Merge branch 'bnxt_en-ntuple-fuilter-support'

Michael Chan says:

====================
bnxt_en: Add basic ntuple filter support

The current driver only supports ntuple filters added by aRFS.  This
patch series adds basic support for user defined TCP/UDP ntuple filters
added by the user using ethtool.  Many of the patches are refactoring
patches to make the existing code more general to support both aRFS
and user defined filters.  aRFS filters always have the Toeplitz hash
value from the NIC.  A Toepliz hash function is added in patch 5 to
get the same hash value for user defined filters.  The hash is used
to store all ntuple filters in the table and all filters must be
hashed identically using the same function and key.

v2: Fix compile error in patch #4 when CONFIG_BNXT_SRIOV is disabled.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -4199,15 +4199,24 @@ static void bnxt_init_vnics(struct bnxt *bp)
 		vnic->fw_l2_ctx_id = INVALID_HW_RING_ID;
 
 		if (bp->vnic_info[i].rss_hash_key) {
-			if (i == 0)
+			if (!i) {
+				u8 *key = (void *)vnic->rss_hash_key;
+				int k;
+
+				bp->toeplitz_prefix = 0;
 				get_random_bytes(vnic->rss_hash_key,
 					      HW_HASH_KEY_SIZE);
-			else
+				for (k = 0; k < 8; k++) {
+					bp->toeplitz_prefix <<= 8;
+					bp->toeplitz_prefix |= key[k];
+				}
+			} else {
 				memcpy(vnic->rss_hash_key,
 				       bp->vnic_info[0].rss_hash_key,
 				       HW_HASH_KEY_SIZE);
 			}
 		}
+	}
 }
 
 static int bnxt_calc_nr_ring_pages(u32 ring_size, int desc_per_pg)
@@ -4789,9 +4798,8 @@ static void bnxt_clear_ring_indices(struct bnxt *bp)
 	}
 }
 
-static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
+static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i;
 
 	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
@@ -4803,40 +4811,73 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool irq_reinit)
 		struct bnxt_ntuple_filter *fltr;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
-			hlist_del(&fltr->hash);
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			bnxt_del_l2_filter(bp, fltr->l2_fltr);
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+			bp->ntp_fltr_count--;
 			kfree(fltr);
 		}
 	}
-	if (irq_reinit) {
+	if (!all)
+		return;
+
 	bitmap_free(bp->ntp_fltr_bmap);
 	bp->ntp_fltr_bmap = NULL;
-	}
 	bp->ntp_fltr_count = 0;
-#endif
 }
 
 static int bnxt_alloc_ntp_fltrs(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
-	if (!(bp->flags & BNXT_FLAG_RFS))
+	if (!(bp->flags & BNXT_FLAG_RFS) || bp->ntp_fltr_bmap)
 		return 0;
 
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++)
 		INIT_HLIST_HEAD(&bp->ntp_fltr_hash_tbl[i]);
 
 	bp->ntp_fltr_count = 0;
-	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_NTP_FLTR_MAX_FLTR, GFP_KERNEL);
+	bp->ntp_fltr_bmap = bitmap_zalloc(BNXT_MAX_FLTR, GFP_KERNEL);
 
 	if (!bp->ntp_fltr_bmap)
 		rc = -ENOMEM;
 
 	return rc;
-#else
-	return 0;
-#endif
+}
+
+static void bnxt_free_l2_filters(struct bnxt *bp, bool all)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++) {
+		struct hlist_head *head;
+		struct hlist_node *tmp;
+		struct bnxt_l2_filter *fltr;
+
+		head = &bp->l2_fltr_hash_tbl[i];
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
+			if (!all && (fltr->base.flags & BNXT_ACT_FUNC_DST))
+				continue;
+			hlist_del(&fltr->base.hash);
+			if (fltr->base.flags) {
+				clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+				bp->ntp_fltr_count--;
+			}
+			kfree(fltr);
+		}
+	}
+}
+
+static void bnxt_init_l2_fltr_tbl(struct bnxt *bp)
+{
+	int i;
+
+	for (i = 0; i < BNXT_L2_FLTR_HASH_SIZE; i++)
+		INIT_HLIST_HEAD(&bp->l2_fltr_hash_tbl[i]);
+	get_random_bytes(&bp->hash_seed, sizeof(bp->hash_seed));
 }
 
 static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
@@ -4846,7 +4887,8 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_rx_rings(bp);
 	bnxt_free_cp_rings(bp);
 	bnxt_free_all_cp_arrays(bp);
-	bnxt_free_ntp_fltrs(bp, irq_re_init);
+	bnxt_free_ntp_fltrs(bp, false);
+	bnxt_free_l2_filters(bp, false);
 	if (irq_re_init) {
 		bnxt_free_ring_stats(bp);
 		if (!(bp->phy_flags & BNXT_PHY_FL_PORT_STATS_NO_RESET) ||
@@ -5290,25 +5332,301 @@ static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id)
 	return hwrm_req_send_silent(bp, req);
 }
 
