summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/igc/igc_main.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-07-30 08:58:55 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2025-07-30 08:58:55 -0700
commit8be4d31cb8aaeea27bde4b7ddb26e28a89062ebf (patch)
treefec3039a08284cd87f4ec9c3bea5b5a439f1859f /drivers/net/ethernet/intel/igc/igc_main.c
parent4b290aae788e06561754b28c6842e4080957d3f7 (diff)
parentfa582ca7e187a15e772e6a72fe035f649b387a60 (diff)
Merge tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: "Core & protocols: - Wrap datapath globals into net_aligned_data, to avoid false sharing - Preserve MSG_ZEROCOPY in forwarding (e.g. out of a container) - Add SO_INQ and SCM_INQ support to AF_UNIX - Add SIOCINQ support to AF_VSOCK - Add TCP_MAXSEG sockopt to MPTCP - Add IPv6 force_forwarding sysctl to enable forwarding per interface - Make TCP validation of whether packet fully fits in the receive window and the rcv_buf more strict. With increased use of HW aggregation a single "packet" can be multiple 100s of kB - Add MSG_MORE flag to optimize large TCP transmissions via sockmap, improves latency up to 33% for sockmap users - Convert TCP send queue handling from tasklet to BH workque - Improve BPF iteration over TCP sockets to see each socket exactly once - Remove obsolete and unused TCP RFC3517/RFC6675 loss recovery code - Support enabling kernel threads for NAPI processing on per-NAPI instance basis rather than a whole device. Fully stop the kernel NAPI thread when threaded NAPI gets disabled. Previously thread would stick around until ifdown due to tricky synchronization - Allow multicast routing to take effect on locally-generated packets - Add output interface argument for End.X in segment routing - MCTP: add support for gateway routing, improve bind() handling - Don't require rtnl_lock when fetching an IPv6 neighbor over Netlink - Add a new neighbor flag ("extern_valid"), which cedes refresh responsibilities to userspace. This is needed for EVPN multi-homing where a neighbor entry for a multi-homed host needs to be synced across all the VTEPs among which the host is multi-homed - Support NUD_PERMANENT for proxy neighbor entries - Add a new queuing discipline for IETF RFC9332 DualQ Coupled AQM - Add sequence numbers to netconsole messages. Unregister netconsole's console when all net targets are removed. Code refactoring. Add a number of selftests - Align IPSec inbound SA lookup to RFC 4301. Only SPI and protocol should be used for an inbound SA lookup - Support inspecting ref_tracker state via DebugFS - Don't force bonding advertisement frames tx to ~333 ms boundaries. Add broadcast_neighbor option to send ARP/ND on all bonded links - Allow providing upcall pid for the 'execute' command in openvswitch - Remove DCCP support from Netfilter's conntrack - Disallow multiple packet duplications in the queuing layer - Prevent use of deprecated iptables code on PREEMPT_RT Driver API: - Support RSS and hashing configuration over ethtool Netlink - Add dedicated ethtool callbacks for getting and setting hashing fields - Add support for power budget evaluation strategy in PSE / Power-over-Ethernet. Generate Netlink events for overcurrent etc - Support DPLL phase offset monitoring across all device inputs. Support providing clock reference and SYNC over separate DPLL inputs - Support traffic classes in devlink rate API for bandwidth management - Remove rtnl_lock dependency from UDP tunnel port configuration Device drivers: - Add a new Broadcom driver for 800G Ethernet (bnge) - Add a standalone driver for Microchip ZL3073x DPLL - Remove IBM's NETIUCV device driver - Ethernet high-speed NICs: - Broadcom (bnxt): - support zero-copy Tx of DMABUF memory - take page size into account for page pool recycling rings - Intel (100G, ice, idpf): - idpf: XDP and AF_XDP support preparations - idpf: add flow steering - add link_down_events statistic - clean up the TSPLL code - preparations for live VM migration - nVidia/Mellanox: - support zero-copy Rx/Tx interfaces (DMABUF and io_uring) - optimize context memory usage for matchers - expose serial numbers in devlink info - support PCIe congestion metrics - Meta (fbnic): - add 25G, 50G, and 100G link modes to phylink - support dumping FW logs - Marvell/Cavium: - support for CN20K generation of the Octeon chips - Amazon: - add