bnx2x: VF RSS support - PF side

This patch adds support for Receive Side Scaling for queues of
Virtual Functions on the PF side. This includes support for the
requests for multiple queues from VF drivers, configuration of the
HW for multiple queues per VF, and support for rss configuration
of said queues.

Signed-off-by: Ariel Elior <ariele@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 513 insertions, 144 deletions

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 3e77a1b1a44a..0c338026ce01 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -825,15 +825,13 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp)
 #define BD_UNMAP_LEN(bd)		(le16_to_cpu((bd)->nbytes))
 
 #define BNX2X_DB_MIN_SHIFT		3	/* 8 bytes */
-#define BNX2X_DB_SHIFT			7	/* 128 bytes*/
+#define BNX2X_DB_SHIFT			3	/* 8 bytes*/
 #if (BNX2X_DB_SHIFT < BNX2X_DB_MIN_SHIFT)
 #error "Min DB doorbell stride is 8"
 #endif
-#define DPM_TRIGER_TYPE			0x40
 #define DOORBELL(bp, cid, val) \
 	do { \
-		writel((u32)(val), bp->doorbells + (bp->db_size * (cid)) + \
-		       DPM_TRIGER_TYPE); \
+		writel((u32)(val), bp->doorbells + (bp->db_size * (cid))); \
 	} while (0)
 
 /* TX CSUM helpers */
@@ -1100,13 +1098,27 @@ struct bnx2x_port {
 extern struct workqueue_struct *bnx2x_wq;
 
 #define BNX2X_MAX_NUM_OF_VFS	64
-#define BNX2X_VF_CID_WND	0
+#define BNX2X_VF_CID_WND	4 /* log num of queues per VF. HW config. */
 #define BNX2X_CIDS_PER_VF	(1 << BNX2X_VF_CID_WND)
-#define BNX2X_CLIENTS_PER_VF	1
-#define BNX2X_FIRST_VF_CID	256
+
+/* We need to reserve doorbell addresses for all VF and queue combinations */
 #define BNX2X_VF_CIDS		(BNX2X_MAX_NUM_OF_VFS * BNX2X_CIDS_PER_VF)
+
+/* The doorbell is configured to have the same number of CIDs for PFs and for
+ * VFs. For this reason the PF CID zone is as large as the VF zone.
+ */
+#define BNX2X_FIRST_VF_CID	BNX2X_VF_CIDS
+#define BNX2X_MAX_NUM_VF_QUEUES	64
 #define BNX2X_VF_ID_INVALID	0xFF
 
+/* the number of VF CIDS multiplied by the amount of bytes reserved for each
+ * cid must not exceed the size of the VF doorbell
+ */
+#define BNX2X_VF_BAR_SIZE	512
+#if (BNX2X_VF_BAR_SIZE < BNX2X_CIDS_PER_VF * (1 << BNX2X_DB_SHIFT))
+#error "VF doorbell bar size is 512"
+#endif
+
 /*
  * The total number of L2 queues, MSIX vectors and HW contexts (CIDs) is
  * control by the number of fast-path status blocks supported by the
@@ -1650,10 +1662,10 @@ struct bnx2x {
 	dma_addr_t			fw_stats_data_mapping;
 	int				fw_stats_data_sz;
 
-	/* For max 196 cids (64*3 + non-eth), 32KB ILT page size and 1KB
+	/* For max 1024 cids (VF RSS), 32KB ILT page size and 1KB
 	 * context size we need 8 ILT entries.
 	 */
-#define ILT_MAX_L2_LINES	8
+#define ILT_MAX_L2_LINES	32
 	struct hw_context	context[ILT_MAX_L2_LINES];
 
 	struct bnx2x_ilt	*ilt;
@@ -1869,7 +1881,7 @@ extern int num_queues;
 #define FUNC_FLG_TPA		0x0008
 #define FUNC_FLG_SPQ		0x0010
 #define FUNC_FLG_LEADING	0x0020	/* PF only */
-
+#define FUNC_FLG_LEADING_STATS	0x0040
 struct bnx2x_func_init_params {
 	/* dma */
 	dma_addr_t	fw_stat_map;	/* valid iff FUNC_FLG_STATS */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 2e90868a9276..e7400d9d60c4 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4784,6 +4784,11 @@ int bnx2x_resume(struct pci_dev *pdev)
 void bnx2x_set_ctx_validation(struct bnx2x *bp, struct eth_context *cxt,
 			      u32 cid)
 {
+	if (!cxt) {
+		BNX2X_ERR("bad context pointer %p\n", cxt);
+		return;
+	}
+
 	/* ustorm cxt validation */
 	cxt->ustorm_ag_context.cdu_usage =
 		CDU_RSRVD_VALUE_TYPE_A(HW_CID(bp, cid),
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 17f117c1d8d2..5729aa7be1d0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -6893,7 +6893,7 @@ static int bnx2x_init_hw_common(struct bnx2x *bp)
 		bnx2x_init_block(bp, BLOCK_TM, PHASE_COMMON);
 
 	bnx2x_init_block(bp, BLOCK_DORQ, PHASE_COMMON);
-	REG_WR(bp, DORQ_REG_DPM_CID_OFST, BNX2X_DB_SHIFT);
+
 	if (!CHIP_REV_IS_SLOW(bp))
 		/* enable hw interrupt from doorbell Q */
 		REG_WR(bp, DORQ_REG_DORQ_INT_MASK, 0);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 8e627b886d7b..5ecf267dc4cc 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -6335,6 +6335,7 @@
 #define PCI_ID_VAL2					0x438
 #define PCI_ID_VAL3					0x43c
 
+#define GRC_CONFIG_REG_VF_MSIX_CONTROL		    0x61C
 #define GRC_CONFIG_REG_PF_INIT_VF		0x624
 #define GRC_CR_PF_INIT_VF_PF_FIRST_VF_NUM_MASK	0xf
 /* First VF_NUM for PF is encoded in this register.
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 1d46b68fb766..9fbeee522d2c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4416,6 +4416,16 @@ void bnx2x_init_rss_config_obj(struct bnx2x *bp,
 	rss_obj->config_rss = bnx2x_setup_rss;
 }
 
+int validate_vlan_mac(struct bnx2x *bp,
+		      struct bnx2x_vlan_mac_obj *vlan_mac)
+{
+	if (!vlan_mac->get_n_elements) {
+		BNX2X_ERR("vlan mac object was not intialized\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /********************** Queue state object ***********************************/
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 533a3abd8c82..658f4e33abf9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -1407,4 +1407,6 @@ int bnx2x_config_rss(struct bnx2x *bp,
 void bnx2x_get_rss_ind_table(struct bnx2x_rss_config_obj *rss_obj,
 			     u8 *ind_table);
 
+int validate_vlan_mac(struct bnx2x *bp,
+		      struct bnx2x_vlan_mac_obj *vlan_mac);
 #endif /* BNX2X_SP_VERBS */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index fbc026c4cab2..73731eb68f2a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -170,6 +170,11 @@ enum bnx2x_vfop_qteardown_state {
 	   BNX2X_VFOP_QTEARDOWN_DONE
 };
 
+enum bnx2x_vfop_rss_state {
+	   BNX2X_VFOP_RSS_CONFIG,
+	   BNX2X_VFOP_RSS_DONE
+};
+
 #define bnx2x_vfop_reset_wq(vf)	atomic_set(&vf->op_in_progress, 0)
 
 void bnx2x_vfop_qctor_dump_tx(struct bnx2x *bp, struct bnx2x_virtf *vf,
@@ -265,11 +270,6 @@ void bnx2x_vfop_qctor_prep(struct bnx2x *bp,
 	__set_bit(BNX2X_Q_FLG_TX_SEC, &setup_p->flags);
 	__set_bit(BNX2X_Q_FLG_ANTI_SPOOF, &setup_p->flags);
 
