cxgb4: Add T4 filter support

The T4 architecture is capable of filtering ingress packets at line rate
using the rule in TCAM. If packet hits a rule in the TCAM then it can be either
dropped or passed to the receive queues based on a rule settings.

This patch adds framework for managing filters and to use T4's filter
capabilities. It constructs a Firmware Filter Work Request which writes the
filter at a specified index to get the work done. It hosts shadow copy of
ingress filter entry to check field size limitations and save memory in the
case where the filter table is large.

Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -545,6 +545,129 @@ struct adapter {
 	spinlock_t stats_lock;
 };
 
+/* Defined bit width of user definable filter tuples
+ */
+#define ETHTYPE_BITWIDTH 16
+#define FRAG_BITWIDTH 1
+#define MACIDX_BITWIDTH 9
+#define FCOE_BITWIDTH 1
+#define IPORT_BITWIDTH 3
+#define MATCHTYPE_BITWIDTH 3
+#define PROTO_BITWIDTH 8
+#define TOS_BITWIDTH 8
+#define PF_BITWIDTH 8
+#define VF_BITWIDTH 8
+#define IVLAN_BITWIDTH 16
+#define OVLAN_BITWIDTH 16
+
+/* Filter matching rules.  These consist of a set of ingress packet field
+ * (value, mask) tuples.  The associated ingress packet field matches the
+ * tuple when ((field & mask) == value).  (Thus a wildcard "don't care" field
+ * rule can be constructed by specifying a tuple of (0, 0).)  A filter rule
+ * matches an ingress packet when all of the individual individual field
+ * matching rules are true.
+ *
+ * Partial field masks are always valid, however, while it may be easy to
+ * understand their meanings for some fields (e.g. IP address to match a
+ * subnet), for others making sensible partial masks is less intuitive (e.g.
+ * MPS match type) ...
+ *
+ * Most of the following data structures are modeled on T4 capabilities.
+ * Drivers for earlier chips use the subsets which make sense for those chips.
+ * We really need to come up with a hardware-independent mechanism to
+ * represent hardware filter capabilities ...
+ */
+struct ch_filter_tuple {
+	/* Compressed header matching field rules.  The TP_VLAN_PRI_MAP
+	 * register selects which of these fields will participate in the
+	 * filter match rules -- up to a maximum of 36 bits.  Because
+	 * TP_VLAN_PRI_MAP is a global register, all filters must use the same
+	 * set of fields.
+	 */
+	uint32_t ethtype:ETHTYPE_BITWIDTH;      /* Ethernet type */
+	uint32_t frag:FRAG_BITWIDTH;            /* IP fragmentation header */
+	uint32_t ivlan_vld:1;                   /* inner VLAN valid */
+	uint32_t ovlan_vld:1;                   /* outer VLAN valid */
+	uint32_t pfvf_vld:1;                    /* PF/VF valid */
+	uint32_t macidx:MACIDX_BITWIDTH;        /* exact match MAC index */
+	uint32_t fcoe:FCOE_BITWIDTH;            /* FCoE packet */
+	uint32_t iport:IPORT_BITWIDTH;          /* ingress port */
+	uint32_t matchtype:MATCHTYPE_BITWIDTH;  /* MPS match type */
+	uint32_t proto:PROTO_BITWIDTH;          /* protocol type */
+	uint32_t tos:TOS_BITWIDTH;              /* TOS/Traffic Type */
+	uint32_t pf:PF_BITWIDTH;                /* PCI-E PF ID */
+	uint32_t vf:VF_BITWIDTH;                /* PCI-E VF ID */
+	uint32_t ivlan:IVLAN_BITWIDTH;          /* inner VLAN */
+	uint32_t ovlan:OVLAN_BITWIDTH;          /* outer VLAN */
+
+	/* Uncompressed header matching field rules.  These are always
+	 * available for field rules.
+	 */
+	uint8_t lip[16];        /* local IP address (IPv4 in [3:0]) */
+	uint8_t fip[16];        /* foreign IP address (IPv4 in [3:0]) */
+	uint16_t lport;         /* local port */
+	uint16_t fport;         /* foreign port */
+};
+
+/* A filter ioctl command.
+ */
+struct ch_filter_specification {
+	/* Administrative fields for filter.
+	 */
+	uint32_t hitcnts:1;     /* count filter hits in TCB */
+	uint32_t prio:1;        /* filter has priority over active/server */
+
+	/* Fundamental filter typing.  This is the one element of filter
+	 * matching that doesn't exist as a (value, mask) tuple.
+	 */
+	uint32_t type:1;        /* 0 => IPv4, 1 => IPv6 */
+
+	/* Packet dispatch information.  Ingress packets which match the
+	 * filter rules will be dropped, passed to the host or switched back
+	 * out as egress packets.
+	 */
+	uint32_t action:2;      /* drop, pass, switch */
+
+	uint32_t rpttid:1;      /* report TID in RSS hash field */
+
+	uint32_t dirsteer:1;    /* 0 => RSS, 1 => steer to iq */
+	uint32_t iq:10;         /* ingress queue */
+
+	uint32_t maskhash:1;    /* dirsteer=0: store RSS hash in TCB */
+	uint32_t dirsteerhash:1;/* dirsteer=1: 0 => TCB contains RSS hash */
+				/*             1 => TCB contains IQ ID */
+
+	/* Switch proxy/rewrite fields.  An ingress packet which matches a
+	 * filter with "switch" set will be looped back out as an egress
+	 * packet -- potentially with some Ethernet header rewriting.
+	 */
+	uint32_t eport:2;       /* egress port to switch packet out */
+	uint32_t newdmac:1;     /* rewrite destination MAC address */
+	uint32_t newsmac:1;     /* rewrite source MAC address */
+	uint32_t newvlan:2;     /* rewrite VLAN Tag */
+	uint8_t dmac[ETH_ALEN]; /* new destination MAC address */
+	uint8_t smac[ETH_ALEN]; /* new source MAC address */
+	uint16_t vlan;          /* VLAN Tag to insert */
+
+	/* Filter rule value/mask pairs.
+	 */
+	struct ch_filter_tuple val;
+	struct ch_filter_tuple mask;
+};
+
+enum {
+	FILTER_PASS = 0,        /* default */
+	FILTER_DROP,
+	FILTER_SWITCH
+};
+
+enum {
+	VLAN_NOCHANGE = 0,      /* default */
+	VLAN_REMOVE,
+	VLAN_INSERT,
+	VLAN_REWRITE
+};
+
 static inline u32 t4_read_reg(struct adapter *adap, u32 reg_addr)
 {
 	return readl(adap->regs + reg_addr);
@@ -701,6 +824,12 @@ static inline int t4_wr_mbox_ns(struct adapter *adap, int mbox, const void *cmd,
 void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
 		       unsigned int data_reg, const u32 *vals,
 		       unsigned int nregs, unsigned int start_idx);
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+		      unsigned int data_reg, u32 *vals, unsigned int nregs,
+		      unsigned int start_idx);
+
+struct fw_filter_wr;
+
 void t4_intr_enable(struct adapter *adapter);
 void t4_intr_disable(struct adapter *adapter);
 int t4_slow_intr_handler(struct adapter *adapter);
@@ -737,6 +866,8 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
 void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
 		  const unsigned short *alpha, const unsigned short *beta);
 
