Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull more infiniband changes from Roland Dreier:
 "Second batch of InfiniBand/RDMA changes for 3.8:
   - cxgb4 changes to fix lookup engine hash collisions
   - mlx4 changes to make flow steering usable
   - fix to IPoIB to avoid pinning dst reference for too long"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  RDMA/cxgb4: Fix bug for active and passive LE hash collision path
  RDMA/cxgb4: Fix LE hash collision bug for passive open connection
  RDMA/cxgb4: Fix LE hash collision bug for active open connection
  mlx4_core: Allow choosing flow steering mode
  mlx4_core: Adjustments to Flow Steering activation logic for SR-IOV
  mlx4_core: Fix error flow in the flow steering wrapper
  mlx4_core: Add QPN enforcement for flow steering rules set by VFs
  cxgb4: Add LE hash collision bug fix path in LLD driver
  cxgb4: Add T4 filter support
  IPoIB: Call skb_dst_drop() once skb is enqueued for sending

15 files changed, 1309 insertions, 59 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 378988b5709a..6db997c78a5f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -35,6 +35,8 @@
 #ifndef __CXGB4_H__
 #define __CXGB4_H__
 
+#include "t4_hw.h"
+
 #include <linux/bitops.h>
 #include <linux/cache.h>
 #include <linux/interrupt.h>
@@ -212,6 +214,8 @@ struct tp_err_stats {
 struct tp_params {
 	unsigned int ntxchan;        /* # of Tx channels */
 	unsigned int tre;            /* log2 of core clocks per TP tick */
+	unsigned short tx_modq_map;  /* TX modulation scheduler queue to */
+				     /* channel map */
 
 	uint32_t dack_re;            /* DACK timer resolution */
 	unsigned short tx_modq[NCHAN];	/* channel to modulation queue map */
@@ -526,6 +530,7 @@ struct adapter {
 	struct net_device *port[MAX_NPORTS];
 	u8 chan_map[NCHAN];                   /* channel -> port map */
 
+	u32 filter_mode;
 	unsigned int l2t_start;
 	unsigned int l2t_end;
 	struct l2t_data *l2t;
@@ -545,6 +550,129 @@ 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 +829,12 @@ 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 +871,8 @@ 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,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a27b4ae20f43..f0718e1a8369 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/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;
@@ -2249,8 +2481,34 @@ int cxgb4_alloc_stid(struct tid_info *t, int family, void *data)
 }
 EXPORT_SYMBOL(cxgb4_alloc_stid);
 
-/*
- * Release a server TID.
+/* Allocate a server filter TID and set it to the supplied value.
+ */
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
+{
+	int stid;
+
+	spin_lock_bh(&t->stid_lock);
+	if (family == PF_INET) {
+		stid = find_next_zero_bit(t->stid_bmap,
+				t->nstids + t->nsftids, t->nstids);
+		if (stid < (t->nstids + t->nsftids))
+			__set_bit(stid, t->stid_bmap);
+		else
+			stid = -1;
+	} else {
+		stid = -1;
+	}
+	if (stid >= 0) {
+		t->stid_tab[stid].data = data;
+		stid += t->stid_base;
+		t->stids_in_use++;
+	}
+	spin_unlock_bh(&t->stid_lock);
+	return stid;
+}
+EXPORT_SYMBOL(cxgb4_alloc_sftid);
+
+/* Release a server TID.
  */
 void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
 {
@@ -2362,18 +2620,26 @@ 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 + t->nsftids);
+	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);
+	       t->nsftids * sizeof(*t->stid_tab) +
+	       stid_bmap_size * sizeof(long) +
+	       t->nftids * sizeof(*t->ftid_tab) +
+	       t->nsftids * sizeof(*t->ftid_tab);
+
 	t->tid_tab = t4_alloc_mem(size);
 	if (!t->tid_tab)
 		return -ENOMEM;
 
 	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->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids + t->nsftids];
+	t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
 	spin_lock_init(&t->stid_lock);
 	spin_lock_init(&t->atid_lock);
 
@@ -2388,7 +2654,7 @@ static int tid_init(struct tid_info *t)
 			t->atid_tab[natids - 1].next = &t->atid_tab[natids];
 		t->afree = t->atid_tab;
 	}
-	bitmap_zero(t->stid_bmap, t->nstids);
+	bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
 	return 0;
 }
 
