Merge tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - BPF:
      - add syscall program type and libbpf support for generating
        instructions and bindings for in-kernel BPF loaders (BPF loaders
        for BPF), this is a stepping stone for signed BPF programs
      - infrastructure to migrate TCP child sockets from one listener to
        another in the same reuseport group/map to improve flexibility
        of service hand-off/restart
      - add broadcast support to XDP redirect

   - allow bypass of the lockless qdisc to improving performance (for
     pktgen: +23% with one thread, +44% with 2 threads)

   - add a simpler version of "DO_ONCE()" which does not require jump
     labels, intended for slow-path usage

   - virtio/vsock: introduce SOCK_SEQPACKET support

   - add getsocketopt to retrieve netns cookie

   - ip: treat lowest address of a IPv4 subnet as ordinary unicast
     address allowing reclaiming of precious IPv4 addresses

   - ipv6: use prandom_u32() for ID generation

   - ip: add support for more flexible field selection for hashing
     across multi-path routes (w/ offload to mlxsw)

   - icmp: add support for extended RFC 8335 PROBE (ping)

   - seg6: add support for SRv6 End.DT46 behavior

   - mptcp:
      - DSS checksum support (RFC 8684) to detect middlebox meddling
      - support Connection-time 'C' flag
      - time stamping support

   - sctp: packetization Layer Path MTU Discovery (RFC 8899)

   - xfrm: speed up state addition with seq set

   - WiFi:
      - hidden AP discovery on 6 GHz and other HE 6 GHz improvements
      - aggregation handling improvements for some drivers
      - minstrel improvements for no-ack frames
      - deferred rate control for TXQs to improve reaction times
      - switch from round robin to virtual time-based airtime scheduler

   - add trace points:
      - tcp checksum errors
      - openvswitch - action execution, upcalls
      - socket errors via sk_error_report

  Device APIs:

   - devlink: add rate API for hierarchical control of max egress rate
     of virtual devices (VFs, SFs etc.)

   - don't require RCU read lock to be held around BPF hooks in NAPI
     context

   - page_pool: generic buffer recycling

  New hardware/drivers:

   - mobile:
      - iosm: PCIe Driver for Intel M.2 Modem
      - support for Qualcomm MSM8998 (ipa)

   - WiFi: Qualcomm QCN9074 and WCN6855 PCI devices

   - sparx5: Microchip SparX-5 family of Enterprise Ethernet switches

   - Mellanox BlueField Gigabit Ethernet (control NIC of the DPU)

   - NXP SJA1110 Automotive Ethernet 10-port switch

   - Qualcomm QCA8327 switch support (qca8k)

   - Mikrotik 10/25G NIC (atl1c)

  Driver changes:

   - ACPI support for some MDIO, MAC and PHY devices from Marvell and
     NXP (our first foray into MAC/PHY description via ACPI)

   - HW timestamping (PTP) support: bnxt_en, ice, sja1105, hns3, tja11xx

   - Mellanox/Nvidia NIC (mlx5)
      - NIC VF offload of L2 bridging
      - support IRQ distribution to Sub-functions

   - Marvell (prestera):
      - add flower and match all
      - devlink trap
      - link aggregation

   - Netronome (nfp): connection tracking offload

   - Intel 1GE (igc): add AF_XDP support

   - Marvell DPU (octeontx2): ingress ratelimit offload

   - Google vNIC (gve): new ring/descriptor format support

   - Qualcomm mobile (rmnet & ipa): inline checksum offload support

   - MediaTek WiFi (mt76)
      - mt7915 MSI support
      - mt7915 Tx status reporting
      - mt7915 thermal sensors support
      - mt7921 decapsulation offload
      - mt7921 enable runtime pm and deep sleep

   - Realtek WiFi (rtw88)
      - beacon filter support
      - Tx antenna path diversity support
      - firmware crash information via devcoredump

   - Qualcomm WiFi (wcn36xx)
      - Wake-on-WLAN support with magic packets and GTK rekeying

   - Micrel PHY (ksz886x/ksz8081): add cable test support"

