Merge tag 'mlx5-updates-2019-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2019-11-01

Misc updates for mlx5 netdev and core driver

1) Steering Core: Replace CRC32 internal implementation with standard
kernel lib.
2) Steering Core: Support IPv4 and IPv6 mixed matcher.
3) Steering Core: Lockless FTE read lookups
4) TC: Bit sized fields rewrite support.
5) FPGA: Standalone FPGA support.
6) SRIOV: Reset VF parameters configurations on SRIOV disable.
7) netdev: Dump WQs wqe descriptors on CQE with error events.
8) MISC Cleanups.
====================

Signed-off-by: David S. Miller <[e-mail]>

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

···
 
 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_icm_pool.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/cmd.c

···
 	if (!ent->page_queue) {
 		alloc_ret = alloc_ent(cmd);
 		if (alloc_ret < 0) {
-			mlx5_core_err(dev, "failed to allocate command entry\n");
+			mlx5_core_err_rl(dev, "failed to allocate command entry\n");
 			if (ent->callback) {
 				ent->callback(-EAGAIN, ent->context);
 				mlx5_free_cmd_msg(dev, ent->out);

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

···
 
 struct mlx5_fields {
 	u8  field;
-	u8  size;
+	u8  field_bsize;
+	u32 field_mask;
 	u32 offset;
 	u32 match_offset;
 };
 
-#define OFFLOAD(fw_field, size, field, off, match_field) \
-		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \
+#define OFFLOAD(fw_field, field_bsize, field_mask, field, off, match_field) \
+		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, field_bsize, field_mask, \
 		 offsetof(struct pedit_headers, field) + (off), \
 		 MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)}
 
···
 })
 
 static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
-			 void *matchmaskp, int size)
+			 void *matchmaskp, u8 bsize)
 {
 	bool same = false;
 
-	switch (size) {
-	case sizeof(u8):
+	switch (bsize) {
+	case 8:
 		same = SAME_VAL_MASK(u8, valp, maskp, matchvalp, matchmaskp);
 		break;
-	case sizeof(u16):
+	case 16:
 		same = SAME_VAL_MASK(u16, valp, maskp, matchvalp, matchmaskp);
 		break;
-	case sizeof(u32):
+	case 32:
 		same = SAME_VAL_MASK(u32, valp, maskp, matchvalp, matchmaskp);
 		break;
 	}
···
 }
 
 static struct mlx5_fields fields[] = {
-	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16),
-	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0, dmac_15_0),
-	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16),
-	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0, smac_15_0),
-	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0, ethertype),
-	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0, first_vid),
+	OFFLOAD(DMAC_47_16, 32, U32_MAX, eth.h_dest[0], 0, dmac_47_16),
+	OFFLOAD(DMAC_15_0,  16, U16_MAX, eth.h_dest[4], 0, dmac_15_0),
+	OFFLOAD(SMAC_47_16, 32, U32_MAX, eth.h_source[0], 0, smac_47_16),
+	OFFLOAD(SMAC_15_0,  16, U16_MAX, eth.h_source[4], 0, smac_15_0),
+	OFFLOAD(ETHERTYPE,  16, U16_MAX, eth.h_proto, 0, ethertype),
+	OFFLOAD(FIRST_VID,  16, U16_MAX, vlan.h_vlan_TCI, 0, first_vid),
 
-	OFFLOAD(IP_TTL, 1, ip4.ttl,   0, ttl_hoplimit),
-	OFFLOAD(SIPV4,  4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
-	OFFLOAD(DIPV4,  4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+	OFFLOAD(IP_DSCP, 8,    0xfc, ip4.tos,   0, ip_dscp),
+	OFFLOAD(IP_TTL,  8,  U8_MAX, ip4.ttl,   0, ttl_hoplimit),
+	OFFLOAD(SIPV4,  32, U32_MAX, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+	OFFLOAD(DIPV4,  32, U32_MAX, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 
-	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0,
+	OFFLOAD(SIPV6_127_96, 32, U32_MAX, ip6.saddr.s6_addr32[0], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[0]),
-	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0,
+	OFFLOAD(SIPV6_95_64,  32, U32_MAX, ip6.saddr.s6_addr32[1], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[4]),
-	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0,
+	OFFLOAD(SIPV6_63_32,  32, U32_MAX, ip6.saddr.s6_addr32[2], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[8]),
-	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0,
+	OFFLOAD(SIPV6_31_0,   32, U32_MAX, ip6.saddr.s6_addr32[3], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[12]),
-	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0,
+	OFFLOAD(DIPV6_127_96, 32, U32_MAX, ip6.daddr.s6_addr32[0], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]),
-	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0,
+	OFFLOAD(DIPV6_95_64,  32, U32_MAX, ip6.daddr.s6_addr32[1], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]),
-	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0,
+	OFFLOAD(DIPV6_63_32,  32, U32_MAX, ip6.daddr.s6_addr32[2], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]),
-	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0,
+	OFFLOAD(DIPV6_31_0,   32, U32_MAX, ip6.daddr.s6_addr32[3], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
-	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit),
+	OFFLOAD(IPV6_HOPLIMIT, 8,  U8_MAX, ip6.hop_limit, 0, ttl_hoplimit),
 