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid);
+
 void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
 			 const u8 *addr);
 int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -175,6 +175,30 @@ enum {
 	MIN_FL_ENTRIES       = 16
 };
 
+/* Host shadow copy of ingress filter entry.  This is in host native format
+ * and doesn't match the ordering or bit order, etc. of the hardware of the
+ * firmware command.  The use of bit-field structure elements is purely to
+ * remind ourselves of the field size limitations and save memory in the case
+ * where the filter table is large.
+ */
+struct filter_entry {
+	/* Administrative fields for filter.
+	 */
+	u32 valid:1;            /* filter allocated and valid */
+	u32 locked:1;           /* filter is administratively locked */
+
+	u32 pending:1;          /* filter action is pending firmware reply */
+	u32 smtidx:8;           /* Source MAC Table index for smac */
+	struct l2t_entry *l2t;  /* Layer Two Table entry for dmac */
+
+	/* The filter itself.  Most of this is a straight copy of information
+	 * provided by the extended ioctl().  Some fields are translated to
+	 * internal forms -- for instance the Ingress Queue ID passed in from
+	 * the ioctl() is translated into the Absolute Ingress Queue ID.
+	 */
+	struct ch_filter_specification fs;
+};
+
 #define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
 			 NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
 			 NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
@@ -325,6 +349,9 @@ enum {
 
 static unsigned int tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT;
 
+module_param(tp_vlan_pri_map, uint, 0644);
+MODULE_PARM_DESC(tp_vlan_pri_map, "global compressed filter configuration");
+
 static struct dentry *cxgb4_debugfs_root;
 
 static LIST_HEAD(adapter_list);
@@ -506,8 +533,67 @@ static int link_start(struct net_device *dev)
 	return ret;
 }
 
-/*
- * Response queue handler for the FW event queue.
+/* Clear a filter and release any of its resources that we own.  This also
+ * clears the filter's "pending" status.
+ */
+static void clear_filter(struct adapter *adap, struct filter_entry *f)
+{
+	/* If the new or old filter have loopback rewriteing rules then we'll
+	 * need to free any existing Layer Two Table (L2T) entries of the old
+	 * filter rule.  The firmware will handle freeing up any Source MAC
+	 * Table (SMT) entries used for rewriting Source MAC Addresses in
+	 * loopback rules.
+	 */
+	if (f->l2t)
+		cxgb4_l2t_release(f->l2t);
+
+	/* The zeroing of the filter rule below clears the filter valid,
+	 * pending, locked flags, l2t pointer, etc. so it's all we need for
+	 * this operation.
+	 */
+	memset(f, 0, sizeof(*f));
+}
+
+/* Handle a filter write/deletion reply.
+ */
+static void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
+{
+	unsigned int idx = GET_TID(rpl);
+	unsigned int nidx = idx - adap->tids.ftid_base;
+	unsigned int ret;
+	struct filter_entry *f;
+
+	if (idx >= adap->tids.ftid_base && nidx <
+	   (adap->tids.nftids + adap->tids.nsftids)) {
+		idx = nidx;
+		ret = GET_TCB_COOKIE(rpl->cookie);
+		f = &adap->tids.ftid_tab[idx];
+
+		if (ret == FW_FILTER_WR_FLT_DELETED) {
+			/* Clear the filter when we get confirmation from the
+			 * hardware that the filter has been deleted.
+			 */
+			clear_filter(adap, f);
+		} else if (ret == FW_FILTER_WR_SMT_TBL_FULL) {
+			dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n",
+				idx);
+			clear_filter(adap, f);
+		} else if (ret == FW_FILTER_WR_FLT_ADDED) {
+			f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff;
+			f->pending = 0;  /* asynchronous setup completed */
+			f->valid = 1;
+		} else {
+			/* Something went wrong.  Issue a warning about the
+			 * problem and clear everything out.
+			 */
+			dev_err(adap->pdev_dev, "filter %u setup failed with error %u\n",
+				idx, ret);
+			clear_filter(adap, f);
+		}
+	}
+}
+
+/* Response queue handler for the FW event queue.
  */
 static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 			  const struct pkt_gl *gl)
@@ -542,6 +628,10 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 		const struct cpl_l2t_write_rpl *p = (void *)rsp;
 
 		do_l2t_write_rpl(q->adap, p);
+	} else if (opcode == CPL_SET_TCB_RPL) {
+		const struct cpl_set_tcb_rpl *p = (void *)rsp;
+
+		filter_rpl(q->adap, p);
 	} else
 		dev_err(q->adap->pdev_dev,
 			"unexpected CPL %#x on FW event queue\n", opcode);
@@ -983,6 +1073,148 @@ static void t4_free_mem(void *addr)
 		kfree(addr);
 }
 
