Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Support offloading wireless authentication to userspace via
    NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.

 2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
    Setup and cleanup of namespaces now all run asynchronously and thus
    performance is significantly increased.

 3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
    Streiff.

 4) Support zerocopy on RDS sockets, from Sowmini Varadhan.

 5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
    Borkmann.

 6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
    Chevallier.

 7) Support grafting of child qdiscs in mlxsw driver, from Nogah
    Frankel.

 8) Add packet forwarding tests to selftests, from Ido Schimmel.

 9) Deal with sub-optimal GSO packets better in BBR congestion control,
    from Eric Dumazet.

10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.

11) Add path MTU tests to selftests, from Stefano Brivio.

12) Various bits of IPSEC offloading support for mlx5, from Aviad
    Yehezkel, Yossi Kuperman, and Saeed Mahameed.

13) Support RSS spreading on ntuple filters in SFC driver, from Edward
    Cree.

14) Lots of sockmap work from John Fastabend. Applications can use eBPF
    to filter sendmsg and sendpage operations.

15) In-kernel receive TLS support, from Dave Watson.

16) Add XDP support to ixgbevf, this is significant because it should
    allow optimized XDP usage in various cloud environments. From Tony
    Nguyen.

17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
    Venkataramanan et al.

18) IP fragmentation match offload support in nfp driver, from Pieter
    Jansen van Vuuren.

19) Support XDP redirect in i40e driver, from Björn Töpel.

20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
    tracepoints in their raw form, from Alexei Starovoitov.

21) Lots of striding RQ improvements to mlx5 driver with many
    performance improvements, from Tariq Toukan.

22) Use rhashtable for inet frag reassembly, from Eric Dumazet.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
  net: mvneta: improve suspend/resume
  net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
  ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
  net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
  net: bgmac: Correctly annotate register space
  route: check sysctl_fib_multipath_use_neigh earlier than hash
  fix typo in command value in drivers/net/phy/mdio-bitbang.
  sky2: Increase D3 delay to sky2 stops working after suspend
  net/mlx5e: Set EQE based as default TX interrupt moderation mode
  ibmvnic: Disable irqs before exiting reset from closed state
  net: sched: do not emit messages while holding spinlock
  vlan: also check phy_driver ts_info for vlan's real device
  Bluetooth: Mark expected switch fall-throughs
  Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
  Bluetooth: btrsi: remove unused including <linux/version.h>
  Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
  sh_eth: kill useless check in __sh_eth_get_regs()
  sh_eth: add sh_eth_cpu_data::no_xdfar flag
  ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
  ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
  ...

1 files changed, 243 insertions, 98 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c7e5e6f09647..1991f0c7bc0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1922,7 +1922,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
 		/* Sync BD data before updating doorbell */
 		wmb();
 
-		bnxt_db_write(bp, db, DB_KEY_TX | prod);
+		bnxt_db_write_relaxed(bp, db, DB_KEY_TX | prod);
 	}
 
 	cpr->cp_raw_cons = raw_cons;
@@ -2317,6 +2317,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 			if (rc)
 				return rc;
 
+			ring->grp_idx = i;
 			rxr->rx_agg_bmap_size = bp->rx_agg_ring_mask + 1;
 			mem_size = rxr->rx_agg_bmap_size / 8;
 			rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL);
@@ -2389,6 +2390,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp)
 		if (rc)
 			return rc;
 
+		ring->grp_idx = txr->bnapi->index;
 		if (bp->tx_push_size) {
 			dma_addr_t mapping;
 
@@ -2442,8 +2444,10 @@ static void bnxt_free_cp_rings(struct bnxt *bp)
 
 static int bnxt_alloc_cp_rings(struct bnxt *bp)
 {
-	int i, rc;
+	int i, rc, ulp_base_vec, ulp_msix;
 
+	ulp_msix = bnxt_get_ulp_msix_num(bp);
+	ulp_base_vec = bnxt_get_ulp_msix_base(bp);
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr;
@@ -2458,6 +2462,11 @@ static int bnxt_alloc_cp_rings(struct bnxt *bp)
 		rc = bnxt_alloc_ring(bp, ring);
 		if (rc)
 			return rc;
+
+		if (ulp_msix && i >= ulp_base_vec)
+			ring->map_idx = i + ulp_msix;
+		else
+			ring->map_idx = i;
 	}
 	return 0;
 }
@@ -3059,12 +3068,21 @@ static void bnxt_free_stats(struct bnxt *bp)
 	u32 size, i;
 	struct pci_dev *pdev = bp->pdev;
 