-	OFFLOAD(TCP_SPORT, 2, tcp.source,  0, tcp_sport),
-	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0, tcp_dport),
-	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags),
+	OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source,  0, tcp_sport),
+	OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest,    0, tcp_dport),
+	/* in linux iphdr tcp_flags is 8 bits long */
+	OFFLOAD(TCP_FLAGS,  8,  U8_MAX, tcp.ack_seq, 5, tcp_flags),
 
-	OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport),
-	OFFLOAD(UDP_DPORT, 2, udp.dest,   0, udp_dport),
+	OFFLOAD(UDP_SPORT, 16, U16_MAX, udp.source, 0, udp_sport),
+	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
 /* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
···
 				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
-	void *headers_c = get_match_headers_criteria(*action_flags,
-						     &parse_attr->spec);
-	void *headers_v = get_match_headers_value(*action_flags,
-						  &parse_attr->spec);
 	int i, action_size, nactions, max_actions, first, last, next_z;
-	void *s_masks_p, *a_masks_p, *vals_p;
+	void *headers_c, *headers_v, *action, *vals_p;
+	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5_fields *f;
-	u8 cmd, field_bsize;
-	u32 s_mask, a_mask;
 	unsigned long mask;
 	__be32 mask_be32;
 	__be16 mask_be16;
-	void *action;
+	u8 cmd;
+
+	headers_c = get_match_headers_criteria(*action_flags, &parse_attr->spec);
+	headers_v = get_match_headers_value(*action_flags, &parse_attr->spec);
 
 	set_masks = &hdrs[0].masks;
 	add_masks = &hdrs[1].masks;
···
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
 
-		memcpy(&s_mask, s_masks_p, f->size);
-		memcpy(&a_mask, a_masks_p, f->size);
+		s_mask = *s_masks_p & f->field_mask;
+		a_mask = *a_masks_p & f->field_mask;
 
 		if (!s_mask && !a_mask) /* nothing to offload here */
 			continue;
···
 			vals_p = (void *)set_vals + f->offset;
 			/* don't rewrite if we have a match on the same value */
 			if (cmp_val_mask(vals_p, s_masks_p, match_val,
-					 match_mask, f->size))
+					 match_mask, f->field_bsize))
 				skip = true;
 			/* clear to denote we consumed this field */
-			memset(s_masks_p, 0, f->size);
+			*s_masks_p &= ~f->field_mask;
 		} else {
-			u32 zero = 0;
-
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
 			/* add 0 is no change */
-			if (!memcmp(vals_p, &zero, f->size))
+			if ((*(u32 *)vals_p & f->field_mask) == 0)
 				skip = true;
 			/* clear to denote we consumed this field */
-			memset(a_masks_p, 0, f->size);
+			*a_masks_p &= ~f->field_mask;
 		}
 		if (skip)
 			continue;
 
-		field_bsize = f->size * BITS_PER_BYTE;
-
-		if (field_bsize == 32) {
+		if (f->field_bsize == 32) {
 			mask_be32 = *(__be32 *)&mask;
 			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-		} else if (field_bsize == 16) {
+		} else if (f->field_bsize == 16) {
 			mask_be16 = *(__be16 *)&mask;
 			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
 		}
 
-		first = find_first_bit(&mask, field_bsize);
-		next_z = find_next_zero_bit(&mask, field_bsize, first);
-		last  = find_last_bit(&mask, field_bsize);
+		first = find_first_bit(&mask, f->field_bsize);
+		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
+		last  = find_last_bit(&mask, f->field_bsize);
 		if (first < next_z && next_z < last) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "rewrite of few sub-fields isn't supported");
···
 		MLX5_SET(set_action_in, action, field, f->field);
 
 		if (cmd == MLX5_ACTION_TYPE_SET) {
-			MLX5_SET(set_action_in, action, offset, first);
+			int start;
+
+			/* if field is bit sized it can start not from first bit */
+			start = find_first_bit((unsigned long *)&f->field_mask,
+					       f->field_bsize);
+
+			MLX5_SET(set_action_in, action, offset, first - start);
 			/* length is num of bits to be written, zero means length of 32 */
 			MLX5_SET(set_action_in, action, length, (last - first + 1));
 		}
 