@@ -2404,7 +2670,8 @@ static int tid_init(struct tid_info *t)
  *	Returns <0 on error and one of the %NET_XMIT_* values on success.
  */
 int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
-			__be32 sip, __be16 sport, unsigned int queue)
+			__be32 sip, __be16 sport, __be16 vlan,
+			unsigned int queue)
 {
 	unsigned int chan;
 	struct sk_buff *skb;
@@ -2750,6 +3017,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 {
 	void *handle;
 	struct cxgb4_lld_info lli;
+	unsigned short i;
 
 	lli.pdev = adap->pdev;
 	lli.l2t = adap->l2t;
@@ -2776,10 +3044,16 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
 			t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
 			(adap->fn * 4));
+	lli.filt_mode = adap->filter_mode;
+	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
+	for (i = 0; i < NCHAN; i++)
+		lli.tx_modq[i] = i;
 	lli.gts_reg = adap->regs + MYPF_REG(SGE_PF_GTS);
 	lli.db_reg = adap->regs + MYPF_REG(SGE_PF_KDOORBELL);
 	lli.fw_vers = adap->params.fw_vers;
 	lli.dbfifo_int_thresh = dbfifo_int_thresh;
+	lli.sge_pktshift = adap->sge.pktshift;
+	lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
 
 	handle = ulds[uld].add(&lli);
 	if (IS_ERR(handle)) {
@@ -2999,6 +3273,126 @@ 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 + adapter->tids.nsftids)
+		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;
+}
+
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+		__be32 sip, __be16 sport, __be16 vlan,
+		unsigned int queue, unsigned char port, unsigned char mask)
+{
+	int ret;
+	struct filter_entry *f;
+	struct adapter *adap;
+	int i;
+	u8 *val;
+
+	adap = netdev2adap(dev);
+
+	/* Adjust stid to correct filter index */
+	stid -= adap->tids.nstids;
+	stid += adap->tids.nftids;
+
+	/* Check to make sure the filter requested is writable ...
+	 */
+	f = &adap->tids.ftid_tab[stid];
+	ret = writable_filter(f);
+	if (ret)
+		return ret;
+
+	/* Clear out any old resources being used by the filter before
+	 * we start constructing the new filter.
+	 */
+	if (f->valid)
+		clear_filter(adap, f);
+
+	/* Clear out filter specifications */
+	memset(&f->fs, 0, sizeof(struct ch_filter_specification));
+	f->fs.val.lport = cpu_to_be16(sport);
+	f->fs.mask.lport  = ~0;
+	val = (u8 *)&sip;
+	if ((val[0] | val[1] | val[2] | val[3]) != 0) {
+		for (i = 0; i < 4; i++) {
+			f->fs.val.lip[i] = val[i];
+			f->fs.mask.lip[i] = ~0;
+		}
+		if (adap->filter_mode & F_PORT) {
+			f->fs.val.iport = port;
+			f->fs.mask.iport = mask;
+		}
+	}
+
+	f->fs.dirsteer = 1;
+	f->fs.iq = queue;
+	/* Mark filter as locked */
+	f->locked = 1;
+	f->fs.rpttid = 1;
+
+	ret = set_filter_wr(adap, stid);
+	if (ret) {
+		clear_filter(adap, f);
+		return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(cxgb4_create_server_filter);
+
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+		unsigned int queue, bool ipv6)
+{
+	int ret;
+	struct filter_entry *f;
+	struct adapter *adap;
+
+	adap = netdev2adap(dev);
+
+	/* Adjust stid to correct filter index */
+	stid -= adap->tids.nstids;
+	stid += adap->tids.nftids;
+
+	f = &adap->tids.ftid_tab[stid];
+	/* Unlock the filter */
+	f->locked = 0;
+
+	ret = delete_filter(adap, stid);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL(cxgb4_remove_server_filter);
+
 static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
 						struct rtnl_link_stats64 *ns)
 {
@@ -3245,6 +3639,34 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	v = t4_read_reg(adap, TP_PIO_DATA);
 	t4_write_reg(adap, TP_PIO_DATA, v & ~CSUM_HAS_PSEUDO_HDR);
 
+	/* first 4 Tx modulation queues point to consecutive Tx channels */
+	adap->params.tp.tx_modq_map = 0xE4;
+	t4_write_reg(adap, A_TP_TX_MOD_QUEUE_REQ_MAP,
+		     V_TX_MOD_QUEUE_REQ_MAP(adap->params.tp.tx_modq_map));
+
+	/* associate each Tx modulation queue with consecutive Tx channels */
+	v = 0x84218421;
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_HDR);
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_FIFO);
+	t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			  &v, 1, A_TP_TX_SCHED_PCMD);
+
+#define T4_TX_MODQ_10G_WEIGHT_DEFAULT 16 /* in KB units */
+	if (is_offload(adap)) {
+		t4_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT0,
+			     V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+		t4_write_reg(adap, A_TP_TX_MOD_CHANNEL_WEIGHT,
+			     V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+			     V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+	}
+
 	/* get basic stuff going */
 	return t4_early_init(adap, adap->fn);
 }
@@ -4035,6 +4457,10 @@ static int adap_init0(struct adapter *adap)
 	for (j = 0; j < NCHAN; j++)
 		adap->params.tp.tx_modq[j] = j;
 
+	t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+			 &adap->filter_mode, 1,
+			 TP_VLAN_PRI_MAP);
+
 	adap->flags |= FW_OK;
 	return 0;
 