-	if (vfq_is_leading(q)) {
-		__set_bit(BNX2X_Q_FLG_LEADING_RSS, &setup_p->flags);
-		__set_bit(BNX2X_Q_FLG_MCAST, &setup_p->flags);
-	}
-
 	/* Setup-op rx parameters */
 	if (test_bit(BNX2X_Q_TYPE_HAS_RX, &q_type)) {
 		struct bnx2x_rxq_setup_params *rxq_p = &setup_p->rxq_params;
@@ -398,7 +398,11 @@ static void bnx2x_vfop_qdtor(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		    BNX2X_Q_LOGICAL_STATE_STOPPED) {
 			DP(BNX2X_MSG_IOV,
 			   "Entered qdtor but queue was already stopped. Aborting gracefully\n");
-			goto op_done;
+
+			/* next state */
+			vfop->state = BNX2X_VFOP_QDTOR_DONE;
+
+			bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 		}
 
 		/* next state */
@@ -432,8 +436,10 @@ op_err:
 op_done:
 	case BNX2X_VFOP_QDTOR_DONE:
 		/* invalidate the context */
-		qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
-		qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+		if (qdtor->cxt) {
+			qdtor->cxt->ustorm_ag_context.cdu_usage = 0;
+			qdtor->cxt->xstorm_ag_context.cdu_reserved = 0;
+		}
 		bnx2x_vfop_end(bp, vf, vfop);
 		return;
 	default:
@@ -465,7 +471,8 @@ static int bnx2x_vfop_qdtor_cmd(struct bnx2x *bp,
 		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdtor,
 					     cmd->block);
 	}
-	DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop.\n", vf->abs_vfid);
+	DP(BNX2X_MSG_IOV, "VF[%d] failed to add a vfop. rc %d\n",
+	   vf->abs_vfid, vfop->rc);
 	return -ENOMEM;
 }
 
@@ -474,10 +481,18 @@ bnx2x_vf_set_igu_info(struct bnx2x *bp, u8 igu_sb_id, u8 abs_vfid)
 {
 	struct bnx2x_virtf *vf = bnx2x_vf_by_abs_fid(bp, abs_vfid);
 	if (vf) {
+		/* the first igu entry belonging to VFs of this PF */
+		if (!BP_VFDB(bp)->first_vf_igu_entry)
+			BP_VFDB(bp)->first_vf_igu_entry = igu_sb_id;
+
+		/* the first igu entry belonging to this VF */
 		if (!vf_sb_count(vf))
 			vf->igu_base_id = igu_sb_id;
+
 		++vf_sb_count(vf);
+		++vf->sb_count;
 	}
+	BP_VFDB(bp)->vf_sbs_pool++;
 }
 
 /* VFOP MAC/VLAN helpers */
@@ -733,6 +748,7 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
 				     int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -752,6 +768,9 @@ static int bnx2x_vfop_mac_delall_cmd(struct bnx2x *bp,
 		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
 
 		/* set extra args */
@@ -772,6 +791,7 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
 			    int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -794,6 +814,9 @@ int bnx2x_vfop_mac_list_cmd(struct bnx2x *bp,
 		bnx2x_vfop_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, mac_obj);
 
 		/* set extra args */
@@ -814,6 +837,7 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 			    int qid, u16 vid, bool add)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -834,6 +858,9 @@ int bnx2x_vfop_vlan_set_cmd(struct bnx2x *bp,
 		ramrod->user_req.u.vlan.vlan = vid;
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -853,6 +880,7 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
 			       int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -872,6 +900,9 @@ static int bnx2x_vfop_vlan_delall_cmd(struct bnx2x *bp,
 		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -892,6 +923,7 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
 			     int qid, bool drv_only)
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+	int rc;
 
 	if (vfop) {
 		struct bnx2x_vfop_args_filters filters = {
@@ -911,6 +943,9 @@ int bnx2x_vfop_vlan_list_cmd(struct bnx2x *bp,
 		bnx2x_vfop_vlan_mac_prep_ramrod(ramrod, &flags);
 
 		/* set object */
+		rc = validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj));
+		if (rc)
+			return rc;
 		ramrod->vlan_mac_obj = &bnx2x_vfq(vf, qid, vlan_obj);
 
 		/* set extra args */
@@ -1021,21 +1056,25 @@ static void bnx2x_vfop_qflr(struct bnx2x *bp, struct bnx2x_virtf *vf)
 	case BNX2X_VFOP_QFLR_CLR_VLAN:
 		/* vlan-clear-all: driver-only, don't consume credit */
 		vfop->state = BNX2X_VFOP_QFLR_CLR_MAC;
-		vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid, true);
+		if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, vlan_obj)))
+			vfop->rc = bnx2x_vfop_vlan_delall_cmd(bp, vf, &cmd, qid,
+							      true);
 		if (vfop->rc)
 			goto op_err;
-		return;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 
 	case BNX2X_VFOP_QFLR_CLR_MAC:
 		/* mac-clear-all: driver only consume credit */
 		vfop->state = BNX2X_VFOP_QFLR_TERMINATE;
-		vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid, true);
+		if (!validate_vlan_mac(bp, &bnx2x_vfq(vf, qid, mac_obj)))
+			vfop->rc = bnx2x_vfop_mac_delall_cmd(bp, vf, &cmd, qid,
+							     true);
 		DP(BNX2X_MSG_IOV,
 		   "VF[%d] vfop->rc after bnx2x_vfop_mac_delall_cmd was %d",
 		   vf->abs_vfid, vfop->rc);
 		if (vfop->rc)
 			goto op_err;
-		return;
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_CONT);
 
 	case BNX2X_VFOP_QFLR_TERMINATE:
 		qstate = &vfop->op_p->qctor.qstate;
@@ -1332,10 +1371,13 @@ int bnx2x_vfop_qdown_cmd(struct bnx2x *bp,
 {
 	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
 
+	/* for non leading queues skip directly to qdown sate */
 	if (vfop) {
 		vfop->args.qx.qid = qid;
-		bnx2x_vfop_opset(BNX2X_VFOP_QTEARDOWN_RXMODE,
-				 bnx2x_vfop_qdown, cmd->done);
+		bnx2x_vfop_opset(qid == LEADING_IDX ?
+				 BNX2X_VFOP_QTEARDOWN_RXMODE :
+				 BNX2X_VFOP_QTEARDOWN_QDTOR, bnx2x_vfop_qdown,
+				 cmd->done);
 		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_qdown,
 					     cmd->block);
 	}
@@ -1488,15 +1530,16 @@ int bnx2x_vf_flr_clnup_epilog(struct bnx2x *bp, u8 abs_vfid)
  * both known
  */
 static void
-bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
+bnx2x_iov_static_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
+	struct vf_pf_resc_request *resc = &vf->alloc_resc;
 	u16 vlan_count = 0;
 
 	/* will be set only during VF-ACQUIRE */
 	resc->num_rxqs = 0;
 	resc->num_txqs = 0;
 
-	/* no credit calculcis for macs (just yet) */
+	/* no credit calculations for macs (just yet) */
 	resc->num_mac_filters = 1;
 
 	/* divvy up vlan rules */
@@ -1508,13 +1551,14 @@ bnx2x_iov_static_resc(struct bnx2x *bp, struct vf_pf_resc_request *resc)
 	resc->num_mc_filters = 0;
 
 	/* num_sbs already set */
+	resc->num_sbs = vf->sb_count;
 }
 
 /* FLR routines: */
 static void bnx2x_vf_free_resc(struct bnx2x *bp, struct bnx2x_virtf *vf)
 {
 	/* reset the state variables */
-	bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+	bnx2x_iov_static_resc(bp, vf);
 	vf->state = VF_FREE;
 }
 
@@ -1734,8 +1778,7 @@ void bnx2x_iov_init_dq(struct bnx2x *bp)
 	/* The VF doorbell size  0 - *B, 4 - 128B. We set it here to match
 	 * the Pf doorbell size although the 2 are independent.
 	 */
-	REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST,
-	       BNX2X_DB_SHIFT - BNX2X_DB_MIN_SHIFT);
+	REG_WR(bp, DORQ_REG_VF_NORM_CID_OFST, 3);
 
 	/* No security checks for now -
 	 * configure single rule (out of 16) mask = 0x1, value = 0x0,
@@ -1802,7 +1845,7 @@ bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 {
 	int sb_id;
 	u32 val;
-	u8 fid;
+	u8 fid, current_pf = 0;
 
 	/* IGU in normal mode - read CAM */
 	for (sb_id = 0; sb_id < IGU_REG_MAPPING_MEMORY_SIZE; sb_id++) {
@@ -1810,16 +1853,18 @@ bnx2x_get_vf_igu_cam_info(struct bnx2x *bp)
 		if (!(val & IGU_REG_MAPPING_MEMORY_VALID))
 			continue;
 		fid = GET_FIELD((val), IGU_REG_MAPPING_MEMORY_FID);
-		if (!(fid & IGU_FID_ENCODE_IS_PF))
+		if (fid & IGU_FID_ENCODE_IS_PF)
+			current_pf = fid & IGU_FID_PF_NUM_MASK;
+		else if (current_pf == BP_ABS_FUNC(bp))
 			bnx2x_vf_set_igu_info(bp, sb_id,
 					      (fid & IGU_FID_VF_NUM_MASK));
-
 		DP(BNX2X_MSG_IOV, "%s[%d], igu_sb_id=%d, msix=%d\n",
 		   ((fid & IGU_FID_ENCODE_IS_PF) ? "PF" : "VF"),
 		   ((fid & IGU_FID_ENCODE_IS_PF) ? (fid & IGU_FID_PF_NUM_MASK) :
 		   (fid & IGU_FID_VF_NUM_MASK)), sb_id,
 		   GET_FIELD((val), IGU_REG_MAPPING_MEMORY_VECTOR));
 	}
+	DP(BNX2X_MSG_IOV, "vf_sbs_pool is %d\n", BP_VFDB(bp)->vf_sbs_pool);
 }
 
 static void __bnx2x_iov_free_vfdb(struct bnx2x *bp)
@@ -1885,23 +1930,11 @@ static int bnx2x_sriov_info(struct bnx2x *bp, struct bnx2x_sriov *iov)
 	return 0;
 }
 
-static u8 bnx2x_iov_get_max_queue_count(struct bnx2x *bp)
-{
-	int i;
-	u8 queue_count = 0;
-
-	if (IS_SRIOV(bp))
-		for_each_vf(bp, i)
-			queue_count += bnx2x_vf(bp, i, alloc_resc.num_sbs);
-
-	return queue_count;
-}
-
 /* must be called after PF bars are mapped */
 int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
-			int num_vfs_param)
+		       int num_vfs_param)
 {
-	int err, i, qcount;
+	int err, i;
 	struct bnx2x_sriov *iov;
 	struct pci_dev *dev = bp->pdev;
 
@@ -1999,12 +2032,13 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param,
 	/* re-read the IGU CAM for VFs - index and abs_vfid must be set */
 	bnx2x_get_vf_igu_cam_info(bp);
 
-	/* get the total queue count and allocate the global queue arrays */
-	qcount = bnx2x_iov_get_max_queue_count(bp);
-
 	/* allocate the queue arrays for all VFs */
-	bp->vfdb->vfqs = kzalloc(qcount * sizeof(struct bnx2x_vf_queue),
-				 GFP_KERNEL);
+	bp->vfdb->vfqs = kzalloc(
+		BNX2X_MAX_NUM_VF_QUEUES * sizeof(struct bnx2x_vf_queue),
+		GFP_KERNEL);
+
+	DP(BNX2X_MSG_IOV, "bp->vfdb->vfqs was %p\n", bp->vfdb->vfqs);
+
 	if (!bp->vfdb->vfqs) {
 		BNX2X_ERR("failed to allocate vf queue array\n");
 		err = -ENOMEM;
@@ -2125,49 +2159,14 @@ static void bnx2x_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			     q_type);
 
 	DP(BNX2X_MSG_IOV,
-	   "initialized vf %d's queue object. func id set to %d\n",
-	   vf->abs_vfid, q->sp_obj.func_id);
-
-	/* mac/vlan objects are per queue, but only those
-	 * that belong to the leading queue are initialized
-	 */
-	if (vfq_is_leading(q)) {
-		/* mac */
-		bnx2x_init_mac_obj(bp, &q->mac_obj,
-				   cl_id, q->cid, func_id,
-				   bnx2x_vf_sp(bp, vf, mac_rdata),
-				   bnx2x_vf_sp_map(bp, vf, mac_rdata),
-				   BNX2X_FILTER_MAC_PENDING,
-				   &vf->filter_state,
-				   BNX2X_OBJ_TYPE_RX_TX,
-				   &bp->macs_pool);
-		/* vlan */
-		bnx2x_init_vlan_obj(bp, &q->vlan_obj,
-				    cl_id, q->cid, func_id,
-				    bnx2x_vf_sp(bp, vf, vlan_rdata),
-				    bnx2x_vf_sp_map(bp, vf, vlan_rdata),
-				    BNX2X_FILTER_VLAN_PENDING,
-				    &vf->filter_state,
-				    BNX2X_OBJ_TYPE_RX_TX,
-				    &bp->vlans_pool);
-
-		/* mcast */
-		bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
-				     q->cid, func_id, func_id,
-				     bnx2x_vf_sp(bp, vf, mcast_rdata),
-				     bnx2x_vf_sp_map(bp, vf, mcast_rdata),
-				     BNX2X_FILTER_MCAST_PENDING,
-				     &vf->filter_state,
-				     BNX2X_OBJ_TYPE_RX_TX);
-
-		vf->leading_rss = cl_id;
-	}
+	   "initialized vf %d's queue object. func id set to %d. cid set to 0x%x\n",
+	   vf->abs_vfid, q->sp_obj.func_id, q->cid);
 }
 
 /* called by bnx2x_nic_load */
 int bnx2x_iov_nic_init(struct bnx2x *bp)
 {
-	int vfid, qcount, i;
+	int vfid;
 
 	if (!IS_SRIOV(bp)) {
 		DP(BNX2X_MSG_IOV, "vfdb was not allocated\n");
@@ -2196,7 +2195,7 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 		   BNX2X_FIRST_VF_CID + base_vf_cid, base_cxt);
 
 		/* init statically provisioned resources */
-		bnx2x_iov_static_resc(bp, &vf->alloc_resc);
+		bnx2x_iov_static_resc(bp, vf);
 
 		/* queues are initialized during VF-ACQUIRE */
 
@@ -2232,13 +2231,12 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 	}
 
 	/* Final VF init */
-	qcount = 0;
-	for_each_vf(bp, i) {
-		struct bnx2x_virtf *vf = BP_VF(bp, i);
+	for_each_vf(bp, vfid) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vfid);
 
 		/* fill in the BDF and bars */
-		vf->bus = bnx2x_vf_bus(bp, i);
-		vf->devfn = bnx2x_vf_devfn(bp, i);
+		vf->bus = bnx2x_vf_bus(bp, vfid);
+		vf->devfn = bnx2x_vf_devfn(bp, vfid);
 		bnx2x_vf_set_bars(bp, vf);
 
 		DP(BNX2X_MSG_IOV,
@@ -2247,10 +2245,6 @@ int bnx2x_iov_nic_init(struct bnx2x *bp)
 		   (unsigned)vf->bars[0].bar, vf->bars[0].size,
 		   (unsigned)vf->bars[1].bar, vf->bars[1].size,
 		   (unsigned)vf->bars[2].bar, vf->bars[2].size);
-
-		/* set local queue arrays */
-		vf->vfqs = &bp->vfdb->vfqs[qcount];
-		qcount += bnx2x_vf(bp, i, alloc_resc.num_sbs);
 	}
 
 	return 0;
@@ -2556,6 +2550,9 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 		for_each_vfq(vf, j) {
 			struct bnx2x_vf_queue *rxq = vfq_get(vf, j);
 
+			dma_addr_t q_stats_addr =
+				vf->fw_stat_map + j * vf->stats_stride;
+
 			/* collect stats fro active queues only */
 			if (bnx2x_get_q_logical_state(bp, &rxq->sp_obj) ==
 			    BNX2X_Q_LOGICAL_STATE_STOPPED)
@@ -2563,13 +2560,13 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 
 			/* create stats query entry for this queue */
 			cur_query_entry->kind = STATS_TYPE_QUEUE;
-			cur_query_entry->index = vfq_cl_id(vf, rxq);
+			cur_query_entry->index = vfq_stat_id(vf, rxq);
 			cur_query_entry->funcID =
 				cpu_to_le16(FW_VF_HANDLE(vf->abs_vfid));
 			cur_query_entry->address.hi =
-				cpu_to_le32(U64_HI(vf->fw_stat_map));
+				cpu_to_le32(U64_HI(q_stats_addr));
 			cur_query_entry->address.lo =
-				cpu_to_le32(U64_LO(vf->fw_stat_map));
+				cpu_to_le32(U64_LO(q_stats_addr));
 			DP(BNX2X_MSG_IOV,
 			   "added address %x %x for vf %d queue %d client %d\n",
 			   cur_query_entry->address.hi,
@@ -2578,6 +2575,10 @@ void bnx2x_iov_adjust_stats_req(struct bnx2x *bp)
 			cur_query_entry++;
 			cur_data_offset += sizeof(struct per_queue_stats);
 			stats_count++;
+
+			/* all stats are coalesced to the leading queue */
+			if (vf->cfg_flags & VF_CFG_STATS_COALESCE)
+				break;
 		}
 	}
 	bp->fw_stats_req->hdr.cmd_num = bp->fw_stats_num + stats_count;
@@ -2596,6 +2597,11 @@ void bnx2x_iov_sp_task(struct bnx2x *bp)
 	for_each_vf(bp, i) {
 		struct bnx2x_virtf *vf = BP_VF(bp, i);
 
+		if (!vf) {
+			BNX2X_ERR("VF was null! skipping...\n");
+			continue;
+		}
+
 		if (!list_empty(&vf->op_list_head) &&
 		    atomic_read(&vf->op_in_progress)) {
 			DP(BNX2X_MSG_IOV, "running pending op for vf %d\n", i);
@@ -2743,7 +2749,7 @@ int bnx2x_vf_acquire(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		struct bnx2x_vf_queue *q = vfq_get(vf, i);
 
 		if (!q) {
-			DP(BNX2X_MSG_IOV, "q number %d was not allocated\n", i);
+			BNX2X_ERR("q number %d was not allocated\n", i);
 			return -EINVAL;
 		}
 
@@ -2947,6 +2953,43 @@ op_done:
 	bnx2x_vfop_end(bp, vf, vfop);
 }
 
+static void bnx2x_vfop_rss(struct bnx2x *bp, struct bnx2x_virtf *vf)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_cur(bp, vf);
+	enum bnx2x_vfop_rss_state state;
+
+	if (!vfop) {
+		BNX2X_ERR("vfop was null\n");
+		return;
+	}
+
+	state = vfop->state;
+	bnx2x_vfop_reset_wq(vf);
+
+	if (vfop->rc < 0)
+		goto op_err;
+
+	DP(BNX2X_MSG_IOV, "vf[%d] STATE: %d\n", vf->abs_vfid, state);
+
+	switch (state) {
+	case BNX2X_VFOP_RSS_CONFIG:
+		/* next state */
+		vfop->state = BNX2X_VFOP_RSS_DONE;
+		bnx2x_config_rss(bp, &vfop->op_p->rss);
+		bnx2x_vfop_finalize(vf, vfop->rc, VFOP_DONE);
+op_err:
+		BNX2X_ERR("RSS error: rc %d\n", vfop->rc);
+op_done:
+	case BNX2X_VFOP_RSS_DONE:
+		bnx2x_vfop_end(bp, vf, vfop);
+		return;
+	default:
+		bnx2x_vfop_default(state);
+	}
+op_pending:
+	return;
+}
+
 int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 			   struct bnx2x_virtf *vf,
 			   struct bnx2x_vfop_cmd *cmd)
@@ -2961,6 +3004,21 @@ int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 	return -ENOMEM;
 }
 
+int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
+		       struct bnx2x_virtf *vf,
+		       struct bnx2x_vfop_cmd *cmd)
+{
+	struct bnx2x_vfop *vfop = bnx2x_vfop_add(bp, vf);
+
+	if (vfop) {
+		bnx2x_vfop_opset(BNX2X_VFOP_RSS_CONFIG, bnx2x_vfop_rss,
+				 cmd->done);
+		return bnx2x_vfop_transition(bp, vf, bnx2x_vfop_rss,
+					     cmd->block);
+	}
+	return -ENOMEM;
+}
+
 /* VF release ~ VF close + VF release-resources
  * Release is the ultimate SW shutdown and is called whenever an
  * irrecoverable error is encountered.
@@ -2972,6 +3030,8 @@ void bnx2x_vf_release(struct bnx2x *bp, struct bnx2x_virtf *vf, bool block)
 		.block = block,
 	};
 	int rc;
+
+	DP(BNX2X_MSG_IOV, "PF releasing vf %d\n", vf->abs_vfid);
 	bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_RELEASE_VF);
 
 	rc = bnx2x_vfop_release_cmd(bp, vf, &cmd);
@@ -3000,6 +3060,12 @@ static inline void bnx2x_vf_get_bars(struct bnx2x *bp, struct bnx2x_virtf *vf,
 void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 			      enum channel_tlvs tlv)
 {
+	/* we don't lock the channel for unsupported tlvs */
+	if (!bnx2x_tlv_supported(tlv)) {
+		BNX2X_ERR("attempting to lock with unsupported tlv. Aborting\n");
+		return;
+	}
+
 	/* lock the channel */
 	mutex_lock(&vf->op_mutex);
 
@@ -3014,19 +3080,32 @@ void bnx2x_lock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 void bnx2x_unlock_vf_pf_channel(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				enum channel_tlvs expected_tlv)
 {
+	enum channel_tlvs current_tlv;
+
+	if (!vf) {
+		BNX2X_ERR("VF was %p\n", vf);
+		return;
+	}
+
+	current_tlv = vf->op_current;
+
+	/* we don't unlock the channel for unsupported tlvs */
+	if (!bnx2x_tlv_supported(expected_tlv))
+		return;
+
 	WARN(expected_tlv != vf->op_current,
 	     "lock mismatch: expected %d found %d", expected_tlv,
 	     vf->op_current);
 
+	/* record the locking op */
+	vf->op_current = CHANNEL_TLV_NONE;
+
 	/* lock the channel */
 	mutex_unlock(&vf->op_mutex);
 
 	/* log the unlock */
 	DP(BNX2X_MSG_IOV, "VF[%d]: vf pf channel unlocked by %d\n",
 	   vf->abs_vfid, vf->op_current);
-
-	/* record the locking op */
-	vf->op_current = CHANNEL_TLV_NONE;
 }
 
 int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param)
@@ -3057,11 +3136,77 @@ int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs_param)
 		return bnx2x_enable_sriov(bp);
 	}
 }
+#define IGU_ENTRY_SIZE 4
 
 int bnx2x_enable_sriov(struct bnx2x *bp)
 {
 	int rc = 0, req_vfs = bp->requested_nr_virtfn;
+	int vf_idx, sb_idx, vfq_idx, qcount, first_vf;
+	u32 igu_entry, address;
+	u16 num_vf_queues;
+
+	if (req_vfs == 0)
+		return 0;
+
+	first_vf = bp->vfdb->sriov.first_vf_in_pf;
+
+	/* statically distribute vf sb pool between VFs */
+	num_vf_queues = min_t(u16, BNX2X_VF_MAX_QUEUES,
+			      BP_VFDB(bp)->vf_sbs_pool / req_vfs);
+
+	/* zero previous values learned from igu cam */
+	for (vf_idx = 0; vf_idx < req_vfs; vf_idx++) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
+
+		vf->sb_count = 0;
+		vf_sb_count(BP_VF(bp, vf_idx)) = 0;
+	}
+	bp->vfdb->vf_sbs_pool = 0;
+
+	/* prepare IGU cam */
+	sb_idx = BP_VFDB(bp)->first_vf_igu_entry;
+	address = IGU_REG_MAPPING_MEMORY + sb_idx * IGU_ENTRY_SIZE;
+	for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+		for (vfq_idx = 0; vfq_idx < num_vf_queues; vfq_idx++) {
+			igu_entry = vf_idx << IGU_REG_MAPPING_MEMORY_FID_SHIFT |
+				vfq_idx << IGU_REG_MAPPING_MEMORY_VECTOR_SHIFT |
+				IGU_REG_MAPPING_MEMORY_VALID;
+			DP(BNX2X_MSG_IOV, "assigning sb %d to vf %d\n",
+			   sb_idx, vf_idx);
+			REG_WR(bp, address, igu_entry);
+			sb_idx++;
+			address += IGU_ENTRY_SIZE;
+		}
+	}
+
+	/* Reinitialize vf database according to igu cam */
+	bnx2x_get_vf_igu_cam_info(bp);
+
+	DP(BNX2X_MSG_IOV, "vf_sbs_pool %d, num_vf_queues %d\n",
+	   BP_VFDB(bp)->vf_sbs_pool, num_vf_queues);
+
+	qcount = 0;
+	for_each_vf(bp, vf_idx) {
+		struct bnx2x_virtf *vf = BP_VF(bp, vf_idx);
 
+		/* set local queue arrays */
+		vf->vfqs = &bp->vfdb->vfqs[qcount];
+		qcount += vf_sb_count(vf);
+	}
+
+	/* prepare msix vectors in VF configuration space */
+	for (vf_idx = first_vf; vf_idx < first_vf + req_vfs; vf_idx++) {
+		bnx2x_pretend_func(bp, HW_VF_HANDLE(bp, vf_idx));
+		REG_WR(bp, PCICFG_OFFSET + GRC_CONFIG_REG_VF_MSIX_CONTROL,
+		       num_vf_queues);
+	}
+	bnx2x_pretend_func(bp, BP_ABS_FUNC(bp));
+
+	/* enable sriov. This will probe all the VFs, and consequentially cause
+	 * the "acquire" messages to appear on the VF PF channel.
+	 */
+	DP(BNX2X_MSG_IOV, "about to call enable sriov\n");
+	pci_disable_sriov(bp->pdev);
 	rc = pci_enable_sriov(bp->pdev, req_vfs);
 	if (rc) {
 		BNX2X_ERR("pci_enable_sriov failed with %d\n", rc);
@@ -3089,9 +3234,8 @@ void bnx2x_disable_sriov(struct bnx2x *bp)
 	pci_disable_sriov(bp->pdev);
 }
 
-static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
-			     struct bnx2x_virtf **vf,
-			     struct pf_vf_bulletin_content **bulletin)
+int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx, struct bnx2x_virtf **vf,
+			struct pf_vf_bulletin_content **bulletin)
 {
 	if (bp->state != BNX2X_STATE_OPEN) {
 		BNX2X_ERR("vf ndo called though PF is down\n");
@@ -3114,7 +3258,13 @@ static int bnx2x_vf_ndo_prep(struct bnx2x *bp, int vfidx,
 	*bulletin = BP_VF_BULLETIN(bp, vfidx);
 
 	if (!*vf) {
-		BNX2X_ERR("vf ndo called but vf was null. vfidx was %d\n",
+		BNX2X_ERR("vf ndo called but vf struct is null. vfidx was %d\n",
+			  vfidx);
+		return -EINVAL;
+	}
+
+	if (!(*vf)->vfqs) {
+		BNX2X_ERR("vf ndo called but vfqs struct is null. Was ndo invoked before dynamically enabling SR-IOV? vfidx was %d\n",
 			  vfidx);
 		return -EINVAL;
 	}
@@ -3142,8 +3292,8 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 	rc = bnx2x_vf_ndo_prep(bp, vfidx, &vf, &bulletin);
 	if (rc)
 		return rc;
-	mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
-	vlan_obj = &bnx2x_vfq(vf, 0, vlan_obj);
+	mac_obj = &bnx2x_leading_vfq(vf, mac_obj);
+	vlan_obj = &bnx2x_leading_vfq(vf, vlan_obj);
 	if (!mac_obj || !vlan_obj) {
 		BNX2X_ERR("VF partially initialized\n");
 		return -EINVAL;
@@ -3155,10 +3305,13 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx,
 	ivi->spoofchk = 1; /*always enabled */
 	if (vf->state == VF_ENABLED) {
 		/* mac and vlan are in vlan_mac objects */
-		mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
-					0, ETH_ALEN);
-		vlan_obj->get_n_elements(bp, vlan_obj, 1, (u8 *)&ivi->vlan,
-					 0, VLAN_HLEN);
+		if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj)))
+			mac_obj->get_n_elements(bp, mac_obj, 1, (u8 *)&ivi->mac,
+						0, ETH_ALEN);
+		if (validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, vlan_obj)))
+			vlan_obj->get_n_elements(bp, vlan_obj, 1,
+						 (u8 *)&ivi->vlan, 0,
+						 VLAN_HLEN);
 	} else {
 		/* mac */
 		if (bulletin->valid_bitmap & (1 << MAC_ADDR_VALID))
@@ -3226,14 +3379,18 @@ int bnx2x_set_vf_mac(struct net_device *dev, int vfidx, u8 *mac)
 		return rc;
 	}
 
-	/* is vf initialized and queue set up? */
 	q_logical_state =
-		bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+		bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
 	if (vf->state == VF_ENABLED &&
 	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
 		/* configure the mac in device on this vf's queue */
 		unsigned long ramrod_flags = 0;
-		struct bnx2x_vlan_mac_obj *mac_obj = &bnx2x_vfq(vf, 0, mac_obj);
+		struct bnx2x_vlan_mac_obj *mac_obj =
+			&bnx2x_leading_vfq(vf, mac_obj);
+
+		rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+		if (rc)
+			return rc;
 
 		/* must lock vfpf channel to protect against vf flows */
 		bnx2x_lock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
@@ -3293,18 +3450,21 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 
 	/* is vf initialized and queue set up? */
 	q_logical_state =
-		bnx2x_get_q_logical_state(bp, &bnx2x_vfq(vf, 0, sp_obj));
+		bnx2x_get_q_logical_state(bp, &bnx2x_leading_vfq(vf, sp_obj));
 	if (vf->state == VF_ENABLED &&
 	    q_logical_state == BNX2X_Q_LOGICAL_STATE_ACTIVE) {
 		/* configure the vlan in device on this vf's queue */
 		unsigned long ramrod_flags = 0;
 		unsigned long vlan_mac_flags = 0;
 		struct bnx2x_vlan_mac_obj *vlan_obj =
-			&bnx2x_vfq(vf, 0, vlan_obj);
+			&bnx2x_leading_vfq(vf, vlan_obj);
 		struct bnx2x_vlan_mac_ramrod_params ramrod_param;
 		struct bnx2x_queue_state_params q_params = {NULL};
 		struct bnx2x_queue_update_params *update_params;
 
+		rc = validate_vlan_mac(bp, &bnx2x_leading_vfq(vf, mac_obj));
+		if (rc)
+			return rc;
 		memset(&ramrod_param, 0, sizeof(ramrod_param));
 
 		/* must lock vfpf channel to protect against vf flows */
@@ -3324,7 +3484,7 @@ int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
 		 */
 		__set_bit(RAMROD_COMP_WAIT, &q_params.ramrod_flags);
 		q_params.cmd = BNX2X_Q_CMD_UPDATE;
-		q_params.q_obj = &bnx2x_vfq(vf, 0, sp_obj);
+		q_params.q_obj = &bnx2x_leading_vfq(vf, sp_obj);
 		update_params = &q_params.params.update;
 		__set_bit(BNX2X_Q_UPDATE_DEF_VLAN_EN_CHNG,
 			  &update_params->update_flags);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
index d143a7cdbbbe..8e9847fef861 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h
@@ -81,6 +81,7 @@ struct bnx2x_vf_queue {
 	u32 cid;
 	u16 index;
 	u16 sb_idx;
+	bool is_leading;
 };
 
 /* struct bnx2x_vfop_qctor_params - prepare queue construction parameters:
@@ -194,6 +195,7 @@ struct bnx2x_virtf {
 #define VF_CFG_INT_SIMD		0x0008
 #define VF_CACHE_LINE		0x0010
 #define VF_CFG_VLAN		0x0020
+#define VF_CFG_STATS_COALESCE	0x0040
 
 	u8 state;
 #define VF_FREE		0	/* VF ready to be acquired holds no resc */
@@ -213,6 +215,7 @@ struct bnx2x_virtf {
 
 	/* dma */
 	dma_addr_t fw_stat_map;		/* valid iff VF_CFG_STATS */
+	u16 stats_stride;
 	dma_addr_t spq_map;
 	dma_addr_t bulletin_map;
 
@@ -239,7 +242,10 @@ struct bnx2x_virtf {
 	u8 igu_base_id;	/* base igu status block id */
 
 	struct bnx2x_vf_queue	*vfqs;
-#define bnx2x_vfq(vf, nr, var)	((vf)->vfqs[(nr)].var)
+#define LEADING_IDX			0
+#define bnx2x_vfq_is_leading(vfq)	((vfq)->index == LEADING_IDX)
+#define bnx2x_vfq(vf, nr, var)		((vf)->vfqs[(nr)].var)
+#define bnx2x_leading_vfq(vf, var)	((vf)->vfqs[LEADING_IDX].var)
 
 	u8 index;	/* index in the vf array */
 	u8 abs_vfid;
@@ -358,6 +364,10 @@ struct bnx2x_vf_sp {
 		struct client_init_ramrod_data  init_data;
 		struct client_update_ramrod_data update_data;
 	} q_data;
+
+	union {
+		struct eth_rss_update_ramrod_data e2;
+	} rss_rdata;
 };
 
 struct hw_dma {
@@ -403,6 +413,10 @@ struct bnx2x_vfdb {
 
 #define FLRD_VFS_DWORDS (BNX2X_MAX_NUM_OF_VFS / 32)
 	u32 flrd_vfs[FLRD_VFS_DWORDS];
+
+	/* the number of msix vectors belonging to this PF designated for VFs */
+	u16 vf_sbs_pool;
+	u16 first_vf_igu_entry;
 };
 
 /* queue access */
@@ -411,11 +425,6 @@ static inline struct bnx2x_vf_queue *vfq_get(struct bnx2x_virtf *vf, u8 index)
 	return &(vf->vfqs[index]);
 }
 
-static inline bool vfq_is_leading(struct bnx2x_vf_queue *vfq)
-{
-	return (vfq->index == 0);
-}
-
 /* FW ids */
 static inline u8 vf_igu_sb(struct bnx2x_virtf *vf, u16 sb_idx)
 {
@@ -434,7 +443,10 @@ static u8 vfq_cl_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 
 static inline u8 vfq_stat_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
 {
-	return vfq_cl_id(vf, q);
+	if (vf->cfg_flags & VF_CFG_STATS_COALESCE)
+		return vf->leading_rss;
+	else
+		return vfq_cl_id(vf, q);
 }
 
 static inline u8 vfq_qzone_id(struct bnx2x_virtf *vf, struct bnx2x_vf_queue *q)
@@ -691,6 +703,10 @@ int bnx2x_vfop_release_cmd(struct bnx2x *bp,
 			   struct bnx2x_virtf *vf,
 			   struct bnx2x_vfop_cmd *cmd);
 
+int bnx2x_vfop_rss_cmd(struct bnx2x *bp,
+		       struct bnx2x_virtf *vf,
+		       struct bnx2x_vfop_cmd *cmd);
+
 /* VF release ~ VF close + VF release-resources
  *
  * Release is the ultimate SW shutdown and is called whenever an
@@ -758,7 +774,7 @@ int bnx2x_enable_sriov(struct bnx2x *bp);
 void bnx2x_disable_sriov(struct bnx2x *bp);
 static inline int bnx2x_vf_headroom(struct bnx2x *bp)
 {
-	return bp->vfdb->sriov.nr_virtfn * BNX2X_CLIENTS_PER_VF;
+	return bp->vfdb->sriov.nr_virtfn * BNX2X_CIDS_PER_VF;
 }
 void bnx2x_pf_set_vfs_vlan(struct bnx2x *bp);
 int bnx2x_sriov_configure(struct pci_dev *dev, int num_vfs);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 2088063151d6..a7e88a405a43 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -257,17 +257,23 @@ int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count)
 
 			/* humble our request */
 			req->resc_request.num_txqs =
-				bp->acquire_resp.resc.num_txqs;
+				min(req->resc_request.num_txqs,
+				    bp->acquire_resp.resc.num_txqs);
 			req->resc_request.num_rxqs =
-				bp->acquire_resp.resc.num_rxqs;
+				min(req->resc_request.num_rxqs,
+				    bp->acquire_resp.resc.num_rxqs);
 			req->resc_request.num_sbs =
-				bp->acquire_resp.resc.num_sbs;
+				min(req->resc_request.num_sbs,
+				    bp->acquire_resp.resc.num_sbs);
 			req->resc_request.num_mac_filters =
-				bp->acquire_resp.resc.num_mac_filters;
+				min(req->resc_request.num_mac_filters,
+				    bp->acquire_resp.resc.num_mac_filters);
 			req->resc_request.num_vlan_filters =
-				bp->acquire_resp.resc.num_vlan_filters;
+				min(req->resc_request.num_vlan_filters,
+				    bp->acquire_resp.resc.num_vlan_filters);
 			req->resc_request.num_mc_filters =
-				bp->acquire_resp.resc.num_mc_filters;
+				min(req->resc_request.num_mc_filters,
+				    bp->acquire_resp.resc.num_mc_filters);
 
 			/* Clear response buffer */
 			memset(&bp->vf2pf_mbox->resp, 0,
@@ -293,7 +299,7 @@ int bnx2x_vfpf_acquire(struct bnx2x *bp, u8 tx_count, u8 rx_count)
 	bp->common.flash_size = 0;
 	bp->flags |=
 		NO_WOL_FLAG | NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG | NO_FCOE_FLAG;
-	bp->igu_sb_cnt = 1;
+	bp->igu_sb_cnt = bp->acquire_resp.resc.num_sbs;
 	bp->igu_base_sb = bp->acquire_resp.resc.hw_sbs[0].hw_sb_id;
 	strlcpy(bp->fw_ver, bp->acquire_resp.pfdev_info.fw_ver,
 		sizeof(bp->fw_ver));
@@ -452,6 +458,53 @@ free_irq:
 	bnx2x_free_irq(bp);
 }
 
+static void bnx2x_leading_vfq_init(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				   struct bnx2x_vf_queue *q)
+{
+	u8 cl_id = vfq_cl_id(vf, q);
+	u8 func_id = FW_VF_HANDLE(vf->abs_vfid);
+
+	/* mac */
+	bnx2x_init_mac_obj(bp, &q->mac_obj,
+			   cl_id, q->cid, func_id,
+			   bnx2x_vf_sp(bp, vf, mac_rdata),
+			   bnx2x_vf_sp_map(bp, vf, mac_rdata),
+			   BNX2X_FILTER_MAC_PENDING,
+			   &vf->filter_state,
+			   BNX2X_OBJ_TYPE_RX_TX,
+			   &bp->macs_pool);
+	/* vlan */
+	bnx2x_init_vlan_obj(bp, &q->vlan_obj,
+			    cl_id, q->cid, func_id,
+			    bnx2x_vf_sp(bp, vf, vlan_rdata),
+			    bnx2x_vf_sp_map(bp, vf, vlan_rdata),
+			    BNX2X_FILTER_VLAN_PENDING,
+			    &vf->filter_state,
+			    BNX2X_OBJ_TYPE_RX_TX,
+			    &bp->vlans_pool);
+
+	/* mcast */
+	bnx2x_init_mcast_obj(bp, &vf->mcast_obj, cl_id,
+			     q->cid, func_id, func_id,
+			     bnx2x_vf_sp(bp, vf, mcast_rdata),
+			     bnx2x_vf_sp_map(bp, vf, mcast_rdata),
+			     BNX2X_FILTER_MCAST_PENDING,
+			     &vf->filter_state,
+			     BNX2X_OBJ_TYPE_RX_TX);
+
+	/* rss */
+	bnx2x_init_rss_config_obj(bp, &vf->rss_conf_obj, cl_id, q->cid,
+				  func_id, func_id,
+				  bnx2x_vf_sp(bp, vf, rss_rdata),
+				  bnx2x_vf_sp_map(bp, vf, rss_rdata),
+				  BNX2X_FILTER_RSS_CONF_PENDING,
+				  &vf->filter_state,
+				  BNX2X_OBJ_TYPE_RX_TX);
+
+	vf->leading_rss = cl_id;
+	q->is_leading = true;
+}
+
 /* ask the pf to open a queue for the vf */
 int bnx2x_vfpf_setup_q(struct bnx2x *bp, int fp_idx)
 {
@@ -948,7 +1001,7 @@ static void bnx2x_vf_mbx_acquire_resp(struct bnx2x *bp, struct bnx2x_virtf *vf,
 
 	/* fill in pfdev info */
 	resp->pfdev_info.chip_num = bp->common.chip_id;
-	resp->pfdev_info.db_size = (1 << BNX2X_DB_SHIFT);
+	resp->pfdev_info.db_size = bp->db_size;
 	resp->pfdev_info.indices_per_sb = HC_SB_MAX_INDICES_E2;
 	resp->pfdev_info.pf_cap = (PFVF_CAP_RSS |
 				   /* PFVF_CAP_DHC |*/ PFVF_CAP_TPA);
@@ -1054,8 +1107,13 @@ static void bnx2x_vf_mbx_init_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	/* record ghost addresses from vf message */
 	vf->spq_map = init->spq_addr;
 	vf->fw_stat_map = init->stats_addr;
+	vf->stats_stride = init->stats_stride;
 	vf->op_rc = bnx2x_vf_init(bp, vf, (dma_addr_t *)init->sb_addr);
 
+	/* set VF multiqueue statistics collection mode */
+	if (init->flags & VFPF_INIT_FLG_STATS_COALESCE)
+		vf->cfg_flags |= VF_CFG_STATS_COALESCE;
+
 	/* response */
 	bnx2x_vf_mbx_resp(bp, vf);
 }
@@ -1080,6 +1138,8 @@ static void bnx2x_vf_mbx_set_q_flags(struct bnx2x *bp, u32 mbx_q_flags,
 		__set_bit(BNX2X_Q_FLG_HC, sp_q_flags);
 	if (mbx_q_flags & VFPF_QUEUE_FLG_DHC)
 		__set_bit(BNX2X_Q_FLG_DHC, sp_q_flags);
+	if (mbx_q_flags & VFPF_QUEUE_FLG_LEADING_RSS)
+		__set_bit(BNX2X_Q_FLG_LEADING_RSS, sp_q_flags);
 
 	/* outer vlan removal is set according to PF's multi function mode */
 	if (IS_MF_SD(bp))
@@ -1113,6 +1173,9 @@ static void bnx2x_vf_mbx_setup_q(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		struct bnx2x_queue_init_params *init_p;
 		struct bnx2x_queue_setup_params *setup_p;
 
+		if (bnx2x_vfq_is_leading(q))
+			bnx2x_leading_vfq_init(bp, vf, q);
+
 		/* re-init the VF operation context */
 		memset(&vf->op_params.qctor, 0 , sizeof(vf->op_params.qctor));
 		setup_p = &vf->op_params.qctor.prep_qsetup;
@@ -1552,6 +1615,68 @@ static void bnx2x_vf_mbx_release_vf(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		bnx2x_vf_mbx_resp(bp, vf);
 }
 
+static void bnx2x_vf_mbx_update_rss(struct bnx2x *bp, struct bnx2x_virtf *vf,
+				    struct bnx2x_vf_mbx *mbx)
+{
+	struct bnx2x_vfop_cmd cmd = {
+		.done = bnx2x_vf_mbx_resp,
+		.block = false,
+	};
+	struct bnx2x_config_rss_params *vf_op_params = &vf->op_params.rss;
+	struct vfpf_rss_tlv *rss_tlv = &mbx->msg->req.update_rss;
+
+	if (rss_tlv->ind_table_size != T_ETH_INDIRECTION_TABLE_SIZE ||
+	    rss_tlv->rss_key_size != T_ETH_RSS_KEY) {
+		BNX2X_ERR("failing rss configuration of vf %d due to size mismatch\n",
+			  vf->index);
+		vf->op_rc = -EINVAL;
+		goto mbx_resp;
+	}
+
+	/* set vfop params according to rss tlv */
+	memcpy(vf_op_params->ind_table, rss_tlv->ind_table,
+	       T_ETH_INDIRECTION_TABLE_SIZE);
+	memcpy(vf_op_params->rss_key, rss_tlv->rss_key,
+	       sizeof(rss_tlv->rss_key));
+	vf_op_params->rss_obj = &vf->rss_conf_obj;
+	vf_op_params->rss_result_mask = rss_tlv->rss_result_mask;
+
+	/* flags handled individually for backward/forward compatability */
+	if (rss_tlv->rss_flags & VFPF_RSS_MODE_DISABLED)
+		__set_bit(BNX2X_RSS_MODE_DISABLED, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_MODE_REGULAR)
+		__set_bit(BNX2X_RSS_MODE_REGULAR, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_SET_SRCH)
+		__set_bit(BNX2X_RSS_SET_SRCH, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4)
+		__set_bit(BNX2X_RSS_IPV4, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP)
+		__set_bit(BNX2X_RSS_IPV4_TCP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP)
+		__set_bit(BNX2X_RSS_IPV4_UDP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6)
+		__set_bit(BNX2X_RSS_IPV6, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP)
+		__set_bit(BNX2X_RSS_IPV6_TCP, &vf_op_params->rss_flags);
+	if (rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)
+		__set_bit(BNX2X_RSS_IPV6_UDP, &vf_op_params->rss_flags);
+
+	if ((!(rss_tlv->rss_flags & VFPF_RSS_IPV4_TCP) &&
+	     rss_tlv->rss_flags & VFPF_RSS_IPV4_UDP) ||
+	    (!(rss_tlv->rss_flags & VFPF_RSS_IPV6_TCP) &&
+	     rss_tlv->rss_flags & VFPF_RSS_IPV6_UDP)) {
+		BNX2X_ERR("about to hit a FW assert. aborting...\n");
+		vf->op_rc = -EINVAL;
+		goto mbx_resp;
+	}
+
+	vf->op_rc = bnx2x_vfop_rss_cmd(bp, vf, &cmd);
+
+mbx_resp:
+	if (vf->op_rc)
+		bnx2x_vf_mbx_resp(bp, vf);
+}
+
 /* dispatch request */
 static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 				  struct bnx2x_vf_mbx *mbx)
@@ -1588,6 +1713,9 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		case CHANNEL_TLV_RELEASE:
 			bnx2x_vf_mbx_release_vf(bp, vf, mbx);
 			break;
+		case CHANNEL_TLV_UPDATE_RSS:
+			bnx2x_vf_mbx_update_rss(bp, vf, mbx);
+			break;
 		}
 
 	} else {
@@ -1607,7 +1735,7 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		/* test whether we can respond to the VF (do we have an address
 		 * for it?)
 		 */
-		if (vf->state == VF_ACQUIRED) {
+		if (vf->state == VF_ACQUIRED || vf->state == VF_ENABLED) {
 			/* mbx_resp uses the op_rc of the VF */
 			vf->op_rc = PFVF_STATUS_NOT_SUPPORTED;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
index f3ad174a3a63..1179fe06d0c7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.h
@@ -51,6 +51,7 @@ struct hw_sb_info {
 #define VFPF_QUEUE_FLG_COS		0x0080
 #define VFPF_QUEUE_FLG_HC		0x0100
 #define VFPF_QUEUE_FLG_DHC		0x0200
+#define VFPF_QUEUE_FLG_LEADING_RSS	0x0400
 
 #define VFPF_QUEUE_DROP_IP_CS_ERR	(1 << 0)
 #define VFPF_QUEUE_DROP_TCP_CS_ERR	(1 << 1)
@@ -131,6 +132,27 @@ struct vfpf_q_op_tlv {
 	u8 padding[3];
 };
 
+/* receive side scaling tlv */
+struct vfpf_rss_tlv {
+	struct vfpf_first_tlv	first_tlv;
+	u32			rss_flags;
+#define VFPF_RSS_MODE_DISABLED	(1 << 0)
+#define VFPF_RSS_MODE_REGULAR	(1 << 1)
+#define VFPF_RSS_SET_SRCH	(1 << 2)
+#define VFPF_RSS_IPV4		(1 << 3)
+#define VFPF_RSS_IPV4_TCP	(1 << 4)
+#define VFPF_RSS_IPV4_UDP	(1 << 5)
+#define VFPF_RSS_IPV6		(1 << 6)
+#define VFPF_RSS_IPV6_TCP	(1 << 7)
+#define VFPF_RSS_IPV6_UDP	(1 << 8)
+	u8			rss_result_mask;
+	u8			ind_table_size;
+	u8			rss_key_size;
+	u8			padding;
+	u8			ind_table[T_ETH_INDIRECTION_TABLE_SIZE];
+	u32			rss_key[T_ETH_RSS_KEY];	/* hash values */
+};
+
 /* acquire response tlv - carries the allocated resources */
 struct pfvf_acquire_resp_tlv {
 	struct pfvf_tlv hdr;
@@ -166,12 +188,20 @@ struct pfvf_acquire_resp_tlv {
 	} resc;
 };
 
+#define VFPF_INIT_FLG_STATS_COALESCE	(1 << 0) /* when set the VFs queues
+						  * stats will be coalesced on
+						  * the leading RSS queue
+						  */
+
 /* Init VF */
 struct vfpf_init_tlv {
 	struct vfpf_first_tlv first_tlv;
 	aligned_u64 sb_addr[PFVF_MAX_SBS_PER_VF]; /* vf_sb based */
 	aligned_u64 spq_addr;
 	aligned_u64 stats_addr;
+	u16 stats_stride;
+	u32 flags;
+	u32 padding[2];
 };
 
 /* Setup Queue */
@@ -293,13 +323,14 @@ union vfpf_tlvs {
 	struct vfpf_q_op_tlv		q_op;
 	struct vfpf_setup_q_tlv		setup_q;
 	struct vfpf_set_q_filters_tlv	set_q_filters;
-	struct vfpf_release_tlv         release;
-	struct channel_list_end_tlv     list_end;
+	struct vfpf_release_tlv		release;
+	struct vfpf_rss_tlv		update_rss;
+	struct channel_list_end_tlv	list_end;
 	struct tlv_buffer_size		tlv_buf_size;
 };
 
 union pfvf_tlvs {
-	struct pfvf_general_resp_tlv    general_resp;
+	struct pfvf_general_resp_tlv	general_resp;
 	struct pfvf_acquire_resp_tlv	acquire_resp;
 	struct channel_list_end_tlv	list_end;
 	struct tlv_buffer_size		tlv_buf_size;
@@ -355,14 +386,18 @@ enum channel_tlvs {
 	CHANNEL_TLV_INIT,
 	CHANNEL_TLV_SETUP_Q,
 	CHANNEL_TLV_SET_Q_FILTERS,
+	CHANNEL_TLV_ACTIVATE_Q,
+	CHANNEL_TLV_DEACTIVATE_Q,
 	CHANNEL_TLV_TEARDOWN_Q,
 	CHANNEL_TLV_CLOSE,
 	CHANNEL_TLV_RELEASE,
+	CHANNEL_TLV_UPDATE_RSS_DEPRECATED,
 	CHANNEL_TLV_PF_RELEASE_VF,
 	CHANNEL_TLV_LIST_END,
 	CHANNEL_TLV_FLR,
 	CHANNEL_TLV_PF_SET_MAC,
 	CHANNEL_TLV_PF_SET_VLAN,
+	CHANNEL_TLV_UPDATE_RSS,
 	CHANNEL_TLV_MAX
 };