Merge branch 'bnxt_en-ptp-and-rss-updates'

Michael Chan says:

====================
bnxt_en: PTP and RSS updates

The first 2 patches are v2 of the PTP patches posted about 3 weeks ago:

https://lore.kernel.org/netdev/20240229070202.107488-1-michael.chan@broadcom.com/

The devlink parameter is dropped and v2 is just to increase the timeout
accuracy and to use a default timeout of 1 second.

Patches 3 to 12 implement additional RSS contexts and ntuple filters for
the RSS contexts.
====================

Link: https://lore.kernel.org/r/20240325222902.220712-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 509 insertions, 136 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 493b724848c8..388e80bf91f5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4241,6 +4241,7 @@ static void bnxt_init_vnics(struct bnxt *bp)
 		int j;
 
 		vnic->fw_vnic_id = INVALID_HW_RING_ID;
+		vnic->vnic_id = i;
 		for (j = 0; j < BNXT_MAX_CTX_PER_VNIC; j++)
 			vnic->fw_rss_cos_lb_ctx[j] = INVALID_HW_RING_ID;
 
@@ -5788,8 +5789,22 @@ void bnxt_fill_ipv6_mask(__be32 mask[4])
 static void
 bnxt_cfg_rfs_ring_tbl_idx(struct bnxt *bp,
 			  struct hwrm_cfa_ntuple_filter_alloc_input *req,
-			  u16 rxq)
+			  struct bnxt_ntuple_filter *fltr)
 {
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+	u16 rxq = fltr->base.rxq;
+
+	if (fltr->base.flags & BNXT_ACT_RSS_CTX) {
+		list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list) {
+			if (rss_ctx->index == fltr->base.fw_vnic_id) {
+				struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+				req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
+				break;
+			}
+		}
+		return;
+	}
 	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
 		struct bnxt_vnic_info *vnic;
 		u32 enables;
@@ -5830,7 +5845,7 @@ int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 		req->flags =
 			cpu_to_le32(CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP);
 	} else if (bp->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V2) {
-		bnxt_cfg_rfs_ring_tbl_idx(bp, req, fltr->base.rxq);
+		bnxt_cfg_rfs_ring_tbl_idx(bp, req, fltr);
 	} else {
 		vnic = &bp->vnic_info[fltr->base.rxq + 1];
 		req->dst_id = cpu_to_le16(vnic->fw_vnic_id);
@@ -5938,9 +5953,9 @@ static void bnxt_hwrm_vnic_update_tunl_tpa(struct bnxt *bp,
 	req->tnl_tpa_en_bitmap = cpu_to_le32(tunl_tpa_bmap);
 }
 
-static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags)
+int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			   u32 tpa_flags)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	u16 max_aggs = VNIC_TPA_CFG_REQ_MAX_AGGS_MAX;
 	struct hwrm_vnic_tpa_cfg_input *req;
 	int rc;
@@ -6025,9 +6040,10 @@ static u16 bnxt_cp_ring_for_tx(struct bnxt *bp, struct bnxt_tx_ring_info *txr)
 		return bnxt_cp_ring_from_grp(bp, &txr->tx_ring_struct);
 }
 
-static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
+int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx)
 {
 	int entries;
+	u16 *tbl;
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		entries = BNXT_MAX_RSS_TABLE_ENTRIES_P5;
@@ -6035,16 +6051,22 @@ static int bnxt_alloc_rss_indir_tbl(struct bnxt *bp)
 		entries = HW_HASH_INDEX_SIZE;
 
 	bp->rss_indir_tbl_entries = entries;
-	bp->rss_indir_tbl = kmalloc_array(entries, sizeof(*bp->rss_indir_tbl),
-					  GFP_KERNEL);
-	if (!bp->rss_indir_tbl)
+	tbl = kmalloc_array(entries, sizeof(*bp->rss_indir_tbl), GFP_KERNEL);
+	if (!tbl)
 		return -ENOMEM;
+
+	if (rss_ctx)
+		rss_ctx->rss_indir_tbl = tbl;
+	else
+		bp->rss_indir_tbl = tbl;
+
 	return 0;
 }
 
-static void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp)
+void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx)
 {
 	u16 max_rings, max_entries, pad, i;
+	u16 *rss_indir_tbl;
 
 	if (!bp->rx_nr_rings)
 		return;
@@ -6055,13 +6077,17 @@ static void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp)
 		max_rings = bp->rx_nr_rings;
 
 	max_entries = bnxt_get_rxfh_indir_size(bp->dev);
+	if (rss_ctx)
+		rss_indir_tbl = &rss_ctx->rss_indir_tbl[0];
+	else
+		rss_indir_tbl = &bp->rss_indir_tbl[0];
 
 	for (i = 0; i < max_entries; i++)
-		bp->rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, max_rings);
+		rss_indir_tbl[i] = ethtool_rxfh_indir_default(i, max_rings);
 
 	pad = bp->rss_indir_tbl_entries - max_entries;
 	if (pad)
-		memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
+		memset(&rss_indir_tbl[i], 0, pad * sizeof(u16));
 }
 
 static u16 bnxt_get_max_rss_ring(struct bnxt *bp)
@@ -6117,6 +6143,8 @@ static void bnxt_fill_hw_rss_tbl_p5(struct bnxt *bp,
 
 		if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
 			j = ethtool_rxfh_indir_default(i, bp->rx_nr_rings);
+		else if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			j = vnic->rss_ctx->rss_indir_tbl[i];
 		else
 			j = bp->rss_indir_tbl[i];
 		rxr = &bp->rx_ring[j];
@@ -6154,9 +6182,9 @@ __bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct hwrm_vnic_rss_cfg_input *req,
 	req->hash_key_tbl_addr = cpu_to_le64(vnic->rss_hash_key_dma_addr);
 }
 
-static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
+static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  bool set_rss)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_rss_cfg_input *req;
 	int rc;
 
@@ -6174,9 +6202,9 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	return hwrm_req_send(bp, req);
 }
 
-static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss)
+static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp,
+				     struct bnxt_vnic_info *vnic, bool set_rss)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_rss_cfg_input *req;
 	dma_addr_t ring_tbl_map;
 	u32 i, nr_ctxs;
@@ -6229,9 +6257,8 @@ static void bnxt_hwrm_update_rss_hash_cfg(struct bnxt *bp)
 	hwrm_req_drop(bp, req);
 }
 
-static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
+static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_plcmodes_cfg_input *req;
 	int rc;
 