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	if (!atomic_dec_and_test(&fltr->refcnt))
+		return;
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	if (fltr->base.flags) {
+		clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+		bp->ntp_fltr_count--;
+	}
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	kfree_rcu(fltr, base.rcu);
+}
+
+static struct bnxt_l2_filter *__bnxt_lookup_l2_filter(struct bnxt *bp,
+						      struct bnxt_l2_key *key,
+						      u32 idx)
+{
+	struct hlist_head *head = &bp->l2_fltr_hash_tbl[idx];
+	struct bnxt_l2_filter *fltr;
+
+	hlist_for_each_entry_rcu(fltr, head, base.hash) {
+		struct bnxt_l2_key *l2_key = &fltr->l2_key;
+
+		if (ether_addr_equal(l2_key->dst_mac_addr, key->dst_mac_addr) &&
+		    l2_key->vlan == key->vlan)
+			return fltr;
+	}
+	return NULL;
+}
+
+static struct bnxt_l2_filter *bnxt_lookup_l2_filter(struct bnxt *bp,
+						    struct bnxt_l2_key *key,
+						    u32 idx)
+{
+	struct bnxt_l2_filter *fltr = NULL;
+
+	rcu_read_lock();
+	fltr = __bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		atomic_inc(&fltr->refcnt);
+	rcu_read_unlock();
+	return fltr;
+}
+
+#define BNXT_IPV4_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4))
+
+#define BNXT_IPV6_4TUPLE(bp, fkeys)					\
+	(((fkeys)->basic.ip_proto == IPPROTO_TCP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6) ||	\
+	 ((fkeys)->basic.ip_proto == IPPROTO_UDP &&			\
+	  (bp)->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6))
+
+static u32 bnxt_get_rss_flow_tuple_len(struct bnxt *bp, struct flow_keys *fkeys)
+{
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		if (BNXT_IPV4_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v4addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4)
+			return sizeof(fkeys->addrs.v4addrs);
+	}
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IPV6)) {
+		if (BNXT_IPV6_4TUPLE(bp, fkeys))
+			return sizeof(fkeys->addrs.v6addrs) +
+			       sizeof(fkeys->ports);
+
+		if (bp->rss_hash_cfg & VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6)
+			return sizeof(fkeys->addrs.v6addrs);
+	}
+
+	return 0;
+}
+
+static u32 bnxt_toeplitz(struct bnxt *bp, struct flow_keys *fkeys,
+			 const unsigned char *key)
+{
+	u64 prefix = bp->toeplitz_prefix, hash = 0;
+	struct bnxt_ipv4_tuple tuple4;
+	struct bnxt_ipv6_tuple tuple6;
+	int i, j, len = 0;
+	u8 *four_tuple;
+
+	len = bnxt_get_rss_flow_tuple_len(bp, fkeys);
+	if (!len)
+		return 0;
+
+	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
+		tuple4.v4addrs = fkeys->addrs.v4addrs;
+		tuple4.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple4;
+	} else {
+		tuple6.v6addrs = fkeys->addrs.v6addrs;
+		tuple6.ports = fkeys->ports;
+		four_tuple = (unsigned char *)&tuple6;
+	}
+
+	for (i = 0, j = 8; i < len; i++, j++) {
+		u8 byte = four_tuple[i];
+		int bit;
+
+		for (bit = 0; bit < 8; bit++, prefix <<= 1, byte <<= 1) {
+			if (byte & 0x80)
+				hash ^= prefix;
+		}
+		prefix |= (j < HW_HASH_KEY_SIZE) ? key[j] : 0;
+	}
+
+	/* The valid part of the hash is in the upper 32 bits. */
+	return (hash >> 32) & BNXT_NTP_FLTR_HASH_MASK;
+}
+
 #ifdef CONFIG_RFS_ACCEL
-static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+static struct bnxt_l2_filter *
+bnxt_lookup_l2_filter_from_key(struct bnxt *bp, struct bnxt_l2_key *key)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	return fltr;
+}
+#endif
+
+static int bnxt_init_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr,
+			       struct bnxt_l2_key *key, u32 idx)
+{
+	struct hlist_head *head;
+
+	ether_addr_copy(fltr->l2_key.dst_mac_addr, key->dst_mac_addr);
+	fltr->l2_key.vlan = key->vlan;
+	fltr->base.type = BNXT_FLTR_TYPE_L2;
+	if (fltr->base.flags) {
+		int bit_id;
+
+		bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
+						 BNXT_MAX_FLTR, 0);
+		if (bit_id < 0)
+			return -ENOMEM;
+		fltr->base.sw_id = (u16)bit_id;
+	}
+	head = &bp->l2_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	atomic_set(&fltr->refcnt, 1);
+	return 0;
+}
+
+static struct bnxt_l2_filter *bnxt_alloc_l2_filter(struct bnxt *bp,
+						   struct bnxt_l2_key *key,
+						   gfp_t gfp)
+{
+	struct bnxt_l2_filter *fltr;
+	u32 idx;
+	int rc;
+
+	idx = jhash2(&key->filter_key, BNXT_L2_KEY_SIZE, bp->hash_seed) &
+	      BNXT_L2_FLTR_HASH_MASK;
+	fltr = bnxt_lookup_l2_filter(bp, key, idx);
+	if (fltr)
+		return fltr;
+
+	fltr = kzalloc(sizeof(*fltr), gfp);
+	if (!fltr)
+		return ERR_PTR(-ENOMEM);
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	rc = bnxt_init_l2_filter(bp, fltr, key, idx);
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	if (rc) {
+		bnxt_del_l2_filter(bp, fltr);
+		fltr = ERR_PTR(rc);
+	}
+	return fltr;
+}
+
+static u16 bnxt_vf_target_id(struct bnxt_pf_info *pf, u16 vf_idx)
+{
+#ifdef CONFIG_BNXT_SRIOV
+	struct bnxt_vf_info *vf = &pf->vf[vf_idx];
+
+	return vf->fw_fid;
+#else
+	return INVALID_HW_RING_ID;
+#endif
+}
+
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_free_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+		if (target_id == INVALID_HW_RING_ID)
+			return -EINVAL;
+	}
+
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->l2_filter_id = fltr->base.filter_id;
+	return hwrm_req_send(bp, req);
+}
+
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr)
+{
+	struct hwrm_cfa_l2_filter_alloc_output *resp;
+	struct hwrm_cfa_l2_filter_alloc_input *req;
+	u16 target_id = 0xffff;
+	int rc;
+
+	if (fltr->base.flags & BNXT_ACT_FUNC_DST) {
+		struct bnxt_pf_info *pf = &bp->pf;
+
+		if (fltr->base.vf_idx >= pf->active_vfs)
+			return -EINVAL;
+
+		target_id = bnxt_vf_target_id(pf, fltr->base.vf_idx);
+	}
+	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
+	if (rc)
+		return rc;
+
+	req->target_id = cpu_to_le16(target_id);
+	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
+
+	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
+		req->flags |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
+	req->dst_id = cpu_to_le16(fltr->base.fw_vnic_id);
+	req->enables =
+		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
+			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
+	ether_addr_copy(req->l2_addr, fltr->l2_key.dst_mac_addr);
+	eth_broadcast_addr(req->l2_addr_mask);
+
+	if (fltr->l2_key.vlan) {
+		req->enables |=
+			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK |
+				CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS);
+		req->num_vlans = 1;
+		req->l2_ivlan = cpu_to_le16(fltr->l2_key.vlan);
+		req->l2_ivlan_mask = cpu_to_le16(0xfff);
+	}
+
+	resp = hwrm_req_hold(bp, req);
+	rc = hwrm_req_send(bp, req);
+	if (!rc) {
+		fltr->base.filter_id = resp->l2_filter_id;
+		set_bit(BNXT_FLTR_VALID, &fltr->base.state);
+	}
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 				     struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_free_input *req;
 	int rc;
 
+	set_bit(BNXT_FLTR_FW_DELETED, &fltr->base.state);
 	rc = hwrm_req_init(bp, req, HWRM_CFA_NTUPLE_FILTER_FREE);
 	if (rc)
 		return rc;
 
-	req->ntuple_filter_id = fltr->filter_id;
+	req->ntuple_filter_id = fltr->base.filter_id;
 	return hwrm_req_send(bp, req);
 }
 
 #define BNXT_NTP_FLTR_FLAGS					\
 	(CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE |	\
-	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR |	\
 	 CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK |	\
@@ -5324,12 +5642,21 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 #define BNXT_NTP_TUNNEL_FLTR_FLAG				\
 		CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE
 