-		if (field_bsize == 32)
+		if (f->field_bsize == 32)
 			MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p) >> first);
-		else if (field_bsize == 16)
+		else if (f->field_bsize == 16)
 			MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p) >> first);
-		else if (field_bsize == 8)
+		else if (f->field_bsize == 8)
 			MLX5_SET(set_action_in, action, data, *(u8 *)vals_p >> first);
 
 		action += action_size;
···
 			return -EOPNOTSUPP;
 		}
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	}
+
+	if (!(attr->action &
+	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+		NL_SET_ERR_MSG(extack, "Rule must have at least one forward/drop action");
+		return -EOPNOTSUPP;
 	}
 
 	if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {

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

···
 		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
+				struct mlx5e_tx_wqe_info *wi;
+				u16 ci;
+
+				ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+				wi = &sq->db.wqe_info[ci];
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
+				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover_work);
 			}

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

···
 	flush_workqueue(esw->work_queue);
 }
 
+static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int i;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		memset(&vport->info, 0, sizeof(vport->info));
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
···
 	return err;
 }
 
-void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
 {
 	int old_mode;
 
···
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
+	if (clear_vf)
+		mlx5_eswitch_clear_vf_vports_info(esw);
 }
 
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)

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

···
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
 int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode);
-void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       u16 vport, u8 mac[ETH_ALEN]);
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
···
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int  mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) { return 0; }
-static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
+static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {}
 static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
 static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)

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

···
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_disable(esw, false);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
···
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_disable(esw, false);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");

drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h

···
 
 #include <linux/mlx5/driver.h>
 
-enum mlx5_fpga_device_id {
-	MLX5_FPGA_DEVICE_UNKNOWN = 0,
-	MLX5_FPGA_DEVICE_KU040 = 1,
-	MLX5_FPGA_DEVICE_KU060 = 2,
-	MLX5_FPGA_DEVICE_KU060_2 = 3,
+enum mlx5_fpga_id {
+	MLX5_FPGA_NEWTON = 0,
+	MLX5_FPGA_EDISON = 1,
+	MLX5_FPGA_MORSE = 2,
+	MLX5_FPGA_MORSEQ = 3,
 };
 
 enum mlx5_fpga_image {

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

···
 	}
 }
 
-static const char *mlx5_fpga_device_name(u32 device)
+static const char *mlx5_fpga_name(u32 fpga_id)
 {
-	switch (device) {
-	case MLX5_FPGA_DEVICE_KU040:
-		return "ku040";
-	case MLX5_FPGA_DEVICE_KU060:
-		return "ku060";
-	case MLX5_FPGA_DEVICE_KU060_2:
-		return "ku060_2";
-	case MLX5_FPGA_DEVICE_UNKNOWN:
-	default:
-		return "unknown";
+	static char ret[32];
+
+	switch (fpga_id) {
+	case MLX5_FPGA_NEWTON:
+		return "Newton";
+	case MLX5_FPGA_EDISON:
+		return "Edison";
+	case MLX5_FPGA_MORSE:
+		return "Morse";
+	case MLX5_FPGA_MORSEQ:
+		return "MorseQ";
 	}
+
+	snprintf(ret, sizeof(ret), "Unknown %d", fpga_id);
+	return ret;
+}
+
+static int mlx5_is_fpga_lookaside(u32 fpga_id)
+{
+	return fpga_id != MLX5_FPGA_NEWTON && fpga_id != MLX5_FPGA_EDISON;
 }
 
 static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev)
···
 	fdev->last_admin_image = query.admin_image;
 	fdev->last_oper_image = query.oper_image;
 
-	mlx5_fpga_dbg(fdev, "Status %u; Admin image %u; Oper image %u\n",
-		      query.status, query.admin_image, query.oper_image);
+	mlx5_fpga_info(fdev, "Status %u; Admin image %u; Oper image %u\n",
+		       query.status, query.admin_image, query.oper_image);
+
+	/* for FPGA lookaside projects FPGA load status is not important */
+	if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id)))
+		return 0;
 
 	if (query.status != MLX5_FPGA_STATUS_SUCCESS) {
 		mlx5_fpga_err(fdev, "%s image failed to load; status %u\n",
···
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 	unsigned int max_num_qps;
 	unsigned long flags;
-	u32 fpga_device_id;
+	u32 fpga_id;
 	int err;
 
 	if (!fdev)
 		return 0;
 
-	err = mlx5_fpga_device_load_check(fdev);
-	if (err)
-		goto out;
-
 	err = mlx5_fpga_caps(fdev->mdev);
 	if (err)
 		goto out;
 
