diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-02 14:03:31 -0800 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-02-02 14:03:31 -0800 |
| commit | edb9b8f380c3413bf783475279b1a941c7e5cec1 (patch) | |
| tree | 3b093cdb23c0d4c34e8cd472341968f5edfb5091 | |
| parent | e7368fd30165ced757d64da48e2091c83815ce5c (diff) | |
| parent | 9983a2c986534db004b50d95b7fe64bb9b925dca (diff) | |
Merge tag 'net-6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf, can and netfilter.
Current release - regressions:
- phy: fix null-deref in phy_attach_direct
- mac802154: fix possible double free upon parsing error
Previous releases - regressions:
- bpf: preserve reg parent/live fields when copying range info,
prevent mis-verification of programs as safe
- ip6: fix GRE tunnels not generating IPv6 link local addresses
- phy: dp83822: fix null-deref on DP83825/DP83826 devices
- sctp: do not check hb_timer.expires when resetting hb_timer
- eth: mtk_sock: fix SGMII configuration after phylink conversion
Previous releases - always broken:
- eth: xdp: execute xdp_do_flush() before napi_complete_done()
- skb: do not mix page pool and page referenced frags in GRO
- bpf:
- fix a possible task gone issue with bpf_send_signal[_thread]()
- fix an off-by-one bug in bpf_mem_cache_idx() to select the right
cache
- add missing btf_put to register_btf_id_dtor_kfuncs
- sockmap: fon't let sock_map_{close,destroy,unhash} call itself
- gso: fix null-deref in skb_segment_list()
- mctp: purge receive queues on sk destruction
- fix UaF caused by accept on already connected socket in exotic
socket families
- tls: don't treat list head as an entry in tls_is_tx_ready()
- netfilter: br_netfilter: disable sabotage_in hook after first
suppression
- wwan: t7xx: fix runtime PM implementation
Misc:
- MAINTAINERS: spring cleanup of networking maintainers"
* tag 'net-6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (65 commits)
mtk_sgmii: enable PCS polling to allow SFP work
net: mediatek: sgmii: fix duplex configuration
net: mediatek: sgmii: ensure the SGMII PHY is powered down on configuration
MAINTAINERS: update SCTP maintainers
MAINTAINERS: ipv6: retire Hideaki Yoshifuji
mailmap: add John Crispin's entry
MAINTAINERS: bonding: move Veaceslav Falico to CREDITS
net: openvswitch: fix flow memory leak in ovs_flow_cmd_new
net: ethernet: mtk_eth_soc: disable hardware DSA untagging for second MAC
virtio-net: Keep stop() to follow mirror sequence of open()
selftests: net: udpgso_bench_tx: Cater for pending datagrams zerocopy benchmarking
selftests: net: udpgso_bench: Fix racing bug between the rx/tx programs
selftests: net: udpgso_bench_rx/tx: Stop when wrong CLI args are provided
selftests: net: udpgso_bench_rx: Fix 'used uninitialized' compiler warning
can: mcp251xfd: mcp251xfd_ring_set_ringparam(): assign missing tx_obj_num_coalesce_irq
can: isotp: split tx timer into transmission and timeout
can: isotp: handle wait_event_interruptible() return values
can: raw: fix CAN FD frame transmissions over CAN XL devices
can: j1939: fix errant WARN_ON_ONCE in j1939_session_deactivate
hv_netvsc: Fix missed pagebuf entries in netvsc_dma_map/unmap()
...
68 files changed, 599 insertions, 272 deletions
@@ -214,6 +214,7 @@ Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com> Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> +John Crispin <john@phrozen.org> <blogic@openwrt.org> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> @@ -1173,6 +1173,10 @@ D: Future Domain TMC-16x0 SCSI driver (author) D: APM driver (early port) D: DRM drivers (author of several) +N: Veaceslav Falico +E: vfalico@gmail.com +D: Co-maintainer and co-author of the network bonding driver. + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -4179,6 +4183,10 @@ S: B-1206 Jingmao Guojigongyu S: 16 Baliqiao Nanjie, Beijing 101100 S: People's Repulic of China +N: Vlad Yasevich +E: vyasevich@gmail.com +D: SCTP protocol maintainer. + N: Aviad Yehezkel E: aviadye@nvidia.com D: Kernel TLS implementation and offload support. diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index dc2e60ced927..b481b81f3be5 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -819,7 +819,7 @@ NAPI ---- This driver supports NAPI (Rx polling mode). For more information on NAPI, see -https://www.linuxfoundation.org/collaborate/workgroups/networking/napi +https://wiki.linuxfoundation.org/networking/napi MACVLAN diff --git a/MAINTAINERS b/MAINTAINERS index c99f7055627d..e65f97d25b94 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3771,7 +3771,6 @@ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <j.vosburgh@gmail.com> -M: Veaceslav Falico <vfalico@gmail.com> M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Supported @@ -14609,7 +14608,6 @@ F: tools/testing/selftests/net/ipsec.c NETWORKING [IPv4/IPv6] M: "David S. Miller" <davem@davemloft.net> -M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> M: David Ahern <dsahern@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -18692,9 +18690,9 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Vlad Yasevich <vyasevich@gmail.com> M: Neil Horman <nhorman@tuxdriver.com> M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> +M: Xin Long <lucien.xin@gmail.com> L: linux-sctp@vger.kernel.org S: Maintained W: http://lksctp.sourceforge.net diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c index 3585f02575df..57eeb066a945 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c @@ -48,6 +48,7 @@ mcp251xfd_ring_set_ringparam(struct net_device *ndev, priv->rx_obj_num = layout.cur_rx; priv->rx_obj_num_coalesce_irq = layout.rx_coalesce; priv->tx->obj_num = layout.cur_tx; + priv->tx_obj_num_coalesce_irq = layout.tx_coalesce; return 0; } diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index c26755f662c1..f6f3b43dfb06 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -35,12 +35,13 @@ config NET_DSA_LANTIQ_GSWIP the xrx200 / VR9 SoC. config NET_DSA_MT7530 - tristate "MediaTek MT753x and MT7621 Ethernet switch support" + tristate "MediaTek MT7530 and MT7531 Ethernet switch support" select NET_DSA_TAG_MTK select MEDIATEK_GE_PHY help - This enables support for the MediaTek MT7530, MT7531, and MT7621 - Ethernet switch chips. + This enables support for the MediaTek MT7530 and MT7531 Ethernet + switch chips. Multi-chip module MT7530 in MT7621AT, MT7621DAT, + MT7621ST and MT7623AI SoCs is supported. config NET_DSA_MV88E6060 tristate "Marvell 88E6060 ethernet switch chip support" diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 3f8032947d86..027fff9f7db0 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2410,6 +2410,9 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) cleaned = qman_p_poll_dqrr(np->p, budget); + if (np->xdp_act & XDP_REDIRECT) + xdp_do_flush(); + if (cleaned < budget) { napi_complete_done(napi, cleaned); qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); @@ -2417,9 +2420,6 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); } - if (np->xdp_act & XDP_REDIRECT) - xdp_do_flush(); - return cleaned; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 0c35abb7d065..2e79d18fc3c7 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1993,10 +1993,15 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) if (rx_cleaned >= budget || txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) { work_done = budget; + if (ch->xdp.res & XDP_REDIRECT) + xdp_do_flush(); goto out; } } while (store_cleaned); + if (ch->xdp.res & XDP_REDIRECT) + xdp_do_flush(); + /* Update NET DIM with the values for this CDAN */ dpaa2_io_update_net_dim(ch->dpio, ch->stats.frames_per_cdan, ch->stats.bytes_per_cdan); @@ -2032,9 +2037,7 @@ out: txc_fq->dq_bytes = 0; } - if (ch->xdp.res & XDP_REDIRECT) - xdp_do_flush_map(); - else if (rx_cleaned && ch->xdp.res & XDP_TX) + if (rx_cleaned && ch->xdp.res & XDP_TX) dpaa2_eth_xdp_tx_flush(priv, ch, &priv->fq[flowid]); return work_done; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 9349f841bd06..587ad81a2dc3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1055,6 +1055,9 @@ static struct phylink_pcs *memac_pcs_create(struct device_node *mac_node, return ERR_PTR(-EPROBE_DEFER); pcs = lynx_pcs_create(mdiodev); + if (!pcs) + mdio_device_free(mdiodev); + return pcs; } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2f0b604abc5e..713069f809ec 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -880,7 +880,7 @@ void ice_set_ethtool_repr_ops(struct net_device *netdev); void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); u16 ice_get_avail_txq_count(struct ice_pf *pf); u16 ice_get_avail_rxq_count(struct ice_pf *pf); -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx); +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked); void ice_update_vsi_stats(struct ice_vsi *vsi); void ice_update_pf_stats(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 4f24d441c35e..0a55c552189a 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -441,7 +441,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto out; } - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); out: /* enable previously downed VSIs */ @@ -731,12 +731,13 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) /** * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs * @pf: pointer to the PF struct + * @locked: is adev device lock held * * Assumed caller has already disabled all VSIs before * calling this function. Reconfiguring DCB based on * local_dcbx_cfg. */ -void ice_pf_dcb_recfg(struct ice_pf *pf) +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; struct iidc_event *event; @@ -783,14 +784,16 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } - /* Notify the AUX drivers that TC change is finished */ - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return; + if (!locked) { + /* Notify the AUX drivers that TC change is finished */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return; - set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } } /** @@ -1044,7 +1047,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, } /* changes in configuration update VSI */ - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); /* enable previously downed VSIs */ ice_dcb_ena_dis_vsi(pf, true, true); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 4c421c842a13..800879a88c5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -23,7 +23,7 @@ u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index); int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked); int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg); -void ice_pf_dcb_recfg(struct ice_pf *pf); +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked); void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); void ice_update_dcb_stats(struct ice_pf *pf); @@ -128,7 +128,7 @@ static inline u8 ice_get_pfc_mode(struct ice_pf *pf) return 0; } -static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { } +static inline void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { } static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 4191994d8f3a..a359f1610fc1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3641,7 +3641,9 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int new_rx = 0, new_tx = 0; + bool locked = false; u32 curr_combined; + int ret = 0; /* do not support changing channels in Safe Mode */ if (ice_is_safe_mode(pf)) { @@ -3705,15 +3707,33 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EINVAL; } - ice_vsi_recfg_qs(vsi, new_rx, new_tx); + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(dev, "Cannot change channels when RDMA is active\n"); + ret = -EBUSY; + goto adev_unlock; + } + } + + ice_vsi_recfg_qs(vsi, new_rx, new_tx, locked); - if (!netif_is_rxfh_configured(dev)) - return ice_vsi_set_dflt_rss_lut(vsi, new_rx); + if (!netif_is_rxfh_configured(dev)) { + ret = ice_vsi_set_dflt_rss_lut(vsi, new_rx); + goto adev_unlock; + } /* Update rss_size due to change in Rx queues */ vsi->rss_size = ice_get_valid_rss_size(&pf->hw, new_rx); - return 0; +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } + return ret; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 237ede2cffb0..5f86e4111fa9 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4195,12 +4195,13 @@ bool ice_is_wol_supported(struct ice_hw *hw) * @vsi: VSI being changed * @new_rx: new number of Rx queues * @new_tx: new number of Tx queues + * @locked: is adev device_lock held * * Only change the number of queues if new_tx, or new_rx is non-0. * * Returns 0 on success. */ -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) { struct ice_pf *pf = vsi->back; int err = 0, timeout = 50; @@ -4229,7 +4230,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) ice_vsi_close(vsi); ice_vsi_rebuild(vsi, false); - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); done: clear_bit(ICE_CFG_BUSY, pf->state); diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index c34734d432e0..4e10ced736db 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -417,10 +417,12 @@ static int igc_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, * * We need to convert the system time value stored in the RX/TXSTMP registers * into a hwtstamp which can be used by the upper level timestamping functions. + * + * Returns 0 on success. **/ -static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) +static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) { switch (adapter->hw.mac.type) { case igc_i225: @@ -430,8 +432,9 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, systim & 0xFFFFFFFF); break; default: - break; + return -EINVAL; } + return 0; } /** @@ -652,7 +655,8 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; - igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) + return; switch (adapter->link_speed) { case SPEED_10: diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index bda1a6fa2ec4..e4407f09c9d3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1500,6 +1500,9 @@ static const struct devlink_param rvu_af_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set, rvu_af_dl_dwrr_mtu_validate), +}; + +static const struct devlink_param rvu_af_dl_param_exact_match[] = { DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, "npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), @@ -1556,7 +1559,6 @@ int rvu_register_dl(struct rvu *rvu) { struct rvu_devlink *rvu_dl; struct devlink *dl; - size_t size; int err; dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink), @@ -1578,21 +1580,32 @@ int rvu_register_dl(struct rvu *rvu) goto err_dl_health; } + err = devlink_params_register(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + if (err) { + dev_err(rvu->dev, + "devlink params register failed with error %d", err); + goto err_dl_health; + } + /* Register exact match devlink only for CN10K-B */ - size = ARRAY_SIZE(rvu_af_dl_params); if (!rvu_npc_exact_has_match_table(rvu)) - size -= 1; + goto done; - err = devlink_params_register(dl, rvu_af_dl_params, size); + err = devlink_params_register(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); if (err) { dev_err(rvu->dev, - "devlink params register failed with error %d", err); - goto err_dl_health; + "devlink exact match params register failed with error %d", err); + goto err_dl_exact_match; } +done: devlink_register(dl); return 0; +err_dl_exact_match: + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + err_dl_health: rvu_health_reporters_destroy(rvu); devlink_free(dl); @@ -1605,8 +1618,14 @@ void rvu_unregister_dl(struct rvu *rvu) struct devlink *dl = rvu_dl->dl; devlink_unregister(dl); - devlink_params_unregister(dl, rvu_af_dl_params, - ARRAY_SIZE(rvu_af_dl_params)); + + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + + /* Unregister exact match devlink only for CN10K-B */ + if (rvu_npc_exact_has_match_table(rvu)) + devlink_params_unregister(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); + rvu_health_reporters_destroy(rvu); devlink_free(dl); } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e3de9a53b2d9..d56eda6397a4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3177,7 +3177,8 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if (mtk_uses_dsa(dev) && !eth->prog) { + if ((mtk_uses_dsa(dev) && !eth->prog) && + !(mac->id == 1 && MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_TRGMII))) { for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { struct metadata_dst *md_dst = eth->dsa_meta[i]; @@ -3194,7 +3195,8 @@ static int mtk_open(struct net_device *dev) } } else { /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA. + * one MAC does not use DSA, or the second MAC of the MT7621 and + * MT7623 SoCs is being used. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 18a50529ce7b..2d9186d32bc0 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -519,7 +519,7 @@ #define SGMII_SPEED_10 FIELD_PREP(SGMII_SPEED_MASK, 0) #define SGMII_SPEED_100 FIELD_PREP(SGMII_SPEED_MASK, 1) #define SGMII_SPEED_1000 FIELD_PREP(SGMII_SPEED_MASK, 2) -#define SGMII_DUPLEX_FULL BIT(4) +#define SGMII_DUPLEX_HALF BIT(4) #define SGMII_IF_MODE_BIT5 BIT(5) #define SGMII_REMOTE_FAULT_DIS BIT(8) #define SGMII_CODE_SYNC_SET_VAL BIT(9) @@ -1036,11 +1036,13 @@ struct mtk_soc_data { * @regmap: The register map pointing at the range used to setup * SGMII modes * @ana_rgc3: The offset refers to register ANA_RGC3 related to regmap + * @interface: Currently configured interface mode * @pcs: Phylink PCS structure */ struct mtk_pcs { struct regmap *regmap; u32 ana_rgc3; + phy_interface_t interface; struct phylink_pcs pcs; }; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 269208a841c7..1ff024f42444 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -615,8 +615,7 @@ mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry, u32 ib1_mask = mtk_get_ib1_pkt_type_mask(ppe->eth) | MTK_FOE_IB1_UDP; int type; - flow_info = kzalloc(offsetof(struct mtk_flow_entry, l2_data.end), - GFP_ATOMIC); + flow_info = kzalloc(sizeof(*flow_info), GFP_ATOMIC); if (!flow_info) return; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index ea64fac1d425..b5e432031340 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -279,7 +279,6 @@ struct mtk_flow_entry { struct { struct mtk_flow_entry *base_flow; struct hlist_node list; - struct {} end; } l2_data; }; struct rhash_head node; diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 5c286f2c9418..bb00de1003ac 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -43,11 +43,6 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, int advertise, link_timer; bool changed, use_an; - if (interface == PHY_INTERFACE_MODE_2500BASEX) - rgc3 = RG_PHY_SPEED_3_125G; - else - rgc3 = 0; - advertise = phylink_mii_c22_pcs_encode_advertisement(interface, advertising); if (advertise < 0) @@ -88,9 +83,22 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, bmcr = 0; } - /* Configure the underlying interface speed */ - regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, - RG_PHY_SPEED_3_125G, rgc3); + if (mpcs->interface != interface) { + /* PHYA power down */ + regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, + SGMII_PHYA_PWD, SGMII_PHYA_PWD); + + if (interface == PHY_INTERFACE_MODE_2500BASEX) + rgc3 = RG_PHY_SPEED_3_125G; + else + rgc3 = 0; + + /* Configure the underlying interface speed */ + regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, + RG_PHY_SPEED_3_125G, rgc3); + + mpcs->interface = interface; + } /* Update the advertisement, noting whether it has changed */ regmap_update_bits_check(mpcs->regmap, SGMSYS_PCS_ADVERTISE, @@ -108,9 +116,17 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1, SGMII_AN_RESTART | SGMII_AN_ENABLE, bmcr); - /* Release PHYA power down state */ - regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, - SGMII_PHYA_PWD, 0); + /* Release PHYA power down state + * Only removing bit SGMII_PHYA_PWD isn't enough. + * There are cases when the SGMII_PHYA_PWD register contains 0x9 which + * prevents SGMII from working. The SGMII still shows link but no traffic + * can flow. Writing 0x0 to the PHYA_PWD register fix the issue. 0x0 was + * taken from a good working state of the SGMII interface. + * Unknown how much the QPHY needs but it is racy without a sleep. + * Tested on mt7622 & mt7986. + */ + usleep_range(50, 100); + regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, 0); return changed; } @@ -138,11 +154,11 @@ static void mtk_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, else sgm_mode = SGMII_SPEED_1000; - if (duplex == DUPLEX_FULL) - sgm_mode |= SGMII_DUPLEX_FULL; + if (duplex != DUPLEX_FULL) + sgm_mode |= SGMII_DUPLEX_HALF; regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE, - SGMII_DUPLEX_FULL | SGMII_SPEED_MASK, + SGMII_DUPLEX_HALF | SGMII_SPEED_MASK, sgm_mode); } } @@ -171,6 +187,8 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) return PTR_ERR(ss->pcs[i].regmap); ss->pcs[i].pcs.ops = &mtk_pcs_ops; + ss->pcs[i].pcs.poll = true; + ss->pcs[i].interface = PHY_INTERFACE_MODE_NA; } return 0; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index 5314c064ceae..55b484b10562 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -608,12 +608,12 @@ allocate_new: lan966x_fdma_rx_reload(rx); } - if (counter < weight && napi_complete_done(napi, counter)) - lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA); - if (redirect) xdp_do_flush(); + if (counter < weight && napi_complete_done(napi, counter)) + lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA); + return counter; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a8678d5612ee..060a77f2265d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -460,6 +460,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, sizeof(struct nfp_tun_neigh_v4); unsigned long cookie = (unsigned long)neigh; struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_neigh_lag lag_info; struct nfp_neigh_entry *nn_entry; u32 port_id; u8 mtype; @@ -468,6 +469,11 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, if (!port_id) return; + if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) { + memset(&lag_info, 0, sizeof(struct nfp_tun_neigh_lag)); + nfp_flower_lag_get_info_from_netdev(app, netdev, &lag_info); + } + spin_lock_bh(&priv->predt_lock); nn_entry = rhashtable_lookup_fast(&priv->neigh_table, &cookie, neigh_table_params); @@ -515,7 +521,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, neigh_ha_snapshot(common->dst_addr, neigh, netdev); if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) - nfp_flower_lag_get_info_from_netdev(app, netdev, lag); + memcpy(lag, &lag_info, sizeof(struct nfp_tun_neigh_lag)); common->port_id = cpu_to_be32(port_id); if (rhashtable_insert_fast(&priv->neigh_table, diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 7c2af482192d..cb1746bc0e0c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1438,6 +1438,10 @@ int qede_poll(struct napi_struct *napi, int budget) rx_work_done = (likely(fp->type & QEDE_FASTPATH_RX) && qede_has_rx_work(fp->rxq)) ? qede_rx_int(fp, budget) : 0; + + if (fp->xdp_xmit & QEDE_XDP_REDIRECT) + xdp_do_flush(); + /* Handle case where we are called by netpoll with a budget of 0 */ if (rx_work_done < budget || !budget) { if (!qede_poll_is_more_work(fp)) { @@ -1457,9 +1461,6 @@ int qede_poll(struct napi_struct *napi, int budget) qede_update_tx_producer(fp->xdp_tx); } - if (fp->xdp_xmit & QEDE_XDP_REDIRECT) - xdp_do_flush_map(); - return rx_work_done; } diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 0556542d7a6b..3a86f1213a05 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1003,8 +1003,11 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) /* Determine netdevice features */ net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL); - if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) + if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) { net_dev->features |= NETIF_F_TSO6; + if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) + net_dev->hw_enc_features |= NETIF_F_TSO6; + } /* Check whether device supports TSO */ if (!efx->type->tso_versions || !efx->type->tso_versions(efx)) net_dev->features &= ~NETIF_F_ALL_TSO; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 835caa15d55f..732774645c1a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -560,6 +560,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) + plat_dat->rx_clk_runs_in_lpi = 1; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b7e5af58ab75..1a5b8dab5e9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1080,7 +1080,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { - priv->eee_active = phy_init_eee(phy, 1) >= 0; + priv->eee_active = + phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; priv->eee_enabled = stmmac_eee_init(priv); priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9352dad58996..e02d1e3ef672 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -987,9 +987,6 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, void netvsc_dma_unmap(struct hv_device *hv_dev, struct hv_netvsc_packet *packet) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; int i; if (!hv_is_isolation_supported()) @@ -998,7 +995,7 @@ void netvsc_dma_unmap(struct hv_device *hv_dev, if (!packet->dma_range) return; - for (i = 0; i < page_count; i++) + for (i = 0; i < packet->page_buf_cnt; i++) dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma, packet->dma_range[i].mapping_size, DMA_TO_DEVICE); @@ -1028,9 +1025,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->page_buf_cnt; dma_addr_t dma; int i; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index a6f05e35d91f..b7cb71817780 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -233,7 +233,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_COMPLETE_INT_EN | DP83822_DUP_MODE_CHANGE_INT_EN | DP83822_SPEED_CHANGED_INT_EN; @@ -253,7 +254,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_PAGE_RX_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index c49062ad72c6..5e41658b1e2f 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -271,6 +271,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 716870a4499c..607aa786c8cb 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1517,7 +1517,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * another mac interface, so we should create a device link between * phy dev and mac dev. */ - if (phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) + if (dev && phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) phydev->devlink = device_link_add(dev->dev.parent, &phydev->mdio.dev, DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 18b3de854aeb..61e33e4dd0cd 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1677,13 +1677,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget) received = virtnet_receive(rq, budget, &xdp_xmit); + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush(); + /* Out of packets? */ if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit & VIRTIO_XDP_REDIR) - xdp_do_flush(); - if (xdp_xmit & VIRTIO_XDP_TX) { sq = virtnet_xdp_get_sq(vi); if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { @@ -2158,8 +2158,8 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); napi_disable(&vi->rq[i].napi); + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); virtnet_napi_tx_disable(&vi->sq[i].napi); } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c index 7eff3531b9a5..7ff33c1d6ac7 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c @@ -152,6 +152,15 @@ static irqreturn_t t7xx_dpmaif_isr_handler(int irq, void *data) } t7xx_pcie_mac_clear_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t t7xx_dpmaif_isr_thread(int irq, void *data) +{ + struct dpmaif_isr_para *isr_para = data; + struct dpmaif_ctrl *dpmaif_ctrl = isr_para->dpmaif_ctrl; + t7xx_dpmaif_irq_cb(isr_para); t7xx_pcie_mac_set_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); return IRQ_HANDLED; @@ -188,7 +197,7 @@ static void t7xx_dpmaif_register_pcie_irq(struct dpmaif_ctrl *dpmaif_ctrl) t7xx_pcie_mac_clear_int(t7xx_dev, int_type); t7xx_dev->intr_handler[int_type] = t7xx_dpmaif_isr_handler; - t7xx_dev->intr_thread[int_type] = NULL; + t7xx_dev->intr_thread[int_type] = t7xx_dpmaif_isr_thread; t7xx_dev->callback_param[int_type] = isr_para; t7xx_pcie_mac_clear_int_status(t7xx_dev, int_type); diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index aa2174a10437..f4ff2198b5ef 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -840,14 +840,13 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) if (!rxq->que_started) { atomic_set(&rxq->rx_processing, 0); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); dev_err(rxq->dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index); return work_done; } - if (!rxq->sleep_lock_pending) { - pm_runtime_get_noresume(rxq->dpmaif_ctrl->dev); + if (!rxq->sleep_lock_pending) t7xx_pci_disable_sleep(t7xx_dev); - } ret = try_wait_for_completion(&t7xx_dev->sleep_lock_acquire); if (!ret) { @@ -876,22 +875,22 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) napi_complete_done(napi, work_done); t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index); + t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); + pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); + atomic_set(&rxq->rx_processing, 0); } else { t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); } - t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); - pm_runtime_put_noidle(rxq->dpmaif_ctrl->dev); - atomic_set(&rxq->rx_processing, 0); - return work_done; } void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int que_mask) { struct dpmaif_rx_queue *rxq; - int qno; + struct dpmaif_ctrl *ctrl; + int qno, ret; qno = ffs(que_mask) - 1; if (qno < 0 || qno > DPMAIF_RXQ_NUM - 1) { @@ -900,6 +899,18 @@ void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int } rxq = &dpmaif_ctrl->rxq[qno]; + ctrl = rxq->dpmaif_ctrl; + /* We need to make sure that the modem has been resumed before + * calling napi. This can't be done inside the polling function + * as we could be blocked waiting for device to be resumed, + * which can't be done from softirq context the poll function + * is running in. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0 && ret != -EACCES) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", ret); + return; + } napi_schedule(&rxq->napi); } diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c index 494a28e386a3..3ef4a8a4f8fd 100644 --- a/drivers/net/wwan/t7xx/t7xx_netdev.c +++ b/drivers/net/wwan/t7xx/t7xx_netdev.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/netdev_features.h> #include <linux/netdevice.h> +#include <linux/pm_runtime.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/wwan.h> @@ -45,12 +46,25 @@ static void t7xx_ccmni_enable_napi(struct t7xx_ccmni_ctrl *ctlb) { - int i; + struct dpmaif_ctrl *ctrl; + int i, ret; + + ctrl = ctlb->hif_ctrl; if (ctlb->is_napi_en) return; for (i = 0; i < RXQ_NUM; i++) { + /* The usage count has to be bumped every time before calling + * napi_schedule. It will be decresed in the poll routine, + * right after napi_complete_done is called. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", + ret); + return; + } napi_enable(ctlb->napi[i]); napi_schedule(ctlb->napi[i]); } diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 871f2a27a398..226fc1703e90 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -121,6 +121,8 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) iowrite32(T7XX_L1_BIT(0), IREG_BASE(t7xx_dev) + ENABLE_ASPM_LOWPWR); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED); + pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); + pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 83ca2e8eb6b5..a152678b82b7 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -252,6 +252,7 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + bool rx_clk_runs_in_lpi; int has_xgmac; bool vlan_fail_q_en; u8 vlan_fail_q; diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 72299f261b25..43db6e47503c 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -38,4 +38,16 @@ */ #define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +/** + * is_insidevar - check if the @ptr points inside the @var memory range. + * @ptr: the pointer to a memory address. + * @var: the variable which address and size identify the memory range. + * + * Evaluates to true if the address in @ptr lies within the memory + * range allocated to @var. + */ +#define is_insidevar(ptr, var) \ + ((uintptr_t)(ptr) >= (uintptr_t)(var) && \ + (uintptr_t)(ptr) < (uintptr_t)(var) + sizeof(var)) + #endif diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index a4a41ee3e80b..e14c822f8911 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks) */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_socket_sock_rcv_skb) BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7dd8af06413..b7017cae6fd1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7782,9 +7782,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); - return 0; end: - btf_free_dtor_kfunc_tab(btf); + if (ret) + btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index ebcc3dd0fa19..1db156405b68 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size) if (size <= 192) return size_index[(size - 1) / 8] - 1; - return fls(size - 1) - 1; + return fls(size - 1) - 2; } #define NUM_CACHES 11 diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index dbef0b0967ae..7ee218827259 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3243,13 +3243,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; + copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; @@ -3577,7 +3588,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { @@ -3598,7 +3609,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -9592,7 +9603,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -10845,7 +10856,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -10856,7 +10867,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -11655,7 +11666,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f47274de012b..c09792c551bf 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -833,6 +833,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -867,7 +868,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index f20f4373ff40..9554abcfd5b4 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv, if (nf_bridge && !nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { + nf_bridge_info_free(skb); state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/can/isotp.c b/net/can/isotp.c index 608f8c24ae46..fc81d77724a1 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -140,7 +140,7 @@ struct isotp_sock { canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; - struct hrtimer rxtimer, txtimer; + struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; @@ -871,7 +871,7 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) } /* start timer to send next consecutive frame with correct delay */ - hrtimer_start(&so->txtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); + hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) @@ -879,49 +879,39 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; - enum hrtimer_restart restart = HRTIMER_NORESTART; - switch (so->tx.state) { - case ISOTP_SENDING: - - /* cfecho should be consumed by isotp_rcv_echo() here */ - if (!so->cfecho) { - /* start timeout for unlikely lost echo skb */ - hrtimer_set_expires(&so->txtimer, - ktime_add(ktime_get(), - ktime_set(ISOTP_ECHO_TIMEOUT, 0))); - restart = HRTIMER_RESTART; + /* don't handle timeouts in IDLE state */ + if (so->tx.state == ISOTP_IDLE) + return HRTIMER_NORESTART; - /* push out the next consecutive frame */ - isotp_send_cframe(so); - break; - } + /* we did not get any flow control or echo frame in time */ - /* cfecho has not been cleared in isotp_rcv_echo() */ - pr_notice_once("can-isotp: cfecho %08X timeout\n", so->cfecho); - fallthrough; + /* report 'communication error on send' */ + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); - case ISOTP_WAIT_FC: - case ISOTP_WAIT_FIRST_FC: + /* reset tx state */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); - /* we did not get any flow control frame in time */ + return HRTIMER_NORESTART; +} - /* report 'communication error on send' */ - sk->sk_err = ECOMM; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); +static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txfrtimer); - /* reset tx state */ - so->tx.state = ISOTP_IDLE; - wake_up_interruptible(&so->wait); - break; + /* start echo timeout handling and cover below protocol error */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); - default: - WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n", - so->tx.state, so->cfecho); - } + /* cfecho should be consumed by isotp_rcv_echo() here */ + if (so->tx.state == ISOTP_SENDING && !so->cfecho) + isotp_send_cframe(so); - return restart; + return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) @@ -1162,6 +1152,10 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + /* force state machines to be idle also when a signal occurred */ + so->tx.state = ISOTP_IDLE; + so->rx.state = ISOTP_IDLE; + spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); @@ -1194,6 +1188,7 @@ static int isotp_release(struct socket *sock) } } + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); @@ -1597,6 +1592,8 @@ static int isotp_init(struct sock *sk) so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; + hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 5c722b55fe23..fce9b9ebf13f 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1092,10 +1092,6 @@ static bool j1939_session_deactivate(struct j1939_session *session) bool active; j1939_session_list_lock(priv); - /* This function should be called with a session ref-count of at - * least 2. - */ - WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); j1939_session_list_unlock(priv); diff --git a/net/can/raw.c b/net/can/raw.c index 81071cdb0301..ba86782ba8bb 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -132,8 +132,8 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; /* make sure to not pass oversized frames to the socket */ - if ((can_is_canfd_skb(oskb) && !ro->fd_frames && !ro->xl_frames) || - (can_is_canxl_skb(oskb) && !ro->xl_frames)) + if ((!ro->fd_frames && can_is_canfd_skb(oskb)) || + (!ro->xl_frames && can_is_canxl_skb(oskb))) return; /* eliminate multiple filter matches for the same skb */ @@ -670,6 +670,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (copy_from_sockptr(&ro->fd_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames && !ro->fd_frames) { + ro->fd_frames = ro->xl_frames; + return -EINVAL; + } break; case CAN_RAW_XL_FRAMES: @@ -679,6 +684,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (copy_from_sockptr(&ro->xl_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames) + ro->fd_frames = ro->xl_frames; break; case CAN_RAW_JOIN_FILTERS: @@ -786,6 +794,25 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } +static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +{ + /* Classical CAN -> no checks for flags and device capabilities */ + if (can_is_can_skb(skb)) + return false; + + /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ + if (ro->fd_frames && can_is_canfd_skb(skb) && + (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) + return false; + + /* CAN XL -> needs to be enabled and a CAN XL device */ + if (ro->xl_frames && can_is_canxl_skb(skb) && + can_is_canxl_dev_mtu(mtu)) + return false; + + return true; +} + static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; @@ -833,20 +860,8 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto free_skb; err = -EINVAL; - if (ro->xl_frames && can_is_canxl_dev_mtu(dev->mtu)) { - /* CAN XL, CAN FD and Classical CAN */ - if (!can_is_canxl_skb(skb) && !can_is_canfd_skb(skb) && - !can_is_can_skb(skb)) - goto free_skb; - } else if (ro->fd_frames && dev->mtu == CANFD_MTU) { - /* CAN FD and Classical CAN */ - if (!can_is_canfd_skb(skb) && !can_is_can_skb(skb)) - goto free_skb; - } else { - /* Classical CAN */ - if (!can_is_can_skb(skb)) - goto free_skb; - } + if (raw_bad_txframe(ro, skb, dev->mtu)) + goto free_skb; sockcm_init(&sockc, sk); if (msg->msg_controllen) { diff --git a/net/core/gro.c b/net/core/gro.c index 506f83d715f8..4bac7ea6e025 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -162,6 +162,15 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) struct sk_buff *lp; int segs; + /* Do not splice page pool based packets w/ non-page pool + * packets. This can result in reference count issues as page + * pool pages will not decrement the reference count and will + * instead be immediately returned to the pool or have frag + * count decremented. + */ + if (p->pp_recycle != skb->pp_recycle) + return -ETOOMANYREFS; + /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ gro_max_size = READ_ONCE(p->dev->gro_max_size); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4a0eb5593275..a31ff4d83ecc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4100,7 +4100,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_shinfo(skb)->frag_list = NULL; - do { + while (list_skb) { nskb = list_skb; list_skb = list_skb->next; @@ -4146,8 +4146,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; - - } while (list_skb); + } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 22fa2c5bc6ec..a68a7290a3b2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1569,15 +1569,16 @@ void sock_map_unhash(struct sock *sk) psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; + saved_unhash = READ_ONCE(sk->sk_prot)->unhash; + } else { + saved_unhash = psock->saved_unhash; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); } - - saved_unhash = psock->saved_unhash; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - saved_unhash(sk); + if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) + return; + if (saved_unhash) + saved_unhash(sk); } EXPORT_SYMBOL_GPL(sock_map_unhash); @@ -1590,17 +1591,18 @@ void sock_map_destroy(struct sock *sk) psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->destroy) - sk->sk_prot->destroy(sk); - return; + saved_destroy = READ_ONCE(sk->sk_prot)->destroy; + } else { + saved_destroy = psock->saved_destroy; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + sk_psock_put(sk, psock); } - - saved_destroy = psock->saved_destroy; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - sk_psock_put(sk, psock); - saved_destroy(sk); + if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) + return; + if (saved_destroy) + saved_destroy(sk); } EXPORT_SYMBOL_GPL(sock_map_destroy); @@ -1615,16 +1617,21 @@ void sock_map_close(struct sock *sk, long timeout) if (unlikely(!psock)) { rcu_read_unlock(); release_sock(sk); - return sk->sk_prot->close(sk, timeout); + saved_close = READ_ONCE(sk->sk_prot)->close; + } else { + saved_close = psock->saved_close; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); } - - saved_close = psock->saved_close; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - release_sock(sk); - cancel_work_sync(&psock->work); - sk_psock_put(sk, psock); + /* Make sure we do not recurse. This is a bug. + * Leak the socket instead of crashing on a stack overflow. + */ + if (WARN_ON_ONCE(saved_close == sock_map_close)) + return; saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 94aad3870c5f..cf26d65ca389 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -6,6 +6,7 @@ #include <linux/bpf.h> #include <linux/init.h> #include <linux/wait.h> +#include <linux/util_macros.h> #include <net/inet_common.h> #include <net/tls.h> @@ -639,10 +640,9 @@ EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); */ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; struct proto *prot = newsk->sk_prot; - if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + if (is_insidevar(prot, tcp_bpf_prots)) newsk->sk_prot = sk->sk_prot_creator; } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7a84a4acffc..faa47f9ea73a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3127,17 +3127,17 @@ static void add_v4_addrs(struct inet6_dev *idev) offset = sizeof(struct in6_addr) - 4; memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); - if (idev->dev->flags&IFF_POINTOPOINT) { + if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { + scope = IPV6_ADDR_COMPATv4; + plen = 96; + pflags |= RTF_NONEXTHOP; + } else { if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) return; addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; - } else { - scope = IPV6_ADDR_COMPATv4; - plen = 96; - pflags |= RTF_NONEXTHOP; } if (addr.s6_addr32[3]) { @@ -3447,6 +3447,30 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static void addrconf_init_auto_addrs(struct net_device *dev) +{ + switch (dev->type) { +#if IS_ENABLED(CONFIG_IPV6_SIT) + case ARPHRD_SIT: + addrconf_sit_config(dev); + break; +#endif +#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) + case ARPHRD_IP6GRE: + case ARPHRD_IPGRE: + addrconf_gre_config(dev); + break; +#endif + case ARPHRD_LOOPBACK: + init_loopback(dev); + break; + + default: + addrconf_dev_config(dev); + break; + } +} + static int fixup_permanent_addr(struct net *net, struct inet6_dev *idev, struct inet6_ifaddr *ifp) @@ -3615,26 +3639,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - switch (dev->type) { -#if IS_ENABLED(CONFIG_IPV6_SIT) - case ARPHRD_SIT: - addrconf_sit_config(dev); - break; -#endif -#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) - case ARPHRD_IP6GRE: - case ARPHRD_IPGRE: - addrconf_gre_config(dev); - break; -#endif - case ARPHRD_LOOPBACK: - init_loopback(dev); - break; - - default: - addrconf_dev_config(dev); - break; - } + addrconf_init_auto_addrs(dev); if (!IS_ERR_OR_NULL(idev)) { if (run_pending) @@ -6397,7 +6402,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; @@ -6408,7 +6413,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev && idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } } diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c2aae2a6d6a6..97bb4401dd3e 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -213,7 +213,6 @@ __ieee802154_rx_handle_packet(struct ieee802154_local *local, ret = ieee802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); - kfree_skb(skb); return; } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 45bbe3e54cc2..3150f3f0c872 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -587,6 +587,11 @@ static void mctp_sk_unhash(struct sock *sk) del_timer_sync(&msk->key_expiry); } +static void mctp_sk_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); +} + static struct proto mctp_proto = { .name = "MCTP", .owner = THIS_MODULE, @@ -623,6 +628,7 @@ static int mctp_pf_create(struct net *net, struct socket *sock, return -ENOMEM; sock_init_data(sock, sk); + sk->sk_destruct = mctp_sk_destruct; rc = 0; if (sk->sk_prot->init) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 945dd40e7077..011d414038ea 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -142,10 +142,11 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) } #endif +/* do_basic_checks ensures sch->length > 0, do not use before */ #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ - ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))) && \ - (sch)->length; \ + (offset) < (skb)->len && \ + ((sch) = skb_header_pointer((skb), (offset), sizeof(_sch), &(_sch))); \ (offset) += (ntohs((sch)->length) + 3) & ~3, (count)++) /* Some validity checks to make sure the chunks are fine */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6f7f4392cffb..5a4cb796150f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a71795355aec..fcee6012293b 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1004,14 +1004,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; - goto err_kfree_key; + goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); @@ -1019,14 +1019,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) - goto err_kfree_flow; + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -1126,10 +1126,10 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); -err_kfree_flow: - ovs_flow_free(new_flow, false); err_kfree_key: kfree(key); +err_kfree_flow: + ovs_flow_free(new_flow, false); error: return error; } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 1990d496fcfc..e595079c2caf 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -83,7 +83,10 @@ static struct qrtr_node *node_get(unsigned int node_id) node->id = node_id; - radix_tree_insert(&nodes, node_id, node); + if (radix_tree_insert(&nodes, node_id, node)) { + kfree(node); + return NULL; + } return node; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 36fefc3957d7..ca2b17f32670 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -488,6 +488,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -497,8 +503,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f46643850df8..cc28e41fb745 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -431,7 +431,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); if (p->inner.clprio[prio].feed.rb_node) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index ca1eba95c293..2f66a2006517 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -196,9 +196,7 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if ((time_before(transport->hb_timer.expires, expires) || - !timer_pending(&transport->hb_timer)) && - !mod_timer(&transport->hb_timer, + if (!mod_timer(&transport->hb_timer, expires + get_random_u32_below(transport->rto))) sctp_transport_hold(transport); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9ed978634125..a83d2b4275fa 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2427,7 +2427,7 @@ static bool tls_is_tx_ready(struct tls_sw_context_tx *ctx) { struct tls_rec *rec; - rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); + rec = list_first_entry_or_null(&ctx->tx_list, struct tls_rec, list); if (!rec) return false; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 2cf0c7a3fe23..567e07c19ecc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -30,6 +30,8 @@ #define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 +#define __always_unused __attribute__((__unused__)) + #define _FAIL(errnum, fmt...) \ ({ \ error_at_line(0, (errnum), __func__, __LINE__, fmt); \ @@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype) return socket_loopback_reuseport(family, sotype, -1); } -static void test_insert_invalid(int family, int sotype, int mapfd) +static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd) FAIL_ERRNO("map_update: expected EBADF"); } -static void test_insert_opened(int family, int sotype, int mapfd) +static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd) xclose(s); } -static void test_insert_bound(int family, int sotype, int mapfd) +static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -386,7 +391,8 @@ close: xclose(s); } -static void test_insert(int family, int sotype, int mapfd) +static void test_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_insert(int family, int sotype, int mapfd) +static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_close(int family, int sotype, int mapfd) +static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd) FAIL_ERRNO("map_delete: expected EINVAL/EINVAL"); } -static void test_lookup_after_insert(int family, int sotype, int mapfd) +static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 cookie, value; socklen_t len; @@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_after_delete(int family, int sotype, int mapfd) +static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_32_bit_value(int family, int sotype, int mapfd) +static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key, value32; int err, s; @@ -523,7 +534,8 @@ close: xclose(s); } -static void test_update_existing(int family, int sotype, int mapfd) +static void test_update_existing(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int s1, s2; u64 value; @@ -551,7 +563,7 @@ close_s1: /* Exercise the code path where we destroy child sockets that never * got accept()'ed, aka orphans, when parent socket gets closed. */ -static void test_destroy_orphan_child(int family, int sotype, int mapfd) +static void do_destroy_orphan_child(int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -582,10 +594,38 @@ close_srv: xclose(s); } +static void