@@ -4661,6 +5087,17 @@ 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 +
+					adapter->tids.nsftids); i++, f++)
+				if (f->valid)
+					clear_filter(adapter, f);
+		}
+
 		if (adapter->flags & FULL_INIT_DONE)
 			cxgb_down(adapter);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 39bec73ff87c..e2bbc7f3e2de 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -38,6 +38,7 @@
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
+#include <linux/inetdevice.h>
 #include <linux/atomic.h>
 
 /* CPL message priority levels */
@@ -97,7 +98,9 @@ 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;
@@ -129,7 +132,7 @@ static inline void *lookup_atid(const struct tid_info *t, unsigned int atid)
 static inline void *lookup_stid(const struct tid_info *t, unsigned int stid)
 {
 	stid -= t->stid_base;
-	return stid < t->nstids ? t->stid_tab[stid].data : NULL;
+	return stid < (t->nstids + t->nsftids) ? t->stid_tab[stid].data : NULL;
 }
 
 static inline void cxgb4_insert_tid(struct tid_info *t, void *data,
@@ -141,6 +144,7 @@ static inline void cxgb4_insert_tid(struct tid_info *t, void *data,
 
 int cxgb4_alloc_atid(struct tid_info *t, void *data);
 int cxgb4_alloc_stid(struct tid_info *t, int family, void *data);
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data);
 void cxgb4_free_atid(struct tid_info *t, unsigned int atid);
 void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family);
 void cxgb4_remove_tid(struct tid_info *t, unsigned int qid, unsigned int tid);
@@ -148,8 +152,14 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int qid, unsigned int tid);
 struct in6_addr;
 
 int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
-			__be32 sip, __be16 sport, unsigned int queue);
-
+			__be32 sip, __be16 sport, __be16 vlan,
+			unsigned int queue);
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+			       __be32 sip, __be16 sport, __be16 vlan,
+			       unsigned int queue,
+			       unsigned char port, unsigned char mask);
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+			       unsigned int queue, bool ipv6);
 static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
 {
 	skb_set_queue_mapping(skb, (queue << 1) | prio);
@@ -221,9 +231,16 @@ struct cxgb4_lld_info {
 	unsigned int iscsi_iolen;            /* iSCSI max I/O length */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
+	unsigned short filt_mode;            /* filter optional components */
+	unsigned short tx_modq[NCHAN];       /* maps each tx channel to a */
+					     /* scheduler queue */
 	void __iomem *gts_reg;               /* address of GTS register */
 	void __iomem *db_reg;                /* address of kernel doorbell */
 	int dbfifo_int_thresh;		     /* doorbell fifo int threshold */
+	unsigned int sge_pktshift;           /* Padding between CPL and */
+					     /*	packet data */
+	bool enable_fw_ofld_conn;            /* Enable connection through fw */
+					     /* WR */
 };
 
 struct cxgb4_uld_info {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 6ac77a62f361..29878098101e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/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;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
index 02b31d0c6410..108c0f1fce1c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h
+++ b/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);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 8d9c7547b070..22f3af5166bf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/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); \
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index b760808fd6d9..261d17703adc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -193,8 +193,24 @@ struct work_request_hdr {
 	__be64 wr_lo;
 };
 
+/* wr_hi fields */
+#define S_WR_OP    24
+#define V_WR_OP(x) ((__u64)(x) << S_WR_OP)
+
 #define WR_HDR struct work_request_hdr wr
 
+/* option 0 fields */
+#define S_MSS_IDX    60
+#define M_MSS_IDX    0xF
+#define V_MSS_IDX(x) ((__u64)(x) << S_MSS_IDX)
+#define G_MSS_IDX(x) (((x) >> S_MSS_IDX) & M_MSS_IDX)
+
+/* option 2 fields */
+#define S_RSS_QUEUE    0
+#define M_RSS_QUEUE    0x3FF
+#define V_RSS_QUEUE(x) ((x) << S_RSS_QUEUE)
+#define G_RSS_QUEUE(x) (((x) >> S_RSS_QUEUE) & M_RSS_QUEUE)
+
 struct cpl_pass_open_req {
 	WR_HDR;
 	union opcode_tid ot;
@@ -204,12 +220,14 @@ struct cpl_pass_open_req {
 	__be32 peer_ip;
 	__be64 opt0;
 #define TX_CHAN(x)    ((x) << 2)
+#define NO_CONG(x)    ((x) << 4)
 #define DELACK(x)     ((x) << 5)
 #define ULP_MODE(x)   ((x) << 8)
 #define RCV_BUFSIZ(x) ((x) << 12)
 #define DSCP(x)       ((x) << 22)
 #define SMAC_SEL(x)   ((u64)(x) << 28)
 #define L2T_IDX(x)    ((u64)(x) << 36)
+#define TCAM_BYPASS(x) ((u64)(x) << 48)
 #define NAGLE(x)      ((u64)(x) << 49)
 #define WND_SCALE(x)  ((u64)(x) << 50)
 #define KEEP_ALIVE(x) ((u64)(x) << 54)
@@ -247,8 +265,10 @@ struct cpl_pass_accept_rpl {
 #define RSS_QUEUE_VALID      (1 << 10)
 #define RX_COALESCE_VALID(x) ((x) << 11)
 #define RX_COALESCE(x)       ((x) << 12)
+#define PACE(x)	      ((x) << 16)
 #define TX_QUEUE(x)          ((x) << 23)
 #define RX_CHANNEL(x)        ((x) << 26)
+#define CCTRL_ECN(x)         ((x) << 27)
 #define WND_SCALE_EN(x)      ((x) << 28)
 #define TSTAMPS_EN(x)        ((x) << 29)
 #define SACK_EN(x)           ((x) << 30)
@@ -292,6 +312,9 @@ struct cpl_pass_establish {
 	union opcode_tid ot;
 	__be32 rsvd;
 	__be32 tos_stid;
+#define PASS_OPEN_TID(x) ((x) << 0)
+#define PASS_OPEN_TOS(x) ((x) << 24)
+#define GET_PASS_OPEN_TID(x)	(((x) >> 0) & 0xFFFFFF)
 #define GET_POPEN_TID(x) ((x) & 0xffffff)
 #define GET_POPEN_TOS(x) (((x) >> 24) & 0xff)
 	__be16 mac_idx;
@@ -332,6 +355,7 @@ 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;
 };
@@ -536,6 +560,37 @@ struct cpl_rx_pkt {
 	__be16 err_vec;
 };
 