-	fpga_device_id = MLX5_CAP_FPGA(fdev->mdev, fpga_device);
-	mlx5_fpga_info(fdev, "%s:%u; %s image, version %u; SBU %06x:%04x version %d\n",
-		       mlx5_fpga_device_name(fpga_device_id),
-		       fpga_device_id,
+	err = mlx5_fpga_device_load_check(fdev);
+	if (err)
+		goto out;
+
+	fpga_id = MLX5_CAP_FPGA(fdev->mdev, fpga_id);
+	mlx5_fpga_info(fdev, "FPGA card %s:%u\n", mlx5_fpga_name(fpga_id), fpga_id);
+
+	/* No QPs if FPGA does not participate in net processing */
+	if (mlx5_is_fpga_lookaside(fpga_id))
+		goto out;
+
+	mlx5_fpga_info(fdev, "%s(%d): image, version %u; SBU %06x:%04x version %d\n",
 		       mlx5_fpga_image_name(fdev->last_oper_image),
+		       fdev->last_oper_image,
 		       MLX5_CAP_FPGA(fdev->mdev, image_version),
 		       MLX5_CAP_FPGA(fdev->mdev, ieee_vendor_id),
 		       MLX5_CAP_FPGA(fdev->mdev, sandbox_product_id),
···
 	int err;
 
 	if (!fdev)
+		return;
+
+	if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id)))
 		return;
 
 	spin_lock_irqsave(&fdev->state_lock, flags);

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

···
 	}
 }
 
+static void del_sw_fte_rcu(struct rcu_head *head)
+{
+	struct fs_fte *fte = container_of(head, struct fs_fte, rcu);
+	struct mlx5_flow_steering *steering = get_steering(&fte->node);
+
+	kmem_cache_free(steering->ftes_cache, fte);
+}
+
 static void del_sw_fte(struct fs_node *node)
 {
-	struct mlx5_flow_steering *steering = get_steering(node);
 	struct mlx5_flow_group *fg;
 	struct fs_fte *fte;
 	int err;
···
 				     rhash_fte);
 	WARN_ON(err);
 	ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index);
-	kmem_cache_free(steering->ftes_cache, fte);
+
+	call_rcu(&fte->rcu, del_sw_fte_rcu);
 }
 
 static void del_hw_flow_group(struct fs_node *node)
···
 }
 
 static struct fs_fte *
-lookup_fte_locked(struct mlx5_flow_group *g,
-		  const u32 *match_value,
-		  bool take_write)
+lookup_fte_for_write_locked(struct mlx5_flow_group *g, const u32 *match_value)
 {
 	struct fs_fte *fte_tmp;
 
-	if (take_write)
-		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
-	else
-		nested_down_read_ref_node(&g->node, FS_LOCK_PARENT);
-	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value,
-					 rhash_fte);
+	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+
+	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, rhash_fte);
 	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
 		fte_tmp = NULL;
 		goto out;
 	}
+
+	if (!fte_tmp->node.active) {
+		tree_put_node(&fte_tmp->node, false);
+		fte_tmp = NULL;
+		goto out;
+	}
+	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+
+out:
+	up_write_ref_node(&g->node, false);
+	return fte_tmp;
+}
+
+static struct fs_fte *
+lookup_fte_for_read_locked(struct mlx5_flow_group *g, const u32 *match_value)
+{
+	struct fs_fte *fte_tmp;
+
+	if (!tree_get_node(&g->node))
+		return NULL;
+
+	rcu_read_lock();
+	fte_tmp = rhashtable_lookup(&g->ftes_hash, match_value, rhash_fte);
+	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+		rcu_read_unlock();
+		fte_tmp = NULL;
+		goto out;
+	}
+	rcu_read_unlock();
+
 	if (!fte_tmp->node.active) {
 		tree_put_node(&fte_tmp->node, false);
 		fte_tmp = NULL;
···
 	}
 
 	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+
 out:
-	if (take_write)
-		up_write_ref_node(&g->node, false);
-	else
-		up_read_ref_node(&g->node);
+	tree_put_node(&g->node, false);
 	return fte_tmp;
+}
+
+static struct fs_fte *
+lookup_fte_locked(struct mlx5_flow_group *g, const u32 *match_value, bool write)
+{
+	if (write)
+		return lookup_fte_for_write_locked(g, match_value);
+	else
+		return lookup_fte_for_read_locked(g, match_value);
 }
 
 static struct mlx5_flow_handle *
···
 		return rule;
 	}
 
+	fte = alloc_fte(ft, spec, flow_act);
+	if (IS_ERR(fte)) {
+		up_write_ref_node(&ft->node, false);
+		err = PTR_ERR(fte);
+		goto err_alloc_fte;
+	}
+
 	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 	up_write_ref_node(&ft->node, false);
 
