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, 85 insertions, 49 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5985a7e5ca8a..c36057efc7ae 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -287,6 +287,15 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q)
 	/* make sure the context is associated with the right VSI */
 	tlan_ctx->src_vsi = ice_get_hw_vsi_num(hw, vsi->idx);
 
+	/* Restrict Tx timestamps to the PF VSI */
+	switch (vsi->type) {
+	case ICE_VSI_PF:
+		tlan_ctx->tsyn_ena = 1;
+		break;
+	default:
+		break;
+	}
+
 	tlan_ctx->tso_ena = ICE_TX_LEGACY;
 	tlan_ctx->tso_qnum = pf_q;
 
@@ -319,11 +328,9 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
  *
  * Configure the Rx descriptor ring in RLAN context.
  */
-int ice_setup_rx_ctx(struct ice_ring *ring)
+static int ice_setup_rx_ctx(struct ice_ring *ring)
 {
-	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	int chain_len = ICE_MAX_CHAINED_RX_BUFS;
-	u16 num_bufs = ICE_DESC_UNUSED(ring);
 	struct ice_vsi *vsi = ring->vsi;
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
@@ -339,48 +346,6 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* clear the context structure first */
 	memset(&rlan_ctx, 0, sizeof(rlan_ctx));
 
-	ring->rx_buf_len = vsi->rx_buf_len;
-
-	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->q_index, ring->q_vector->napi.napi_id);
-
-		ring->xsk_pool = ice_xsk_pool(ring);
-		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-
-			ring->rx_buf_len =
-				xsk_pool_get_rx_frame_size(ring->xsk_pool);
-			/* For AF_XDP ZC, we disallow packets to span on
-			 * multiple buffers, thus letting us skip that
-			 * handling in the fast-path.
-			 */
-			chain_len = 1;
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_XSK_BUFF_POOL,
-							 NULL);
-			if (err)
-				return err;
-			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
-
-			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
-				 ring->q_index);
-		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				xdp_rxq_info_reg(&ring->xdp_rxq,
-						 ring->netdev,
-						 ring->q_index, ring->q_vector->napi.napi_id);
-
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (err)
-				return err;
-		}
-	}
 	/* Receive Queue Base Address.
 	 * Indicates the starting address of the descriptor queue defined in
 	 * 128 Byte units.
@@ -415,6 +380,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	 */
 	rlan_ctx.showiv = 0;
 
+	/* For AF_XDP ZC, we disallow packets to span on
+	 * multiple buffers, thus letting us skip that
+	 * handling in the fast-path.
+	 */
+	if (ring->xsk_pool)
+		chain_len = 1;
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
@@ -431,14 +402,15 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	 * of same priority
 	 */
 	if (vsi->type != ICE_VSI_VF)
-		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3);
+		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true);
 	else
-		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3);
+		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3,
+					false);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
 	if (err) {
-		dev_err(dev, "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
 			pf_q, err);
 		return -EIO;
 	}
@@ -458,6 +430,66 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
+	return 0;
+}
+
+/**
+ * ice_vsi_cfg_rxq - Configure an Rx queue
+ * @ring: the ring being configured
+ *
+ * Return 0 on success and a negative value on error.
+ */
+int ice_vsi_cfg_rxq(struct ice_ring *ring)
+{
+	struct device *dev = ice_pf_to_dev(ring->vsi->back);
+	u16 num_bufs = ICE_DESC_UNUSED(ring);
+	int err;
+
+	ring->rx_buf_len = ring->vsi->rx_buf_len;
+
+	if (ring->vsi->type == ICE_VSI_PF) {
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+			/* coverity[check_return] */
+			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->q_index, ring->q_vector->napi.napi_id);
+
+		ring->xsk_pool = ice_xsk_pool(ring);
+		if (ring->xsk_pool) {
+			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+			ring->rx_buf_len =
+				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_XSK_BUFF_POOL,
+							 NULL);
+			if (err)
+				return err;
+			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+
+			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
+				 ring->q_index);
+		} else {
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+				/* coverity[check_return] */
+				xdp_rxq_info_reg(&ring->xdp_rxq,
+						 ring->netdev,
+						 ring->q_index, ring->q_vector->napi.napi_id);
+
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (err)
+				return err;
+		}
+	}
+
+	err = ice_setup_rx_ctx(ring);
+	if (err) {
+		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+			ring->q_index, err);
+		return err;
+	}
+
 	if (ring->xsk_pool) {
 		bool ok;
 
@@ -470,9 +502,13 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 		}
 
 		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
-		if (!ok)
+		if (!ok) {
+			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
+
 			dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
 				 ring->q_index, pf_q);
+		}
+
 		return 0;
 	}