-static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+void bnxt_fill_ipv6_mask(__be32 mask[4])
+{
+	int i;
+
+	for (i = 0; i < 4; i++)
+		mask[i] = cpu_to_be32(~0);
+}
+
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 				      struct bnxt_ntuple_filter *fltr)
 {
 	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct hwrm_cfa_ntuple_filter_alloc_input *req;
 	struct flow_keys *keys = &fltr->fkeys;
+	struct bnxt_l2_filter *l2_fltr;
 	struct bnxt_vnic_info *vnic;
 	u32 flags = 0;
 	int rc;
@@ -5338,122 +5665,111 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	if (rc)
 		return rc;
 
-	req->l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
+	l2_fltr = fltr->l2_fltr;
+	req->l2_filter_id = l2_fltr->base.filter_id;
+
 
 	if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
 		flags = CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX;
-		req->dst_id = cpu_to_le16(fltr->rxq);
+		req->dst_id = cpu_to_le16(fltr->base.rxq);
 	} else {
-		vnic = &bp->vnic_info[fltr->rxq + 1];
+		vnic = &bp->vnic_info[fltr->base.rxq + 1];
 		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	}
 	req->flags = cpu_to_le32(flags);
 	req->enables = cpu_to_le32(BNXT_NTP_FLTR_FLAGS);
 
 	req->ethertype = htons(ETH_P_IP);
-	memcpy(req->src_macaddr, fltr->src_mac_addr, ETH_ALEN);
 	req->ip_addr_type = CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4;
 	req->ip_protocol = keys->basic.ip_proto;
 
 	if (keys->basic.n_proto == htons(ETH_P_IPV6)) {
-		int i;
-
 		req->ethertype = htons(ETH_P_IPV6);
 		req->ip_addr_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6;
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
 			*(struct in6_addr *)&req->src_ipaddr[0] =
 				keys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(req->src_ipaddr_mask);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
 			*(struct in6_addr *)&req->dst_ipaddr[0] =
 				keys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			req->src_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
-			req->dst_ipaddr_mask[i] = cpu_to_be32(0xffffffff);
+			bnxt_fill_ipv6_mask(req->dst_ipaddr_mask);
 		}
 	} else {
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
 			req->src_ipaddr[0] = keys->addrs.v4addrs.src;
 			req->src_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
 			req->dst_ipaddr[0] = keys->addrs.v4addrs.dst;
 			req->dst_ipaddr_mask[0] = cpu_to_be32(0xffffffff);
 		}
+	}
 	if (keys->control.flags & FLOW_DIS_ENCAPSULATION) {
 		req->enables |= cpu_to_le32(BNXT_NTP_TUNNEL_FLTR_FLAG);
 		req->tunnel_type =
 			CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL;
 	}
 
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
 		req->src_port = keys->ports.src;
 		req->src_port_mask = cpu_to_be16(0xffff);
+	}
+	if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
 		req->dst_port = keys->ports.dst;
 		req->dst_port_mask = cpu_to_be16(0xffff);
+	}
 
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
 	if (!rc)
-		fltr->filter_id = resp->ntuple_filter_id;
+		fltr->base.filter_id = resp->ntuple_filter_id;
 	hwrm_req_drop(bp, req);
 	return rc;
 }
-#endif
 
 static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx,
 				     const u8 *mac_addr)
 {
-	struct hwrm_cfa_l2_filter_alloc_output *resp;
-	struct hwrm_cfa_l2_filter_alloc_input *req;
+	struct bnxt_l2_filter *fltr;
+	struct bnxt_l2_key key;
 	int rc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_ALLOC);
-	if (rc)
-		return rc;
-
-	req->flags = cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX);
-	if (!BNXT_CHIP_TYPE_NITRO_A0(bp))
-		req->flags |=
-			cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST);
-	req->dst_id = cpu_to_le16(bp->vnic_info[vnic_id].fw_vnic_id);
-	req->enables =
-		cpu_to_le32(CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID |
-			    CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK);
-	memcpy(req->l2_addr, mac_addr, ETH_ALEN);
-	req->l2_addr_mask[0] = 0xff;
-	req->l2_addr_mask[1] = 0xff;
-	req->l2_addr_mask[2] = 0xff;
-	req->l2_addr_mask[3] = 0xff;
-	req->l2_addr_mask[4] = 0xff;
-	req->l2_addr_mask[5] = 0xff;
+	ether_addr_copy(key.dst_mac_addr, mac_addr);
+	key.vlan = 0;
+	fltr = bnxt_alloc_l2_filter(bp, &key, GFP_KERNEL);
+	if (IS_ERR(fltr))
+		return PTR_ERR(fltr);
 
-	resp = hwrm_req_hold(bp, req);
-	rc = hwrm_req_send(bp, req);
-	if (!rc)
-		bp->vnic_info[vnic_id].fw_l2_filter_id[idx] =
-							resp->l2_filter_id;
-	hwrm_req_drop(bp, req);
+	fltr->base.fw_vnic_id = bp->vnic_info[vnic_id].fw_vnic_id;
+	rc = bnxt_hwrm_l2_filter_alloc(bp, fltr);
+	if (rc)
+		bnxt_del_l2_filter(bp, fltr);
+	else
+		bp->vnic_info[vnic_id].l2_filters[idx] = fltr;
 	return rc;
 }
 
 static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp)
 {
-	struct hwrm_cfa_l2_filter_free_input *req;
 	u16 i, j, num_of_vnics = 1; /* only vnic 0 supported */
-	int rc;
+	int rc = 0;
 
 	/* Any associated ntuple filters will also be cleared by firmware. */
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 0; i < num_of_vnics; i++) {
 		struct bnxt_vnic_info *vnic = &bp->vnic_info[i];
 
 		for (j = 0; j < vnic->uc_filter_count; j++) {
-			req->l2_filter_id = vnic->fw_l2_filter_id[j];
+			struct bnxt_l2_filter *fltr = vnic->l2_filters[j];
 
-			rc = hwrm_req_send(bp, req);
+			bnxt_hwrm_l2_filter_free(bp, fltr);
+			bnxt_del_l2_filter(bp, fltr);
 		}
 		vnic->uc_filter_count = 0;
 	}
-	hwrm_req_drop(bp, req);
+
 	return rc;
 }
 
@@ -9370,7 +9686,6 @@ static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 
 static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int i, rc = 0;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
@@ -9399,9 +9714,6 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 			break;
 	}
 	return rc;
-#else
-	return 0;
-#endif
 }
 
 /* Allow PF, trusted VFs and VFs with default VLAN to be in promiscuous mode */
@@ -9729,7 +10041,6 @@ static int bnxt_setup_int_mode(struct bnxt *bp)
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
 static unsigned int bnxt_get_max_func_rss_ctxs(struct bnxt *bp)
 {
 	return bp->hw_resc.max_rsscos_ctxs;
@@ -9739,7 +10050,6 @@ static unsigned int bnxt_get_max_func_vnics(struct bnxt *bp)
 {
 	return bp->hw_resc.max_vnics;
 }
-#endif
 