···
 	if (err)
 		goto err_release_fg;
 
-	fte = alloc_fte(ft, spec, flow_act);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		goto err_release_fg;
-	}
-
 	err = insert_fte(g, fte);
-	if (err) {
-		kmem_cache_free(steering->ftes_cache, fte);
+	if (err)
 		goto err_release_fg;
-	}
 
 	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
 	up_write_ref_node(&g->node, false);
···
 
 err_release_fg:
 	up_write_ref_node(&g->node, false);
+	kmem_cache_free(steering->ftes_cache, fte);
+err_alloc_fte:
 	tree_put_node(&g->node, false);
 	return ERR_PTR(err);
 }

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

···
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 	struct rhash_head		hash;
+	struct rcu_head	rcu;
 	int				modify_mask;
 };
 

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

···
 {
 	*port1 = 1;
 	*port2 = 2;
-	if (!tracker->netdev_state[0].tx_enabled ||
-	    !tracker->netdev_state[0].link_up) {
+	if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled ||
+	    !tracker->netdev_state[MLX5_LAG_P1].link_up) {
 		*port1 = 2;
 		return;
 	}
 
-	if (!tracker->netdev_state[1].tx_enabled ||
-	    !tracker->netdev_state[1].link_up)
+	if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled ||
+	    !tracker->netdev_state[MLX5_LAG_P2].link_up)
 		*port2 = 1;
 }
 
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	u8 v2p_port1, v2p_port2;
 	int err;
 
 	mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1,
 				       &v2p_port2);
 
-	if (v2p_port1 != ldev->v2p_map[0] ||
-	    v2p_port2 != ldev->v2p_map[1]) {
-		ldev->v2p_map[0] = v2p_port1;
-		ldev->v2p_map[1] = v2p_port2;
+	if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] ||
+	    v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) {
+		ldev->v2p_map[MLX5_LAG_P1] = v2p_port1;
+		ldev->v2p_map[MLX5_LAG_P2] = v2p_port2;
 
 		mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d",
-			       ldev->v2p_map[0], ldev->v2p_map[1]);
+			       ldev->v2p_map[MLX5_LAG_P1],
+			       ldev->v2p_map[MLX5_LAG_P2]);
 
 		err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
 		if (err)
···
 static int mlx5_create_lag(struct mlx5_lag *ldev,
 			   struct lag_tracker *tracker)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	int err;
 
-	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
-				       &ldev->v2p_map[1]);
+	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1],
+				       &ldev->v2p_map[MLX5_LAG_P2]);
 
 	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
-		       ldev->v2p_map[0], ldev->v2p_map[1]);
+		       ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]);
 
-	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]);
+	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1],
+				  ldev->v2p_map[MLX5_LAG_P2]);
 	if (err)
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
···
 		      u8 flags)
 {
 	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	int err;
 
 	err = mlx5_create_lag(ldev, tracker);
···
 
 static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	int err;
 
···
 
 static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 {
-	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+	if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev)
 		return false;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	return mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+	return mlx5_esw_lag_prereq(ldev->pf[MLX5_LAG_P1].dev,
+				   ldev->pf[MLX5_LAG_P2].dev);
 #else
-	return (!mlx5_sriov_is_enabled(ldev->pf[0].dev) &&
-		!mlx5_sriov_is_enabled(ldev->pf[1].dev));
+	return (!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P1].dev) &&
+		!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P2].dev));
 #endif
 }
 
···
 
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
-	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
 	struct lag_tracker tracker;
 	bool do_bond, roce_lag;
 	int err;
···
 		goto unlock;
 
 	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		ndev = ldev->tracker.netdev_state[0].tx_enabled ?
-		       ldev->pf[0].netdev : ldev->pf[1].netdev;
+		ndev = ldev->tracker.netdev_state[MLX5_LAG_P1].tx_enabled ?
+		       ldev->pf[MLX5_LAG_P1].netdev :
+		       ldev->pf[MLX5_LAG_P2].netdev;
 	} else {
-		ndev = ldev->pf[0].netdev;
+		ndev = ldev->pf[MLX5_LAG_P1].netdev;
 	}
 	if (ndev)
 		dev_hold(ndev);
···
 		return true;
 
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !__mlx5_lag_is_roce(ldev) || ldev->pf[0].dev == dev)
+	if (!ldev || !__mlx5_lag_is_roce(ldev) ||
+	    ldev->pf[MLX5_LAG_P1].dev == dev)
 		return true;
 