test_destroy_orphan_child(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd) +{ + int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + const struct test { + int progfd; + enum bpf_attach_type atype; + } tests[] = { + { -1, -1 }, + { msg_verdict, BPF_SK_MSG_VERDICT }, + { skb_verdict, BPF_SK_SKB_VERDICT }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (t->progfd != -1 && + xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0) + return; + + do_destroy_orphan_child(family, sotype, mapfd); + + if (t->progfd != -1) + xbpf_prog_detach2(t->progfd, mapfd, t->atype); + } +} + /* Perform a passive open after removing listening socket from SOCKMAP * to ensure that callbacks get restored properly. */ -static void test_clone_after_delete(int family, int sotype, int mapfd) +static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -621,7 +661,8 @@ close_srv: * SOCKMAP, but got accept()'ed only after the parent has been removed * from SOCKMAP, gets cloned without parent psock state or callbacks. */ -static void test_accept_after_delete(int family, int sotype, int mapfd) +static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0; @@ -675,7 +716,8 @@ close_srv: /* Check that child socket that got created and accepted while parent * was in a SOCKMAP is cloned without parent psock state or callbacks. */ -static void test_accept_before_delete(int family, int sotype, int mapfd) +static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0, one = 1; @@ -784,7 +826,8 @@ done: return NULL; } -static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) +static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; struct sockaddr_storage addr; @@ -847,7 +890,8 @@ static void *listen_thread(void *arg) return NULL; } -static void test_race_insert_listen(int family, int socktype, int mapfd) +static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused, + int family, int socktype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; const u32 zero = 0; @@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { const struct op_test { - void (*fn)(int family, int sotype, int mapfd); + void (*fn)(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd); const char *name; int sotype; } tests[] = { @@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, if (!test__start_subtest(s)) continue; - t->fn(family, sotype, map_fd); + t->fn(skel, family, sotype, map_fd); test_ops_cleanup(map); } } diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 68b14fdfebdb..d63fd8991b03 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -225,3 +225,39 @@ .result_unpriv = ACCEPT, .insn_processed = 15, }, +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ +{ + "write tracking and register parent chain bug", + .insns = { + /* r6 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* r0 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + /* if r0 > r6 goto +1 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1), + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef), + /* r1 = 42 */ + BPF_MOV64_IMM(BPF_REG_1, 42), + /* *(u8 *)(r10 - 8) = r1 */ + BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8), + /* r2 = *(u64 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8), + /* exit(0) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid read from stack off -8+1 size 8", + .result = REJECT, +}, diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index 2d89cb0ad288..330d0b1ceced 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -6,7 +6,7 @@ ksft_skip=4 NS=ns IP6=2001:db8:1::1/64 TGT6=2001:db8:1::2 -TMPF=`mktemp` +TMPF=$(mktemp --suffix ".pcap") cleanup() { diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index dc932fd65363..640bc43452fa 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m' readonly YELLOW='\033[0;33m' readonly RED='\033[0;31m' readonly NC='\033[0m' # No Color +readonly TESTPORT=8000 readonly KSFT_PASS=0 readonly KSFT_FAIL=1 @@ -56,11 +57,26 @@ trap wake_children EXIT run_one() { local -r args=$@ + local nr_socks=0 + local i=0 + local -r timeout=10 + + ./udpgso_bench_rx -p "$TESTPORT" & + ./udpgso_bench_rx -p "$TESTPORT" -t & + + # Wait for the above test program to get ready to receive connections. + while [ "$i" -lt "$timeout" ]; do + nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")" + [ "$nr_socks" -eq 2 ] && break + i=$((i + 1)) + sleep 1 + done + if [ "$nr_socks" -ne 2 ]; then + echo "timed out while waiting for udpgso_bench_rx" + exit 1 + fi - ./udpgso_bench_rx & - ./udpgso_bench_rx -t & - - ./udpgso_bench_tx ${args} + ./udpgso_bench_tx -p "$TESTPORT" ${args} } run_in_netns() { diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 6a193425c367..4058c7451e70 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) static void do_flush_udp(int fd) { static char rbuf[ETH_MAX_MTU]; - int ret, len, gso_size, budget = 256; + int ret, len, gso_size = 0, budget = 256; len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { @@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv) cfg_verify = true; cfg_read_all = true; break; + default: + exit(1); } } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index f1fdaa270291..477392715a9a 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -62,6 +62,7 @@ static int cfg_payload_len = (1472 * 42); static int cfg_port = 8000; static int cfg_runtime_ms = -1; static bool cfg_poll; +static int cfg_poll_loop_timeout_ms = 2000; static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd) } } -static void flush_errqueue(int fd, const bool do_poll) +static void flush_errqueue(int fd, const bool do_poll, + unsigned long poll_timeout, const bool poll_err) { if (do_poll) { struct pollfd fds = {0}; int ret; fds.fd = fd; - ret = poll(&fds, 1, 500); + ret = poll(&fds, 1, poll_timeout); if (ret == 0) { - if (cfg_verbose) + if ((cfg_verbose) && (poll_err)) fprintf(stderr, "poll timeout\n"); } else if (ret < 0) { error(1, errno, "poll"); @@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll) flush_errqueue_recv(fd); } +static void flush_errqueue_retry(int fd, unsigned long num_sends) +{ + unsigned long tnow, tstop; + bool first_try = true; + + tnow = gettimeofday_ms(); + tstop = tnow + cfg_poll_loop_timeout_ms; + do { + flush_errqueue(fd, true, tstop - tnow, first_try); + first_try = false; + tnow = gettimeofday_ms(); + } while ((stat_zcopies != num_sends) && (tnow < tstop)); +} + static int send_tcp(int fd, char *data) { int ret, done = 0, count = 0; @@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", + error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] " + "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) { + while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv) case 'l': cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; break; + case 'L': + cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000; + break; case 'm': cfg_sendmmsg = true; break; @@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + default: + exit(1); } } @@ -677,7 +699,7 @@ int main(int argc, char **argv) num_sends += send_udp(fd, buf[i]); num_msgs++; if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp) - flush_errqueue(fd, cfg_poll); + flush_errqueue(fd, cfg_poll, 500, true); if (cfg_msg_nr && num_msgs >= cfg_msg_nr) break; @@ -696,7 +718,7 @@ int main(int argc, char **argv) } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); if (cfg_zerocopy || cfg_tx_tstamp) - flush_errqueue(fd, true); + flush_errqueue_retry(fd, num_sends); if (close(fd)) error(1, errno, "close"); |