diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-12 21:33:35 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-03-12 21:33:35 +0300 |
| commit | 2c7e63d702f6c4209c5af833308e7fcbc7d4ab17 (patch) | |
| tree | e46b218ced108b588a1d83364397d57334121efd | |
| parent | 281f36d4a9970c206c2c44042904d4e34c092fbe (diff) | |
| parent | c38b8f5f791ecce13ab77e2257f8fd2444ba80f6 (diff) | |
| download | linux-2c7e63d702f6c4209c5af833308e7fcbc7d4ab17.tar.xz | |
Merge tag 'net-7.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from CAN and netfilter.
Current release - regressions:
- eth: mana: Null service_wq on setup error to prevent double destroy
Previous releases - regressions:
- nexthop: fix percpu use-after-free in remove_nh_grp_entry
- sched: teql: fix NULL pointer dereference in iptunnel_xmit on TEQL slave xmit
- bpf: fix nd_tbl NULL dereference when IPv6 is disabled
- neighbour: restore protocol != 0 check in pneigh update
- tipc: fix divide-by-zero in tipc_sk_filter_connect()
- eth:
- mlx5:
- fix crash when moving to switchdev mode
- fix DMA FIFO desync on error CQE SQ recovery
- iavf: fix PTP use-after-free during reset
- bonding: fix type confusion in bond_setup_by_slave()
- lan78xx: fix WARN in __netif_napi_del_locked on disconnect
Previous releases - always broken:
- core: add xmit recursion limit to tunnel xmit functions
- net-shapers: don't free reply skb after genlmsg_reply()
- netfilter:
- fix stack out-of-bounds read in pipapo_drop()
- fix OOB read in nfnl_cthelper_dump_table()
- mctp:
- fix device leak on probe failure
- i2c: fix skb memory leak in receive path
- can: keep the max bitrate error at 5%
- eth:
- bonding: fix nd_tbl NULL dereference when IPv6 is disabled
- bnxt_en: fix RSS table size check when changing ethtool channels
- amd-xgbe: prevent CRC errors during RX adaptation with AN disabled
- octeontx2-af: devlink: fix NIX RAS reporter recovery condition"
* tag 'net-7.0-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (71 commits)
net: prevent NULL deref in ip[6]tunnel_xmit()
octeontx2-af: devlink: fix NIX RAS reporter to use RAS interrupt status
octeontx2-af: devlink: fix NIX RAS reporter recovery condition
net: ethernet: ti: am65-cpsw-nuss: Fix rx_filter value for PTP support
net/mana: Null service_wq on setup error to prevent double destroy
selftests: rtnetlink: add neighbour update test
neighbour: restore protocol != 0 check in pneigh update
net: dsa: realtek: Fix LED group port bit for non-zero LED group
tipc: fix divide-by-zero in tipc_sk_filter_connect()
net: dsa: microchip: Fix error path in PTP IRQ setup
bpf: bpf_out_neigh_v6: Fix nd_tbl NULL dereference when IPv6 is disabled
bpf: bpf_out_neigh_v4: Fix nd_tbl NULL dereference when IPv6 is disabled
net: bonding: Fix nd_tbl NULL dereference when IPv6 is disabled
ipv6: move the disable_ipv6_mod knob to core code
net: bcmgenet: fix broken EEE by converting to phylib-managed state
net-shapers: don't free reply skb after genlmsg_reply()
net: dsa: mxl862xx: don't set user_mii_bus
net: ethernet: arc: emac: quiesce interrupts before requesting IRQ
page_pool: store detach_time as ktime_t to avoid false-negatives
net: macb: Shuffle the tx ring before enabling tx
...
77 files changed, 667 insertions, 326 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 837db4f7bcca..bc3bcc641663 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16358,7 +16358,6 @@ F: net/dsa/tag_mtk.c MEDIATEK T7XX 5G WWAN MODEM DRIVER M: Chandrashekar Devegowda <chandrashekar.devegowda@intel.com> -R: Chiranjeevi Rapolu <chiranjeevi.rapolu@linux.intel.com> R: Liu Haijun <haijun.liu@mediatek.com> R: Ricardo Martinez <ricardo.martinez@linux.intel.com> L: netdev@vger.kernel.org @@ -25759,6 +25758,7 @@ F: include/net/pkt_cls.h F: include/net/pkt_sched.h F: include/net/sch_priv.h F: include/net/tc_act/ +F: include/net/tc_wrapper.h F: include/uapi/linux/pkt_cls.h F: include/uapi/linux/pkt_sched.h F: include/uapi/linux/tc_act/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 14ed91391fcc..707419270ebf 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1509,6 +1509,50 @@ static netdev_features_t bond_fix_features(struct net_device *dev, return features; } +static int bond_header_create(struct sk_buff *skb, struct net_device *bond_dev, + unsigned short type, const void *daddr, + const void *saddr, unsigned int len) +{ + struct bonding *bond = netdev_priv(bond_dev); + const struct header_ops *slave_ops; + struct slave *slave; + int ret = 0; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + slave_ops = READ_ONCE(slave->dev->header_ops); + if (slave_ops && slave_ops->create) + ret = slave_ops->create(skb, slave->dev, + type, daddr, saddr, len); + } + rcu_read_unlock(); + return ret; +} + +static int bond_header_parse(const struct sk_buff *skb, unsigned char *haddr) +{ + struct bonding *bond = netdev_priv(skb->dev); + const struct header_ops *slave_ops; + struct slave *slave; + int ret = 0; + + rcu_read_lock(); + slave = rcu_dereference(bond->curr_active_slave); + if (slave) { + slave_ops = READ_ONCE(slave->dev->header_ops); + if (slave_ops && slave_ops->parse) + ret = slave_ops->parse(skb, haddr); + } + rcu_read_unlock(); + return ret; +} + +static const struct header_ops bond_header_ops = { + .create = bond_header_create, + .parse = bond_header_parse, +}; + static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -1516,7 +1560,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev, dev_close(bond_dev); - bond_dev->header_ops = slave_dev->header_ops; + bond_dev->header_ops = slave_dev->header_ops ? + &bond_header_ops : NULL; bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; @@ -2801,8 +2846,14 @@ static void bond_miimon_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + case BOND_LINK_BACK: + slave_dbg(bond->dev, slave->dev, "link_new_state %d on slave\n", + slave->link_new_state); + continue; + default: - slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", + slave_err(bond->dev, slave->dev, "invalid link_new_state %d on slave\n", slave->link_new_state); bond_propose_link_state(slave, BOND_LINK_NOCHANGE); @@ -3377,7 +3428,7 @@ int bond_rcv_validate(const struct sk_buff *skb, struct bonding *bond, } else if (is_arp) { return bond_arp_rcv(skb, bond, slave); #if IS_ENABLED(CONFIG_IPV6) - } else if (is_ipv6) { + } else if (is_ipv6 && likely(ipv6_mod_enabled())) { return bond_na_rcv(skb, bond, slave); #endif } else { @@ -5069,13 +5120,18 @@ static void bond_set_slave_arr(struct bonding *bond, { struct bond_up_slave *usable, *all; - usable = rtnl_dereference(bond->usable_slaves); - rcu_assign_pointer(bond->usable_slaves, usable_slaves); - kfree_rcu(usable, rcu); - all = rtnl_dereference(bond->all_slaves); rcu_assign_pointer(bond->all_slaves, all_slaves); kfree_rcu(all, rcu); + + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) { + kfree_rcu(usable_slaves, rcu); + return; + } + + usable = rtnl_dereference(bond->usable_slaves); + rcu_assign_pointer(bond->usable_slaves, usable_slaves); + kfree_rcu(usable, rcu); } static void bond_reset_slave_arr(struct bonding *bond) diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index b90890030751..1873d8287bb9 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -297,6 +297,7 @@ static void ser_release(struct work_struct *work) dev_close(ser->dev); unregister_netdevice(ser->dev); debugfs_deinit(ser); + tty_kref_put(tty->link); tty_kref_put(tty); } rtnl_unlock(); @@ -331,6 +332,7 @@ static int ldisc_open(struct tty_struct *tty) ser = netdev_priv(dev); ser->tty = tty_kref_get(tty); + tty_kref_get(tty->link); ser->dev = dev; debugfs_init(ser, tty); tty->receive_room = 4096; @@ -339,6 +341,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty->link); tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c index cc4022241553..42498e9d3f38 100644 --- a/drivers/net/can/dev/calc_bittiming.c +++ b/drivers/net/can/dev/calc_bittiming.c @@ -8,7 +8,7 @@ #include <linux/units.h> #include <linux/can/dev.h> -#define CAN_CALC_MAX_ERROR 50 /* in one-tenth of a percent */ +#define CAN_CALC_MAX_ERROR 500 /* max error 5% */ /* CiA recommended sample points for Non Return to Zero encoding. */ static int can_calc_sample_point_nrz(const struct can_bittiming *bt) diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index e00d3dbc4cf4..91b1fa970f8f 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -755,7 +755,9 @@ static int hi3110_open(struct net_device *net) return ret; mutex_lock(&priv->hi3110_lock); - hi3110_power_enable(priv->transceiver, 1); + ret = hi3110_power_enable(priv->transceiver, 1); + if (ret) + goto out_close_candev; priv->force_quit = 0; priv->tx_skb = NULL; @@ -790,6 +792,7 @@ static int hi3110_open(struct net_device *net) hi3110_hw_sleep(spi); out_close: hi3110_power_enable(priv->transceiver, 0); + out_close_candev: close_candev(net); mutex_unlock(&priv->hi3110_lock); return ret; diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 4a2cc57a628f..8b98039320ad 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -1108,6 +1108,7 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) const struct ksz_dev_ops *ops = port->ksz_dev->dev_ops; struct ksz_irq *ptpirq = &port->ptpirq; struct ksz_ptp_irq *ptpmsg_irq; + int ret; ptpmsg_irq = &port->ptpmsg_irq[n]; ptpmsg_irq->num = irq_create_mapping(ptpirq->domain, n); @@ -1119,9 +1120,13 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) strscpy(ptpmsg_irq->name, name[n]); - return request_threaded_irq(ptpmsg_irq->num, NULL, - ksz_ptp_msg_thread_fn, IRQF_ONESHOT, - ptpmsg_irq->name, ptpmsg_irq); + ret = request_threaded_irq(ptpmsg_irq->num, NULL, + ksz_ptp_msg_thread_fn, IRQF_ONESHOT, + ptpmsg_irq->name, ptpmsg_irq); + if (ret) + irq_dispose_mapping(ptpmsg_irq->num); + + return ret; } int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c index b1e2094b5816..d7ab04f5afef 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx.c +++ b/drivers/net/dsa/mxl862xx/mxl862xx.c @@ -149,7 +149,6 @@ static int mxl862xx_setup_mdio(struct dsa_switch *ds) return -ENOMEM; bus->priv = priv; - ds->user_mii_bus = bus; bus->name = KBUILD_MODNAME "-mii"; snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(dev)); bus->read_c45 = mxl862xx_phy_read_c45_mii_bus; diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index f938a3f701cc..31fa94dac627 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -1480,8 +1480,7 @@ static void rtl8365mb_stats_update(struct realtek_priv *priv, int port) stats->rx_packets = cnt[RTL8365MB_MIB_ifInUcastPkts] + cnt[RTL8365MB_MIB_ifInMulticastPkts] + - cnt[RTL8365MB_MIB_ifInBroadcastPkts] - - cnt[RTL8365MB_MIB_ifOutDiscards]; + cnt[RTL8365MB_MIB_ifInBroadcastPkts]; stats->tx_packets = cnt[RTL8365MB_MIB_ifOutUcastPkts] + cnt[RTL8365MB_MIB_ifOutMulticastPkts] + diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c index 99c890681ae6..509ffd3f8db5 100644 --- a/drivers/net/dsa/realtek/rtl8366rb-leds.c +++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c @@ -12,11 +12,11 @@ static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port) case 0: return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); case 1: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_X_1_CTRL_MASK, BIT(port)); case 2: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_2_X_CTRL_MASK, BIT(port)); case 3: - return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port)); + return FIELD_PREP(RTL8366RB_LED_X_3_CTRL_MASK, BIT(port)); default: return 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 94d17b06da40..c72c2bfdcffb 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2339,14 +2339,13 @@ int sja1105_static_config_reload(struct sja1105_private *priv, goto out; } + rc = sja1105_reload_cbs(priv); + +out: dsa_switch_for_each_available_port(dp, ds) if (dp->pl) phylink_replay_link_end(dp->pl); - rc = sja1105_reload_cbs(priv); - if (rc < 0) - goto out; -out: mutex_unlock(&priv->mgmt_lock); mutex_unlock(&priv->fdb_lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 8b79d88480db..23beea48ae26 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1271,20 +1271,25 @@ static int xgbe_start(struct xgbe_prv_data *pdata) if (ret) goto err_napi; + /* Reset the phy settings */ + ret = xgbe_phy_reset(pdata); + if (ret) + goto err_irqs; + + /* Start the phy */ ret = phy_if->phy_start(pdata); if (ret) goto err_irqs; hw_if->enable_tx(pdata); hw_if->enable_rx(pdata); + /* Synchronize flag with hardware state after enabling TX/RX. + * This prevents stale state after device restart cycles. + */ + pdata->data_path_stopped = false; udp_tunnel_nic_reset_ntf(netdev); - /* Reset the phy settings */ - ret = xgbe_phy_reset(pdata); - if (ret) - goto err_txrx; - netif_tx_start_all_queues(netdev); xgbe_start_timers(pdata); @@ -1294,10 +1299,6 @@ static int xgbe_start(struct xgbe_prv_data *pdata) return 0; -err_txrx: - hw_if->disable_rx(pdata); - hw_if->disable_tx(pdata); - err_irqs: xgbe_free_irqs(pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index c63ddb12237e..b8cf6ccfe641 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -1942,7 +1942,7 @@ static void xgbe_set_rx_adap_mode(struct xgbe_prv_data *pdata, static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int reg; + int reg; /* step 2: force PCS to send RX_ADAPT Req to PHY */ XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_RX_EQ_CTRL4, @@ -1964,11 +1964,20 @@ static void xgbe_rx_adaptation(struct xgbe_prv_data *pdata) /* Step 4: Check for Block lock */ - /* Link status is latched low, so read once to clear - * and then read again to get current state - */ - reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + goto set_mode; + + /* Link status is latched low so that momentary link drops + * can be detected. If link was already down read again + * to get the latest state. + */ + if (!pdata->phy.link && !(reg & MDIO_STAT1_LSTATUS)) { + reg = XMDIO_READ(pdata, MDIO_MMD_PCS, MDIO_STAT1); + if (reg < 0) + goto set_mode; + } + if (reg & MDIO_STAT1_LSTATUS) { /* If the block lock is found, update the helpers * and declare the link up @@ -2008,6 +2017,48 @@ rx_adapt_reinit: xgbe_rx_adaptation(pdata); } +/* + * xgbe_phy_stop_data_path - Stop TX/RX to prevent packet corruption + * @pdata: driver private data + * + * This function stops the data path (TX and RX) to prevent packet + * corruption during critical PHY operations like RX adaptation. + * Must be called before initiating RX adaptation when link goes down. + */ +static void xgbe_phy_stop_data_path(struct xgbe_prv_data *pdata) +{ + if (pdata->data_path_stopped) + return; + + /* Stop TX/RX to prevent packet corruption during RX adaptation */ + pdata->hw_if.disable_tx(pdata); + pdata->hw_if.disable_rx(pdata); + pdata->data_path_stopped = true; + + netif_dbg(pdata, link, pdata->netdev, + "stopping data path for RX adaptation\n"); +} + +/* + * xgbe_phy_start_data_path - Re-enable TX/RX after RX adaptation + * @pdata: driver private data + * + * This function re-enables the data path (TX and RX) after RX adaptation + * has completed successfully. Only called when link is confirmed up. + */ +static void xgbe_phy_start_data_path(struct xgbe_prv_data *pdata) +{ + if (!pdata->data_path_stopped) + return; + + pdata->hw_if.enable_rx(pdata); + pdata->hw_if.enable_tx(pdata); + pdata->data_path_stopped = false; + + netif_dbg(pdata, link, pdata->netdev, + "restarting data path after RX adaptation\n"); +} + static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata) { int reg; @@ -2801,13 +2852,27 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) if (pdata->en_rx_adap) { /* if the link is available and adaptation is done, * declare link up + * + * Note: When link is up and adaptation is done, we can + * safely re-enable the data path if it was stopped + * for adaptation. */ - if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) + if ((reg & MDIO_STAT1_LSTATUS) && pdata->rx_adapt_done) { + xgbe_phy_start_data_path(pdata); return 1; + } /* If either link is not available or adaptation is not done, * retrigger the adaptation logic. (if the mode is not set, * then issue mailbox command first) */ + + /* CRITICAL: Stop data path BEFORE triggering RX adaptation + * to prevent CRC errors from packets corrupted during + * the adaptation process. This is especially important + * when AN is OFF in 10G KR mode. + */ + xgbe_phy_stop_data_path(pdata); + if (pdata->mode_set) { xgbe_phy_rx_adaptation(pdata); } else { @@ -2815,8 +2880,11 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) xgbe_phy_set_mode(pdata, phy_data->cur_mode); } - if (pdata->rx_adapt_done) + if (pdata->rx_adapt_done) { + /* Adaptation complete, safe to re-enable data path */ + xgbe_phy_start_data_path(pdata); return 1; + } } else if (reg & MDIO_STAT1_LSTATUS) return 1; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index e1d7d7150e16..438033a71523 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1243,6 +1243,10 @@ struct xgbe_prv_data { bool en_rx_adap; int rx_adapt_retries; bool rx_adapt_done; + /* Flag to track if data path (TX/RX) was stopped for RX adaptation. + * This prevents packet corruption during the adaptation window. + */ + bool data_path_stopped; bool mode_set; bool sph; }; diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 8283aeee35fb..dde4046cbf01 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -934,6 +934,17 @@ int arc_emac_probe(struct net_device *ndev, int interface) /* Set poll rate so that it polls every 1 ms */ arc_reg_set(priv, R_POLLRATE, clock_frequency / 1000000); + /* + * Put the device into a known quiescent state before requesting + * the IRQ. Clear only EMAC interrupt status bits here; leave the + * MDIO completion bit alone and avoid writing TXPL_MASK, which is + * used to force TX polling rather than acknowledge interrupts. + */ + arc_reg_set(priv, R_ENABLE, 0); + arc_reg_set(priv, R_STATUS, RXINT_MASK | TXINT_MASK | ERR_MASK | + TXCH_MASK | MSER_MASK | RXCR_MASK | + RXFR_MASK | RXFL_MASK); + ndev->irq = irq; dev_info(dev, "IRQ is %d\n", ndev->irq); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index ba47e8294fff..28d0ece2e7b1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -979,8 +979,8 @@ static int bnxt_set_channels(struct net_device *dev, if (bnxt_get_nr_rss_ctxs(bp, req_rx_rings) != bnxt_get_nr_rss_ctxs(bp, bp->rx_nr_rings) && - netif_is_rxfh_configured(dev)) { - netdev_warn(dev, "RSS table size change required, RSS table entries must be default to proceed\n"); + (netif_is_rxfh_configured(dev) || bp->num_rss_ctx)) { + netdev_warn(dev, "RSS