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 {
@@ -11742,7 +12052,6 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 {
 	struct net_device *dev = bp->dev;
 	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-	struct hwrm_cfa_l2_filter_free_input *req;
 	struct netdev_hw_addr *ha;
 	int i, off = 0, rc;
 	bool uc_update;
@@ -11754,16 +12063,12 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 	if (!uc_update)
 		goto skip_uc;
 
-	rc = hwrm_req_init(bp, req, HWRM_CFA_L2_FILTER_FREE);
-	if (rc)
-		return rc;
-	hwrm_req_hold(bp, req);
 	for (i = 1; i < vnic->uc_filter_count; i++) {
-		req->l2_filter_id = vnic->fw_l2_filter_id[i];
+		struct bnxt_l2_filter *fltr = vnic->l2_filters[i];
 
-		rc = hwrm_req_send(bp, req);
+		bnxt_hwrm_l2_filter_free(bp, fltr);
+		bnxt_del_l2_filter(bp, fltr);
 	}
-	hwrm_req_drop(bp, req);
 
 	vnic->uc_filter_count = 1;
 
@@ -11858,7 +12163,6 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 /* If runtime conditions support RFS */
 static bool bnxt_rfs_capable(struct bnxt *bp)
 {
-#ifdef CONFIG_RFS_ACCEL
 	int vnics, max_vnics, max_rss_ctxs;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
@@ -11894,9 +12198,6 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	netdev_warn(bp->dev, "Unable to reserve resources to support NTUPLE filters.\n");
 	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, 1);
 	return false;
-#else
-	return false;
-#endif
 }
 
 static netdev_features_t bnxt_fix_features(struct net_device *dev,
@@ -13559,38 +13860,102 @@ static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-#ifdef CONFIG_RFS_ACCEL
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb)
+{
+	struct bnxt_vnic_info *vnic;
+
+	if (skb)
+		return skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
+
+	vnic = &bp->vnic_info[0];
+	return bnxt_toeplitz(bp, fkeys, (void *)vnic->rss_hash_key);
+}
+
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx)
+{
+	struct hlist_head *head;
+	int bit_id;
+
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap, BNXT_MAX_FLTR, 0);
+	if (bit_id < 0) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return -ENOMEM;
+	}
+
+	fltr->base.sw_id = (u16)bit_id;
+	fltr->base.type = BNXT_FLTR_TYPE_NTUPLE;
+	fltr->base.flags |= BNXT_ACT_RING_DST;
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_add_head_rcu(&fltr->base.hash, head);
+	set_bit(BNXT_FLTR_INSERTED, &fltr->base.state);
+	bp->ntp_fltr_count++;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	return 0;
+}
+
 static bool bnxt_fltr_match(struct bnxt_ntuple_filter *f1,
 			    struct bnxt_ntuple_filter *f2)
 {
 	struct flow_keys *keys1 = &f1->fkeys;
 	struct flow_keys *keys2 = &f2->fkeys;
 
+	if (f1->ntuple_flags != f2->ntuple_flags)
+		return false;
+
 	if (keys1->basic.n_proto != keys2->basic.n_proto ||
 	    keys1->basic.ip_proto != keys2->basic.ip_proto)
 		return false;
 
 	if (keys1->basic.n_proto == htons(ETH_P_IP)) {
-		if (keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src ||
-		    keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst)
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     keys1->addrs.v4addrs.src != keys2->addrs.v4addrs.src) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     keys1->addrs.v4addrs.dst != keys2->addrs.v4addrs.dst))
 			return false;
 	} else {
-		if (memcmp(&keys1->addrs.v6addrs.src, &keys2->addrs.v6addrs.src,
-			   sizeof(keys1->addrs.v6addrs.src)) ||
-		    memcmp(&keys1->addrs.v6addrs.dst, &keys2->addrs.v6addrs.dst,
-			   sizeof(keys1->addrs.v6addrs.dst)))
+		if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.src,
+			    &keys2->addrs.v6addrs.src,
+			    sizeof(keys1->addrs.v6addrs.src))) ||
+		    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) &&
+		     memcmp(&keys1->addrs.v6addrs.dst,
+			    &keys2->addrs.v6addrs.dst,
+			    sizeof(keys1->addrs.v6addrs.dst))))
 			return false;
 	}
 
-	if (keys1->ports.ports == keys2->ports.ports &&
-	    keys1->control.flags == keys2->control.flags &&
-	    ether_addr_equal(f1->src_mac_addr, f2->src_mac_addr) &&
-	    ether_addr_equal(f1->dst_mac_addr, f2->dst_mac_addr))
+	if (((f1->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) &&
+	     keys1->ports.src != keys2->ports.src) ||
+	    ((f1->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) &&
+	     keys1->ports.dst != keys2->ports.dst))
+		return false;
+
+	if (keys1->control.flags == keys2->control.flags &&
+	    f1->l2_fltr == f2->l2_fltr)
 		return true;
 
 	return false;
 }
 
+struct bnxt_ntuple_filter *
+bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx)
+{
+	struct bnxt_ntuple_filter *f;
+	struct hlist_head *head;
+
+	head = &bp->ntp_fltr_hash_tbl[idx];
+	hlist_for_each_entry_rcu(f, head, base.hash) {
+		if (bnxt_fltr_match(f, fltr))
+			return f;
+	}
+	return NULL;
+}
+
+#ifdef CONFIG_RFS_ACCEL
 static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 			      u16 rxq_index, u32 flow_id)
 {
@@ -13598,29 +13963,31 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	struct bnxt_ntuple_filter *fltr, *new_fltr;
 	struct flow_keys *fkeys;
 	struct ethhdr *eth = (struct ethhdr *)skb_mac_header(skb);
-	int rc = 0, idx, bit_id, l2_idx = 0;
-	struct hlist_head *head;
+	struct bnxt_l2_filter *l2_fltr;
+	int rc = 0, idx;
 	u32 flags;
 
-	if (!ether_addr_equal(dev->dev_addr, eth->h_dest)) {
-		struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
-		int off = 0, j;
+	if (ether_addr_equal(dev->dev_addr, eth->h_dest)) {
+		l2_fltr = bp->vnic_info[0].l2_filters[0];
+		atomic_inc(&l2_fltr->refcnt);
+	} else {
+		struct bnxt_l2_key key;
 