 	/* If bonded, we do not add an IB device for PF1. */
···
 	ldev = mlx5_lag_dev_get(dev);
 	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
-		mdev[0] = ldev->pf[0].dev;
-		mdev[1] = ldev->pf[1].dev;
+		mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev;
+		mdev[MLX5_LAG_P2] = ldev->pf[MLX5_LAG_P2].dev;
 	} else {
 		num_ports = 1;
-		mdev[0] = dev;
+		mdev[MLX5_LAG_P1] = dev;
 	}
 
 	for (i = 0; i < num_ports; ++i) {

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

···
 #include "lag_mp.h"
 
 enum {
+	MLX5_LAG_P1,
+	MLX5_LAG_P2,
+};
+
+enum {
 	MLX5_LAG_FLAG_ROCE   = 1 << 0,
 	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
 	MLX5_LAG_FLAG_MULTIPATH = 1 << 2,

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

···
 
 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
 {
-	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+	if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev)
 		return false;
 
-	return mlx5_esw_multipath_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+	return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev,
+					 ldev->pf[MLX5_LAG_P2].dev);
 }
 
 static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
···
  *     2 - set affinity to port 2.
  *
  **/
-static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port)
+static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev,
+				       enum mlx5_lag_port_affinity port)
 {
 	struct lag_tracker tracker;
 
···
 		return;
 
 	switch (port) {
-	case 0:
-		tracker.netdev_state[0].tx_enabled = true;
-		tracker.netdev_state[1].tx_enabled = true;
-		tracker.netdev_state[0].link_up = true;
-		tracker.netdev_state[1].link_up = true;
+	case MLX5_LAG_NORMAL_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
 		break;
-	case 1:
-		tracker.netdev_state[0].tx_enabled = true;
-		tracker.netdev_state[0].link_up = true;
-		tracker.netdev_state[1].tx_enabled = false;
-		tracker.netdev_state[1].link_up = false;
+	case MLX5_LAG_P1_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = false;
 		break;
-	case 2:
-		tracker.netdev_state[0].tx_enabled = false;
-		tracker.netdev_state[0].link_up = false;
-		tracker.netdev_state[1].tx_enabled = true;
-		tracker.netdev_state[1].link_up = true;
+	case MLX5_LAG_P2_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = false;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
 		break;
 	default:
-		mlx5_core_warn(ldev->pf[0].dev, "Invalid affinity port %d",
-			       port);
+		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+			       "Invalid affinity port %d", port);
 		return;
 	}
 
-	if (tracker.netdev_state[0].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[0].dev->priv.events,
+	if (tracker.netdev_state[MLX5_LAG_P1].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P1].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
-	if (tracker.netdev_state[1].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[1].dev->priv.events,
+	if (tracker.netdev_state[MLX5_LAG_P2].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P2].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
···
 	/* Verify next hops are ports of the same hca */
 	fib_nh0 = fib_info_nh(fi, 0);
 	fib_nh1 = fib_info_nh(fi, 1);
-	if (!(fib_nh0->fib_nh_dev == ldev->pf[0].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[1].netdev) &&
-	    !(fib_nh0->fib_nh_dev == ldev->pf[1].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[0].netdev)) {
-		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
+	if (!(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev) &&
+	    !(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev)) {
+		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+			       "Multipath offload require two ports of the same HCA\n");
 		return;
 	}
 
···
 		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH);
 	}
 
-	mlx5_lag_set_port_affinity(ldev, 0);
+	mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY);
 	mp->mfi = fi;
 }
 
···
 		}
 	} else if (event == FIB_EVENT_NH_ADD &&
 		   fib_info_num_path(fi) == 2) {
-		mlx5_lag_set_port_affinity(ldev, 0);
+		mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY);
 	}
 }
 
···
 			return notifier_from_errno(-EINVAL);
 		}
 		fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
-		if (fib_dev != ldev->pf[0].netdev &&
-		    fib_dev != ldev->pf[1].netdev) {
+		if (fib_dev != ldev->pf[MLX5_LAG_P1].netdev &&
+		    fib_dev != ldev->pf[MLX5_LAG_P2].netdev) {
 			return NOTIFY_DONE;
 		}
 		fib_work = mlx5_lag_init_fib_work(ldev, event);

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

···
 #include "lag.h"
 #include "mlx5_core.h"
 
+enum mlx5_lag_port_affinity {
+	MLX5_LAG_NORMAL_AFFINITY,
+	MLX5_LAG_P1_AFFINITY,
+	MLX5_LAG_P2_AFFINITY,
+};
+
 struct lag_mp {
 	struct notifier_block     fib_nb;
 	struct fib_info           *mfi; /* used in tracking fib events */

