diff options
23 files changed, 156 insertions, 70 deletions
diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 59cb9982afe6..2555e75e5cc1 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -19,9 +19,6 @@ Userdata append support by Matthew Wood <thepacketgeek@gmail.com>, Jan 22 2024 Sysdata append support by Breno Leitao <leitao@debian.org>, Jan 15 2025 -Please send bug reports to Matt Mackall <mpm@selenic.com> -Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com> - Introduction: ============= diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2250426ec91b..2532b6f82e97 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -4382,6 +4382,15 @@ int ice_get_phy_lane_number(struct ice_hw *hw) unsigned int lane; int err; + /* E82X does not have sequential IDs, lane number is PF ID. + * For E825 device, the exception is the variant with external + * PHY (0x579F), in which there is also 1:1 pf_id -> lane_number + * mapping. + */ + if (hw->mac_type == ICE_MAC_GENERIC || + hw->device_id == ICE_DEV_ID_E825C_SGMII) + return hw->pf_id; + options = kcalloc(ICE_AQC_PORT_OPT_MAX, sizeof(*options), GFP_KERNEL); if (!options) return -ENOMEM; @@ -6497,6 +6506,28 @@ u32 ice_get_link_speed(u16 index) } /** + * ice_get_dest_cgu - get destination CGU dev for given HW + * @hw: pointer to the HW struct + * + * Get CGU client id for CGU register read/write operations. + * + * Return: CGU device id to use in SBQ transactions. + */ +static enum ice_sbq_dev_id ice_get_dest_cgu(struct ice_hw *hw) +{ + /* On dual complex E825 only complex 0 has functional CGU powering all + * the PHYs. + * SBQ destination device cgu points to CGU on a current complex and to + * access primary CGU from the secondary complex, the driver should use + * cgu_peer as a destination device. + */ + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) && + !ice_is_primary(hw)) + return ice_sbq_dev_cgu_peer; + return ice_sbq_dev_cgu; +} + +/** * ice_read_cgu_reg - Read a CGU register * @hw: Pointer to the HW struct * @addr: Register address to read @@ -6510,8 +6541,8 @@ u32 ice_get_link_speed(u16 index) int ice_read_cgu_reg(struct ice_hw *hw, u32 addr, u32 *val) { struct ice_sbq_msg_input cgu_msg = { + .dest_dev = ice_get_dest_cgu(hw), .opcode = ice_sbq_msg_rd, - .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr }; int err; @@ -6542,8 +6573,8 @@ int ice_read_cgu_reg(struct ice_hw *hw, u32 addr, u32 *val) int ice_write_cgu_reg(struct ice_hw *hw, u32 addr, u32 val) { struct ice_sbq_msg_input cgu_msg = { + .dest_dev = ice_get_dest_cgu(hw), .opcode = ice_sbq_msg_wr, - .dest_dev = ice_sbq_dev_cgu, .msg_addr_low = addr, .data = val }; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 363ae79a3620..013c93b6605e 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -1479,7 +1479,7 @@ static void ice_init_prof_masks(struct ice_hw *hw, enum ice_block blk) per_pf = ICE_PROF_MASK_COUNT / hw->dev_caps.num_funcs; hw->blk[blk].masks.count = per_pf; - hw->blk[blk].masks.first = hw->pf_id * per_pf; + hw->blk[blk].masks.first = hw->logical_pf_id * per_pf; memset(hw->blk[blk].masks.masks, 0, sizeof(hw->blk[blk].masks.masks)); diff --git a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h index 183dd5457d6a..21bb861febbf 100644 --- a/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_sbq_cmd.h @@ -50,6 +50,7 @@ enum ice_sbq_dev_id { ice_sbq_dev_phy_0 = 0x02, ice_sbq_dev_cgu = 0x06, ice_sbq_dev_phy_0_peer = 0x0D, + ice_sbq_dev_cgu_peer = 0x0F, }; enum ice_sbq_msg_opcode { diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index f8a208c84f15..10e2445e0ded 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2281,7 +2281,7 @@ static int igb_get_sset_count(struct net_device *netdev, int sset) case ETH_SS_PRIV_FLAGS: return IGB_PRIV_FLAGS_STR_LEN; default: - return -ENOTSUPP; + return -EOPNOTSUPP; } } diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index f3e7218ba6f3..bb783042d1af 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -810,7 +810,7 @@ static int igc_ethtool_get_sset_count(struct net_device *netdev, int sset) case ETH_SS_PRIV_FLAGS: return IGC_PRIV_FLAGS_STR_LEN; default: - return -ENOTSUPP; + return -EOPNOTSUPP; } } @@ -2094,6 +2094,9 @@ static void igc_ethtool_diag_test(struct net_device *netdev, netdev_info(adapter->netdev, "Offline testing starting"); set_bit(__IGC_TESTING, &adapter->state); + /* power up PHY for link test */ + igc_power_up_phy_copper(&adapter->hw); + /* Link test performed before hardware reset so autoneg doesn't * interfere with test result */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index ca1ccc630001..3190ce7e44c7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -11507,10 +11507,10 @@ static int ixgbe_recovery_probe(struct ixgbe_adapter *adapter) shutdown_aci: mutex_destroy(&adapter->hw.aci.lock); ixgbe_release_hw_control(adapter); - devlink_free(adapter->devlink); clean_up_probe: disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); free_netdev(netdev); + devlink_free(adapter->devlink); pci_release_mem_regions(pdev); if (disable_dev) pci_disable_device(pdev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 114dd88fc71c..6885d2343c48 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -641,7 +641,7 @@ static int ixgbe_ptp_feature_enable(struct ptp_clock_info *ptp, * disabled */ if (rq->type != PTP_CLK_REQ_PPS || !adapter->ptp_setup_sdp) - return -ENOTSUPP; + return -EOPNOTSUPP; if (on) adapter->flags2 |= IXGBE_FLAG2_PTP_PPS_ENABLED; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c index 76382626ad41..929adeb50a98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c @@ -66,7 +66,6 @@ static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw) esw->fdb_table.legacy.addr_grp = NULL; esw->fdb_table.legacy.allmulti_grp = NULL; esw->fdb_table.legacy.promisc_grp = NULL; - atomic64_set(&esw->user_count, 0); } static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 34749814f19b..44a142a041b2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1978,7 +1978,6 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) /* Holds true only as long as DMFS is the default */ mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, MLX5_FLOW_STEERING_MODE_DMFS); - atomic64_set(&esw->user_count, 0); } static int esw_get_nr_ft_offloads_steering_src_ports(struct mlx5_eswitch *esw) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 132626a3f9f7..9ef72f294117 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2557,14 +2557,16 @@ nfp_net_alloc(struct pci_dev *pdev, const struct nfp_dev_info *dev_info, err = nfp_net_tlv_caps_parse(&nn->pdev->dev, nn->dp.ctrl_bar, &nn->tlv_caps); if (err) - goto err_free_nn; + goto err_free_xsk_pools; err = nfp_ccm_mbox_alloc(nn); if (err) - goto err_free_nn; + goto err_free_xsk_pools; return nn; +err_free_xsk_pools: + kfree(nn->dp.xsk_pools); err_free_nn: if (nn->dp.netdev) free_netdev(nn->dp.netdev); diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c index 36ccc53b1797..ef860cfc629f 100644 --- a/drivers/net/mctp/mctp-usb.c +++ b/drivers/net/mctp/mctp-usb.c @@ -96,11 +96,13 @@ static netdev_tx_t mctp_usb_start_xmit(struct sk_buff *skb, skb->data, skb->len, mctp_usb_out_complete, skb); + /* Stops TX queue first to prevent race condition with URB complete */ + netif_stop_queue(dev); rc = usb_submit_urb(urb, GFP_ATOMIC); - if (rc) + if (rc) { + netif_wake_queue(dev); goto err_drop; - else - netif_stop_queue(dev); + } return NETDEV_TX_OK; diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 194570443493..5d8d0214786c 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -886,8 +886,11 @@ static ssize_t userdatum_value_show(struct config_item *item, char *buf) static void update_userdata(struct netconsole_target *nt) { - int complete_idx = 0, child_count = 0; struct list_head *entry; + int child_count = 0; + unsigned long flags; + + spin_lock_irqsave(&target_list_lock, flags); /* Clear the current string in case the last userdatum was deleted */ nt->userdata_length = 0; @@ -897,8 +900,11 @@ static void update_userdata(struct netconsole_target *nt) struct userdatum *udm_item; struct config_item *item; - if (WARN_ON_ONCE(child_count >= MAX_EXTRADATA_ITEMS)) - break; + if (child_count >= MAX_EXTRADATA_ITEMS) { + spin_unlock_irqrestore(&target_list_lock, flags); + WARN_ON_ONCE(1); + return; + } child_count++; item = container_of(entry, struct config_item, ci_entry); @@ -912,12 +918,11 @@ static void update_userdata(struct netconsole_target *nt) * one entry length (1/MAX_EXTRADATA_ITEMS long), entry