+/* Send a Work Request to write the filter at a specified index.  We construct
+ * a Firmware Filter Work Request to have the work done and put the indicated
+ * filter into "pending" mode which will prevent any further actions against
+ * it till we get a reply from the firmware on the completion status of the
+ * request.
+ */
+static int set_filter_wr(struct adapter *adapter, int fidx)
+{
+	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+	struct sk_buff *skb;
+	struct fw_filter_wr *fwr;
+	unsigned int ftid;
+
+	/* If the new filter requires loopback Destination MAC and/or VLAN
+	 * rewriting then we need to allocate a Layer 2 Table (L2T) entry for
+	 * the filter.
+	 */
+	if (f->fs.newdmac || f->fs.newvlan) {
+		/* allocate L2T entry for new filter */
+		f->l2t = t4_l2t_alloc_switching(adapter->l2t);
+		if (f->l2t == NULL)
+			return -EAGAIN;
+		if (t4_l2t_set_switching(adapter, f->l2t, f->fs.vlan,
+					f->fs.eport, f->fs.dmac)) {
+			cxgb4_l2t_release(f->l2t);
+			f->l2t = NULL;
+			return -ENOMEM;
+		}
+	}
+
+	ftid = adapter->tids.ftid_base + fidx;
+
+	skb = alloc_skb(sizeof(*fwr), GFP_KERNEL | __GFP_NOFAIL);
+	fwr = (struct fw_filter_wr *)__skb_put(skb, sizeof(*fwr));
+	memset(fwr, 0, sizeof(*fwr));
+
+	/* It would be nice to put most of the following in t4_hw.c but most
+	 * of the work is translating the cxgbtool ch_filter_specification
+	 * into the Work Request and the definition of that structure is
+	 * currently in cxgbtool.h which isn't appropriate to pull into the
+	 * common code.  We may eventually try to come up with a more neutral
+	 * filter specification structure but for now it's easiest to simply
+	 * put this fairly direct code in line ...
+	 */
+	fwr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+	fwr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*fwr)/16));
+	fwr->tid_to_iq =
+		htonl(V_FW_FILTER_WR_TID(ftid) |
+		      V_FW_FILTER_WR_RQTYPE(f->fs.type) |
+		      V_FW_FILTER_WR_NOREPLY(0) |
+		      V_FW_FILTER_WR_IQ(f->fs.iq));
+	fwr->del_filter_to_l2tix =
+		htonl(V_FW_FILTER_WR_RPTTID(f->fs.rpttid) |
+		      V_FW_FILTER_WR_DROP(f->fs.action == FILTER_DROP) |
+		      V_FW_FILTER_WR_DIRSTEER(f->fs.dirsteer) |
+		      V_FW_FILTER_WR_MASKHASH(f->fs.maskhash) |
+		      V_FW_FILTER_WR_DIRSTEERHASH(f->fs.dirsteerhash) |
+		      V_FW_FILTER_WR_LPBK(f->fs.action == FILTER_SWITCH) |
+		      V_FW_FILTER_WR_DMAC(f->fs.newdmac) |
+		      V_FW_FILTER_WR_SMAC(f->fs.newsmac) |
+		      V_FW_FILTER_WR_INSVLAN(f->fs.newvlan == VLAN_INSERT ||
+					     f->fs.newvlan == VLAN_REWRITE) |
+		      V_FW_FILTER_WR_RMVLAN(f->fs.newvlan == VLAN_REMOVE ||
+					    f->fs.newvlan == VLAN_REWRITE) |
+		      V_FW_FILTER_WR_HITCNTS(f->fs.hitcnts) |
+		      V_FW_FILTER_WR_TXCHAN(f->fs.eport) |
+		      V_FW_FILTER_WR_PRIO(f->fs.prio) |
+		      V_FW_FILTER_WR_L2TIX(f->l2t ? f->l2t->idx : 0));
+	fwr->ethtype = htons(f->fs.val.ethtype);
+	fwr->ethtypem = htons(f->fs.mask.ethtype);
+	fwr->frag_to_ovlan_vldm =
+		(V_FW_FILTER_WR_FRAG(f->fs.val.frag) |
+		 V_FW_FILTER_WR_FRAGM(f->fs.mask.frag) |
+		 V_FW_FILTER_WR_IVLAN_VLD(f->fs.val.ivlan_vld) |
+		 V_FW_FILTER_WR_OVLAN_VLD(f->fs.val.ovlan_vld) |
+		 V_FW_FILTER_WR_IVLAN_VLDM(f->fs.mask.ivlan_vld) |
+		 V_FW_FILTER_WR_OVLAN_VLDM(f->fs.mask.ovlan_vld));
+	fwr->smac_sel = 0;
+	fwr->rx_chan_rx_rpl_iq =
+		htons(V_FW_FILTER_WR_RX_CHAN(0) |
+		      V_FW_FILTER_WR_RX_RPL_IQ(adapter->sge.fw_evtq.abs_id));
+	fwr->maci_to_matchtypem =
+		htonl(V_FW_FILTER_WR_MACI(f->fs.val.macidx) |
+		      V_FW_FILTER_WR_MACIM(f->fs.mask.macidx) |
+		      V_FW_FILTER_WR_FCOE(f->fs.val.fcoe) |
+		      V_FW_FILTER_WR_FCOEM(f->fs.mask.fcoe) |
+		      V_FW_FILTER_WR_PORT(f->fs.val.iport) |
+		      V_FW_FILTER_WR_PORTM(f->fs.mask.iport) |
+		      V_FW_FILTER_WR_MATCHTYPE(f->fs.val.matchtype) |
+		      V_FW_FILTER_WR_MATCHTYPEM(f->fs.mask.matchtype));
+	fwr->ptcl = f->fs.val.proto;
+	fwr->ptclm = f->fs.mask.proto;
+	fwr->ttyp = f->fs.val.tos;
+	fwr->ttypm = f->fs.mask.tos;
+	fwr->ivlan = htons(f->fs.val.ivlan);
+	fwr->ivlanm = htons(f->fs.mask.ivlan);
+	fwr->ovlan = htons(f->fs.val.ovlan);
+	fwr->ovlanm = htons(f->fs.mask.ovlan);
+	memcpy(fwr->lip, f->fs.val.lip, sizeof(fwr->lip));
+	memcpy(fwr->lipm, f->fs.mask.lip, sizeof(fwr->lipm));
+	memcpy(fwr->fip, f->fs.val.fip, sizeof(fwr->fip));
+	memcpy(fwr->fipm, f->fs.mask.fip, sizeof(fwr->fipm));
+	fwr->lp = htons(f->fs.val.lport);
+	fwr->lpm = htons(f->fs.mask.lport);
+	fwr->fp = htons(f->fs.val.fport);
+	fwr->fpm = htons(f->fs.mask.fport);
+	if (f->fs.newsmac)
+		memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma));
+
+	/* Mark the filter as "pending" and ship off the Filter Work Request.
+	 * When we get the Work Request Reply we'll clear the pending status.
+	 */
+	f->pending = 1;
+	set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
+	t4_ofld_send(adapter, skb);
+	return 0;
+}
+
+/* Delete the filter at a specified index.
+ */
+static int del_filter_wr(struct adapter *adapter, int fidx)
+{
+	struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+	struct sk_buff *skb;
+	struct fw_filter_wr *fwr;
+	unsigned int len, ftid;
+
+	len = sizeof(*fwr);
+	ftid = adapter->tids.ftid_base + fidx;
+
+	skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
+	fwr = (struct fw_filter_wr *)__skb_put(skb, len);
+	t4_mk_filtdelwr(ftid, fwr, adapter->sge.fw_evtq.abs_id);
+
+	/* Mark the filter as "pending" and ship off the Filter Work Request.
+	 * When we get the Work Request Reply we'll clear the pending status.
+	 */
+	f->pending = 1;
+	t4_mgmt_tx(adapter, skb);
+	return 0;
+}
+
 static inline int is_offload(const struct adapter *adap)
 {
 	return adap->params.offload;
@@ -2195,7 +2427,7 @@ int cxgb4_alloc_atid(struct tid_info *t, void *data)
 	if (t->afree) {
 		union aopen_entry *p = t->afree;
 