@@ -6256,7 +6283,8 @@ static int bnxt_hwrm_vnic_set_hds(struct bnxt *bp, u16 vnic_id)
 	return hwrm_req_send(bp, req);
 }
 
-static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id,
+static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp,
+					struct bnxt_vnic_info *vnic,
 					u16 ctx_idx)
 {
 	struct hwrm_vnic_rss_cos_lb_ctx_free_input *req;
@@ -6265,10 +6293,10 @@ static void bnxt_hwrm_vnic_ctx_free_one(struct bnxt *bp, u16 vnic_id,
 		return;
 
 	req->rss_cos_lb_ctx_id =
-		cpu_to_le16(bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx]);
+		cpu_to_le16(vnic->fw_rss_cos_lb_ctx[ctx_idx]);
 
 	hwrm_req_send(bp, req);
-	bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
+	vnic->fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID;
 }
 
 static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp)
@@ -6280,13 +6308,14 @@ static void bnxt_hwrm_vnic_ctx_free(struct bnxt *bp)
 
 		for (j = 0; j < BNXT_MAX_CTX_PER_VNIC; j++) {
 			if (vnic->fw_rss_cos_lb_ctx[j] != INVALID_HW_RING_ID)
-				bnxt_hwrm_vnic_ctx_free_one(bp, i, j);
+				bnxt_hwrm_vnic_ctx_free_one(bp, vnic, j);
 		}
 	}
 	bp->rsscos_nr_ctxs = 0;
 }
 
-static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
+static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp,
+				    struct bnxt_vnic_info *vnic, u16 ctx_idx)
 {
 	struct hwrm_vnic_rss_cos_lb_ctx_alloc_output *resp;
 	struct hwrm_vnic_rss_cos_lb_ctx_alloc_input *req;
@@ -6299,7 +6328,7 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
 	resp = hwrm_req_hold(bp, req);
 	rc = hwrm_req_send(bp, req);
 	if (!rc)
-		bp->vnic_info[vnic_id].fw_rss_cos_lb_ctx[ctx_idx] =
+		vnic->fw_rss_cos_lb_ctx[ctx_idx] =
 			le16_to_cpu(resp->rss_cos_lb_ctx_id);
 	hwrm_req_drop(bp, req);
 
@@ -6313,10 +6342,9 @@ static u32 bnxt_get_roce_vnic_mode(struct bnxt *bp)
 	return VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE;
 }
 
-int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
+int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	struct bnxt_vnic_info *vnic0 = &bp->vnic_info[BNXT_VNIC_DEFAULT];
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_cfg_input *req;
 	unsigned int ring = 0, grp_idx;
 	u16 def_vlan = 0;
@@ -6364,8 +6392,8 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	if (vnic->flags & BNXT_VNIC_RSS_FLAG)
 		ring = 0;
 	else if (vnic->flags & BNXT_VNIC_RFS_FLAG)
-		ring = vnic_id - 1;
-	else if ((vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
+		ring = vnic->vnic_id - 1;
+	else if ((vnic->vnic_id == 1) && BNXT_CHIP_TYPE_NITRO_A0(bp))
 		ring = bp->rx_nr_rings - 1;
 
 	grp_idx = bp->rx_ring[ring].bnapi->index;
@@ -6381,25 +6409,25 @@ vnic_mru:
 #endif
 	if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan)
 		req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE);
-	if (!vnic_id && bnxt_ulp_registered(bp->edev))
+	if (vnic->vnic_id == BNXT_VNIC_DEFAULT && bnxt_ulp_registered(bp->edev))
 		req->flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp));
 
 	return hwrm_req_send(bp, req);
 }
 
-static void bnxt_hwrm_vnic_free_one(struct bnxt *bp, u16 vnic_id)
+static void bnxt_hwrm_vnic_free_one(struct bnxt *bp,
+				    struct bnxt_vnic_info *vnic)
 {
-	if (bp->vnic_info[vnic_id].fw_vnic_id != INVALID_HW_RING_ID) {
+	if (vnic->fw_vnic_id != INVALID_HW_RING_ID) {
 		struct hwrm_vnic_free_input *req;
 
 		if (hwrm_req_init(bp, req, HWRM_VNIC_FREE))
 			return;
 
-		req->vnic_id =
-			cpu_to_le32(bp->vnic_info[vnic_id].fw_vnic_id);
+		req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
 
 		hwrm_req_send(bp, req);
-		bp->vnic_info[vnic_id].fw_vnic_id = INVALID_HW_RING_ID;
+		vnic->fw_vnic_id = INVALID_HW_RING_ID;
 	}
 }
 
@@ -6408,15 +6436,14 @@ static void bnxt_hwrm_vnic_free(struct bnxt *bp)
 	u16 i;
 
 	for (i = 0; i < bp->nr_vnics; i++)
-		bnxt_hwrm_vnic_free_one(bp, i);
+		bnxt_hwrm_vnic_free_one(bp, &bp->vnic_info[i]);
 }
 
-static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
-				unsigned int start_rx_ring_idx,
-				unsigned int nr_rings)
+int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			 unsigned int start_rx_ring_idx,
+			 unsigned int nr_rings)
 {
 	unsigned int i, j, grp_idx, end_idx = start_rx_ring_idx + nr_rings;
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	struct hwrm_vnic_alloc_output *resp;
 	struct hwrm_vnic_alloc_input *req;
 	int rc;
@@ -6442,7 +6469,7 @@ static int bnxt_hwrm_vnic_alloc(struct bnxt *bp, u16 vnic_id,
 vnic_no_ring_grps:
 	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++)
 		vnic->fw_rss_cos_lb_ctx[i] = INVALID_HW_RING_ID;
-	if (vnic_id == BNXT_VNIC_DEFAULT)
+	if (vnic->vnic_id == BNXT_VNIC_DEFAULT)
 		req->flags = cpu_to_le32(VNIC_ALLOC_REQ_FLAGS_DEFAULT);
 
 	resp = hwrm_req_hold(bp, req);
@@ -7341,7 +7368,7 @@ static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp)
 	if (hw_resc->resv_rx_rings != bp->rx_nr_rings) {
 		hw_resc->resv_rx_rings = bp->rx_nr_rings;
 		if (!netif_is_rxfh_configured(bp->dev))
-			bnxt_set_dflt_rss_indir_tbl(bp);
+			bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 	}
 }
 