-		netif_addr_lock_bh(dev);
-		for (j = 0; j < vnic->uc_filter_count; j++, off += ETH_ALEN) {
-			if (ether_addr_equal(eth->h_dest,
-					     vnic->uc_list + off)) {
-				l2_idx = j + 1;
-				break;
-			}
-		}
-		netif_addr_unlock_bh(dev);
-		if (!l2_idx)
+		ether_addr_copy(key.dst_mac_addr, eth->h_dest);
+		key.vlan = 0;
+		l2_fltr = bnxt_lookup_l2_filter_from_key(bp, &key);
+		if (!l2_fltr)
 			return -EINVAL;
+		if (l2_fltr->base.flags & BNXT_ACT_FUNC_DST) {
+			bnxt_del_l2_filter(bp, l2_fltr);
+			return -EINVAL;
+		}
 	}
 	new_fltr = kzalloc(sizeof(*new_fltr), GFP_ATOMIC);
-	if (!new_fltr)
+	if (!new_fltr) {
+		bnxt_del_l2_filter(bp, l2_fltr);
 		return -ENOMEM;
+	}
 
 	fkeys = &new_fltr->fkeys;
 	if (!skb_flow_dissect_flow_keys(skb, fkeys, 0)) {
@@ -13647,46 +14014,48 @@ static int bnxt_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 		goto err_free;
 	}
 
-	memcpy(new_fltr->dst_mac_addr, eth->h_dest, ETH_ALEN);
-	memcpy(new_fltr->src_mac_addr, eth->h_source, ETH_ALEN);
+	new_fltr->l2_fltr = l2_fltr;
+	new_fltr->ntuple_flags = BNXT_NTUPLE_MATCH_ALL;
 
-	idx = skb_get_hash_raw(skb) & BNXT_NTP_FLTR_HASH_MASK;
-	head = &bp->ntp_fltr_hash_tbl[idx];
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, skb);
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(fltr, head, hash) {
-		if (bnxt_fltr_match(fltr, new_fltr)) {
-			rc = fltr->sw_id;
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
 		rcu_read_unlock();
+		rc = fltr->base.sw_id;
 		goto err_free;
 	}
-	}
 	rcu_read_unlock();
 
-	spin_lock_bh(&bp->ntp_fltr_lock);
-	bit_id = bitmap_find_free_region(bp->ntp_fltr_bmap,
-					 BNXT_NTP_FLTR_MAX_FLTR, 0);
-	if (bit_id < 0) {
-		spin_unlock_bh(&bp->ntp_fltr_lock);
-		rc = -ENOMEM;
-		goto err_free;
-	}
-
-	new_fltr->sw_id = (u16)bit_id;
 	new_fltr->flow_id = flow_id;
-	new_fltr->l2_fltr_idx = l2_idx;
-	new_fltr->rxq = rxq_index;
-	hlist_add_head_rcu(&new_fltr->hash, head);
-	bp->ntp_fltr_count++;
-	spin_unlock_bh(&bp->ntp_fltr_lock);
-
+	new_fltr->base.rxq = rxq_index;
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
 		bnxt_queue_sp_work(bp, BNXT_RX_NTP_FLTR_SP_EVENT);
-
-	return new_fltr->sw_id;
+		return new_fltr->base.sw_id;
+	}
 
 err_free:
+	bnxt_del_l2_filter(bp, l2_fltr);
 	kfree(new_fltr);
 	return rc;
 }
+#endif
+
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr)
+{
+	spin_lock_bh(&bp->ntp_fltr_lock);
+	if (!test_and_clear_bit(BNXT_FLTR_INSERTED, &fltr->base.state)) {
+		spin_unlock_bh(&bp->ntp_fltr_lock);
+		return;
+	}
+	hlist_del_rcu(&fltr->base.hash);
+	bp->ntp_fltr_count--;
+	spin_unlock_bh(&bp->ntp_fltr_lock);
+	bnxt_del_l2_filter(bp, fltr->l2_fltr);
+	clear_bit(fltr->base.sw_id, bp->ntp_fltr_bmap);
+	kfree_rcu(fltr, base.rcu);
+}
 
 static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 {
@@ -13699,13 +14068,15 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 		int rc;
 
 		head = &bp->ntp_fltr_hash_tbl[i];
-		hlist_for_each_entry_safe(fltr, tmp, head, hash) {
+		hlist_for_each_entry_safe(fltr, tmp, head, base.hash) {
 			bool del = false;
 
-			if (test_bit(BNXT_FLTR_VALID, &fltr->state)) {
-				if (rps_may_expire_flow(bp->dev, fltr->rxq,
+			if (test_bit(BNXT_FLTR_VALID, &fltr->base.state)) {
+				if (fltr->base.flags & BNXT_ACT_NO_AGING)
+					continue;
+				if (rps_may_expire_flow(bp->dev, fltr->base.rxq,
 							fltr->flow_id,
-							fltr->sw_id)) {
+							fltr->base.sw_id)) {
 					bnxt_hwrm_cfa_ntuple_filter_free(bp,
 									 fltr);
 					del = true;
@@ -13716,32 +14087,17 @@ static void bnxt_cfg_ntp_filters(struct bnxt *bp)
 				if (rc)
 					del = true;
 				else
-					set_bit(BNXT_FLTR_VALID, &fltr->state);
+					set_bit(BNXT_FLTR_VALID, &fltr->base.state);
 			}
 
-			if (del) {
-				spin_lock_bh(&bp->ntp_fltr_lock);
-				hlist_del_rcu(&fltr->hash);
-				bp->ntp_fltr_count--;
-				spin_unlock_bh(&bp->ntp_fltr_lock);
-				synchronize_rcu();
-				clear_bit(fltr->sw_id, bp->ntp_fltr_bmap);
-				kfree(fltr);
-			}
+			if (del)
+				bnxt_del_ntp_filter(bp, fltr);
 		}
 	}
 	if (test_and_clear_bit(BNXT_HWRM_PF_UNLOAD_SP_EVENT, &bp->sp_event))
 		netdev_info(bp->dev, "Receive PF driver unload event!\n");
 }
 
-#else
-
-static void bnxt_cfg_ntp_filters(struct bnxt *bp)
-{
-}
-
-#endif /* CONFIG_RFS_ACCEL */
-
 static int bnxt_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
 				    unsigned int entry, struct udp_tunnel_info *ti)
 {
@@ -13900,6 +14256,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 
 	bnxt_ptp_clear(bp);
 	unregister_netdev(dev);
+	bnxt_free_l2_filters(bp, true);
+	bnxt_free_ntp_fltrs(bp, true);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	/* Flush any pending tasks */
 	cancel_work_sync(&bp->sp_task);
@@ -14449,6 +14807,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	bnxt_init_l2_fltr_tbl(bp);
 	bnxt_set_rx_skb_mode(bp, false);
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);

drivers/net/ethernet/broadcom/bnxt/bnxt.h

@@ -1219,7 +1219,7 @@ struct bnxt_vnic_info {
 	u16		fw_rss_cos_lb_ctx[BNXT_MAX_CTX_PER_VNIC];
 	u16		fw_l2_ctx_id;
 #define BNXT_MAX_UC_ADDRS	4
-	__le64		fw_l2_filter_id[BNXT_MAX_UC_ADDRS];
+	struct bnxt_l2_filter *l2_filters[BNXT_MAX_UC_ADDRS];
 				/* index 0 always dev_addr */
 	u16		uc_filter_count;
 	u8		*uc_list;
@@ -1332,19 +1332,71 @@ struct bnxt_pf_info {
 	struct bnxt_vf_info	*vf;
 };
 
