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, 48 insertions, 6 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 04748aa4c7c8..6ee8e0032d52 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -10,6 +10,7 @@
 #include "ice_txrx_lib.h"
 #include "ice_lib.h"
 #include "ice.h"
+#include "ice_trace.h"
 #include "ice_dcb_lib.h"
 #include "ice_xsk.h"
 
@@ -224,6 +225,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
 
 		smp_rmb();	/* prevent any other reads prior to eop_desc */
 
+		ice_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* if the descriptor isn't done, no work yet to do */
 		if (!(eop_desc->cmd_type_offset_bsz &
 		      cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)))
@@ -254,6 +256,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
 
 		/* unmap remaining buffers */
 		while (tx_desc != eop_desc) {
+			ice_trace(clean_tx_irq_unmap, tx_ring, tx_desc, tx_buf);
 			tx_buf++;
 			tx_desc++;
 			i++;
@@ -272,6 +275,7 @@ static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget)
 				dma_unmap_len_set(tx_buf, len, 0);
 			}
 		}
+		ice_trace(clean_tx_irq_unmap_eop, tx_ring, tx_desc, tx_buf);
 
 		/* move us one more past the eop_desc for start of next pkt */
 		tx_buf++;
@@ -1082,7 +1086,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		u16 stat_err_bits;
 		int rx_buf_pgcnt;
 		u16 vlan_tag = 0;
-		u8 rx_ptype;
+		u16 rx_ptype;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean);
@@ -1102,6 +1106,7 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		ice_trace(clean_rx_irq, rx_ring, rx_desc);
 		if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
 			struct ice_vsi *ctrl_vsi = rx_ring->vsi;
 
@@ -1135,15 +1140,11 @@ int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 		xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size);
 #endif
 
-		rcu_read_lock();
 		xdp_prog = READ_ONCE(rx_ring->xdp_prog);
-		if (!xdp_prog) {
-			rcu_read_unlock();
+		if (!xdp_prog)
 			goto construct_skb;
-		}
 
 		xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog);
-		rcu_read_unlock();
 		if (!xdp_res)
 			goto construct_skb;
 		if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) {
@@ -1207,6 +1208,7 @@ construct_skb:
 
 		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
+		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 		skb = NULL;
@@ -2137,6 +2139,41 @@ static bool ice_chk_linearize(struct sk_buff *skb, unsigned int count)
 }
 
 /**
+ * ice_tstamp - set up context descriptor for hardware timestamp
+ * @tx_ring: pointer to the Tx ring to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @first: Tx buffer
+ * @off: Tx offload parameters
+ */
+static void
+ice_tstamp(struct ice_ring *tx_ring, struct sk_buff *skb,
+	   struct ice_tx_buf *first, struct ice_tx_offload_params *off)
+{
+	s8 idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return;
+
+	if (!tx_ring->ptp_tx)
+		return;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (first->tx_flags & ICE_TX_FLAGS_TSO)
+		return;
+
+	/* Grab an open timestamp slot */
+	idx = ice_ptp_request_ts(tx_ring->tx_tstamps, skb);
+	if (idx < 0)
+		return;
+
+	off->cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX |
+			     (ICE_TX_CTX_DESC_TSYN << ICE_TXD_CTX_QW1_CMD_S) |
+			     ((u64)idx << ICE_TXD_CTX_QW1_TSO_LEN_S));
+	first->tx_flags |= ICE_TX_FLAGS_TSYN;
+}
+
+/**
  * ice_xmit_frame_ring - Sends buffer on Tx ring
  * @skb: send buffer
  * @tx_ring: ring to send buffer on
@@ -2153,6 +2190,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	unsigned int count;
 	int tso, csum;
 
+	ice_trace(xmit_frame_ring, tx_ring, skb);
+
 	count = ice_xmit_desc_count(skb);
 	if (ice_chk_linearize(skb, count)) {
 		if (__skb_linearize(skb))
@@ -2205,6 +2244,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 					ICE_TX_CTX_DESC_SWTCH_UPLINK <<
 					ICE_TXD_CTX_QW1_CMD_S);
 
+	ice_tstamp(tx_ring, skb, first, &offload);
+
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {
 		struct ice_tx_ctx_desc *cdesc;
 		u16 i = tx_ring->next_to_use;
@@ -2225,6 +2266,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring)
 	return NETDEV_TX_OK;
 
 out_drop:
+	ice_trace(xmit_frame_ring_drop, tx_ring, skb);
 	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
 }