diff options
48 files changed, 612 insertions, 315 deletions
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 8dcb8a49ab67..e044d9e8d016 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1326,14 +1326,17 @@ mt7530_setup(struct dsa_switch *ds) if (phy_node->parent == priv->dev->of_node->parent) { ret = of_get_phy_mode(mac_np, &interface); - if (ret && ret != -ENODEV) + if (ret && ret != -ENODEV) { + of_node_put(mac_np); return ret; + } id = of_mdio_parse_addr(ds->dev, phy_node); if (id == 0) priv->p5_intf_sel = P5_INTF_SEL_PHY_P0; if (id == 4) priv->p5_intf_sel = P5_INTF_SEL_PHY_P4; } + of_node_put(mac_np); of_node_put(phy_node); break; } @@ -1501,7 +1504,7 @@ unsupported: phylink_set(mask, 100baseT_Full); if (state->interface != PHY_INTERFACE_MODE_MII) { - phylink_set(mask, 1000baseT_Half); + /* This switch only supports 1G full-duplex. */ phylink_set(mask, 1000baseT_Full); if (port == 5) phylink_set(mask, 1000baseX_Full); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 31fb5a28e1c4..57d0e195cddf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -1141,6 +1141,9 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay) { + if (!(test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))) + return; + if (BNXT_PF(bp)) queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay); else @@ -1157,10 +1160,12 @@ static void bnxt_queue_sp_work(struct bnxt *bp) static void bnxt_cancel_sp_work(struct bnxt *bp) { - if (BNXT_PF(bp)) + if (BNXT_PF(bp)) { flush_workqueue(bnxt_pf_wq); - else + } else { cancel_work_sync(&bp->sp_task); + cancel_delayed_work_sync(&bp->fw_reset_task); + } } static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) @@ -6102,6 +6107,21 @@ static int bnxt_get_func_stat_ctxs(struct bnxt *bp) return cp + ulp_stat; } +/* Check if a default RSS map needs to be setup. This function is only + * used on older firmware that does not require reserving RX rings. + */ +static void bnxt_check_rss_tbl_no_rmgr(struct bnxt *bp) +{ + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + /* The RSS map is valid for RX rings set to resv_rx_rings */ + if (hw_resc->resv_rx_rings != bp->rx_nr_rings) { + hw_resc->resv_rx_rings = bp->rx_nr_rings; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + } +} + static bool bnxt_need_reserve_rings(struct bnxt *bp) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -6110,22 +6130,28 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp) int rx = bp->rx_nr_rings, stat; int vnic = 1, grp = rx; - if (bp->hwrm_spec_code < 0x10601) - return false; - - if (hw_resc->resv_tx_rings != bp->tx_nr_rings) + if (hw_resc->resv_tx_rings != bp->tx_nr_rings && + bp->hwrm_spec_code >= 0x10601) return true; + /* Old firmware does not need RX ring reservations but we still + * need to setup a default RSS map when needed. With new firmware + * we go through RX ring reservations first and then set up the + * RSS map for the successfully reserved RX rings when needed. + */ + if (!BNXT_NEW_RM(bp)) { + bnxt_check_rss_tbl_no_rmgr(bp); + return false; + } if ((bp->flags & BNXT_FLAG_RFS) && !(bp->flags & BNXT_FLAG_CHIP_P5)) vnic = rx + 1; if (bp->flags & BNXT_FLAG_AGG_RINGS) rx <<= 1; stat = bnxt_get_func_stat_ctxs(bp); - if (BNXT_NEW_RM(bp) && - (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || - hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || - (hw_resc->resv_hw_ring_grps != grp && - !(bp->flags & BNXT_FLAG_CHIP_P5)))) + if (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp || + hw_resc->resv_vnics != vnic || hw_resc->resv_stat_ctxs != stat || + (hw_resc->resv_hw_ring_grps != grp && + !(bp->flags & BNXT_FLAG_CHIP_P5))) return true; if ((bp->flags & BNXT_FLAG_CHIP_P5) && BNXT_PF(bp) && hw_resc->resv_irqs != nq) @@ -6214,6 +6240,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp) if (!tx || !rx || !cp || !grp || !vnic || !stat) return -ENOMEM; + if (!netif_is_rxfh_configured(bp->dev)) + bnxt_set_dflt_rss_indir_tbl(bp); + return rc; } @@ -8495,9 +8524,6 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init) rc = bnxt_init_int_mode(bp); bnxt_ulp_irq_restart(bp, rc); } - if (!netif_is_rxfh_configured(bp->dev)) - bnxt_set_dflt_rss_indir_tbl(bp); - if (rc) { netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc); return rc; @@ -9284,16 +9310,19 @@ static ssize_t bnxt_show_temp(struct device *dev, struct hwrm_temp_monitor_query_input req = {0}; struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); - u32 temp = 0; + u32 len = 0; resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) - temp = resp->temp * 1000; /* display millidegree */ + if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - return sprintf(buf, "%u\n", temp); + if (len) + return len; + + return sprintf(buf, "unknown\n"); } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); @@ -9475,15 +9504,15 