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

···
 
 static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
-	int err = 0;
-
 	if (cleanup) {
 		mlx5_unregister_device(dev);
 		mlx5_drain_health_wq(dev);
···
 	mlx5_function_teardown(dev, cleanup);
 out:
 	mutex_unlock(&dev->intf_state_mutex);
-	return err;
+	return 0;
 }
 
 static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)

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

···
 	return 0;
 }
 
-static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
+static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev, bool clear_vf)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
 	int num_vfs = pci_num_vf(dev->pdev);
···
 	}
 
 	if (MLX5_ESWITCH_MANAGER(dev))
-		mlx5_eswitch_disable(dev->priv.eswitch);
+		mlx5_eswitch_disable(dev->priv.eswitch, clear_vf);
 
 	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
···
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
 		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
-		mlx5_device_disable_sriov(dev);
+		mlx5_device_disable_sriov(dev, true);
 	}
 	return err;
 }
···
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
 
 	pci_disable_sriov(pdev);
-	mlx5_device_disable_sriov(dev);
+	mlx5_device_disable_sriov(dev, true);
 }
 
 int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
···
 	if (!mlx5_core_is_pf(dev))
 		return;
 
-	mlx5_device_disable_sriov(dev);
+	mlx5_device_disable_sriov(dev, false);
 }
 
 static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)

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

···
-// 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

···
 		goto uninit_resourses;
 	}
 
-	/* Init CRC table for htbl CRC calculation */
-	mlx5dr_crc32_init_table();
-
 	return dmn;
 
 uninit_resourses:

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

···
 
 int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
 				   struct mlx5dr_matcher_rx_tx *nic_matcher,
-				   bool ipv6)
+				   enum mlx5dr_ipv outer_ipv,
+				   enum mlx5dr_ipv inner_ipv)
 {
-	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;
-	}
+	nic_matcher->ste_builder =
+		nic_matcher->ste_builder_arr[outer_ipv][inner_ipv];
+	nic_matcher->num_of_builders =
+		nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv];
 
-	if (!nic_matcher->num_of_builders) {
+	if (!nic_matcher->ste_builder) {
 		mlx5dr_dbg(matcher->tbl->dmn,
 			   "Rule not supported on this matcher due to IP related fields\n");
 		return -EINVAL;
···
 
 static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 				       struct mlx5dr_matcher_rx_tx *nic_matcher,
-				       bool ipv6)
+				       enum mlx5dr_ipv outer_ipv,
+				       enum mlx5dr_ipv inner_ipv)
 {
 	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;
-	}
-
+	sb = nic_matcher->ste_builder_arr[outer_ipv][inner_ipv];
 	rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
 
 	/* Create a temporary mask to track and clear used mask fields */
···
 		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 (outer_ipv == DR_RULE_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_L2_DST(mask.inner, mask.misc, inner))
 			mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
 
-		if (ipv6) {
+		if (inner_ipv == DR_RULE_IPV6) {
 			if (dr_mask_is_dst_addr_set(&mask.inner))
 				mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
 								 inner, rx);
···
 		}
 	}
 
-	*num_of_builders = idx;
+	nic_matcher->ste_builder = sb;
+	nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv] = idx;
 
 	return 0;
 }
···
 	}
 }
 
-static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
-			       struct mlx5dr_matcher_rx_tx *nic_matcher)
+static int dr_matcher_set_all_ste_builders(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);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV4);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV6);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV4);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV6);
 
-	if (ret_v4 && ret_v6) {
+	if (!nic_matcher->ste_builder) {
 		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;
+	return 0;
+}
+
+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 = dr_matcher_set_all_ste_builders(matcher, nic_matcher);
+	if (ret)
+		return ret;
 
 	nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
 						      DR_CHUNK_SIZE_1,

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

···
 	return 0;
 }
 
-static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param)
+static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec)
 {
-	return (param->outer.ip_version == 6 ||
-		param->inner.ip_version == 6 ||
-		param->outer.ethertype == ETH_P_IPV6 ||
-		param->inner.ethertype == ETH_P_IPV6);
+	if (spec->ip_version == 6 || spec->ethertype == ETH_P_IPV6)
+		return DR_RULE_IPV6;
+
+	return DR_RULE_IPV4;
 }
 
 static bool dr_rule_skip(enum mlx5dr_domain_type domain,
···
 
 	ret = mlx5dr_matcher_select_builders(matcher,
 					     nic_matcher,
-					     dr_rule_is_ipv6(param));
+					     dr_rule_get_ipv(&param->outer),
+					     dr_rule_get_ipv(&param->inner));
 	if (ret)
 		goto out_err;
 