count is * checked to not exceed MAX items with child_count above */ - complete_idx += scnprintf(&nt->extradata_complete[complete_idx], - MAX_EXTRADATA_ENTRY_LEN, " %s=%s\n", - item->ci_name, udm_item->value); + nt->userdata_length += scnprintf(&nt->extradata_complete[nt->userdata_length], + MAX_EXTRADATA_ENTRY_LEN, " %s=%s\n", + item->ci_name, udm_item->value); } - nt->userdata_length = strnlen(nt->extradata_complete, - sizeof(nt->extradata_complete)); + spin_unlock_irqrestore(&target_list_lock, flags); } static ssize_t userdatum_value_store(struct config_item *item, const char *buf, diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index a2cd1cc35cde..1f381d7b13ff 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -84,7 +84,7 @@ #define DP83869_CLK_DELAY_DEF 7 /* STRAP_STS1 bits */ -#define DP83869_STRAP_OP_MODE_MASK GENMASK(2, 0) +#define DP83869_STRAP_OP_MODE_MASK GENMASK(11, 9) #define DP83869_STRAP_STS1_RESERVED BIT(11) #define DP83869_STRAP_MIRROR_ENABLED BIT(12) @@ -528,7 +528,7 @@ static int dp83869_set_strapped_mode(struct phy_device *phydev) if (val < 0) return val; - dp83869->mode = val & DP83869_STRAP_OP_MODE_MASK; + dp83869->mode = FIELD_GET(DP83869_STRAP_OP_MODE_MASK, val); return 0; } diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 85bd5d845409..232bbd79a4de 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -230,7 +230,9 @@ static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf) int i; unsigned long gpio_bits = dev->driver_info->data; - usbnet_get_endpoints(dev,intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* Toggle the GPIOs in a manufacturer/model specific way */ for (i = 2; i >= 0; i--) { @@ -848,7 +850,9 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf) dev->driver_priv = priv; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; /* Maybe the boot loader passed the MAC address via device tree */ if (!eth_platform_get_mac_address(&dev->udev->dev, buf)) { @@ -1281,7 +1285,9 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf) int ret; u8 buf[ETH_ALEN] = {0}; - usbnet_get_endpoints(dev,intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret; /* Get the MAC address */ ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID, 0, 0, ETH_ALEN, buf, 0); diff --git a/include/net/tcp.h b/include/net/tcp.h index 5ca230ed526a..ab20f549b8f9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -370,7 +370,7 @@ void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); -void tcp_rcvbuf_grow(struct sock *sk); +void tcp_rcvbuf_grow(struct sock *sk, u32 newval); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 9d2c36c6a0ed..6757233bd064 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -218,6 +218,9 @@ TRACE_EVENT(tcp_rcvbuf_grow, __field(__u32, space) __field(__u32, ooo_space) __field(__u32, rcvbuf) + __field(__u32, rcv_ssthresh) + __field(__u32, window_clamp) + __field(__u32, rcv_wnd) __field(__u8, scaling_ratio) __field(__u16, sport) __field(__u16, dport) @@ -245,6 +248,9 @@ TRACE_EVENT(tcp_rcvbuf_grow, tp->rcv_nxt; __entry->rcvbuf = sk->sk_rcvbuf; + __entry->rcv_ssthresh = tp->rcv_ssthresh; + __entry->window_clamp = tp->window_clamp; + __entry->rcv_wnd = tp->rcv_wnd; __entry->scaling_ratio = tp->scaling_ratio; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); @@ -264,11 +270,14 @@ TRACE_EVENT(tcp_rcvbuf_grow, ), TP_printk("time=%u rtt_us=%u copied=%u inq=%u space=%u ooo=%u scaling_ratio=%u rcvbuf=%u " + "rcv_ssthresh=%u window_clamp=%u rcv_wnd=%u " "family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 " "saddrv6=%pI6c daddrv6=%pI6c skaddr=%p sock_cookie=%llx", __entry->time, __entry->rtt_us, __entry->copied, __entry->inq, __entry->space, __entry->ooo_space, __entry->scaling_ratio, __entry->rcvbuf, + __entry->rcv_ssthresh, __entry->window_clamp, + __entry->rcv_wnd, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 31ea5af49f2d..e4a979b75cc6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -891,18 +891,27 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, } } -void tcp_rcvbuf_grow(struct sock *sk) +void tcp_rcvbuf_grow(struct sock *sk, u32 newval) { const struct net *net = sock_net(sk); struct tcp_sock *tp = tcp_sk(sk); - int rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap, oldval; + u64 