-		atid = p - t->atid_tab;
+		atid = (p - t->atid_tab) + t->atid_base;
 		t->afree = p->next;
 		p->data = data;
 		t->atids_in_use++;
@@ -2210,7 +2442,7 @@ EXPORT_SYMBOL(cxgb4_alloc_atid);
  */
 void cxgb4_free_atid(struct tid_info *t, unsigned int atid)
 {
-	union aopen_entry *p = &t->atid_tab[atid];
+	union aopen_entry *p = &t->atid_tab[atid - t->atid_base];
 
 	spin_lock_bh(&t->atid_lock);
 	p->next = t->afree;
@@ -2362,11 +2594,16 @@ EXPORT_SYMBOL(cxgb4_remove_tid);
 static int tid_init(struct tid_info *t)
 {
 	size_t size;
+	unsigned int stid_bmap_size;
 	unsigned int natids = t->natids;
 
-	size = t->ntids * sizeof(*t->tid_tab) + natids * sizeof(*t->atid_tab) +
+	stid_bmap_size = BITS_TO_LONGS(t->nstids);
+	size = t->ntids * sizeof(*t->tid_tab) +
+	       natids * sizeof(*t->atid_tab) +
 	       t->nstids * sizeof(*t->stid_tab) +
-	       BITS_TO_LONGS(t->nstids) * sizeof(long);
+	       stid_bmap_size * sizeof(long) +
+	       t->nftids * sizeof(*t->ftid_tab);
+
 	t->tid_tab = t4_alloc_mem(size);
 	if (!t->tid_tab)
 		return -ENOMEM;
@@ -2374,6 +2611,7 @@ static int tid_init(struct tid_info *t)
 	t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
 	t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
 	t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids];
+	t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
 	spin_lock_init(&t->stid_lock);
 	spin_lock_init(&t->atid_lock);
 
@@ -2999,6 +3237,40 @@ static int cxgb_close(struct net_device *dev)
 	return t4_enable_vi(adapter, adapter->fn, pi->viid, false, false);
 }
 
+/* Return an error number if the indicated filter isn't writable ...
+ */
+static int writable_filter(struct filter_entry *f)
+{
+	if (f->locked)
+		return -EPERM;
+	if (f->pending)
+		return -EBUSY;
+
+	return 0;
+}
+
+/* Delete the filter at the specified index (if valid).  The checks for all
+ * the common problems with doing this like the filter being locked, currently
+ * pending in another operation, etc.
+ */
+static int delete_filter(struct adapter *adapter, unsigned int fidx)
+{
+	struct filter_entry *f;
+	int ret;
+
+	if (fidx >= adapter->tids.nftids)
+		return -EINVAL;
+
+	f = &adapter->tids.ftid_tab[fidx];
+	ret = writable_filter(f);
+	if (ret)
+		return ret;
+	if (f->valid)
+		return del_filter_wr(adapter, fidx);
+
+	return 0;
+}
+
 static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
 						struct rtnl_link_stats64 *ns)
 {
@@ -4661,6 +4933,16 @@ static void remove_one(struct pci_dev *pdev)
 		if (adapter->debugfs_root)
 			debugfs_remove_recursive(adapter->debugfs_root);
 
+		/* If we allocated filters, free up state associated with any
+		 * valid filters ...
+		 */
+		if (adapter->tids.ftid_tab) {
+			struct filter_entry *f = &adapter->tids.ftid_tab[0];
+			for (i = 0; i < adapter->tids.nftids; i++, f++)
+				if (f->valid)
+					clear_filter(adapter, f);
+		}
+
 		if (adapter->flags & FULL_INIT_DONE)
 			cxgb_down(adapter);
 

drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h

@@ -97,7 +97,9 @@ struct tid_info {
 
 	union aopen_entry *atid_tab;
 	unsigned int natids;
+	unsigned int atid_base;
 
+	struct filter_entry *ftid_tab;
 	unsigned int nftids;
 	unsigned int ftid_base;
 	unsigned int aftid_base;

drivers/net/ethernet/chelsio/cxgb4/l2t.c

@@ -484,6 +484,38 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
 		handle_failed_resolution(adap, arpq);
 }
 