+	bp->flags &= ~BNXT_FLAG_PORT_STATS;
+	bp->flags &= ~BNXT_FLAG_PORT_STATS_EXT;
+
 	if (bp->hw_rx_port_stats) {
 		dma_free_coherent(&pdev->dev, bp->hw_port_stats_size,
 				  bp->hw_rx_port_stats,
 				  bp->hw_rx_port_stats_map);
 		bp->hw_rx_port_stats = NULL;
-		bp->flags &= ~BNXT_FLAG_PORT_STATS;
+	}
+
+	if (bp->hw_rx_port_stats_ext) {
+		dma_free_coherent(&pdev->dev, sizeof(struct rx_port_stats_ext),
+				  bp->hw_rx_port_stats_ext,
+				  bp->hw_rx_port_stats_ext_map);
+		bp->hw_rx_port_stats_ext = NULL;
 	}
 
 	if (!bp->bnapi)
@@ -3120,6 +3138,21 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 		bp->hw_tx_port_stats_map = bp->hw_rx_port_stats_map +
 					   sizeof(struct rx_port_stats) + 512;
 		bp->flags |= BNXT_FLAG_PORT_STATS;
+
+		/* Display extended statistics only if FW supports it */
+		if (bp->hwrm_spec_code < 0x10804 ||
+		    bp->hwrm_spec_code == 0x10900)
+			return 0;
+
+		bp->hw_rx_port_stats_ext =
+			dma_zalloc_coherent(&pdev->dev,
+					    sizeof(struct rx_port_stats_ext),
+					    &bp->hw_rx_port_stats_ext_map,
+					    GFP_KERNEL);
+		if (!bp->hw_rx_port_stats_ext)
+			return 0;
+
+		bp->flags |= BNXT_FLAG_PORT_STATS_EXT;
 	}
 	return 0;
 }
@@ -3357,6 +3390,15 @@ static void bnxt_disable_int(struct bnxt *bp)
 	}
 }
 
+static int bnxt_cp_num_to_irq_num(struct bnxt *bp, int n)
+{
+	struct bnxt_napi *bnapi = bp->bnapi[n];
+	struct bnxt_cp_ring_info *cpr;
+
+	cpr = &bnapi->cp_ring;
+	return cpr->cp_ring_struct.map_idx;
+}
+
 static void bnxt_disable_int_sync(struct bnxt *bp)
 {
 	int i;
@@ -3364,8 +3406,11 @@ static void bnxt_disable_int_sync(struct bnxt *bp)
 	atomic_inc(&bp->intr_sem);
 
 	bnxt_disable_int(bp);
-	for (i = 0; i < bp->cp_nr_rings; i++)
-		synchronize_irq(bp->irq_tbl[i].vector);
+	for (i = 0; i < bp->cp_nr_rings; i++) {
+		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
+
+		synchronize_irq(bp->irq_tbl[map_idx].vector);
+	}
 }
 
 static void bnxt_enable_int(struct bnxt *bp)
@@ -3398,7 +3443,8 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	int i, intr_process, rc, tmo_count;
 	struct input *req = msg;
 	u32 *data = msg;
-	__le32 *resp_len, *valid;
+	__le32 *resp_len;
+	u8 *valid;
 	u16 cp_ring_id, len = 0;
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
@@ -3450,6 +3496,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 
 	i = 0;
 	tmo_count = timeout * 40;
+	resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
 	if (intr_process) {
 		/* Wait until hwrm response cmpl interrupt is processed */
 		while (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID &&
@@ -3462,9 +3509,11 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 				   le16_to_cpu(req->req_type));
 			return -1;
 		}
+		len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
+		      HWRM_RESP_LEN_SFT;
+		valid = bp->hwrm_cmd_resp_addr + len - 1;
 	} else {
 		/* Check if response len is updated */
-		resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
 		for (i = 0; i < tmo_count; i++) {
 			len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
 			      HWRM_RESP_LEN_SFT;
@@ -3480,10 +3529,12 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			return -1;
 		}
 