table size change required, RSS table entries must be default (with no additional RSS contexts present) to proceed\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index a71cd729fde6..482a31e7b72b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1342,8 +1342,7 @@ static void bcmgenet_get_ethtool_stats(struct net_device *dev, } } -void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, - bool tx_lpi_enabled) +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) { struct bcmgenet_priv *priv = netdev_priv(dev); u32 off = priv->hw_params->tbuf_offset + TBUF_ENERGY_CTRL; @@ -1363,7 +1362,7 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, /* Enable EEE and switch to a 27Mhz clock automatically */ reg = bcmgenet_readl(priv->base + off); - if (tx_lpi_enabled) + if (enable) reg |= TBUF_EEE_EN | TBUF_PM_EN; else reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); @@ -1382,14 +1381,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, priv->clk_eee_enabled = false; } - priv->eee.eee_enabled = enable; - priv->eee.tx_lpi_enabled = tx_lpi_enabled; } static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_keee *p = &priv->eee; + int ret; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1397,17 +1394,21 @@ static int bcmgenet_get_eee(struct net_device *dev, struct ethtool_keee *e) if (!dev->phydev) return -ENODEV; - e->tx_lpi_enabled = p->tx_lpi_enabled; + ret = phy_ethtool_get_eee(dev->phydev, e); + if (ret) + return ret; + + /* tx_lpi_timer is maintained by the MAC hardware register; the + * PHY-level eee_cfg timer is not set for GENET. + */ e->tx_lpi_timer = bcmgenet_umac_readl(priv, UMAC_EEE_LPI_TIMER); - return phy_ethtool_get_eee(dev->phydev, e); + return 0; } static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e) { struct bcmgenet_priv *priv = netdev_priv(dev); - struct ethtool_keee *p = &priv->eee; - bool active; if (GENET_IS_V1(priv)) return -EOPNOTSUPP; @@ -1415,15 +1416,7 @@ static int bcmgenet_set_eee(struct net_device *dev, struct ethtool_keee *e) if (!dev->phydev) return -ENODEV; - p->eee_enabled = e->eee_enabled; - - if (!p->eee_enabled) { - bcmgenet_eee_enable_set(dev, false, false); - } else { - active = phy_init_eee(dev->phydev, false) >= 0; - bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); - bcmgenet_eee_enable_set(dev, active, e->tx_lpi_enabled); - } + bcmgenet_umac_writel(priv, e->tx_lpi_timer, UMAC_EEE_LPI_TIMER); return phy_ethtool_set_eee(dev->phydev, e); } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 5ec3979779ec..9e4110c7fdf6 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -665,8 +665,6 @@ struct bcmgenet_priv { u8 sopass[SOPASS_MAX]; struct bcmgenet_mib_counters mib; - - struct ethtool_keee eee; }; static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv) @@ -749,7 +747,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv, int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv, enum bcmgenet_power_mode mode); -void bcmgenet_eee_enable_set(struct net_device *dev, bool enable, - bool tx_lpi_enabled); +void bcmgenet_eee_enable_set(struct net_device *dev, bool enable); #endif /* __BCMGENET_H__ */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 38f854b94a79..a4e0d5a68268 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -29,7 +29,6 @@ static void bcmgenet_mac_config(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; u32 reg, cmd_bits = 0; - bool active; /* speed */ if (phydev->speed == SPEED_1000) @@ -90,10 +89,6 @@ static void bcmgenet_mac_config(struct net_device *dev) bcmgenet_umac_writel(priv, reg, UMAC_CMD); spin_unlock_bh(&priv->reg_lock); - active = phy_init_eee(phydev, 0) >= 0; - bcmgenet_eee_enable_set(dev, - priv->eee.eee_enabled && active, - priv->eee.tx_lpi_enabled); } /* setup netdev link state when PHY link status change and @@ -113,6 +108,8 @@ void bcmgenet_mii_setup(struct net_device *dev) bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); } + bcmgenet_eee_enable_set(dev, phydev->enable_tx_lpi); + phy_print_status(phydev); } @@ -412,6 +409,9 @@ int bcmgenet_mii_probe(struct net_device *dev) /* Indicate that the MAC is responsible for PHY PM */ dev->phydev->mac_managed_pm = true; + if (!GENET_IS_V1(priv)) + phy_support_eee(dev->phydev); + return 0; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 5bc35f651ebd..f290d608b409 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -36,6 +36,7 @@ #include <linux/tcp.h> #include <linux/types.h> #include <linux/udp.h> +#include <linux/gcd.h> #include <net/pkt_sched.h> #include "macb.h" @@ -668,6 +669,97 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, netif_tx_stop_all_queues(ndev); } +/* Use juggling algorithm to left rotate tx ring and tx skb array */ +static void gem_shuffle_tx_one_ring(struct macb_queue *queue) +{ + unsigned int head, tail, count, ring_size, desc_size; + struct macb_tx_skb tx_skb, *skb_curr, *skb_next; + struct macb_dma_desc *desc_curr, *desc_next; + unsigned int i, cycles, shift, curr, next; + struct macb *bp = queue->bp; + unsigned char desc[24]; + unsigned long flags; + + desc_size = macb_dma_desc_get_size(bp); + + if (WARN_ON_ONCE(desc_size > ARRAY_SIZE(desc))) + return; + + spin_lock_irqsave(&queue->tx_ptr_lock, flags); + head = queue->tx_head; + tail = queue->tx_tail; + ring_size = bp->tx_ring_size; + count = CIRC_CNT(head, tail, ring_size); + + if (!(tail % ring_size)) + goto unlock; + + if (!count) { + queue->tx_head = 0; + queue->tx_tail = 0; + goto unlock; + } + + shift = tail % ring_size; + cycles = gcd(ring_size, shift); + + for (i = 0; i < cycles; i++) { + memcpy(&desc, macb_tx_desc(queue, i), desc_size); + memcpy(&tx_skb, macb_tx_skb(queue, i), + sizeof(struct macb_tx_skb)); + + curr = i; + next = (curr + shift) % ring_size; + + while (next != i) { + desc_curr = macb_tx_desc(queue, curr); + desc_next = macb_tx_desc(queue, next); + + memcpy(desc_curr, desc_next, desc_size); + + if (next == ring_size - 1) + desc_curr->ctrl &= ~MACB_BIT(TX_WRAP); + if (curr == ring_size - 1) + desc_curr->ctrl |= MACB_BIT(TX_WRAP); + + skb_curr = macb_tx_skb(queue, curr); + skb_next = macb_tx_skb(queue, next); + memcpy(skb_curr, skb_next, sizeof(struct macb_tx_skb)); + + curr = next; + next = (curr + shift) % ring_size; + } + + desc_curr = macb_tx_desc(queue, curr); + memcpy(desc_curr, &desc, desc_size); + if (i == ring_size - 1) + desc_curr->ctrl &= ~MACB_BIT(TX_WRAP); + if (curr == ring_size - 1) + desc_curr->ctrl |= MACB_BIT(TX_WRAP); + memcpy(macb_tx_skb(queue, curr), &tx_skb, + sizeof(struct macb_tx_skb)); + } + + queue->tx_head = count; + queue->tx_tail = 0; + + /* Make descriptor updates visible to hardware */ + wmb(); + +unlock: + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); +} + +/* Rotate the queue so that the tail is at index 0 */ +static void gem_shuffle_tx_rings(struct macb *bp) +{ + struct macb_queue *queue; + int q; + + for (q = 0, queue = bp->queues; q < bp->num_queues; q++, queue++) + gem_shuffle_tx_one_ring(queue); +} + static void macb_mac_link_up(struct phylink_config *config, struct phy_device *phy, unsigned int mode, phy_interface_t interface, @@ -706,8 +798,6 @@ static void macb_mac_link_up(struct phylink_config *config, ctrl |= MACB_BIT(PAE); for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue->tx_head = 0; - queue->tx_tail = 0; queue_writel(queue, IER, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -721,8 +811,10 @@ static void macb_mac_link_up(struct phylink_config *config, spin_unlock_irqrestore(&bp->lock, flags); - if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { macb_set_tx_clk(bp, speed); + gem_shuffle_tx_rings(bp); + } /* Enable Rx and Tx; Enable PTP unicast */ ctrl = macb_readl(bp, NCR); diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index 7fd39f895290..92a0f824dae7 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -333,11 +333,13 @@ static int netc_get_phy_addr(struct device_node *np) mdio_node = of_get_child_by_name(np, "mdio"); if (!mdio_node) - return 0; + return -ENODEV; phy_node = of_get_next_child(mdio_node, NULL); - if (!phy_node) + if (!phy_node) { + err = -ENODEV; goto of_put_mdio_node; + } err = of_property_read_u32(phy_node, "reg", &addr); if (err) @@ -423,6 +425,9 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev) addr = netc_get_phy_addr(gchild); if (addr < 0) { + if (addr == -ENODEV) + continue; + dev_err(dev, "Failed to get PHY address\n"); return addr; } @@ -433,12 +438,6 @@ static int imx95_enetc_mdio_phyaddr_config(struct platform_device *pdev) return -EINVAL; } - /* The default value of LaBCR[MDIO_PHYAD_PRTAD ] is - * 0, so no need to set the register. - */ - if (!addr) - continue; - switch (bus_devfn) { case IMX95_ENETC0_BUS_DEVFN: netc_reg_write(priv->ierb, IERB_LBCR(0), @@ -578,16 +577,13 @@ static int imx94_enetc_mdio_phyaddr_config(struct netc_blk_ctrl *priv, addr = netc_get_phy_addr(np); if (addr < 0) { + if (addr == -ENODEV) + return 0; + dev_err(dev, "Failed to get PHY address\n"); return addr; } - /* The default value of LaBCR[MDIO_PHYAD_PRTAD] is 0, - * so no need to set the register. - */ - if (!addr) - return 0; - if (phy_mask & BIT(addr)) { dev_err(dev, "Find same PHY address in EMDIO and ENETC node\n"); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 