@@ -7349,7 +7376,7 @@ static int bnxt_get_total_vnics(struct bnxt *bp, int rx_rings)
 {
 	if (bp->flags & BNXT_FLAG_RFS) {
 		if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
-			return 2;
+			return 2 + bp->num_rss_ctx;
 		if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS))
 			return rx_rings + 1;
 	}
@@ -7497,7 +7524,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		return -ENOMEM;
 
 	if (!netif_is_rxfh_configured(bp->dev))
-		bnxt_set_dflt_rss_indir_tbl(bp);
+		bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 
 	return rc;
 }
@@ -9676,7 +9703,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa)
 	else if (BNXT_NO_FW_ACCESS(bp))
 		return 0;
 	for (i = 0; i < bp->nr_vnics; i++) {
-		rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags);
+		rc = bnxt_hwrm_vnic_set_tpa(bp, &bp->vnic_info[i], tpa_flags);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic set tpa failure rc for vnic %d: %x\n",
 				   i, rc);
@@ -9691,7 +9718,7 @@ static void bnxt_hwrm_clear_vnic_rss(struct bnxt *bp)
 	int i;
 
 	for (i = 0; i < bp->nr_vnics; i++)
-		bnxt_hwrm_vnic_set_rss(bp, i, false);
+		bnxt_hwrm_vnic_set_rss(bp, &bp->vnic_info[i], false);
 }
 
 static void bnxt_clear_vnic(struct bnxt *bp)
@@ -9769,28 +9796,27 @@ static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size)
 	return hwrm_req_send(bp, req);
 }
 
-static int __bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
+static int __bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id];
 	int rc;
 
 	if (vnic->flags & BNXT_VNIC_RFS_NEW_RSS_FLAG)
 		goto skip_rss_ctx;
 
 	/* allocate context for vnic */
-	rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 0);
+	rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, 0);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 	bp->rsscos_nr_ctxs++;
 
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
-		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, 1);
+		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, 1);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d cos ctx alloc failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 			goto vnic_setup_err;
 		}
 		bp->rsscos_nr_ctxs++;
@@ -9798,26 +9824,26 @@ static int __bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
 
 skip_rss_ctx:
 	/* configure default vnic, ring grp */
-	rc = bnxt_hwrm_vnic_cfg(bp, vnic_id);
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 
 	/* Enable RSS hashing on vnic */
-	rc = bnxt_hwrm_vnic_set_rss(bp, vnic_id, true);
+	rc = bnxt_hwrm_vnic_set_rss(bp, vnic, true);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		goto vnic_setup_err;
 	}
 
 	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
-		rc = bnxt_hwrm_vnic_set_hds(bp, vnic_id);
+		rc = bnxt_hwrm_vnic_set_hds(bp, vnic);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d set hds failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 		}
 	}
 
@@ -9825,16 +9851,33 @@ vnic_setup_err:
 	return rc;
 }
 
-static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
+int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic)
+{
+	int rc;
+
+	rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+	if (rc) {
+		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+			   vnic->vnic_id, rc);
+		return rc;
+	}
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
+	if (rc)
+		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
+			   vnic->vnic_id, rc);
+	return rc;
+}
+
+int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	int rc, i, nr_ctxs;
 
 	nr_ctxs = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings);
 	for (i = 0; i < nr_ctxs; i++) {
-		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic_id, i);
+		rc = bnxt_hwrm_vnic_ctx_alloc(bp, vnic, i);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d ctx %d alloc failure rc: %x\n",
-				   vnic_id, i, rc);
+				   vnic->vnic_id, i, rc);
 			break;
 		}
 		bp->rsscos_nr_ctxs++;
@@ -9842,63 +9885,57 @@ static int __bnxt_setup_vnic_p5(struct bnxt *bp, u16 vnic_id)
 	if (i < nr_ctxs)
 		return -ENOMEM;
 
-	rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic_id, true);
-	if (rc) {
-		netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-			   vnic_id, rc);
-		return rc;
-	}
-	rc = bnxt_hwrm_vnic_cfg(bp, vnic_id);
-	if (rc) {
-		netdev_err(bp->dev, "hwrm vnic %d cfg failure rc: %x\n",
-			   vnic_id, rc);
+	rc = bnxt_hwrm_vnic_rss_cfg_p5(bp, vnic);
+	if (rc)
 		return rc;
-	}
+
 	if (bp->flags & BNXT_FLAG_AGG_RINGS) {
-		rc = bnxt_hwrm_vnic_set_hds(bp, vnic_id);
+		rc = bnxt_hwrm_vnic_set_hds(bp, vnic);
 		if (rc) {
 			netdev_err(bp->dev, "hwrm vnic %d set hds failure rc: %x\n",
-				   vnic_id, rc);
+				   vnic->vnic_id, rc);
 		}
 	}
 	return rc;
 }
 
-static int bnxt_setup_vnic(struct bnxt *bp, u16 vnic_id)
+static int bnxt_setup_vnic(struct bnxt *bp, struct bnxt_vnic_info *vnic)
 {
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
-		return __bnxt_setup_vnic_p5(bp, vnic_id);
+		return __bnxt_setup_vnic_p5(bp, vnic);
 	else
-		return __bnxt_setup_vnic(bp, vnic_id);
+		return __bnxt_setup_vnic(bp, vnic);
 }
 
-static int bnxt_alloc_and_setup_vnic(struct bnxt *bp, u16 vnic_id,
+static int bnxt_alloc_and_setup_vnic(struct bnxt *bp,
+				     struct bnxt_vnic_info *vnic,
 				     u16 start_rx_ring_idx, int rx_rings)
 {
 	int rc;
 
-	rc = bnxt_hwrm_vnic_alloc(bp, vnic_id, start_rx_ring_idx, rx_rings);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, start_rx_ring_idx, rx_rings);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic %d alloc failure rc: %x\n",
-			   vnic_id, rc);
+			   vnic->vnic_id, rc);
 		return rc;
 	}
-	return bnxt_setup_vnic(bp, vnic_id);
+	return bnxt_setup_vnic(bp, vnic);
 }
 
 static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 {
+	struct bnxt_vnic_info *vnic;
 	int i, rc = 0;
 
-	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
-		return bnxt_alloc_and_setup_vnic(bp, BNXT_VNIC_NTUPLE, 0,
-						 bp->rx_nr_rings);
+	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
+		vnic = &bp->vnic_info[BNXT_VNIC_NTUPLE];
+		return bnxt_alloc_and_setup_vnic(bp, vnic, 0, bp->rx_nr_rings);
+	}
 
 	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
 		return 0;
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {
-		struct bnxt_vnic_info *vnic;
 		u16 vnic_id = i + 1;
 		u16 ring_id = i;
 