* tag 'net-next-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2168 commits)
  tcp: change ICSK_CA_PRIV_SIZE definition
  tcp_yeah: check struct yeah size at compile time
  gve: DQO: Fix off by one in gve_rx_dqo()
  stmmac: intel: set PCI_D3hot in suspend
  stmmac: intel: Enable PHY WOL option in EHL
  net: stmmac: option to enable PHY WOL with PMT enabled
  net: say "local" instead of "static" addresses in ndo_dflt_fdb_{add,del}
  net: use netdev_info in ndo_dflt_fdb_{add,del}
  ptp: Set lookup cookie when creating a PTP PPS source.
  net: sock: add trace for socket errors
  net: sock: introduce sk_error_report
  net: dsa: replay the local bridge FDB entries pointing to the bridge dev too
  net: dsa: ensure during dsa_fdb_offload_notify that dev_hold and dev_put are on the same dev
  net: dsa: include fdb entries pointing to bridge in the host fdb list
  net: dsa: include bridge addresses which are local in the host fdb list
  net: dsa: sync static FDB entries on foreign interfaces to hardware
  net: dsa: install the host MDB and FDB entries in the master's RX filter
  net: dsa: reference count the FDB addresses at the cross-chip notifier level
  net: dsa: introduce a separate cross-chip notifier type for host FDBs
  net: dsa: reference count the MDB entries at the cross-chip notifier level
  ...

1 files changed, 100 insertions, 20 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 27f9dac8719c..dde9802c6c72 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -169,12 +169,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		vsi->alloc_txq = min3(pf->num_lan_msix,
-				      ice_get_avail_txq_count(pf),
-				      (u16)num_online_cpus());
 		if (vsi->req_txq) {
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
+		} else {
+			vsi->alloc_txq = min3(pf->num_lan_msix,
+					      ice_get_avail_txq_count(pf),
+					      (u16)num_online_cpus());
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -183,12 +184,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 			vsi->alloc_rxq = 1;
 		} else {
-			vsi->alloc_rxq = min3(pf->num_lan_msix,
-					      ice_get_avail_rxq_count(pf),
-					      (u16)num_online_cpus());
 			if (vsi->req_rxq) {
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
+			} else {
+				vsi->alloc_rxq = min3(pf->num_lan_msix,
+						      ice_get_avail_rxq_count(pf),
+						      (u16)num_online_cpus());
 			}
 		}
 
@@ -629,6 +631,17 @@ bool ice_is_safe_mode(struct ice_pf *pf)
 }
 
 /**
+ * ice_is_aux_ena
+ * @pf: pointer to the PF struct
+ *
+ * returns true if AUX devices/drivers are supported, false otherwise
+ */
+bool ice_is_aux_ena(struct ice_pf *pf)
+{
+	return test_bit(ICE_FLAG_AUX_ENA, pf->flags);
+}
+
+/**
  * ice_vsi_clean_rss_flow_fld - Delete RSS configuration
  * @vsi: the VSI being cleaned up
  *
@@ -1192,11 +1205,11 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi)
 	num_q_vectors = vsi->num_q_vectors;
 	/* reserve slots from OS requested IRQs */
 	if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) {
-		struct ice_vf *vf;
 		int i;
 
 		ice_for_each_vf(pf, i) {
-			vf = &pf->vf[i];
+			struct ice_vf *vf = &pf->vf[i];
+
 			if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI) {
 				base = pf->vsi[vf->ctrl_vsi_idx]->base_vector;
 				break;
@@ -1285,6 +1298,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->reg_idx = vsi->txq_map[i];
 		ring->ring_active = false;
 		ring->vsi = vsi;
+		ring->tx_tstamps = &pf->ptp.port.tx;
 		ring->dev = dev;
 		ring->count = vsi->num_tx_desc;
 		WRITE_ONCE(vsi->tx_rings[i], ring);
@@ -1662,9 +1676,11 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi)
  * @pf_q: index of the Rx queue in the PF's queue space
  * @rxdid: flexible descriptor RXDID
  * @prio: priority for the RXDID for this queue
+ * @ena_ts: true to enable timestamp and false to disable timestamp
  */
 void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
+ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			bool ena_ts)
 {
 	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
 
@@ -1679,9 +1695,40 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
 	regval |= (prio << QRXFLXP_CNTXT_RXDID_PRIO_S) &
 		QRXFLXP_CNTXT_RXDID_PRIO_M;
 