-		/* Last word of resp contains valid bit */
-		valid = bp->hwrm_cmd_resp_addr + len - 4;
+		/* Last byte of resp contains valid bit */
+		valid = bp->hwrm_cmd_resp_addr + len - 1;
 		for (i = 0; i < 5; i++) {
-			if (le32_to_cpu(*valid) & HWRM_RESP_VALID_MASK)
+			/* make sure we read from updated DMA memory */
+			dma_rmb();
+			if (*valid)
 				break;
 			udelay(1);
 		}
@@ -3496,6 +3547,11 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 	}
 
+	/* Zero valid bit for compatibility.  Valid bit in an older spec
+	 * may become a new field in a newer spec.  We must make sure that
+	 * a new field not implemented by old spec will read zero.
+	 */
+	*valid = 0;
 	rc = le16_to_cpu(resp->error_code);
 	if (rc && !silent)
 		netdev_err(bp->dev, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n",
@@ -3577,9 +3633,13 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			    FUNC_DRV_RGTR_REQ_ENABLES_VER);
 
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
-	req.ver_maj = DRV_VER_MAJ;
-	req.ver_min = DRV_VER_MIN;
-	req.ver_upd = DRV_VER_UPD;
+	req.flags = cpu_to_le32(FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE);
+	req.ver_maj_8b = DRV_VER_MAJ;
+	req.ver_min_8b = DRV_VER_MIN;
+	req.ver_upd_8b = DRV_VER_UPD;
+	req.ver_maj = cpu_to_le16(DRV_VER_MAJ);
+	req.ver_min = cpu_to_le16(DRV_VER_MIN);
+	req.ver_upd = cpu_to_le16(DRV_VER_UPD);
 
 	if (BNXT_PF(bp)) {
 		u32 data[8];
@@ -3998,6 +4058,13 @@ static int bnxt_hwrm_vnic_ctx_alloc(struct bnxt *bp, u16 vnic_id, u16 ctx_idx)
 	return rc;
 }
 
+static u32 bnxt_get_roce_vnic_mode(struct bnxt *bp)
+{
+	if (bp->flags & BNXT_FLAG_ROCE_MIRROR_CAP)
+		return VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE;
+	return VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE;
+}
+
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 {
 	unsigned int ring = 0, grp_idx;
@@ -4053,8 +4120,7 @@ int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id)
 	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, BNXT_ROCE_ULP))
-		req.flags |=
-			cpu_to_le32(VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE);
+		req.flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp));
 
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
@@ -4135,9 +4201,13 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp)
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		if (resp->flags &
-		    cpu_to_le32(VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP))
+		u32 flags = le32_to_cpu(resp->flags);
+
+		if (flags & VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP)
 			bp->flags |= BNXT_FLAG_NEW_RSS_CAP;
+		if (flags &
+		    VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP)
+			bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -4204,12 +4274,12 @@ static int bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 				    struct bnxt_ring_struct *ring,
-				    u32 ring_type, u32 map_index,
-				    u32 stats_ctx_id)
+				    u32 ring_type, u32 map_index)
 {
 	int rc = 0, err = 0;
 	struct hwrm_ring_alloc_input req = {0};
 	struct hwrm_ring_alloc_output *resp = bp->hwrm_cmd_resp_addr;
+	struct bnxt_ring_grp_info *grp_info;
 	u16 ring_id;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_ALLOC, -1, -1);
@@ -4231,10 +4301,10 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 	case HWRM_RING_ALLOC_TX:
 		req.ring_type = RING_ALLOC_REQ_RING_TYPE_TX;
 		/* Association of transmit ring with completion ring */
-		req.cmpl_ring_id =
-			cpu_to_le16(bp->grp_info[map_index].cp_fw_ring_id);
+		grp_info = &bp->grp_info[ring->grp_idx];
+		req.cmpl_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
 		req.length = cpu_to_le32(bp->tx_ring_mask + 1);
-		req.stat_ctx_id = cpu_to_le32(stats_ctx_id);
+		req.stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
 		req.queue_id = cpu_to_le16(ring->queue_id);
 		break;
 	case HWRM_RING_ALLOC_RX:
@@ -4321,10 +4391,11 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 		struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+		u32 map_idx = ring->map_idx;
 