-struct bnxt_ntuple_filter {
+struct bnxt_filter_base {
 	struct hlist_node	hash;
-	u8			dst_mac_addr[ETH_ALEN];
-	u8			src_mac_addr[ETH_ALEN];
-	struct flow_keys	fkeys;
 	__le64			filter_id;
+	u8			type;
+#define BNXT_FLTR_TYPE_NTUPLE	1
+#define BNXT_FLTR_TYPE_L2	2
+	u8			flags;
+#define BNXT_ACT_DROP		1
+#define BNXT_ACT_RING_DST	2
+#define BNXT_ACT_FUNC_DST	4
+#define BNXT_ACT_NO_AGING	8
 	u16			sw_id;
-	u8			l2_fltr_idx;
 	u16			rxq;
-	u32			flow_id;
+	u16			fw_vnic_id;
+	u16			vf_idx;
 	unsigned long		state;
 #define BNXT_FLTR_VALID		0
-#define BNXT_FLTR_UPDATE	1
+#define BNXT_FLTR_INSERTED	1
+#define BNXT_FLTR_FW_DELETED	2
+
+	struct rcu_head         rcu;
+};
+
+struct bnxt_ntuple_filter {
+	struct bnxt_filter_base	base;
+	struct flow_keys	fkeys;
+	struct bnxt_l2_filter	*l2_fltr;
+	u32			ntuple_flags;
+#define BNXT_NTUPLE_MATCH_SRC_IP	1
+#define BNXT_NTUPLE_MATCH_DST_IP	2
+#define BNXT_NTUPLE_MATCH_SRC_PORT	4
+#define BNXT_NTUPLE_MATCH_DST_PORT	8
+#define BNXT_NTUPLE_MATCH_ALL		(BNXT_NTUPLE_MATCH_SRC_IP |	\
+					 BNXT_NTUPLE_MATCH_DST_IP |	\
+					 BNXT_NTUPLE_MATCH_SRC_PORT |	\
+					 BNXT_NTUPLE_MATCH_DST_PORT)
+	u32			flow_id;
+};
+
+struct bnxt_l2_key {
+	union {
+		struct {
+			u8	dst_mac_addr[ETH_ALEN];
+			u16	vlan;
+		};
+		u32	filter_key;
+	};
+};
+
+struct bnxt_ipv4_tuple {
+	struct flow_dissector_key_ipv4_addrs v4addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+struct bnxt_ipv6_tuple {
+	struct flow_dissector_key_ipv6_addrs v6addrs;
+	struct flow_dissector_key_ports ports;
+};
+
+#define BNXT_L2_KEY_SIZE	(sizeof(struct bnxt_l2_key) / 4)
+
+struct bnxt_l2_filter {
+	struct bnxt_filter_base	base;
+	struct bnxt_l2_key	l2_key;
+	atomic_t		refcnt;
 };
 
 struct bnxt_link_info {
@@ -2367,6 +2419,7 @@ struct bnxt {
 	int			db_size;
 
 #define BNXT_NTP_FLTR_MAX_FLTR	4096
+#define BNXT_MAX_FLTR		(BNXT_NTP_FLTR_MAX_FLTR + BNXT_L2_FLTR_MAX_FLTR)
 #define BNXT_NTP_FLTR_HASH_SIZE	512
 #define BNXT_NTP_FLTR_HASH_MASK	(BNXT_NTP_FLTR_HASH_SIZE - 1)
 	struct hlist_head	ntp_fltr_hash_tbl[BNXT_NTP_FLTR_HASH_SIZE];
@@ -2375,6 +2428,14 @@ struct bnxt {
 	unsigned long		*ntp_fltr_bmap;
 	int			ntp_fltr_count;
 
+#define BNXT_L2_FLTR_MAX_FLTR	1024
+#define BNXT_L2_FLTR_HASH_SIZE	32
+#define BNXT_L2_FLTR_HASH_MASK	(BNXT_L2_FLTR_HASH_SIZE - 1)
+	struct hlist_head	l2_fltr_hash_tbl[BNXT_L2_FLTR_HASH_SIZE];
+
+	u32			hash_seed;
+	u64			toeplitz_prefix;
+
 	/* To protect link related settings during link changes and
 	 * ethtool settings changes.
 	 */
@@ -2582,6 +2643,14 @@ int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
 			    int bmap_size, bool async_only);
 int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp);
+void bnxt_del_l2_filter(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_free(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_l2_filter_alloc(struct bnxt *bp, struct bnxt_l2_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
+				     struct bnxt_ntuple_filter *fltr);
+int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
+				      struct bnxt_ntuple_filter *fltr);
+void bnxt_fill_ipv6_mask(__be32 mask[4]);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
@@ -2625,6 +2694,13 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 int bnxt_fw_init_one(struct bnxt *bp);
 bool bnxt_hwrm_reset_permitted(struct bnxt *bp);
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
+struct bnxt_ntuple_filter *bnxt_lookup_ntp_filter_from_idx(struct bnxt *bp,
+				struct bnxt_ntuple_filter *fltr, u32 idx);
+u32 bnxt_get_ntp_filter_idx(struct bnxt *bp, struct flow_keys *fkeys,
+			    const struct sk_buff *skb);
+int bnxt_insert_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr,
+			   u32 idx);
+void bnxt_del_ntp_filter(struct bnxt *bp, struct bnxt_ntuple_filter *fltr);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 int bnxt_restore_pf_fw_resources(struct bnxt *bp);
 int bnxt_get_port_parent_id(struct net_device *dev,

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c

@@ -1011,29 +1011,60 @@ static int bnxt_set_channels(struct net_device *dev,
 	return rc;
 }
 
-#ifdef CONFIG_RFS_ACCEL
-static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
-			    u32 *rule_locs)
+static u32 bnxt_get_all_fltr_ids_rcu(struct bnxt *bp, struct hlist_head tbl[],
+				     int tbl_size, u32 *ids, u32 start,
+				     u32 id_cnt)
 {
-	int i, j = 0;
+	int i, j = start;
 
-	cmd->data = bp->ntp_fltr_count;
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
+	if (j >= id_cnt)
+		return j;
+	for (i = 0; i < tbl_size; i++) {
 		struct hlist_head *head;
-		struct bnxt_ntuple_filter *fltr;
+		struct bnxt_filter_base *fltr;
 