+/* Allocate an L2T entry for use by a switching rule.  Such need to be
+ * explicitly freed and while busy they are not on any hash chain, so normal
+ * address resolution updates do not see them.
+ */
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d)
+{
+	struct l2t_entry *e;
+
+	write_lock_bh(&d->lock);
+	e = alloc_l2e(d);
+	if (e) {
+		spin_lock(&e->lock);          /* avoid race with t4_l2t_free */
+		e->state = L2T_STATE_SWITCHING;
+		atomic_set(&e->refcnt, 1);
+		spin_unlock(&e->lock);
+	}
+	write_unlock_bh(&d->lock);
+	return e;
+}
+
+/* Sets/updates the contents of a switching L2T entry that has been allocated
+ * with an earlier call to @t4_l2t_alloc_switching.
+ */
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+		u8 port, u8 *eth_addr)
+{
+	e->vlan = vlan;
+	e->lport = port;
+	memcpy(e->dmac, eth_addr, ETH_ALEN);
+	return write_l2e(adap, e, 0);
+}
+
 struct l2t_data *t4_init_l2t(void)
 {
 	int i;

drivers/net/ethernet/chelsio/cxgb4/l2t.h

@@ -100,6 +100,9 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
 				unsigned int priority);
 
 void t4_l2t_update(struct adapter *adap, struct neighbour *neigh);
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d);
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+			 u8 port, u8 *eth_addr);
 struct l2t_data *t4_init_l2t(void);
 void do_l2t_write_rpl(struct adapter *p, const struct cpl_l2t_write_rpl *rpl);
 

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

@@ -109,7 +109,7 @@ void t4_set_reg_field(struct adapter *adapter, unsigned int addr, u32 mask,
  *	Reads registers that are accessed indirectly through an address/data
  *	register pair.
  */
-static void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
 			     unsigned int data_reg, u32 *vals,
 			     unsigned int nregs, unsigned int start_idx)
 {
@@ -2268,6 +2268,26 @@ int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
 	return 0;
 }
 
+/*     t4_mk_filtdelwr - create a delete filter WR
+ *     @ftid: the filter ID
+ *     @wr: the filter work request to populate
+ *     @qid: ingress queue to receive the delete notification
+ *
+ *     Creates a filter work request to delete the supplied filter.  If @qid is
+ *     negative the delete notification is suppressed.
+ */
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid)
+{
+	memset(wr, 0, sizeof(*wr));
+	wr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+	wr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*wr) / 16));
+	wr->tid_to_iq = htonl(V_FW_FILTER_WR_TID(ftid) |
+			V_FW_FILTER_WR_NOREPLY(qid < 0));
+	wr->del_filter_to_l2tix = htonl(F_FW_FILTER_WR_DEL_FILTER);
+	if (qid >= 0)
+		wr->rx_chan_rx_rpl_iq = htons(V_FW_FILTER_WR_RX_RPL_IQ(qid));
+}
+
 #define INIT_CMD(var, cmd, rd_wr) do { \
 	(var).op_to_write = htonl(FW_CMD_OP(FW_##cmd##_CMD) | \
 				  FW_CMD_REQUEST | FW_CMD_##rd_wr); \

drivers/net/ethernet/chelsio/cxgb4/t4_msg.h

@@ -332,6 +332,7 @@ struct cpl_set_tcb_field {
 	__be16 word_cookie;
 #define TCB_WORD(x)   ((x) << 0)
 #define TCB_COOKIE(x) ((x) << 5)
+#define GET_TCB_COOKIE(x) (((x) >> 5) & 7)
 	__be64 mask;
 	__be64 val;
 };

drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h

@@ -35,6 +35,10 @@
 #ifndef _T4FW_INTERFACE_H_
 #define _T4FW_INTERFACE_H_
 
+enum fw_ret_val {
+	FW_ENOEXEC      = 8,            /* Exec format error; inv microcode */
+};
+
 #define FW_T4VF_SGE_BASE_ADDR      0x0000
 #define FW_T4VF_MPS_BASE_ADDR      0x0100
 #define FW_T4VF_PL_BASE_ADDR       0x0200
@@ -82,6 +86,281 @@ struct fw_wr_hdr {
 