-		cpr->cp_doorbell = bp->bar1 + i * 0x80;
-		rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_CMPL, i,
-					      INVALID_STATS_CTX_ID);
+		cpr->cp_doorbell = bp->bar1 + map_idx * 0x80;
+		rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_CMPL,
+					      map_idx);
 		if (rc)
 			goto err_out;
 		BNXT_CP_DB(cpr->cp_doorbell, cpr->cp_raw_cons);
@@ -4340,11 +4411,10 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 map_idx = txr->bnapi->index;
-		u16 fw_stats_ctx = bp->grp_info[map_idx].fw_stats_ctx;
+		u32 map_idx = i;
 
 		rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_TX,
-					      map_idx, fw_stats_ctx);
+					      map_idx);
 		if (rc)
 			goto err_out;
 		txr->tx_doorbell = bp->bar1 + map_idx * 0x80;
@@ -4356,7 +4426,7 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		u32 map_idx = rxr->bnapi->index;
 
 		rc = hwrm_ring_alloc_send_msg(bp, ring, HWRM_RING_ALLOC_RX,
-					      map_idx, INVALID_STATS_CTX_ID);
+					      map_idx);
 		if (rc)
 			goto err_out;
 		rxr->rx_doorbell = bp->bar1 + map_idx * 0x80;
@@ -4369,13 +4439,12 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 			struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 			struct bnxt_ring_struct *ring =
 						&rxr->rx_agg_ring_struct;
-			u32 grp_idx = rxr->bnapi->index;
+			u32 grp_idx = ring->grp_idx;
 			u32 map_idx = grp_idx + bp->rx_nr_rings;
 
 			rc = hwrm_ring_alloc_send_msg(bp, ring,
 						      HWRM_RING_ALLOC_AGG,
-						      map_idx,
-						      INVALID_STATS_CTX_ID);
+						      map_idx);
 			if (rc)
 				goto err_out;
 
@@ -4669,20 +4738,59 @@ static int bnxt_hwrm_reserve_rings(struct bnxt *bp, int tx, int rx, int grp,
 		return bnxt_hwrm_reserve_vf_rings(bp, tx, rx, grp, cp, vnic);
 }
 
+static int bnxt_cp_rings_in_use(struct bnxt *bp)
+{
+	int cp = bp->cp_nr_rings;
+	int ulp_msix, ulp_base;
+
+	ulp_msix = bnxt_get_ulp_msix_num(bp);
+	if (ulp_msix) {
+		ulp_base = bnxt_get_ulp_msix_base(bp);
+		cp += ulp_msix;
+		if ((ulp_base + ulp_msix) > cp)
+			cp = ulp_base + ulp_msix;
+	}
+	return cp;
+}
+
+static bool bnxt_need_reserve_rings(struct bnxt *bp)
+{
+	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+	int cp = bnxt_cp_rings_in_use(bp);
+	int rx = bp->rx_nr_rings;
+	int vnic = 1, grp = rx;
+
+	if (bp->hwrm_spec_code < 0x10601)
+		return false;
+
+	if (hw_resc->resv_tx_rings != bp->tx_nr_rings)
+		return true;
+
+	if (bp->flags & BNXT_FLAG_RFS)
+		vnic = rx + 1;
+	if (bp->flags & BNXT_FLAG_AGG_RINGS)
+		rx <<= 1;
+	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
+	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
+	     hw_resc->resv_hw_ring_grps != grp || hw_resc->resv_vnics != vnic))
+		return true;
+	return false;
+}
+
 static int bnxt_trim_rings(struct bnxt *bp, int *rx, int *tx, int max,
 			   bool shared);
 
 static int __bnxt_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+	int cp = bnxt_cp_rings_in_use(bp);
 	int tx = bp->tx_nr_rings;
 	int rx = bp->rx_nr_rings;
-	int cp = bp->cp_nr_rings;
 	int grp, rx_rings, rc;
 	bool sh = false;
 	int vnic = 1;
 