@@ -9909,12 +9946,104 @@ static int bnxt_alloc_rfs_vnics(struct bnxt *bp)
 		vnic->flags |= BNXT_VNIC_RFS_FLAG;
 		if (bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP)
 			vnic->flags |= BNXT_VNIC_RFS_NEW_RSS_FLAG;
-		if (bnxt_alloc_and_setup_vnic(bp, vnic_id, ring_id, 1))
+		if (bnxt_alloc_and_setup_vnic(bp, &bp->vnic_info[vnic_id], ring_id, 1))
 			break;
 	}
 	return rc;
 }
 
+void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			  bool all)
+{
+	struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+	struct bnxt_filter_base *usr_fltr, *tmp;
+	struct bnxt_ntuple_filter *ntp_fltr;
+	int i;
+
+	bnxt_hwrm_vnic_free_one(bp, &rss_ctx->vnic);
+	for (i = 0; i < BNXT_MAX_CTX_PER_VNIC; i++) {
+		if (vnic->fw_rss_cos_lb_ctx[i] != INVALID_HW_RING_ID)
+			bnxt_hwrm_vnic_ctx_free_one(bp, vnic, i);
+	}
+	if (!all)
+		return;
+
+	list_for_each_entry_safe(usr_fltr, tmp, &bp->usr_fltr_list, list) {
+		if ((usr_fltr->flags & BNXT_ACT_RSS_CTX) &&
+		    usr_fltr->fw_vnic_id == rss_ctx->index) {
+			ntp_fltr = container_of(usr_fltr,
+						struct bnxt_ntuple_filter,
+						base);
+			bnxt_hwrm_cfa_ntuple_filter_free(bp, ntp_fltr);
+			bnxt_del_ntp_filter(bp, ntp_fltr);
+			bnxt_del_one_usr_fltr(bp, usr_fltr);
+		}
+	}
+
+	if (vnic->rss_table)
+		dma_free_coherent(&bp->pdev->dev, vnic->rss_table_size,
+				  vnic->rss_table,
+				  vnic->rss_table_dma_addr);
+	kfree(rss_ctx->rss_indir_tbl);
+	list_del(&rss_ctx->list);
+	bp->num_rss_ctx--;
+	clear_bit(rss_ctx->index, bp->rss_ctx_bmap);
+	kfree(rss_ctx);
+}
+
+static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
+{
+	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list) {
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		if (bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings) ||
+		    bnxt_hwrm_vnic_set_tpa(bp, vnic, set_tpa) ||
+		    __bnxt_setup_vnic_p5(bp, vnic)) {
+			netdev_err(bp->dev, "Failed to restore RSS ctx %d\n",
+				   rss_ctx->index);
+			bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+		}
+	}
+}
+
+struct bnxt_rss_ctx *bnxt_alloc_rss_ctx(struct bnxt *bp)
+{
+	struct bnxt_rss_ctx *rss_ctx = NULL;
+
+	rss_ctx = kzalloc(sizeof(*rss_ctx), GFP_KERNEL);
+	if (rss_ctx) {
+		rss_ctx->vnic.rss_ctx = rss_ctx;
+		list_add_tail(&rss_ctx->list, &bp->rss_ctx_list);
+		bp->num_rss_ctx++;
+	}
+	return rss_ctx;
+}
+
+void bnxt_clear_rss_ctxs(struct bnxt *bp, bool all)
+{
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list)
+		bnxt_del_one_rss_ctx(bp, rss_ctx, all);
+
+	if (all)
+		bitmap_free(bp->rss_ctx_bmap);
+}
+
+static void bnxt_init_multi_rss_ctx(struct bnxt *bp)
+{
+	bp->rss_ctx_bmap = bitmap_zalloc(BNXT_RSS_CTX_BMAP_LEN, GFP_KERNEL);
+	if (bp->rss_ctx_bmap) {
+		/* burn index 0 since we cannot have context 0 */
+		__set_bit(0, bp->rss_ctx_bmap);
+		INIT_LIST_HEAD(&bp->rss_ctx_list);
+		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
+	}
+}
+
 /* Allow PF, trusted VFs and VFs with default VLAN to be in promiscuous mode */
 static bool bnxt_promisc_ok(struct bnxt *bp)
 {
@@ -9927,16 +10056,17 @@ static bool bnxt_promisc_ok(struct bnxt *bp)
 
 static int bnxt_setup_nitroa0_vnic(struct bnxt *bp)
 {
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[1];
 	unsigned int rc = 0;
 
-	rc = bnxt_hwrm_vnic_alloc(bp, 1, bp->rx_nr_rings - 1, 1);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, bp->rx_nr_rings - 1, 1);
 	if (rc) {
 		netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
 			   rc);
 		return rc;
 	}
 
-	rc = bnxt_hwrm_vnic_cfg(bp, 1);
+	rc = bnxt_hwrm_vnic_cfg(bp, vnic);
 	if (rc) {
 		netdev_err(bp->dev, "Cannot allocate special vnic for NS2 A0: %x\n",
 			   rc);
@@ -9979,7 +10109,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 		rx_nr_rings--;
 
 	/* default vnic 0 */
-	rc = bnxt_hwrm_vnic_alloc(bp, BNXT_VNIC_DEFAULT, 0, rx_nr_rings);
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, rx_nr_rings);
 	if (rc) {
 		netdev_err(bp->dev, "hwrm vnic alloc failure rc: %x\n", rc);
 		goto err_out;
@@ -9988,7 +10118,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	if (BNXT_VF(bp))
 		bnxt_hwrm_func_qcfg(bp);
 
-	rc = bnxt_setup_vnic(bp, BNXT_VNIC_DEFAULT);
+	rc = bnxt_setup_vnic(bp, vnic);
 	if (rc)
 		goto err_out;
 	if (bp->rss_cap & BNXT_RSS_CAP_RSS_HASH_TYPE_DELTA)
@@ -11760,6 +11890,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		bnxt_vf_reps_open(bp);
 	bnxt_ptp_init_rtc(bp, true);
 	bnxt_ptp_cfg_tstamp_filters(bp);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_hwrm_realloc_rss_ctx_vnic(bp);
 	bnxt_cfg_usr_fltrs(bp);
 	return 0;
 
@@ -11908,6 +12040,8 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	while (bnxt_drv_busy(bp))
 		msleep(20);
 
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, false);
 	/* Flush rings and disable interrupts */
 	bnxt_shutdown_nic(bp, irq_re_init);
 