3d7648a119e5..9b09eb144b81 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2952,8 +2952,6 @@ static int e1000_tx_map(struct e1000_adapter *adapter, dma_error: dev_err(&pdev->dev, "TX DMA map failed\n"); buffer_info->dma = 0; - if (count) - count--; while (count--) { if (i == 0) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 35dab1e3132f..9befdacd6730 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5652,8 +5652,6 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, dma_error: dev_err(&pdev->dev, "Tx DMA map failed\n"); buffer_info->dma = 0; - if (count) - count--; while (count--) { if (i == 0) diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index fdf40f8fb239..a26c3d47ec15 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3833,10 +3833,10 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) cfilter.n_proto = ETH_P_IP; if (mask.dst_ip[0] & tcf.dst_ip[0]) memcpy(&cfilter.ip.v4.dst_ip, tcf.dst_ip, - ARRAY_SIZE(tcf.dst_ip)); - else if (mask.src_ip[0] & tcf.dst_ip[0]) + sizeof(cfilter.ip.v4.dst_ip)); + else if (mask.src_ip[0] & tcf.src_ip[0]) memcpy(&cfilter.ip.v4.src_ip, tcf.src_ip, - ARRAY_SIZE(tcf.dst_ip)); + sizeof(cfilter.ip.v4.src_ip)); break; case VIRTCHNL_TCP_V6_FLOW: cfilter.n_proto = ETH_P_IPV6; @@ -3891,7 +3891,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) /* for ipv6, mask is set for all sixteen bytes (4 words) */ if (cfilter.n_proto == ETH_P_IPV6 && mask.dst_ip[3]) if (memcmp(&cfilter.ip.v6.dst_ip6, &cf->ip.v6.dst_ip6, - sizeof(cfilter.ip.v6.src_ip6))) + sizeof(cfilter.ip.v6.dst_ip6))) continue; if (mask.vlan_id) if (cfilter.vlan_id != cf->vlan_id) @@ -3979,10 +3979,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) cfilter->n_proto = ETH_P_IP; if (mask.dst_ip[0] & tcf.dst_ip[0]) memcpy(&cfilter->ip.v4.dst_ip, tcf.dst_ip, - ARRAY_SIZE(tcf.dst_ip)); - else if (mask.src_ip[0] & tcf.dst_ip[0]) + sizeof(cfilter->ip.v4.dst_ip)); + else if (mask.src_ip[0] & tcf.src_ip[0]) memcpy(&cfilter->ip.v4.src_ip, tcf.src_ip, - ARRAY_SIZE(tcf.dst_ip)); + sizeof(cfilter->ip.v4.src_ip)); break; case VIRTCHNL_TCP_V6_FLOW: cfilter->n_proto = ETH_P_IPV6; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index a87e0c6d4017..e9fb0a0919e3 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -260,7 +260,6 @@ struct iavf_adapter { struct work_struct adminq_task; struct work_struct finish_config; wait_queue_head_t down_waitqueue; - wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -626,5 +625,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); -int iavf_wait_for_reset(struct iavf_adapter *adapter); +void iavf_reset_step(struct iavf_adapter *adapter); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index f3a1b2fb9bf8..ab67c709d5a0 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -492,7 +492,6 @@ static int iavf_set_ringparam(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; - int ret = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -537,13 +536,11 @@ static int iavf_set_ringparam(struct net_device *netdev, } if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); } - return ret; + return 0; } /** @@ -1723,7 +1720,6 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; - int ret = 0; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1745,13 +1741,10 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset"); - - return ret; + return 0; } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 86c1964f42e1..7925ee152c76 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -186,31 +186,6 @@ static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) } /** - * iavf_wait_for_reset - Wait for reset to finish. - * @adapter: board private structure - * - * Returns 0 if reset finished successfully, negative on timeout or interrupt. - */ -int iavf_wait_for_reset(struct iavf_adapter *adapter) -{ - int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, - !iavf_is_reset_in_progress(adapter), - msecs_to_jiffies(5000)); - - /* If ret < 0 then it means wait was interrupted. - * If ret == 0 then it means we got a timeout while waiting - * for reset to finish. - * If ret > 0 it means reset has finished. - */ - if (ret > 0) - return 0; - else if (ret < 0) - return -EINTR; - else - return -EBUSY; -} - -/** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out @@ -3036,6 +3011,8 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_ptp_release(adapter); + /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. @@ -3111,18 +3088,16 @@ static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter) } /** - * iavf_reset_task - Call-back task to handle hardware reset - * @work: pointer to work_struct + * iavf_reset_step - Perform the VF reset sequence + * @adapter: board private structure * - * During reset we need to shut down and reinitialize the admin queue - * before we can use it to communicate with the PF again. We also clear - * and reinit the rings because that context is lost as well. - **/ -static void iavf_reset_task(struct work_struct *work) + * Requests a reset from PF, polls for completion, and reconfigures + * the driver. Caller must hold the netdev instance lock. + * + * This can sleep for several seconds while polling HW registers. + */ +void iavf_reset_step(struct iavf_adapter *adapter) { - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - reset_task); struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; @@ -3133,7 +3108,7 @@ static void iavf_reset_task(struct work_struct *work) int i = 0, err; bool running; - netdev_lock(netdev); + netdev_assert_locked(netdev); iavf_misc_irq_disable(adapter); if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { @@ -3178,7 +3153,6 @@ static void iavf_reset_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); iavf_disable_vf(adapter); - netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3190,7 +3164,6 @@ continue_reset: iavf_startup(adapter); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); - netdev_unlock(netdev); return; } @@ -3211,6 +3184,8 @@ continue_reset: iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + iavf_ptp_release(adapter); + /* free the Tx/Rx rings and descriptors, might be better to just * re-use them sometime in the future */ @@ -3331,9 +3306,6 @@ continue_reset: adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - wake_up(&adapter->reset_waitqueue); - netdev_unlock(netdev); - return; reset_err: if (running) { @@ -3342,10 +3314,21 @@ reset_err: } iavf_disable_vf(adapter); - netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } +static void iavf_reset_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + reset_task); + struct net_device *netdev = adapter->netdev; + + netdev_lock(netdev); + iavf_reset_step(adapter); + netdev_unlock(netdev); +} + /** * iavf_adminq_task - worker thread to clean the admin queue * @work: pointer to work_struct containing our data @@ -4611,22 +4594,17 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); - int ret = 0; netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret < 0) - netdev_warn(netdev, "MTU change interrupted waiting for reset"); - else if (ret) - netdev_warn(netdev, "MTU change timed out waiting for reset"); + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + iavf_reset_step(adapter); } - return ret; + return 0; } /** @@ -5431,9 +5409,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); - /* Setup the wait queue for indicating transition to running state */ - init_waitqueue_head(&adapter->reset_waitqueue); - /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 88156082a41d..a52c100dcbc5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -2736,7 +2736,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); - wake_up(&adapter->reset_waitqueue); adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index 6c72bd15db6d..6144cee8034d 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1360,7 +1360,7 @@ ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, cdev = pf->cdev_info; if (!cdev) - return -ENODEV; + return -EOPNOTSUPP; ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_ROCEV2); @@ -1427,7 +1427,7 @@ ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, cdev = pf->cdev_info; if (!cdev) - return -ENODEV; + return -EOPNOTSUPP; ctx->val.vbool = !!