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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 166 insertions, 64 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 3e81af1884fc..fe88b127ca42 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -120,12 +120,14 @@ static void ice_pf_dcb_recfg(struct ice_pf *pf)
 			tc_map = ICE_DFLT_TRAFFIC_CLASS;
 
 		ret = ice_vsi_cfg_tc(pf->vsi[v], tc_map);
-		if (ret)
+		if (ret) {
 			dev_err(&pf->pdev->dev,
 				"Failed to config TC for VSI index: %d\n",
 				pf->vsi[v]->idx);
-		else
-			ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+			continue;
+		}
+
+		ice_vsi_map_rings_to_vectors(pf->vsi[v]);
 	}
 }
 
@@ -133,8 +135,10 @@ static void ice_pf_dcb_recfg(struct ice_pf *pf)
  * ice_pf_dcb_cfg - Apply new DCB configuration
  * @pf: pointer to the PF struct
  * @new_cfg: DCBX config to apply
+ * @locked: is the RTNL held
  */
-static int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg)
+static
+int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)
 {
 	struct ice_dcbx_cfg *old_cfg, *curr_cfg;
 	struct ice_aqc_port_ets_elem buf = { 0 };
@@ -163,7 +167,8 @@ static int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg)
 	/* avoid race conditions by holding the lock while disabling and
 	 * re-enabling the VSI
 	 */
-	rtnl_lock();
+	if (!locked)
+		rtnl_lock();
 	ice_pf_dis_all_vsi(pf, true);
 
 	memcpy(curr_cfg, new_cfg, sizeof(*curr_cfg));
@@ -192,7 +197,8 @@ static int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg)
 
 out:
 	ice_pf_ena_all_vsi(pf, true);
-	rtnl_unlock();
+	if (!locked)
+		rtnl_unlock();
 	devm_kfree(&pf->pdev->dev, old_cfg);
 	return ret;
 }
@@ -271,15 +277,16 @@ dcb_error:
 	prev_cfg->etscfg.tcbwtable[0] = ICE_TC_MAX_BW;
 	prev_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS;
 	memcpy(&prev_cfg->etsrec, &prev_cfg->etscfg, sizeof(prev_cfg->etsrec));
-	ice_pf_dcb_cfg(pf, prev_cfg);
+	ice_pf_dcb_cfg(pf, prev_cfg, false);
 	devm_kfree(&pf->pdev->dev, prev_cfg);
 }
 
 /**
  * ice_dcb_init_cfg - set the initial DCB config in SW
- * @pf: pf to apply config to
+ * @pf: PF to apply config to
+ * @locked: Is the RTNL held
  */
-static int ice_dcb_init_cfg(struct ice_pf *pf)
+static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked)
 {
 	struct ice_dcbx_cfg *newcfg;
 	struct ice_port_info *pi;
@@ -294,7 +301,7 @@ static int ice_dcb_init_cfg(struct ice_pf *pf)
 	memset(&pi->local_dcbx_cfg, 0, sizeof(*newcfg));
 
 	dev_info(&pf->pdev->dev, "Configuring initial DCB values\n");
-	if (ice_pf_dcb_cfg(pf, newcfg))
+	if (ice_pf_dcb_cfg(pf, newcfg, locked))
 		ret = -EINVAL;
 
 	devm_kfree(&pf->pdev->dev, newcfg);
@@ -304,9 +311,10 @@ static int ice_dcb_init_cfg(struct ice_pf *pf)
 
 /**
  * ice_dcb_sw_default_config - Apply a default DCB config
- * @pf: pf to apply config to
+ * @pf: PF to apply config to
+ * @locked: was this function called with RTNL held
  */
-static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf)
+static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked)
 {
 	struct ice_aqc_port_ets_elem buf = { 0 };
 	struct ice_dcbx_cfg *dcbcfg;
@@ -338,7 +346,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf)
 	dcbcfg->app[0].priority = 3;
 	dcbcfg->app[0].prot_id = ICE_APP_PROT_ID_FCOE;
 
-	ret = ice_pf_dcb_cfg(pf, dcbcfg);
+	ret = ice_pf_dcb_cfg(pf, dcbcfg, locked);
 	devm_kfree(&pf->pdev->dev, dcbcfg);
 	if (ret)
 		return ret;
@@ -348,9 +356,10 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf)
 
 /**
  * ice_init_pf_dcb - initialize DCB for a PF
- * @pf: pf to initiialize DCB for
+ * @pf: PF to initialize DCB for
+ * @locked: Was function called with RTNL held
  */
-int ice_init_pf_dcb(struct ice_pf *pf)
+int ice_init_pf_dcb(struct ice_pf *pf, bool locked)
 {
 	struct device *dev = &pf->pdev->dev;
 	struct ice_port_info *port_info;
@@ -360,33 +369,10 @@ int ice_init_pf_dcb(struct ice_pf *pf)
 
 	port_info = hw->port_info;
 