@@ -12405,33 +12539,26 @@ static bool bnxt_rfs_supported(struct bnxt *bp)
 }
 
 /* If runtime conditions support RFS */
-static bool bnxt_rfs_capable(struct bnxt *bp)
+bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx)
 {
 	struct bnxt_hw_rings hwr = {0};
 	int max_vnics, max_rss_ctxs;
 
-	hwr.rss_ctx = 1;
-	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp)) {
-		/* 2 VNICS: default + Ntuple */
-		hwr.vnic = 2;
-		hwr.rss_ctx = bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) *
-			      hwr.vnic;
-		goto check_reserve_vnic;
-	}
-	if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+	if ((bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
+	    !BNXT_SUPPORTS_NTUPLE_VNIC(bp))
 		return bnxt_rfs_supported(bp);
+
 	if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp) || !bp->rx_nr_rings)
 		return false;
 
-	hwr.vnic = 1 + bp->rx_nr_rings;
-check_reserve_vnic:
+	hwr.grp = bp->rx_nr_rings;
+	hwr.vnic = bnxt_get_total_vnics(bp, bp->rx_nr_rings);
+	if (new_rss_ctx)
+		hwr.vnic++;
+	hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	max_vnics = bnxt_get_max_func_vnics(bp);
 	max_rss_ctxs = bnxt_get_max_func_rss_ctxs(bp);
 
-	if (!(bp->flags & BNXT_FLAG_CHIP_P5_PLUS) &&
-	    !(bp->rss_cap & BNXT_RSS_CAP_NEW_RSS_CAP))
-		hwr.rss_ctx = hwr.vnic;
-
 	if (hwr.vnic > max_vnics || hwr.rss_ctx > max_rss_ctxs) {
 		if (bp->rx_nr_rings > 1)
 			netdev_warn(bp->dev,
@@ -12465,7 +12592,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	netdev_features_t vlan_features;
 
-	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp))
+	if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp, false))
 		features &= ~NETIF_F_NTUPLE;
 
 	if ((bp->flags & BNXT_FLAG_NO_AGG_RINGS) || bp->xdp_prog)
@@ -13601,7 +13728,7 @@ static void bnxt_set_dflt_rfs(struct bnxt *bp)
 	bp->flags &= ~BNXT_FLAG_RFS;
 	if (bnxt_rfs_supported(bp)) {
 		dev->hw_features |= NETIF_F_NTUPLE;
-		if (bnxt_rfs_capable(bp)) {
+		if (bnxt_rfs_capable(bp, false)) {
 			bp->flags |= BNXT_FLAG_RFS;
 			dev->features |= NETIF_F_NTUPLE;
 		}
@@ -14601,6 +14728,8 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	unregister_netdev(dev);
 	bnxt_free_l2_filters(bp, true);
 	bnxt_free_ntp_fltrs(bp, true);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, true);
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	/* Flush any pending tasks */
 	cancel_work_sync(&bp->sp_task);
@@ -15059,7 +15188,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			bp->flags |= BNXT_FLAG_CHIP_P7;
 	}
 
-	rc = bnxt_alloc_rss_indir_tbl(bp);
+	rc = bnxt_alloc_rss_indir_tbl(bp, NULL);
 	if (rc)
 		goto init_err_pci_clean;
 
@@ -15212,6 +15341,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_LIST_HEAD(&bp->usr_fltr_list);
 
+	if (BNXT_SUPPORTS_NTUPLE_VNIC(bp))
+		bnxt_init_multi_rss_ctx(bp);
+
 	rc = register_netdev(dev);
 	if (rc)
 		goto init_err_cleanup;
@@ -15232,6 +15364,8 @@ init_err_dl:
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, true);
 	bnxt_hwrm_func_drv_unrgtr(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_hwmon_uninit(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index dd849e715c9b..0640fcb57ef8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1256,8 +1256,22 @@ struct bnxt_vnic_info {
 #define BNXT_VNIC_UCAST_FLAG	8
 #define BNXT_VNIC_RFS_NEW_RSS_FLAG	0x10
 #define BNXT_VNIC_NTUPLE_FLAG		0x20
+#define BNXT_VNIC_RSSCTX_FLAG		0x40
+	struct bnxt_rss_ctx	*rss_ctx;
+	u32		vnic_id;
 };
 
+struct bnxt_rss_ctx {
+	struct list_head list;
+	struct bnxt_vnic_info vnic;
+	u16	*rss_indir_tbl;
+	u8	index;
+};
+
+#define BNXT_MAX_ETH_RSS_CTX	32
+#define BNXT_RSS_CTX_BMAP_LEN	(BNXT_MAX_ETH_RSS_CTX + 1)
+#define BNXT_VNIC_ID_INVALID	0xffffffff
+
 struct bnxt_hw_rings {
 	int tx;
 	int rx;
@@ -1360,6 +1374,7 @@ struct bnxt_filter_base {
 #define BNXT_ACT_RING_DST	2
 #define BNXT_ACT_FUNC_DST	4
 #define BNXT_ACT_NO_AGING	8
+#define BNXT_ACT_RSS_CTX	0x10
 	u16			sw_id;
 	u16			rxq;
 	u16			fw_vnic_id;
@@ -2227,6 +2242,9 @@ struct bnxt {
 	/* grp_info indexed by completion ring index */
 	struct bnxt_ring_grp_info	*grp_info;
 	struct bnxt_vnic_info	*vnic_info;
+	struct list_head	rss_ctx_list;
+	unsigned long		*rss_ctx_bmap;
+	u32			num_rss_ctx;
 	int			nr_vnics;
 	u16			*rss_indir_tbl;
 	u16			rss_indir_tbl_entries;
@@ -2241,6 +2259,7 @@ struct bnxt {
 #define BNXT_RSS_CAP_AH_V6_RSS_CAP		BIT(5)
 #define BNXT_RSS_CAP_ESP_V4_RSS_CAP		BIT(6)
 #define BNXT_RSS_CAP_ESP_V6_RSS_CAP		BIT(7)
+#define BNXT_RSS_CAP_MULTI_RSS_CTX		BIT(8)
 
 	u8			rss_hash_key[HW_HASH_KEY_SIZE];
 	u8			rss_hash_key_valid:1;
@@ -2340,6 +2359,10 @@ struct bnxt {
 #define BNXT_SUPPORTS_NTUPLE_VNIC(bp)	\
 	(BNXT_PF(bp) && ((bp)->fw_cap & BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3))
 