 #define HW_TPL_FR_MT_PR_IV_P_FC         0X32B
 
+/* filter wr reply code in cookie in CPL_SET_TCB_RPL */
+enum fw_filter_wr_cookie {
+	FW_FILTER_WR_SUCCESS,
+	FW_FILTER_WR_FLT_ADDED,
+	FW_FILTER_WR_FLT_DELETED,
+	FW_FILTER_WR_SMT_TBL_FULL,
+	FW_FILTER_WR_EINVAL,
+};
+
+struct fw_filter_wr {
+	__be32 op_pkd;
+	__be32 len16_pkd;
+	__be64 r3;
+	__be32 tid_to_iq;
+	__be32 del_filter_to_l2tix;
+	__be16 ethtype;
+	__be16 ethtypem;
+	__u8   frag_to_ovlan_vldm;
+	__u8   smac_sel;
+	__be16 rx_chan_rx_rpl_iq;
+	__be32 maci_to_matchtypem;
+	__u8   ptcl;
+	__u8   ptclm;
+	__u8   ttyp;
+	__u8   ttypm;
+	__be16 ivlan;
+	__be16 ivlanm;
+	__be16 ovlan;
+	__be16 ovlanm;
+	__u8   lip[16];
+	__u8   lipm[16];
+	__u8   fip[16];
+	__u8   fipm[16];
+	__be16 lp;
+	__be16 lpm;
+	__be16 fp;
+	__be16 fpm;
+	__be16 r7;
+	__u8   sma[6];
+};
+
+#define S_FW_FILTER_WR_TID      12
+#define M_FW_FILTER_WR_TID      0xfffff
+#define V_FW_FILTER_WR_TID(x)   ((x) << S_FW_FILTER_WR_TID)
+#define G_FW_FILTER_WR_TID(x)   \
+	(((x) >> S_FW_FILTER_WR_TID) & M_FW_FILTER_WR_TID)
+
+#define S_FW_FILTER_WR_RQTYPE           11
+#define M_FW_FILTER_WR_RQTYPE           0x1
+#define V_FW_FILTER_WR_RQTYPE(x)        ((x) << S_FW_FILTER_WR_RQTYPE)
+#define G_FW_FILTER_WR_RQTYPE(x)        \
+	(((x) >> S_FW_FILTER_WR_RQTYPE) & M_FW_FILTER_WR_RQTYPE)
+#define F_FW_FILTER_WR_RQTYPE   V_FW_FILTER_WR_RQTYPE(1U)
+
+#define S_FW_FILTER_WR_NOREPLY          10
+#define M_FW_FILTER_WR_NOREPLY          0x1
+#define V_FW_FILTER_WR_NOREPLY(x)       ((x) << S_FW_FILTER_WR_NOREPLY)
+#define G_FW_FILTER_WR_NOREPLY(x)       \
+	(((x) >> S_FW_FILTER_WR_NOREPLY) & M_FW_FILTER_WR_NOREPLY)
+#define F_FW_FILTER_WR_NOREPLY  V_FW_FILTER_WR_NOREPLY(1U)
+
+#define S_FW_FILTER_WR_IQ       0
+#define M_FW_FILTER_WR_IQ       0x3ff
+#define V_FW_FILTER_WR_IQ(x)    ((x) << S_FW_FILTER_WR_IQ)
+#define G_FW_FILTER_WR_IQ(x)    \
+	(((x) >> S_FW_FILTER_WR_IQ) & M_FW_FILTER_WR_IQ)
+
+#define S_FW_FILTER_WR_DEL_FILTER       31
+#define M_FW_FILTER_WR_DEL_FILTER       0x1
+#define V_FW_FILTER_WR_DEL_FILTER(x)    ((x) << S_FW_FILTER_WR_DEL_FILTER)
+#define G_FW_FILTER_WR_DEL_FILTER(x)    \
+	(((x) >> S_FW_FILTER_WR_DEL_FILTER) & M_FW_FILTER_WR_DEL_FILTER)
+#define F_FW_FILTER_WR_DEL_FILTER       V_FW_FILTER_WR_DEL_FILTER(1U)
+
+#define S_FW_FILTER_WR_RPTTID           25
+#define M_FW_FILTER_WR_RPTTID           0x1
+#define V_FW_FILTER_WR_RPTTID(x)        ((x) << S_FW_FILTER_WR_RPTTID)
+#define G_FW_FILTER_WR_RPTTID(x)        \
+	(((x) >> S_FW_FILTER_WR_RPTTID) & M_FW_FILTER_WR_RPTTID)
+#define F_FW_FILTER_WR_RPTTID   V_FW_FILTER_WR_RPTTID(1U)
+
+#define S_FW_FILTER_WR_DROP     24
+#define M_FW_FILTER_WR_DROP     0x1
+#define V_FW_FILTER_WR_DROP(x)  ((x) << S_FW_FILTER_WR_DROP)
+#define G_FW_FILTER_WR_DROP(x)  \
+	(((x) >> S_FW_FILTER_WR_DROP) & M_FW_FILTER_WR_DROP)
+#define F_FW_FILTER_WR_DROP     V_FW_FILTER_WR_DROP(1U)
+
+#define S_FW_FILTER_WR_DIRSTEER         23
+#define M_FW_FILTER_WR_DIRSTEER         0x1
+#define V_FW_FILTER_WR_DIRSTEER(x)      ((x) << S_FW_FILTER_WR_DIRSTEER)
+#define G_FW_FILTER_WR_DIRSTEER(x)      \
+	(((x) >> S_FW_FILTER_WR_DIRSTEER) & M_FW_FILTER_WR_DIRSTEER)
+#define F_FW_FILTER_WR_DIRSTEER V_FW_FILTER_WR_DIRSTEER(1U)
+
+#define S_FW_FILTER_WR_MASKHASH         22
+#define M_FW_FILTER_WR_MASKHASH         0x1
+#define V_FW_FILTER_WR_MASKHASH(x)      ((x) << S_FW_FILTER_WR_MASKHASH)
+#define G_FW_FILTER_WR_MASKHASH(x)      \
+	(((x) >> S_FW_FILTER_WR_MASKHASH) & M_FW_FILTER_WR_MASKHASH)
+#define F_FW_FILTER_WR_MASKHASH V_FW_FILTER_WR_MASKHASH(1U)
+
+#define S_FW_FILTER_WR_DIRSTEERHASH     21
+#define M_FW_FILTER_WR_DIRSTEERHASH     0x1
+#define V_FW_FILTER_WR_DIRSTEERHASH(x)  ((x) << S_FW_FILTER_WR_DIRSTEERHASH)
+#define G_FW_FILTER_WR_DIRSTEERHASH(x)  \