-	if (bp->hwrm_spec_code < 0x10601)
+	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
 	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -4691,14 +4799,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
-
 	grp = bp->rx_nr_rings;
-	if (tx == hw_resc->resv_tx_rings &&
-	    (!(bp->flags & BNXT_FLAG_NEW_RM) ||
-	      (rx == hw_resc->resv_rx_rings &&
-	       grp == hw_resc->resv_hw_ring_grps &&
-	       cp == hw_resc->resv_cp_rings && vnic == hw_resc->resv_vnics)))
-		return 0;
 
 	rc = bnxt_hwrm_reserve_rings(bp, tx, rx, grp, cp, vnic);
 	if (rc)
@@ -4742,30 +4843,6 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	return rc;
 }
 
-static bool bnxt_need_reserve_rings(struct bnxt *bp)
-{
-	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	int rx = bp->rx_nr_rings;
-	int vnic = 1;
-
-	if (bp->hwrm_spec_code < 0x10601)
-		return false;
-
-	if (hw_resc->resv_tx_rings != bp->tx_nr_rings)
-		return true;
-
-	if (bp->flags & BNXT_FLAG_RFS)
-		vnic = rx + 1;
-	if (bp->flags & BNXT_FLAG_AGG_RINGS)
-		rx <<= 1;
-	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
-	    (hw_resc->resv_rx_rings != rx ||
-	     hw_resc->resv_cp_rings != bp->cp_nr_rings ||
-	     hw_resc->resv_vnics != vnic))
-		return true;
-	return false;
-}
-
 static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 				    int ring_grps, int cp_rings, int vnics)
 {
@@ -5055,7 +5132,7 @@ func_qcfg_exit:
 	return rc;
 }
 
-static int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp)
+int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 {
 	struct hwrm_func_resource_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_resource_qcaps_input req = {0};
@@ -5072,6 +5149,10 @@ static int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp)
 		goto hwrm_func_resc_qcaps_exit;
 	}
 
+	hw_resc->max_tx_sch_inputs = le16_to_cpu(resp->max_tx_scheduler_inputs);
+	if (!all)
+		goto hwrm_func_resc_qcaps_exit;
+
 	hw_resc->min_rsscos_ctxs = le16_to_cpu(resp->min_rsscos_ctx);
 	hw_resc->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx);
 	hw_resc->min_cp_rings = le16_to_cpu(resp->min_cmpl_rings);
@@ -5178,7 +5259,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	if (rc)
 		return rc;
 	if (bp->hwrm_spec_code >= 0x10803) {
-		rc = bnxt_hwrm_func_resc_qcaps(bp);
+		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
 		if (!rc)
 			bp->flags |= BNXT_FLAG_NEW_RM;
 	}
@@ -5326,6 +5407,21 @@ static int bnxt_hwrm_port_qstats(struct bnxt *bp)
 	return rc;
 }
 
+static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
+{
+	struct hwrm_port_qstats_ext_input req = {0};
+	struct bnxt_pf_info *pf = &bp->pf;
+
+	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_QSTATS_EXT, -1, -1);
+	req.port_id = cpu_to_le16(pf->port_id);
+	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
+	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
 static void bnxt_hwrm_free_tunnel_ports(struct bnxt *bp)
 {
 	if (bp->vxlan_port_cnt) {
@@ -5418,10 +5514,9 @@ static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size)
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 	req.fid = cpu_to_le16(0xffff);
 	req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE);
-	req.cache_linesize = FUNC_QCFG_RESP_CACHE_LINESIZE_CACHE_LINESIZE_64;
+	req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64;
 	if (size == 128)
-		req.cache_linesize =
-			FUNC_QCFG_RESP_CACHE_LINESIZE_CACHE_LINESIZE_128;
+		req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128;
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
@@ -5740,6 +5835,7 @@ static void bnxt_setup_msix(struct bnxt *bp)
 	}
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
+		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		char *attr;
 
 		if (bp->flags & BNXT_FLAG_SHARED_RINGS)
@@ -5749,9 +5845,9 @@ static void bnxt_setup_msix(struct bnxt *bp)
 		else
 			attr = "tx";
 