HW clock (without timestamping, just hypervisor time access) - Ethernet virtual: - VirtIO net: - support segmentation of UDP-tunnel-encapsulated packets - Google (gve): - support packet timestamping and clock synchronization - Microsoft vNIC: - add handler for device-originated servicing events - allow dynamic MSI-X vector allocation - support Tx bandwidth clamping - Ethernet NICs consumer, and embedded: - AMD: - amd-xgbe: hardware timestamping and PTP clock support - Broadcom integrated MACs (bcmgenet, bcmasp): - use napi_complete_done() return value to support NAPI polling - add support for re-starting auto-negotiation - Broadcom switches (b53): - support BCM5325 switches - add bcm63xx EPHY power control - Synopsys (stmmac): - lots of code refactoring and cleanups - TI: - icssg-prueth: read firmware-names from device tree - icssg: PRP offload support - Microchip: - lan78xx: convert to PHYLINK for improved PHY and MAC management - ksz: add KSZ8463 switch support - Intel: - support similar queue priority scheme in multi-queue and time-sensitive networking (taprio) - support packet pre-emption in both - RealTek (r8169): - enable EEE at 5Gbps on RTL8126 - Airoha: - add PPPoE offload support - MDIO bus controller for Airoha AN7583 - Ethernet PHYs: - support for the IPQ5018 internal GE PHY - micrel KSZ9477 switch-integrated PHYs: - add MDI/MDI-X control support - add RX error counters - add cable test support - add Signal Quality Indicator (SQI) reporting - dp83tg720: improve reset handling and reduce link recovery time - support bcm54811 (and its MII-Lite interface type) - air_en8811h: support resume/suspend - support PHY counters for QCA807x and QCA808x - support WoL for QCA807x - CAN drivers: - rcar_canfd: support for Transceiver Delay Compensation - kvaser: report FW versions via devlink dev info - WiFi: - extended regulatory info support (6 GHz) - add statistics and beacon monitor for Multi-Link Operation (MLO) - support S1G aggregation, improve S1G support - add Radio Measurement action fields - support per-radio RTS threshold - some work around how FIPS affects wifi, which was wrong (RC4 is used by TKIP, not only WEP) - improvements for unsolicited probe response handling - WiFi drivers: - RealTek (rtw88): - IBSS mode for SDIO devices - RealTek (rtw89): - BT coexistence for MLO/WiFi7 - concurrent station + P2P support - support for USB devices RTL8851BU/RTL8852BU - Intel (iwlwifi): - use embedded PNVM in (to be released) FW images to fix compatibility issues - many cleanups (unused FW APIs, PCIe code, WoWLAN) - some FIPS interoperability - MediaTek (mt76): - firmware recovery improvements - more MLO work - Qualcomm/Atheros (ath12k): - fix scan on multi-radio devices - more EHT/Wi-Fi 7 features - encapsulation/decapsulation offload - Broadcom (brcm80211): - support SDIO 43751 device - Bluetooth: - hci_event: add support for handling LE BIG Sync Lost event - ISO: add socket option to report packet seqnum via CMSG - ISO: support SCM_TIMESTAMPING for ISO TS - Bluetooth drivers: - intel_pcie: support Function Level Reset - nxpuart: add support for 4M baudrate - nxpuart: implement powerup sequence, reset, FW dump, and FW loading" * tag 'net-next-6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1742 commits) dpll: zl3073x: Fix build failure selftests: bpf: fix legacy netfilter options ipv6: annotate data-races around rt->fib6_nsiblings ipv6: fix possible infinite loop in fib6_info_uses_dev() ipv6: prevent infinite loop in rt6_nlmsg_size() ipv6: add a retry logic in net6_rt_notify() vrf: Drop existing dst reference in vrf_ip6_input_dst net/sched: taprio: align entry index attr validation with mqprio net: fsl_pq_mdio: use dev_err_probe selftests: rtnetlink.sh: remove esp4_offload after test vsock: remove unnecessary null check in vsock_getname() igb: xsk: solve negative overflow of nb_pkts in zerocopy mode stmmac: xsk: fix negative overflow of budget in zerocopy mode dt-bindings: ieee802154: Convert at86rf230.txt yaml format net: dsa: microchip: Disable PTP function of KSZ8463 net: dsa: microchip: Setup fiber ports for KSZ8463 net: dsa: microchip: Write switch MAC address differently for KSZ8463 net: dsa: microchip: Use different registers for KSZ8463 net: dsa: microchip: Add KSZ8463 switch support to KSZ DSA driver dt-bindings: net: dsa: microchip: Add KSZ8463 switch support ...
