack >> 6) & 1;
 }
 
 static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe)
-- 
cgit v1.2.3


From 504e15724893a839213fad5eedfbd511d9ba75cc Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@nvidia.com>
Date: Sun, 11 Jul 2021 16:56:54 +0300
Subject: net/mlx5: Allow skipping counter refresh on creation

CT creates a counter for each CT rule, and for each such counter,
fs_counters tries to queue mlx5_fc_stats_work() work again via
mod_delayed_work(0) call to refresh all counters. This call has a
large performance impact when reaching high insertion rate and
accounts for ~8% of the insertion time when using software steering.

Allow skipping the refresh of all counters during counter creation.
Change CT to use this refresh skipping for it's counters.

Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Reviewed-by: Oz Shlomo <ozsh@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c    |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 14 +++++++++++---
 include/linux/mlx5/fs.h                               |  4 ++++
 3 files changed, 16 insertions(+), 4 deletions(-)

(limited to 'include/linux/mlx5')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index f44e5de25037..c1c6e74c79c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -889,7 +889,7 @@ mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv)
 		return ERR_PTR(-ENOMEM);
 
 	counter->is_shared = false;
-	counter->counter = mlx5_fc_create(ct_priv->dev, true);
+	counter->counter = mlx5_fc_create_ex(ct_priv->dev, true);
 	if (IS_ERR(counter->counter)) {
 		ct_dbg("Failed to create counter for ct entry");
 		ret = PTR_ERR(counter->counter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 60c9df1bc912..31c99d53faf7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -301,7 +301,7 @@ static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging)
 	return mlx5_fc_single_alloc(dev);
 }
 
-struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
+struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging)
 {
 	struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging);
 	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
@@ -332,8 +332,6 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
 			goto err_out_alloc;
 
 		llist_add(&counter->addlist, &fc_stats->addlist);
-
-		mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
 	}
 
 	return counter;
@@ -342,6 +340,16 @@ err_out_alloc:
 	mlx5_fc_release(dev, counter);
 	return ERR_PTR(err);
 }
+
+struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
+{
+	struct mlx5_fc *counter = mlx5_fc_create_ex(dev, aging);
+	struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+
+	if (aging)
+		mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
+	return counter;
+}
 EXPORT_SYMBOL(mlx5_fc_create);
 
 u32 mlx5_fc_id(struct mlx5_fc *counter)
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index a7e1155bc4da..cd2d4c572367 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -245,6 +245,10 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
 				 struct mlx5_flow_destination *old_dest);
 
 struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
+
+/* As mlx5_fc_create() but doesn't queue stats refresh thread. */
+struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging);
+
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
 u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
-- 
cgit v1.2.3