+	(((x) >> S_FW_FILTER_WR_DIRSTEERHASH) & M_FW_FILTER_WR_DIRSTEERHASH)
+#define F_FW_FILTER_WR_DIRSTEERHASH     V_FW_FILTER_WR_DIRSTEERHASH(1U)
+
+#define S_FW_FILTER_WR_LPBK     20
+#define M_FW_FILTER_WR_LPBK     0x1
+#define V_FW_FILTER_WR_LPBK(x)  ((x) << S_FW_FILTER_WR_LPBK)
+#define G_FW_FILTER_WR_LPBK(x)  \
+	(((x) >> S_FW_FILTER_WR_LPBK) & M_FW_FILTER_WR_LPBK)
+#define F_FW_FILTER_WR_LPBK     V_FW_FILTER_WR_LPBK(1U)
+
+#define S_FW_FILTER_WR_DMAC     19
+#define M_FW_FILTER_WR_DMAC     0x1
+#define V_FW_FILTER_WR_DMAC(x)  ((x) << S_FW_FILTER_WR_DMAC)
+#define G_FW_FILTER_WR_DMAC(x)  \
+	(((x) >> S_FW_FILTER_WR_DMAC) & M_FW_FILTER_WR_DMAC)
+#define F_FW_FILTER_WR_DMAC     V_FW_FILTER_WR_DMAC(1U)
+
+#define S_FW_FILTER_WR_SMAC     18
+#define M_FW_FILTER_WR_SMAC     0x1
+#define V_FW_FILTER_WR_SMAC(x)  ((x) << S_FW_FILTER_WR_SMAC)
+#define G_FW_FILTER_WR_SMAC(x)  \
+	(((x) >> S_FW_FILTER_WR_SMAC) & M_FW_FILTER_WR_SMAC)
+#define F_FW_FILTER_WR_SMAC     V_FW_FILTER_WR_SMAC(1U)
+
+#define S_FW_FILTER_WR_INSVLAN          17
+#define M_FW_FILTER_WR_INSVLAN          0x1
+#define V_FW_FILTER_WR_INSVLAN(x)       ((x) << S_FW_FILTER_WR_INSVLAN)
+#define G_FW_FILTER_WR_INSVLAN(x)       \
+	(((x) >> S_FW_FILTER_WR_INSVLAN) & M_FW_FILTER_WR_INSVLAN)
+#define F_FW_FILTER_WR_INSVLAN  V_FW_FILTER_WR_INSVLAN(1U)
+
+#define S_FW_FILTER_WR_RMVLAN           16
+#define M_FW_FILTER_WR_RMVLAN           0x1
+#define V_FW_FILTER_WR_RMVLAN(x)        ((x) << S_FW_FILTER_WR_RMVLAN)
+#define G_FW_FILTER_WR_RMVLAN(x)        \
+	(((x) >> S_FW_FILTER_WR_RMVLAN) & M_FW_FILTER_WR_RMVLAN)
+#define F_FW_FILTER_WR_RMVLAN   V_FW_FILTER_WR_RMVLAN(1U)
+
+#define S_FW_FILTER_WR_HITCNTS          15
+#define M_FW_FILTER_WR_HITCNTS          0x1
+#define V_FW_FILTER_WR_HITCNTS(x)       ((x) << S_FW_FILTER_WR_HITCNTS)
+#define G_FW_FILTER_WR_HITCNTS(x)       \
+	(((x) >> S_FW_FILTER_WR_HITCNTS) & M_FW_FILTER_WR_HITCNTS)
+#define F_FW_FILTER_WR_HITCNTS  V_FW_FILTER_WR_HITCNTS(1U)
+
+#define S_FW_FILTER_WR_TXCHAN           13
+#define M_FW_FILTER_WR_TXCHAN           0x3
+#define V_FW_FILTER_WR_TXCHAN(x)        ((x) << S_FW_FILTER_WR_TXCHAN)
+#define G_FW_FILTER_WR_TXCHAN(x)        \
+	(((x) >> S_FW_FILTER_WR_TXCHAN) & M_FW_FILTER_WR_TXCHAN)
+
+#define S_FW_FILTER_WR_PRIO     12
+#define M_FW_FILTER_WR_PRIO     0x1
+#define V_FW_FILTER_WR_PRIO(x)  ((x) << S_FW_FILTER_WR_PRIO)
+#define G_FW_FILTER_WR_PRIO(x)  \
+	(((x) >> S_FW_FILTER_WR_PRIO) & M_FW_FILTER_WR_PRIO)
+#define F_FW_FILTER_WR_PRIO     V_FW_FILTER_WR_PRIO(1U)
+
+#define S_FW_FILTER_WR_L2TIX    0
+#define M_FW_FILTER_WR_L2TIX    0xfff
+#define V_FW_FILTER_WR_L2TIX(x) ((x) << S_FW_FILTER_WR_L2TIX)
+#define G_FW_FILTER_WR_L2TIX(x) \
+	(((x) >> S_FW_FILTER_WR_L2TIX) & M_FW_FILTER_WR_L2TIX)
+
+#define S_FW_FILTER_WR_FRAG     7
+#define M_FW_FILTER_WR_FRAG     0x1
+#define V_FW_FILTER_WR_FRAG(x)  ((x) << S_FW_FILTER_WR_FRAG)
+#define G_FW_FILTER_WR_FRAG(x)  \
+	(((x) >> S_FW_FILTER_WR_FRAG) & M_FW_FILTER_WR_FRAG)
+#define F_FW_FILTER_WR_FRAG     V_FW_FILTER_WR_FRAG(1U)
+
+#define S_FW_FILTER_WR_FRAGM    6
+#define M_FW_FILTER_WR_FRAGM    0x1
+#define V_FW_FILTER_WR_FRAGM(x) ((x) << S_FW_FILTER_WR_FRAGM)
+#define G_FW_FILTER_WR_FRAGM(x) \
+	(((x) >> S_FW_FILTER_WR_FRAGM) & M_FW_FILTER_WR_FRAGM)
+#define F_FW_FILTER_WR_FRAGM    V_FW_FILTER_WR_FRAGM(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLD        5
+#define M_FW_FILTER_WR_IVLAN_VLD        0x1
+#define V_FW_FILTER_WR_IVLAN_VLD(x)     ((x) << S_FW_FILTER_WR_IVLAN_VLD)
+#define G_FW_FILTER_WR_IVLAN_VLD(x)     \
+	(((x) >> S_FW_FILTER_WR_IVLAN_VLD) & M_FW_FILTER_WR_IVLAN_VLD)
+#define F_FW_FILTER_WR_IVLAN_VLD        V_FW_FILTER_WR_IVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLD        4