Diffstat (limited to 'drivers/net/ethernet/intel/igc/igc_main.c')
-rw-r--r--drivers/net/ethernet/intel/igc/igc_main.c100
1 files changed, 67 insertions, 33 deletions
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 031c332f66c4..458e5eaa92e5 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -683,9 +683,9 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter,
wr32(IGC_SRRCTL(reg_idx), srrctl);
- rxdctl |= IGC_RX_PTHRESH;
- rxdctl |= IGC_RX_HTHRESH << 8;
- rxdctl |= IGC_RX_WTHRESH << 16;
+ rxdctl |= IGC_RXDCTL_PTHRESH;
+ rxdctl |= IGC_RXDCTL_HTHRESH << 8;
+ rxdctl |= IGC_RXDCTL_WTHRESH << 16;
/* initialize rx_buffer_info */
memset(ring->rx_buffer_info, 0,
@@ -749,11 +749,9 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter,
wr32(IGC_TDH(reg_idx), 0);
writel(0, ring->tail);
- txdctl |= IGC_TX_PTHRESH;
- txdctl |= IGC_TX_HTHRESH << 8;
- txdctl |= IGC_TX_WTHRESH << 16;
+ txdctl |= IGC_TXDCTL_PTHRESH(8) | IGC_TXDCTL_HTHRESH(1) |
+ IGC_TXDCTL_WTHRESH(16) | IGC_TXDCTL_QUEUE_ENABLE;
- txdctl |= IGC_TXDCTL_QUEUE_ENABLE;
wr32(IGC_TXDCTL(reg_idx), txdctl);
}
@@ -1687,6 +1685,15 @@ done:
first->tx_flags = tx_flags;
first->protocol = protocol;
+ /* For preemptible queue, manually pad the skb so that HW includes
+ * padding bytes in mCRC calculation
+ */
+ if (tx_ring->preemptible && skb->len < ETH_ZLEN) {
+ if (skb_padto(skb, ETH_ZLEN))
+ goto out_drop;
+ skb_put(skb, ETH_ZLEN - skb->len);
+ }
+
tso = igc_tso(tx_ring, first, launch_time, first_flag, &hdr_len);
if (tso < 0)
goto out_drop;
@@ -3867,6 +3874,22 @@ static void igc_del_flex_filter(struct igc_adapter *adapter,
wr32(IGC_WUFC, wufc);
}
+static void igc_set_default_queue_filter(struct igc_adapter *adapter, u32 queue)
+{
+ struct igc_hw *hw = &adapter->hw;
+ u32 mrqc = rd32(IGC_MRQC);
+
+ mrqc &= ~IGC_MRQC_DEFAULT_QUEUE_MASK;
+ mrqc |= FIELD_PREP(IGC_MRQC_DEFAULT_QUEUE_MASK, queue);
+ wr32(IGC_MRQC, mrqc);
+}
+
+static void igc_reset_default_queue_filter(struct igc_adapter *adapter)
+{
+ /* Reset the default queue to its default value which is Queue 0 */
+ igc_set_default_queue_filter(adapter, 0);
+}
+
static int igc_enable_nfc_rule(struct igc_adapter *adapter,
struct igc_nfc_rule *rule)
{
@@ -3905,6 +3928,9 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter,
return err;
}
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE)
+ igc_set_default_queue_filter(adapter, rule->action);
+
return 0;
}
@@ -3932,6 +3958,9 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter,
if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR)
igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST,
rule->filter.dst_addr);
+
+ if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE)
+ igc_reset_default_queue_filter(adapter);
}
/**
@@ -6296,24 +6325,6 @@ int igc_close(struct net_device *netdev)
return 0;
}
-/**
- * igc_ioctl - Access the hwtstamp interface
- * @netdev: network interface device structure
- * @ifr: interface request data
- * @cmd: ioctl command
- **/
-static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
- switch (cmd) {
- case SIOCGHWTSTAMP:
- return igc_ptp_get_ts_config(netdev, ifr);
- case SIOCSHWTSTAMP:
- return igc_ptp_set_ts_config(netdev, ifr);