-	/* check if device is DCB capable */
-	if (!hw->func_caps.common_cap.dcb) {
-		dev_dbg(dev, "DCB not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	/* Best effort to put DCBx and LLDP into a good state */
-	port_info->dcbx_status = ice_get_dcbx_status(hw);
-	if (port_info->dcbx_status != ICE_DCBX_STATUS_DONE &&
-	    port_info->dcbx_status != ICE_DCBX_STATUS_IN_PROGRESS) {
-		bool dcbx_status;
-
-		/* Attempt to start LLDP engine. Ignore errors
-		 * as this will error if it is already started
-		 */
-		ice_aq_start_lldp(hw, NULL);
-
-		/* Attempt to start DCBX. Ignore errors as this
-		 * will error if it is already started
-		 */
-		ice_aq_start_stop_dcbx(hw, true, &dcbx_status, NULL);
-	}
-
 	err = ice_init_dcb(hw);
 	if (err) {
-		/* FW LLDP not in usable state, default to SW DCBx/LLDP */
-		dev_info(&pf->pdev->dev, "FW LLDP not in usable state\n");
+		/* FW LLDP is not active, default to SW DCBX/LLDP */
+		dev_info(&pf->pdev->dev, "FW LLDP is not active\n");
 		hw->port_info->dcbx_status = ICE_DCBX_STATUS_NOT_STARTED;
 		hw->port_info->is_sw_lldp = true;
 	}
@@ -398,15 +384,16 @@ int ice_init_pf_dcb(struct ice_pf *pf)
 	if (port_info->is_sw_lldp) {
 		sw_default = 1;
 		dev_info(&pf->pdev->dev, "DCBx/LLDP in SW mode.\n");
+		clear_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags);
+	} else {
+		set_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags);
 	}
 
-	if (port_info->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED) {
-		sw_default = 1;
+	if (port_info->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED)
 		dev_info(&pf->pdev->dev, "DCBX not started\n");
-	}
 
 	if (sw_default) {
-		err = ice_dcb_sw_dflt_cfg(pf);
+		err = ice_dcb_sw_dflt_cfg(pf, locked);
 		if (err) {
 			dev_err(&pf->pdev->dev,
 				"Failed to set local DCB config %d\n", err);
@@ -425,7 +412,7 @@ int ice_init_pf_dcb(struct ice_pf *pf)
 
 	set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags);
 
-	err = ice_dcb_init_cfg(pf);
+	err = ice_dcb_init_cfg(pf, locked);
 	if (err)
 		goto dcb_init_err;
 
@@ -515,6 +502,55 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,
 }
 
 /**
+ * ice_dcb_need_recfg - Check if DCB needs reconfig
+ * @pf: board private structure
+ * @old_cfg: current DCB config
+ * @new_cfg: new DCB config
+ */
+static bool ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
+			       struct ice_dcbx_cfg *new_cfg)
+{
+	bool need_reconfig = false;
+
+	/* Check if ETS configuration has changed */
+	if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg,
+		   sizeof(new_cfg->etscfg))) {
+		/* If Priority Table has changed reconfig is needed */
+		if (memcmp(&new_cfg->etscfg.prio_table,
+			   &old_cfg->etscfg.prio_table,
+			   sizeof(new_cfg->etscfg.prio_table))) {
+			need_reconfig = true;
+			dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n");
+		}
+
+		if (memcmp(&new_cfg->etscfg.tcbwtable,
+			   &old_cfg->etscfg.tcbwtable,
+			   sizeof(new_cfg->etscfg.tcbwtable)))
+			dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n");
+
+		if (memcmp(&new_cfg->etscfg.tsatable,
+			   &old_cfg->etscfg.tsatable,
+			   sizeof(new_cfg->etscfg.tsatable)))
+			dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n");
+	}
+
+	/* Check if PFC configuration has changed */
+	if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) {
+		need_reconfig = true;
+		dev_dbg(&pf->pdev->dev, "PFC config change detected.\n");
+	}
+
+	/* Check if APP Table has changed */
+	if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) {
+		need_reconfig = true;
+		dev_dbg(&pf->pdev->dev, "APP Table change detected.\n");
+	}
+
+	dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig);
+	return need_reconfig;
+}
+
+/**
  * ice_dcb_process_lldp_set_mib_change - Process MIB change
  * @pf: ptr to ice_pf
  * @event: pointer to the admin queue receive event
@@ -523,29 +559,95 @@ void
 ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 				    struct ice_rq_event_info *event)
 {
-	if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) {
-		struct ice_dcbx_cfg *dcbcfg, *prev_cfg;
-		int err;
-
-		prev_cfg = &pf->hw.port_info->local_dcbx_cfg;
-		dcbcfg = devm_kmemdup(&pf->pdev->dev, prev_cfg,
-				      sizeof(*dcbcfg), GFP_KERNEL);
-		if (!dcbcfg)
+	struct ice_aqc_port_ets_elem buf = { 0 };
+	struct ice_aqc_lldp_get_mib *mib;
+	struct ice_dcbx_cfg tmp_dcbx_cfg;
+	bool need_reconfig = false;
+	struct ice_port_info *pi;
+	u8 type;
+	int ret;
+
+	/* Not DCB capable or capability disabled */
+	if (!(test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)))
+		return;
+
+	if (pf->dcbx_cap & DCB_CAP_DCBX_HOST) {
+		dev_dbg(&pf->pdev->dev,
+			"MIB Change Event in HOST mode\n");
+		return;
+	}
+
+	pi = pf->hw.port_info;
+	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	/* Ignore if event is not for Nearest Bridge */
+	type = ((mib->type >> ICE_AQ_LLDP_BRID_TYPE_S) &
+		ICE_AQ_LLDP_BRID_TYPE_M);
+	dev_dbg(&pf->pdev->dev, "LLDP event MIB bridge type 0x%x\n", type);
+	if (type != ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID)
+		return;
+
+	/* Check MIB Type and return if event for Remote MIB update */
+	type = mib->type & ICE_AQ_LLDP_MIB_TYPE_M;
+	dev_dbg(&pf->pdev->dev,
+		"LLDP event mib type %s\n", type ? "remote" : "local");
+	if (type == ICE_AQ_LLDP_MIB_REMOTE) {
+		/* Update the remote cached instance and return */
+		ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
+					 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID,
+					 &pi->remote_dcbx_cfg);
+		if (ret) {
+			dev_err(&pf->pdev->dev, "Failed to get remote DCB config\n");
 			return;
+		}
+	}
 
-		err = ice_lldp_to_dcb_cfg(event->msg_buf, dcbcfg);
-		if (!err)
-			ice_pf_dcb_cfg(pf, dcbcfg);
+	/* store the old configuration */
+	tmp_dcbx_cfg = pf->hw.port_info->local_dcbx_cfg;
 
-		devm_kfree(&pf->pdev->dev, dcbcfg);
+	/* Reset the old DCBX configuration data */
+	memset(&pi->local_dcbx_cfg, 0, sizeof(pi->local_dcbx_cfg));
 
-		/* Get updated DCBx data from firmware */
-		err = ice_get_dcb_cfg(pf->hw.port_info);
-		if (err)
-			dev_err(&pf->pdev->dev,
-				"Failed to get DCB config\n");
-	} else {
+	/* Get updated DCBX data from firmware */
+	ret = ice_get_dcb_cfg(pf->hw.port_info);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Failed to get DCB config\n");
+		return;
+	}
+
+	/* No change detected in DCBX configs */
+	if (!memcmp(&tmp_dcbx_cfg, &pi->local_dcbx_cfg, sizeof(tmp_dcbx_cfg))) {
 		dev_dbg(&pf->pdev->dev,
-			"MIB Change Event in HOST mode\n");
+			"No change detected in DCBX configuration.\n");
+		return;
+	}
+
+	need_reconfig = ice_dcb_need_recfg(pf, &tmp_dcbx_cfg,
+					   &pi->local_dcbx_cfg);
+	if (!need_reconfig)
+		return;
+
+	/* Enable DCB tagging only when more than one TC */
+	if (ice_dcb_get_num_tc(&pi->local_dcbx_cfg) > 1) {
+		dev_dbg(&pf->pdev->dev, "DCB tagging enabled (num TC > 1)\n");
+		set_bit(ICE_FLAG_DCB_ENA, pf->flags);
+	} else {
+		dev_dbg(&pf->pdev->dev, "DCB tagging disabled (num TC = 1)\n");
+		clear_bit(ICE_FLAG_DCB_ENA, pf->flags);
 	}
+
+	rtnl_lock();
+	ice_pf_dis_all_vsi(pf, true);
+
+	ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL);
+	if (ret) {
+		dev_err(&pf->pdev->dev, "Query Port ETS failed\n");
+		rtnl_unlock();
+		return;
+	}
+
+	/* changes in configuration update VSI */
+	ice_pf_dcb_recfg(pf);
+
+	ice_pf_ena_all_vsi(pf, true);
+	rtnl_unlock();
 }