+#define M_FW_FILTER_WR_OVLAN_VLD        0x1
+#define V_FW_FILTER_WR_OVLAN_VLD(x)     ((x) << S_FW_FILTER_WR_OVLAN_VLD)
+#define G_FW_FILTER_WR_OVLAN_VLD(x)     \
+	(((x) >> S_FW_FILTER_WR_OVLAN_VLD) & M_FW_FILTER_WR_OVLAN_VLD)
+#define F_FW_FILTER_WR_OVLAN_VLD        V_FW_FILTER_WR_OVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLDM       3
+#define M_FW_FILTER_WR_IVLAN_VLDM       0x1
+#define V_FW_FILTER_WR_IVLAN_VLDM(x)    ((x) << S_FW_FILTER_WR_IVLAN_VLDM)
+#define G_FW_FILTER_WR_IVLAN_VLDM(x)    \
+	(((x) >> S_FW_FILTER_WR_IVLAN_VLDM) & M_FW_FILTER_WR_IVLAN_VLDM)
+#define F_FW_FILTER_WR_IVLAN_VLDM       V_FW_FILTER_WR_IVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLDM       2
+#define M_FW_FILTER_WR_OVLAN_VLDM       0x1
+#define V_FW_FILTER_WR_OVLAN_VLDM(x)    ((x) << S_FW_FILTER_WR_OVLAN_VLDM)
+#define G_FW_FILTER_WR_OVLAN_VLDM(x)    \
+	(((x) >> S_FW_FILTER_WR_OVLAN_VLDM) & M_FW_FILTER_WR_OVLAN_VLDM)
+#define F_FW_FILTER_WR_OVLAN_VLDM       V_FW_FILTER_WR_OVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_RX_CHAN          15
+#define M_FW_FILTER_WR_RX_CHAN          0x1
+#define V_FW_FILTER_WR_RX_CHAN(x)       ((x) << S_FW_FILTER_WR_RX_CHAN)
+#define G_FW_FILTER_WR_RX_CHAN(x)       \
+	(((x) >> S_FW_FILTER_WR_RX_CHAN) & M_FW_FILTER_WR_RX_CHAN)
+#define F_FW_FILTER_WR_RX_CHAN  V_FW_FILTER_WR_RX_CHAN(1U)
+
+#define S_FW_FILTER_WR_RX_RPL_IQ        0
+#define M_FW_FILTER_WR_RX_RPL_IQ        0x3ff
+#define V_FW_FILTER_WR_RX_RPL_IQ(x)     ((x) << S_FW_FILTER_WR_RX_RPL_IQ)
+#define G_FW_FILTER_WR_RX_RPL_IQ(x)     \
+	(((x) >> S_FW_FILTER_WR_RX_RPL_IQ) & M_FW_FILTER_WR_RX_RPL_IQ)
+
+#define S_FW_FILTER_WR_MACI     23
+#define M_FW_FILTER_WR_MACI     0x1ff
+#define V_FW_FILTER_WR_MACI(x)  ((x) << S_FW_FILTER_WR_MACI)
+#define G_FW_FILTER_WR_MACI(x)  \
+	(((x) >> S_FW_FILTER_WR_MACI) & M_FW_FILTER_WR_MACI)
+
+#define S_FW_FILTER_WR_MACIM    14
+#define M_FW_FILTER_WR_MACIM    0x1ff
+#define V_FW_FILTER_WR_MACIM(x) ((x) << S_FW_FILTER_WR_MACIM)
+#define G_FW_FILTER_WR_MACIM(x) \
+	(((x) >> S_FW_FILTER_WR_MACIM) & M_FW_FILTER_WR_MACIM)
+
+#define S_FW_FILTER_WR_FCOE     13
+#define M_FW_FILTER_WR_FCOE     0x1
+#define V_FW_FILTER_WR_FCOE(x)  ((x) << S_FW_FILTER_WR_FCOE)
+#define G_FW_FILTER_WR_FCOE(x)  \
+	(((x) >> S_FW_FILTER_WR_FCOE) & M_FW_FILTER_WR_FCOE)
+#define F_FW_FILTER_WR_FCOE     V_FW_FILTER_WR_FCOE(1U)
+
+#define S_FW_FILTER_WR_FCOEM    12
+#define M_FW_FILTER_WR_FCOEM    0x1
+#define V_FW_FILTER_WR_FCOEM(x) ((x) << S_FW_FILTER_WR_FCOEM)
+#define G_FW_FILTER_WR_FCOEM(x) \
+	(((x) >> S_FW_FILTER_WR_FCOEM) & M_FW_FILTER_WR_FCOEM)
+#define F_FW_FILTER_WR_FCOEM    V_FW_FILTER_WR_FCOEM(1U)
+
+#define S_FW_FILTER_WR_PORT     9
+#define M_FW_FILTER_WR_PORT     0x7
+#define V_FW_FILTER_WR_PORT(x)  ((x) << S_FW_FILTER_WR_PORT)
+#define G_FW_FILTER_WR_PORT(x)  \
+	(((x) >> S_FW_FILTER_WR_PORT) & M_FW_FILTER_WR_PORT)
+
+#define S_FW_FILTER_WR_PORTM    6
+#define M_FW_FILTER_WR_PORTM    0x7
+#define V_FW_FILTER_WR_PORTM(x) ((x) << S_FW_FILTER_WR_PORTM)
+#define G_FW_FILTER_WR_PORTM(x) \
+	(((x) >> S_FW_FILTER_WR_PORTM) & M_FW_FILTER_WR_PORTM)
+
+#define S_FW_FILTER_WR_MATCHTYPE        3
+#define M_FW_FILTER_WR_MATCHTYPE        0x7
+#define V_FW_FILTER_WR_MATCHTYPE(x)     ((x) << S_FW_FILTER_WR_MATCHTYPE)
+#define G_FW_FILTER_WR_MATCHTYPE(x)     \
+	(((x) >> S_FW_FILTER_WR_MATCHTYPE) & M_FW_FILTER_WR_MATCHTYPE)
+
+#define S_FW_FILTER_WR_MATCHTYPEM       0
+#define M_FW_FILTER_WR_MATCHTYPEM       0x7
+#define V_FW_FILTER_WR_MATCHTYPEM(x)    ((x) << S_FW_FILTER_WR_MATCHTYPEM)
+#define G_FW_FILTER_WR_MATCHTYPEM(x)    \
+	(((x) >> S_FW_FILTER_WR_MATCHTYPEM) & M_FW_FILTER_WR_MATCHTYPEM)
+
 struct fw_ulptx_wr {
 	__be32 op_to_compl;
 	__be32 flowid_len16;