+	if (ena_ts)
+		/* Enable TimeSync on this queue */
+		regval |= QRXFLXP_CNTXT_TS_M;
+
 	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
 }
 
+int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx)
+{
+	if (q_idx >= vsi->num_rxq)
+		return -EINVAL;
+
+	return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]);
+}
+
+int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx)
+{
+	struct ice_aqc_add_tx_qgrp *qg_buf;
+	int err;
+
+	if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx])
+		return -EINVAL;
+
+	qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL);
+	if (!qg_buf)
+		return -ENOMEM;
+
+	qg_buf->num_txqs = 1;
+
+	err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf);
+	kfree(qg_buf);
+	return err;
+}
+
 /**
  * ice_vsi_cfg_rxqs - Configure the VSI for Rx
  * @vsi: the VSI being configured
@@ -1699,15 +1746,11 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
 	ice_vsi_cfg_frame_size(vsi);
 setup_rings:
 	/* set up individual rings */
-	for (i = 0; i < vsi->num_rxq; i++) {
-		int err;
+	ice_for_each_rxq(vsi, i) {
+		int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]);
 
-		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
-		if (err) {
-			dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
-				i, err);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
@@ -2217,7 +2260,7 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 	}
 
 	if (status)
-		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
+		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
 			create ? "adding" : "removing", tx ? "TX" : "RX",
 			vsi->vsi_num, ice_stat_str(status));
 }
@@ -2832,11 +2875,11 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	 * cleared in the same manner.
 	 */
 	if (vsi->type == ICE_VSI_CTRL && vsi->vf_id != ICE_INVAL_VFID) {
-		struct ice_vf *vf;
 		int i;
 
 		ice_for_each_vf(pf, i) {
-			vf = &pf->vf[i];
+			struct ice_vf *vf = &pf->vf[i];
+
 			if (i != vsi->vf_id && vf->ctrl_vsi_idx != ICE_NO_VSI)
 				break;
 		}
@@ -3196,6 +3239,34 @@ bool ice_is_reset_in_progress(unsigned long *state)
 	       test_bit(ICE_GLOBR_REQ, state);
 }
 
+/**
+ * ice_wait_for_reset - Wait for driver to finish reset and rebuild
+ * @pf: pointer to the PF structure
+ * @timeout: length of time to wait, in jiffies
+ *
+ * Wait (sleep) for a short time until the driver finishes cleaning up from
+ * a device reset. The caller must be able to sleep. Use this to delay
+ * operations that could fail while the driver is cleaning up after a device
+ * reset.
+ *
+ * Returns 0 on success, -EBUSY if the reset is not finished within the
+ * timeout, and -ERESTARTSYS if the thread was interrupted.
+ */
+int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout)
+{
+	long ret;
+
+	ret = wait_event_interruptible_timeout(pf->reset_wait_queue,
+					       !ice_is_reset_in_progress(pf->state),
+					       timeout);
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+	else
+		return 0;
+}
+
 #ifdef CONFIG_DCB
 /**
  * ice_vsi_update_q_map - update our copy of the VSI info with new queue map
@@ -3330,13 +3401,22 @@ int ice_status_to_errno(enum ice_status err)
 	case ICE_ERR_DOES_NOT_EXIST:
 		return -ENOENT;
 	case ICE_ERR_OUT_OF_RANGE:
-		return -ENOTTY;
+	case ICE_ERR_AQ_ERROR:
+	case ICE_ERR_AQ_TIMEOUT:
+	case ICE_ERR_AQ_EMPTY:
+	case ICE_ERR_AQ_FW_CRITICAL:
+		return -EIO;
 	case ICE_ERR_PARAM:
+	case ICE_ERR_INVAL_SIZE:
 		return -EINVAL;
 	case ICE_ERR_NO_MEMORY:
 		return -ENOMEM;
 	case ICE_ERR_MAX_LIMIT:
 		return -EAGAIN;
+	case ICE_ERR_RESET_ONGOING:
+		return -EBUSY;
+	case ICE_ERR_AQ_FULL:
+		return -ENOSPC;
 	default:
 		return -EINVAL;
 	}