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

···
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/types.h>
+#include <linux/crc32.h>
 #include "dr_types.h"
 
 #define DR_STE_CRC_POLY 0xEDB88320L
···
 	u8 mask[DR_STE_SIZE_MASK];
 };
 
+static u32 dr_ste_crc32_calc(const void *input_data, size_t length)
+{
+	u32 crc = crc32(0, input_data, length);
+
+	return htonl(crc);
+}
+
 u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
 {
 	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
···
 		bit = bit >> 1;
 	}
 
-	crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG);
+	crc32 = dr_ste_crc32_calc(masked, DR_STE_SIZE_TAG);
 	index = crc32 & (htbl->chunk->num_of_entries - 1);
 
 	return index;

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

···
 	DR_ACTION_TYP_MAX,
 };
 
+enum mlx5dr_ipv {
+	DR_RULE_IPV4,
+	DR_RULE_IPV6,
+	DR_RULE_IPV_MAX,
+};
+
 struct mlx5dr_icm_pool;
 struct mlx5dr_icm_chunk;
 struct mlx5dr_icm_bucket;
···
 	struct mlx5dr_ste_htbl *s_htbl;
 	struct mlx5dr_ste_htbl *e_anchor;
 	struct mlx5dr_ste_build *ste_builder;
-	struct mlx5dr_ste_build ste_builder4[DR_RULE_MAX_STES];
-	struct mlx5dr_ste_build ste_builder6[DR_RULE_MAX_STES];
+	struct mlx5dr_ste_build ste_builder_arr[DR_RULE_IPV_MAX]
+					       [DR_RULE_IPV_MAX]
+					       [DR_RULE_MAX_STES];
 	u8 num_of_builders;
-	u8 num_of_builders4;
-	u8 num_of_builders6;
+	u8 num_of_builders_arr[DR_RULE_IPV_MAX][DR_RULE_IPV_MAX];
 	u64 default_icm_addr;
 	struct mlx5dr_table_rx_tx *nic_tbl;
 };
···
 
 int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
 				   struct mlx5dr_matcher_rx_tx *nic_matcher,
-				   bool ipv6);
+				   enum mlx5dr_ipv outer_ipv,
+				   enum mlx5dr_ipv inner_ipv);
 
 static inline u32
 mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size)
···
 void mlx5dr_ste_copy_param(u8 match_criteria,
 			   struct mlx5dr_match_param *set_param,
 			   struct mlx5dr_match_parameters *mask);
-
-void mlx5dr_crc32_init_table(void);
-u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length);
 
 struct mlx5dr_qp {
 	struct mlx5_core_dev *mdev;

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

···
 #include "wq.h"
 #include "mlx5_core.h"
 
-u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
-{
-	return (u32)wq->fbc.sz_m1 + 1;
-}
-
-u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
-{
-	return wq->fbc.sz_m1 + 1;
-}
-
-u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
-{
-	return wq->fbc.log_stride;
-}
-
-u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
-{
-	return (u32)wq->fbc.sz_m1 + 1;
-}
-
 static u32 wq_get_byte_sz(u8 log_sz, u8 log_stride)
 {
 	return ((u32)1 << log_sz) << log_stride;
···
 	mlx5_db_free(mdev, &wq_ctrl->db);
 
 	return err;
+}
+
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides)
+{
+	size_t len;
+	void *wqe;
+
+	if (!net_ratelimit())
+		return;
+
+	nstrides = max_t(u8, nstrides, 1);
+
+	len = nstrides << wq->fbc.log_stride;
+	wqe = mlx5_wq_cyc_get_wqe(wq, ix);
+
+	pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %ld\n",
+		mlx5_wq_cyc_get_size(wq), wq->cur_sz, ix, len);
+	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
 }
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,

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

···
 int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
···
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
 		     struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
-u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq);
 
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
+
+static inline u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
+{
+	return (u32)wq->fbc.sz_m1 + 1;
+}
 
 static inline int mlx5_wq_cyc_is_full(struct mlx5_wq_cyc *wq)
 {
···
 	return !equal && !smaller;
 }
 
+static inline u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
+{
+	return wq->fbc.sz_m1 + 1;
+}
+
+static inline u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
+{
+	return wq->fbc.log_stride;
+}
+
 static inline u32 mlx5_cqwq_ctr2ix(struct mlx5_cqwq *wq, u32 ctr)
 {
 	return ctr & wq->fbc.sz_m1;
···
 	dma_rmb();
 
 	return cqe;
+}
+
+static inline u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
+{
+	return (u32)wq->fbc.sz_m1 + 1;
 }
 
 static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq)