mlx5-updates-2019-09-01 (Software steering support)

Abstract:
 --------
 Mellanox ConnetX devices supports packet matching, packet modification and
 redirection. These functionalities are also referred to as flow-steering.
 To configure a steering rule, the rule is written to the device owned
 memory, this memory is accessed and cached by the device when processing
 a packet.
 Steering rules are constructed from multiple steering entries (STE).
 
 Rules are configured using the Firmware command interface. The Firmware
 processes the given driver command and translates them to STEs, then
 writes them to the device memory in the current steering tables.
 This process is slow due to the architecture of the command interface and
 the processing complexity of each rule.
 
 The highlight of this patchset is to cut the middle man (The firmware) and
 do steering rules programming into device directly from the driver, with
 no firmware intervention whatsoever.
 
 Motivation:
 -----------
 Software (driver managed) steering allows for high rule insertion rates
 compared to the FW steering described above, this is achieved by using
 internal RDMA writes to the device owned memory instead of the slow
 command interface to program steering rules.
 
 Software (driver managed) steering, doesn't depend on new FW
 for new steering functionality, new implementations can be done in the
 driver skipping the FW layer.
 
 Performance:
 ------------
 The insertion rate on a single core using the new approach allows
 programming ~300K rules per sec. (Done via direct raw test to the new mlx5
 sw steering layer, without any kernel layer involved).
 
 Test: TC L2 rules
 33K/s with Software steering (this patchset).
 5K/s  with FW and current driver.
 This will improve OVS based solution performance.
 
 Architecture and implementation details:
 ----------------------------------------
 Software steering will be dynamically selected via devlink device
 parameter. Example:
 $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
           pci/0000:06:00.0:
           name flow_steering_mode type driver-specific
           values:
              cmode runtime value smfs
 
 mlx5 software steering module a.k.a (DR - Direct Rule) is implemented
 and contained in mlx5/core/steering directory and controlled by
 MLX5_SW_STEERING kconfig flag.
 
 mlx5 core steering layer (fs_core) already provides a shim layer for
 implementing different steering mechanisms, software steering will
 leverage that as seen at the end of this series.
 
 When Software Steering for a specific steering domain
 (NIC/RDMA/Vport/ESwitch, etc ..) is supported, it will cause rules
 targeting this domain to be created using  SW steering instead of FW.
 
 The implementation includes:
 Domain - The steering domain is the object that all other object resides
     in. It holds the memory allocator, send engine, locks and other shared
     data needed by lower objects such as table, matcher, rule, action.
     Each domain can contain multiple tables. Domain is equivalent to
     namespaces e.g (NIC/RDMA/Vport/ESwitch, etc ..) as implemented
     currently in mlx5_core fs_core (flow steering core).
 
 Table - Table objects are used for holding multiple matchers, each table
     has a level used to prevent processing loops. Packets are being
     directed to this table once it is set as the root table, this is done
     by fs_core using a FW command. A packet is being processed inside the
     table matcher by matcher until a successful hit, otherwise the packet
     will perform the default action.
 
 Matcher - Matchers objects are used to specify the fields mask for
     matching when processing a packet. A matcher belongs to a table, each
     matcher can hold multiple rules, each rule with different matching
     values corresponding to the matcher mask. Each matcher has a priority
     used for rule processing order inside the table.
 
 Action - Action objects are created to specify different steering actions
     such as count, reformat (encapsulate, decapsulate, ...), modify
     header, forward to table and many other actions. When creating a rule
     a sequence of actions can be provided to be executed on a successful
     match.
 
 Rule - Rule objects are used to specify a specific match on packets as
     well as the actions that should be executed. A rule belongs to a
     matcher.
 
 STE - This layer is used to hold the specific STE format for the device
     and to convert the requested rule to STEs. Each rule is constructed of
     an STE chain, Multiple rules construct a steering graph. Each node in
     the graph is a hash table containing multiple STEs. The index of each
     STE in the hash table is being calculated using a CRC32 hash function.
 
 Memory pool - Used for managing and caching device owned memory for rule
     insertion. The memory is being allocated using DM (device memory) API.
 
 Communication with device - layer for standard RDMA operation using  RC QP
     to configure the device steering.
 
 Command utility - This module holds all of the FW commands that are
     required for SW steering to function.
 
 Patch planning and files:
 -------------------------
 1) First patch, adds the support to Add flow steering actions to fs_cmd
 shim layer.
 
 2) Next 12 patch will add a file per each Software steering
 functionality/module as described above. (See patches with title: DR, *)
 
 3) Add CONFIG_MLX5_SW_STEERING for software steering support and enable
 build with the new files
 
 4) Next two patches will add the support for software steering in mlx5
 steering shim layer
 net/mlx5: Add API to set the namespace steering mode
 net/mlx5: Add direct rule fs_cmd implementation
 
 5) Last two patches will add the new devlink parameter to select mlx5
 steering mode, will be valid only for switchdev mode for now.
 Two modes are supported:
     1. DMFS - Device managed flow steering
     2. SMFS - Software/Driver managed flow steering.
 
     In the DMFS mode, the HW steering entities are created through the
     FW. In the SMFS mode this entities are created though the driver
     directly.
 
     The driver will use the devlink steering mode only if the steering
     domain supports it, for now SMFS will manages only the switchdev
     eswitch steering domain.
 
     User command examples:
     - Set SMFS flow steering mode::
 
         $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
 
     - Read device flow steering mode::
 
         $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
           pci/0000:06:00.0:
           name flow_steering_mode type driver-specific
           values:
              cmode runtime value smfs
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEGhZs6bAKwk/OTgTpSD+KveBX+j4FAl1uxPAACgkQSD+KveBX
 +j5AkggAymoYqG2G+s8cLa4vQFySaD1Td3VzzWglp7PlpDBE3UcSoMAMg/gIDU1D
 8F04PeCsJ6snt1ICk56vPNyAEHWfWeBUd56+QK5lEJBuwozyFvBh6HP81Bnr6T/n
 n6uTx45ljAFQPTHJjEOLBPSzEXecLu07+mvpzSoW0F3ehfGbELhL1IkVobr/RELx
 z4xZW9uM2vm5ylheWvjf4V1S/SvokgJazW9+4fh//rl8tfXgun5IfPoS0hqKie1/
 h5sjcMSYkYR4gLVqrhKmBYHmHVl/h0TYROckW8iC/+XX7ailSo9uPG7lPa6cm+GE
 7Bajlbz4oD/K5RWoByo+q+dmyjeVhQ==
 =M9bS
 -----END PGP SIGNATURE-----

Merge tag 'mlx5-updates-2019-09-01-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-09-01  (Software steering support)

Abstract:
--------
Mellanox ConnetX devices supports packet matching, packet modification and
redirection. These functionalities are also referred to as flow-steering.
To configure a steering rule, the rule is written to the device owned
memory, this memory is accessed and cached by the device when processing
a packet.
Steering rules are constructed from multiple steering entries (STE).

Rules are configured using the Firmware command interface. The Firmware
processes the given driver command and translates them to STEs, then
writes them to the device memory in the current steering tables.
This process is slow due to the architecture of the command interface and
the processing complexity of each rule.

The highlight of this patchset is to cut the middle man (The firmware) and
do steering rules programming into device directly from the driver, with
no firmware intervention whatsoever.

Motivation:
-----------
Software (driver managed) steering allows for high rule insertion rates
compared to the FW steering described above, this is achieved by using
internal RDMA writes to the device owned memory instead of the slow
command interface to program steering rules.

Software (driver managed) steering, doesn't depend on new FW
for new steering functionality, new implementations can be done in the
driver skipping the FW layer.

Performance:
------------
The insertion rate on a single core using the new approach allows
programming ~300K rules per sec. (Done via direct raw test to the new mlx5
sw steering layer, without any kernel layer involved).

Test: TC L2 rules
33K/s with Software steering (this patchset).
5K/s  with FW and current driver.
This will improve OVS based solution performance.

Architecture and implementation details:
----------------------------------------
Software steering will be dynamically selected via devlink device
parameter. Example:
$ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
          pci/0000:06:00.0:
          name flow_steering_mode type driver-specific
          values:
             cmode runtime value smfs

mlx5 software steering module a.k.a (DR - Direct Rule) is implemented
and contained in mlx5/core/steering directory and controlled by
MLX5_SW_STEERING kconfig flag.

mlx5 core steering layer (fs_core) already provides a shim layer for
implementing different steering mechanisms, software steering will
leverage that as seen at the end of this series.

When Software Steering for a specific steering domain
(NIC/RDMA/Vport/ESwitch, etc ..) is supported, it will cause rules
targeting this domain to be created using  SW steering instead of FW.

The implementation includes:
Domain - The steering domain is the object that all other object resides
    in. It holds the memory allocator, send engine, locks and other shared
    data needed by lower objects such as table, matcher, rule, action.
    Each domain can contain multiple tables. Domain is equivalent to
    namespaces e.g (NIC/RDMA/Vport/ESwitch, etc ..) as implemented
    currently in mlx5_core fs_core (flow steering core).

Table - Table objects are used for holding multiple matchers, each table
    has a level used to prevent processing loops. Packets are being
    directed to this table once it is set as the root table, this is done
    by fs_core using a FW command. A packet is being processed inside the
    table matcher by matcher until a successful hit, otherwise the packet
    will perform the default action.

Matcher - Matchers objects are used to specify the fields mask for
    matching when processing a packet. A matcher belongs to a table, each
    matcher can hold multiple rules, each rule with different matching
    values corresponding to the matcher mask. Each matcher has a priority
    used for rule processing order inside the table.

Action - Action objects are created to specify different steering actions
    such as count, reformat (encapsulate, decapsulate, ...), modify
    header, forward to table and many other actions. When creating a rule
    a sequence of actions can be provided to be executed on a successful
    match.

Rule - Rule objects are used to specify a specific match on packets as
    well as the actions that should be executed. A rule belongs to a
    matcher.

STE - This layer is used to hold the specific STE format for the device
    and to convert the requested rule to STEs. Each rule is constructed of
    an STE chain, Multiple rules construct a steering graph. Each node in
    the graph is a hash table containing multiple STEs. The index of each
    STE in the hash table is being calculated using a CRC32 hash function.

Memory pool - Used for managing and caching device owned memory for rule
    insertion. The memory is being allocated using DM (device memory) API.

Communication with device - layer for standard RDMA operation using  RC QP
    to configure the device steering.

Command utility - This module holds all of the FW commands that are
    required for SW steering to function.

Patch planning and files:
-------------------------
1) First patch, adds the support to Add flow steering actions to fs_cmd
shim layer.

2) Next 12 patch will add a file per each Software steering
functionality/module as described above. (See patches with title: DR, *)

3) Add CONFIG_MLX5_SW_STEERING for software steering support and enable
build with the new files

4) Next two patches will add the support for software steering in mlx5
steering shim layer
net/mlx5: Add API to set the namespace steering mode
net/mlx5: Add direct rule fs_cmd implementation

5) Last two patches will add the new devlink parameter to select mlx5
steering mode, will be valid only for switchdev mode for now.
Two modes are supported:
    1. DMFS - Device managed flow steering
    2. SMFS - Software/Driver managed flow steering.

    In the DMFS mode, the HW steering entities are created through the
    FW. In the SMFS mode this entities are created though the driver
    directly.

    The driver will use the devlink steering mode only if the steering
    domain supports it, for now SMFS will manages only the switchdev
    eswitch steering domain.

    User command examples:
    - Set SMFS flow steering mode::

        $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime

    - Read device flow steering mode::

        $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
          pci/0000:06:00.0:
          name flow_steering_mode type driver-specific
          values:
             cmode runtime value smfs
====================

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

Documentation/networking/device_drivers/mellanox/mlx5.rst

@@ -11,6 +11,7 @@ Contents
 
 - `Enabling the driver and kconfig options`_
 - `Devlink info`_
+- `Devlink parameters`_
 - `Devlink health reporters`_
 - `mlx5 tracepoints`_
 
@@ -122,6 +123,38 @@ User command example::
          stored:
             fw.version 16.26.0100
 
+Devlink parameters
+==================
+
+flow_steering_mode: Device flow steering mode
+---------------------------------------------
+The flow steering mode parameter controls the flow steering mode of the driver.
+Two modes are supported:
+1. 'dmfs' - Device managed flow steering.
+2. 'smfs  - Software/Driver managed flow steering.
+
+In DMFS mode, the HW steering entities are created and managed through the
+Firmware.
+In SMFS mode, the HW steering entities are created and managed though by
+the driver directly into Hardware without firmware intervention.
+
+SMFS mode is faster and provides better rule inserstion rate compared to default DMFS mode.
+
+User command examples:
+
+- Set SMFS flow steering mode::
+
+    $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime
+
+- Read device flow steering mode::
+
+    $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode
+      pci/0000:06:00.0:
+      name flow_steering_mode type driver-specific
+      values:
+         cmode runtime value smfs
+
+
 Devlink health reporters
 ========================
 

drivers/infiniband/hw/mlx5/cmd.c

@@ -186,136 +186,6 @@ int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length)
 	return err;
 }
 
-int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
-			  u16 uid, phys_addr_t *addr, u32 *obj_id)
-{
-	struct mlx5_core_dev *dev = dm->dev;
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
-	u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {};
-	unsigned long *block_map;
-	u64 icm_start_addr;
-	u32 log_icm_size;
-	u32 num_blocks;
-	u32 max_blocks;
-	u64 block_idx;
-	void *sw_icm;
-	int ret;
-
-	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
-		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM);
-	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
-
-	switch (type) {
-	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
-		icm_start_addr = MLX5_CAP64_DEV_MEM(dev,
-						steering_sw_icm_start_address);
-		log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size);
-		block_map = dm->steering_sw_icm_alloc_blocks;
-		break;
-	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
-		icm_start_addr = MLX5_CAP64_DEV_MEM(dev,
-					header_modify_sw_icm_start_address);
-		log_icm_size = MLX5_CAP_DEV_MEM(dev,
-						log_header_modify_sw_icm_size);
-		block_map = dm->header_modify_sw_icm_alloc_blocks;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >>
-		     MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
-	max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
-	spin_lock(&dm->lock);
-	block_idx = bitmap_find_next_zero_area(block_map,
-					       max_blocks,
-					       0,
-					       num_blocks, 0);
-
-	if (block_idx < max_blocks)
-		bitmap_set(block_map,
-			   block_idx, num_blocks);
-
-	spin_unlock(&dm->lock);
-
-	if (block_idx >= max_blocks)
-		return -ENOMEM;
-
-	sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm);
-	icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
-	MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr,
-		   icm_start_addr);
-	MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length));
-
-	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (ret) {
-		spin_lock(&dm->lock);
-		bitmap_clear(block_map,
-			     block_idx, num_blocks);
-		spin_unlock(&dm->lock);
-
-		return ret;
-	}
-
-	*addr = icm_start_addr;
-	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
-
-	return 0;
-}
-
-int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
-			    u16 uid, phys_addr_t addr, u32 obj_id)
-{
-	struct mlx5_core_dev *dev = dm->dev;
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
-	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
-	unsigned long *block_map;
-	u32 num_blocks;
-	u64 start_idx;
-	int err;
-
-	num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >>
-		     MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
-
-	switch (type) {
-	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
-		start_idx =
-			(addr - MLX5_CAP64_DEV_MEM(
-					dev, steering_sw_icm_start_address)) >>
-			MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
-		block_map = dm->steering_sw_icm_alloc_blocks;
-		break;
-	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
-		start_idx =
-			(addr -
-			 MLX5_CAP64_DEV_MEM(
-				 dev, header_modify_sw_icm_start_address)) >>
-			MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
-		block_map = dm->header_modify_sw_icm_alloc_blocks;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	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_SW_ICM);
-	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id);
-	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
-
-	err =  mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-	if (err)
-		return err;
-
-	spin_lock(&dm->lock);
-	bitmap_clear(block_map,
-		     start_idx, num_blocks);
-	spin_unlock(&dm->lock);
-
-	return 0;
-}
-
 int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out)
 {
 	u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {};

drivers/infiniband/hw/mlx5/cmd.h

@@ -65,8 +65,4 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
 			     u16 uid);
 int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		     u16 opmod, u8 port);
-int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
-			  u16 uid, phys_addr_t *addr, u32 *obj_id);
-int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
-			    u16 uid, phys_addr_t addr, u32 obj_id);
 #endif /* MLX5_IB_CMD_H */

drivers/infiniband/hw/mlx5/flow.c

@@ -322,11 +322,11 @@ void mlx5_ib_destroy_flow_action_raw(struct mlx5_ib_flow_action *maction)
 	switch (maction->flow_action_raw.sub_type) {
 	case MLX5_IB_FLOW_ACTION_MODIFY_HEADER:
 		mlx5_modify_header_dealloc(maction->flow_action_raw.dev->mdev,
-					   maction->flow_action_raw.action_id);
+					   maction->flow_action_raw.modify_hdr);
 		break;
 	case MLX5_IB_FLOW_ACTION_PACKET_REFORMAT:
 		mlx5_packet_reformat_dealloc(maction->flow_action_raw.dev->mdev,
-			maction->flow_action_raw.action_id);
+					     maction->flow_action_raw.pkt_reformat);
 		break;
 	case MLX5_IB_FLOW_ACTION_DECAP:
 		break;
@@ -352,10 +352,11 @@ mlx5_ib_create_modify_header(struct mlx5_ib_dev *dev,
 	if (!maction)
 		return ERR_PTR(-ENOMEM);
 
-	ret = mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in,
+	maction->flow_action_raw.modify_hdr =
-				       &maction->flow_action_raw.action_id);
+		mlx5_modify_header_alloc(dev->mdev, namespace, num_actions, in);
 
-	if (ret) {
+	if (IS_ERR(maction->flow_action_raw.modify_hdr)) {
+		ret = PTR_ERR(maction->flow_action_raw.modify_hdr);
 		kfree(maction);
 		return ERR_PTR(ret);
 	}
@@ -479,11 +480,13 @@ static int mlx5_ib_flow_action_create_packet_reformat_ctx(
 	if (ret)
 		return ret;
 
-	ret = mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
+	maction->flow_action_raw.pkt_reformat =
-					 in, namespace,
+		mlx5_packet_reformat_alloc(dev->mdev, prm_prt, len,
-					 &maction->flow_action_raw.action_id);
+					   in, namespace);
-	if (ret)
+	if (IS_ERR(maction->flow_action_raw.pkt_reformat)) {
+		ret = PTR_ERR(maction->flow_action_raw.pkt_reformat);
 		return ret;
+	}
 
 	maction->flow_action_raw.sub_type =
 		MLX5_IB_FLOW_ACTION_PACKET_REFORMAT;

drivers/infiniband/hw/mlx5/main.c

@@ -2280,6 +2280,7 @@ static inline int check_dm_type_support(struct mlx5_ib_dev *dev,
 			return -EOPNOTSUPP;
 		break;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
 		if (!capable(CAP_SYS_RAWIO) ||
 		    !capable(CAP_NET_RAW))
 			return -EPERM;
@@ -2344,18 +2345,18 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
 				  struct uverbs_attr_bundle *attrs,
 				  int type)
 {
-	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
+	struct mlx5_core_dev *dev = to_mdev(ctx->device)->mdev;
 	u64 act_size;
 	int err;
 
 	/* Allocation size must a multiple of the basic block size
 	 * and a power of 2.
 	 */
-	act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev));
+	act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dev));
 	act_size = roundup_pow_of_two(act_size);
 
 	dm->size = act_size;
-	err = mlx5_cmd_alloc_sw_icm(dm_db, type, act_size,
+	err = mlx5_dm_sw_icm_alloc(dev, type, act_size,
 				   to_mucontext(ctx)->devx_uid, &dm->dev_addr,
 				   &dm->icm_dm.obj_id);
 	if (err)
@@ -2365,9 +2366,9 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
 			     &dm->dev_addr, sizeof(dm->dev_addr));
 	if (err)
-		mlx5_cmd_dealloc_sw_icm(dm_db, type, dm->size,
+		mlx5_dm_sw_icm_dealloc(dev, type, dm->size,
-					to_mucontext(ctx)->devx_uid,
+				       to_mucontext(ctx)->devx_uid, dm->dev_addr,
-					dm->dev_addr, dm->icm_dm.obj_id);
+				       dm->icm_dm.obj_id);
 
 	return err;
 }
@@ -2407,8 +2408,14 @@ struct ib_dm *mlx5_ib_alloc_dm(struct ib_device *ibdev,
 					    attrs);
 		break;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		err = handle_alloc_dm_sw_icm(context, dm,
+					     attr, attrs,
+					     MLX5_SW_ICM_TYPE_STEERING);
+		break;
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
-		err = handle_alloc_dm_sw_icm(context, dm, attr, attrs, type);
+		err = handle_alloc_dm_sw_icm(context, dm,
+					     attr, attrs,
+					     MLX5_SW_ICM_TYPE_HEADER_MODIFY);
 		break;
 	default:
 		err = -EOPNOTSUPP;
@@ -2428,6 +2435,7 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 {
 	struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context(
 		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
+	struct mlx5_core_dev *dev = to_mdev(ibdm->device)->mdev;
 	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
 	u32 page_idx;
@@ -2439,18 +2447,22 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 		if (ret)
 			return ret;
 
-		page_idx = (dm->dev_addr -
+		page_idx = (dm->dev_addr - pci_resource_start(dev->pdev, 0) -
-			    pci_resource_start(dm_db->dev->pdev, 0) -
+			    MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr)) >>
-			    MLX5_CAP64_DEV_MEM(dm_db->dev,
-					       memic_bar_start_addr)) >>
 			    PAGE_SHIFT;
 		bitmap_clear(ctx->dm_pages, page_idx,
 			     DIV_ROUND_UP(dm->size, PAGE_SIZE));
 		break;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
+		ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_STEERING,
+					     dm->size, ctx->devx_uid, dm->dev_addr,
+					     dm->icm_dm.obj_id);
+		if (ret)
+			return ret;
+		break;
 	case MLX5_IB_UAPI_DM_TYPE_HEADER_MODIFY_SW_ICM:
-		ret = mlx5_cmd_dealloc_sw_icm(dm_db, dm->type, dm->size,
+		ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_HEADER_MODIFY,
-					      ctx->devx_uid, dm->dev_addr,
+					     dm->size, ctx->devx_uid, dm->dev_addr,
 					     dm->icm_dm.obj_id);
 		if (ret)
 			return ret;
@@ -2646,7 +2658,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 			if (action->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 				return -EINVAL;
 			action->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			action->modify_id = maction->flow_action_raw.action_id;
+			action->modify_hdr =
+				maction->flow_action_raw.modify_hdr;
 			return 0;
 		}
 		if (maction->flow_action_raw.sub_type ==
@@ -2663,8 +2676,8 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 				return -EINVAL;
 			action->action |=
 				MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-			action->reformat_id =
+			action->pkt_reformat =
-				maction->flow_action_raw.action_id;
+				maction->flow_action_raw.pkt_reformat;
 			return 0;
 		}
 		/* fall through */
@@ -6096,8 +6109,6 @@ static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device,
 
 static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 {
-	struct mlx5_core_dev *mdev = dev->mdev;
-
 	mlx5_ib_cleanup_multiport_master(dev);
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		srcu_barrier(&dev->mr_srcu);
@@ -6105,29 +6116,11 @@ static void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 	}
 
 	WARN_ON(!bitmap_empty(dev->dm.memic_alloc_pages, MLX5_MAX_MEMIC_PAGES));
-
-	WARN_ON(dev->dm.steering_sw_icm_alloc_blocks &&
-		!bitmap_empty(
-			dev->dm.steering_sw_icm_alloc_blocks,
-			BIT(MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size) -
-			    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
-
-	kfree(dev->dm.steering_sw_icm_alloc_blocks);
-
-	WARN_ON(dev->dm.header_modify_sw_icm_alloc_blocks &&
-		!bitmap_empty(dev->dm.header_modify_sw_icm_alloc_blocks,
-			      BIT(MLX5_CAP_DEV_MEM(
-					  mdev, log_header_modify_sw_icm_size) -
-				  MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev))));
-
-	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
 }
 
 static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_core_dev *mdev = dev->mdev;
-	u64 header_modify_icm_blocks = 0;
-	u64 steering_icm_blocks = 0;
 	int err;
 	int i;
 
@@ -6174,51 +6167,17 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	INIT_LIST_HEAD(&dev->qp_list);
 	spin_lock_init(&dev->reset_flow_resource_lock);
 
-	if (MLX5_CAP_GEN_64(mdev, general_obj_types) &
-	    MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM) {
-		if (MLX5_CAP64_DEV_MEM(mdev, steering_sw_icm_start_address)) {
-			steering_icm_blocks =
-				BIT(MLX5_CAP_DEV_MEM(mdev,
-						     log_steering_sw_icm_size) -
-				    MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
-
-			dev->dm.steering_sw_icm_alloc_blocks =
-				kcalloc(BITS_TO_LONGS(steering_icm_blocks),
-					sizeof(unsigned long), GFP_KERNEL);
-			if (!dev->dm.steering_sw_icm_alloc_blocks)
-				goto err_mp;
-		}
-
-		if (MLX5_CAP64_DEV_MEM(mdev,
-				       header_modify_sw_icm_start_address)) {
-			header_modify_icm_blocks = BIT(
-				MLX5_CAP_DEV_MEM(
-					mdev, log_header_modify_sw_icm_size) -
-				MLX5_LOG_SW_ICM_BLOCK_SIZE(mdev));
-
-			dev->dm.header_modify_sw_icm_alloc_blocks =
-				kcalloc(BITS_TO_LONGS(header_modify_icm_blocks),
-					sizeof(unsigned long), GFP_KERNEL);
-			if (!dev->dm.header_modify_sw_icm_alloc_blocks)
-				goto err_dm;
-		}
-	}
-
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
 		err = init_srcu_struct(&dev->mr_srcu);
 		if (err)
-			goto err_dm;
+			goto err_mp;
 	}
 
 	return 0;
 
-err_dm:
-	kfree(dev->dm.steering_sw_icm_alloc_blocks);
-	kfree(dev->dm.header_modify_sw_icm_alloc_blocks);
-
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -868,7 +868,10 @@ struct mlx5_ib_flow_action {
 		struct {
 			struct mlx5_ib_dev *dev;
 			u32 sub_type;
-			u32 action_id;
+			union {
+				struct mlx5_modify_hdr *modify_hdr;
+				struct mlx5_pkt_reformat *pkt_reformat;
+			};
 		} flow_action_raw;
 	};
 };
@@ -881,8 +884,6 @@ struct mlx5_dm {
 	 */
 	spinlock_t lock;
 	DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES);
-	unsigned long *steering_sw_icm_alloc_blocks;
-	unsigned long *header_modify_sw_icm_alloc_blocks;
 };
 
 struct mlx5_read_counters_attr {

drivers/net/ethernet/mellanox/mlx5/core/Kconfig

@@ -154,3 +154,10 @@ config MLX5_EN_TLS
 	Build support for TLS cryptography-offload accelaration in the NIC.
 	Note: Support for hardware with this capability needs to be selected
 	for this option to become available.
+
+config MLX5_SW_STEERING
+	bool "Mellanox Technologies software-managed steering"
+	depends on MLX5_CORE_EN && MLX5_ESWITCH
+	default y
+	help
+	Build support for software-managed steering in the NIC.

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -15,7 +15,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
 		transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \
 		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
-		lib/devcom.o lib/pci_vsc.o diag/fs_tracepoint.o \
+		lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \
 		diag/fw_tracer.o diag/crdump.o devlink.o
 
 #
@@ -67,3 +67,10 @@ mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
 
 mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o \
 				   en_accel/ktls.o en_accel/ktls_tx.o
+
+mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \
+					steering/dr_matcher.o steering/dr_rule.o \
+					steering/dr_icm_pool.o steering/dr_crc32.o \
+					steering/dr_ste.o steering/dr_send.o \
+					steering/dr_cmd.o steering/dr_fw.o \
+					steering/dr_action.o steering/fs_dr.o

drivers/net/ethernet/mellanox/mlx5/core/devlink.c

@@ -4,6 +4,7 @@
 #include <devlink.h>
 
 #include "mlx5_core.h"
+#include "fs_core.h"
 #include "eswitch.h"
 
 static int mlx5_devlink_flash_update(struct devlink *devlink,
@@ -107,12 +108,121 @@ void mlx5_devlink_free(struct devlink *devlink)
 	devlink_free(devlink);
 }
 
+static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id,
+					 union devlink_param_value val,
+					 struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	char *value = val.vstr;
+	int err = 0;
+
+	if (!strcmp(value, "dmfs")) {
+		return 0;
+	} else if (!strcmp(value, "smfs")) {
+		u8 eswitch_mode;
+		bool smfs_cap;
+
+		eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch);
+		smfs_cap = mlx5_fs_dr_is_supported(dev);
+
+		if (!smfs_cap) {
+			err = -EOPNOTSUPP;
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Software managed steering is not supported by current device");
+		}
+
+		else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Software managed steering is not supported when eswitch offlaods enabled.");
+			err = -EOPNOTSUPP;
+		}
+	} else {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Bad parameter: supported values are [\"dmfs\", \"smfs\"]");
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int mlx5_devlink_fs_mode_set(struct devlink *devlink, u32 id,
+				    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	enum mlx5_flow_steering_mode mode;
+
+	if (!strcmp(ctx->val.vstr, "smfs"))
+		mode = MLX5_FLOW_STEERING_MODE_SMFS;
+	else
+		mode = MLX5_FLOW_STEERING_MODE_DMFS;
+	dev->priv.steering->mode = mode;
+
+	return 0;
+}
+
+static int mlx5_devlink_fs_mode_get(struct devlink *devlink, u32 id,
+				    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS)
+		strcpy(ctx->val.vstr, "smfs");
+	else
+		strcpy(ctx->val.vstr, "dmfs");
+	return 0;
+}
+
+enum mlx5_devlink_param_id {
+	MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+};
+
+static const struct devlink_param mlx5_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+			     "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set,
+			     mlx5_devlink_fs_mode_validate),
+};
+
+static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	union devlink_param_value value;
+
+	if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS)
+		strcpy(value.vstr, "dmfs");
+	else
+		strcpy(value.vstr, "smfs");
+	devlink_param_driverinit_value_set(devlink,
+					   MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
+					   value);
+}
+
 int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 {
-	return devlink_register(devlink, dev);
+	int err;
+
+	err = devlink_register(devlink, dev);
+	if (err)
+		return err;
+
+	err = devlink_params_register(devlink, mlx5_devlink_params,
+				      ARRAY_SIZE(mlx5_devlink_params));
+	if (err)
+		goto params_reg_err;
+	mlx5_devlink_set_params_init_values(devlink);
+	devlink_params_publish(devlink);
+	return 0;
+
+params_reg_err:
+	devlink_unregister(devlink);
+	return err;
 }
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
+	devlink_params_unregister(devlink, mlx5_devlink_params,
+				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
 }

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c

@@ -291,14 +291,14 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 		 */
 		goto out;
 	}
-
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
-	err = mlx5_packet_reformat_alloc(priv->mdev,
 						     e->reformat_type,
 						     ipv4_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
+						     MLX5_FLOW_NAMESPACE_FDB);
-					 &e->encap_id);
+	if (IS_ERR(e->pkt_reformat)) {
-	if (err)
+		err = PTR_ERR(e->pkt_reformat);
 		goto destroy_neigh_entry;
+	}
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
@@ -407,13 +407,14 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5_packet_reformat_alloc(priv->mdev,
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
 						     e->reformat_type,
 						     ipv6_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
+						     MLX5_FLOW_NAMESPACE_FDB);
-					 &e->encap_id);
+	if (IS_ERR(e->pkt_reformat)) {
-	if (err)
+		err = PTR_ERR(e->pkt_reformat);
 		goto destroy_neigh_entry;
+	}
 
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));

drivers/net/ethernet/mellanox/mlx5/core/en_rep.h

@@ -161,7 +161,7 @@ struct mlx5e_encap_entry {
 	 */
 	struct hlist_node encap_hlist;
 	struct list_head flows;
-	u32 encap_id;
+	struct mlx5_pkt_reformat *pkt_reformat;
 	const struct ip_tunnel_info *tun_info;
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -61,7 +61,7 @@
 struct mlx5_nic_flow_attr {
 	u32 action;
 	u32 flow_tag;
-	u32 mod_hdr_id;
+	struct mlx5_modify_hdr *modify_hdr;
 	u32 hairpin_tirn;
 	u8 match_level;
 	struct mlx5_flow_table	*hairpin_ft;
@@ -201,7 +201,7 @@ struct mlx5e_mod_hdr_entry {
 
 	struct mod_hdr_key key;
 
-	u32 mod_hdr_id;
+	struct mlx5_modify_hdr *modify_hdr;
 
 	refcount_t refcnt;
 	struct completion res_ready;
@@ -334,7 +334,7 @@ static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv,
 
 	WARN_ON(!list_empty(&mh->flows));
 	if (mh->compl_result > 0)
-		mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id);
+		mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr);
 
 	kfree(mh);
 }
@@ -395,11 +395,11 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv,
 	hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key);
 	mutex_unlock(&tbl->lock);
 
-	err = mlx5_modify_header_alloc(priv->mdev, namespace,
+	mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace,
 						  mh->key.num_actions,
-				       mh->key.actions,
+						  mh->key.actions);
-				       &mh->mod_hdr_id);
+	if (IS_ERR(mh->modify_hdr)) {
-	if (err) {
+		err = PTR_ERR(mh->modify_hdr);
 		mh->compl_result = err;
 		goto alloc_header_err;
 	}
@@ -412,9 +412,9 @@ attach_flow:
 	list_add(&flow->mod_hdr, &mh->flows);
 	spin_unlock(&mh->flows_lock);
 	if (mlx5e_is_eswitch_flow(flow))
-		flow->esw_attr->mod_hdr_id = mh->mod_hdr_id;
+		flow->esw_attr->modify_hdr = mh->modify_hdr;
 	else
-		flow->nic_attr->mod_hdr_id = mh->mod_hdr_id;
+		flow->nic_attr->modify_hdr = mh->modify_hdr;
 
 	return 0;
 
@@ -906,7 +906,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 	struct mlx5_flow_destination dest[2] = {};
 	struct mlx5_flow_act flow_act = {
 		.action = attr->action,
-		.reformat_id = 0,
 		.flags    = FLOW_ACT_NO_APPEND,
 	};
 	struct mlx5_fc *counter = NULL;
@@ -947,7 +946,7 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) {
 		err = mlx5e_attach_mod_hdr(priv, flow, parse_attr);
-		flow_act.modify_id = attr->mod_hdr_id;
+		flow_act.modify_hdr = attr->modify_hdr;
 		kfree(parse_attr->mod_hdr_actions);
 		if (err)
 			return err;
@@ -1304,14 +1303,13 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	err = mlx5_packet_reformat_alloc(priv->mdev,
+	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
 						     e->reformat_type,
 						     e->encap_size, e->encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
+						     MLX5_FLOW_NAMESPACE_FDB);
-					 &e->encap_id);
+	if (IS_ERR(e->pkt_reformat)) {
-	if (err) {
+		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n",
-		mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n",
+			       PTR_ERR(e->pkt_reformat));
-			       err);
 		return;
 	}
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
@@ -1326,7 +1324,7 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 		esw_attr = flow->esw_attr;
 		spec = &esw_attr->parse_attr->spec;
 
-		esw_attr->dests[flow->tmp_efi_index].encap_id = e->encap_id;
+		esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat;
 		esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
 		/* Flow can be associated with multiple encap entries.
 		 * Before offloading the flow verify that all of them have
@@ -1395,7 +1393,7 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 
 	/* we know that the encap is valid */
 	e->flags &= ~MLX5_ENCAP_ENTRY_VALID;
-	mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+	mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
 }
 
 static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow)
@@ -1561,7 +1559,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr
 		mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 
 		if (e->flags & MLX5_ENCAP_ENTRY_VALID)
-			mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id);
+			mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
 	}
 
 	kfree(e->encap_header);
@@ -1896,7 +1894,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			*match_level = MLX5_MATCH_L2;
 		}
 	} else if (*match_level != MLX5_MATCH_NONE) {
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1);
+		/* cvlan_tag enabled in match criteria and
+		 * disabled in match value means both S & C tags
+		 * don't exist (untagged of both)
+		 */
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
 		*match_level = MLX5_MATCH_L2;
 	}
@@ -3045,7 +3046,7 @@ attach_flow:
 	flow->encaps[out_index].index = out_index;
 	*encap_dev = e->out_dev;
 	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
-		attr->dests[out_index].encap_id = e->encap_id;
+		attr->dests[out_index].pkt_reformat = e->pkt_reformat;
 		attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
 		*encap_valid = true;
 	} else {

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -69,7 +69,7 @@ struct vport_ingress {
 	struct mlx5_flow_group *allow_spoofchk_only_grp;
 	struct mlx5_flow_group *allow_untagged_only_grp;
 	struct mlx5_flow_group *drop_grp;
-	int modify_metadata_id;
+	struct mlx5_modify_hdr   *modify_metadata;
 	struct mlx5_flow_handle  *modify_metadata_rule;
 	struct mlx5_flow_handle  *allow_rule;
 	struct mlx5_flow_handle  *drop_rule;
@@ -153,6 +153,7 @@ struct mlx5_eswitch_fdb {
 		} legacy;
 
 		struct offloads_fdb {
+			struct mlx5_flow_namespace *ns;
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
 			struct mlx5_flow_group *peer_miss_grp;
@@ -385,11 +386,11 @@ struct mlx5_esw_flow_attr {
 	struct {
 		u32 flags;
 		struct mlx5_eswitch_rep *rep;
+		struct mlx5_pkt_reformat *pkt_reformat;
 		struct mlx5_core_dev *mdev;
-		u32 encap_id;
 		struct mlx5_termtbl_handle *termtbl;
 	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
-	u32	mod_hdr_id;
+	struct  mlx5_modify_hdr *modify_hdr;
 	u8	inner_match_level;
 	u8	outer_match_level;
 	struct mlx5_fc *counter;

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -190,10 +190,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 						MLX5_FLOW_DEST_VPORT_VHCA_ID;
 				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
 					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
-					flow_act.reformat_id = attr->dests[j].encap_id;
+					flow_act.pkt_reformat = attr->dests[j].pkt_reformat;
 					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-					dest[i].vport.reformat_id =
+					dest[i].vport.pkt_reformat =
-						attr->dests[j].encap_id;
+						attr->dests[j].pkt_reformat;
 				}
 				i++;
 			}
@@ -213,7 +213,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
-		flow_act.modify_id = attr->mod_hdr_id;
+		flow_act.modify_hdr = attr->modify_hdr;
 
 	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
 	if (IS_ERR(fdb)) {
@@ -276,7 +276,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
 			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
-			dest[i].vport.reformat_id = attr->dests[i].encap_id;
+			dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat;
 		}
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
@@ -1068,6 +1068,13 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		err = -EOPNOTSUPP;
 		goto ns_err;
 	}
+	esw->fdb_table.offloads.ns = root_ns;
+	err = mlx5_flow_namespace_set_mode(root_ns,
+					   esw->dev->priv.steering->mode);
+	if (err) {
+		esw_warn(dev, "Failed to set FDB namespace steering mode\n");
+		goto ns_err;
+	}
 
 	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
 			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
@@ -1207,6 +1214,8 @@ send_vport_err:
 	esw_destroy_offloads_fast_fdb_tables(esw);
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 slow_fdb_err:
+	/* Holds true only as long as DMFS is the default */
+	mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS);
 ns_err:
 	kvfree(flow_group_in);
 	return err;
@@ -1226,6 +1235,9 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	esw_destroy_offloads_fast_fdb_tables(esw);
+	/* Holds true only as long as DMFS is the default */
+	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
+				     MLX5_FLOW_STEERING_MODE_DMFS);
 }
 
 static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
@@ -1623,13 +1635,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 	esw_del_fdb_peer_miss_rules(esw);
 }
 
+static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
+					 struct mlx5_eswitch *peer_esw,
+					 bool pair)
+{
+	struct mlx5_flow_root_namespace *peer_ns;
+	struct mlx5_flow_root_namespace *ns;
+	int err;
+
+	peer_ns = peer_esw->dev->priv.steering->fdb_root_ns;
+	ns = esw->dev->priv.steering->fdb_root_ns;
+
+	if (pair) {
+		err = mlx5_flow_namespace_set_peer(ns, peer_ns);
+		if (err)
+			return err;
+
+		mlx5_flow_namespace_set_peer(peer_ns, ns);
+		if (err) {
+			mlx5_flow_namespace_set_peer(ns, NULL);
+			return err;
+		}
+	} else {
+		mlx5_flow_namespace_set_peer(ns, NULL);
+		mlx5_flow_namespace_set_peer(peer_ns, NULL);
+	}
+
+	return 0;
+}
+
 static int mlx5_esw_offloads_devcom_event(int event,
 					  void *my_data,
 					  void *event_data)
 {
 	struct mlx5_eswitch *esw = my_data;
-	struct mlx5_eswitch *peer_esw = event_data;
 	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+	struct mlx5_eswitch *peer_esw = event_data;
 	int err;
 
 	switch (event) {
@@ -1638,9 +1679,12 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		    mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
 			break;
 
-		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true);
 		if (err)
 			goto err_out;
+		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		if (err)
+			goto err_peer;
 
 		err = mlx5_esw_offloads_pair(peer_esw, esw);
 		if (err)
@@ -1656,6 +1700,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
 		mlx5_esw_offloads_unpair(peer_esw);
 		mlx5_esw_offloads_unpair(esw);
+		mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
 		break;
 	}
 
@@ -1663,7 +1708,8 @@ static int mlx5_esw_offloads_devcom_event(int event,
 
 err_pair:
 	mlx5_esw_offloads_unpair(esw);
-
+err_peer:
+	mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
 err_out:
 	mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
 		      event, err);
@@ -1734,7 +1780,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
 
 	if (vport->ingress.modify_metadata_rule) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-		flow_act.modify_id = vport->ingress.modify_metadata_id;
+		flow_act.modify_hdr = vport->ingress.modify_metadata;
 	}
 
 	vport->ingress.allow_rule =
@@ -1770,9 +1816,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 	MLX5_SET(set_action_in, action, data,
 		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
 
-	err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+	vport->ingress.modify_metadata =
-				       1, action, &vport->ingress.modify_metadata_id);
+		mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-	if (err) {
+					 1, action);
+	if (IS_ERR(vport->ingress.modify_metadata)) {
+		err = PTR_ERR(vport->ingress.modify_metadata);
 		esw_warn(esw->dev,
 			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
 			 vport->vport, err);
@@ -1780,7 +1828,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	flow_act.modify_id = vport->ingress.modify_metadata_id;
+	flow_act.modify_hdr = vport->ingress.modify_metadata;
 	vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
 								  &spec, &flow_act, NULL, 0);
 	if (IS_ERR(vport->ingress.modify_metadata_rule)) {
@@ -1794,7 +1842,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 
 out:
 	if (err)
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
 	return err;
 }
 
@@ -1803,7 +1851,7 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 {
 	if (vport->ingress.modify_metadata_rule) {
 		mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
 
 		vport->ingress.modify_metadata_rule = NULL;
 	}
@@ -2113,9 +2161,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	else
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
+	mlx5_rdma_enable_roce(esw->dev);
 	err = esw_offloads_steering_init(esw);
 	if (err)
-		return err;
+		goto err_steering_init;
 
 	err = esw_set_passing_vport_metadata(esw, true);
 	if (err)
@@ -2130,8 +2179,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	esw_offloads_devcom_init(esw);
 	mutex_init(&esw->offloads.termtbl_mutex);
 
-	mlx5_rdma_enable_roce(esw->dev);
-
 	return 0;
 
 err_reps:
@@ -2139,6 +2186,8 @@ err_reps:
 	esw_set_passing_vport_metadata(esw, false);
 err_vport_metadata:
 	esw_offloads_steering_cleanup(esw);
+err_steering_init:
+	mlx5_rdma_disable_roce(esw->dev);
 	return err;
 }
 
@@ -2163,12 +2212,12 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 
 void esw_offloads_disable(struct mlx5_eswitch *esw)
 {
-	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw);
 	mlx5_eswitch_disable_pf_vf_vports(esw);
 	esw_set_passing_vport_metadata(esw, false);
 	esw_offloads_steering_cleanup(esw);
+	mlx5_rdma_disable_roce(esw->dev);
 	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
 

drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c

@@ -107,6 +107,50 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns,
 	return 0;
 }
 
+static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+					       int reformat_type,
+					       size_t size,
+					       void *reformat_data,
+					       enum mlx5_flow_namespace_type namespace,
+					       struct mlx5_pkt_reformat *pkt_reformat)
+{
+	return 0;
+}
+
+static void mlx5_cmd_stub_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+						  struct mlx5_pkt_reformat *pkt_reformat)
+{
+}
+
+static int mlx5_cmd_stub_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+					     u8 namespace, u8 num_actions,
+					     void *modify_actions,
+					     struct mlx5_modify_hdr *modify_hdr)
+{
+	return 0;
+}
+
+static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+						struct mlx5_modify_hdr *modify_hdr)
+{
+}
+
+static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns,
+				  struct mlx5_flow_root_namespace *peer_ns)
+{
+	return 0;
+}
+
+static int mlx5_cmd_stub_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+	return 0;
+}
+
+static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+	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)
@@ -412,11 +456,13 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	} else {
 		MLX5_SET(flow_context, in_flow_context, action,
 			 fte->action.action);
+		if (fte->action.pkt_reformat)
 			MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
-			 fte->action.reformat_id);
+				 fte->action.pkt_reformat->id);
 	}
+	if (fte->action.modify_hdr)
 		MLX5_SET(flow_context, in_flow_context, modify_header_id,
-		 fte->action.modify_id);
+			 fte->action.modify_hdr->id);
 
 	vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan);
 
@@ -468,7 +514,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 						    MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
 					MLX5_SET(extended_dest_format, in_dests,
 						 packet_reformat_id,
-						 dst->dest_attr.vport.reformat_id);
+						 dst->dest_attr.vport.pkt_reformat->id);
 				}
 				break;
 			default:
@@ -643,14 +689,15 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
-int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
+static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
 					  int reformat_type,
 					  size_t size,
 					  void *reformat_data,
 					  enum mlx5_flow_namespace_type namespace,
-			       u32 *packet_reformat_id)
+					  struct mlx5_pkt_reformat *pkt_reformat)
 {
 	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)];
+	struct mlx5_core_dev *dev = ns->dev;
 	void *packet_reformat_context_in;
 	int max_encap_size;
 	void *reformat;
@@ -693,35 +740,36 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
 	memset(out, 0, sizeof(out));
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 
-	*packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out,
+	pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out,
 				    out, packet_reformat_id);
 	kfree(in);
 	return err;
 }
-EXPORT_SYMBOL(mlx5_packet_reformat_alloc);
 
-void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
+static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
-				  u32 packet_reformat_id)
+					     struct mlx5_pkt_reformat *pkt_reformat)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)];
 	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)];
+	struct mlx5_core_dev *dev = ns->dev;
 
 	memset(in, 0, sizeof(in));
 	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
 	MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
-		 packet_reformat_id);
+		 pkt_reformat->id);
 
 	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
-EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
 
-int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
 					u8 namespace, u8 num_actions,
-			     void *modify_actions, u32 *modify_header_id)
+					void *modify_actions,
+					struct mlx5_modify_hdr *modify_hdr)
 {
 	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)];
 	int max_actions, actions_size, inlen, err;
+	struct mlx5_core_dev *dev = ns->dev;
 	void *actions_in;
 	u8 table_type;
 	u32 *in;
@@ -772,26 +820,26 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 	memset(out, 0, sizeof(out));
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 
-	*modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
+	modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id);
 	kfree(in);
 	return err;
 }
-EXPORT_SYMBOL(mlx5_modify_header_alloc);
 
-void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id)
+static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+					   struct mlx5_modify_hdr *modify_hdr)
 {
 	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)];
 	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)];
+	struct mlx5_core_dev *dev = ns->dev;
 
 	memset(in, 0, sizeof(in));
 	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
 	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
-		 modify_header_id);
+		 modify_hdr->id);
 
 	mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
-EXPORT_SYMBOL(mlx5_modify_header_dealloc);
 
 static const struct mlx5_flow_cmds mlx5_flow_cmds = {
 	.create_flow_table = mlx5_cmd_create_flow_table,
@@ -803,6 +851,13 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = {
 	.update_fte = mlx5_cmd_update_fte,
 	.delete_fte = mlx5_cmd_delete_fte,
 	.update_root_ft = mlx5_cmd_update_root_ft,
+	.packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc,
+	.packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc,
+	.modify_header_alloc = mlx5_cmd_modify_header_alloc,
+	.modify_header_dealloc = mlx5_cmd_modify_header_dealloc,
+	.set_peer = mlx5_cmd_stub_set_peer,
+	.create_ns = mlx5_cmd_stub_create_ns,
+	.destroy_ns = mlx5_cmd_stub_destroy_ns,
 };
 
 static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
@@ -815,9 +870,16 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = {
 	.update_fte = mlx5_cmd_stub_update_fte,
 	.delete_fte = mlx5_cmd_stub_delete_fte,
 	.update_root_ft = mlx5_cmd_stub_update_root_ft,
+	.packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc,
+	.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,
+	.set_peer = mlx5_cmd_stub_set_peer,
+	.create_ns = mlx5_cmd_stub_create_ns,
+	.destroy_ns = mlx5_cmd_stub_destroy_ns,
 };
 
-static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void)
 {
 	return &mlx5_flow_cmds;
 }

drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h

@@ -75,6 +75,30 @@ struct mlx5_flow_cmds {
 			      struct mlx5_flow_table *ft,
 			      u32 underlay_qpn,
 			      bool disconnect);
+
+	int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns,
+				     int reformat_type,
+				     size_t size,
+				     void *reformat_data,
+				     enum mlx5_flow_namespace_type namespace,
+				     struct mlx5_pkt_reformat *pkt_reformat);
+
+	void (*packet_reformat_dealloc)(struct mlx5_flow_root_namespace *ns,
+					struct mlx5_pkt_reformat *pkt_reformat);
+
+	int (*modify_header_alloc)(struct mlx5_flow_root_namespace *ns,
+				   u8 namespace, u8 num_actions,
+				   void *modify_actions,
+				   struct mlx5_modify_hdr *modify_hdr);
+
+	void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_modify_hdr *modify_hdr);
+
+	int (*set_peer)(struct mlx5_flow_root_namespace *ns,
+			struct mlx5_flow_root_namespace *peer_ns);
+
+	int (*create_ns)(struct mlx5_flow_root_namespace *ns);
+	int (*destroy_ns)(struct mlx5_flow_root_namespace *ns);
 };
 
 int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id);
@@ -90,5 +114,6 @@ int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len,
 			   u32 *out);
 
 const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type);
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
 
 #endif

drivers/net/ethernet/mellanox/mlx5/core/fs_core.c

@@ -1415,7 +1415,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
 		      (d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
 		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
-		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
+		      (d1->vport.pkt_reformat->id ==
+		       d2->vport.pkt_reformat->id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
 		     d1->ft == d2->ft) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
@@ -2888,3 +2889,160 @@ out:
 	return err;
 }
 EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn);
+
+static struct mlx5_flow_root_namespace
+*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type)
+{
+	struct mlx5_flow_namespace *ns;
+
+	if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||
+	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)
+		ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);
+	else
+		ns = mlx5_get_flow_namespace(dev, ns_type);
+	if (!ns)
+		return NULL;
+
+	return find_root(&ns->node);
+}
+
+struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+						 u8 ns_type, u8 num_actions,
+						 void *modify_actions)
+{
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_modify_hdr *modify_hdr;
+	int err;
+
+	root = get_root_namespace(dev, ns_type);
+	if (!root)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	modify_hdr = kzalloc(sizeof(*modify_hdr), GFP_KERNEL);
+	if (!modify_hdr)
+		return ERR_PTR(-ENOMEM);
+
+	modify_hdr->ns_type = ns_type;
+	err = root->cmds->modify_header_alloc(root, ns_type, num_actions,
+					      modify_actions, modify_hdr);
+	if (err) {
+		kfree(modify_hdr);
+		return ERR_PTR(err);
+	}
+
+	return modify_hdr;
+}
+EXPORT_SYMBOL(mlx5_modify_header_alloc);
+
+void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
+				struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5_flow_root_namespace *root;
+
+	root = get_root_namespace(dev, modify_hdr->ns_type);
+	if (WARN_ON(!root))
+		return;
+	root->cmds->modify_header_dealloc(root, modify_hdr);
+	kfree(modify_hdr);
+}
+EXPORT_SYMBOL(mlx5_modify_header_dealloc);
+
+struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
+						     int reformat_type,
+						     size_t size,
+						     void *reformat_data,
+						     enum mlx5_flow_namespace_type ns_type)
+{
+	struct mlx5_pkt_reformat *pkt_reformat;
+	struct mlx5_flow_root_namespace *root;
+	int err;
+
+	root = get_root_namespace(dev, ns_type);
+	if (!root)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	pkt_reformat = kzalloc(sizeof(*pkt_reformat), GFP_KERNEL);
+	if (!pkt_reformat)
+		return ERR_PTR(-ENOMEM);
+
+	pkt_reformat->ns_type = ns_type;
+	pkt_reformat->reformat_type = reformat_type;
+	err = root->cmds->packet_reformat_alloc(root, reformat_type, size,
+						reformat_data, ns_type,
+						pkt_reformat);
+	if (err) {
+		kfree(pkt_reformat);
+		return ERR_PTR(err);
+	}
+
+	return pkt_reformat;
+}
+EXPORT_SYMBOL(mlx5_packet_reformat_alloc);
+
+void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
+				  struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5_flow_root_namespace *root;
+
+	root = get_root_namespace(dev, pkt_reformat->ns_type);
+	if (WARN_ON(!root))
+		return;
+	root->cmds->packet_reformat_dealloc(root, pkt_reformat);
+	kfree(pkt_reformat);
+}
+EXPORT_SYMBOL(mlx5_packet_reformat_dealloc);
+
+int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_root_namespace *peer_ns)
+{
+	if (peer_ns && ns->mode != peer_ns->mode) {
+		mlx5_core_err(ns->dev,
+			      "Can't peer namespace of different steering mode\n");
+		return -EINVAL;
+	}
+
+	return ns->cmds->set_peer(ns, peer_ns);
+}
+
+/* This function should be called only at init stage of the namespace.
+ * It is not safe to call this function while steering operations
+ * are executed in the namespace.
+ */
+int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
+				 enum mlx5_flow_steering_mode mode)
+{
+	struct mlx5_flow_root_namespace *root;
+	const struct mlx5_flow_cmds *cmds;
+	int err;
+
+	root = find_root(&ns->node);
+	if (&root->ns != ns)
+	/* Can't set cmds to non root namespace */
+		return -EINVAL;
+
+	if (root->table_type != FS_FT_FDB)
+		return -EOPNOTSUPP;
+
+	if (root->mode == mode)
+		return 0;
+
+	if (mode == MLX5_FLOW_STEERING_MODE_SMFS)
+		cmds = mlx5_fs_cmd_get_dr_cmds();
+	else
+		cmds = mlx5_fs_cmd_get_fw_cmds();
+	if (!cmds)
+		return -EOPNOTSUPP;
+
+	err = cmds->create_ns(root);
+	if (err) {
+		mlx5_core_err(root->dev, "Failed to create flow namespace (%d)\n",
+			      err);
+		return err;
+	}
+
+	root->cmds->destroy_ns(root);
+	root->cmds = cmds;
+	root->mode = mode;
+
+	return 0;
+}

drivers/net/ethernet/mellanox/mlx5/core/fs_core.h

@@ -37,6 +37,24 @@
 #include <linux/mlx5/fs.h>
 #include <linux/rhashtable.h>
 #include <linux/llist.h>
+#include <steering/fs_dr.h>
+
+struct mlx5_modify_hdr {
+	enum mlx5_flow_namespace_type ns_type;
+	union {
+		struct mlx5_fs_dr_action action;
+		u32 id;
+	};
+};
+
+struct mlx5_pkt_reformat {
+	enum mlx5_flow_namespace_type ns_type;
+	int reformat_type; /* from mlx5_ifc */
+	union {
+		struct mlx5_fs_dr_action action;
+		u32 id;
+	};
+};
 
 /* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only,
  * and those are in parallel to one another when going over them to connect
@@ -80,8 +98,14 @@ enum fs_fte_status {
 	FS_FTE_STATUS_EXISTING = 1UL << 0,
 };
 
+enum mlx5_flow_steering_mode {
+	MLX5_FLOW_STEERING_MODE_DMFS,
+	MLX5_FLOW_STEERING_MODE_SMFS
+};
+
 struct mlx5_flow_steering {
 	struct mlx5_core_dev *dev;
+	enum   mlx5_flow_steering_mode	mode;
 	struct kmem_cache		*fgs_cache;
 	struct kmem_cache               *ftes_cache;
 	struct mlx5_flow_root_namespace *root_ns;
@@ -128,6 +152,7 @@ struct mlx5_flow_handle {
 /* Type of children is mlx5_flow_group */
 struct mlx5_flow_table {
 	struct fs_node			node;
+	struct mlx5_fs_dr_table		fs_dr_table;
 	u32				id;
 	u16				vport;
 	unsigned int			max_fte;
@@ -168,6 +193,7 @@ struct mlx5_ft_underlay_qp {
 /* Type of children is mlx5_flow_rule */
 struct fs_fte {
 	struct fs_node			node;
+	struct mlx5_fs_dr_rule		fs_dr_rule;
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	u32				dests_size;
 	u32				index;
@@ -203,6 +229,7 @@ struct mlx5_flow_group_mask {
 /* Type of children is fs_fte */
 struct mlx5_flow_group {
 	struct fs_node			node;
+	struct mlx5_fs_dr_matcher	fs_dr_matcher;
 	struct mlx5_flow_group_mask	mask;
 	u32				start_index;
 	u32				max_ftes;
@@ -214,6 +241,8 @@ struct mlx5_flow_group {
 
 struct mlx5_flow_root_namespace {
 	struct mlx5_flow_namespace	ns;
+	enum   mlx5_flow_steering_mode	mode;
+	struct mlx5_fs_dr_domain	fs_dr_domain;
 	enum   fs_flow_table_type	table_type;
 	struct mlx5_core_dev		*dev;
 	struct mlx5_flow_table		*root_ft;
@@ -231,6 +260,14 @@ void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev,
 void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev,
 				      unsigned long interval);
 
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void);
+
+int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns,
+				 struct mlx5_flow_root_namespace *peer_ns);
+
+int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns,
+				 enum mlx5_flow_steering_mode mode);
+
 int mlx5_init_fs(struct mlx5_core_dev *dev);
 void mlx5_cleanup_fs(struct mlx5_core_dev *dev);
 

drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c

@@ -0,0 +1,223 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2019 Mellanox Technologies
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+
+#include "mlx5_core.h"
+#include "lib/mlx5.h"
+
+struct mlx5_dm {
+	/* protect access to icm bitmask */
+	spinlock_t lock;
+	unsigned long *steering_sw_icm_alloc_blocks;
+	unsigned long *header_modify_sw_icm_alloc_blocks;
+};
+
+struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev)
+{
+	u64 header_modify_icm_blocks = 0;
+	u64 steering_icm_blocks = 0;
+	struct mlx5_dm *dm;
+
+	if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM))
+		return 0;
+
+	dm = kzalloc(sizeof(*dm), GFP_KERNEL);
+	if (!dm)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&dm->lock);
+
+	if (MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address)) {
+		steering_icm_blocks =
+			BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) -
+			    MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
+
+		dm->steering_sw_icm_alloc_blocks =
+			kcalloc(BITS_TO_LONGS(steering_icm_blocks),
+				sizeof(unsigned long), GFP_KERNEL);
+		if (!dm->steering_sw_icm_alloc_blocks)
+			goto err_steering;
+	}
+
+	if (MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address)) {
+		header_modify_icm_blocks =
+			BIT(MLX5_CAP_DEV_MEM(dev, log_header_modify_sw_icm_size) -
+			    MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
+
+		dm->header_modify_sw_icm_alloc_blocks =
+			kcalloc(BITS_TO_LONGS(header_modify_icm_blocks),
+				sizeof(unsigned long), GFP_KERNEL);
+		if (!dm->header_modify_sw_icm_alloc_blocks)
+			goto err_modify_hdr;
+	}
+
+	return dm;
+
+err_modify_hdr:
+	kfree(dm->steering_sw_icm_alloc_blocks);
+
+err_steering:
+	kfree(dm);
+
+	return ERR_PTR(-ENOMEM);
+}
+
+void mlx5_dm_cleanup(struct mlx5_core_dev *dev)
+{
+	struct mlx5_dm *dm = dev->dm;
+
+	if (!dev->dm)
+		return;
+
+	if (dm->steering_sw_icm_alloc_blocks) {
+		WARN_ON(!bitmap_empty(dm->steering_sw_icm_alloc_blocks,
+				      BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) -
+					  MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))));
+		kfree(dm->steering_sw_icm_alloc_blocks);
+	}
+
+	if (dm->header_modify_sw_icm_alloc_blocks) {
+		WARN_ON(!bitmap_empty(dm->header_modify_sw_icm_alloc_blocks,
+				      BIT(MLX5_CAP_DEV_MEM(dev,
+							   log_header_modify_sw_icm_size) -
+				      MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))));
+		kfree(dm->header_modify_sw_icm_alloc_blocks);
+	}
+
+	kfree(dm);
+}
+
+int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
+			 u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id)
+{
+	u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {};
+	struct mlx5_dm *dm = dev->dm;
+	unsigned long *block_map;
+	u64 icm_start_addr;
+	u32 log_icm_size;
+	u32 max_blocks;
+	u64 block_idx;
+	void *sw_icm;
+	int ret;
+
+	if (!dev->dm)
+		return -EOPNOTSUPP;
+
+	if (!length || (length & (length - 1)) ||
+	    length & (MLX5_SW_ICM_BLOCK_SIZE(dev) - 1))
+		return -EINVAL;
+
+	MLX5_SET(general_obj_in_cmd_hdr, in, opcode,
+		 MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM);
+	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
+
+	switch (type) {
+	case MLX5_SW_ICM_TYPE_STEERING:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address);
+		log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size);
+		block_map = dm->steering_sw_icm_alloc_blocks;
+		break;
+	case MLX5_SW_ICM_TYPE_HEADER_MODIFY:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address);
+		log_icm_size = MLX5_CAP_DEV_MEM(dev,
+						log_header_modify_sw_icm_size);
+		block_map = dm->header_modify_sw_icm_alloc_blocks;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (!block_map)
+		return -EOPNOTSUPP;
+
+	max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
+	spin_lock(&dm->lock);
+	block_idx = bitmap_find_next_zero_area(block_map,
+					       max_blocks,
+					       0,
+					       num_blocks, 0);
+
+	if (block_idx < max_blocks)
+		bitmap_set(block_map,
+			   block_idx, num_blocks);
+
+	spin_unlock(&dm->lock);
+
+	if (block_idx >= max_blocks)
+		return -ENOMEM;
+
+	sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm);
+	icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+	MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr,
+		   icm_start_addr);
+	MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length));
+
+	ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (ret) {
+		spin_lock(&dm->lock);
+		bitmap_clear(block_map,
+			     block_idx, num_blocks);
+		spin_unlock(&dm->lock);
+
+		return ret;
+	}
+
+	*addr = icm_start_addr;
+	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_alloc);
+
+int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
+			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id)
+{
+	u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
+	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
+	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
+	struct mlx5_dm *dm = dev->dm;
+	unsigned long *block_map;
+	u64 icm_start_addr;
+	u64 start_idx;
+	int err;
+
+	if (!dev->dm)
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case MLX5_SW_ICM_TYPE_STEERING:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address);
+		block_map = dm->steering_sw_icm_alloc_blocks;
+		break;
+	case MLX5_SW_ICM_TYPE_HEADER_MODIFY:
+		icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address);
+		block_map = dm->header_modify_sw_icm_alloc_blocks;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	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_SW_ICM);
+	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id);
+	MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid);
+
+	err =  mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	start_idx = (addr - icm_start_addr) >> MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+	spin_lock(&dm->lock);
+	bitmap_clear(block_map,
+		     start_idx, num_blocks);
+	spin_unlock(&dm->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_dealloc);

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -876,6 +876,10 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 		goto err_eswitch_cleanup;
 	}
 
+	dev->dm = mlx5_dm_create(dev);
+	if (IS_ERR(dev->dm))
+		mlx5_core_warn(dev, "Failed to init device memory%d\n", err);
+
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 
@@ -910,6 +914,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
+	mlx5_dm_cleanup(dev);
 	mlx5_fpga_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_sriov_cleanup(dev);

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -198,6 +198,9 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size);
 int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode);
 int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 
+struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
+void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
+
 #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
 			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\

drivers/net/ethernet/mellanox/mlx5/core/rdma.c

@@ -14,9 +14,6 @@ static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_roce *roce = &dev->priv.roce;
 
-	if (!roce->ft)
-		return;
-
 	mlx5_del_flow_rules(roce->allow_rule);
 	mlx5_destroy_flow_group(roce->fg);
 	mlx5_destroy_flow_table(roce->ft);
@@ -145,6 +142,11 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev)
 
 void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev)
 {
+	struct mlx5_core_roce *roce = &dev->priv.roce;
+
+	if (!roce->ft)
+		return;
+
 	mlx5_rdma_disable_roce_steering(dev);
 	mlx5_rdma_del_roce_addr(dev);
 	mlx5_nic_vport_disable_roce(dev);

drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+subdir-ccflags-y += -I$(src)/..

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c

@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev,
+				       bool other_vport,
+				       u16 vport_number,
+				       u64 *icm_address_rx,
+				       u64 *icm_address_tx)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
+	int err;
+
+	MLX5_SET(query_esw_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
+	MLX5_SET(query_esw_vport_context_in, in, other_vport, other_vport);
+	MLX5_SET(query_esw_vport_context_in, in, vport_number, vport_number);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	*icm_address_rx =
+		MLX5_GET64(query_esw_vport_context_out, out,
+			   esw_vport_context.sw_steering_vport_icm_address_rx);
+	*icm_address_tx =
+		MLX5_GET64(query_esw_vport_context_out, out,
+			   esw_vport_context.sw_steering_vport_icm_address_tx);
+	return 0;
+}
+
+int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport,
+			  u16 vport_number, u16 *gvmi)
+{
+	u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {};
+	int out_size;
+	void *out;
+	int err;
+
+	out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	out = kzalloc(out_size, GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, other_function, other_vport);
+	MLX5_SET(query_hca_cap_in, in, function_id, vport_number);
+	MLX5_SET(query_hca_cap_in, in, op_mod,
+		 MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 |
+		 HCA_CAP_OPMOD_GET_CUR);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size);
+	if (err) {
+		kfree(out);
+		return err;
+	}
+
+	*gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id);
+
+	kfree(out);
+	return 0;
+}
+
+int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev,
+			      struct mlx5dr_esw_caps *caps)
+{
+	caps->drop_icm_address_rx =
+		MLX5_CAP64_ESW_FLOWTABLE(mdev,
+					 sw_steering_fdb_action_drop_icm_address_rx);
+	caps->drop_icm_address_tx =
+		MLX5_CAP64_ESW_FLOWTABLE(mdev,
+					 sw_steering_fdb_action_drop_icm_address_tx);
+	caps->uplink_icm_address_rx =
+		MLX5_CAP64_ESW_FLOWTABLE(mdev,
+					 sw_steering_uplink_icm_address_rx);
+	caps->uplink_icm_address_tx =
+		MLX5_CAP64_ESW_FLOWTABLE(mdev,
+					 sw_steering_uplink_icm_address_tx);
+	caps->sw_owner =
+		MLX5_CAP_ESW_FLOWTABLE_FDB(mdev,
+					   sw_owner);
+
+	return 0;
+}
+
+int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev,
+			    struct mlx5dr_cmd_caps *caps)
+{
+	caps->prio_tag_required	= MLX5_CAP_GEN(mdev, prio_tag_required);
+	caps->eswitch_manager	= MLX5_CAP_GEN(mdev, eswitch_manager);
+	caps->gvmi		= MLX5_CAP_GEN(mdev, vhca_id);
+	caps->flex_protocols	= MLX5_CAP_GEN(mdev, flex_parser_protocols);
+
+	if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) {
+		caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0);
+		caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1);
+	}
+
+	if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) {
+		caps->flex_parser_id_icmpv6_dw0 =
+			MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0);
+		caps->flex_parser_id_icmpv6_dw1 =
+			MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw1);
+	}
+
+	caps->nic_rx_drop_address =
+		MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_rx_action_drop_icm_address);
+	caps->nic_tx_drop_address =
+		MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_drop_icm_address);
+	caps->nic_tx_allow_address =
+		MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_allow_icm_address);
+
+	caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner);
+	caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level);
+
+	caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner);
+
+	caps->log_icm_size = MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size);
+	caps->hdr_modify_icm_addr =
+		MLX5_CAP64_DEV_MEM(mdev, header_modify_sw_icm_start_address);
+
+	caps->roce_min_src_udp = MLX5_CAP_ROCE(mdev, r_roce_min_src_udp_port);
+
+	return 0;
+}
+
+int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev,
+				enum fs_flow_table_type type,
+				u32 table_id,
+				struct mlx5dr_cmd_query_flow_table_details *output)
+{
+	u32 out[MLX5_ST_SZ_DW(query_flow_table_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_flow_table_in)] = {};
+	int err;
+
+	MLX5_SET(query_flow_table_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_FLOW_TABLE);
+
+	MLX5_SET(query_flow_table_in, in, table_type, type);
+	MLX5_SET(query_flow_table_in, in, table_id, table_id);
+
+	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	output->status = MLX5_GET(query_flow_table_out, out, status);
+	output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level);
+
+	output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out,
+						 flow_table_context.sw_owner_icm_root_1);
+	output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out,
+						 flow_table_context.sw_owner_icm_root_0);
+
+	return 0;
+}
+
+int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev)
+{
+	u32 out[MLX5_ST_SZ_DW(sync_steering_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {};
+
+	MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev,
+					u32 table_type,
+					u32 table_id,
+					u32 group_id,
+					u32 modify_header_id,
+					u32 vport_id)
+{
+	u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {};
+	void *in_flow_context;
+	unsigned int inlen;
+	void *in_dests;
+	u32 *in;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(set_fte_in) +
+		1 * MLX5_ST_SZ_BYTES(dest_format_struct); /* One destination only */
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY);
+	MLX5_SET(set_fte_in, in, table_type, table_type);
+	MLX5_SET(set_fte_in, in, table_id, table_id);
+
+	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
+	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
+	MLX5_SET(flow_context, in_flow_context, modify_header_id, modify_header_id);
+	MLX5_SET(flow_context, in_flow_context, destination_list_size, 1);
+	MLX5_SET(flow_context, in_flow_context, action,
+		 MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+		 MLX5_FLOW_CONTEXT_ACTION_MOD_HDR);
+
+	in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination);
+	MLX5_SET(dest_format_struct, in_dests, destination_type,
+		 MLX5_FLOW_DESTINATION_TYPE_VPORT);
+	MLX5_SET(dest_format_struct, in_dests, destination_id, vport_id);
+
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	kvfree(in);
+
+	return err;
+}
+
+int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev,
+				    u32 table_type,
+				    u32 table_id)
+{
+	u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {};
+
+	MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY);
+	MLX5_SET(delete_fte_in, in, table_type, table_type);
+	MLX5_SET(delete_fte_in, in, table_id, table_id);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev,
+				   u32 table_type,
+				   u8 num_of_actions,
+				   u64 *actions,
+				   u32 *modify_header_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)] = {};
+	void *p_actions;
+	u32 inlen;
+	u32 *in;
+	int err;
+
+	inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) +
+		 num_of_actions * sizeof(u64);
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(alloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type);
+	MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_of_actions);
+	p_actions = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions);
+	memcpy(p_actions, actions, num_of_actions * sizeof(u64));
+
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	if (err)
+		goto out;
+
+	*modify_header_id = MLX5_GET(alloc_modify_header_context_out, out,
+				     modify_header_id);
+out:
+	kvfree(in);
+	return err;
+}
+
+int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev,
+				     u32 modify_header_id)
+{
+	u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {};
+
+	MLX5_SET(dealloc_modify_header_context_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT);
+	MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id,
+		 modify_header_id);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev,
+				       u32 table_type,
+				       u32 table_id,
+				       u32 *group_id)
+{
+	u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {};
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	u32 *in;
+	int err;
+
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP);
+	MLX5_SET(create_flow_group_in, in, table_type, table_type);
+	MLX5_SET(create_flow_group_in, in, table_id, table_id);
+
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	if (err)
+		goto out;
+
+	*group_id = MLX5_GET(create_flow_group_out, out, group_id);
+
+out:
+	kfree(in);
+	return err;
+}
+
+int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev,
+				  u32 table_type,
+				  u32 table_id,
+				  u32 group_id)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {};
+	u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {};
+
+	MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP);
+	MLX5_SET(destroy_flow_group_in, in, table_type, table_type);
+	MLX5_SET(destroy_flow_group_in, in, table_id, table_id);
+	MLX5_SET(destroy_flow_group_in, in, group_id, group_id);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev,
+				 u32 table_type,
+				 u64 icm_addr_rx,
+				 u64 icm_addr_tx,
+				 u8 level,
+				 bool sw_owner,
+				 bool term_tbl,
+				 u64 *fdb_rx_icm_addr,
+				 u32 *table_id)
+{
+	u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {};
+	void *ft_mdev;
+	int err;
+
+	MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE);
+	MLX5_SET(create_flow_table_in, in, table_type, table_type);
+
+	ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context);
+	MLX5_SET(flow_table_context, ft_mdev, termination_table, term_tbl);
+	MLX5_SET(flow_table_context, ft_mdev, sw_owner, sw_owner);
+	MLX5_SET(flow_table_context, ft_mdev, level, level);
+
+	if (sw_owner) {
+		/* icm_addr_0 used for FDB RX / NIC TX / NIC_RX
+		 * icm_addr_1 used for FDB TX
+		 */
+		if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) {
+			MLX5_SET64(flow_table_context, ft_mdev,
+				   sw_owner_icm_root_0, icm_addr_rx);
+		} else if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) {
+			MLX5_SET64(flow_table_context, ft_mdev,
+				   sw_owner_icm_root_0, icm_addr_tx);
+		} else if (table_type == MLX5_FLOW_TABLE_TYPE_FDB) {
+			MLX5_SET64(flow_table_context, ft_mdev,
+				   sw_owner_icm_root_0, icm_addr_rx);
+			MLX5_SET64(flow_table_context, ft_mdev,
+				   sw_owner_icm_root_1, icm_addr_tx);
+		}
+	}
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	*table_id = MLX5_GET(create_flow_table_out, out, table_id);
+	if (!sw_owner && table_type == MLX5_FLOW_TABLE_TYPE_FDB)
+		*fdb_rx_icm_addr =
+		(u64)MLX5_GET(create_flow_table_out, out, icm_address_31_0) |
+		(u64)MLX5_GET(create_flow_table_out, out, icm_address_39_32) << 32 |
+		(u64)MLX5_GET(create_flow_table_out, out, icm_address_63_40) << 40;
+
+	return 0;
+}
+
+int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev,
+				  u32 table_id,
+				  u32 table_type)
+{
+	u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {};
+
+	MLX5_SET(destroy_flow_table_in, in, opcode,
+		 MLX5_CMD_OP_DESTROY_FLOW_TABLE);
+	MLX5_SET(destroy_flow_table_in, in, table_type, table_type);
+	MLX5_SET(destroy_flow_table_in, in, table_id, table_id);
+
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev,
+				   enum mlx5_reformat_ctx_type rt,
+				   size_t reformat_size,
+				   void *reformat_data,
+				   u32 *reformat_id)
+{
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {};
+	size_t inlen, cmd_data_sz, cmd_total_sz;
+	void *prctx;
+	void *pdata;
+	void *in;
+	int err;
+
+	cmd_total_sz = MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in);
+	cmd_data_sz = MLX5_FLD_SZ_BYTES(alloc_packet_reformat_context_in,
+					packet_reformat_context.reformat_data);
+	inlen = ALIGN(cmd_total_sz + reformat_size - cmd_data_sz, 4);
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(alloc_packet_reformat_context_in, in, opcode,
+		 MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT);
+
+	prctx = MLX5_ADDR_OF(alloc_packet_reformat_context_in, in, packet_reformat_context);
+	pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data);
+
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt);
+	MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size);
+	memcpy(pdata, reformat_data, reformat_size);
+
+	err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out));
+	if (err)
+		return err;
+
+	*reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
+	kvfree(in);
+
+	return err;
+}
+
+void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev,
+				     u32 reformat_id)
+{
+	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {};
+
+	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
+		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
+	MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id,
+		 reformat_id);
+
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num,
+			 u16 index, struct mlx5dr_cmd_gid_attr *attr)
+{
+	u32 out[MLX5_ST_SZ_DW(query_roce_address_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_roce_address_in)] = {};
+	int err;
+
+	MLX5_SET(query_roce_address_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_ROCE_ADDRESS);
+
+	MLX5_SET(query_roce_address_in, in, roce_address_index, index);
+	MLX5_SET(query_roce_address_in, in, vhca_port_num, vhca_port_num);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return err;
+
+	memcpy(&attr->gid,
+	       MLX5_ADDR_OF(query_roce_address_out,
+			    out, roce_address.source_l3_address),
+	       sizeof(attr->gid));
+	memcpy(attr->mac,
+	       MLX5_ADDR_OF(query_roce_address_out, out,
+			    roce_address.source_mac_47_32),
+	       sizeof(attr->mac));
+
+	if (MLX5_GET(query_roce_address_out, out,
+		     roce_address.roce_version) == MLX5_ROCE_VERSION_2)
+		attr->roce_ver = MLX5_ROCE_VERSION_2;
+	else
+		attr->roce_ver = MLX5_ROCE_VERSION_1;
+
+	return 0;
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c

@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved.
+ * Slicing-by-16 contributed by Bulat Ziganshin
+ *
+ * This software is provided 'as-is', without any express or implied warranty.
+ * In no event will the author be held liable for any damages arising from the
+ * of this software.
+ *
+ * Permission is granted to anyone to use this software for any purpose,
+ * including commercial applications, and to alter it and redistribute it
+ * freely, subject to the following restrictions:
+ *
+ * 1. The origin of this software must not be misrepresented; you must not
+ *    claim that you wrote the original software.
+ * 2. If you use this software in a product, an acknowledgment in the product
+ *    documentation would be appreciated but is not required.
+ * 3. Altered source versions must be plainly marked as such, and must not be
+ *    misrepresented as being the original software.
+ *
+ * Taken from http://create.stephan-brumme.com/crc32/ and adapted.
+ */
+
+#include "dr_types.h"
+
+#define DR_STE_CRC_POLY 0xEDB88320L
+
+static u32 dr_ste_crc_tab32[8][256];
+
+static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j)
+{
+	tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff];
+}
+
+void mlx5dr_crc32_init_table(void)
+{
+	u32 crc, i, j;
+
+	for (i = 0; i < 256; i++) {
+		crc = i;
+		for (j = 0; j < 8; j++) {
+			if (crc & 0x00000001L)
+				crc = (crc >> 1) ^ DR_STE_CRC_POLY;
+			else
+				crc = crc >> 1;
+		}
+		dr_ste_crc_tab32[0][i] = crc;
+	}
+
+	/* Init CRC lookup tables according to crc_slice_8 algorithm */
+	for (i = 0; i < 256; i++) {
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i);
+		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i);
+	}
+}
+
+/* Compute CRC32 (Slicing-by-8 algorithm) */
+u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length)
+{
+	const u32 *curr = (const u32 *)input_data;
+	const u8 *curr_char;
+	u32 crc = 0, one, two;
+
+	if (!input_data)
+		return 0;
+
+	/* Process eight bytes at once (Slicing-by-8) */
+	while (length >= 8) {
+		one = *curr++ ^ crc;
+		two = *curr++;
+
+		crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff]
+			^ dr_ste_crc_tab32[1][(two >> 16) & 0xff]
+			^ dr_ste_crc_tab32[2][(two >> 8) & 0xff]
+			^ dr_ste_crc_tab32[3][two & 0xff]
+			^ dr_ste_crc_tab32[4][(one >> 24) & 0xff]
+			^ dr_ste_crc_tab32[5][(one >> 16) & 0xff]
+			^ dr_ste_crc_tab32[6][(one >> 8) & 0xff]
+			^ dr_ste_crc_tab32[7][one & 0xff];
+
+		length -= 8;
+	}
+
+	curr_char = (const u8 *)curr;
+	/* Remaining 1 to 7 bytes (standard algorithm) */
+	while (length-- != 0)
+		crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff)
+			^ *curr_char++];
+
+	return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) |
+		((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000);
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c

@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/mlx5/eswitch.h>
+#include "dr_types.h"
+
+static int dr_domain_init_cache(struct mlx5dr_domain *dmn)
+{
+	/* Per vport cached FW FT for checksum recalculation, this
+	 * recalculation is needed due to a HW bug.
+	 */
+	dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports,
+					  sizeof(dmn->cache.recalc_cs_ft[0]),
+					  GFP_KERNEL);
+	if (!dmn->cache.recalc_cs_ft)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn)
+{
+	int i;
+
+	for (i = 0; i < dmn->info.caps.num_vports; i++) {
+		if (!dmn->cache.recalc_cs_ft[i])
+			continue;
+
+		mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]);
+	}
+
+	kfree(dmn->cache.recalc_cs_ft);
+}
+
+int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn,
+					      u32 vport_num,
+					      u64 *rx_icm_addr)
+{
+	struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
+
+	recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num];
+	if (!recalc_cs_ft) {
+		/* Table not in cache, need to allocate a new one */
+		recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num);
+		if (!recalc_cs_ft)
+			return -EINVAL;
+
+		dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft;
+	}
+
+	*rx_icm_addr = recalc_cs_ft->rx_icm_addr;
+
+	return 0;
+}
+
+static int dr_domain_init_resources(struct mlx5dr_domain *dmn)
+{
+	int ret;
+
+	ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn);
+	if (ret) {
+		mlx5dr_dbg(dmn, "Couldn't allocate PD\n");
+		return ret;
+	}
+
+	dmn->uar = mlx5_get_uars_page(dmn->mdev);
+	if (!dmn->uar) {
+		mlx5dr_err(dmn, "Couldn't allocate UAR\n");
+		goto clean_pd;
+	}
+
+	dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE);
+	if (!dmn->ste_icm_pool) {
+		mlx5dr_err(dmn, "Couldn't get icm memory for %s\n",
+			   dev_name(dmn->mdev->device));
+		goto clean_uar;
+	}
+
+	dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION);
+	if (!dmn->action_icm_pool) {
+		mlx5dr_err(dmn, "Couldn't get action icm memory for %s\n",
+			   dev_name(dmn->mdev->device));
+		goto free_ste_icm_pool;
+	}
+
+	ret = mlx5dr_send_ring_alloc(dmn);
+	if (ret) {
+		mlx5dr_err(dmn, "Couldn't create send-ring for %s\n",
+			   dev_name(dmn->mdev->device));
+		goto free_action_icm_pool;
+	}
+
+	return 0;
+
+free_action_icm_pool:
+	mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+free_ste_icm_pool:
+	mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+clean_uar:
+	mlx5_put_uars_page(dmn->mdev, dmn->uar);
+clean_pd:
+	mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+
+	return ret;
+}
+
+static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn)
+{
+	mlx5dr_send_ring_free(dmn, dmn->send_ring);
+	mlx5dr_icm_pool_destroy(dmn->action_icm_pool);
+	mlx5dr_icm_pool_destroy(dmn->ste_icm_pool);
+	mlx5_put_uars_page(dmn->mdev, dmn->uar);
+	mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn);
+}
+
+static int dr_domain_query_vport(struct mlx5dr_domain *dmn,
+				 bool other_vport,
+				 u16 vport_number)
+{
+	struct mlx5dr_cmd_vport_cap *vport_caps;
+	int ret;
+
+	vport_caps = &dmn->info.caps.vports_caps[vport_number];
+
+	ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev,
+						 other_vport,
+						 vport_number,
+						 &vport_caps->icm_address_rx,
+						 &vport_caps->icm_address_tx);
+	if (ret)
+		return ret;
+
+	ret = mlx5dr_cmd_query_gvmi(dmn->mdev,
+				    other_vport,
+				    vport_number,
+				    &vport_caps->vport_gvmi);
+	if (ret)
+		return ret;
+
+	vport_caps->num = vport_number;
+	vport_caps->vhca_gvmi = dmn->info.caps.gvmi;
+
+	return 0;
+}
+
+static int dr_domain_query_vports(struct mlx5dr_domain *dmn)
+{
+	struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps;
+	struct mlx5dr_cmd_vport_cap *wire_vport;
+	int vport;
+	int ret;
+
+	/* Query vports (except wire vport) */
+	for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) {
+		ret = dr_domain_query_vport(dmn, !!vport, vport);
+		if (ret)
+			return ret;
+	}
+
+	/* Last vport is the wire port */
+	wire_vport = &dmn->info.caps.vports_caps[vport];
+	wire_vport->num = WIRE_PORT;
+	wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx;
+	wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx;
+	wire_vport->vport_gvmi = 0;
+	wire_vport->vhca_gvmi = dmn->info.caps.gvmi;
+
+	return 0;
+}
+
+static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev,
+				    struct mlx5dr_domain *dmn)
+{
+	int ret;
+
+	if (!dmn->info.caps.eswitch_manager)
+		return -EOPNOTSUPP;
+
+	ret = mlx5dr_cmd_query_esw_caps(mdev, &dmn->info.caps.esw_caps);
+	if (ret)
+		return ret;
+
+	dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner;
+	dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx;
+	dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx;
+
+	dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports,
+					     sizeof(dmn->info.caps.vports_caps[0]),
+					     GFP_KERNEL);
+	if (!dmn->info.caps.vports_caps)
+		return -ENOMEM;
+
+	ret = dr_domain_query_vports(dmn);
+	if (ret) {
+		mlx5dr_dbg(dmn, "Failed to query vports caps\n");
+		goto free_vports_caps;
+	}
+
+	dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1;
+
+	return 0;
+
+free_vports_caps:
+	kfree(dmn->info.caps.vports_caps);
+	dmn->info.caps.vports_caps = NULL;
+	return ret;
+}
+
+static int dr_domain_caps_init(struct mlx5_core_dev *mdev,
+			       struct mlx5dr_domain *dmn)
+{
+	struct mlx5dr_cmd_vport_cap *vport_cap;
+	int ret;
+
+	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) {
+		mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n");
+		return -EOPNOTSUPP;
+	}
+
+	dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev);
+
+	ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps);
+	if (ret)
+		return ret;
+
+	ret = dr_domain_query_fdb_caps(mdev, dmn);
+	if (ret)
+		return ret;
+
+	switch (dmn->type) {
+	case MLX5DR_DOMAIN_TYPE_NIC_RX:
+		if (!dmn->info.caps.rx_sw_owner)
+			return -ENOTSUPP;
+
+		dmn->info.supp_sw_steering = true;
+		dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+		dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address;
+		dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address;
+		break;
+	case MLX5DR_DOMAIN_TYPE_NIC_TX:
+		if (!dmn->info.caps.tx_sw_owner)
+			return -ENOTSUPP;
+
+		dmn->info.supp_sw_steering = true;
+		dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+		dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address;
+		dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address;
+		break;
+	case MLX5DR_DOMAIN_TYPE_FDB:
+		if (!dmn->info.caps.eswitch_manager)
+			return -ENOTSUPP;
+
+		if (!dmn->info.caps.fdb_sw_owner)
+			return -ENOTSUPP;
+
+		dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX;
+		dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX;
+		vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0);
+		if (!vport_cap) {
+			mlx5dr_dbg(dmn, "Failed to get esw manager vport\n");
+			return -ENOENT;
+		}
+
+		dmn->info.supp_sw_steering = true;
+		dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx;
+		dmn->info.rx.default_icm_addr = vport_cap->icm_address_rx;
+		dmn->info.rx.drop_icm_addr = dmn->info.caps.esw_rx_drop_address;
+		dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address;
+		break;
+	default:
+		mlx5dr_dbg(dmn, "Invalid domain\n");
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn)
+{
+	kfree(dmn->info.caps.vports_caps);
+}
+
+struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
+{
+	struct mlx5dr_domain *dmn;
+	int ret;
+
+	if (type > MLX5DR_DOMAIN_TYPE_FDB)
+		return NULL;
+
+	dmn = kzalloc(sizeof(*dmn), GFP_KERNEL);
+	if (!dmn)
+		return NULL;
+
+	dmn->mdev = mdev;
+	dmn->type = type;
+	refcount_set(&dmn->refcount, 1);
+	mutex_init(&dmn->mutex);
+
+	if (dr_domain_caps_init(mdev, dmn)) {
+		mlx5dr_dbg(dmn, "Failed init domain, no caps\n");
+		goto free_domain;
+	}
+
+	dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K;
+	dmn->info.max_log_sw_icm_sz = min_t(u32, DR_CHUNK_SIZE_1024K,
+					    dmn->info.caps.log_icm_size);
+
+	if (!dmn->info.supp_sw_steering) {
+		mlx5dr_err(dmn, "SW steering not supported for %s\n",
+			   dev_name(mdev->device));
+		goto uninit_caps;
+	}
+
+	/* Allocate resources */
+	ret = dr_domain_init_resources(dmn);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed init domain resources for %s\n",
+			   dev_name(mdev->device));
+		goto uninit_caps;
+	}
+
+	ret = dr_domain_init_cache(dmn);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed initialize domain cache\n");
+		goto uninit_resourses;
+	}
+
+	/* Init CRC table for htbl CRC calculation */
+	mlx5dr_crc32_init_table();
+
+	return dmn;
+
+uninit_resourses:
+	dr_domain_uninit_resources(dmn);
+uninit_caps:
+	dr_domain_caps_uninit(dmn);
+free_domain:
+	kfree(dmn);
+	return NULL;
+}
+
+/* Assure synchronization of the device steering tables with updates made by SW
+ * insertion.
+ */
+int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
+{
+	int ret = 0;
+
+	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
+		mutex_lock(&dmn->mutex);
+		ret = mlx5dr_send_ring_force_drain(dmn);
+		mutex_unlock(&dmn->mutex);
+		if (ret)
+			return ret;
+	}
+
+	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
+		ret = mlx5dr_cmd_sync_steering(dmn->mdev);
+
+	return ret;
+}
+
+int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
+{
+	if (refcount_read(&dmn->refcount) > 1)
+		return -EBUSY;
+
+	/* make sure resources are not used by the hardware */
+	mlx5dr_cmd_sync_steering(dmn->mdev);
+	dr_domain_uninit_cache(dmn);
+	dr_domain_uninit_resources(dmn);
+	dr_domain_caps_uninit(dmn);
+	mutex_destroy(&dmn->mutex);
+	kfree(dmn);
+	return 0;
+}
+
+void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+			    struct mlx5dr_domain *peer_dmn)
+{
+	mutex_lock(&dmn->mutex);
+
+	if (dmn->peer_dmn)
+		refcount_dec(&dmn->peer_dmn->refcount);
+
+	dmn->peer_dmn = peer_dmn;
+
+	if (dmn->peer_dmn)
+		refcount_inc(&dmn->peer_dmn->refcount);
+
+	mutex_unlock(&dmn->mutex);
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c

@@ -0,0 +1,93 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/types.h>
+#include "dr_types.h"
+
+struct mlx5dr_fw_recalc_cs_ft *
+mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num)
+{
+	struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft;
+	u32 table_id, group_id, modify_hdr_id;
+	u64 rx_icm_addr, modify_ttl_action;
+	int ret;
+
+	recalc_cs_ft = kzalloc(sizeof(*recalc_cs_ft), GFP_KERNEL);
+	if (!recalc_cs_ft)
+		return NULL;
+
+	ret = mlx5dr_cmd_create_flow_table(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB,
+					   0, 0, dmn->info.caps.max_ft_level - 1,
+					   false, true, &rx_icm_addr, &table_id);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed creating TTL W/A FW flow table %d\n", ret);
+		goto free_ttl_tbl;
+	}
+
+	ret = mlx5dr_cmd_create_empty_flow_group(dmn->mdev,
+						 MLX5_FLOW_TABLE_TYPE_FDB,
+						 table_id, &group_id);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed creating TTL W/A FW flow group %d\n", ret);
+		goto destroy_flow_table;
+	}
+
+	/* Modify TTL action by adding zero to trigger CS recalculation */
+	modify_ttl_action = 0;
+	MLX5_SET(set_action_in, &modify_ttl_action, action_type, MLX5_ACTION_TYPE_ADD);
+	MLX5_SET(set_action_in, &modify_ttl_action, field, MLX5_ACTION_IN_FIELD_OUT_IP_TTL);
+
+	ret = mlx5dr_cmd_alloc_modify_header(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, 1,
+					     &modify_ttl_action,
+					     &modify_hdr_id);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed modify header TTL %d\n", ret);
+		goto destroy_flow_group;
+	}
+
+	ret = mlx5dr_cmd_set_fte_modify_and_vport(dmn->mdev,
+						  MLX5_FLOW_TABLE_TYPE_FDB,
+						  table_id, group_id, modify_hdr_id,
+						  vport_num);
+	if (ret) {
+		mlx5dr_err(dmn, "Failed setting TTL W/A flow table entry %d\n", ret);
+		goto dealloc_modify_header;
+	}
+
+	recalc_cs_ft->modify_hdr_id = modify_hdr_id;
+	recalc_cs_ft->rx_icm_addr = rx_icm_addr;
+	recalc_cs_ft->table_id = table_id;
+	recalc_cs_ft->group_id = group_id;
+
+	return recalc_cs_ft;
+
+dealloc_modify_header:
+	mlx5dr_cmd_dealloc_modify_header(dmn->mdev, modify_hdr_id);
+destroy_flow_group:
+	mlx5dr_cmd_destroy_flow_group(dmn->mdev,
+				      MLX5_FLOW_TABLE_TYPE_FDB,
+				      table_id, group_id);
+destroy_flow_table:
+	mlx5dr_cmd_destroy_flow_table(dmn->mdev, table_id, MLX5_FLOW_TABLE_TYPE_FDB);
+free_ttl_tbl:
+	kfree(recalc_cs_ft);
+	return NULL;
+}
+
+void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn,
+				    struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft)
+{
+	mlx5dr_cmd_del_flow_table_entry(dmn->mdev,
+					MLX5_FLOW_TABLE_TYPE_FDB,
+					recalc_cs_ft->table_id);
+	mlx5dr_cmd_dealloc_modify_header(dmn->mdev, recalc_cs_ft->modify_hdr_id);
+	mlx5dr_cmd_destroy_flow_group(dmn->mdev,
+				      MLX5_FLOW_TABLE_TYPE_FDB,
+				      recalc_cs_ft->table_id,
+				      recalc_cs_ft->group_id);
+	mlx5dr_cmd_destroy_flow_table(dmn->mdev,
+				      recalc_cs_ft->table_id,
+				      MLX5_FLOW_TABLE_TYPE_FDB);
+
+	kfree(recalc_cs_ft);
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c

@@ -0,0 +1,570 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64
+#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024)
+
+struct mlx5dr_icm_pool;
+
+struct mlx5dr_icm_bucket {
+	struct mlx5dr_icm_pool *pool;
+
+	/* Chunks that aren't visible to HW not directly and not in cache */
+	struct list_head free_list;
+	unsigned int free_list_count;
+
+	/* Used chunks, HW may be accessing this memory */
+	struct list_head used_list;
+	unsigned int used_list_count;
+
+	/* HW may be accessing this memory but at some future,
+	 * undetermined time, it might cease to do so. Before deciding to call
+	 * sync_ste, this list is moved to sync_list
+	 */
+	struct list_head hot_list;
+	unsigned int hot_list_count;
+
+	/* Pending sync list, entries from the hot list are moved to this list.
+	 * sync_ste is executed and then sync_list is concatenated to the free list
+	 */
+	struct list_head sync_list;
+	unsigned int sync_list_count;
+
+	u32 total_chunks;
+	u32 num_of_entries;
+	u32 entry_size;
+	/* protect the ICM bucket */
+	struct mutex mutex;
+};
+
+struct mlx5dr_icm_pool {
+	struct mlx5dr_icm_bucket *buckets;
+	enum mlx5dr_icm_type icm_type;
+	enum mlx5dr_icm_chunk_size max_log_chunk_sz;
+	enum mlx5dr_icm_chunk_size num_of_buckets;
+	struct list_head icm_mr_list;
+	/* protect the ICM MR list */
+	struct mutex mr_mutex;
+	struct mlx5dr_domain *dmn;
+};
+
+struct mlx5dr_icm_dm {
+	u32 obj_id;
+	enum mlx5_sw_icm_type type;
+	u64 addr;
+	size_t length;
+};
+
+struct mlx5dr_icm_mr {
+	struct mlx5dr_icm_pool *pool;
+	struct mlx5_core_mkey mkey;
+	struct mlx5dr_icm_dm dm;
+	size_t used_length;
+	size_t length;
+	u64 icm_start_addr;
+	struct list_head mr_list;
+};
+
+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 inlen = MLX5_ST_SZ_BYTES(create_mkey_in);
+	u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
+	void *mkc;
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+
+	MLX5_SET(mkc, mkc, access_mode_1_0, mode);
+	MLX5_SET(mkc, mkc, access_mode_4_2, (mode >> 2) & 0x7);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, lr, 1);
+	if (mode == MLX5_MKC_ACCESS_MODE_SW_ICM) {
+		MLX5_SET(mkc, mkc, rw, 1);
+		MLX5_SET(mkc, mkc, rr, 1);
+	}
+
+	MLX5_SET64(mkc, mkc, len, length);
+	MLX5_SET(mkc, mkc, pd, pd);
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+	MLX5_SET64(mkc, mkc, start_addr, start_addr);
+
+	return mlx5_core_create_mkey(mdev, mkey, in, inlen);
+}
+
+static struct mlx5dr_icm_mr *
+dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool,
+		      enum mlx5_sw_icm_type type,
+		      size_t align_base)
+{
+	struct mlx5_core_dev *mdev = pool->dmn->mdev;
+	struct mlx5dr_icm_mr *icm_mr;
+	size_t align_diff;
+	int err;
+
+	icm_mr = kvzalloc(sizeof(*icm_mr), GFP_KERNEL);
+	if (!icm_mr)
+		return NULL;
+
+	icm_mr->pool = pool;
+	INIT_LIST_HEAD(&icm_mr->mr_list);
+
+	icm_mr->dm.type = type;
+
+	/* 2^log_biggest_table * entry-size * double-for-alignment */
+	icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
+							       pool->icm_type) * 2;
+
+	err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0,
+				   &icm_mr->dm.addr, &icm_mr->dm.obj_id);
+	if (err) {
+		mlx5dr_err(pool->dmn, "Failed to allocate SW ICM memory, err (%d)\n", err);
+		goto free_icm_mr;
+	}
+
+	/* Register device memory */
+	err = dr_icm_create_dm_mkey(mdev, pool->dmn->pdn,
+				    icm_mr->dm.length,
+				    icm_mr->dm.addr,
+				    MLX5_MKC_ACCESS_MODE_SW_ICM,
+				    &icm_mr->mkey);
+	if (err) {
+		mlx5dr_err(pool->dmn, "Failed to create SW ICM MKEY, err (%d)\n", err);
+		goto free_dm;
+	}
+
+	icm_mr->icm_start_addr = icm_mr->dm.addr;
+
+	align_diff = icm_mr->icm_start_addr % align_base;
+	if (align_diff)
+		icm_mr->used_length = align_base - align_diff;
+
+	list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list);
+
+	return icm_mr;
+
+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);
+free_icm_mr:
+	kvfree(icm_mr);
+	return NULL;
+}
+
+static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr)
+{
+	struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev;
+	struct mlx5dr_icm_dm *dm = &icm_mr->dm;
+
+	list_del(&icm_mr->mr_list);
+	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);
+}
+
+static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk)
+{
+	struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+	chunk->ste_arr = kvzalloc(bucket->num_of_entries *
+				  sizeof(chunk->ste_arr[0]), GFP_KERNEL);
+	if (!chunk->ste_arr)
+		return -ENOMEM;
+
+	chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries *
+				     DR_STE_SIZE_REDUCED, GFP_KERNEL);
+	if (!chunk->hw_ste_arr)
+		goto out_free_ste_arr;
+
+	chunk->miss_list = kvmalloc(bucket->num_of_entries *
+				    sizeof(chunk->miss_list[0]), GFP_KERNEL);
+	if (!chunk->miss_list)
+		goto out_free_hw_ste_arr;
+
+	return 0;
+
+out_free_hw_ste_arr:
+	kvfree(chunk->hw_ste_arr);
+out_free_ste_arr:
+	kvfree(chunk->ste_arr);
+	return -ENOMEM;
+}
+
+static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket)
+{
+	size_t mr_free_size, mr_req_size, mr_row_size;
+	struct mlx5dr_icm_pool *pool = bucket->pool;
+	struct mlx5dr_icm_mr *icm_mr = NULL;
+	struct mlx5dr_icm_chunk *chunk;
+	enum mlx5_sw_icm_type dm_type;
+	size_t align_base;
+	int i, err = 0;
+
+	mr_req_size = bucket->num_of_entries * bucket->entry_size;
+	mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz,
+							 pool->icm_type);
+
+	if (pool->icm_type == DR_ICM_TYPE_STE) {
+		dm_type = MLX5_SW_ICM_TYPE_STEERING;
+		/* Align base is the biggest chunk size / row size */
+		align_base = mr_row_size;
+	} else {
+		dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY;
+		/* Align base is 64B */
+		align_base = DR_ICM_MODIFY_HDR_ALIGN_BASE;
+	}
+
+	mutex_lock(&pool->mr_mutex);
+	if (!list_empty(&pool->icm_mr_list)) {
+		icm_mr = list_last_entry(&pool->icm_mr_list,
+					 struct mlx5dr_icm_mr, mr_list);
+
+		if (icm_mr)
+			mr_free_size = icm_mr->dm.length - icm_mr->used_length;
+	}
+
+	if (!icm_mr || mr_free_size < mr_row_size) {
+		icm_mr = dr_icm_pool_mr_create(pool, dm_type, align_base);
+		if (!icm_mr) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+	}
+
+	/* Create memory aligned chunks */
+	for (i = 0; i < mr_row_size / mr_req_size; i++) {
+		chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL);
+		if (!chunk) {
+			err = -ENOMEM;
+			goto out_err;
+		}
+
+		chunk->bucket = bucket;
+		chunk->rkey = icm_mr->mkey.key;
+		/* mr start addr is zero based */
+		chunk->mr_addr = icm_mr->used_length;
+		chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length;
+		icm_mr->used_length += mr_req_size;
+		chunk->num_of_entries = bucket->num_of_entries;
+		chunk->byte_size = chunk->num_of_entries * bucket->entry_size;
+
+		if (pool->icm_type == DR_ICM_TYPE_STE) {
+			err = dr_icm_chunk_ste_init(chunk);
+			if (err)
+				goto out_free_chunk;
+		}
+
+		INIT_LIST_HEAD(&chunk->chunk_list);
+		list_add(&chunk->chunk_list, &bucket->free_list);
+		bucket->free_list_count++;
+		bucket->total_chunks++;
+	}
+	mutex_unlock(&pool->mr_mutex);
+	return 0;
+
+out_free_chunk:
+	kvfree(chunk);
+out_err:
+	mutex_unlock(&pool->mr_mutex);
+	return err;
+}
+
+static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk)
+{
+	kvfree(chunk->miss_list);
+	kvfree(chunk->hw_ste_arr);
+	kvfree(chunk->ste_arr);
+}
+
+static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk)
+{
+	struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+	list_del(&chunk->chunk_list);
+	bucket->total_chunks--;
+
+	if (bucket->pool->icm_type == DR_ICM_TYPE_STE)
+		dr_icm_chunk_ste_cleanup(chunk);
+
+	kvfree(chunk);
+}
+
+static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool,
+			       struct mlx5dr_icm_bucket *bucket,
+			       enum mlx5dr_icm_chunk_size chunk_size)
+{
+	if (pool->icm_type == DR_ICM_TYPE_STE)
+		bucket->entry_size = DR_STE_SIZE;
+	else
+		bucket->entry_size = DR_MODIFY_ACTION_SIZE;
+
+	bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size);
+	bucket->pool = pool;
+	mutex_init(&bucket->mutex);
+	INIT_LIST_HEAD(&bucket->free_list);
+	INIT_LIST_HEAD(&bucket->used_list);
+	INIT_LIST_HEAD(&bucket->hot_list);
+	INIT_LIST_HEAD(&bucket->sync_list);
+}
+
+static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket)
+{
+	struct mlx5dr_icm_chunk *chunk, *next;
+
+	mutex_destroy(&bucket->mutex);
+	list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
+	list_splice_tail_init(&bucket->hot_list, &bucket->free_list);
+
+	list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list)
+		dr_icm_chunk_destroy(chunk);
+
+	WARN_ON(bucket->total_chunks != 0);
+
+	/* Cleanup of unreturned chunks */
+	list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list)
+		dr_icm_chunk_destroy(chunk);
+}
+
+static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool)
+{
+	u64 hot_size = 0;
+	int chunk_order;
+
+	for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++)
+		hot_size += pool->buckets[chunk_order].hot_list_count *
+			    mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type);
+
+	return hot_size;
+}
+
+static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool,
+				     struct mlx5dr_icm_bucket *bucket)
+{
+	u64 bytes_for_sync;
+
+	bytes_for_sync = dr_icm_hot_mem_size(pool);
+	if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count)
+		return false;
+
+	return true;
+}
+
+static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket)
+{
+	list_splice_tail_init(&bucket->hot_list, &bucket->sync_list);
+	bucket->sync_list_count += bucket->hot_list_count;
+	bucket->hot_list_count = 0;
+}
+
+static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket)
+{
+	list_splice_tail_init(&bucket->sync_list, &bucket->free_list);
+	bucket->free_list_count += bucket->sync_list_count;
+	bucket->sync_list_count = 0;
+}
+
+static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket)
+{
+	list_splice_tail_init(&bucket->sync_list, &bucket->hot_list);
+	bucket->hot_list_count += bucket->sync_list_count;
+	bucket->sync_list_count = 0;
+}
+
+static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool,
+				       struct mlx5dr_icm_bucket *cb,
+				       bool buckets[DR_CHUNK_SIZE_MAX])
+{
+	struct mlx5dr_icm_bucket *bucket;
+	int i;
+
+	for (i = 0; i < pool->num_of_buckets; i++) {
+		bucket = &pool->buckets[i];
+		if (bucket == cb) {
+			dr_icm_chill_bucket_start(bucket);
+			continue;
+		}
+
+		/* Freeing the mutex is done at the end of that process, after
+		 * sync_ste was executed at dr_icm_chill_buckets_end func.
+		 */
+		if (mutex_trylock(&bucket->mutex)) {
+			dr_icm_chill_bucket_start(bucket);
+			buckets[i] = true;
+		}
+	}
+}
+
+static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool,
+				     struct mlx5dr_icm_bucket *cb,
+				     bool buckets[DR_CHUNK_SIZE_MAX])
+{
+	struct mlx5dr_icm_bucket *bucket;
+	int i;
+
+	for (i = 0; i < pool->num_of_buckets; i++) {
+		bucket = &pool->buckets[i];
+		if (bucket == cb) {
+			dr_icm_chill_bucket_end(bucket);
+			continue;
+		}
+
+		if (!buckets[i])
+			continue;
+
+		dr_icm_chill_bucket_end(bucket);
+		mutex_unlock(&bucket->mutex);
+	}
+}
+
+static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool,
+				       struct mlx5dr_icm_bucket *cb,
+				       bool buckets[DR_CHUNK_SIZE_MAX])
+{
+	struct mlx5dr_icm_bucket *bucket;
+	int i;
+
+	for (i = 0; i < pool->num_of_buckets; i++) {
+		bucket = &pool->buckets[i];
+		if (bucket == cb) {
+			dr_icm_chill_bucket_abort(bucket);
+			continue;
+		}
+
+		if (!buckets[i])
+			continue;
+
+		dr_icm_chill_bucket_abort(bucket);
+		mutex_unlock(&bucket->mutex);
+	}
+}
+
+/* Allocate an ICM chunk, each chunk holds a piece of ICM memory and
+ * also memory used for HW STE management for optimizations.
+ */
+struct mlx5dr_icm_chunk *
+mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool,
+		       enum mlx5dr_icm_chunk_size chunk_size)
+{
+	struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */
+	bool buckets[DR_CHUNK_SIZE_MAX] = {};
+	struct mlx5dr_icm_bucket *bucket;
+	int err;
+
+	if (chunk_size > pool->max_log_chunk_sz)
+		return NULL;
+
+	bucket = &pool->buckets[chunk_size];
+
+	mutex_lock(&bucket->mutex);
+
+	/* Take chunk from pool if available, otherwise allocate new chunks */
+	if (list_empty(&bucket->free_list)) {
+		if (dr_icm_reuse_hot_entries(pool, bucket)) {
+			dr_icm_chill_buckets_start(pool, bucket, buckets);
+			err = mlx5dr_cmd_sync_steering(pool->dmn->mdev);
+			if (err) {
+				dr_icm_chill_buckets_abort(pool, bucket, buckets);
+				mlx5dr_dbg(pool->dmn, "Sync_steering failed\n");
+				chunk = NULL;
+				goto out;
+			}
+			dr_icm_chill_buckets_end(pool, bucket, buckets);
+		} else {
+			dr_icm_chunks_create(bucket);
+		}
+	}
+
+	if (!list_empty(&bucket->free_list)) {
+		chunk = list_last_entry(&bucket->free_list,
+					struct mlx5dr_icm_chunk,
+					chunk_list);
+		if (chunk) {
+			list_del_init(&chunk->chunk_list);
+			list_add_tail(&chunk->chunk_list, &bucket->used_list);
+			bucket->free_list_count--;
+			bucket->used_list_count++;
+		}
+	}
+out:
+	mutex_unlock(&bucket->mutex);
+	return chunk;
+}
+
+void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk)
+{
+	struct mlx5dr_icm_bucket *bucket = chunk->bucket;
+
+	if (bucket->pool->icm_type == DR_ICM_TYPE_STE) {
+		memset(chunk->ste_arr, 0,
+		       bucket->num_of_entries * sizeof(chunk->ste_arr[0]));
+		memset(chunk->hw_ste_arr, 0,
+		       bucket->num_of_entries * DR_STE_SIZE_REDUCED);
+	}
+
+	mutex_lock(&bucket->mutex);
+	list_del_init(&chunk->chunk_list);
+	list_add_tail(&chunk->chunk_list, &bucket->hot_list);
+	bucket->hot_list_count++;
+	bucket->used_list_count--;
+	mutex_unlock(&bucket->mutex);
+}
+
+struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn,
+					       enum mlx5dr_icm_type icm_type)
+{
+	enum mlx5dr_icm_chunk_size max_log_chunk_sz;
+	struct mlx5dr_icm_pool *pool;
+	int i;
+
+	if (icm_type == DR_ICM_TYPE_STE)
+		max_log_chunk_sz = dmn->info.max_log_sw_icm_sz;
+	else
+		max_log_chunk_sz = dmn->info.max_log_action_icm_sz;
+
+	pool = kvzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return NULL;
+
+	pool->buckets = kcalloc(max_log_chunk_sz + 1,
+				sizeof(pool->buckets[0]),
+				GFP_KERNEL);
+	if (!pool->buckets)
+		goto free_pool;
+
+	pool->dmn = dmn;
+	pool->icm_type = icm_type;
+	pool->max_log_chunk_sz = max_log_chunk_sz;
+	pool->num_of_buckets = max_log_chunk_sz + 1;
+	INIT_LIST_HEAD(&pool->icm_mr_list);
+
+	for (i = 0; i < pool->num_of_buckets; i++)
+		dr_icm_bucket_init(pool, &pool->buckets[i], i);
+
+	mutex_init(&pool->mr_mutex);
+
+	return pool;
+
+free_pool:
+	kvfree(pool);
+	return NULL;
+}
+
+void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool)
+{
+	struct mlx5dr_icm_mr *icm_mr, *next;
+	int i;
+
+	mutex_destroy(&pool->mr_mutex);
+
+	list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list)
+		dr_icm_pool_mr_destroy(icm_mr);
+
+	for (i = 0; i < pool->num_of_buckets; i++)
+		dr_icm_bucket_cleanup(&pool->buckets[i]);
+
+	kfree(pool->buckets);
+	kvfree(pool);
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c

@@ -0,0 +1,770 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+static bool dr_mask_is_smac_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->smac_47_16 || spec->smac_15_0);
+}
+
+static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->dmac_47_16 || spec->dmac_15_0);
+}
+
+static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->src_ip_127_96 || spec->src_ip_95_64 ||
+		spec->src_ip_63_32 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->dst_ip_127_96 || spec->dst_ip_95_64 ||
+		spec->dst_ip_63_32 || spec->dst_ip_31_0);
+}
+
+static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->ip_protocol || spec->frag || spec->tcp_flags ||
+		spec->ip_ecn || spec->ip_dscp);
+}
+
+static bool dr_mask_is_tcp_udp_base_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->tcp_sport || spec->tcp_dport ||
+		spec->udp_sport || spec->udp_dport);
+}
+
+static bool dr_mask_is_ipv4_set(struct mlx5dr_match_spec *spec)
+{
+	return (spec->dst_ip_31_0 || spec->src_ip_31_0);
+}
+
+static bool dr_mask_is_ipv4_5_tuple_set(struct mlx5dr_match_spec *spec)
+{
+	return (dr_mask_is_l3_base_set(spec) ||
+		dr_mask_is_tcp_udp_base_set(spec) ||
+		dr_mask_is_ipv4_set(spec));
+}
+
+static bool dr_mask_is_eth_l2_tnl_set(struct mlx5dr_match_misc *misc)
+{
+	return misc->vxlan_vni;
+}
+
+static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec)
+{
+	return spec->ttl_hoplimit;
+}
+
+#define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \
+	(_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \
+	(_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \
+	(_spec).ethertype || (_spec).ip_version || \
+	(_misc)._inner_outer##_second_vid || \
+	(_misc)._inner_outer##_second_cfi || \
+	(_misc)._inner_outer##_second_prio || \
+	(_misc)._inner_outer##_second_cvlan_tag || \
+	(_misc)._inner_outer##_second_svlan_tag)
+
+#define DR_MASK_IS_ETH_L4_SET(_spec, _misc, _inner_outer) ( \
+	dr_mask_is_l3_base_set(&(_spec)) || \
+	dr_mask_is_tcp_udp_base_set(&(_spec)) || \
+	dr_mask_is_ttl_set(&(_spec)) || \
+	(_misc)._inner_outer##_ipv6_flow_label)
+
+#define DR_MASK_IS_ETH_L4_MISC_SET(_misc3, _inner_outer) ( \
+	(_misc3)._inner_outer##_tcp_seq_num || \
+	(_misc3)._inner_outer##_tcp_ack_num)
+
+#define DR_MASK_IS_FIRST_MPLS_SET(_misc2, _inner_outer) ( \
+	(_misc2)._inner_outer##_first_mpls_label || \
+	(_misc2)._inner_outer##_first_mpls_exp || \
+	(_misc2)._inner_outer##_first_mpls_s_bos || \
+	(_misc2)._inner_outer##_first_mpls_ttl)
+
+static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc)
+{
+	return (misc->gre_key_h || misc->gre_key_l ||
+		misc->gre_protocol || misc->gre_c_present ||
+		misc->gre_k_present || misc->gre_s_present);
+}
+
+#define DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET(_misc2, gre_udp) ( \
+	(_misc2).outer_first_mpls_over_##gre_udp##_label || \
+	(_misc2).outer_first_mpls_over_##gre_udp##_exp || \
+	(_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \
+	(_misc2).outer_first_mpls_over_##gre_udp##_ttl)
+
+#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \
+	DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \
+	DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp))
+
+static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3)
+{
+	return (misc3->outer_vxlan_gpe_vni ||
+		misc3->outer_vxlan_gpe_next_protocol ||
+		misc3->outer_vxlan_gpe_flags);
+}
+
+static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
+{
+	return (misc3->icmpv6_type || misc3->icmpv6_code ||
+		misc3->icmpv6_header_data);
+}
+
+static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2)
+{
+	return misc2->metadata_reg_a;
+}
+
+static bool dr_mask_is_reg_c_0_3_set(struct mlx5dr_match_misc2 *misc2)
+{
+	return (misc2->metadata_reg_c_0 || misc2->metadata_reg_c_1 ||
+		misc2->metadata_reg_c_2 || misc2->metadata_reg_c_3);
+}
+
+static bool dr_mask_is_reg_c_4_7_set(struct mlx5dr_match_misc2 *misc2)
+{
+	return (misc2->metadata_reg_c_4 || misc2->metadata_reg_c_5 ||
+		misc2->metadata_reg_c_6 || misc2->metadata_reg_c_7);
+}
+
+static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc)
+{
+	return (misc->source_sqn || misc->source_port);
+}
+
+static bool
+dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn)
+{
+	return dmn->info.caps.flex_protocols &
+	       MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+}
+
+int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
+				   struct mlx5dr_matcher_rx_tx *nic_matcher,
+				   bool ipv6)
+{
+	if (ipv6) {
+		nic_matcher->ste_builder = nic_matcher->ste_builder6;
+		nic_matcher->num_of_builders = nic_matcher->num_of_builders6;
+	} else {
+		nic_matcher->ste_builder = nic_matcher->ste_builder4;
+		nic_matcher->num_of_builders = nic_matcher->num_of_builders4;
+	}
+
+	if (!nic_matcher->num_of_builders) {
+		mlx5dr_dbg(matcher->tbl->dmn,
+			   "Rule not supported on this matcher due to IP related fields\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
+				       struct mlx5dr_matcher_rx_tx *nic_matcher,
+				       bool ipv6)
+{
+	struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
+	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+	struct mlx5dr_match_param mask = {};
+	struct mlx5dr_match_misc3 *misc3;
+	struct mlx5dr_ste_build *sb;
+	u8 *num_of_builders;
+	bool inner, rx;
+	int idx = 0;
+	int ret, i;
+
+	if (ipv6) {
+		sb = nic_matcher->ste_builder6;
+		num_of_builders = &nic_matcher->num_of_builders6;
+	} else {
+		sb = nic_matcher->ste_builder4;
+		num_of_builders = &nic_matcher->num_of_builders4;
+	}
+
+	rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
+
+	/* Create a temporary mask to track and clear used mask fields */
+	if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER)
+		mask.outer = matcher->mask.outer;
+
+	if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC)
+		mask.misc = matcher->mask.misc;
+
+	if (matcher->match_criteria & DR_MATCHER_CRITERIA_INNER)
+		mask.inner = matcher->mask.inner;
+
+	if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC2)
+		mask.misc2 = matcher->mask.misc2;
+
+	if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC3)
+		mask.misc3 = matcher->mask.misc3;
+
+	ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria,
+					 &matcher->mask, NULL);
+	if (ret)
+		return ret;
+
+	/* Outer */
+	if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER |
+				       DR_MATCHER_CRITERIA_MISC |
+				       DR_MATCHER_CRITERIA_MISC2 |
+				       DR_MATCHER_CRITERIA_MISC3)) {
+		inner = false;
+
+		if (dr_mask_is_wqe_metadata_set(&mask.misc2))
+			mlx5dr_ste_build_general_purpose(&sb[idx++], &mask, inner, rx);
+
+		if (dr_mask_is_reg_c_0_3_set(&mask.misc2))
+			mlx5dr_ste_build_register_0(&sb[idx++], &mask, inner, rx);
+
+		if (dr_mask_is_reg_c_4_7_set(&mask.misc2))
+			mlx5dr_ste_build_register_1(&sb[idx++], &mask, inner, rx);
+
+		if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) &&
+		    (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+		     dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) {
+			ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask,
+							    &dmn->info.caps,
+							    inner, rx);
+			if (ret)
+				return ret;
+		}
+
+		if (dr_mask_is_smac_set(&mask.outer) &&
+		    dr_mask_is_dmac_set(&mask.outer)) {
+			ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask,
+							      inner, rx);
+			if (ret)
+				return ret;
+		}
+
+		if (dr_mask_is_smac_set(&mask.outer))
+			mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer))
+			mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+		if (ipv6) {
+			if (dr_mask_is_dst_addr_set(&mask.outer))
+				mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+								 inner, rx);
+
+			if (dr_mask_is_src_addr_set(&mask.outer))
+				mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+								 inner, rx);
+
+			if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer))
+				mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+							    inner, rx);
+		} else {
+			if (dr_mask_is_ipv4_5_tuple_set(&mask.outer))
+				mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+								     inner, rx);
+
+			if (dr_mask_is_ttl_set(&mask.outer))
+				mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+								  inner, rx);
+		}
+
+		if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) &&
+		    dr_matcher_supp_flex_parser_vxlan_gpe(dmn))
+			mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask,
+							 inner, rx);
+
+		if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer))
+			mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer))
+			mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+			mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask,
+						       inner, rx);
+
+		misc3 = &mask.misc3;
+		if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) &&
+		     mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) ||
+		    (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) &&
+		     mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) {
+			ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++],
+							     &mask, &dmn->info.caps,
+							     inner, rx);
+			if (ret)
+				return ret;
+		}
+		if (dr_mask_is_gre_set(&mask.misc))
+			mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx);
+	}
+
+	/* Inner */
+	if (matcher->match_criteria & (DR_MATCHER_CRITERIA_INNER |
+				       DR_MATCHER_CRITERIA_MISC |
+				       DR_MATCHER_CRITERIA_MISC2 |
+				       DR_MATCHER_CRITERIA_MISC3)) {
+		inner = true;
+
+		if (dr_mask_is_eth_l2_tnl_set(&mask.misc))
+			mlx5dr_ste_build_eth_l2_tnl(&sb[idx++], &mask, inner, rx);
+
+		if (dr_mask_is_smac_set(&mask.inner) &&
+		    dr_mask_is_dmac_set(&mask.inner)) {
+			ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++],
+							      &mask, inner, rx);
+			if (ret)
+				return ret;
+		}
+
+		if (dr_mask_is_smac_set(&mask.inner))
+			mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner))
+			mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
+
+		if (ipv6) {
+			if (dr_mask_is_dst_addr_set(&mask.inner))
+				mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
+								 inner, rx);
+
+			if (dr_mask_is_src_addr_set(&mask.inner))
+				mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask,
+								 inner, rx);
+
+			if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner))
+				mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask,
+							    inner, rx);
+		} else {
+			if (dr_mask_is_ipv4_5_tuple_set(&mask.inner))
+				mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask,
+								     inner, rx);
+
+			if (dr_mask_is_ttl_set(&mask.inner))
+				mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask,
+								  inner, rx);
+		}
+
+		if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, inner))
+			mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner))
+			mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx);
+
+		if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2))
+			mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx);
+	}
+	/* Empty matcher, takes all */
+	if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY)
+		mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx);
+
+	if (idx == 0) {
+		mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n");
+		return -EINVAL;
+	}
+
+	/* Check that all mask fields were consumed */
+	for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) {
+		if (((u8 *)&mask)[i] != 0) {
+			mlx5dr_info(dmn, "Mask contains unsupported parameters\n");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	*num_of_builders = idx;
+
+	return 0;
+}
+
+static int dr_matcher_connect(struct mlx5dr_domain *dmn,
+			      struct mlx5dr_matcher_rx_tx *curr_nic_matcher,
+			      struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+			      struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+	struct mlx5dr_table_rx_tx *nic_tbl = curr_nic_matcher->nic_tbl;
+	struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+	struct mlx5dr_htbl_connect_info info;
+	struct mlx5dr_ste_htbl *prev_htbl;
+	int ret;
+
+	/* Connect end anchor hash table to next_htbl or to the default address */
+	if (next_nic_matcher) {
+		info.type = CONNECT_HIT;
+		info.hit_next_htbl = next_nic_matcher->s_htbl;
+	} else {
+		info.type = CONNECT_MISS;
+		info.miss_icm_addr = nic_tbl->default_icm_addr;
+	}
+	ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+						curr_nic_matcher->e_anchor,
+						&info, info.type == CONNECT_HIT);
+	if (ret)
+		return ret;
+
+	/* Connect start hash table to end anchor */
+	info.type = CONNECT_MISS;
+	info.miss_icm_addr = curr_nic_matcher->e_anchor->chunk->icm_addr;
+	ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+						curr_nic_matcher->s_htbl,
+						&info, false);
+	if (ret)
+		return ret;
+
+	/* Connect previous hash table to matcher start hash table */
+	if (prev_nic_matcher)
+		prev_htbl = prev_nic_matcher->e_anchor;
+	else
+		prev_htbl = nic_tbl->s_anchor;
+
+	info.type = CONNECT_HIT;
+	info.hit_next_htbl = curr_nic_matcher->s_htbl;
+	ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_htbl,
+						&info, true);
+	if (ret)
+		return ret;
+
+	/* Update the pointing ste and next hash table */
+	curr_nic_matcher->s_htbl->pointing_ste = prev_htbl->ste_arr;
+	prev_htbl->ste_arr[0].next_htbl = curr_nic_matcher->s_htbl;
+
+	if (next_nic_matcher) {
+		next_nic_matcher->s_htbl->pointing_ste = curr_nic_matcher->e_anchor->ste_arr;
+		curr_nic_matcher->e_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+	}
+
+	return 0;
+}
+
+static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher)
+{
+	struct mlx5dr_matcher *next_matcher, *prev_matcher, *tmp_matcher;
+	struct mlx5dr_table *tbl = matcher->tbl;
+	struct mlx5dr_domain *dmn = tbl->dmn;
+	bool first = true;
+	int ret;
+
+	next_matcher = NULL;
+	if (!list_empty(&tbl->matcher_list))
+		list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) {
+			if (tmp_matcher->prio >= matcher->prio) {
+				next_matcher = tmp_matcher;
+				break;
+			}
+			first = false;
+		}
+
+	prev_matcher = NULL;
+	if (next_matcher && !first)
+		prev_matcher = list_entry(next_matcher->matcher_list.prev,
+					  struct mlx5dr_matcher,
+					  matcher_list);
+	else if (!first)
+		prev_matcher = list_entry(tbl->matcher_list.prev,
+					  struct mlx5dr_matcher,
+					  matcher_list);
+
+	if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+	    dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+		ret = dr_matcher_connect(dmn, &matcher->rx,
+					 next_matcher ? &next_matcher->rx : NULL,
+					 prev_matcher ?	&prev_matcher->rx : NULL);
+		if (ret)
+			return ret;
+	}
+
+	if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+	    dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+		ret = dr_matcher_connect(dmn, &matcher->tx,
+					 next_matcher ? &next_matcher->tx : NULL,
+					 prev_matcher ?	&prev_matcher->tx : NULL);
+		if (ret)
+			return ret;
+	}
+
+	if (prev_matcher)
+		list_add(&matcher->matcher_list, &prev_matcher->matcher_list);
+	else if (next_matcher)
+		list_add_tail(&matcher->matcher_list,
+			      &next_matcher->matcher_list);
+	else
+		list_add(&matcher->matcher_list, &tbl->matcher_list);
+
+	return 0;
+}
+
+static void dr_matcher_uninit_nic(struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+	mlx5dr_htbl_put(nic_matcher->s_htbl);
+	mlx5dr_htbl_put(nic_matcher->e_anchor);
+}
+
+static void dr_matcher_uninit_fdb(struct mlx5dr_matcher *matcher)
+{
+	dr_matcher_uninit_nic(&matcher->rx);
+	dr_matcher_uninit_nic(&matcher->tx);
+}
+
+static void dr_matcher_uninit(struct mlx5dr_matcher *matcher)
+{
+	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+
+	switch (dmn->type) {
+	case MLX5DR_DOMAIN_TYPE_NIC_RX:
+		dr_matcher_uninit_nic(&matcher->rx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_NIC_TX:
+		dr_matcher_uninit_nic(&matcher->tx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_FDB:
+		dr_matcher_uninit_fdb(matcher);
+		break;
+	default:
+		WARN_ON(true);
+		break;
+	}
+}
+
+static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
+			       struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+	int ret, ret_v4, ret_v6;
+
+	ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false);
+	ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true);
+
+	if (ret_v4 && ret_v6) {
+		mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n");
+		return -EINVAL;
+	}
+
+	if (!ret_v4)
+		nic_matcher->ste_builder = nic_matcher->ste_builder4;
+	else
+		nic_matcher->ste_builder = nic_matcher->ste_builder6;
+
+	nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+						      DR_CHUNK_SIZE_1,
+						      MLX5DR_STE_LU_TYPE_DONT_CARE,
+						      0);
+	if (!nic_matcher->e_anchor)
+		return -ENOMEM;
+
+	nic_matcher->s_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+						    DR_CHUNK_SIZE_1,
+						    nic_matcher->ste_builder[0].lu_type,
+						    nic_matcher->ste_builder[0].byte_mask);
+	if (!nic_matcher->s_htbl) {
+		ret = -ENOMEM;
+		goto free_e_htbl;
+	}
+
+	/* make sure the tables exist while empty */
+	mlx5dr_htbl_get(nic_matcher->s_htbl);
+	mlx5dr_htbl_get(nic_matcher->e_anchor);
+
+	return 0;
+
+free_e_htbl:
+	mlx5dr_ste_htbl_free(nic_matcher->e_anchor);
+	return ret;
+}
+
+static int dr_matcher_init_fdb(struct mlx5dr_matcher *matcher)
+{
+	int ret;
+
+	ret = dr_matcher_init_nic(matcher, &matcher->rx);
+	if (ret)
+		return ret;
+
+	ret = dr_matcher_init_nic(matcher, &matcher->tx);
+	if (ret)
+		goto uninit_nic_rx;
+
+	return 0;
+
+uninit_nic_rx:
+	dr_matcher_uninit_nic(&matcher->rx);
+	return ret;
+}
+
+static int dr_matcher_init(struct mlx5dr_matcher *matcher,
+			   struct mlx5dr_match_parameters *mask)
+{
+	struct mlx5dr_table *tbl = matcher->tbl;
+	struct mlx5dr_domain *dmn = tbl->dmn;
+	int ret;
+
+	if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) {
+		mlx5dr_info(dmn, "Invalid match criteria attribute\n");
+		return -EINVAL;
+	}
+
+	if (mask) {
+		if (mask->match_sz > sizeof(struct mlx5dr_match_param)) {
+			mlx5dr_info(dmn, "Invalid match size attribute\n");
+			return -EINVAL;
+		}
+		mlx5dr_ste_copy_param(matcher->match_criteria,
+				      &matcher->mask, mask);
+	}
+
+	switch (dmn->type) {
+	case MLX5DR_DOMAIN_TYPE_NIC_RX:
+		matcher->rx.nic_tbl = &tbl->rx;
+		ret = dr_matcher_init_nic(matcher, &matcher->rx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_NIC_TX:
+		matcher->tx.nic_tbl = &tbl->tx;
+		ret = dr_matcher_init_nic(matcher, &matcher->tx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_FDB:
+		matcher->rx.nic_tbl = &tbl->rx;
+		matcher->tx.nic_tbl = &tbl->tx;
+		ret = dr_matcher_init_fdb(matcher);
+		break;
+	default:
+		WARN_ON(true);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *tbl,
+		      u16 priority,
+		      u8 match_criteria_enable,
+		      struct mlx5dr_match_parameters *mask)
+{
+	struct mlx5dr_matcher *matcher;
+	int ret;
+
+	refcount_inc(&tbl->refcount);
+
+	matcher = kzalloc(sizeof(*matcher), GFP_KERNEL);
+	if (!matcher)
+		goto dec_ref;
+
+	matcher->tbl = tbl;
+	matcher->prio = priority;
+	matcher->match_criteria = match_criteria_enable;
+	refcount_set(&matcher->refcount, 1);
+	INIT_LIST_HEAD(&matcher->matcher_list);
+
+	mutex_lock(&tbl->dmn->mutex);
+
+	ret = dr_matcher_init(matcher, mask);
+	if (ret)
+		goto free_matcher;
+
+	ret = dr_matcher_add_to_tbl(matcher);
+	if (ret)
+		goto matcher_uninit;
+
+	mutex_unlock(&tbl->dmn->mutex);
+
+	return matcher;
+
+matcher_uninit:
+	dr_matcher_uninit(matcher);
+free_matcher:
+	mutex_unlock(&tbl->dmn->mutex);
+	kfree(matcher);
+dec_ref:
+	refcount_dec(&tbl->refcount);
+	return NULL;
+}
+
+static int dr_matcher_disconnect(struct mlx5dr_domain *dmn,
+				 struct mlx5dr_table_rx_tx *nic_tbl,
+				 struct mlx5dr_matcher_rx_tx *next_nic_matcher,
+				 struct mlx5dr_matcher_rx_tx *prev_nic_matcher)
+{
+	struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+	struct mlx5dr_htbl_connect_info info;
+	struct mlx5dr_ste_htbl *prev_anchor;
+
+	if (prev_nic_matcher)
+		prev_anchor = prev_nic_matcher->e_anchor;
+	else
+		prev_anchor = nic_tbl->s_anchor;
+
+	/* Connect previous anchor hash table to next matcher or to the default address */
+	if (next_nic_matcher) {
+		info.type = CONNECT_HIT;
+		info.hit_next_htbl = next_nic_matcher->s_htbl;
+		next_nic_matcher->s_htbl->pointing_ste = prev_anchor->ste_arr;
+		prev_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl;
+	} else {
+		info.type = CONNECT_MISS;
+		info.miss_icm_addr = nic_tbl->default_icm_addr;
+		prev_anchor->ste_arr[0].next_htbl = NULL;
+	}
+
+	return mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_anchor,
+						 &info, true);
+}
+
+static int dr_matcher_remove_from_tbl(struct mlx5dr_matcher *matcher)
+{
+	struct mlx5dr_matcher *prev_matcher, *next_matcher;
+	struct mlx5dr_table *tbl = matcher->tbl;
+	struct mlx5dr_domain *dmn = tbl->dmn;
+	int ret = 0;
+
+	if (list_is_last(&matcher->matcher_list, &tbl->matcher_list))
+		next_matcher = NULL;
+	else
+		next_matcher = list_next_entry(matcher, matcher_list);
+
+	if (matcher->matcher_list.prev == &tbl->matcher_list)
+		prev_matcher = NULL;
+	else
+		prev_matcher = list_prev_entry(matcher, matcher_list);
+
+	if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+	    dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) {
+		ret = dr_matcher_disconnect(dmn, &tbl->rx,
+					    next_matcher ? &next_matcher->rx : NULL,
+					    prev_matcher ? &prev_matcher->rx : NULL);
+		if (ret)
+			return ret;
+	}
+
+	if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB ||
+	    dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) {
+		ret = dr_matcher_disconnect(dmn, &tbl->tx,
+					    next_matcher ? &next_matcher->tx : NULL,
+					    prev_matcher ? &prev_matcher->tx : NULL);
+		if (ret)
+			return ret;
+	}
+
+	list_del(&matcher->matcher_list);
+
+	return 0;
+}
+
+int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher)
+{
+	struct mlx5dr_table *tbl = matcher->tbl;
+
+	if (refcount_read(&matcher->refcount) > 1)
+		return -EBUSY;
+
+	mutex_lock(&tbl->dmn->mutex);
+
+	dr_matcher_remove_from_tbl(matcher);
+	dr_matcher_uninit(matcher);
+	refcount_dec(&matcher->tbl->refcount);
+
+	mutex_unlock(&tbl->dmn->mutex);
+	kfree(matcher);
+
+	return 0;
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c

@@ -0,0 +1,976 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+#define QUEUE_SIZE 128
+#define SIGNAL_PER_DIV_QUEUE 16
+#define TH_NUMS_TO_DRAIN 2
+
+enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 };
+
+struct dr_data_seg {
+	u64 addr;
+	u32 length;
+	u32 lkey;
+	unsigned int send_flags;
+};
+
+struct postsend_info {
+	struct dr_data_seg write;
+	struct dr_data_seg read;
+	u64 remote_addr;
+	u32 rkey;
+};
+
+struct dr_qp_rtr_attr {
+	struct mlx5dr_cmd_gid_attr dgid_attr;
+	enum ib_mtu mtu;
+	u32 qp_num;
+	u16 port_num;
+	u8 min_rnr_timer;
+	u8 sgid_index;
+	u16 udp_src_port;
+};
+
+struct dr_qp_rts_attr {
+	u8 timeout;
+	u8 retry_cnt;
+	u8 rnr_retry;
+};
+
+struct dr_qp_init_attr {
+	u32 cqn;
+	u32 pdn;
+	u32 max_send_wr;
+	struct mlx5_uars_page *uar;
+};
+
+static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64)
+{
+	unsigned int idx;
+	u8 opcode;
+
+	opcode = get_cqe_opcode(cqe64);
+	if (opcode == MLX5_CQE_REQ_ERR) {
+		idx = be16_to_cpu(cqe64->wqe_counter) &
+			(dr_cq->qp->sq.wqe_cnt - 1);
+		dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+	} else if (opcode == MLX5_CQE_RESP_ERR) {
+		++dr_cq->qp->sq.cc;
+	} else {
+		idx = be16_to_cpu(cqe64->wqe_counter) &
+			(dr_cq->qp->sq.wqe_cnt - 1);
+		dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1;
+
+		return CQ_OK;
+	}
+
+	return CQ_POLL_ERR;
+}
+
+static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq)
+{
+	struct mlx5_cqe64 *cqe64;
+	int err;
+
+	cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq);
+	if (!cqe64)
+		return CQ_EMPTY;
+
+	mlx5_cqwq_pop(&dr_cq->wq);
+	err = dr_parse_cqe(dr_cq, cqe64);
+	mlx5_cqwq_update_db_record(&dr_cq->wq);
+
+	return err;
+}
+
+static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne)
+{
+	int npolled;
+	int err = 0;
+
+	for (npolled = 0; npolled < ne; ++npolled) {
+		err = dr_cq_poll_one(dr_cq);
+		if (err != CQ_OK)
+			break;
+	}
+
+	return err == CQ_POLL_ERR ? err : npolled;
+}
+
+static void dr_qp_event(struct mlx5_core_qp *mqp, int event)
+{
+	pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn);
+}
+
+static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev,
+					 struct dr_qp_init_attr *attr)
+{
+	u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {};
+	struct mlx5_wq_param wqp;
+	struct mlx5dr_qp *dr_qp;
+	int inlen;
+	void *qpc;
+	void *in;
+	int err;
+
+	dr_qp = kzalloc(sizeof(*dr_qp), GFP_KERNEL);
+	if (!dr_qp)
+		return NULL;
+
+	wqp.buf_numa_node = mdev->priv.numa_node;
+	wqp.db_numa_node = mdev->priv.numa_node;
+
+	dr_qp->rq.pc = 0;
+	dr_qp->rq.cc = 0;
+	dr_qp->rq.wqe_cnt = 4;
+	dr_qp->sq.pc = 0;
+	dr_qp->sq.cc = 0;
+	dr_qp->sq.wqe_cnt = roundup_pow_of_two(attr->max_send_wr);
+
+	MLX5_SET(qpc, temp_qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+	MLX5_SET(qpc, temp_qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+	MLX5_SET(qpc, temp_qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+	err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq,
+				&dr_qp->wq_ctrl);
+	if (err) {
+		mlx5_core_info(mdev, "Can't create QP WQ\n");
+		goto err_wq;
+	}
+
+	dr_qp->sq.wqe_head = kcalloc(dr_qp->sq.wqe_cnt,
+				     sizeof(dr_qp->sq.wqe_head[0]),
+				     GFP_KERNEL);
+
+	if (!dr_qp->sq.wqe_head) {
+		mlx5_core_warn(mdev, "Can't allocate wqe head\n");
+		goto err_wqe_head;
+	}
+
+	inlen = MLX5_ST_SZ_BYTES(create_qp_in) +
+		MLX5_FLD_SZ_BYTES(create_qp_in, pas[0]) *
+		dr_qp->wq_ctrl.buf.npages;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_in;
+	}
+
+	qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+	MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC);
+	MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
+	MLX5_SET(qpc, qpc, pd, attr->pdn);
+	MLX5_SET(qpc, qpc, uar_page, attr->uar->index);
+	MLX5_SET(qpc, qpc, log_page_size,
+		 dr_qp->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET(qpc, qpc, fre, 1);
+	MLX5_SET(qpc, qpc, rlky, 1);
+	MLX5_SET(qpc, qpc, cqn_snd, attr->cqn);
+	MLX5_SET(qpc, qpc, cqn_rcv, attr->cqn);
+	MLX5_SET(qpc, qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4);
+	MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
+	MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
+	MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+	MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma);
+	if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
+		MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
+	mlx5_fill_page_frag_array(&dr_qp->wq_ctrl.buf,
+				  (__be64 *)MLX5_ADDR_OF(create_qp_in,
+							 in, pas));
+
+	err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen);
+	kfree(in);
+
+	if (err) {
+		mlx5_core_warn(mdev, " Can't create QP\n");
+		goto err_in;
+	}
+	dr_qp->mqp.event = dr_qp_event;
+	dr_qp->uar = attr->uar;
+
+	return dr_qp;
+
+err_in:
+	kfree(dr_qp->sq.wqe_head);
+err_wqe_head:
+	mlx5_wq_destroy(&dr_qp->wq_ctrl);
+err_wq:
+	kfree(dr_qp);
+	return NULL;
+}
+
+static void dr_destroy_qp(struct mlx5_core_dev *mdev,
+			  struct mlx5dr_qp *dr_qp)
+{
+	mlx5_core_destroy_qp(mdev, &dr_qp->mqp);
+	kfree(dr_qp->sq.wqe_head);
+	mlx5_wq_destroy(&dr_qp->wq_ctrl);
+	kfree(dr_qp);
+}
+
+static void dr_cmd_notify_hw(struct mlx5dr_qp *dr_qp, void *ctrl)
+{
+	dma_wmb();
+	*dr_qp->wq.sq.db = cpu_to_be32(dr_qp->sq.pc & 0xfffff);
+
+	/* After wmb() the hw aware of new work */
+	wmb();
+
+	mlx5_write64(ctrl, dr_qp->uar->map + MLX5_BF_OFFSET);
+}
+
+static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr,
+			     u32 rkey, struct dr_data_seg *data_seg,
+			     u32 opcode, int nreq)
+{
+	struct mlx5_wqe_raddr_seg *wq_raddr;
+	struct mlx5_wqe_ctrl_seg *wq_ctrl;
+	struct mlx5_wqe_data_seg *wq_dseg;
+	unsigned int size;
+	unsigned int idx;
+
+	size = sizeof(*wq_ctrl) / 16 + sizeof(*wq_dseg) / 16 +
+		sizeof(*wq_raddr) / 16;
+
+	idx = dr_qp->sq.pc & (dr_qp->sq.wqe_cnt - 1);
+
+	wq_ctrl = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx);
+	wq_ctrl->imm = 0;
+	wq_ctrl->fm_ce_se = (data_seg->send_flags) ?
+		MLX5_WQE_CTRL_CQ_UPDATE : 0;
+	wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) |
+						opcode);
+	wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8);
+	wq_raddr = (void *)(wq_ctrl + 1);
+	wq_raddr->raddr = cpu_to_be64(remote_addr);
+	wq_raddr->rkey = cpu_to_be32(rkey);
+	wq_raddr->reserved = 0;
+
+	wq_dseg = (void *)(wq_raddr + 1);
+	wq_dseg->byte_count = cpu_to_be32(data_seg->length);
+	wq_dseg->lkey = cpu_to_be32(data_seg->lkey);
+	wq_dseg->addr = cpu_to_be64(data_seg->addr);
+
+	dr_qp->sq.wqe_head[idx] = dr_qp->sq.pc++;
+
+	if (nreq)
+		dr_cmd_notify_hw(dr_qp, wq_ctrl);
+}
+
+static void dr_post_send(struct mlx5dr_qp *dr_qp, struct postsend_info *send_info)
+{
+	dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+			 &send_info->write, MLX5_OPCODE_RDMA_WRITE, 0);
+	dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey,
+			 &send_info->read, MLX5_OPCODE_RDMA_READ, 1);
+}
+
+/**
+ * mlx5dr_send_fill_and_append_ste_send_info: Add data to be sent
+ * with send_list parameters:
+ *
+ *     @ste:       The data that attached to this specific ste
+ *     @size:      of data to write
+ *     @offset:    of the data from start of the hw_ste entry
+ *     @data:      data
+ *     @ste_info:  ste to be sent with send_list
+ *     @send_list: to append into it
+ *     @copy_data: if true indicates that the data should be kept because
+ *                 it's not backuped any where (like in re-hash).
+ *                 if false, it lets the data to be updated after
+ *                 it was added to the list.
+ */
+void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size,
+					       u16 offset, u8 *data,
+					       struct mlx5dr_ste_send_info *ste_info,
+					       struct list_head *send_list,
+					       bool copy_data)
+{
+	ste_info->size = size;
+	ste_info->ste = ste;
+	ste_info->offset = offset;
+
+	if (copy_data) {
+		memcpy(ste_info->data_cont, data, size);
+		ste_info->data = ste_info->data_cont;
+	} else {
+		ste_info->data = data;
+	}
+
+	list_add_tail(&ste_info->send_list, send_list);
+}
+
+/* The function tries to consume one wc each time, unless the queue is full, in
+ * that case, which means that the hw is behind the sw in a full queue len
+ * the function will drain the cq till it empty.
+ */
+static int dr_handle_pending_wc(struct mlx5dr_domain *dmn,
+				struct mlx5dr_send_ring *send_ring)
+{
+	bool is_drain = false;
+	int ne;
+
+	if (send_ring->pending_wqe < send_ring->signal_th)
+		return 0;
+
+	/* Queue is full start drain it */
+	if (send_ring->pending_wqe >=
+	    dmn->send_ring->signal_th * TH_NUMS_TO_DRAIN)
+		is_drain = true;
+
+	do {
+		ne = dr_poll_cq(send_ring->cq, 1);
+		if (ne < 0)
+			return ne;
+		else if (ne == 1)
+			send_ring->pending_wqe -= send_ring->signal_th;
+	} while (is_drain && send_ring->pending_wqe);
+
+	return 0;
+}
+
+static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring,
+			      struct postsend_info *send_info)
+{
+	send_ring->pending_wqe++;
+
+	if (send_ring->pending_wqe % send_ring->signal_th == 0)
+		send_info->write.send_flags |= IB_SEND_SIGNALED;
+
+	send_ring->pending_wqe++;
+	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;
+
+	if (send_ring->pending_wqe % send_ring->signal_th == 0)
+		send_info->read.send_flags = IB_SEND_SIGNALED;
+	else
+		send_info->read.send_flags = 0;
+}
+
+static int dr_postsend_icm_data(struct mlx5dr_domain *dmn,
+				struct postsend_info *send_info)
+{
+	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+	u32 buff_offset;
+	int ret;
+
+	ret = dr_handle_pending_wc(dmn, send_ring);
+	if (ret)
+		return ret;
+
+	if (send_info->write.length > dmn->info.max_inline_size) {
+		buff_offset = (send_ring->tx_head &
+			       (dmn->send_ring->signal_th - 1)) *
+			send_ring->max_post_send_size;
+		/* Copy to ring mr */
+		memcpy(send_ring->buf + buff_offset,
+		       (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_ring->tx_head++;
+	dr_fill_data_segs(send_ring, send_info);
+	dr_post_send(send_ring->qp, send_info);
+
+	return 0;
+}
+
+static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn,
+				   struct mlx5dr_ste_htbl *htbl,
+				   u8 **data,
+				   u32 *byte_size,
+				   int *iterations,
+				   int *num_stes)
+{
+	int alloc_size;
+
+	if (htbl->chunk->byte_size > dmn->send_ring->max_post_send_size) {
+		*iterations = htbl->chunk->byte_size /
+			dmn->send_ring->max_post_send_size;
+		*byte_size = dmn->send_ring->max_post_send_size;
+		alloc_size = *byte_size;
+		*num_stes = *byte_size / DR_STE_SIZE;
+	} else {
+		*iterations = 1;
+		*num_stes = htbl->chunk->num_of_entries;
+		alloc_size = *num_stes * DR_STE_SIZE;
+	}
+
+	*data = kzalloc(alloc_size, GFP_KERNEL);
+	if (!*data)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ * mlx5dr_send_postsend_ste: write size bytes into offset from the hw cm.
+ *
+ *     @dmn:    Domain
+ *     @ste:    The ste struct that contains the data (at
+ *              least part of it)
+ *     @data:   The real data to send size data
+ *     @size:   for writing.
+ *     @offset: The offset from the icm mapped data to
+ *              start write to this for write only part of the
+ *              buffer.
+ *
+ * Return: 0 on success.
+ */
+int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste,
+			     u8 *data, u16 size, u16 offset)
+{
+	struct postsend_info send_info = {};
+
+	send_info.write.addr = (uintptr_t)data;
+	send_info.write.length = size;
+	send_info.write.lkey = 0;
+	send_info.remote_addr = mlx5dr_ste_get_mr_addr(ste) + offset;
+	send_info.rkey = ste->htbl->chunk->rkey;
+
+	return dr_postsend_icm_data(dmn, &send_info);
+}
+
+int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn,
+			      struct mlx5dr_ste_htbl *htbl,
+			      u8 *formatted_ste, u8 *mask)
+{
+	u32 byte_size = htbl->chunk->byte_size;
+	int num_stes_per_iter;
+	int iterations;
+	u8 *data;
+	int ret;
+	int i;
+	int j;
+
+	ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+				      &iterations, &num_stes_per_iter);
+	if (ret)
+		return ret;
+
+	/* Send the data iteration times */
+	for (i = 0; i < iterations; i++) {
+		u32 ste_index = i * (byte_size / DR_STE_SIZE);
+		struct postsend_info send_info = {};
+
+		/* Copy all ste's on the data buffer
+		 * need to add the bit_mask
+		 */
+		for (j = 0; j < num_stes_per_iter; j++) {
+			u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste;
+			u32 ste_off = j * DR_STE_SIZE;
+
+			if (mlx5dr_ste_is_not_valid_entry(hw_ste)) {
+				memcpy(data + ste_off,
+				       formatted_ste, DR_STE_SIZE);
+			} else {
+				/* Copy data */
+				memcpy(data + ste_off,
+				       htbl->ste_arr[ste_index + j].hw_ste,
+				       DR_STE_SIZE_REDUCED);
+				/* Copy bit_mask */
+				memcpy(data + ste_off + DR_STE_SIZE_REDUCED,
+				       mask, DR_STE_SIZE_MASK);
+			}
+		}
+
+		send_info.write.addr = (uintptr_t)data;
+		send_info.write.length = byte_size;
+		send_info.write.lkey = 0;
+		send_info.remote_addr =
+			mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+		send_info.rkey = htbl->chunk->rkey;
+
+		ret = dr_postsend_icm_data(dmn, &send_info);
+		if (ret)
+			goto out_free;
+	}
+
+out_free:
+	kfree(data);
+	return ret;
+}
+
+/* Initialize htble with default STEs */
+int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn,
+					struct mlx5dr_ste_htbl *htbl,
+					u8 *ste_init_data,
+					bool update_hw_ste)
+{
+	u32 byte_size = htbl->chunk->byte_size;
+	int iterations;
+	int num_stes;
+	u8 *data;
+	int ret;
+	int i;
+
+	ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size,
+				      &iterations, &num_stes);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_stes; i++) {
+		u8 *copy_dst;
+
+		/* Copy the same ste on the data buffer */
+		copy_dst = data + i * DR_STE_SIZE;
+		memcpy(copy_dst, ste_init_data, DR_STE_SIZE);
+
+		if (update_hw_ste) {
+			/* Copy the reduced ste to hash table ste_arr */
+			copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED;
+			memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED);
+		}
+	}
+
+	/* Send the data iteration times */
+	for (i = 0; i < iterations; i++) {
+		u8 ste_index = i * (byte_size / DR_STE_SIZE);
+		struct postsend_info send_info = {};
+
+		send_info.write.addr = (uintptr_t)data;
+		send_info.write.length = byte_size;
+		send_info.write.lkey = 0;
+		send_info.remote_addr =
+			mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index);
+		send_info.rkey = htbl->chunk->rkey;
+
+		ret = dr_postsend_icm_data(dmn, &send_info);
+		if (ret)
+			goto out_free;
+	}
+
+out_free:
+	kfree(data);
+	return ret;
+}
+
+int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
+				struct mlx5dr_action *action)
+{
+	struct postsend_info send_info = {};
+	int ret;
+
+	send_info.write.addr = (uintptr_t)action->rewrite.data;
+	send_info.write.length = action->rewrite.chunk->byte_size;
+	send_info.write.lkey = 0;
+	send_info.remote_addr = action->rewrite.chunk->mr_addr;
+	send_info.rkey = action->rewrite.chunk->rkey;
+
+	mutex_lock(&dmn->mutex);
+	ret = dr_postsend_icm_data(dmn, &send_info);
+	mutex_unlock(&dmn->mutex);
+
+	return ret;
+}
+
+static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,
+				 struct mlx5dr_qp *dr_qp,
+				 int port)
+{
+	u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {};
+	void *qpc;
+
+	qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc);
+
+	MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, port);
+	MLX5_SET(qpc, qpc, pm_state, MLX5_QPC_PM_STATE_MIGRATED);
+	MLX5_SET(qpc, qpc, rre, 1);
+	MLX5_SET(qpc, qpc, rwe, 1);
+
+	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc,
+				   &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev,
+				    struct mlx5dr_qp *dr_qp,
+				    struct dr_qp_rts_attr *attr)
+{
+	u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {};
+	void *qpc;
+
+	qpc  = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc);
+
+	MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+	MLX5_SET(qpc, qpc, log_ack_req_freq, 0);
+	MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt);
+	MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry);
+
+	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc,
+				   &dr_qp->mqp);
+}
+
+static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev,
+				     struct mlx5dr_qp *dr_qp,
+				     struct dr_qp_rtr_attr *attr)
+{
+	u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {};
+	void *qpc;
+
+	qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc);
+
+	MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn);
+
+	MLX5_SET(qpc, qpc, mtu, attr->mtu);
+	MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1);
+	MLX5_SET(qpc, qpc, remote_qpn, attr->qp_num);
+	memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rmac_47_32),
+	       attr->dgid_attr.mac, sizeof(attr->dgid_attr.mac));
+	memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rgid_rip),
+	       attr->dgid_attr.gid, sizeof(attr->dgid_attr.gid));
+	MLX5_SET(qpc, qpc, primary_address_path.src_addr_index,
+		 attr->sgid_index);
+
+	if (attr->dgid_attr.roce_ver == MLX5_ROCE_VERSION_2)
+		MLX5_SET(qpc, qpc, primary_address_path.udp_sport,
+			 attr->udp_src_port);
+
+	MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num);
+	MLX5_SET(qpc, qpc, min_rnr_nak, 1);
+
+	return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc,
+				   &dr_qp->mqp);
+}
+
+static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn)
+{
+	struct mlx5dr_qp *dr_qp = dmn->send_ring->qp;
+	struct dr_qp_rts_attr rts_attr = {};
+	struct dr_qp_rtr_attr rtr_attr = {};
+	enum ib_mtu mtu = IB_MTU_1024;
+	u16 gid_index = 0;
+	int port = 1;
+	int ret;
+
+	/* Init */
+	ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port);
+	if (ret)
+		return ret;
+
+	/* RTR */
+	ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr);
+	if (ret)
+		return ret;
+
+	rtr_attr.mtu		= mtu;
+	rtr_attr.qp_num		= dr_qp->mqp.qpn;
+	rtr_attr.min_rnr_timer	= 12;
+	rtr_attr.port_num	= port;
+	rtr_attr.sgid_index	= gid_index;
+	rtr_attr.udp_src_port	= dmn->info.caps.roce_min_src_udp;
+
+	ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr);
+	if (ret)
+		return ret;
+
+	/* RTS */
+	rts_attr.timeout	= 14;
+	rts_attr.retry_cnt	= 7;
+	rts_attr.rnr_retry	= 7;
+
+	ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void dr_cq_event(struct mlx5_core_cq *mcq,
+			enum mlx5_event event)
+{
+	pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn);
+}
+
+static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev,
+				      struct mlx5_uars_page *uar,
+				      size_t ncqe)
+{
+	u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {};
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
+	struct mlx5_wq_param wqp;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5dr_cq *cq;
+	int inlen, err, eqn;
+	unsigned int irqn;
+	void *cqc, *in;
+	__be64 *pas;
+	u32 i;
+
+	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	if (!cq)
+		return NULL;
+
+	ncqe = roundup_pow_of_two(ncqe);
+	MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(ncqe));
+
+	wqp.buf_numa_node = mdev->priv.numa_node;
+	wqp.db_numa_node = mdev->priv.numa_node;
+
+	err = mlx5_cqwq_create(mdev, &wqp, temp_cqc, &cq->wq,
+			       &cq->wq_ctrl);
+	if (err)
+		goto out;
+
+	for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) {
+		cqe = mlx5_cqwq_get_wqe(&cq->wq, i);
+		cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK;
+	}
+
+	inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
+		sizeof(u64) * cq->wq_ctrl.buf.npages;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		goto err_cqwq;
+
+	err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
+	if (err) {
+		kvfree(in);
+		goto err_cqwq;
+	}
+
+	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
+	MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe));
+	MLX5_SET(cqc, cqc, c_eqn, eqn);
+	MLX5_SET(cqc, cqc, uar_page, uar->index);
+	MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift -
+		 MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma);
+
+	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
+	mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas);
+
+	cq->mcq.event = dr_cq_event;
+
+	err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out));
+	kvfree(in);
+
+	if (err)
+		goto err_cqwq;
+
+	cq->mcq.cqe_sz = 64;
+	cq->mcq.set_ci_db = cq->wq_ctrl.db.db;
+	cq->mcq.arm_db = cq->wq_ctrl.db.db + 1;
+	*cq->mcq.set_ci_db = 0;
+	*cq->mcq.arm_db = 0;
+	cq->mcq.vector = 0;
+	cq->mcq.irqn = irqn;
+	cq->mcq.uar = uar;
+
+	return cq;
+
+err_cqwq:
+	mlx5_wq_destroy(&cq->wq_ctrl);
+out:
+	kfree(cq);
+	return NULL;
+}
+
+static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq)
+{
+	mlx5_core_destroy_cq(mdev, &cq->mcq);
+	mlx5_wq_destroy(&cq->wq_ctrl);
+	kfree(cq);
+}
+
+static int
+dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey)
+{
+	u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {};
+	void *mkc;
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA);
+	MLX5_SET(mkc, mkc, a, 1);
+	MLX5_SET(mkc, mkc, rw, 1);
+	MLX5_SET(mkc, mkc, rr, 1);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, lr, 1);
+
+	MLX5_SET(mkc, mkc, pd, pdn);
+	MLX5_SET(mkc, mkc, length64, 1);
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+
+	return mlx5_core_create_mkey(mdev, mkey, in, sizeof(in));
+}
+
+static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev,
+				   u32 pdn, void *buf, size_t size)
+{
+	struct mlx5dr_mr *mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	struct device *dma_device;
+	dma_addr_t dma_addr;
+	int err;
+
+	if (!mr)
+		return NULL;
+
+	dma_device = &mdev->pdev->dev;
+	dma_addr = dma_map_single(dma_device, buf, size,
+				  DMA_BIDIRECTIONAL);
+	err = dma_mapping_error(dma_device, dma_addr);
+	if (err) {
+		mlx5_core_warn(mdev, "Can't dma buf\n");
+		kfree(mr);
+		return NULL;
+	}
+
+	err = dr_create_mkey(mdev, pdn, &mr->mkey);
+	if (err) {
+		mlx5_core_warn(mdev, "Can't create mkey\n");
+		dma_unmap_single(dma_device, dma_addr, size,
+				 DMA_BIDIRECTIONAL);
+		kfree(mr);
+		return NULL;
+	}
+
+	mr->dma_addr = dma_addr;
+	mr->size = size;
+	mr->addr = buf;
+
+	return mr;
+}
+
+static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr)
+{
+	mlx5_core_destroy_mkey(mdev, &mr->mkey);
+	dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size,
+			 DMA_BIDIRECTIONAL);
+	kfree(mr);
+}
+
+int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn)
+{
+	struct dr_qp_init_attr init_attr = {};
+	int cq_size;
+	int size;
+	int ret;
+
+	dmn->send_ring = kzalloc(sizeof(*dmn->send_ring), GFP_KERNEL);
+	if (!dmn->send_ring)
+		return -ENOMEM;
+
+	cq_size = QUEUE_SIZE + 1;
+	dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size);
+	if (!dmn->send_ring->cq) {
+		ret = -ENOMEM;
+		goto free_send_ring;
+	}
+
+	init_attr.cqn = dmn->send_ring->cq->mcq.cqn;
+	init_attr.pdn = dmn->pdn;
+	init_attr.uar = dmn->uar;
+	init_attr.max_send_wr = QUEUE_SIZE;
+
+	dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr);
+	if (!dmn->send_ring->qp)  {
+		ret = -ENOMEM;
+		goto clean_cq;
+	}
+
+	dmn->send_ring->cq->qp = dmn->send_ring->qp;
+
+	dmn->info.max_send_wr = QUEUE_SIZE;
+	dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data,
+					DR_STE_SIZE);
+
+	dmn->send_ring->signal_th = dmn->info.max_send_wr /
+		SIGNAL_PER_DIV_QUEUE;
+
+	/* Prepare qp to be used */
+	ret = dr_prepare_qp_to_rts(dmn);
+	if (ret)
+		goto clean_qp;
+
+	dmn->send_ring->max_post_send_size =
+		mlx5dr_icm_pool_chunk_size_to_byte(DR_CHUNK_SIZE_1K,
+						   DR_ICM_TYPE_STE);
+
+	/* Allocating the max size as a buffer for writing */
+	size = dmn->send_ring->signal_th * dmn->send_ring->max_post_send_size;
+	dmn->send_ring->buf = kzalloc(size, GFP_KERNEL);
+	if (!dmn->send_ring->buf) {
+		ret = -ENOMEM;
+		goto clean_qp;
+	}
+
+	memset(dmn->send_ring->buf, 0, size);
+	dmn->send_ring->buf_size = size;
+
+	dmn->send_ring->mr = dr_reg_mr(dmn->mdev,
+				       dmn->pdn, dmn->send_ring->buf, size);
+	if (!dmn->send_ring->mr) {
+		ret = -ENOMEM;
+		goto free_mem;
+	}
+
+	dmn->send_ring->sync_mr = dr_reg_mr(dmn->mdev,
+					    dmn->pdn, dmn->send_ring->sync_buff,
+					    MIN_READ_SYNC);
+	if (!dmn->send_ring->sync_mr) {
+		ret = -ENOMEM;
+		goto clean_mr;
+	}
+
+	return 0;
+
+clean_mr:
+	dr_dereg_mr(dmn->mdev, dmn->send_ring->mr);
+free_mem:
+	kfree(dmn->send_ring->buf);
+clean_qp:
+	dr_destroy_qp(dmn->mdev, dmn->send_ring->qp);
+clean_cq:
+	dr_destroy_cq(dmn->mdev, dmn->send_ring->cq);
+free_send_ring:
+	kfree(dmn->send_ring);
+
+	return ret;
+}
+
+void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
+			   struct mlx5dr_send_ring *send_ring)
+{
+	dr_destroy_qp(dmn->mdev, send_ring->qp);
+	dr_destroy_cq(dmn->mdev, send_ring->cq);
+	dr_dereg_mr(dmn->mdev, send_ring->sync_mr);
+	dr_dereg_mr(dmn->mdev, send_ring->mr);
+	kfree(send_ring->buf);
+	kfree(send_ring);
+}
+
+int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
+{
+	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
+	struct postsend_info send_info = {};
+	u8 data[DR_STE_SIZE];
+	int num_of_sends_req;
+	int ret;
+	int i;
+
+	/* Sending this amount of requests makes sure we will get drain */
+	num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
+
+	/* Send fake requests forcing the last to be signaled */
+	send_info.write.addr = (uintptr_t)data;
+	send_info.write.length = DR_STE_SIZE;
+	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;
+
+	for (i = 0; i < num_of_sends_req; i++) {
+		ret = dr_postsend_icm_data(dmn, &send_info);
+		if (ret)
+			return ret;
+	}
+
+	ret = dr_handle_pending_wc(dmn, send_ring);
+
+	return ret;
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c

@@ -0,0 +1,294 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "dr_types.h"
+
+int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+				 struct mlx5dr_action *action)
+{
+	struct mlx5dr_matcher *last_matcher = NULL;
+	struct mlx5dr_htbl_connect_info info;
+	struct mlx5dr_ste_htbl *last_htbl;
+	int ret;
+
+	if (action && action->action_type != DR_ACTION_TYP_FT)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&tbl->dmn->mutex);
+
+	if (!list_empty(&tbl->matcher_list))
+		last_matcher = list_last_entry(&tbl->matcher_list,
+					       struct mlx5dr_matcher,
+					       matcher_list);
+
+	if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX ||
+	    tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+		if (last_matcher)
+			last_htbl = last_matcher->rx.e_anchor;
+		else
+			last_htbl = tbl->rx.s_anchor;
+
+		tbl->rx.default_icm_addr = action ?
+			action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr :
+			tbl->rx.nic_dmn->default_icm_addr;
+
+		info.type = CONNECT_MISS;
+		info.miss_icm_addr = tbl->rx.default_icm_addr;
+
+		ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+							tbl->rx.nic_dmn,
+							last_htbl,
+							&info, true);
+		if (ret) {
+			mlx5dr_dbg(tbl->dmn, "Failed to set RX miss action, ret %d\n", ret);
+			goto out;
+		}
+	}
+
+	if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX ||
+	    tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) {
+		if (last_matcher)
+			last_htbl = last_matcher->tx.e_anchor;
+		else
+			last_htbl = tbl->tx.s_anchor;
+
+		tbl->tx.default_icm_addr = action ?
+			action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr :
+			tbl->tx.nic_dmn->default_icm_addr;
+
+		info.type = CONNECT_MISS;
+		info.miss_icm_addr = tbl->tx.default_icm_addr;
+
+		ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn,
+							tbl->tx.nic_dmn,
+							last_htbl, &info, true);
+		if (ret) {
+			mlx5dr_dbg(tbl->dmn, "Failed to set TX miss action, ret %d\n", ret);
+			goto out;
+		}
+	}
+
+	/* Release old action */
+	if (tbl->miss_action)
+		refcount_dec(&tbl->miss_action->refcount);
+
+	/* Set new miss action */
+	tbl->miss_action = action;
+	if (tbl->miss_action)
+		refcount_inc(&action->refcount);
+
+out:
+	mutex_unlock(&tbl->dmn->mutex);
+	return ret;
+}
+
+static void dr_table_uninit_nic(struct mlx5dr_table_rx_tx *nic_tbl)
+{
+	mlx5dr_htbl_put(nic_tbl->s_anchor);
+}
+
+static void dr_table_uninit_fdb(struct mlx5dr_table *tbl)
+{
+	dr_table_uninit_nic(&tbl->rx);
+	dr_table_uninit_nic(&tbl->tx);
+}
+
+static void dr_table_uninit(struct mlx5dr_table *tbl)
+{
+	mutex_lock(&tbl->dmn->mutex);
+
+	switch (tbl->dmn->type) {
+	case MLX5DR_DOMAIN_TYPE_NIC_RX:
+		dr_table_uninit_nic(&tbl->rx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_NIC_TX:
+		dr_table_uninit_nic(&tbl->tx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_FDB:
+		dr_table_uninit_fdb(tbl);
+		break;
+	default:
+		WARN_ON(true);
+		break;
+	}
+
+	mutex_unlock(&tbl->dmn->mutex);
+}
+
+static int dr_table_init_nic(struct mlx5dr_domain *dmn,
+			     struct mlx5dr_table_rx_tx *nic_tbl)
+{
+	struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn;
+	struct mlx5dr_htbl_connect_info info;
+	int ret;
+
+	nic_tbl->default_icm_addr = nic_dmn->default_icm_addr;
+
+	nic_tbl->s_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
+						  DR_CHUNK_SIZE_1,
+						  MLX5DR_STE_LU_TYPE_DONT_CARE,
+						  0);
+	if (!nic_tbl->s_anchor)
+		return -ENOMEM;
+
+	info.type = CONNECT_MISS;
+	info.miss_icm_addr = nic_dmn->default_icm_addr;
+	ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn,
+						nic_tbl->s_anchor,
+						&info, true);
+	if (ret)
+		goto free_s_anchor;
+
+	mlx5dr_htbl_get(nic_tbl->s_anchor);
+
+	return 0;
+
+free_s_anchor:
+	mlx5dr_ste_htbl_free(nic_tbl->s_anchor);
+	return ret;
+}
+
+static int dr_table_init_fdb(struct mlx5dr_table *tbl)
+{
+	int ret;
+
+	ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+	if (ret)
+		return ret;
+
+	ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+	if (ret)
+		goto destroy_rx;
+
+	return 0;
+
+destroy_rx:
+	dr_table_uninit_nic(&tbl->rx);
+	return ret;
+}
+
+static int dr_table_init(struct mlx5dr_table *tbl)
+{
+	int ret = 0;
+
+	INIT_LIST_HEAD(&tbl->matcher_list);
+
+	mutex_lock(&tbl->dmn->mutex);
+
+	switch (tbl->dmn->type) {
+	case MLX5DR_DOMAIN_TYPE_NIC_RX:
+		tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_RX;
+		tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+		ret = dr_table_init_nic(tbl->dmn, &tbl->rx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_NIC_TX:
+		tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_TX;
+		tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+		ret = dr_table_init_nic(tbl->dmn, &tbl->tx);
+		break;
+	case MLX5DR_DOMAIN_TYPE_FDB:
+		tbl->table_type = MLX5_FLOW_TABLE_TYPE_FDB;
+		tbl->rx.nic_dmn = &tbl->dmn->info.rx;
+		tbl->tx.nic_dmn = &tbl->dmn->info.tx;
+		ret = dr_table_init_fdb(tbl);
+		break;
+	default:
+		WARN_ON(true);
+		break;
+	}
+
+	mutex_unlock(&tbl->dmn->mutex);
+
+	return ret;
+}
+
+static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+	return mlx5dr_cmd_destroy_flow_table(tbl->dmn->mdev,
+					     tbl->table_id,
+					     tbl->table_type);
+}
+
+static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl)
+{
+	u64 icm_addr_rx = 0;
+	u64 icm_addr_tx = 0;
+	int ret;
+
+	if (tbl->rx.s_anchor)
+		icm_addr_rx = tbl->rx.s_anchor->chunk->icm_addr;
+
+	if (tbl->tx.s_anchor)
+		icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr;
+
+	ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev,
+					   tbl->table_type,
+					   icm_addr_rx,
+					   icm_addr_tx,
+					   tbl->dmn->info.caps.max_ft_level - 1,
+					   true, false, NULL,
+					   &tbl->table_id);
+
+	return ret;
+}
+
+struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level)
+{
+	struct mlx5dr_table *tbl;
+	int ret;
+
+	refcount_inc(&dmn->refcount);
+
+	tbl = kzalloc(sizeof(*tbl), GFP_KERNEL);
+	if (!tbl)
+		goto dec_ref;
+
+	tbl->dmn = dmn;
+	tbl->level = level;
+	refcount_set(&tbl->refcount, 1);
+
+	ret = dr_table_init(tbl);
+	if (ret)
+		goto free_tbl;
+
+	ret = dr_table_create_sw_owned_tbl(tbl);
+	if (ret)
+		goto uninit_tbl;
+
+	return tbl;
+
+uninit_tbl:
+	dr_table_uninit(tbl);
+free_tbl:
+	kfree(tbl);
+dec_ref:
+	refcount_dec(&dmn->refcount);
+	return NULL;
+}
+
+int mlx5dr_table_destroy(struct mlx5dr_table *tbl)
+{
+	int ret;
+
+	if (refcount_read(&tbl->refcount) > 1)
+		return -EBUSY;
+
+	ret = dr_table_destroy_sw_owned_tbl(tbl);
+	if (ret)
+		return ret;
+
+	dr_table_uninit(tbl);
+
+	if (tbl->miss_action)
+		refcount_dec(&tbl->miss_action->refcount);
+
+	refcount_dec(&tbl->dmn->refcount);
+	kfree(tbl);
+
+	return ret;
+}
+
+u32 mlx5dr_table_get_id(struct mlx5dr_table *tbl)
+{
+	return tbl->table_id;
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c

@@ -0,0 +1,600 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies */
+
+#include "mlx5_core.h"
+#include "fs_core.h"
+#include "fs_cmd.h"
+#include "mlx5dr.h"
+#include "fs_dr.h"
+
+static bool mlx5_dr_is_fw_table(u32 flags)
+{
+	if (flags & MLX5_FLOW_TABLE_TERMINATION)
+		return true;
+
+	return false;
+}
+
+static int mlx5_cmd_dr_update_root_ft(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_flow_table *ft,
+				      u32 underlay_qpn,
+				      bool disconnect)
+{
+	return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn,
+							 disconnect);
+}
+
+static int set_miss_action(struct mlx5_flow_root_namespace *ns,
+			   struct mlx5_flow_table *ft,
+			   struct mlx5_flow_table *next_ft)
+{
+	struct mlx5dr_action *old_miss_action;
+	struct mlx5dr_action *action = NULL;
+	struct mlx5dr_table *next_tbl;
+	int err;
+
+	next_tbl = next_ft ? next_ft->fs_dr_table.dr_table : NULL;
+	if (next_tbl) {
+		action = mlx5dr_action_create_dest_table(next_tbl);
+		if (!action)
+			return -EINVAL;
+	}
+	old_miss_action = ft->fs_dr_table.miss_action;
+	err = mlx5dr_table_set_miss_action(ft->fs_dr_table.dr_table, action);
+	if (err && action) {
+		err = mlx5dr_action_destroy(action);
+		if (err) {
+			action = NULL;
+			mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n",
+				      err);
+		}
+	}
+	ft->fs_dr_table.miss_action = action;
+	if (old_miss_action) {
+		err = mlx5dr_action_destroy(old_miss_action);
+		if (err)
+			mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n",
+				      err);
+	}
+
+	return err;
+}
+
+static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns,
+					 struct mlx5_flow_table *ft,
+					 unsigned int log_size,
+					 struct mlx5_flow_table *next_ft)
+{
+	struct mlx5dr_table *tbl;
+	int err;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft,
+								    log_size,
+								    next_ft);
+
+	tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain,
+				  ft->level);
+	if (!tbl) {
+		mlx5_core_err(ns->dev, "Failed creating dr flow_table\n");
+		return -EINVAL;
+	}
+
+	ft->fs_dr_table.dr_table = tbl;
+	ft->id = mlx5dr_table_get_id(tbl);
+
+	if (next_ft) {
+		err = set_miss_action(ns, ft, next_ft);
+		if (err) {
+			mlx5dr_table_destroy(tbl);
+			ft->fs_dr_table.dr_table = NULL;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft)
+{
+	struct mlx5dr_action *action = ft->fs_dr_table.miss_action;
+	int err;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft);
+
+	err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table);
+	if (err) {
+		mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n",
+			      err);
+		return err;
+	}
+	if (action) {
+		err = mlx5dr_action_destroy(action);
+		if (err) {
+			mlx5_core_err(ns->dev, "Failed to destroy action(%d)\n",
+				      err);
+			return err;
+		}
+	}
+
+	return err;
+}
+
+static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns,
+					 struct mlx5_flow_table *ft,
+					 struct mlx5_flow_table *next_ft)
+{
+	return set_miss_action(ns, ft, next_ft);
+}
+
+static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns,
+					 struct mlx5_flow_table *ft,
+					 u32 *in,
+					 struct mlx5_flow_group *fg)
+{
+	struct mlx5dr_matcher *matcher;
+	u16 priority = MLX5_GET(create_flow_group_in, in,
+				start_flow_index);
+	u8 match_criteria_enable = MLX5_GET(create_flow_group_in,
+					    in,
+					    match_criteria_enable);
+	struct mlx5dr_match_parameters mask;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in,
+								    fg);
+
+	mask.match_buf = MLX5_ADDR_OF(create_flow_group_in,
+				      in, match_criteria);
+	mask.match_sz = sizeof(fg->mask.match_criteria);
+
+	matcher = mlx5dr_matcher_create(ft->fs_dr_table.dr_table,
+					priority,
+					match_criteria_enable,
+					&mask);
+	if (!matcher) {
+		mlx5_core_err(ns->dev, "Failed creating matcher\n");
+		return -EINVAL;
+	}
+
+	fg->fs_dr_matcher.dr_matcher = matcher;
+	return 0;
+}
+
+static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns,
+					  struct mlx5_flow_table *ft,
+					  struct mlx5_flow_group *fg)
+{
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg);
+
+	return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher);
+}
+
+static struct mlx5dr_action *create_vport_action(struct mlx5dr_domain *domain,
+						 struct mlx5_flow_rule *dst)
+{
+	struct mlx5_flow_destination *dest_attr = &dst->dest_attr;
+
+	return mlx5dr_action_create_dest_vport(domain, dest_attr->vport.num,
+					       dest_attr->vport.flags &
+					       MLX5_FLOW_DEST_VPORT_VHCA_ID,
+					       dest_attr->vport.vhca_id);
+}
+
+static struct mlx5dr_action *create_ft_action(struct mlx5_core_dev *dev,
+					      struct mlx5_flow_rule *dst)
+{
+	struct mlx5_flow_table *dest_ft = dst->dest_attr.ft;
+
+	if (mlx5_dr_is_fw_table(dest_ft->flags))
+		return mlx5dr_create_action_dest_flow_fw_table(dest_ft, dev);
+	return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table);
+}
+
+static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domain,
+						     struct mlx5_fs_vlan *vlan)
+{
+	u16 n_ethtype = vlan->ethtype;
+	u8  prio = vlan->prio;
+	u16 vid = vlan->vid;
+	u32 vlan_hdr;
+
+	vlan_hdr = (u32)n_ethtype << 16 | (u32)(prio) << 12 |  (u32)vid;
+	return mlx5dr_action_create_push_vlan(domain, htonl(vlan_hdr));
+}
+
+#define MLX5_FLOW_CONTEXT_ACTION_MAX  20
+static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns,
+				  struct mlx5_flow_table *ft,
+				  struct mlx5_flow_group *group,
+				  struct fs_fte *fte)
+{
+	struct mlx5dr_domain *domain = ns->fs_dr_domain.dr_domain;
+	struct mlx5dr_action *term_action = NULL;
+	struct mlx5dr_match_parameters params;
+	struct mlx5_core_dev *dev = ns->dev;
+	struct mlx5dr_action **fs_dr_actions;
+	struct mlx5dr_action *tmp_action;
+	struct mlx5dr_action **actions;
+	bool delay_encap_set = false;
+	struct mlx5dr_rule *rule;
+	struct mlx5_flow_rule *dst;
+	int fs_dr_num_actions = 0;
+	int num_actions = 0;
+	size_t match_sz;
+	int err = 0;
+	int i;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte);
+
+	actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions),
+			  GFP_KERNEL);
+	if (!actions)
+		return -ENOMEM;
+
+	fs_dr_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX,
+				sizeof(*fs_dr_actions), GFP_KERNEL);
+	if (!fs_dr_actions) {
+		kfree(actions);
+		return -ENOMEM;
+	}
+
+	match_sz = sizeof(fte->val);
+
+	/* The order of the actions are must to be keep, only the following
+	 * order is supported by SW steering:
+	 * TX: push vlan -> modify header -> encap
+	 * RX: decap -> pop vlan -> modify header
+	 */
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
+		tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+		tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		enum mlx5dr_action_reformat_type decap_type =
+			DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2;
+
+		tmp_action = mlx5dr_action_create_packet_reformat(domain,
+								  decap_type, 0,
+								  NULL);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+		bool is_decap = fte->action.pkt_reformat->reformat_type ==
+			MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2;
+
+		if (is_decap)
+			actions[num_actions++] =
+				fte->action.pkt_reformat->action.dr_action;
+		else
+			delay_encap_set = true;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) {
+		tmp_action =
+			mlx5dr_action_create_pop_vlan();
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) {
+		tmp_action =
+			mlx5dr_action_create_pop_vlan();
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
+		actions[num_actions++] =
+			fte->action.modify_hdr->action.dr_action;
+
+	if (delay_encap_set)
+		actions[num_actions++] =
+			fte->action.pkt_reformat->action.dr_action;
+
+	/* The order of the actions below is not important */
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
+		tmp_action = mlx5dr_action_create_drop();
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		term_action = tmp_action;
+	}
+
+	if (fte->flow_context.flow_tag) {
+		tmp_action =
+			mlx5dr_action_create_tag(fte->flow_context.flow_tag);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+		actions[num_actions++] = tmp_action;
+	}
+
+	if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
+		list_for_each_entry(dst, &fte->node.children, node.list) {
+			enum mlx5_flow_destination_type type = dst->dest_attr.type;
+			u32 id;
+
+			if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+				err = -ENOSPC;
+				goto free_actions;
+			}
+
+			switch (type) {
+			case MLX5_FLOW_DESTINATION_TYPE_COUNTER:
+				id = dst->dest_attr.counter_id;
+
+				tmp_action =
+					mlx5dr_action_create_flow_counter(id);
+				if (!tmp_action) {
+					err = -ENOMEM;
+					goto free_actions;
+				}
+				fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+				actions[num_actions++] = tmp_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
+				tmp_action = create_ft_action(dev, dst);
+				if (!tmp_action) {
+					err = -ENOMEM;
+					goto free_actions;
+				}
+				fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+				term_action = tmp_action;
+				break;
+			case MLX5_FLOW_DESTINATION_TYPE_VPORT:
+				tmp_action = create_vport_action(domain, dst);
+				if (!tmp_action) {
+					err = -ENOMEM;
+					goto free_actions;
+				}
+				fs_dr_actions[fs_dr_num_actions++] = tmp_action;
+				term_action = tmp_action;
+				break;
+			default:
+				err = -EOPNOTSUPP;
+				goto free_actions;
+			}
+		}
+	}
+
+	params.match_sz = match_sz;
+	params.match_buf = (u64 *)fte->val;
+
+	if (term_action)
+		actions[num_actions++] = term_action;
+
+	rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher,
+				  &params,
+				  num_actions,
+				  actions);
+	if (!rule) {
+		err = -EINVAL;
+		goto free_actions;
+	}
+
+	kfree(actions);
+	fte->fs_dr_rule.dr_rule = rule;
+	fte->fs_dr_rule.num_actions = fs_dr_num_actions;
+	fte->fs_dr_rule.dr_actions = fs_dr_actions;
+
+	return 0;
+
+free_actions:
+	for (i = 0; i < fs_dr_num_actions; i++)
+		if (!IS_ERR_OR_NULL(fs_dr_actions[i]))
+			mlx5dr_action_destroy(fs_dr_actions[i]);
+
+	mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err);
+	kfree(actions);
+	kfree(fs_dr_actions);
+	return err;
+}
+
+static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
+					     int reformat_type,
+					     size_t size,
+					     void *reformat_data,
+					     enum mlx5_flow_namespace_type namespace,
+					     struct mlx5_pkt_reformat *pkt_reformat)
+{
+	struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain;
+	struct mlx5dr_action *action;
+	int dr_reformat;
+
+	switch (reformat_type) {
+	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
+	case MLX5_REFORMAT_TYPE_L2_TO_NVGRE:
+	case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL:
+		dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2;
+		break;
+	case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2:
+		dr_reformat = DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2;
+		break;
+	case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL:
+		dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3;
+		break;
+	default:
+		mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n",
+			      reformat_type);
+		return -EOPNOTSUPP;
+	}
+
+	action = mlx5dr_action_create_packet_reformat(dr_domain,
+						      dr_reformat,
+						      size,
+						      reformat_data);
+	if (!action) {
+		mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n");
+		return -EINVAL;
+	}
+
+	pkt_reformat->action.dr_action = action;
+
+	return 0;
+}
+
+static void mlx5_cmd_dr_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns,
+						struct mlx5_pkt_reformat *pkt_reformat)
+{
+	mlx5dr_action_destroy(pkt_reformat->action.dr_action);
+}
+
+static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
+					   u8 namespace, u8 num_actions,
+					   void *modify_actions,
+					   struct mlx5_modify_hdr *modify_hdr)
+{
+	struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain;
+	struct mlx5dr_action *action;
+	size_t actions_sz;
+
+	actions_sz = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) *
+		num_actions;
+	action = mlx5dr_action_create_modify_header(dr_domain, 0,
+						    actions_sz,
+						    modify_actions);
+	if (!action) {
+		mlx5_core_err(ns->dev, "Failed allocating modify-header action\n");
+		return -EINVAL;
+	}
+
+	modify_hdr->action.dr_action = action;
+
+	return 0;
+}
+
+static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *ns,
+					      struct mlx5_modify_hdr *modify_hdr)
+{
+	mlx5dr_action_destroy(modify_hdr->action.dr_action);
+}
+
+static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns,
+				  struct mlx5_flow_table *ft,
+				  struct mlx5_flow_group *group,
+				  int modify_mask,
+				  struct fs_fte *fte)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns,
+				  struct mlx5_flow_table *ft,
+				  struct fs_fte *fte)
+{
+	struct mlx5_fs_dr_rule *rule = &fte->fs_dr_rule;
+	int err;
+	int i;
+
+	if (mlx5_dr_is_fw_table(ft->flags))
+		return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte);
+
+	err = mlx5dr_rule_destroy(rule->dr_rule);
+	if (err)
+		return err;
+
+	for (i = 0; i < rule->num_actions; i++)
+		if (!IS_ERR_OR_NULL(rule->dr_actions[i]))
+			mlx5dr_action_destroy(rule->dr_actions[i]);
+
+	kfree(rule->dr_actions);
+	return 0;
+}
+
+static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns,
+				struct mlx5_flow_root_namespace *peer_ns)
+{
+	struct mlx5dr_domain *peer_domain = NULL;
+
+	if (peer_ns)
+		peer_domain = peer_ns->fs_dr_domain.dr_domain;
+	mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain,
+			       peer_domain);
+	return 0;
+}
+
+static int mlx5_cmd_dr_create_ns(struct mlx5_flow_root_namespace *ns)
+{
+	ns->fs_dr_domain.dr_domain =
+		mlx5dr_domain_create(ns->dev,
+				     MLX5DR_DOMAIN_TYPE_FDB);
+	if (!ns->fs_dr_domain.dr_domain) {
+		mlx5_core_err(ns->dev, "Failed to create dr flow namespace\n");
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns)
+{
+	return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain);
+}
+
+bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
+{
+	return mlx5dr_is_supported(dev);
+}
+
+static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = {
+	.create_flow_table = mlx5_cmd_dr_create_flow_table,
+	.destroy_flow_table = mlx5_cmd_dr_destroy_flow_table,
+	.modify_flow_table = mlx5_cmd_dr_modify_flow_table,
+	.create_flow_group = mlx5_cmd_dr_create_flow_group,
+	.destroy_flow_group = mlx5_cmd_dr_destroy_flow_group,
+	.create_fte = mlx5_cmd_dr_create_fte,
+	.update_fte = mlx5_cmd_dr_update_fte,
+	.delete_fte = mlx5_cmd_dr_delete_fte,
+	.update_root_ft = mlx5_cmd_dr_update_root_ft,
+	.packet_reformat_alloc = mlx5_cmd_dr_packet_reformat_alloc,
+	.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,
+	.set_peer = mlx5_cmd_dr_set_peer,
+	.create_ns = mlx5_cmd_dr_create_ns,
+	.destroy_ns = mlx5_cmd_dr_destroy_ns,
+};
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
+{
+		return &mlx5_flow_cmds_dr;
+}

drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h

@@ -0,0 +1,60 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+ * Copyright (c) 2019 Mellanox Technologies
+ */
+
+#ifndef _MLX5_FS_DR_
+#define _MLX5_FS_DR_
+
+#include "mlx5dr.h"
+
+struct mlx5_flow_root_namespace;
+struct fs_fte;
+
+struct mlx5_fs_dr_action {
+	struct mlx5dr_action *dr_action;
+};
+
+struct mlx5_fs_dr_ns {
+	struct mlx5_dr_ns *dr_ns;
+};
+
+struct mlx5_fs_dr_rule {
+	struct mlx5dr_rule    *dr_rule;
+	/* Only actions created by fs_dr */
+	struct mlx5dr_action  **dr_actions;
+	int                      num_actions;
+};
+
+struct mlx5_fs_dr_domain {
+	struct mlx5dr_domain	*dr_domain;
+};
+
+struct mlx5_fs_dr_matcher {
+	struct mlx5dr_matcher *dr_matcher;
+};
+
+struct mlx5_fs_dr_table {
+	struct mlx5dr_table  *dr_table;
+	struct mlx5dr_action *miss_action;
+};
+
+#ifdef CONFIG_MLX5_SW_STEERING
+
+bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev);
+
+const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void);
+
+#else
+
+static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void)
+{
+	return NULL;
+}
+
+static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev)
+{
+	return false;
+}
+
+#endif /* CONFIG_MLX5_SW_STEERING */
+#endif

drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h

@@ -0,0 +1,604 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019, Mellanox Technologies */
+
+#ifndef MLX5_IFC_DR_H
+#define MLX5_IFC_DR_H
+
+enum {
+	MLX5DR_ACTION_MDFY_HW_FLD_L2_0		= 0,
+	MLX5DR_ACTION_MDFY_HW_FLD_L2_1		= 1,
+	MLX5DR_ACTION_MDFY_HW_FLD_L2_2		= 2,
+	MLX5DR_ACTION_MDFY_HW_FLD_L3_0		= 3,
+	MLX5DR_ACTION_MDFY_HW_FLD_L3_1		= 4,
+	MLX5DR_ACTION_MDFY_HW_FLD_L3_2		= 5,
+	MLX5DR_ACTION_MDFY_HW_FLD_L3_3		= 6,
+	MLX5DR_ACTION_MDFY_HW_FLD_L3_4		= 7,
+	MLX5DR_ACTION_MDFY_HW_FLD_L4_0		= 8,
+	MLX5DR_ACTION_MDFY_HW_FLD_L4_1		= 9,
+	MLX5DR_ACTION_MDFY_HW_FLD_MPLS		= 10,
+	MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_0	= 11,
+	MLX5DR_ACTION_MDFY_HW_FLD_REG_0		= 12,
+	MLX5DR_ACTION_MDFY_HW_FLD_REG_1		= 13,
+	MLX5DR_ACTION_MDFY_HW_FLD_REG_2		= 14,
+	MLX5DR_ACTION_MDFY_HW_FLD_REG_3		= 15,
+	MLX5DR_ACTION_MDFY_HW_FLD_L4_2		= 16,
+	MLX5DR_ACTION_MDFY_HW_FLD_FLEX_0	= 17,
+	MLX5DR_ACTION_MDFY_HW_FLD_FLEX_1	= 18,
+	MLX5DR_ACTION_MDFY_HW_FLD_FLEX_2	= 19,
+	MLX5DR_ACTION_MDFY_HW_FLD_FLEX_3	= 20,
+	MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_1	= 21,
+	MLX5DR_ACTION_MDFY_HW_FLD_METADATA	= 22,
+	MLX5DR_ACTION_MDFY_HW_FLD_RESERVED	= 23,
+};
+
+enum {
+	MLX5DR_ACTION_MDFY_HW_OP_SET		= 0x2,
+	MLX5DR_ACTION_MDFY_HW_OP_ADD		= 0x3,
+};
+
+enum {
+	MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE	= 0x0,
+	MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4	= 0x1,
+	MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6	= 0x2,
+};
+
+enum {
+	MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE	= 0x0,
+	MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP	= 0x1,
+	MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP	= 0x2,
+};
+
+enum {
+	MLX5DR_STE_LU_TYPE_NOP				= 0x00,
+	MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP		= 0x05,
+	MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I		= 0x0a,
+	MLX5DR_STE_LU_TYPE_ETHL2_DST_O			= 0x06,
+	MLX5DR_STE_LU_TYPE_ETHL2_DST_I			= 0x07,
+	MLX5DR_STE_LU_TYPE_ETHL2_DST_D			= 0x1b,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_O			= 0x08,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_I			= 0x09,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_D			= 0x1c,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_O		= 0x36,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_I		= 0x37,
+	MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_D		= 0x38,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_O		= 0x0d,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_I		= 0x0e,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_D		= 0x1e,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_O		= 0x0f,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_I		= 0x10,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_D		= 0x1f,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_O		= 0x11,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_I		= 0x12,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_D		= 0x20,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_O		= 0x29,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_I		= 0x2a,
+	MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_D		= 0x2b,
+	MLX5DR_STE_LU_TYPE_ETHL4_O			= 0x13,
+	MLX5DR_STE_LU_TYPE_ETHL4_I			= 0x14,
+	MLX5DR_STE_LU_TYPE_ETHL4_D			= 0x21,
+	MLX5DR_STE_LU_TYPE_ETHL4_MISC_O			= 0x2c,
+	MLX5DR_STE_LU_TYPE_ETHL4_MISC_I			= 0x2d,
+	MLX5DR_STE_LU_TYPE_ETHL4_MISC_D			= 0x2e,
+	MLX5DR_STE_LU_TYPE_MPLS_FIRST_O			= 0x15,
+	MLX5DR_STE_LU_TYPE_MPLS_FIRST_I			= 0x24,
+	MLX5DR_STE_LU_TYPE_MPLS_FIRST_D			= 0x25,
+	MLX5DR_STE_LU_TYPE_GRE				= 0x16,
+	MLX5DR_STE_LU_TYPE_FLEX_PARSER_0		= 0x22,
+	MLX5DR_STE_LU_TYPE_FLEX_PARSER_1		= 0x23,
+	MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER	= 0x19,
+	MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE		= 0x18,
+	MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0		= 0x2f,
+	MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1		= 0x30,
+	MLX5DR_STE_LU_TYPE_DONT_CARE			= 0x0f,
+};
+
+enum mlx5dr_ste_entry_type {
+	MLX5DR_STE_TYPE_TX		= 1,
+	MLX5DR_STE_TYPE_RX		= 2,
+	MLX5DR_STE_TYPE_MODIFY_PKT	= 6,
+};
+
+struct mlx5_ifc_ste_general_bits {
+	u8         entry_type[0x4];
+	u8         reserved_at_4[0x4];
+	u8         entry_sub_type[0x8];
+	u8         byte_mask[0x10];
+
+	u8         next_table_base_63_48[0x10];
+	u8         next_lu_type[0x8];
+	u8         next_table_base_39_32_size[0x8];
+
+	u8         next_table_base_31_5_size[0x1b];
+	u8         linear_hash_enable[0x1];
+	u8         reserved_at_5c[0x2];
+	u8         next_table_rank[0x2];
+
+	u8         reserved_at_60[0xa0];
+	u8         tag_value[0x60];
+	u8         bit_mask[0x60];
+};
+
+struct mlx5_ifc_ste_sx_transmit_bits {
+	u8         entry_type[0x4];
+	u8         reserved_at_4[0x4];
+	u8         entry_sub_type[0x8];
+	u8         byte_mask[0x10];
+
+	u8         next_table_base_63_48[0x10];
+	u8         next_lu_type[0x8];
+	u8         next_table_base_39_32_size[0x8];
+
+	u8         next_table_base_31_5_size[0x1b];
+	u8         linear_hash_enable[0x1];
+	u8         reserved_at_5c[0x2];
+	u8         next_table_rank[0x2];
+
+	u8         sx_wire[0x1];
+	u8         sx_func_lb[0x1];
+	u8         sx_sniffer[0x1];
+	u8         sx_wire_enable[0x1];
+	u8         sx_func_lb_enable[0x1];
+	u8         sx_sniffer_enable[0x1];
+	u8         action_type[0x3];
+	u8         reserved_at_69[0x1];
+	u8         action_description[0x6];
+	u8         gvmi[0x10];
+
+	u8         encap_pointer_vlan_data[0x20];
+
+	u8         loopback_syndome_en[0x8];
+	u8         loopback_syndome[0x8];
+	u8         counter_trigger[0x10];
+
+	u8         miss_address_63_48[0x10];
+	u8         counter_trigger_23_16[0x8];
+	u8         miss_address_39_32[0x8];
+
+	u8         miss_address_31_6[0x1a];
+	u8         learning_point[0x1];
+	u8         go_back[0x1];
+	u8         match_polarity[0x1];
+	u8         mask_mode[0x1];
+	u8         miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_rx_steering_mult_bits {
+	u8         entry_type[0x4];
+	u8         reserved_at_4[0x4];
+	u8         entry_sub_type[0x8];
+	u8         byte_mask[0x10];
+
+	u8         next_table_base_63_48[0x10];
+	u8         next_lu_type[0x8];
+	u8         next_table_base_39_32_size[0x8];
+
+	u8         next_table_base_31_5_size[0x1b];
+	u8         linear_hash_enable[0x1];
+	u8         reserved_at_[0x2];
+	u8         next_table_rank[0x2];
+
+	u8         member_count[0x10];
+	u8         gvmi[0x10];
+
+	u8         qp_list_pointer[0x20];
+
+	u8         reserved_at_a0[0x1];
+	u8         tunneling_action[0x3];
+	u8         action_description[0x4];
+	u8         reserved_at_a8[0x8];
+	u8         counter_trigger_15_0[0x10];
+
+	u8         miss_address_63_48[0x10];
+	u8         counter_trigger_23_16[0x08];
+	u8         miss_address_39_32[0x8];
+
+	u8         miss_address_31_6[0x1a];
+	u8         learning_point[0x1];
+	u8         fail_on_error[0x1];
+	u8         match_polarity[0x1];
+	u8         mask_mode[0x1];
+	u8         miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_modify_packet_bits {
+	u8         entry_type[0x4];
+	u8         reserved_at_4[0x4];
+	u8         entry_sub_type[0x8];
+	u8         byte_mask[0x10];
+
+	u8         next_table_base_63_48[0x10];
+	u8         next_lu_type[0x8];
+	u8         next_table_base_39_32_size[0x8];
+
+	u8         next_table_base_31_5_size[0x1b];
+	u8         linear_hash_enable[0x1];
+	u8         reserved_at_[0x2];
+	u8         next_table_rank[0x2];
+
+	u8         number_of_re_write_actions[0x10];
+	u8         gvmi[0x10];
+
+	u8         header_re_write_actions_pointer[0x20];
+
+	u8         reserved_at_a0[0x1];
+	u8         tunneling_action[0x3];
+	u8         action_description[0x4];
+	u8         reserved_at_a8[0x8];
+	u8         counter_trigger_15_0[0x10];
+
+	u8         miss_address_63_48[0x10];
+	u8         counter_trigger_23_16[0x08];
+	u8         miss_address_39_32[0x8];
+
+	u8         miss_address_31_6[0x1a];
+	u8         learning_point[0x1];
+	u8         fail_on_error[0x1];
+	u8         match_polarity[0x1];
+	u8         mask_mode[0x1];
+	u8         miss_rank[0x2];
+};
+
+struct mlx5_ifc_ste_eth_l2_src_bits {
+	u8         smac_47_16[0x20];
+
+	u8         smac_15_0[0x10];
+	u8         l3_ethertype[0x10];
+
+	u8         qp_type[0x2];
+	u8         ethertype_filter[0x1];
+	u8         reserved_at_43[0x1];
+	u8         sx_sniffer[0x1];
+	u8         force_lb[0x1];
+	u8         functional_lb[0x1];
+	u8         port[0x1];
+	u8         reserved_at_48[0x4];
+	u8         first_priority[0x3];
+	u8         first_cfi[0x1];
+	u8         first_vlan_qualifier[0x2];
+	u8         reserved_at_52[0x2];
+	u8         first_vlan_id[0xc];
+
+	u8         ip_fragmented[0x1];
+	u8         tcp_syn[0x1];
+	u8         encp_type[0x2];
+	u8         l3_type[0x2];
+	u8         l4_type[0x2];
+	u8         reserved_at_68[0x4];
+	u8         second_priority[0x3];
+	u8         second_cfi[0x1];
+	u8         second_vlan_qualifier[0x2];
+	u8         reserved_at_72[0x2];
+	u8         second_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l2_dst_bits {
+	u8         dmac_47_16[0x20];
+
+	u8         dmac_15_0[0x10];
+	u8         l3_ethertype[0x10];
+
+	u8         qp_type[0x2];
+	u8         ethertype_filter[0x1];
+	u8         reserved_at_43[0x1];
+	u8         sx_sniffer[0x1];
+	u8         force_lb[0x1];
+	u8         functional_lb[0x1];
+	u8         port[0x1];
+	u8         reserved_at_48[0x4];
+	u8         first_priority[0x3];
+	u8         first_cfi[0x1];
+	u8         first_vlan_qualifier[0x2];
+	u8         reserved_at_52[0x2];
+	u8         first_vlan_id[0xc];
+
+	u8         ip_fragmented[0x1];
+	u8         tcp_syn[0x1];
+	u8         encp_type[0x2];
+	u8         l3_type[0x2];
+	u8         l4_type[0x2];
+	u8         reserved_at_68[0x4];
+	u8         second_priority[0x3];
+	u8         second_cfi[0x1];
+	u8         second_vlan_qualifier[0x2];
+	u8         reserved_at_72[0x2];
+	u8         second_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l2_src_dst_bits {
+	u8         dmac_47_16[0x20];
+
+	u8         dmac_15_0[0x10];
+	u8         smac_47_32[0x10];
+
+	u8         smac_31_0[0x20];
+
+	u8         sx_sniffer[0x1];
+	u8         force_lb[0x1];
+	u8         functional_lb[0x1];
+	u8         port[0x1];
+	u8         l3_type[0x2];
+	u8         reserved_at_66[0x6];
+	u8         first_priority[0x3];
+	u8         first_cfi[0x1];
+	u8         first_vlan_qualifier[0x2];
+	u8         reserved_at_72[0x2];
+	u8         first_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv4_5_tuple_bits {
+	u8         destination_address[0x20];
+
+	u8         source_address[0x20];
+
+	u8         source_port[0x10];
+	u8         destination_port[0x10];
+
+	u8         fragmented[0x1];
+	u8         first_fragment[0x1];
+	u8         reserved_at_62[0x2];
+	u8         reserved_at_64[0x1];
+	u8         ecn[0x2];
+	u8         tcp_ns[0x1];
+	u8         tcp_cwr[0x1];
+	u8         tcp_ece[0x1];
+	u8         tcp_urg[0x1];
+	u8         tcp_ack[0x1];
+	u8         tcp_psh[0x1];
+	u8         tcp_rst[0x1];
+	u8         tcp_syn[0x1];
+	u8         tcp_fin[0x1];
+	u8         dscp[0x6];
+	u8         reserved_at_76[0x2];
+	u8         protocol[0x8];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv6_dst_bits {
+	u8         dst_ip_127_96[0x20];
+
+	u8         dst_ip_95_64[0x20];
+
+	u8         dst_ip_63_32[0x20];
+
+	u8         dst_ip_31_0[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l2_tnl_bits {
+	u8         dmac_47_16[0x20];
+
+	u8         dmac_15_0[0x10];
+	u8         l3_ethertype[0x10];
+
+	u8         l2_tunneling_network_id[0x20];
+
+	u8         ip_fragmented[0x1];
+	u8         tcp_syn[0x1];
+	u8         encp_type[0x2];
+	u8         l3_type[0x2];
+	u8         l4_type[0x2];
+	u8         first_priority[0x3];
+	u8         first_cfi[0x1];
+	u8         reserved_at_6c[0x3];
+	u8         gre_key_flag[0x1];
+	u8         first_vlan_qualifier[0x2];
+	u8         reserved_at_72[0x2];
+	u8         first_vlan_id[0xc];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv6_src_bits {
+	u8         src_ip_127_96[0x20];
+
+	u8         src_ip_95_64[0x20];
+
+	u8         src_ip_63_32[0x20];
+
+	u8         src_ip_31_0[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l3_ipv4_misc_bits {
+	u8         version[0x4];
+	u8         ihl[0x4];
+	u8         reserved_at_8[0x8];
+	u8         total_length[0x10];
+
+	u8         identification[0x10];
+	u8         flags[0x3];
+	u8         fragment_offset[0xd];
+
+	u8         time_to_live[0x8];
+	u8         reserved_at_48[0x8];
+	u8         checksum[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_ste_eth_l4_bits {
+	u8         fragmented[0x1];
+	u8         first_fragment[0x1];
+	u8         reserved_at_2[0x6];
+	u8         protocol[0x8];
+	u8         dst_port[0x10];
+
+	u8         ipv6_version[0x4];
+	u8         reserved_at_24[0x1];
+	u8         ecn[0x2];
+	u8         tcp_ns[0x1];
+	u8         tcp_cwr[0x1];
+	u8         tcp_ece[0x1];
+	u8         tcp_urg[0x1];
+	u8         tcp_ack[0x1];
+	u8         tcp_psh[0x1];
+	u8         tcp_rst[0x1];
+	u8         tcp_syn[0x1];
+	u8         tcp_fin[0x1];
+	u8         src_port[0x10];
+
+	u8         ipv6_payload_length[0x10];
+	u8         ipv6_hop_limit[0x8];
+	u8         dscp[0x6];
+	u8         reserved_at_5e[0x2];
+
+	u8         tcp_data_offset[0x4];
+	u8         reserved_at_64[0x8];
+	u8         flow_label[0x14];
+};
+
+struct mlx5_ifc_ste_eth_l4_misc_bits {
+	u8         checksum[0x10];
+	u8         length[0x10];
+
+	u8         seq_num[0x20];
+
+	u8         ack_num[0x20];
+
+	u8         urgent_pointer[0x10];
+	u8         window_size[0x10];
+};
+
+struct mlx5_ifc_ste_mpls_bits {
+	u8         mpls0_label[0x14];
+	u8         mpls0_exp[0x3];
+	u8         mpls0_s_bos[0x1];
+	u8         mpls0_ttl[0x8];
+
+	u8         mpls1_label[0x20];
+
+	u8         mpls2_label[0x20];
+
+	u8         reserved_at_60[0x16];
+	u8         mpls4_s_bit[0x1];
+	u8         mpls4_qualifier[0x1];
+	u8         mpls3_s_bit[0x1];
+	u8         mpls3_qualifier[0x1];
+	u8         mpls2_s_bit[0x1];
+	u8         mpls2_qualifier[0x1];
+	u8         mpls1_s_bit[0x1];
+	u8         mpls1_qualifier[0x1];
+	u8         mpls0_s_bit[0x1];
+	u8         mpls0_qualifier[0x1];
+};
+
+struct mlx5_ifc_ste_register_0_bits {
+	u8         register_0_h[0x20];
+
+	u8         register_0_l[0x20];
+
+	u8         register_1_h[0x20];
+
+	u8         register_1_l[0x20];
+};
+
+struct mlx5_ifc_ste_register_1_bits {
+	u8         register_2_h[0x20];
+
+	u8         register_2_l[0x20];
+
+	u8         register_3_h[0x20];
+
+	u8         register_3_l[0x20];
+};
+
+struct mlx5_ifc_ste_gre_bits {
+	u8         gre_c_present[0x1];
+	u8         reserved_at_30[0x1];
+	u8         gre_k_present[0x1];
+	u8         gre_s_present[0x1];
+	u8         strict_src_route[0x1];
+	u8         recur[0x3];
+	u8         flags[0x5];
+	u8         version[0x3];
+	u8         gre_protocol[0x10];
+
+	u8         checksum[0x10];
+	u8         offset[0x10];
+
+	u8         gre_key_h[0x18];
+	u8         gre_key_l[0x8];
+
+	u8         seq_num[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_0_bits {
+	u8         parser_3_label[0x14];
+	u8         parser_3_exp[0x3];
+	u8         parser_3_s_bos[0x1];
+	u8         parser_3_ttl[0x8];
+
+	u8         flex_parser_2[0x20];
+
+	u8         flex_parser_1[0x20];
+
+	u8         flex_parser_0[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_1_bits {
+	u8         flex_parser_7[0x20];
+
+	u8         flex_parser_6[0x20];
+
+	u8         flex_parser_5[0x20];
+
+	u8         flex_parser_4[0x20];
+};
+
+struct mlx5_ifc_ste_flex_parser_tnl_bits {
+	u8         flex_parser_tunneling_header_63_32[0x20];
+
+	u8         flex_parser_tunneling_header_31_0[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_ste_general_purpose_bits {
+	u8         general_purpose_lookup_field[0x20];
+
+	u8         reserved_at_20[0x20];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_ste_src_gvmi_qp_bits {
+	u8         loopback_syndrome[0x8];
+	u8         reserved_at_8[0x8];
+	u8         source_gvmi[0x10];
+
+	u8         reserved_at_20[0x5];
+	u8         force_lb[0x1];
+	u8         functional_lb[0x1];
+	u8         source_is_requestor[0x1];
+	u8         source_qp[0x18];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_l2_hdr_bits {
+	u8         dmac_47_16[0x20];
+
+	u8         dmac_15_0[0x10];
+	u8         smac_47_32[0x10];
+
+	u8         smac_31_0[0x20];
+
+	u8         ethertype[0x10];
+	u8         vlan_type[0x10];
+
+	u8         vlan[0x10];
+	u8         reserved_at_90[0x10];
+};
+
+/* Both HW set and HW add share the same HW format with different opcodes */
+struct mlx5_ifc_dr_action_hw_set_bits {
+	u8         opcode[0x8];
+	u8         destination_field_code[0x8];
+	u8         reserved_at_10[0x2];
+	u8         destination_left_shifter[0x6];
+	u8         reserved_at_18[0x3];
+	u8         destination_length[0x5];
+
+	u8         inline_data[0x20];
+};
+
+#endif /* MLX5_IFC_DR_H */

drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h

@@ -0,0 +1,212 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019, Mellanox Technologies */
+
+#ifndef _MLX5DR_H_
+#define _MLX5DR_H_
+
+struct mlx5dr_domain;
+struct mlx5dr_table;
+struct mlx5dr_matcher;
+struct mlx5dr_rule;
+struct mlx5dr_action;
+
+enum mlx5dr_domain_type {
+	MLX5DR_DOMAIN_TYPE_NIC_RX,
+	MLX5DR_DOMAIN_TYPE_NIC_TX,
+	MLX5DR_DOMAIN_TYPE_FDB,
+};
+
+enum mlx5dr_domain_sync_flags {
+	MLX5DR_DOMAIN_SYNC_FLAGS_SW = 1 << 0,
+	MLX5DR_DOMAIN_SYNC_FLAGS_HW = 1 << 1,
+};
+
+enum mlx5dr_action_reformat_type {
+	DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2,
+	DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2,
+	DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2,
+	DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3,
+};
+
+struct mlx5dr_match_parameters {
+	size_t match_sz;
+	u64 *match_buf; /* Device spec format */
+};
+
+#ifdef CONFIG_MLX5_SW_STEERING
+
+struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
+
+int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
+
+int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
+
+void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+			    struct mlx5dr_domain *peer_dmn);
+
+struct mlx5dr_table *
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level);
+
+int mlx5dr_table_destroy(struct mlx5dr_table *table);
+
+u32 mlx5dr_table_get_id(struct mlx5dr_table *table);
+
+struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *table,
+		      u16 priority,
+		      u8 match_criteria_enable,
+		      struct mlx5dr_match_parameters *mask);
+
+int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher);
+
+struct mlx5dr_rule *
+mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
+		   struct mlx5dr_match_parameters *value,
+		   size_t num_actions,
+		   struct mlx5dr_action *actions[]);
+
+int mlx5dr_rule_destroy(struct mlx5dr_rule *rule);
+
+int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+				 struct mlx5dr_action *action);
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_table(struct mlx5dr_table *table);
+
+struct mlx5dr_action *
+mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
+					struct mlx5_core_dev *mdev);
+
+struct mlx5dr_action *
+mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
+				u32 vport, u8 vhca_id_valid,
+				u16 vhca_id);
+
+struct mlx5dr_action *mlx5dr_action_create_drop(void);
+
+struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value);
+
+struct mlx5dr_action *
+mlx5dr_action_create_flow_counter(u32 counter_id);
+
+struct mlx5dr_action *
+mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
+				     enum mlx5dr_action_reformat_type reformat_type,
+				     size_t data_sz,
+				     void *data);
+
+struct mlx5dr_action *
+mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain,
+				   u32 flags,
+				   size_t actions_sz,
+				   __be64 actions[]);
+
+struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void);
+
+struct mlx5dr_action *
+mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, __be32 vlan_hdr);
+
+int mlx5dr_action_destroy(struct mlx5dr_action *action);
+
+static inline bool
+mlx5dr_is_supported(struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner);
+}
+
+#else /* CONFIG_MLX5_SW_STEERING */
+
+static inline struct mlx5dr_domain *
+mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) { return NULL; }
+
+static inline int
+mlx5dr_domain_destroy(struct mlx5dr_domain *domain) { return 0; }
+
+static inline int
+mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags) { return 0; }
+
+static inline void
+mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
+		       struct mlx5dr_domain *peer_dmn) { }
+
+static inline struct mlx5dr_table *
+mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level) { return NULL; }
+
+static inline int
+mlx5dr_table_destroy(struct mlx5dr_table *table) { return 0; }
+
+static inline u32
+mlx5dr_table_get_id(struct mlx5dr_table *table) { return 0; }
+
+static inline struct mlx5dr_matcher *
+mlx5dr_matcher_create(struct mlx5dr_table *table,
+		      u16 priority,
+		      u8 match_criteria_enable,
+		      struct mlx5dr_match_parameters *mask) { return NULL; }
+
+static inline int
+mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) { return 0; }
+
+static inline struct mlx5dr_rule *
+mlx5dr_rule_create(struct mlx5dr_matcher *matcher,
+		   struct mlx5dr_match_parameters *value,
+		   size_t num_actions,
+		   struct mlx5dr_action *actions[]) { return NULL; }
+
+static inline int
+mlx5dr_rule_destroy(struct mlx5dr_rule *rule) { return 0; }
+
+static inline int
+mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl,
+			     struct mlx5dr_action *action) { return 0; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_dest_table(struct mlx5dr_table *table) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft,
+					struct mlx5_core_dev *mdev) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain,
+				u32 vport, u8 vhca_id_valid,
+				u16 vhca_id) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_drop(void) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_tag(u32 tag_value) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_flow_counter(u32 counter_id) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn,
+				     enum mlx5dr_action_reformat_type reformat_type,
+				     size_t data_sz,
+				     void *data) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain,
+				   u32 flags,
+				   size_t actions_sz,
+				   __be64 actions[]) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_pop_vlan(void) { return NULL; }
+
+static inline struct mlx5dr_action *
+mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain,
+			       __be32 vlan_hdr) { return NULL; }
+
+static inline int
+mlx5dr_action_destroy(struct mlx5dr_action *action) { return 0; }
+
+static inline bool
+mlx5dr_is_supported(struct mlx5_core_dev *dev) { return false; }
+
+#endif /* CONFIG_MLX5_SW_STEERING */
+
+#endif /* _MLX5DR_H_ */

include/linux/mlx5/device.h

@@ -1162,6 +1162,9 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap)
 
+#define MLX5_CAP64_FLOWTABLE(mdev, cap) \
+	MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca_cur[MLX5_CAP_FLOW_TABLE], cap)
+
 #define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
 	MLX5_GET(flow_table_nic_cap, mdev->caps.hca_max[MLX5_CAP_FLOW_TABLE], cap)
 
@@ -1225,6 +1228,10 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca_cur[MLX5_CAP_ESWITCH], cap)
 
+#define MLX5_CAP64_ESW_FLOWTABLE(mdev, cap) \
+	MLX5_GET64(flow_table_eswitch_cap, \
+		(mdev)->caps.hca_cur[MLX5_CAP_ESWITCH_FLOW_TABLE], cap)
+
 #define MLX5_CAP_ESW_MAX(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
 		 mdev->caps.hca_max[MLX5_CAP_ESWITCH], cap)

include/linux/mlx5/driver.h

@@ -626,6 +626,11 @@ struct mlx5e_resources {
 	struct mlx5_sq_bfreg       bfreg;
 };
 
+enum mlx5_sw_icm_type {
+	MLX5_SW_ICM_TYPE_STEERING,
+	MLX5_SW_ICM_TYPE_HEADER_MODIFY,
+};
+
 #define MLX5_MAX_RESERVED_GIDS 8
 
 struct mlx5_rsvd_gids {
@@ -657,11 +662,15 @@ struct mlx5_clock {
 	struct mlx5_pps            pps_info;
 };
 
+struct mlx5_dm;
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 struct mlx5_geneve;
 struct mlx5_hv_vhca;
 
+#define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
+#define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -695,6 +704,7 @@ struct mlx5_core_dev {
 	atomic_t		num_qps;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
+	struct mlx5_dm          *dm;
 	struct mlx5_vxlan       *vxlan;
 	struct mlx5_geneve      *geneve;
 	struct {
@@ -1078,6 +1088,10 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 size_t *offsets);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
+int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
+			 u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id);
+int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
+			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
 struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,

include/linux/mlx5/eswitch.h

@@ -60,7 +60,6 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 						u16 vport_num);
 void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type);
-u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw);
 struct mlx5_flow_handle *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw,
 				    u16 vport_num, u32 sqn);
@@ -74,7 +73,14 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev);
 bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
 u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
 					      u16 vport_num);
+u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw);
 #else  /* CONFIG_MLX5_ESWITCH */
+
+static inline u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
+{
+	return MLX5_ESWITCH_NONE;
+}
+
 static inline enum devlink_eswitch_encap_mode
 mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
 {

include/linux/mlx5/fs.h

@@ -84,6 +84,8 @@ enum {
 	FDB_SLOW_PATH,
 };
 
+struct mlx5_pkt_reformat;
+struct mlx5_modify_hdr;
 struct mlx5_flow_table;
 struct mlx5_flow_group;
 struct mlx5_flow_namespace;
@@ -121,7 +123,7 @@ struct mlx5_flow_destination {
 		struct {
 			u16		num;
 			u16		vhca_id;
-			u32		reformat_id;
+			struct mlx5_pkt_reformat *pkt_reformat;
 			u8		flags;
 		} vport;
 	};
@@ -195,8 +197,8 @@ enum {
 
 struct mlx5_flow_act {
 	u32 action;
-	u32 reformat_id;
+	struct mlx5_modify_hdr  *modify_hdr;
-	u32 modify_id;
+	struct mlx5_pkt_reformat *pkt_reformat;
 	uintptr_t esp_id;
 	u32 flags;
 	struct mlx5_fs_vlan vlan[MLX5_FS_VLAN_DEPTH];
@@ -205,8 +207,6 @@ struct mlx5_flow_act {
 
 #define MLX5_DECLARE_FLOW_ACT(name) \
 	struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
-				      .reformat_id = 0, \
-				      .modify_id = 0, \
 				      .flags =  0, }
 
 /* Single destination per rule.
@@ -236,19 +236,18 @@ u32 mlx5_fc_id(struct mlx5_fc *counter);
 int mlx5_fs_add_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
 int mlx5_fs_remove_rx_underlay_qpn(struct mlx5_core_dev *dev, u32 underlay_qpn);
 
-int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
+struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
-			     u8 namespace, u8 num_actions,
+						 u8 ns_type, u8 num_actions,
-			     void *modify_actions, u32 *modify_header_id);
+						 void *modify_actions);
 void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev,
-				u32 modify_header_id);
+				struct mlx5_modify_hdr *modify_hdr);
 
-int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
+struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev,
 						     int reformat_type,
 						     size_t size,
 						     void *reformat_data,
-			       enum mlx5_flow_namespace_type namespace,
+						     enum mlx5_flow_namespace_type ns_type);
-			       u32 *packet_reformat_id);
 void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
-				  u32 packet_reformat_id);
+				  struct mlx5_pkt_reformat *reformat);
 
 #endif

include/linux/mlx5/mlx5_ifc.h

@@ -282,6 +282,7 @@ enum {
 	MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT   = 0x940,
 	MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT = 0x941,
 	MLX5_CMD_OP_QUERY_MODIFY_HEADER_CONTEXT   = 0x942,
+	MLX5_CMD_OP_SYNC_STEERING                 = 0xb00,
 	MLX5_CMD_OP_FPGA_CREATE_QP                = 0x960,
 	MLX5_CMD_OP_FPGA_MODIFY_QP                = 0x961,
 	MLX5_CMD_OP_FPGA_QUERY_QP                 = 0x962,
@@ -485,7 +486,11 @@ union mlx5_ifc_gre_key_bits {
 };
 
 struct mlx5_ifc_fte_match_set_misc_bits {
-	u8         reserved_at_0[0x8];
+	u8         gre_c_present[0x1];
+	u8         reserved_auto1[0x1];
+	u8         gre_k_present[0x1];
+	u8         gre_s_present[0x1];
+	u8         source_vhca_port[0x4];
 	u8         source_sqn[0x18];
 
 	u8         source_eswitch_owner_vhca_id[0x10];
@@ -565,12 +570,38 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 
 	u8         metadata_reg_a[0x20];
 
-	u8         reserved_at_1a0[0x60];
+	u8         metadata_reg_b[0x20];
+
+	u8         reserved_at_1c0[0x40];
 };
 
 struct mlx5_ifc_fte_match_set_misc3_bits {
-	u8         reserved_at_0[0x120];
+	u8         inner_tcp_seq_num[0x20];
+
+	u8         outer_tcp_seq_num[0x20];
+
+	u8         inner_tcp_ack_num[0x20];
+
+	u8         outer_tcp_ack_num[0x20];
+
+	u8	   reserved_at_80[0x8];
+	u8         outer_vxlan_gpe_vni[0x18];
+
+	u8         outer_vxlan_gpe_next_protocol[0x8];
+	u8         outer_vxlan_gpe_flags[0x8];
+	u8	   reserved_at_b0[0x10];
+
+	u8	   icmp_header_data[0x20];
+
+	u8	   icmpv6_header_data[0x20];
+
+	u8	   icmp_type[0x8];
+	u8	   icmp_code[0x8];
+	u8	   icmpv6_type[0x8];
+	u8	   icmpv6_code[0x8];
+
 	u8         geneve_tlv_option_0_data[0x20];
+
 	u8         reserved_at_140[0xc0];
 };
 
@@ -666,7 +697,15 @@ 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[0x7200];
+	u8         reserved_at_e00[0x1200];
+
+	u8         sw_steering_nic_rx_action_drop_icm_address[0x40];
+
+	u8         sw_steering_nic_tx_action_drop_icm_address[0x40];
+
+	u8         sw_steering_nic_tx_action_allow_icm_address[0x40];
+
+	u8         reserved_at_20c0[0x5f40];
 };
 
 enum {
@@ -698,7 +737,17 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress;
 
-	u8      reserved_at_800[0x7800];
+	u8      reserved_at_800[0x1000];
+
+	u8      sw_steering_fdb_action_drop_icm_address_rx[0x40];
+
+	u8      sw_steering_fdb_action_drop_icm_address_tx[0x40];
+
+	u8      sw_steering_uplink_icm_address_rx[0x40];
+
+	u8      sw_steering_uplink_icm_address_tx[0x40];
+
+	u8      reserved_at_1900[0x6700];
 };
 
 enum {
@@ -849,6 +898,25 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         reserved_at_100[0x700];
 };
 
+struct mlx5_ifc_sync_steering_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0xc0];
+};
+
+struct mlx5_ifc_sync_steering_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_device_mem_cap_bits {
 	u8         memic[0x1];
 	u8         reserved_at_1[0x1f];
@@ -1041,6 +1109,12 @@ enum {
 	MLX5_CAP_UMR_FENCE_NONE		= 0x2,
 };
 
+enum {
+	MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED	= 1 << 7,
+	MLX5_FLEX_PARSER_ICMP_V4_ENABLED	= 1 << 8,
+	MLX5_FLEX_PARSER_ICMP_V6_ENABLED	= 1 << 9,
+};
+
 enum {
 	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
 	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
@@ -1414,7 +1488,14 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_6c0[0x4];
 	u8         flex_parser_id_geneve_tlv_option_0[0x4];
-	u8	   reserved_at_6c8[0x28];
+	u8         flex_parser_id_icmp_dw1[0x4];
+	u8         flex_parser_id_icmp_dw0[0x4];
+	u8         flex_parser_id_icmpv6_dw1[0x4];
+	u8         flex_parser_id_icmpv6_dw0[0x4];
+	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	   sf_base_id[0x10];
 
 	u8	   reserved_at_700[0x80];
@@ -2652,6 +2733,7 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_debug_cap_bits debug_cap;
 	struct mlx5_ifc_fpga_cap_bits fpga_cap;
 	struct mlx5_ifc_tls_cap_bits tls_cap;
+	struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -3255,7 +3337,11 @@ struct mlx5_ifc_esw_vport_context_bits {
 	u8         cvlan_pcp[0x3];
 	u8         cvlan_id[0xc];
 
-	u8         reserved_at_60[0x7a0];
+	u8         reserved_at_60[0x720];
+
+	u8         sw_steering_vport_icm_address_rx[0x40];
+
+	u8         sw_steering_vport_icm_address_tx[0x40];
 };
 
 enum {
@@ -4941,7 +5027,87 @@ struct mlx5_ifc_query_hca_cap_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         reserved_at_40[0x40];
+	u8         other_function[0x1];
+	u8         reserved_at_41[0xf];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_other_hca_cap_bits {
+	u8         roce[0x1];
+	u8         reserved_0[0x27f];
+};
+
+struct mlx5_ifc_query_other_hca_cap_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+
+	struct     mlx5_ifc_other_hca_cap_bits other_capability;
+};
+
+struct mlx5_ifc_query_other_hca_cap_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_2[0x10];
+	u8         function_id[0x10];
+
+	u8         reserved_3[0x20];
+};
+
+struct mlx5_ifc_modify_other_hca_cap_out_bits {
+	u8         status[0x8];
+	u8         reserved_0[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_1[0x40];
+};
+
+struct mlx5_ifc_modify_other_hca_cap_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_0[0x10];
+
+	u8         reserved_1[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_2[0x10];
+	u8         function_id[0x10];
+	u8         field_select[0x20];
+
+	struct     mlx5_ifc_other_hca_cap_bits other_capability;
+};
+
+struct mlx5_ifc_flow_table_context_bits {
+	u8         reformat_en[0x1];
+	u8         decap_en[0x1];
+	u8         sw_owner[0x1];
+	u8         termination_table[0x1];
+	u8         table_miss_action[0x4];
+	u8         level[0x8];
+	u8         reserved_at_10[0x8];
+	u8         log_size[0x8];
+
+	u8         reserved_at_20[0x8];
+	u8         table_miss_id[0x18];
+
+	u8         reserved_at_40[0x8];
+	u8         lag_master_next_table_id[0x18];
+
+	u8         reserved_at_60[0x60];
+
+	u8         sw_owner_icm_root_1[0x40];
+
+	u8         sw_owner_icm_root_0[0x40];
+
 };
 
 struct mlx5_ifc_query_flow_table_out_bits {
@@ -4952,12 +5118,7 @@ struct mlx5_ifc_query_flow_table_out_bits {
 
 	u8         reserved_at_40[0x80];
 
-	u8         reserved_at_c0[0x8];
+	struct mlx5_ifc_flow_table_context_bits flow_table_context;
-	u8         level[0x8];
-	u8         reserved_at_d0[0x8];
-	u8         log_size[0x8];
-
-	u8         reserved_at_e0[0x120];
 };
 
 struct mlx5_ifc_query_flow_table_in_bits {
@@ -5227,7 +5388,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits {
 	u8         reserved_at_60[0x20];
 };
 
-enum {
+enum mlx5_reformat_ctx_type {
 	MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0,
 	MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1,
 	MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2,
@@ -5323,7 +5484,16 @@ enum {
 	MLX5_ACTION_IN_FIELD_OUT_DIPV4         = 0x16,
 	MLX5_ACTION_IN_FIELD_OUT_FIRST_VID     = 0x17,
 	MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_A    = 0x49,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_B    = 0x50,
 	MLX5_ACTION_IN_FIELD_METADATA_REG_C_0  = 0x51,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_1  = 0x52,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_2  = 0x53,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_3  = 0x54,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_4  = 0x55,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_5  = 0x56,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM   = 0x59,
+	MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM   = 0x5B,
 };
 
 struct mlx5_ifc_alloc_modify_header_context_out_bits {
@@ -7371,35 +7541,26 @@ struct mlx5_ifc_create_mkey_in_bits {
 	u8         klm_pas_mtt[0][0x20];
 };
 
+enum {
+	MLX5_FLOW_TABLE_TYPE_NIC_RX		= 0x0,
+	MLX5_FLOW_TABLE_TYPE_NIC_TX		= 0x1,
+	MLX5_FLOW_TABLE_TYPE_ESW_EGRESS_ACL	= 0x2,
+	MLX5_FLOW_TABLE_TYPE_ESW_INGRESS_ACL	= 0x3,
+	MLX5_FLOW_TABLE_TYPE_FDB		= 0X4,
+	MLX5_FLOW_TABLE_TYPE_SNIFFER_RX		= 0X5,
+	MLX5_FLOW_TABLE_TYPE_SNIFFER_TX		= 0X6,
+};
+
 struct mlx5_ifc_create_flow_table_out_bits {
 	u8         status[0x8];
-	u8         reserved_at_8[0x18];
+	u8         icm_address_63_40[0x18];
 
 	u8         syndrome[0x20];
 
-	u8         reserved_at_40[0x8];
+	u8         icm_address_39_32[0x8];
 	u8         table_id[0x18];
 
-	u8         reserved_at_60[0x20];
+	u8         icm_address_31_0[0x20];
-};
-
-struct mlx5_ifc_flow_table_context_bits {
-	u8         reformat_en[0x1];
-	u8         decap_en[0x1];
-	u8         reserved_at_2[0x1];
-	u8         termination_table[0x1];
-	u8         table_miss_action[0x4];
-	u8         level[0x8];
-	u8         reserved_at_10[0x8];
-	u8         log_size[0x8];
-
-	u8         reserved_at_20[0x8];
-	u8         table_miss_id[0x18];
-
-	u8         reserved_at_40[0x8];
-	u8         lag_master_next_table_id[0x18];
-
-	u8         reserved_at_60[0xe0];
 };
 
 struct mlx5_ifc_create_flow_table_in_bits {