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int igc_save_launchtime_params(struct igc_adapter *adapter, int queue,
bool enable)
{
@@ -6423,6 +6434,7 @@ static int igc_qbv_clear_schedule(struct igc_adapter *adapter)
ring->start_time = 0;
ring->end_time = NSEC_PER_SEC;
ring->max_sdu = 0;
+ ring->preemptible = false;
}
spin_lock_irqsave(&adapter->qbv_tx_lock, flags);
@@ -6488,9 +6500,12 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
if (!validate_schedule(adapter, qopt))
return -EINVAL;
- /* preemptible isn't supported yet */
- if (qopt->mqprio.preemptible_tcs)
- return -EOPNOTSUPP;
+ if (qopt->mqprio.preemptible_tcs &&
+ !(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO)) {
+ NL_SET_ERR_MSG_MOD(qopt->extack,
+ "reverse-tsn-txq-prio private flag must be enabled before setting preemptible tc");
+ return -ENODEV;
+ }
igc_ptp_read(adapter, &now);
@@ -6583,6 +6598,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
ring->max_sdu = 0;
}
+ igc_fpe_save_preempt_queue(adapter, &qopt->mqprio);
+
return 0;
}
@@ -6702,7 +6719,8 @@ static int igc_tc_query_caps(struct igc_adapter *adapter,
case TC_SETUP_QDISC_TAPRIO: {
struct tc_taprio_caps *caps = base->caps;
- caps->broken_mqprio = true;
+ if (!(adapter->flags & IGC_FLAG_TSN_REVERSE_TXQ_PRIO))
+ caps->broken_mqprio = true;
if (hw->mac.type == igc_i225) {
caps->supports_queue_max_sdu = true;
@@ -6728,6 +6746,20 @@ static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc,
adapter->queue_per_tc[i] = offset[i];
}
+static bool
+igc_tsn_is_tc_to_queue_priority_ordered(struct tc_mqprio_qopt_offload *mqprio)
+{
+ int num_tc = mqprio->qopt.num_tc;
+ int i;
+
+ for (i = 1; i < num_tc; i++) {
+ if (mqprio->qopt.offset[i - 1] > mqprio->qopt.offset[i])
+ return false;
+ }
+
+ return true;
+}
+
static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
struct tc_mqprio_qopt_offload *mqprio)
{
@@ -6739,6 +6771,7 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
if (!mqprio->qopt.num_tc) {
adapter->strict_priority_enable = false;
+ igc_fpe_clear_preempt_queue(adapter);
netdev_reset_tc(adapter->netdev);
goto apply;
}
@@ -6760,10 +6793,9 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
}
}
- /* Preemption is not supported yet. */
- if (mqprio->preemptible_tcs) {
+ if (!igc_tsn_is_tc_to_queue_priority_ordered(mqprio)) {
NL_SET_ERR_MSG_MOD(mqprio->extack,
- "Preemption is not supported yet");
+ "tc to queue mapping must preserve increasing priority (higher tc -> higher queue)");
return -EOPNOTSUPP;
}
@@ -6786,6 +6818,7 @@ static int igc_tsn_enable_mqprio(struct igc_adapter *adapter,
adapter->queue_per_tc[i] = i;
mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+ igc_fpe_save_preempt_queue(adapter, mqprio);
apply:
return igc_tsn_offload_apply(adapter);
@@ -6942,12 +6975,13 @@ static const struct net_device_ops igc_netdev_ops = {
.ndo_fix_features = igc_fix_features,
.ndo_set_features = igc_set_features,
.ndo_features_check = igc_features_check,
- .ndo_eth_ioctl = igc_ioctl,
.ndo_setup_tc = igc_setup_tc,
.ndo_bpf = igc_bpf,
.ndo_xdp_xmit = igc_xdp_xmit,
.ndo_xsk_wakeup = igc_xsk_wakeup,
.ndo_get_tstamp = igc_get_tstamp,
+ .ndo_hwtstamp_get = igc_ptp_hwtstamp_get,
+ .ndo_hwtstamp_set = igc_ptp_hwtstamp_set,
};
u32 igc_rd32(struct igc_hw *hw, u32 reg)