-		snprintf(bp->irq_tbl[i].name, len, "%s-%s-%d", dev->name, attr,
-			 i);
-		bp->irq_tbl[i].handler = bnxt_msix;
+		snprintf(bp->irq_tbl[map_idx].name, len, "%s-%s-%d", dev->name,
+			 attr, i);
+		bp->irq_tbl[map_idx].handler = bnxt_msix;
 	}
 }
 
@@ -5812,7 +5908,7 @@ void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max)
 	bp->hw_resc.max_cp_rings = max;
 }
 
-static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
+unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
@@ -5824,12 +5920,44 @@ void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 	bp->hw_resc.max_irqs = max_irqs;
 }
 
+int bnxt_get_avail_msix(struct bnxt *bp, int num)
+{
+	int max_cp = bnxt_get_max_func_cp_rings(bp);
+	int max_irq = bnxt_get_max_func_irqs(bp);
+	int total_req = bp->cp_nr_rings + num;
+	int max_idx, avail_msix;
+
+	max_idx = min_t(int, bp->total_irqs, max_cp);
+	avail_msix = max_idx - bp->cp_nr_rings;
+	if (!(bp->flags & BNXT_FLAG_NEW_RM) || avail_msix >= num)
+		return avail_msix;
+
+	if (max_irq < total_req) {
+		num = max_irq - bp->cp_nr_rings;
+		if (num <= 0)
+			return 0;
+	}
+	return num;
+}
+
+static int bnxt_get_num_msix(struct bnxt *bp)
+{
+	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+		return bnxt_get_max_func_irqs(bp);
+
+	return bnxt_cp_rings_in_use(bp);
+}
+
 static int bnxt_init_msix(struct bnxt *bp)
 {
-	int i, total_vecs, rc = 0, min = 1;
+	int i, total_vecs, max, rc = 0, min = 1, ulp_msix;
 	struct msix_entry *msix_ent;
 
-	total_vecs = bnxt_get_max_func_irqs(bp);
+	total_vecs = bnxt_get_num_msix(bp);
+	max = bnxt_get_max_func_irqs(bp);
+	if (total_vecs > max)
+		total_vecs = max;
+
 	msix_ent = kcalloc(total_vecs, sizeof(struct msix_entry), GFP_KERNEL);
 	if (!msix_ent)
 		return -ENOMEM;
@@ -5843,7 +5971,8 @@ static int bnxt_init_msix(struct bnxt *bp)
 		min = 2;
 
 	total_vecs = pci_enable_msix_range(bp->pdev, msix_ent, min, total_vecs);
-	if (total_vecs < 0) {
+	ulp_msix = bnxt_get_ulp_msix_num(bp);
+	if (total_vecs < 0 || total_vecs < ulp_msix) {
 		rc = -ENODEV;
 		goto msix_setup_exit;
 	}
@@ -5856,7 +5985,7 @@ static int bnxt_init_msix(struct bnxt *bp)
 		bp->total_irqs = total_vecs;
 		/* Trim rings based upon num of vectors allocated */
 		rc = bnxt_trim_rings(bp, &bp->rx_nr_rings, &bp->tx_nr_rings,
-				     total_vecs, min == 1);
+				     total_vecs - ulp_msix, min == 1);
 		if (rc)
 			goto msix_setup_exit;
 
@@ -5920,9 +6049,8 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 	bp->flags &= ~BNXT_FLAG_USING_MSIX;
 }
 
-static int bnxt_reserve_rings(struct bnxt *bp)
+int bnxt_reserve_rings(struct bnxt *bp)
 {
-	int orig_cp = bp->hw_resc.resv_cp_rings;
 	int tcs = netdev_get_num_tc(bp->dev);
 	int rc;
 
@@ -5934,9 +6062,12 @@ static int bnxt_reserve_rings(struct bnxt *bp)
 		netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc);
 		return rc;
 	}
-	if ((bp->flags & BNXT_FLAG_NEW_RM) && bp->cp_nr_rings > orig_cp) {
+	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
+	    (bnxt_get_num_msix(bp) != bp->total_irqs)) {
+		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
 		rc = bnxt_init_int_mode(bp);
+		bnxt_ulp_irq_restart(bp, rc);
 		if (rc)
 			return rc;
 	}
@@ -5963,7 +6094,9 @@ static void bnxt_free_irq(struct bnxt *bp)
 		return;
 
 	for (i = 0; i < bp->cp_nr_rings; i++) {
-		irq = &bp->irq_tbl[i];
+		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
+
+		irq = &bp->irq_tbl[map_idx];
 		if (irq->requested) {
 			if (irq->have_cpumask) {
 				irq_set_affinity_hint(irq->vector, NULL);
@@ -5982,14 +6115,25 @@ static int bnxt_request_irq(struct bnxt *bp)
 	int i, j, rc = 0;
 	unsigned long flags = 0;
 #ifdef CONFIG_RFS_ACCEL
-	struct cpu_rmap *rmap = bp->dev->rx_cpu_rmap;
+	struct cpu_rmap *rmap;
 #endif
 
+	rc = bnxt_setup_int_mode(bp);
+	if (rc) {
+		netdev_err(bp->dev, "bnxt_setup_int_mode err: %x\n",
+			   rc);
+		return rc;
+	}
+#ifdef CONFIG_RFS_ACCEL
+	rmap = bp->dev->rx_cpu_rmap;
+#endif
 	if (!(bp->flags & BNXT_FLAG_USING_MSIX))
 		flags = IRQF_SHARED;
 
 	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
-		struct bnxt_irq *irq = &bp->irq_tbl[i];
+		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
+		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
+
 #ifdef CONFIG_RFS_ACCEL
 		if (rmap && bp->bnapi[i]->rx_ring) {
 			rc = irq_cpu_rmap_add(rmap, irq->vector);
@@ -6709,13 +6853,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = bnxt_reserve_rings(bp);
 		if (rc)
 			return rc;
-
-		rc = bnxt_setup_int_mode(bp);
-		if (rc) {
-			netdev_err(bp->dev, "bnxt_setup_int_mode err: %x\n",
-				   rc);
-			return rc;
-		}
 	}
 	if ((bp->flags & BNXT_FLAG_RFS) &&
 	    !(bp->flags & BNXT_FLAG_USING_MSIX)) {
@@ -7478,8 +7615,10 @@ static void bnxt_sp_task(struct work_struct *work)
 		bnxt_hwrm_tunnel_dst_port_free(
 			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
 	}
-	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
+	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event)) {
 		bnxt_hwrm_port_qstats(bp);
+		bnxt_hwrm_port_qstats_ext(bp);
+	}
 
 	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
 		int rc;
@@ -8193,6 +8332,7 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_set_vf_rate	= bnxt_set_vf_bw,
 	.ndo_set_vf_link_state	= bnxt_set_vf_link_state,
 	.ndo_set_vf_spoofchk	= bnxt_set_vf_spoofchk,
+	.ndo_set_vf_trust	= bnxt_set_vf_trust,
 #endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= bnxt_poll_controller,
@@ -8390,9 +8530,15 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 	if (sh)
 		bp->flags |= BNXT_FLAG_SHARED_RINGS;
 	dflt_rings = netif_get_num_default_rss_queues();
-	/* Reduce default rings to reduce memory usage on multi-port cards */
-	if (bp->port_count > 1)
-		dflt_rings = min_t(int, dflt_rings, 4);
+	/* Reduce default rings on multi-port cards so that total default
+	 * rings do not exceed CPU count.
+	 */
+	if (bp->port_count > 1) {
+		int max_rings =
+			max_t(int, num_online_cpus() / bp->port_count, 1);
+
+		dflt_rings = min_t(int, dflt_rings, max_rings);
+	}
 	rc = bnxt_get_dflt_rings(bp, &max_rx_rings, &max_tx_rings, sh);
 	if (rc)
 		return rc;
@@ -8431,16 +8577,15 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 	int rc;
 
 	ASSERT_RTNL();
-	if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
-		return 0;
-
 	bnxt_hwrm_func_qcaps(bp);
 
 	if (netif_running(bp->dev))
 		__bnxt_close_nic(bp, true, false);
 
+	bnxt_ulp_irq_stop(bp);
 	bnxt_clear_int_mode(bp);
 	rc = bnxt_init_int_mode(bp);
+	bnxt_ulp_irq_restart(bp, rc);
 
 	if (netif_running(bp->dev)) {
 		if (rc)