+#define BNXT_SUPPORTS_MULTI_RSS_CTX(bp)				\
+	(BNXT_PF(bp) && BNXT_SUPPORTS_NTUPLE_VNIC(bp) &&	\
+	 ((bp)->rss_cap & BNXT_RSS_CAP_MULTI_RSS_CTX))
+
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
 	u16                     hwrm_cmd_kong_seq;
@@ -2693,9 +2716,16 @@ int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 				     struct bnxt_ntuple_filter *fltr);
 int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 				      struct bnxt_ntuple_filter *fltr);
+int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			   u32 tpa_flags);
 void bnxt_fill_ipv6_mask(__be32 mask[4]);
+int bnxt_alloc_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
+void bnxt_set_dflt_rss_indir_tbl(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx);
 int bnxt_get_nr_rss_ctxs(struct bnxt *bp, int rx_rings);
-int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
+int bnxt_hwrm_vnic_cfg(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+int bnxt_hwrm_vnic_alloc(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+			 unsigned int start_rx_ring_idx,
+			 unsigned int nr_rings);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
 int bnxt_nq_rings_in_use(struct bnxt *bp);
 int bnxt_hwrm_set_coal(struct bnxt *);
@@ -2721,6 +2751,12 @@ int bnxt_hwrm_free_wol_fltr(struct bnxt *bp);
 int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all);
 int bnxt_hwrm_func_qcaps(struct bnxt *bp);
 int bnxt_hwrm_fw_set_time(struct bnxt *);
+int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
+void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			  bool all);
+struct bnxt_rss_ctx *bnxt_alloc_rss_ctx(struct bnxt *bp);
+void bnxt_clear_rss_ctxs(struct bnxt *bp, bool all);
 int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
@@ -2728,6 +2764,7 @@ void bnxt_reenable_sriov(struct bnxt *bp);
 void bnxt_close_nic(struct bnxt *, bool, bool);
 void bnxt_get_ring_err_stats(struct bnxt *bp,
 			     struct bnxt_total_ring_err_stats *stats);
+bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx);
 int bnxt_dbg_hwrm_rd_reg(struct bnxt *bp, u32 reg_off, u16 num_words,
 			 u32 *reg_buf);
 void bnxt_fw_exception(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1d240a27455a..9c49f629d565 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -969,6 +969,8 @@ static int bnxt_set_channels(struct net_device *dev,
 	}
 
 	bnxt_clear_usr_fltrs(bp, true);
+	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
+		bnxt_clear_rss_ctxs(bp, false);
 	if (netif_running(dev)) {
 		if (BNXT_PF(bp)) {
 			/* TODO CHIMP_FW: Send message to all VF's
@@ -1205,6 +1207,36 @@ fltr_err:
 	return rc;
 }
 
+static struct bnxt_rss_ctx *bnxt_get_rss_ctx_from_index(struct bnxt *bp,
+							u32 index)
+{
+	struct bnxt_rss_ctx *rss_ctx, *tmp;
+
+	list_for_each_entry_safe(rss_ctx, tmp, &bp->rss_ctx_list, list)
+		if (rss_ctx->index == index)
+			return rss_ctx;
+	return NULL;
+}
+
+static int bnxt_alloc_rss_ctx_rss_table(struct bnxt *bp,
+					struct bnxt_rss_ctx *rss_ctx)
+{
+	int size = L1_CACHE_ALIGN(BNXT_MAX_RSS_TABLE_SIZE_P5);
+	struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+	vnic->rss_table_size = size + HW_HASH_KEY_SIZE;
+	vnic->rss_table = dma_alloc_coherent(&bp->pdev->dev,
+					     vnic->rss_table_size,
+					     &vnic->rss_table_dma_addr,
+					     GFP_KERNEL);
+	if (!vnic->rss_table)
+		return -ENOMEM;
+
+	vnic->rss_hash_key = ((void *)vnic->rss_table) + size;
+	vnic->rss_hash_key_dma_addr = vnic->rss_table_dma_addr + size;
+	return 0;
+}
+
 static int bnxt_add_l2_cls_rule(struct bnxt *bp,
 				struct ethtool_rx_flow_spec *fs)
 {
@@ -1280,22 +1312,24 @@ static bool bnxt_verify_ntuple_ip6_flow(struct ethtool_usrip6_spec *ip_spec,
 }
 
 static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
-				    struct ethtool_rx_flow_spec *fs)
+				    struct ethtool_rxnfc *cmd)
 {
-	u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
-	u32 ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	struct ethtool_rx_flow_spec *fs = &cmd->fs;
 	struct bnxt_ntuple_filter *new_fltr, *fltr;
+	u32 flow_type = fs->flow_type & 0xff;
 	struct bnxt_l2_filter *l2_fltr;
 	struct bnxt_flow_masks *fmasks;
-	u32 flow_type = fs->flow_type;
 	struct flow_keys *fkeys;
-	u32 idx;
+	u32 idx, ring;
 	int rc;
+	u8 vf;
 
 	if (!bp->vnic_info)
 		return -EAGAIN;
 
-	if ((flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
+	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
+	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
+	if ((fs->flow_type & (FLOW_MAC_EXT | FLOW_EXT)) || vf)
 		return -EOPNOTSUPP;
 
 	if (flow_type == IP_USER_FLOW) {
@@ -1403,6 +1437,19 @@ static int bnxt_add_ntuple_cls_rule(struct bnxt *bp,
 	rcu_read_unlock();
 
 	new_fltr->base.flags = BNXT_ACT_NO_AGING;
+	if (fs->flow_type & FLOW_RSS) {
+		struct bnxt_rss_ctx *rss_ctx;
+
+		new_fltr->base.fw_vnic_id = 0;
+		new_fltr->base.flags |= BNXT_ACT_RSS_CTX;
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, cmd->rss_context);
+		if (rss_ctx) {
+			new_fltr->base.fw_vnic_id = rss_ctx->index;
+		} else {
+			rc = -EINVAL;
+			goto ntuple_err;
+		}
+	}
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC)
 		new_fltr->base.flags |= BNXT_ACT_DROP;
 	else
@@ -1444,12 +1491,12 @@ static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	     flow_type == IPV6_USER_FLOW) &&
 	    !(bp->fw_cap & BNXT_FW_CAP_CFA_NTUPLE_RX_EXT_IP_PROTO))
 		return -EOPNOTSUPP;
-	if (flow_type & (FLOW_MAC_EXT | FLOW_RSS))
+	if (flow_type & FLOW_MAC_EXT)
 		return -EINVAL;
 	flow_type &= ~FLOW_EXT;
 