-		head = &bp->ntp_fltr_hash_tbl[i];
-		rcu_read_lock();
+		head = &tbl[i];
 		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (j == cmd->rule_cnt)
-				break;
-			rule_locs[j++] = fltr->sw_id;
+			if (!fltr->flags ||
+			    test_bit(BNXT_FLTR_FW_DELETED, &fltr->state))
+				continue;
+			ids[j++] = fltr->sw_id;
+			if (j == id_cnt)
+				return j;
 		}
-		rcu_read_unlock();
-		if (j == cmd->rule_cnt)
-			break;
 	}
-	cmd->rule_cnt = j;
+	return j;
+}
+
+static struct bnxt_filter_base *bnxt_get_one_fltr_rcu(struct bnxt *bp,
+						      struct hlist_head tbl[],
+						      int tbl_size, u32 id)
+{
+	int i;
+
+	for (i = 0; i < tbl_size; i++) {
+		struct hlist_head *head;
+		struct bnxt_filter_base *fltr;
+
+		head = &tbl[i];
+		hlist_for_each_entry_rcu(fltr, head, hash) {
+			if (fltr->flags && fltr->sw_id == id)
+				return fltr;
+		}
+	}
+	return NULL;
+}
+
+static int bnxt_grxclsrlall(struct bnxt *bp, struct ethtool_rxnfc *cmd,
+			    u32 *rule_locs)
+{
+	cmd->data = bp->ntp_fltr_count;
+	rcu_read_lock();
+	cmd->rule_cnt = bnxt_get_all_fltr_ids_rcu(bp, bp->ntp_fltr_hash_tbl,
+						  BNXT_NTP_FLTR_HASH_SIZE,
+						  rule_locs, 0, cmd->rule_cnt);
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -1041,27 +1072,24 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 {
 	struct ethtool_rx_flow_spec *fs =
 		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct bnxt_filter_base *fltr_base;
 	struct bnxt_ntuple_filter *fltr;
 	struct flow_keys *fkeys;
-	int i, rc = -EINVAL;
+	int rc = -EINVAL;
 
 	if (fs->location >= BNXT_NTP_FLTR_MAX_FLTR)
 		return rc;
 
-	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
-		struct hlist_head *head;
-
-		head = &bp->ntp_fltr_hash_tbl[i];
 	rcu_read_lock();
-		hlist_for_each_entry_rcu(fltr, head, hash) {
-			if (fltr->sw_id == fs->location)
-				goto fltr_found;
-		}
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (!fltr_base) {
 		rcu_read_unlock();
-	}
 		return rc;
+	}
+	fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
 
-fltr_found:
 	fkeys = &fltr->fkeys;
 	if (fkeys->basic.n_proto == htons(ETH_P_IP)) {
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
@@ -1071,20 +1099,23 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		else
 			goto fltr_err;
 
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
 			fs->h_u.tcp_ip4_spec.ip4src = fkeys->addrs.v4addrs.src;
 			fs->m_u.tcp_ip4_spec.ip4src = cpu_to_be32(~0);
-
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
 			fs->h_u.tcp_ip4_spec.ip4dst = fkeys->addrs.v4addrs.dst;
 			fs->m_u.tcp_ip4_spec.ip4dst = cpu_to_be32(~0);
-
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
 			fs->h_u.tcp_ip4_spec.psrc = fkeys->ports.src;
 			fs->m_u.tcp_ip4_spec.psrc = cpu_to_be16(~0);
-
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
 			fs->h_u.tcp_ip4_spec.pdst = fkeys->ports.dst;
 			fs->m_u.tcp_ip4_spec.pdst = cpu_to_be16(~0);
+		}
 	} else {
-		int i;
-
 		if (fkeys->basic.ip_proto == IPPROTO_TCP)
 			fs->flow_type = TCP_V6_FLOW;
 		else if (fkeys->basic.ip_proto == IPPROTO_UDP)
@@ -1092,22 +1123,27 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 		else
 			goto fltr_err;
 
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_IP) {
 			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6src[0] =
 				fkeys->addrs.v6addrs.src;
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6src);
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_IP) {
 			*(struct in6_addr *)&fs->h_u.tcp_ip6_spec.ip6dst[0] =
 				fkeys->addrs.v6addrs.dst;
-		for (i = 0; i < 4; i++) {
-			fs->m_u.tcp_ip6_spec.ip6src[i] = cpu_to_be32(~0);
-			fs->m_u.tcp_ip6_spec.ip6dst[i] = cpu_to_be32(~0);
+			bnxt_fill_ipv6_mask(fs->m_u.tcp_ip6_spec.ip6dst);
 		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_SRC_PORT) {
 			fs->h_u.tcp_ip6_spec.psrc = fkeys->ports.src;
 			fs->m_u.tcp_ip6_spec.psrc = cpu_to_be16(~0);
-
+		}
+		if (fltr->ntuple_flags & BNXT_NTUPLE_MATCH_DST_PORT) {
 			fs->h_u.tcp_ip6_spec.pdst = fkeys->ports.dst;
 			fs->m_u.tcp_ip6_spec.pdst = cpu_to_be16(~0);
 		}
+	}
 
-	fs->ring_cookie = fltr->rxq;
+	fs->ring_cookie = fltr->base.rxq;
 	rc = 0;
 
 fltr_err:
@@ -1115,7 +1151,220 @@ static int bnxt_grxclsrule(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 
 	return rc;
 }
-#endif
+
+#define IPV4_ALL_MASK		((__force __be32)~0)
+#define L4_PORT_ALL_MASK	((__force __be16)~0)
+
+static bool ipv6_mask_is_full(__be32 mask[4])
+{
+	return (mask[0] & mask[1] & mask[2] & mask[3]) == IPV4_ALL_MASK;
+}
+
+static bool ipv6_mask_is_zero(__be32 mask[4])
+{
+	return !(mask[0] | mask[1] | mask[2] | mask[3]);
+}
+
+static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
+				    struct ethtool_rx_flow_spec *fs)
+{
+	u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	struct bnxt_ntuple_filter *new_fltr, *fltr;
+	struct bnxt_l2_filter *l2_fltr;
+	u32 flow_type = fs->flow_type;
+	struct flow_keys *fkeys;
+	u32 idx;
+	int rc;
+
+	if (!bp->vnic_info)
+		return -EAGAIN;
+
+	if ((flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
+		return -EOPNOTSUPP;
+
+	new_fltr = kzalloc(sizeof(*new_fltr), GFP_KERNEL);
+	if (!new_fltr)
+		return -ENOMEM;
+
+	l2_fltr = bp->vnic_info[0].l2_filters[0];
+	atomic_inc(&l2_fltr->refcnt);
+	new_fltr->l2_fltr = l2_fltr;
+	fkeys = &new_fltr->fkeys;
+
+	rc = -EOPNOTSUPP;
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW: {
+		struct ethtool_tcpip4_spec *ip_spec = &fs->h_u.tcp_ip4_spec;
+		struct ethtool_tcpip4_spec *ip_mask = &fs->m_u.tcp_ip4_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V4_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IP);
+
+		if (ip_mask->ip4src == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.src = ip_spec->ip4src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (ip_mask->ip4src) {
+			goto ntuple_err;
+		}
+		if (ip_mask->ip4dst == IPV4_ALL_MASK) {
+			fkeys->addrs.v4addrs.dst = ip_spec->ip4dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (ip_mask->ip4dst) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW: {
+		struct ethtool_tcpip6_spec *ip_spec = &fs->h_u.tcp_ip6_spec;
+		struct ethtool_tcpip6_spec *ip_mask = &fs->m_u.tcp_ip6_spec;
+
+		fkeys->basic.ip_proto = IPPROTO_TCP;
+		if (flow_type == UDP_V6_FLOW)
+			fkeys->basic.ip_proto = IPPROTO_UDP;
+		fkeys->basic.n_proto = htons(ETH_P_IPV6);
+
+		if (ipv6_mask_is_full(ip_mask->ip6src)) {
+			fkeys->addrs.v6addrs.src =
+				*(struct in6_addr *)&ip_spec->ip6src;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6src)) {
+			goto ntuple_err;
+		}
+		if (ipv6_mask_is_full(ip_mask->ip6dst)) {
+			fkeys->addrs.v6addrs.dst =
+				*(struct in6_addr *)&ip_spec->ip6dst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_IP;
+		} else if (!ipv6_mask_is_zero(ip_mask->ip6dst)) {
+			goto ntuple_err;
+		}
+
+		if (ip_mask->psrc == L4_PORT_ALL_MASK) {
+			fkeys->ports.src = ip_spec->psrc;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_SRC_PORT;
+		} else if (ip_mask->psrc) {
+			goto ntuple_err;
+		}
+		if (ip_mask->pdst == L4_PORT_ALL_MASK) {
+			fkeys->ports.dst = ip_spec->pdst;
+			new_fltr->ntuple_flags |= BNXT_NTUPLE_MATCH_DST_PORT;
+		} else if (ip_mask->pdst) {
+			goto ntuple_err;
+		}
+		break;
+	}
+	default:
+		rc = -EOPNOTSUPP;
+		goto ntuple_err;
+	}
+	if (!new_fltr->ntuple_flags)
+		goto ntuple_err;
+
+	idx = bnxt_get_ntp_filter_idx(bp, fkeys, NULL);
+	rcu_read_lock();
+	fltr = bnxt_lookup_ntp_filter_from_idx(bp, new_fltr, idx);
+	if (fltr) {
+		rcu_read_unlock();
+		rc = -EEXIST;
+		goto ntuple_err;
+	}
+	rcu_read_unlock();
+
+	new_fltr->base.rxq = ring;
+	new_fltr->base.flags = BNXT_ACT_NO_AGING;
+	__set_bit(BNXT_FLTR_VALID, &new_fltr->base.state);
+	rc = bnxt_insert_ntp_filter(bp, new_fltr, idx);
+	if (!rc) {
+		rc = bnxt_hwrm_cfa_ntuple_filter_alloc(bp, new_fltr);
+		if (rc) {
+			bnxt_del_ntp_filter(bp, new_fltr);
+			return rc;
+		}
+		fs->location = new_fltr->base.sw_id;
+		return 0;
+	}
+
+ntuple_err:
+	atomic_dec(&l2_fltr->refcnt);
+	kfree(new_fltr);
+	return rc;
+}
+
+static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	u32 ring, flow_type;
+	int rc;
+	u8 vf;
+
+	if (!netif_running(bp->dev))
+		return -EAGAIN;
+	if (!(bp->flags & BNXT_FLAG_RFS))
+		return -EPERM;
+	if (fs->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+
+	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	if (BNXT_VF(bp) && vf)
+		return -EINVAL;
+	if (BNXT_PF(bp) && vf > bp->pf.active_vfs)
+		return -EINVAL;
+	if (!vf && ring >= bp->rx_nr_rings)
+		return -EINVAL;
+
+	flow_type = fs->flow_type;
+	if (flow_type & (FLOW_MAC_EXT | FLOW_RSS))
+		return -EINVAL;
+	flow_type &= ~FLOW_EXT;
+	if (flow_type == ETHER_FLOW)
+		rc = -EOPNOTSUPP;
+	else
+		rc = bnxt_add_ntuple_cls_rule(bp, fs);
+	return rc;
+}
+
+static int bnxt_srxclsrldel(struct bnxt *bp, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
+	struct bnxt_filter_base *fltr_base;
+
+	rcu_read_lock();
+	fltr_base = bnxt_get_one_fltr_rcu(bp, bp->ntp_fltr_hash_tbl,
+					  BNXT_NTP_FLTR_HASH_SIZE,
+					  fs->location);
+	if (fltr_base) {
+		struct bnxt_ntuple_filter *fltr;
+
+		fltr = container_of(fltr_base, struct bnxt_ntuple_filter, base);
+		rcu_read_unlock();
+		if (!(fltr->base.flags & BNXT_ACT_NO_AGING))
+			return -EINVAL;
+		bnxt_hwrm_cfa_ntuple_filter_free(bp, fltr);
+		bnxt_del_ntp_filter(bp, fltr);
+		return 0;
+	}
+
+	rcu_read_unlock();
+	return -ENOENT;
+}
 
 static u64 get_ethtool_ipv4_rss(struct bnxt *bp)
 {
@@ -1265,14 +1514,13 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	int rc = 0;
 
 	switch (cmd->cmd) {
-#ifdef CONFIG_RFS_ACCEL
 	case ETHTOOL_GRXRINGS:
 		cmd->data = bp->rx_nr_rings;
 		break;
 
 	case ETHTOOL_GRXCLSRLCNT:
 		cmd->rule_cnt = bp->ntp_fltr_count;
-		cmd->data = BNXT_NTP_FLTR_MAX_FLTR;
+		cmd->data = BNXT_NTP_FLTR_MAX_FLTR | RX_CLS_LOC_SPECIAL;
 		break;
 
 	case ETHTOOL_GRXCLSRLALL:
@@ -1282,7 +1530,6 @@ static int bnxt_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	case ETHTOOL_GRXCLSRULE:
 		rc = bnxt_grxclsrule(bp, cmd);
 		break;
-#endif
 
 	case ETHTOOL_GRXFH:
 		rc = bnxt_grxfh(bp, cmd);
@@ -1306,6 +1553,14 @@ static int bnxt_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 		rc = bnxt_srxfh(bp, cmd);
 		break;
 
+	case ETHTOOL_SRXCLSRLINS:
+		rc = bnxt_srxclsrlins(bp, cmd);
+		break;
+
+	case ETHTOOL_SRXCLSRLDEL:
+		rc = bnxt_srxclsrldel(bp, cmd);
+		break;
+
 	default:
 		rc = -EOPNOTSUPP;
 		break;