(cdev->rdma_protocol & IIDC_RDMA_PROTOCOL_IWARP); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index fb15c794efc9..a29f1ea04c7d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -327,10 +327,10 @@ static int rvu_nix_report_show(struct devlink_fmsg *fmsg, void *ctx, rvu_report_pair_end(fmsg); break; case NIX_AF_RVU_RAS: - intr_val = nix_event_context->nix_af_rvu_err; + intr_val = nix_event_context->nix_af_rvu_ras; rvu_report_pair_start(fmsg, "NIX_AF_RAS"); devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ", - nix_event_context->nix_af_rvu_err); + nix_event_context->nix_af_rvu_ras); devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:"); if (intr_val & BIT_ULL(34)) devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S"); @@ -475,7 +475,7 @@ static int rvu_hw_nix_ras_recover(struct devlink_health_reporter *reporter, if (blkaddr < 0) return blkaddr; - if (nix_event_ctx->nix_af_rvu_int) + if (nix_event_ctx->nix_af_rvu_ras) rvu_write64(rvu, blkaddr, NIX_AF_RAS_ENA_W1S, ~0ULL); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 60ba840e00fa..afdeb1b3d425 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -47,7 +47,6 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", sq->sqn, sq->cc, sq->pc); sq->cc = 0; - sq->dma_fifo_cc = 0; sq->pc = 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 197a1c6930c0..329608c59313 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -2912,7 +2912,7 @@ void mlx5e_ipsec_disable_events(struct mlx5e_priv *priv) goto out; peer_priv = mlx5_devcom_get_next_peer_data(priv->devcom, &tmp); - if (peer_priv) + if (peer_priv && peer_priv->ipsec) complete_all(&peer_priv->ipsec->comp); mlx5_devcom_for_each_peer_end(priv->devcom); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index efcfcddab376..268e20884757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1589,6 +1589,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi struct skb_shared_info *sinfo; u32 frag_consumed_bytes; struct bpf_prog *prog; + u8 nr_frags_free = 0; struct sk_buff *skb; dma_addr_t addr; u32 truesize; @@ -1631,15 +1632,13 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi prog = rcu_dereference(rq->xdp_prog); if (prog) { - u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + u8 old_nr_frags = sinfo->nr_frags; if (mlx5e_xdp_handle(rq, prog, mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_wqe_frag_info *pwi; - wi -= old_nr_frags - sinfo->nr_frags; - for (pwi = head_wi; pwi < wi; pwi++) pwi->frag_page->frags++; } @@ -1647,10 +1646,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi } nr_frags_free = old_nr_frags - sinfo->nr_frags; - if (unlikely(nr_frags_free)) { - wi -= nr_frags_free; + if (unlikely(nr_frags_free)) truesize -= nr_frags_free * frag_info->frag_stride; - } } skb = mlx5e_build_linear_skb( @@ -1666,7 +1663,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi if (xdp_buff_has_frags(&mxbuf->xdp)) { /* sinfo->nr_frags is reset by build_skb, calculate again. */ - xdp_update_skb_frags_info(skb, wi - head_wi - 1, + xdp_update_skb_frags_info(skb, wi - head_wi - nr_frags_free - 1, sinfo->xdp_frags_size, truesize, xdp_buff_get_skb_flags(&mxbuf->xdp)); @@ -1957,14 +1954,13 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w if (prog) { u8 nr_frags_free, old_nr_frags = sinfo->nr_frags; + u8 new_nr_frags; u32 len; if (mlx5e_xdp_handle(rq, prog, mxbuf)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) { struct mlx5e_frag_page *pfp; - frag_page -= old_nr_frags - sinfo->nr_frags; - for (pfp = head_page; pfp < frag_page; pfp++) pfp->frags++; @@ -1975,13 +1971,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w return NULL; /* page/packet was consumed by XDP */ } - nr_frags_free = old_nr_frags - sinfo->nr_frags; - if (unlikely(nr_frags_free)) { - frag_page -= nr_frags_free; + new_nr_frags = sinfo->nr_frags; + nr_frags_free = old_nr_frags - new_nr_frags; + if (unlikely(nr_frags_free)) truesize -= (nr_frags_free - 1) * PAGE_SIZE + ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); - } len = mxbuf->xdp.data_end - mxbuf->xdp.data; @@ -2003,7 +1998,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w struct mlx5e_frag_page *pagep; /* sinfo->nr_frags is reset by build_skb, calculate again. */ - xdp_update_skb_frags_info(skb, frag_page - head_page, + xdp_update_skb_frags_info(skb, new_nr_frags, sinfo->xdp_frags_size, truesize, xdp_buff_get_skb_flags(&mxbuf->xdp)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d3af87a94a18..123c96716a54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1072,10 +1072,11 @@ static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw) static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw) { - if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) + if (esw->mode == MLX5_ESWITCH_OFFLOADS && + mlx5_eswitch_is_funcs_handler(esw->dev)) { mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb); - - flush_workqueue(esw->work_queue); + atomic_inc(&esw->esw_funcs.generation); + } } static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 6841caef02d1..c2563bee74df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -335,10 +335,12 @@ struct esw_mc_addr { /* SRIOV only */ struct mlx5_host_work { struct work_struct work; struct mlx5_eswitch *esw; + int work_gen; }; struct mlx5_esw_functions { struct mlx5_nb nb; + atomic_t generation; bool host_funcs_disabled; u16 num_vfs; u16 num_ec_vfs; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 1366f6e489bd..7a9ee36b8dca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1241,21 +1241,17 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, flows[peer_vport->index] = flow; } - if (mlx5_esw_host_functions_enabled(esw->dev)) { - mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, - mlx5_core_max_vfs(peer_dev)) { - esw_set_peer_miss_rule_source_port(esw, peer_esw, - spec, - peer_vport->vport); - - flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), - spec, &flow_act, &dest, 1); - if (IS_ERR(flow)) { - err = PTR_ERR(flow); - goto add_vf_flow_err; - } - flows[peer_vport->index] = flow; + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { + esw_set_peer_miss_rule_source_port(esw, peer_esw, spec, + peer_vport->vport); + flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_vf_flow_err; } + flows[peer_vport->index] = flow; } if (mlx5_core_ec_sriov_enabled(peer_dev)) { @@ -1347,7 +1343,8 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + if (mlx5_core_is_ecpf_esw_manager(peer_dev) && + mlx5_esw_host_functions_enabled(peer_dev)) { peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); mlx5_del_flow_rules(flows[peer_vport->index]); } @@ -3582,22 +3579,28 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) } static void -esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out) +esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, int work_gen, + const u32 *out) { struct devlink *devlink; bool host_pf_disabled; u16 new_num_vfs; + devlink = priv_to_devlink(esw->dev); + devl_lock(devlink); + + /* Stale work from one or more mode changes ago. Bail out. */ + if (work_gen != atomic_read(&esw->esw_funcs.generation)) + goto unlock; + new_num_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_num_of_vfs); host_pf_disabled = MLX5_GET(query_esw_functions_out, out, host_params_context.host_pf_disabled); if (new_num_vfs == esw->esw_funcs.num_vfs || host_pf_disabled) - return; + goto unlock; - devlink = priv_to_devlink(esw->dev); - devl_lock(devlink); /* Number of VFs can only change from "0 to x" or "x to 0". */ if (esw->esw_funcs.num_vfs > 0) { mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs); @@ -3612,6 +3615,7 @@ esw_vfs_changed_event_handler(struct mlx5_eswitch *esw, const u32 *out) } } esw->esw_funcs.num_vfs = new_num_vfs; +unlock: devl_unlock(devlink); } @@ -3628,7 +3632,7 @@ static void esw_functions_changed_event_handler(struct work_struct *work) if (IS_ERR(out)) goto out; - esw_vfs_changed_event_handler(esw, out); + esw_vfs_changed_event_handler(esw, host_work->work_gen, out); kvfree(out); out: kfree(host_work); @@ -3648,6 +3652,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type esw = container_of(esw_funcs, struct mlx5_eswitch, esw_funcs); host_work->esw = esw; + host_work->work_gen = atomic_read(&esw_funcs->generation); INIT_WORK(&host_work->work, esw_functions_changed_event_handler); queue_work(esw->work_queue, &host_work->work); diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 37d2f108a839..786186c9a115 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1934,6 +1934,7 @@ remove_irq: mana_gd_remove_irqs(pdev); free_workqueue: destroy_workqueue(gc->service_wq); + gc->service_wq = NULL; dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err); return err; } diff --git a/drivers/net/ethernet/spacemit/k1_emac.c b/drivers/net/ethernet/spacemit/k1_emac.c index 338a2637b1da..15d43e4a748b 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.c +++ b/drivers/net/ethernet/spacemit/k1_emac.c @@ -565,7 +565,9 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv) DMA_FROM_DEVICE); if (dma_mapping_error(&priv->pdev->dev, rx_buf->dma_addr)) { dev_err_ratelimited(&ndev->dev, "Mapping skb failed\n"); - goto err_free_skb; + dev_kfree_skb_any(skb); + rx_buf->skb = NULL; + break; } rx_desc_addr = &((struct emac_desc *)rx_ring->desc_addr)[i]; @@ -590,10 +592,6 @@ static void emac_alloc_rx_desc_buffers(struct emac_priv *priv) rx_ring->head = i; return; - -err_free_skb: - dev_kfree_skb_any(skb); - rx_buf->skb = NULL; } /* Returns number of packets received */ @@ -735,7 +733,7 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb) struct emac_desc tx_desc, *tx_desc_addr; struct device *dev = &priv->pdev->dev; struct emac_tx_desc_buffer *tx_buf; - u32 head, old_head, frag_num, f; + u32 head, old_head, frag_num, f, i; bool buf_idx; frag_num = skb_shinfo(skb)->nr_frags; @@ -803,6 +801,15 @@ static void emac_tx_mem_map(struct emac_priv *priv, struct sk_buff *skb) err_free_skb: dev_dstats_tx_dropped(priv->ndev); + + i = old_head; + while (i != head) { + emac_free_tx_buf(priv, i); + + if (++i == tx_ring->total_cnt) + i = 0; + } + dev_kfree_skb_any(skb); } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 967918050433..265ce5479915 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1351,7 +1351,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, ndev_priv = netdev_priv(ndev); am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark); skb_put(skb, pkt_len); - if (port->rx_ts_enabled) + if (port->rx_ts_filter) am65_cpts_rx_timestamp(common->cpts, skb); skb_mark_for_recycle(skb); skb->protocol = eth_type_trans(skb, ndev); @@ -1811,11 +1811,14 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, switch (cfg->rx_filter) { case HWTSTAMP_FILTER_NONE: - port->rx_ts_enabled = false; + port->rx_ts_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: @@ -1825,8 +1828,8 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - port->rx_ts_enabled = true; - cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + port->rx_ts_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: @@ -1863,7 +1866,7 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN | AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN; - if (port->rx_ts_enabled) + if (port->rx_ts_filter) ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN | AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN; @@ -1888,8 +1891,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev, cfg->flags = 0; cfg->tx_type = port->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - cfg->rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT | - HWTSTAMP_FILTER_PTP_V1_L4_EVENT : HWTSTAMP_FILTER_NONE; + cfg->rx_filter = port->rx_ts_filter; return 0; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 917c37e4e89b..7750448e4746 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -52,7 +52,7 @@ struct am65_cpsw_port { bool disabled; struct am65_cpsw_slave_data slave; bool tx_ts_enabled; - bool rx_ts_enabled; + enum hwtstamp_rx_filters rx_ts_filter; struct am65_cpsw_qos qos; struct devlink_port devlink_port; struct bpf_prog *xdp_prog; diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c index de6bc1736734..15fe4d1163c1 100644 --- a/drivers/net/mctp/mctp-i2c.c +++ b/drivers/net/mctp/mctp-i2c.c @@ -343,6 +343,7 @@ static int mctp_i2c_recv(struct mctp_i2c_dev *midev) } else { status = NET_RX_DROP; spin_unlock_irqrestore(&midev->lock, flags); + kfree_skb(skb); } if (status == NET_RX_SUCCESS) { diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c index ef860cfc629f..3b5dff144177 100644 --- a/drivers/net/mctp/mctp-usb.c +++ b/drivers/net/mctp/mctp-usb.c @@ -329,7 +329,7 @@ static int mctp_usb_probe(struct usb_interface *intf, SET_NETDEV_DEV(netdev, &intf->dev); dev = netdev_priv(netdev); dev->netdev = netdev; - dev->usbdev = usb_get_dev(interface_to_usbdev(intf)); + dev->usbdev = interface_to_usbdev(intf); dev->intf = intf; usb_set_intfdata(intf, dev); @@ -365,7 +365,6 @@ static void mctp_usb_disconnect(struct usb_interface *intf) mctp_unregister_netdev(dev->netdev); usb_free_urb(dev->tx_urb); usb_free_urb(dev->rx_urb); - usb_put_dev(dev->usbdev); free_netdev(dev->netdev); } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index f4bf53da3d4f..5db841377199 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -367,6 +367,12 @@ static void sfp_fixup_ignore_tx_fault(struct sfp *sfp) sfp->state_ignore_mask |= SFP_F_TX_FAULT; } +static void sfp_fixup_ignore_tx_fault_and_los(struct sfp *sfp) +{ + sfp_fixup_ignore_tx_fault(sfp); + sfp_fixup_ignore_los(sfp); +} + static void sfp_fixup_ignore_hw(struct sfp *sfp, unsigned int mask) { sfp->state_hw_mask &= ~mask; @@ -530,7 +536,7 @@ static const struct sfp_quirk sfp_quirks[] = { // Huawei MA5671A can operate at 2500base-X, but report 1.2GBd NRZ in // their EEPROM SFP_QUIRK("HUAWEI", "MA5671A", sfp_quirk_2500basex, - sfp_fixup_ignore_tx_fault), + sfp_fixup_ignore_tx_fault_and_los), // Lantech 8330-262D-E and 8330-265D can operate at 2500base-X, but // incorrectly report 2500MBd NRZ in their EEPROM. diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a0021df12fde..19cdf69fa589 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3119,6 +3119,10 @@ static int lan78xx_init_ltm(struct lan78xx_net *dev) int ret; u32 buf; + /* LAN7850 is USB 2.0 and does not support LTM */ + if (dev->chipid == ID_REV_CHIP_ID_7850_) + return 0; + ret = lan78xx_read_reg(dev, USB_CFG1, &buf); if (ret < 0) goto init_ltm_failed; @@ -3829,6 +3833,7 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev, */ if (!(dev->net->features & NETIF_F_RXCSUM) || unlikely(rx_cmd_a & RX_CMD_A_ICSM_) || + unlikely(rx_cmd_a & RX_CMD_A_CSE_MASK_) || ((rx_cmd_a & RX_CMD_A_FVTG_) && !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) { skb->ip_summed = CHECKSUM_NONE; @@ -3901,7 +3906,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb, return 0; } - if (unlikely(rx_cmd_a & RX_CMD_A_RED_)) { + if (unlikely(rx_cmd_a & RX_CMD_A_RED_) && + (rx_cmd_a & RX_CMD_A_RX_HARD_ERRS_MASK_)) { netif_dbg(dev, rx_err, dev->net, "Error rx_cmd_a=0x%08x", rx_cmd_a); } else { @@ -4176,7 +4182,7 @@ static struct skb_data *lan78xx_tx_buf_fill(struct lan78xx_net *dev, } tx_data += len; - entry->length += len; + entry->length += max_t(unsigned int, len, ETH_ZLEN); entry->num_of_packet += skb_shinfo(skb)->gso_segs ?: 1; dev_kfree_skb_any(skb); @@ -4546,8 +4552,6 @@ static void lan78xx_disconnect(struct usb_interface *intf) phylink_disconnect_phy(dev->phylink); rtnl_unlock(); - netif_napi_del(&dev->napi); - unregister_netdev(net); timer_shutdown_sync(&dev->stat_monitor); diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h index 968e5e5faee0..17a934acff3d 100644 --- a/drivers/net/usb/lan78xx.h +++ b/drivers/net/usb/lan78xx.h @@ -74,6 +74,9 @@ #define RX_CMD_A_ICSM_ (0x00004000) #define RX_CMD_A_LEN_MASK_ (0x00003FFF) +#define RX_CMD_A_RX_HARD_ERRS_MASK_ \ + (RX_CMD_A_RX_ERRS_MASK_ & ~RX_CMD_A_CSE_MASK_) + /* Rx Command B */ #define RX_CMD_B_CSUM_SHIFT_ (16) #define RX_CMD_B_CSUM_MASK_ (0xFFFF0000) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 3a4985b582cb..05acac10cd2b 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -928,7 +928,7 @@ err: static const struct driver_info qmi_wwan_info = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, + .flags = FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, @@ -937,7 +937,7 @@ static const struct driver_info qmi_wwan_info = { static const struct driver_info qmi_wwan_info_quirk_dtr = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN | FLAG_SEND_ZLP, + .flags = FLAG_WWAN | FLAG_NOMAXMTU | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index ed86ba87ca4e..b72ba0803392 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1829,11 +1829,12 @@ usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_NOARP) != 0) net->flags |= IFF_NOARP; - if (net->max_mtu > (dev->hard_mtu - net->hard_header_len)) + if ((dev->driver_info->flags & FLAG_NOMAXMTU) == 0 && + net->max_mtu > (dev->hard_mtu - net->hard_header_len)) net->max_mtu = dev->hard_mtu - net->hard_header_len; - if (net->mtu > net->max_mtu) - net->mtu = net->max_mtu; + if (net->mtu > (dev->hard_mtu - net->hard_header_len)) + net->mtu = dev->hard_mtu - net->hard_header_len; } else if (!info->in || !info->out) status = usbnet_get_endpoints(dev, udev); diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index a936f9ea5610..63bf096b721a 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -298,8 +298,8 @@ int afs_merge_fs_addr4(struct afs_net *net, struct afs_addr_list *alist, srx.transport.sin.sin_addr.s_addr = xdr; peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL); - if (!peer) - return -ENOMEM; + if (IS_ERR(peer)) + return PTR_ERR(peer); for (i = 0; i < alist->nr_ipv4; i++) { if (peer == alist->addrs[i].peer) { @@ -342,8 +342,8 @@ int afs_merge_fs_addr6(struct afs_net *net, struct afs_addr_list *alist, memcpy(&srx.transport.sin6.sin6_addr, xdr, 16); peer = rxrpc_kernel_lookup_peer(net->socket, &srx, GFP_KERNEL); - if (!peer) - return -ENOMEM; + if (IS_ERR(peer)) + return PTR_ERR(peer); for (i = alist->nr_ipv4; i < alist->nr_addrs; i++) { if (peer == alist->addrs[i].peer) { diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 443053a76dcf..a7421382a916 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -333,7 +333,12 @@ struct tcp6_timewait_sock { }; #if IS_ENABLED(CONFIG_IPV6) -bool ipv6_mod_enabled(void); +extern int disable_ipv6_mod; + +static inline bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} static inline struct ipv6_pinfo *inet6_sk(const struct sock *__sk) { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67e25f6d15a4..ae269a2e7f4d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3576,17 +3576,49 @@ struct page_pool_bh { }; DECLARE_PER_CPU(struct page_pool_bh, system_page_pool); +#define XMIT_RECURSION_LIMIT 8 + #ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } + +static inline bool dev_xmit_recursion(void) +{ + return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > + XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + __this_cpu_inc(softnet_data.xmit.recursion); +} + +static inline void dev_xmit_recursion_dec(void) +{ + __this_cpu_dec(softnet_data.xmit.recursion); +} #else static inline int dev_recursion_level(void) { return current->net_xmit.recursion; } +static inline bool dev_xmit_recursion(void) +{ + return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); +} + +static inline void dev_xmit_recursion_inc(void) +{ + current->net_xmit.recursion++; +} + +static inline void