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC && flow_type != ETHER_FLOW)
-		return bnxt_add_ntuple_cls_rule(bp, fs);
+		return bnxt_add_ntuple_cls_rule(bp, cmd);
 
 	ring = ethtool_get_flow_spec_ring(fs->ring_cookie);
 	vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
@@ -1463,7 +1510,7 @@ static int bnxt_srxclsrlins(struct bnxt *bp, struct ethtool_rxnfc *cmd)
 	if (flow_type == ETHER_FLOW)
 		rc = bnxt_add_l2_cls_rule(bp, fs);
 	else
-		rc = bnxt_add_ntuple_cls_rule(bp, fs);
+		rc = bnxt_add_ntuple_cls_rule(bp, cmd);
 	return rc;
 }
 
@@ -1754,7 +1801,10 @@ static u32 bnxt_get_rxfh_key_size(struct net_device *dev)
 static int bnxt_get_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh)
 {
+	u32 rss_context = rxfh->rss_context;
+	struct bnxt_rss_ctx *rss_ctx = NULL;
 	struct bnxt *bp = netdev_priv(dev);
+	u16 *indir_tbl = bp->rss_indir_tbl;
 	struct bnxt_vnic_info *vnic;
 	u32 i, tbl_size;
 
@@ -1764,10 +1814,18 @@ static int bnxt_get_rxfh(struct net_device *dev,
 		return 0;
 
 	vnic = &bp->vnic_info[BNXT_VNIC_DEFAULT];
-	if (rxfh->indir && bp->rss_indir_tbl) {
+	if (rxfh->rss_context) {
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, rss_context);
+		if (!rss_ctx)
+			return -EINVAL;
+		indir_tbl = rss_ctx->rss_indir_tbl;
+		vnic = &rss_ctx->vnic;
+	}
+
+	if (rxfh->indir && indir_tbl) {
 		tbl_size = bnxt_get_rxfh_indir_size(dev);
 		for (i = 0; i < tbl_size; i++)
-			rxfh->indir[i] = bp->rss_indir_tbl[i];
+			rxfh->indir[i] = indir_tbl[i];
 	}
 
 	if (rxfh->key && vnic->rss_hash_key)
@@ -1776,6 +1834,131 @@ static int bnxt_get_rxfh(struct net_device *dev,
 	return 0;
 }
 
+static void bnxt_modify_rss(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
+			    struct ethtool_rxfh_param *rxfh)
+{
+	if (rxfh->key) {
+		if (rss_ctx) {
+			memcpy(rss_ctx->vnic.rss_hash_key, rxfh->key,
+			       HW_HASH_KEY_SIZE);
+		} else {
+			memcpy(bp->rss_hash_key, rxfh->key, HW_HASH_KEY_SIZE);
+			bp->rss_hash_key_updated = true;
+		}
+	}
+	if (rxfh->indir) {
+		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+		u16 *indir_tbl = bp->rss_indir_tbl;
+
+		if (rss_ctx)
+			indir_tbl = rss_ctx->rss_indir_tbl;
+		for (i = 0; i < tbl_size; i++)
+			indir_tbl[i] = rxfh->indir[i];
+		pad = bp->rss_indir_tbl_entries - tbl_size;
+		if (pad)
+			memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
+	}
+}
+
+static int bnxt_set_rxfh_context(struct bnxt *bp,
+				 struct ethtool_rxfh_param *rxfh,
+				 struct netlink_ext_ack *extack)
+{
+	u32 *rss_context = &rxfh->rss_context;
+	struct bnxt_rss_ctx *rss_ctx;
+	struct bnxt_vnic_info *vnic;
+	bool modify = false;
+	int bit_id;
+	int rc;
+
+	if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (*rss_context != ETH_RXFH_CONTEXT_ALLOC) {
+		rss_ctx = bnxt_get_rss_ctx_from_index(bp, *rss_context);
+		if (!rss_ctx) {
+			NL_SET_ERR_MSG_FMT_MOD(extack, "RSS context %u not found",
+					       *rss_context);
+			return -EINVAL;
+		}
+		if (*rss_context && rxfh->rss_delete) {
+			bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+			return 0;
+		}
+		modify = true;
+		vnic = &rss_ctx->vnic;
+		goto modify_context;
+	}
+
+	if (bp->num_rss_ctx >= BNXT_MAX_ETH_RSS_CTX) {
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Out of RSS contexts, maximum %u",
+				       BNXT_MAX_ETH_RSS_CTX);
+		return -EINVAL;
+	}
+
+	if (!bnxt_rfs_capable(bp, true)) {
+		NL_SET_ERR_MSG_MOD(extack, "Out hardware resources");
+		return -ENOMEM;
+	}
+
+	rss_ctx = bnxt_alloc_rss_ctx(bp);
+	if (!rss_ctx)
+		return -ENOMEM;
+
+	vnic = &rss_ctx->vnic;
+	vnic->flags |= BNXT_VNIC_RSSCTX_FLAG;
+	vnic->vnic_id = BNXT_VNIC_ID_INVALID;
+	rc = bnxt_alloc_rss_ctx_rss_table(bp, rss_ctx);
+	if (rc)
+		goto out;
+
+	rc = bnxt_alloc_rss_indir_tbl(bp, rss_ctx);
+	if (rc)
+		goto out;
+
+	bnxt_set_dflt_rss_indir_tbl(bp, rss_ctx);
+	memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE);
+
+	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to allocate VNIC");
+		goto out;
+	}
+
+	rc = bnxt_hwrm_vnic_set_tpa(bp, vnic, bp->flags & BNXT_FLAG_TPA);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to setup TPA");
+		goto out;
+	}
+modify_context:
+	bnxt_modify_rss(bp, rss_ctx, rxfh);
+
+	if (modify)
+		return bnxt_hwrm_vnic_rss_cfg_p5(bp, vnic);
+
+	rc = __bnxt_setup_vnic_p5(bp, vnic);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to setup TPA");
+		goto out;
+	}
+
+	bit_id = bitmap_find_free_region(bp->rss_ctx_bmap,
+					 BNXT_RSS_CTX_BMAP_LEN, 0);
+	if (bit_id < 0) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	rss_ctx->index = (u16)bit_id;
+	*rss_context = rss_ctx->index;
+
+	return 0;
+out:
+	bnxt_del_one_rss_ctx(bp, rss_ctx, true);
+	return rc;
+}
+
 static int bnxt_set_rxfh(struct net_device *dev,
 			 struct ethtool_rxfh_param *rxfh,
 			 struct netlink_ext_ack *extack)
@@ -1786,20 +1969,11 @@ static int bnxt_set_rxfh(struct net_device *dev,
 	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP)
 		return -EOPNOTSUPP;
 