+/* rx_pkt.l2info fields */
+#define S_RX_ETHHDR_LEN    0
+#define M_RX_ETHHDR_LEN    0x1F
+#define V_RX_ETHHDR_LEN(x) ((x) << S_RX_ETHHDR_LEN)
+#define G_RX_ETHHDR_LEN(x) (((x) >> S_RX_ETHHDR_LEN) & M_RX_ETHHDR_LEN)
+
+#define S_RX_MACIDX    8
+#define M_RX_MACIDX    0x1FF
+#define V_RX_MACIDX(x) ((x) << S_RX_MACIDX)
+#define G_RX_MACIDX(x) (((x) >> S_RX_MACIDX) & M_RX_MACIDX)
+
+#define S_RXF_SYN    21
+#define V_RXF_SYN(x) ((x) << S_RXF_SYN)
+#define F_RXF_SYN    V_RXF_SYN(1U)
+
+#define S_RX_CHAN    28
+#define M_RX_CHAN    0xF
+#define V_RX_CHAN(x) ((x) << S_RX_CHAN)
+#define G_RX_CHAN(x) (((x) >> S_RX_CHAN) & M_RX_CHAN)
+
+/* rx_pkt.hdr_len fields */
+#define S_RX_TCPHDR_LEN    0
+#define M_RX_TCPHDR_LEN    0x3F
+#define V_RX_TCPHDR_LEN(x) ((x) << S_RX_TCPHDR_LEN)
+#define G_RX_TCPHDR_LEN(x) (((x) >> S_RX_TCPHDR_LEN) & M_RX_TCPHDR_LEN)
+
+#define S_RX_IPHDR_LEN    6
+#define M_RX_IPHDR_LEN    0x3FF
+#define V_RX_IPHDR_LEN(x) ((x) << S_RX_IPHDR_LEN)
+#define G_RX_IPHDR_LEN(x) (((x) >> S_RX_IPHDR_LEN) & M_RX_IPHDR_LEN)
+
 struct cpl_trace_pkt {
 	u8 opcode;
 	u8 intf;
@@ -634,6 +689,17 @@ struct cpl_fw6_msg {
 /* cpl_fw6_msg.type values */
 enum {
 	FW6_TYPE_CMD_RPL = 0,
+	FW6_TYPE_WR_RPL = 1,
+	FW6_TYPE_CQE = 2,
+	FW6_TYPE_OFLD_CONNECTION_WR_RPL = 3,
+};
+
+struct cpl_fw6_msg_ofld_connection_wr_rpl {
+	__u64   cookie;
+	__be32  tid;    /* or atid in case of active failure */
+	__u8    t_state;
+	__u8    retval;
+	__u8    rsvd[2];
 };
 
 enum {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 75393f5cff41..83ec5f7844ac 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1064,4 +1064,41 @@
 #define  ADDRESS(x)     ((x) << ADDRESS_SHIFT)
 