dev_xmit_recursion_dec(void) +{ + current->net_xmit.recursion--; +} #endif void __netif_schedule(struct Qdisc *q); diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index b0e84896e6ac..bbf799ccf3b3 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -132,6 +132,7 @@ struct driver_info { #define FLAG_MULTI_PACKET 0x2000 #define FLAG_RX_ASSEMBLE 0x4000 /* rx packets may span >1 frames */ #define FLAG_NOARP 0x8000 /* device can't do ARP */ +#define FLAG_NOMAXMTU 0x10000 /* allow max_mtu above hard_mtu */ /* init device ... can sleep, or cause probe() failure */ int (*bind)(struct usbnet *, struct usb_interface *); diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 120db2865811..359b595f1df9 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -156,6 +156,18 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, { int pkt_len, err; + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); IP6CB(skb)->flags = ip6cb_flags; pkt_len = skb->len - skb_inner_network_offset(skb); @@ -166,6 +178,8 @@ static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb, pkt_len = -1; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } #endif #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 4021e6a73e32..80662f812080 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -27,6 +27,13 @@ #include <net/ip6_route.h> #endif +/* Recursion limit for tunnel xmit to detect routing loops. + * Unlike XMIT_RECURSION_LIMIT (8) used in the no-qdisc path, tunnel + * recursion involves route lookups and full IP output, consuming much + * more stack per level, so a lower limit is needed. + */ +#define IP_TUNNEL_RECURSION_LIMIT 4 + /* Keep error state on tunnel for 30 sec */ #define IPTUNNEL_ERR_TIMEO (30*HZ) diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 0d453484a585..cdd95477af7a 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -247,7 +247,7 @@ struct page_pool { /* User-facing fields, protected by page_pools_lock */ struct { struct hlist_node list; - u64 detach_time; + ktime_t detach_time; u32 id; } user; }; diff --git a/net/core/dev.h b/net/core/dev.h index 98793a738f43..781619e76b3e 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -366,41 +366,6 @@ static inline void napi_assert_will_not_race(const struct napi_struct *napi) void kick_defer_list_purge(unsigned int cpu); -#define XMIT_RECURSION_LIMIT 8 - -#ifndef CONFIG_PREEMPT_RT -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - __this_cpu_inc(softnet_data.xmit.recursion); -} - -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} -#else -static inline bool dev_xmit_recursion(void) -{ - return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) -{ - current->net_xmit.recursion++; -} - -static inline void dev_xmit_recursion_dec(void) -{ - current->net_xmit.recursion--; -} -#endif - int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack); diff --git a/net/core/filter.c b/net/core/filter.c index a77d23fe2359..78b548158fb0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2228,6 +2228,9 @@ static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb, return -ENOMEM; } + if (unlikely(!ipv6_mod_enabled())) + goto out_drop; + rcu_read_lock(); if (!nh) { dst = skb_dst(skb); @@ -2335,6 +2338,10 @@ static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb, neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); } else if (nh->nh_family == AF_INET6) { + if (unlikely(!ipv6_mod_enabled())) { + rcu_read_unlock(); + goto out_drop; + } neigh = ip_neigh_gw6(dev, &nh->ipv6_nh); is_v6gw = true; } else if (nh->nh_family == AF_INET) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a95cfe77f7f0..c56a4e7bf790 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ int pneigh_create(struct neigh_table *tbl, struct net *net, update: WRITE_ONCE(n->flags, flags); n->permanent = permanent; - WRITE_ONCE(n->protocol, protocol); + if (protocol) + WRITE_ONCE(n->protocol, protocol); out: mutex_unlock(&tbl->phash_lock); return err; diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index c82a95beceff..ee5060d8eec0 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -245,7 +245,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, goto err_cancel; if (pool->user.detach_time && nla_put_uint(rsp, NETDEV_A_PAGE_POOL_DETACH_TIME, - pool->user.detach_time)) + ktime_divns(pool->user.detach_time, NSEC_PER_SEC))) goto err_cancel; if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL)) @@ -337,7 +337,7 @@ err_unlock: void page_pool_detached(struct page_pool *pool) { mutex_lock(&page_pools_lock); - pool->user.detach_time = ktime_get_boottime_seconds(); + pool->user.detach_time = ktime_get_boottime(); netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_CHANGE_NTF); mutex_unlock(&page_pools_lock); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8036e76aa1e4..c7731e300a44 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -124,6 +124,12 @@ #include <trace/events/sock.h> +/* Keep the definition of IPv6 disable here for now, to avoid annoying linker + * issues in case IPv6=m + */ +int disable_ipv6_mod; +EXPORT_SYMBOL(disable_ipv6_mod); + /* The inetsw table contains everything that inet_create needs to * build a new socket. */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 2e61ac137128..5683c328990f 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -58,6 +58,19 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, struct iphdr *iph; int err; + if (unlikely(dev_recursion_level() > IP_TUNNEL_RECURSION_LIMIT)) { + if (dev) { + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); + DEV_STATS_INC(dev, tx_errors); + } + ip_rt_put(rt); + kfree_skb(skb); + return; + } + + dev_xmit_recursion_inc(); + skb_scrub_packet(skb, xnet); skb_clear_hash_if_not_l4(skb); @@ -88,6 +101,8 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb, pkt_len = 0; iptunnel_xmit_stats(dev, pkt_len); } + + dev_xmit_recursion_dec(); } EXPORT_SYMBOL_GPL(iptunnel_xmit); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1aa2b05ee8de..c942f1282236 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg) } static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, - struct nl_info *nlinfo) + struct nl_info *nlinfo, + struct list_head *deferred_free) { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; @@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); - free_percpu(nhge->stats); nexthop_put(nhge->nh); + list_add(&nhge->nh_list, deferred_free); /* Removal of a NH from a resilient group is notified through * bucket notifications. @@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { struct nh_grp_entry *nhge, *tmp; + LIST_HEAD(deferred_free); /* If there is nothing to do, let's avoid the costly call to * synchronize_net() @@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh, return; list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) - remove_nh_grp_entry(net, nhge, nlinfo); + remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free); /* make sure all see the newly published array before releasing rtnl */ synchronize_net(); + + /* Now safe to free percpu stats — all RCU readers have finished */ + list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) { + list_del(&nhge->nh_list); + free_percpu(nhge->stats); + } } static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 23cc9b4cb2f1..4cbd45b68088 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -86,8 +86,6 @@ struct ipv6_params ipv6_defaults = { .autoconf = 1, }; -static int disable_ipv6_mod; - module_param_named(disable, disable_ipv6_mod, int, 0444); MODULE_PARM_DESC(disable, "Disable IPv6 module such that it is non-functional"); @@ -97,12 +95,6 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); -bool ipv6_mod_enabled(void) -{ - return disable_ipv6_mod == 0; -} -EXPORT_SYMBOL_GPL(ipv6_mod_enabled); - static struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->ipv6_pinfo_offset; diff --git a/net/mctp/route.c b/net/mctp/route.c index 0381377ab760..59ad60b88563 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -359,6 +359,7 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) { struct mctp_sk_key *key; struct mctp_flow *flow; + unsigned long flags; flow = skb_ext_find(skb, SKB_EXT_MCTP); if (!flow) @@ -366,12 +367,14 @@ static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) key = flow->key; - if (key->dev) { + spin_lock_irqsave(&key->lock, flags); + + if (!key->dev) + mctp_dev_set_key(dev, key); + else WARN_ON(key->dev != dev); - return; - } - mctp_dev_set_key(dev, key); + spin_unlock_irqrestore(&key->lock, flags); } #else static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {} diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c index 62fb1031763d..040a31557201 100644 --- a/net/ncsi/ncsi-aen.c +++ b/net/ncsi/ncsi-aen.c @@ -224,7 +224,8 @@ int ncsi_aen_handler(struct ncsi_dev_priv *ndp, struct sk_buff *skb) if (!nah) { netdev_warn(ndp->ndev.dev, "Invalid AEN (0x%x) received\n", h->type); - return -ENOENT; + ret = -ENOENT; + goto out; } ret = ncsi_validate_aen_pkt(h, nah->payload); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 271ec6c3929e..fbd84bc8026a 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -1176,8 +1176,10 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, /* Find the NCSI device */ nd = ncsi_find_dev(orig_dev); ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL; - if (!ndp) - return -ENODEV; + if (!ndp) { + ret = -ENODEV; + goto err_free_skb; + } /* Check if it is AEN packet */ hdr = (struct ncsi_pkt_hdr *)skb_network_header(skb); @@ -1199,7 +1201,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, if (!nrh) { netdev_err(nd->dev, "Received unrecognized packet (0x%x)\n", hdr->type); - return -ENOENT; + ret = -ENOENT; + goto err_free_skb; } /* Associate with the request */ @@ -1207,7 +1210,8 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev, nr = &ndp->requests[hdr->id]; if (!nr->used) { spin_unlock_irqrestore(&ndp->lock, flags); - return -ENODEV; + ret = -ENODEV; + goto err_free_skb; } nr->rsp = skb; @@ -1261,4 +1265,8 @@ out_netlink: out: ncsi_free_request(nr); return ret; + +err_free_skb: + kfree_skb(skb); + return ret; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1862bd7fe804..dacec5f8a11c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -829,7 +829,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, nft_set_elem_change_active(ctx->net, set, ext); nft_setelem_data_deactivate(ctx->net, set, catchall->elem); - break; } } @@ -5873,7 +5872,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, nft_clear(ctx->net, ext); nft_setelem_data_activate(ctx->net, set, catchall->elem); - break; } } @@ -9688,7 +9686,7 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kzalloc_obj(struct nf_hook_ops, diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index d658b1478fa0..d545fa459455 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -601,10 +601,10 @@ restart: goto out; } } - } - if (cb->args[1]) { - cb->args[1] = 0; - goto restart; + if (cb->args[1]) { + cb->args[1] = 0; + goto restart; + } } out: rcu_read_unlock(); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 7f5248b5f1ee..47f7f62906e2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1546,8 +1546,10 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, if (entry->state.pf == PF_BRIDGE) { err = nfqa_parse_bridge(entry, nfqa); - if (err < 0) + if (err < 0) { + nfqnl_reinject(entry, NF_DROP); return err; + } } if (nfqa[NFQA_PAYLOAD]) { diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index b16185e9a6dd..041426e3bdbf 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -344,7 +344,7 @@ static int nft_netdev_event(unsigned long event, struct net_device *dev, break; case NETDEV_REGISTER: /* NOP if not matching or already registered */ - if (!match || (changename && ops)) + if (!match || ops) continue; ops = kmemdup(&basechain->ops, diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index a34632ae6048..7fd24e0cc428 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1640,6 +1640,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, int i; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; int g; for (g = 0; g < f->groups; g++) { @@ -1659,7 +1660,7 @@ static void pipapo_drop(struct nft_pipapo_match *m, } pipapo_unmap(f->mt, f->rules, rulemap[i].to, rulemap[i].n, - rulemap[i + 1].n, i == m->field_count - 1); + last ? 0 : rulemap[i + 1].n, last); if (pipapo_resize(f, f->rules, f->rules - rulemap[i].n)) { /* We can ignore this, a failure to shrink tables down * doesn't make tables invalid. diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 5d93e225d0f8..517106165ad2 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -318,6 +318,12 @@ static int idletimer_tg_checkentry(const struct xt_tgchk_param *par) info->timer = __idletimer_tg_find_by_label(info->label); if (info->timer) { + if (info->timer->timer_type & XT_IDLETIMER_ALARM) { + pr_debug("Adding/Replacing rule with same label and different timer type is not allowed\n"); + mutex_unlock(&list_mutex); + return -EINVAL; + } + info->timer->refcnt++; mod_timer(&info->timer->timer, secs_to_jiffies(info->timeout) + jiffies); diff --git a/net/netfilter/xt_dccp.c b/net/netfilter/xt_dccp.c index e5a13ecbe67a..037ab93e25d0 100644 --- a/net/netfilter/xt_dccp.c +++ b/net/netfilter/xt_dccp.c @@ -62,10 +62,10 @@ dccp_find_option(u_int8_t option, return true; } - if (op[i] < 2) + if (op[i] < 2 || i == optlen - 1) i++; else - i += op[i+1]?:1; + i += op[i + 1] ? : 1; } spin_unlock_bh(&dccp_buflock); diff --git a/net/netfilter/xt_tcpudp.c b/net/netfilter/xt_tcpudp.c index e8991130a3de..f76cf18f1a24 100644 --- a/net/netfilter/xt_tcpudp.c +++ b/net/netfilter/xt_tcpudp.c @@ -59,8 +59,10 @@ tcp_find_option(u_int8_t option, for (i = 0; i < optlen; ) { if (op[i] == option) return !invert; - if (op[i] < 2) i++; - else i += op[i+1]?:1; + if (op[i] < 2 || i == optlen - 1) + i++; + else + i += op[i + 1] ? : 1; } return invert; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 0c2c68c4b07e..0f90272ac254 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -267,12 +267,13 @@ static int rxrpc_listen(struct socket *sock, int backlog) * Lookup or create a remote transport endpoint record for the specified * address. * - * Return: The peer record found with a reference, %NULL if no record is found - * or a negative error code if the address is invalid or unsupported. + * Return: The peer record found with a reference or a negative error code if + * the address is invalid or unsupported. */ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, struct sockaddr_rxrpc *srx, gfp_t gfp) { + struct rxrpc_peer *peer; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; @@ -280,7 +281,8 @@ struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, if (ret < 0) return ERR_PTR(ret); - return rxrpc_lookup_peer(rx->local, srx, gfp); + peer = rxrpc_lookup_peer(rx->local, srx, gfp); + return peer ?: ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(rxrpc_kernel_lookup_peer); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 6e4bdaa876ed..783300d8b019 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -315,6 +315,7 @@ restart: if (__netif_tx_trylock(slave_txq)) { unsigned int length = qdisc_pkt_len(skb); + skb->dev = slave; if (!netif_xmit_frozen_or_stopped(slave_txq) && netdev_start_xmit(skb, slave, slave_txq, false) == NETDEV_TX_OK) { diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index 005bfc766e22..3fd6629cb999 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -759,11 +759,7 @@ int net_shaper_nl_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); @@ -1313,10 +1309,7 @@ int net_shaper_nl_cap_get_doit(struct sk_buff *skb, struct genl_info *info) if (ret) goto free_msg; - ret = genlmsg_reply(msg, info); - if (ret) - goto free_msg; - return 0; + return genlmsg_reply(msg, info); free_msg: nlmsg_free(msg); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 4c618c2b871d..9329919fb07f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2233,6 +2233,8 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, if (skb_queue_empty(&sk->sk_write_queue)) break; get_random_bytes(&delay, 2); + if (tsk->conn_timeout < 4) + tsk->conn_timeout = 4; delay %= (tsk->conn_timeout / 4); delay = msecs_to_jiffies(delay + 100); sk_reset_timer(sk, &sk->sk_timer, jiffies + delay); diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 248c2b91fe42..5a5ff88321d5 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -28,6 +28,7 @@ ALL_TESTS=" kci_test_fdb_get kci_test_fdb_del kci_test_neigh_get + kci_test_neigh_update kci_test_bridge_parent_id kci_test_address_proto kci_test_enslave_bonding @@ -1160,6 +1161,60 @@ kci_test_neigh_get() end_test "PASS: neigh get" } +kci_test_neigh_update() +{ + dstip=10.0.2.4 + dstmac=de:ad:be:ef:13:37 + local ret=0 + + for proxy in "" "proxy" ; do + # add a neighbour entry without any flags + run_cmd ip neigh add $proxy $dstip dev "$devdummy" lladdr $dstmac nud permanent + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .*\(managed\|use\|router\|extern\)" ip neigh show $proxy + + # set the extern_learn flag, but no other + run_cmd ip neigh change $proxy $dstip dev "$devdummy" extern_learn + run_cmd_grep "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* \(managed\|use\|router\)" ip neigh show $proxy + + # flags are reset when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep $dstip ip neigh show $proxy + run_cmd_grep_fail "$dstip dev $devdummy .* extern_learn" ip neigh show $proxy + + # add a protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol boot + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # protocol is retained when not provided + run_cmd ip neigh change $proxy $dstip dev "$devdummy" + run_cmd_grep "$dstip dev $devdummy .* proto boot" ip neigh show $proxy + + # change protocol + run_cmd ip neigh change $proxy $dstip dev "$devdummy" protocol static + run_cmd_grep "$dstip dev $devdummy .* proto static" ip neigh show $proxy + + # also check an extended flag for non-proxy neighs + if [ "$proxy" = "" ]; then + run_cmd ip neigh change $proxy $dstip dev "$devdummy" managed + run_cmd_grep "$dstip dev $devdummy managed" ip neigh show $proxy + + run_cmd ip neigh change $proxy $dstip dev "$devdummy" lladdr $dstmac + run_cmd_grep_fail "$dstip dev $devdummy managed" ip neigh show $proxy + fi + + run_cmd ip neigh del $proxy $dstip dev "$devdummy" + done + + if [ $ret -ne 0 ];then + end_test "FAIL: neigh update" + return 1 + fi + + end_test "PASS: neigh update" +} + kci_test_bridge_parent_id() { local ret=0 |