grow; + + oldval = tp->rcvq_space.space; + tp->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return; + /* DRS is always one RTT late. */ + rcvwin = newval << 1; + /* slow start: allow the sender to double its rate. */ - rcvwin = tp->rcvq_space.space << 1; + grow = (u64)rcvwin * (newval - oldval); + do_div(grow, oldval); + rcvwin += grow << 1; if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt; @@ -943,9 +952,7 @@ void tcp_rcv_space_adjust(struct sock *sk) trace_tcp_rcvbuf_grow(sk, time); - tp->rcvq_space.space = copied; - - tcp_rcvbuf_grow(sk); + tcp_rcvbuf_grow(sk, copied); new_measure: tp->rcvq_space.seq = tp->copied_seq; @@ -5270,7 +5277,7 @@ end: } /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) - tcp_rcvbuf_grow(sk); + tcp_rcvbuf_grow(sk, tp->rcvq_space.space); } static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 6003e47c770a..171643815076 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -85,6 +85,7 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("DssFallback", MPTCP_MIB_DSSFALLBACK), SNMP_MIB_ITEM("SimultConnectFallback", MPTCP_MIB_SIMULTCONNFALLBACK), SNMP_MIB_ITEM("FallbackFailed", MPTCP_MIB_FALLBACKFAILED), + SNMP_MIB_ITEM("WinProbe", MPTCP_MIB_WINPROBE), }; /* mptcp_mib_alloc - allocate percpu mib counters diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 309bac6fea32..a1d3e9369fbb 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -88,6 +88,7 @@ enum linux_mptcp_mib_field { MPTCP_MIB_DSSFALLBACK, /* Bad or missing DSS */ MPTCP_MIB_SIMULTCONNFALLBACK, /* Simultaneous connect */ MPTCP_MIB_FALLBACKFAILED, /* Can't fallback due to msk status */ + MPTCP_MIB_WINPROBE, /* MPTCP-level zero window probe */ __MPTCP_MIB_MAX }; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 0292162a14ee..2d6b8de35c44 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -194,17 +194,26 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, * - mptcp does not maintain a msk-level window clamp * - returns true when the receive buffer is actually updated */ -static bool mptcp_rcvbuf_grow(struct sock *sk) +static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval) { struct mptcp_sock *msk = mptcp_sk(sk); const struct net *net = sock_net(sk); - int rcvwin, rcvbuf, cap; + u32 rcvwin, rcvbuf, cap, oldval; + u64 grow; + oldval = msk->rcvq_space.space; + msk->rcvq_space.space = newval; if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) || (sk->sk_userlocks & SOCK_RCVBUF_LOCK)) return false; - rcvwin = msk->rcvq_space.space << 1; + /* DRS is always one RTT late. */ + rcvwin = newval << 1; + + /* slow start: allow the sender to double its rate. */ + grow = (u64)rcvwin * (newval - oldval); + do_div(grow, oldval); + rcvwin += grow << 1; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue)) rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq; @@ -334,7 +343,7 @@ end: skb_set_owner_r(skb, sk); /* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */ if (sk->sk_socket) - mptcp_rcvbuf_grow(sk); + mptcp_rcvbuf_grow(sk, msk->rcvq_space.space); } static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset, @@ -998,7 +1007,7 @@ static void __mptcp_clean_una(struct sock *sk) if (WARN_ON_ONCE(!msk->recovery)) break; - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); } dfrag_clear(sk, dfrag); @@ -1290,7 +1299,12 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { + /* No need for zero probe if there are any data pending + * either at the msk or ssk level; skb is the current write + * queue tail and can be empty at this point. + */ + if (snd_una != msk->snd_nxt || skb->len || + skb != tcp_send_head(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1341,6 +1355,7 @@ alloc_skb: mpext->dsn64); if (zero_window_probe) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_WINPROBE); mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) @@ -1543,7 +1558,7 @@ static int __subflow_push_pending(struct sock *sk, struct sock *ssk, mptcp_update_post_push(msk, dfrag, ret); } - WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); + msk->first_pending = mptcp_send_next(sk); if (msk->snd_burst <= 0 || !sk_stream_memory_free(ssk) || @@ -1903,7 +1918,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) get_page(dfrag->page); list_add_tail(&dfrag->list, &msk->rtx_queue); if (!msk->first_pending) - WRITE_ONCE(msk->first_pending, dfrag); + msk->first_pending = dfrag; } pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk, dfrag->data_seq, dfrag->data_len, dfrag->already_sent, @@ -1936,22 +1951,36 @@ do_error: static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied); -static int __mptcp_recvmsg_mskq(struct sock *sk, - struct msghdr *msg, - size_t len, int flags, +static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, + size_t len, int flags, int copied_total, struct scm_timestamping_internal *tss, int *cmsg_flags) { struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; + int total_data_len = 0; int copied = 0; skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { - u32 offset = MPTCP_SKB_CB(skb)->offset; + u32 delta, offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; - u32 count = min_t(size_t, len - copied, data_len); + u32 count; int err; + if (flags & MSG_PEEK) { + /* skip already peeked skbs */ + if (total_data_len + data_len <= copied_total) { + total_data_len += data_len; + continue; + } + + /* skip the already peeked data in the current skb */ + delta = copied_total - total_data_len; + offset += delta; + data_len -= delta; + } + + count = min_t(size_t, len - copied, data_len); if (!(flags & MSG_TRUNC)) { err = skb_copy_datagram_msg(skb, offset, msg, count); if (unlikely(err < 0)) { @@ -1968,16 +1997,14 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, copied += count; - if (count < data_len) { - if (!(flags & MSG_PEEK)) { + if (!(flags & MSG_PEEK)) { + msk->bytes_consumed += count; + if (count < data_len) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; - msk->bytes_consumed += count; + break; } - break; - } - if (!(flags & MSG_PEEK)) { /* avoid the indirect call, we know the destructor is sock_rfree */ skb->destructor = NULL; skb->sk = NULL; @@ -1985,7 +2012,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); skb_attempt_defer_free(skb); - msk->bytes_consumed += count; } if (copied >= len) @@ -2049,9 +2075,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; - msk->rcvq_space.space = msk->rcvq_space.copied; - if (mptcp_rcvbuf_grow(sk)) { - + if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) { /* Make subflows follow along. If we do not do this, we * get drops at subflow level if skbs can't be moved to * the mptcp rx queue fast enough (announced rcv_win can @@ -2063,8 +2087,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); - tcp_sk(ssk)->rcvq_space.space = msk->rcvq_space.copied; - tcp_rcvbuf_grow(ssk); + /* subflows can be added before tcp_init_transfer() */ + if (tcp_sk(ssk)->rcvq_space.space) + tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied); unlock_sock_fast(ssk, slow); } } @@ -2183,7 +2208,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int err, bytes_read; - bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags); + bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, + copied, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2874,7 +2900,7 @@ static void __mptcp_clear_xmit(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_data_frag *dtmp, *dfrag; - WRITE_ONCE(msk->first_pending, NULL); + msk->first_pending = NULL; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) dfrag_clear(sk, dfrag); } @@ -3414,9 +3440,6 @@ void __mptcp_data_acked(struct sock *sk) void __mptcp_check_push(struct sock *sk, struct sock *ssk) { - if (!mptcp_send_head(sk)) - return; - if (!sock_owned_by_user(sk)) __mptcp_subflow_push_pending(sk, ssk, false); else diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 52f9cfa4ce95..379a88e14e8d 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -414,7 +414,7 @@ static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk) { const struct mptcp_sock *msk = mptcp_sk(sk); - return READ_ONCE(msk->first_pending); + return msk->first_pending; } static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk) diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh index 4046131e7888..d9e5b967f815 100755 --- a/tools/testing/selftests/net/bareudp.sh +++ b/tools/testing/selftests/net/bareudp.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # Test various bareudp tunnel configurations. |