 #define XGMAC_PORT_INT_CAUSE 0x10dc
+
+#define A_TP_TX_MOD_QUEUE_REQ_MAP 0x7e28
+
+#define A_TP_TX_MOD_CHANNEL_WEIGHT 0x7e34
+
+#define S_TX_MOD_QUEUE_REQ_MAP    0
+#define M_TX_MOD_QUEUE_REQ_MAP    0xffffU
+#define V_TX_MOD_QUEUE_REQ_MAP(x) ((x) << S_TX_MOD_QUEUE_REQ_MAP)
+
+#define A_TP_TX_MOD_QUEUE_WEIGHT0 0x7e30
+
+#define S_TX_MODQ_WEIGHT3    24
+#define M_TX_MODQ_WEIGHT3    0xffU
+#define V_TX_MODQ_WEIGHT3(x) ((x) << S_TX_MODQ_WEIGHT3)
+
+#define S_TX_MODQ_WEIGHT2    16
+#define M_TX_MODQ_WEIGHT2    0xffU
+#define V_TX_MODQ_WEIGHT2(x) ((x) << S_TX_MODQ_WEIGHT2)
+
+#define S_TX_MODQ_WEIGHT1    8
+#define M_TX_MODQ_WEIGHT1    0xffU
+#define V_TX_MODQ_WEIGHT1(x) ((x) << S_TX_MODQ_WEIGHT1)
+
+#define S_TX_MODQ_WEIGHT0    0
+#define M_TX_MODQ_WEIGHT0    0xffU
+#define V_TX_MODQ_WEIGHT0(x) ((x) << S_TX_MODQ_WEIGHT0)
+
+#define A_TP_TX_SCHED_HDR 0x23
+
+#define A_TP_TX_SCHED_FIFO 0x24
+
+#define A_TP_TX_SCHED_PCMD 0x25
+
+#define S_PORT    1
+#define V_PORT(x) ((x) << S_PORT)
+#define F_PORT    V_PORT(1U)
+
 #endif /* __T4_REGS_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 0abc864cdd3a..a0dcccd846c9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -35,6 +35,45 @@
 #ifndef _T4FW_INTERFACE_H_
 #define _T4FW_INTERFACE_H_
 
+enum fw_retval {
+	FW_SUCCESS		= 0,	/* completed sucessfully */
+	FW_EPERM		= 1,	/* operation not permitted */
+	FW_ENOENT		= 2,	/* no such file or directory */
+	FW_EIO			= 5,	/* input/output error; hw bad */
+	FW_ENOEXEC		= 8,	/* exec format error; inv microcode */
+	FW_EAGAIN		= 11,	/* try again */
+	FW_ENOMEM		= 12,	/* out of memory */
+	FW_EFAULT		= 14,	/* bad address; fw bad */
+	FW_EBUSY		= 16,	/* resource busy */
+	FW_EEXIST		= 17,	/* file exists */
+	FW_EINVAL		= 22,	/* invalid argument */
+	FW_ENOSPC		= 28,	/* no space left on device */
+	FW_ENOSYS		= 38,	/* functionality not implemented */
+	FW_EPROTO		= 71,	/* protocol error */
+	FW_EADDRINUSE		= 98,	/* address already in use */
+	FW_EADDRNOTAVAIL	= 99,	/* cannot assigned requested address */
+	FW_ENETDOWN		= 100,	/* network is down */
+	FW_ENETUNREACH		= 101,	/* network is unreachable */
+	FW_ENOBUFS		= 105,	/* no buffer space available */
+	FW_ETIMEDOUT		= 110,	/* timeout */
+	FW_EINPROGRESS		= 115,	/* fw internal */
+	FW_SCSI_ABORT_REQUESTED	= 128,	/* */
+	FW_SCSI_ABORT_TIMEDOUT	= 129,	/* */
+	FW_SCSI_ABORTED		= 130,	/* */
+	FW_SCSI_CLOSE_REQUESTED	= 131,	/* */
+	FW_ERR_LINK_DOWN	= 132,	/* */
+	FW_RDEV_NOT_READY	= 133,	/* */
+	FW_ERR_RDEV_LOST	= 134,	/* */
+	FW_ERR_RDEV_LOGO	= 135,	/* */
+	FW_FCOE_NO_XCHG		= 136,	/* */
+	FW_SCSI_RSP_ERR		= 137,	/* */
+	FW_ERR_RDEV_IMPL_LOGO	= 138,	/* */
+	FW_SCSI_UNDER_FLOW_ERR  = 139,	/* */
+	FW_SCSI_OVER_FLOW_ERR   = 140,	/* */
+	FW_SCSI_DDP_ERR		= 141,	/* DDP error*/
+	FW_SCSI_TASK_ERR	= 142,	/* No SCSI tasks available */
+};
+
 #define FW_T4VF_SGE_BASE_ADDR      0x0000
 #define FW_T4VF_MPS_BASE_ADDR      0x0100
 #define FW_T4VF_PL_BASE_ADDR       0x0200
@@ -46,6 +85,7 @@ enum fw_wr_opcodes {
 	FW_ULPTX_WR                    = 0x04,
 	FW_TP_WR                       = 0x05,
 	FW_ETH_TX_PKT_WR               = 0x08,
+	FW_OFLD_CONNECTION_WR          = 0x2f,
 	FW_FLOWC_WR                    = 0x0a,
 	FW_OFLD_TX_DATA_WR             = 0x0b,
 	FW_CMD_WR                      = 0x10,
@@ -81,6 +121,282 @@ struct fw_wr_hdr {
 #define FW_WR_LEN16(x)	((x) << 0)
 
 #define HW_TPL_FR_MT_PR_IV_P_FC         0X32B
+#define HW_TPL_FR_MT_PR_OV_P_FC         0X327
+
+/* 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;
@@ -100,6 +416,108 @@ struct fw_eth_tx_pkt_wr {
 	__be64 r3;
 };
 
+struct fw_ofld_connection_wr {
+	__be32 op_compl;
+	__be32 len16_pkd;
+	__u64  cookie;
+	__be64 r2;
+	__be64 r3;
+	struct fw_ofld_connection_le {
+		__be32 version_cpl;
+		__be32 filter;
+		__be32 r1;
+		__be16 lport;
+		__be16 pport;
+		union fw_ofld_connection_leip {
+			struct fw_ofld_connection_le_ipv4 {
+				__be32 pip;
+				__be32 lip;
+				__be64 r0;
+				__be64 r1;
+				__be64 r2;
+			} ipv4;
+			struct fw_ofld_connection_le_ipv6 {
+				__be64 pip_hi;
+				__be64 pip_lo;
+				__be64 lip_hi;
+				__be64 lip_lo;
+			} ipv6;
+		} u;
+	} le;
+	struct fw_ofld_connection_tcb {
+		__be32 t_state_to_astid;
+		__be16 cplrxdataack_cplpassacceptrpl;
+		__be16 rcv_adv;
+		__be32 rcv_nxt;
+		__be32 tx_max;
+		__be64 opt0;
+		__be32 opt2;
+		__be32 r1;
+		__be64 r2;
+		__be64 r3;
+	} tcb;
+};
+
+#define S_FW_OFLD_CONNECTION_WR_VERSION                31
+#define M_FW_OFLD_CONNECTION_WR_VERSION                0x1
+#define V_FW_OFLD_CONNECTION_WR_VERSION(x)     \
+	((x) << S_FW_OFLD_CONNECTION_WR_VERSION)
+#define G_FW_OFLD_CONNECTION_WR_VERSION(x)     \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_VERSION) & \
+	M_FW_OFLD_CONNECTION_WR_VERSION)
+#define F_FW_OFLD_CONNECTION_WR_VERSION        \
+	V_FW_OFLD_CONNECTION_WR_VERSION(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPL    30
+#define M_FW_OFLD_CONNECTION_WR_CPL    0x1
+#define V_FW_OFLD_CONNECTION_WR_CPL(x) ((x) << S_FW_OFLD_CONNECTION_WR_CPL)
+#define G_FW_OFLD_CONNECTION_WR_CPL(x) \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPL) & M_FW_OFLD_CONNECTION_WR_CPL)
+#define F_FW_OFLD_CONNECTION_WR_CPL    V_FW_OFLD_CONNECTION_WR_CPL(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_T_STATE                28
+#define M_FW_OFLD_CONNECTION_WR_T_STATE                0xf
+#define V_FW_OFLD_CONNECTION_WR_T_STATE(x)     \
+	((x) << S_FW_OFLD_CONNECTION_WR_T_STATE)
+#define G_FW_OFLD_CONNECTION_WR_T_STATE(x)     \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_T_STATE) & \
+	M_FW_OFLD_CONNECTION_WR_T_STATE)
+
+#define S_FW_OFLD_CONNECTION_WR_RCV_SCALE      24
+#define M_FW_OFLD_CONNECTION_WR_RCV_SCALE      0xf
+#define V_FW_OFLD_CONNECTION_WR_RCV_SCALE(x)   \
+	((x) << S_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+#define G_FW_OFLD_CONNECTION_WR_RCV_SCALE(x)   \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_RCV_SCALE) & \
+	M_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+
+#define S_FW_OFLD_CONNECTION_WR_ASTID          0
+#define M_FW_OFLD_CONNECTION_WR_ASTID          0xffffff
+#define V_FW_OFLD_CONNECTION_WR_ASTID(x)       \
+	((x) << S_FW_OFLD_CONNECTION_WR_ASTID)
+#define G_FW_OFLD_CONNECTION_WR_ASTID(x)       \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_ASTID) & M_FW_OFLD_CONNECTION_WR_ASTID)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   15
+#define M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x)        \
+	((x) << S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define G_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x)        \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK) & \
+	M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK   \
+	V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       14
+#define M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x)    \
+	((x) << S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define G_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x)    \
+	(((x) >> S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL) & \
+	M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define F_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL       \
+	V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(1U)
+
 enum fw_flowc_mnem {
 	FW_FLOWC_MNEM_PFNVFN,		/* PFN [15:8] VFN [7:0] */
 	FW_FLOWC_MNEM_CH,
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 9a9de51ecc91..8b3d0512a46b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -1338,6 +1338,7 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u32 dword_field;
 	int err;
 	u8 byte_field;
 
@@ -1372,10 +1373,18 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
 	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
 
+	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
+	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
+		param->steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+	} else {
+		MLX4_GET(byte_field, outbox, INIT_HCA_UC_STEERING_OFFSET);
+		if (byte_field & 0x8)
+			param->steering_mode = MLX4_STEERING_MODE_B0;
+		else
+			param->steering_mode = MLX4_STEERING_MODE_A0;
+	}
 	/* steering attributes */
-	if (dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
-
+	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
 		MLX4_GET(param->log_mc_entry_sz, outbox,
 			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 2c2e7ade2a34..dbf2f69cc59f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -172,6 +172,7 @@ struct mlx4_init_hca_param {
 	u8  log_uar_sz;
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  fs_hash_enable_bits;
+	u8  steering_mode; /* for QUERY_HCA */
 	u64 dev_cap_enabled;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index b2acbe7706a3..e1bafffbc3b1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -85,15 +85,15 @@ static int probe_vf;
 module_param(probe_vf, int, 0644);
 MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
 
-int mlx4_log_num_mgm_entry_size = 10;
+int mlx4_log_num_mgm_entry_size = MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
 module_param_named(log_num_mgm_entry_size,
 			mlx4_log_num_mgm_entry_size, int, 0444);
 MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
 					 " of qp per mcg, for example:"
-					 " 10 gives 248.range: 9<="
+					 " 10 gives 248.range: 7 <="
 					 " log_num_mgm_entry_size <= 12."
-					 " Not in use with device managed"
-					 " flow steering");
+					 " To activate device managed"
+					 " flow steering when available, set to -1");
 
 static bool enable_64b_cqe_eqe;
 module_param(enable_64b_cqe_eqe, bool, 0444);
@@ -281,28 +281,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 
-	if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
-		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
-		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
-		dev->caps.fs_log_max_ucast_qp_range_size =
-			dev_cap->fs_log_max_ucast_qp_range_size;
-	} else {
-		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
-		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
-			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
-		} else {
-			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
-
-			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
-			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
-				mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
-						"set to use B0 steering. Falling back to A0 steering mode.\n");
-		}
-		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
-	}
-	mlx4_dbg(dev, "Steering mode is: %s\n",
-		 mlx4_steering_mode_str(dev->caps.steering_mode));
-
 	/* Sense port always allowed on supported devices for ConnectX-1 and -2 */
 	if (mlx4_priv(dev)->pci_dev_data & MLX4_PCI_DEV_FORCE_SENSE_PORT)
 		dev->caps.flags |= MLX4_DEV_CAP_FLAG_SENSE_SUPPORT;
@@ -493,6 +471,23 @@ int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
 }
 EXPORT_SYMBOL(mlx4_is_slave_active);
 
+static void slave_adjust_steering_mode(struct mlx4_dev *dev,
+				       struct mlx4_dev_cap *dev_cap,
+				       struct mlx4_init_hca_param *hca_param)
+{
+	dev->caps.steering_mode = hca_param->steering_mode;
+	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+		dev->caps.fs_log_max_ucast_qp_range_size =
+			dev_cap->fs_log_max_ucast_qp_range_size;
+	} else
+		dev->caps.num_qp_per_mgm =
+			4 * ((1 << hca_param->log_mc_entry_sz)/16 - 2);
+
+	mlx4_dbg(dev, "Steering mode is: %s\n",
+		 mlx4_steering_mode_str(dev->caps.steering_mode));
+}
+
 static int mlx4_slave_cap(struct mlx4_dev *dev)
 {
 	int			   err;
@@ -635,6 +630,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		dev->caps.cqe_size   = 32;
 	}
 
+	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
+
 	return 0;
 
 err_mem:
@@ -1321,6 +1318,59 @@ static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
 	}
 }
 
+static int choose_log_fs_mgm_entry_size(int qp_per_entry)
+{
+	int i = MLX4_MIN_MGM_LOG_ENTRY_SIZE;
+
+	for (i = MLX4_MIN_MGM_LOG_ENTRY_SIZE; i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE;
+	      i++) {
+		if (qp_per_entry <= 4 * ((1 << i) / 16 - 2))
+			break;
+	}
+
+	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
+}
+
+static void choose_steering_mode(struct mlx4_dev *dev,
+				 struct mlx4_dev_cap *dev_cap)
+{
+	if (mlx4_log_num_mgm_entry_size == -1 &&
+	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
+	    (!mlx4_is_mfunc(dev) ||
+	     (dev_cap->fs_max_num_qp_per_entry >= (num_vfs + 1))) &&
+	    choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry) >=
+		MLX4_MIN_MGM_LOG_ENTRY_SIZE) {
+		dev->oper_log_mgm_entry_size =
+			choose_log_fs_mgm_entry_size(dev_cap->fs_max_num_qp_per_entry);
+		dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+		dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+		dev->caps.fs_log_max_ucast_qp_range_size =
+			dev_cap->fs_log_max_ucast_qp_range_size;
+	} else {
+		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
+		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
+		else {
+			dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
+
+			if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
+			    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+				mlx4_warn(dev, "Must have both UC_STEER and MC_STEER flags "
+					  "set to use B0 steering. Falling back to A0 steering mode.\n");
+		}
+		dev->oper_log_mgm_entry_size =
+			mlx4_log_num_mgm_entry_size > 0 ?
+			mlx4_log_num_mgm_entry_size :
+			MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE;
+		dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
+	}
+	mlx4_dbg(dev, "Steering mode is: %s, oper_log_mgm_entry_size = %d, "
+		 "modparam log_num_mgm_entry_size = %d\n",
+		 mlx4_steering_mode_str(dev->caps.steering_mode),
+		 dev->oper_log_mgm_entry_size,
+		 mlx4_log_num_mgm_entry_size);
+}
+
 static int mlx4_init_hca(struct mlx4_dev *dev)
 {
 	struct mlx4_priv	  *priv = mlx4_priv(dev);
@@ -1360,6 +1410,8 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			goto err_stop_fw;
 		}
 
+		choose_steering_mode(dev, &dev_cap);
+
 		if (mlx4_is_master(dev))
 			mlx4_parav_master_pf_caps(dev);
 
@@ -2452,6 +2504,17 @@ static int __init mlx4_verify_params(void)
 		port_type_array[0] = true;
 	}
 
+	if (mlx4_log_num_mgm_entry_size != -1 &&
+	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
+		pr_warning("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not "
+			   "in legal range (-1 or %d..%d)\n",
+			   mlx4_log_num_mgm_entry_size,
+			   MLX4_MIN_MGM_LOG_ENTRY_SIZE,
+			   MLX4_MAX_MGM_LOG_ENTRY_SIZE);
+		return -1;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index e151c21baf2b..1ee4db3c6400 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -54,12 +54,7 @@ struct mlx4_mgm {
 
 int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
 {
-	if (dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED)
-		return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE;
-	else
-		return min((1 << mlx4_log_num_mgm_entry_size),
-			   MLX4_MAX_MGM_ENTRY_SIZE);
+	return 1 << dev->oper_log_mgm_entry_size;
 }
 
 int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 1cf42036d7bb..116c5c29d2d1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -94,8 +94,10 @@ enum {
 };
 
 enum {
-	MLX4_MAX_MGM_ENTRY_SIZE = 0x1000,
-	MLX4_MAX_QP_PER_MGM	= 4 * (MLX4_MAX_MGM_ENTRY_SIZE / 16 - 2),
+	MLX4_DEFAULT_MGM_LOG_ENTRY_SIZE = 10,
+	MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
+	MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
+	MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
 	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index b05705f50f0f..561ed2a22a17 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3071,6 +3071,7 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
 	struct list_head *rlist = &tracker->slave_list[slave].res_list[RES_MAC];
 	int err;
+	int qpn;
 	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
 	struct _rule_hw  *rule_header;
 	int header_id;
@@ -3080,13 +3081,21 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 		return -EOPNOTSUPP;
 
 	ctrl = (struct mlx4_net_trans_rule_hw_ctrl *)inbox->buf;
+	qpn = be32_to_cpu(ctrl->qpn) & 0xffffff;
+	err = get_res(dev, slave, qpn, RES_QP, NULL);
+	if (err) {
+		pr_err("Steering rule with qpn 0x%x rejected.\n", qpn);
+		return err;
+	}
 	rule_header = (struct _rule_hw *)(ctrl + 1);
 	header_id = map_hw_to_sw_id(be16_to_cpu(rule_header->id));
 
 	switch (header_id) {
 	case MLX4_NET_TRANS_RULE_ID_ETH:
-		if (validate_eth_header_mac(slave, rule_header, rlist))
-			return -EINVAL;
+		if (validate_eth_header_mac(slave, rule_header, rlist)) {
+			err = -EINVAL;
+			goto err_put;
+		}
 		break;
 	case MLX4_NET_TRANS_RULE_ID_IB:
 		break;
@@ -3094,14 +3103,17 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 	case MLX4_NET_TRANS_RULE_ID_TCP:
 	case MLX4_NET_TRANS_RULE_ID_UDP:
 		pr_warn("Can't attach FS rule without L2 headers, adding L2 header.\n");
-		if (add_eth_header(dev, slave, inbox, rlist, header_id))
-			return -EINVAL;
+		if (add_eth_header(dev, slave, inbox, rlist, header_id)) {
+			err = -EINVAL;
+			goto err_put;
+		}
 		vhcr->in_modifier +=
 			sizeof(struct mlx4_net_trans_rule_hw_eth) >> 2;
 		break;
 	default:
 		pr_err("Corrupted mailbox.\n");
-		return -EINVAL;
+		err = -EINVAL;
+		goto err_put;
 	}
 
 	err = mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
@@ -3109,16 +3121,18 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 			   MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
 			   MLX4_CMD_NATIVE);
 	if (err)
-		return err;
+		goto err_put;
 
 	err = add_res_range(dev, slave, vhcr->out_param, 1, RES_FS_RULE, 0);
 	if (err) {
 		mlx4_err(dev, "Fail to add flow steering resources.\n ");
 		/* detach rule*/
 		mlx4_cmd(dev, vhcr->out_param, 0, 0,
-			 MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
+			 MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
 			 MLX4_CMD_NATIVE);
 	}
+err_put:
+	put_res(dev, slave, qpn, RES_QP);
 	return err;
 }