-	if (rxfh->key) {
-		memcpy(bp->rss_hash_key, rxfh->key, HW_HASH_KEY_SIZE);
-		bp->rss_hash_key_updated = true;
-	}
+	if (rxfh->rss_context)
+		return bnxt_set_rxfh_context(bp, rxfh, extack);
 
-	if (rxfh->indir) {
-		u32 i, pad, tbl_size = bnxt_get_rxfh_indir_size(dev);
+	bnxt_modify_rss(bp, NULL, rxfh);
 
-		for (i = 0; i < tbl_size; i++)
-			bp->rss_indir_tbl[i] = rxfh->indir[i];
-		pad = bp->rss_indir_tbl_entries - tbl_size;
-		if (pad)
-			memset(&bp->rss_indir_tbl[i], 0, pad * sizeof(u16));
-	}
 	bnxt_clear_usr_fltrs(bp, false);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
@@ -5071,6 +5245,7 @@ void bnxt_ethtool_free(struct bnxt *bp)
 
 const struct ethtool_ops bnxt_ethtool_ops = {
 	.cap_link_lanes_supported	= 1,
+	.cap_rss_ctx_supported		= 1,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USECS_IRQ |
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index cc07660330f5..345aac4484ee 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -109,7 +109,8 @@ static void bnxt_ptp_get_current_time(struct bnxt *bp)
 	spin_unlock_bh(&ptp->ptp_lock);
 }
 
-static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
+static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts,
+				   u32 txts_tmo)
 {
 	struct hwrm_port_ts_query_output *resp;
 	struct hwrm_port_ts_query_input *req;
@@ -122,10 +123,15 @@ static int bnxt_hwrm_port_ts_query(struct bnxt *bp, u32 flags, u64 *ts)
 	req->flags = cpu_to_le32(flags);
 	if ((flags & PORT_TS_QUERY_REQ_FLAGS_PATH) ==
 	    PORT_TS_QUERY_REQ_FLAGS_PATH_TX) {
+		u32 tmo_us = txts_tmo * 1000;
+
 		req->enables = cpu_to_le16(BNXT_PTP_QTS_TX_ENABLES);
 		req->ptp_seq_id = cpu_to_le32(bp->ptp_cfg->tx_seqid);
 		req->ptp_hdr_offset = cpu_to_le16(bp->ptp_cfg->tx_hdr_off);
-		req->ts_req_timeout = cpu_to_le16(BNXT_PTP_QTS_TIMEOUT);
+		if (!tmo_us)
+			tmo_us = BNXT_PTP_QTS_TIMEOUT;
+		tmo_us = min(tmo_us, BNXT_PTP_QTS_MAX_TMO_US);
+		req->ts_req_timeout = cpu_to_le16(txts_tmo);
 	}
 	resp = hwrm_req_hold(bp, req);
 
@@ -672,10 +678,17 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 {
 	struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
 	struct skb_shared_hwtstamps timestamp;
+	unsigned long now = jiffies;
 	u64 ts = 0, ns = 0;
+	u32 tmo = 0;
 	int rc;
 
-	rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_PATH_TX, &ts);
+	if (!ptp->txts_pending)
+		ptp->abs_txts_tmo = now + msecs_to_jiffies(ptp->txts_tmo);
+	if (!time_after_eq(now, ptp->abs_txts_tmo))
+		tmo = jiffies_to_msecs(ptp->abs_txts_tmo - now);
+	rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_PATH_TX, &ts,
+				     tmo);
 	if (!rc) {
 		memset(&timestamp, 0, sizeof(timestamp));
 		spin_lock_bh(&ptp->ptp_lock);
@@ -684,6 +697,10 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
+		if (!time_after_eq(jiffies, ptp->abs_txts_tmo)) {
+			ptp->txts_pending = true;
+			return;
+		}
 		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
@@ -691,6 +708,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 	dev_kfree_skb_any(ptp->tx_skb);
 	ptp->tx_skb = NULL;
 	atomic_inc(&ptp->tx_avail);
+	ptp->txts_pending = false;
 }
 
 static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
@@ -714,6 +732,8 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
 		spin_unlock_bh(&ptp->ptp_lock);
 		ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
 	}
+	if (ptp->txts_pending)
+		return 0;
 	return HZ;
 }
 
@@ -891,7 +911,8 @@ int bnxt_ptp_init_rtc(struct bnxt *bp, bool phc_cfg)
 		if (rc)
 			return rc;
 	} else {
-		rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME, &ns);
+		rc = bnxt_hwrm_port_ts_query(bp, PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME,
+					     &ns, 0);
 		if (rc)
 			return rc;
 	}
@@ -965,6 +986,7 @@ int bnxt_ptp_init(struct bnxt *bp, bool phc_cfg)
 		spin_unlock_bh(&ptp->ptp_lock);
 		ptp_schedule_worker(ptp->ptp_clock, 0);
 	}
+	ptp->txts_tmo = BNXT_PTP_DFLT_TX_TMO;
 	return 0;
 
 out:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index fce8dc39a7d0..6a2bba3f9e2d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -22,7 +22,9 @@
 #define BNXT_LO_TIMER_MASK	0x0000ffffffffUL
 #define BNXT_HI_TIMER_MASK	0xffff00000000UL
 
+#define BNXT_PTP_DFLT_TX_TMO	1000 /* ms */
 #define BNXT_PTP_QTS_TIMEOUT	1000
+#define BNXT_PTP_QTS_MAX_TMO_US	65535
 #define BNXT_PTP_QTS_TX_ENABLES	(PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID |	\
 				 PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT | \
 				 PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET)
@@ -115,11 +117,14 @@ struct bnxt_ptp_cfg {
 					 BNXT_PTP_MSG_PDELAY_REQ |	\
 					 BNXT_PTP_MSG_PDELAY_RESP)
 	u8			tx_tstamp_en:1;
+	u8			txts_pending:1;
 	int			rx_filter;
 	u32			tstamp_filters;
 
 	u32			refclk_regs[2];
 	u32			refclk_mapped_regs[2];
+	u32			txts_tmo;
+	unsigned long		abs_txts_tmo;
 };
 
 #if BITS_PER_LONG == 32
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 93f9bd55020f..86dcd2c76587 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -71,7 +71,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	rcu_assign_pointer(ulp->ulp_ops, ulp_ops);
 
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
-		bnxt_hwrm_vnic_cfg(bp, 0);
+		bnxt_hwrm_vnic_cfg(bp, &bp->vnic_info[BNXT_VNIC_DEFAULT]);
 
 	bnxt_fill_msix_vecs(bp, bp->edev->msix_entries);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;