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, 97 insertions, 12 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index 11133c4619bb..a8cf5374be47 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020, Intel Corporation. */
 
+#include <net/xdp_sock_drv.h>
+
 #include "igc.h"
 #include "igc_xdp.h"
 
@@ -32,29 +34,112 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	return 0;
 }
 
-int igc_xdp_register_rxq_info(struct igc_ring *ring)
+static int igc_xdp_enable_pool(struct igc_adapter *adapter,
+			       struct xsk_buff_pool *pool, u16 queue_id)
 {
-	struct net_device *dev = ring->netdev;
+	struct net_device *ndev = adapter->netdev;
+	struct device *dev = &adapter->pdev->dev;
+	struct igc_ring *rx_ring, *tx_ring;
+	struct napi_struct *napi;
+	bool needs_reset;
+	u32 frame_size;
 	int err;
 
-	err = xdp_rxq_info_reg(&ring->xdp_rxq, dev, ring->queue_index, 0);
-	if (err) {
-		netdev_err(dev, "Failed to register xdp rxq info\n");
-		return err;
+	if (queue_id >= adapter->num_rx_queues ||
+	    queue_id >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	frame_size = xsk_pool_get_rx_frame_size(pool);
+	if (frame_size < ETH_FRAME_LEN + VLAN_HLEN * 2) {
+		/* When XDP is enabled, the driver doesn't support frames that
+		 * span over multiple buffers. To avoid that, we check if xsk
+		 * frame size is big enough to fit the max ethernet frame size
+		 * + vlan double tagging.
+		 */
+		return -EOPNOTSUPP;
 	}
 
-	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED,
-					 NULL);
+	err = xsk_pool_dma_map(pool, dev, IGC_RX_DMA_ATTR);
 	if (err) {
-		netdev_err(dev, "Failed to register xdp rxq mem model\n");
-		xdp_rxq_info_unreg(&ring->xdp_rxq);
+		netdev_err(ndev, "Failed to map xsk pool\n");
 		return err;
 	}
 
+	needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter);
+
+	rx_ring = adapter->rx_ring[queue_id];
+	tx_ring = adapter->tx_ring[queue_id];
+	/* Rx and Tx rings share the same napi context. */
+	napi = &rx_ring->q_vector->napi;
+
+	if (needs_reset) {
+		igc_disable_rx_ring(rx_ring);
+		igc_disable_tx_ring(tx_ring);
+		napi_disable(napi);
+	}
+
+	set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+	set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+
+	if (needs_reset) {
+		napi_enable(napi);
+		igc_enable_rx_ring(rx_ring);
+		igc_enable_tx_ring(tx_ring);
+
+		err = igc_xsk_wakeup(ndev, queue_id, XDP_WAKEUP_RX);
+		if (err) {
+			xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id)
+{
+	struct igc_ring *rx_ring, *tx_ring;
+	struct xsk_buff_pool *pool;
+	struct napi_struct *napi;
+	bool needs_reset;
+
+	if (queue_id >= adapter->num_rx_queues ||
+	    queue_id >= adapter->num_tx_queues)
+		return -EINVAL;
+
+	pool = xsk_get_pool_from_qid(adapter->netdev, queue_id);
+	if (!pool)
+		return -EINVAL;
+
+	needs_reset = netif_running(adapter->netdev) && igc_xdp_is_enabled(adapter);
+
+	rx_ring = adapter->rx_ring[queue_id];
+	tx_ring = adapter->tx_ring[queue_id];
+	/* Rx and Tx rings share the same napi context. */
+	napi = &rx_ring->q_vector->napi;
+
+	if (needs_reset) {
+		igc_disable_rx_ring(rx_ring);
+		igc_disable_tx_ring(tx_ring);
+		napi_disable(napi);
+	}
+
+	xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR);
+	clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags);
+	clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags);
+
+	if (needs_reset) {
+		napi_enable(napi);
+		igc_enable_rx_ring(rx_ring);
+		igc_enable_tx_ring(tx_ring);
+	}
+
 	return 0;
 }
 
-void igc_xdp_unregister_rxq_info(struct igc_ring *ring)
+int igc_xdp_setup_pool(struct igc_adapter *adapter, struct xsk_buff_pool *pool,
+		       u16 queue_id)
 {
-	xdp_rxq_info_unreg(&ring->xdp_rxq);
+	return pool ? igc_xdp_enable_pool(adapter, pool, queue_id) :
+		      igc_xdp_disable_pool(adapter, queue_id);
 }