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } } - bnxt_enable_napi(bp); - bnxt_debug_dev_init(bp); - rc = bnxt_init_nic(bp, irq_re_init); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); - goto open_err; + goto open_err_irq; } + bnxt_enable_napi(bp); + bnxt_debug_dev_init(bp); + if (link_re_init) { mutex_lock(&bp->link_lock); rc = bnxt_update_phy_setting(bp); @@ -9514,10 +9543,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bnxt_vf_reps_open(bp); return 0; -open_err: - bnxt_debug_dev_exit(bp); - bnxt_disable_napi(bp); - open_err_irq: bnxt_del_napi(bp); @@ -11761,6 +11786,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); bnxt_cancel_sp_work(bp); bp->sp_event = 0; @@ -12200,6 +12226,10 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (BNXT_CHIP_P5(bp)) bp->flags |= BNXT_FLAG_CHIP_P5; + rc = bnxt_alloc_rss_indir_tbl(bp); + if (rc) + goto init_err_pci_clean; + rc = bnxt_fw_init_one_p2(bp); if (rc) goto init_err_pci_clean; @@ -12304,11 +12334,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - rc = bnxt_alloc_rss_indir_tbl(bp); - if (rc) - goto init_err_pci_clean; - bnxt_set_dflt_rss_indir_tbl(bp); - if (BNXT_PF(bp)) { if (!bnxt_pf_wq) { bnxt_pf_wq = @@ -12339,6 +12364,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) (long)pci_resource_start(pdev, 0), dev->dev_addr); pcie_print_link_status(pdev); + pci_save_state(pdev); return 0; init_err_cleanup: @@ -12536,6 +12562,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) "Cannot re-enable PCI device after reset.\n"); } else { pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); err = bnxt_hwrm_func_reset(bp); if (!err) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 64da654f1038..1bc5130458bf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -472,20 +472,13 @@ static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) static int bnxt_get_num_ring_stats(struct bnxt *bp) { int rx, tx, cmn; - bool sh = false; - - if (bp->flags & BNXT_FLAG_SHARED_RINGS) - sh = true; rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS + bnxt_get_num_tpa_ring_stats(bp); tx = NUM_RING_TX_HW_STATS; cmn = NUM_RING_CMN_SW_STATS; - if (sh) - return (rx + tx + cmn) * bp->cp_nr_rings; - else - return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + - cmn * bp->cp_nr_rings; + return rx * bp->rx_nr_rings + tx * bp->tx_nr_rings + + cmn * bp->cp_nr_rings; } static int bnxt_get_num_stats(struct bnxt *bp) @@ -806,7 +799,7 @@ static void bnxt_get_channels(struct net_device *dev, int max_tx_sch_inputs; /* Get the most up-to-date max_tx_sch_inputs. */ - if (BNXT_NEW_RM(bp)) + if (netif_running(dev) && BNXT_NEW_RM(bp)) bnxt_hwrm_func_resc_qcaps(bp, false); max_tx_sch_inputs = hw_resc->max_tx_sch_inputs; @@ -2323,6 +2316,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data) if (rc != 0) return rc; + if (!dir_entries || !entry_length) + return -EIO; + /* Insert 2 bytes of directory info (count and size of entries) */ if (len < 2) return -EINVAL; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 87776ce3539b..7d83c45369c2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -21,6 +21,7 @@ #include <net/pkt_cls.h> #include <net/tcp.h> #include <net/vxlan.h> +#include <net/geneve.h> #include "hnae3.h" #include "hns3_enet.h" @@ -780,7 +781,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, * and it is udp packet, which has a dest port as the IANA assigned. * the hardware is expected to do the checksum offload, but the * hardware will not do the checksum offload when udp dest port is - * 4789. + * 4789 or 6081. */ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) { @@ -789,7 +790,8 @@ static bool hns3_tunnel_csum_bug(struct sk_buff *skb) l4.hdr = skb_transport_header(skb); if (!(!skb->encapsulation && - l4.udp->dest == htons(IANA_VXLAN_UDP_PORT))) + (l4.udp->dest == htons(IANA_VXLAN_UDP_PORT) || + l4.udp->dest == htons(GENEVE_UDP_PORT)))) return false; skb_checksum_help(skb); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5afb3c9c52d2..d3a774331afc 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -479,6 +479,9 @@ static int reset_rx_pools(struct ibmvnic_adapter *adapter) int i, j, rc; u64 *size_array; + if (!adapter->rx_pool) + return -1; + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); @@ -649,6 +652,9 @@ static int reset_tx_pools(struct ibmvnic_adapter *adapter) int tx_scrqs; int i, rc; + if (!adapter->tx_pool) + return -1; + tx_scrqs = be32_to_cpu(adapter->login_rsp_buf->num_txsubm_subcrqs); for (i = 0; i < tx_scrqs; i++) { rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); @@ -2011,7 +2017,10 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->req_rx_add_entries_per_subcrq != old_num_rx_slots || adapter->req_tx_entries_per_subcrq != - old_num_tx_slots) { + old_num_tx_slots || + !adapter->rx_pool || + !adapter->tso_pool || + !adapter->tx_pool) { release_rx_pools(adapter); release_tx_pools(adapter); release_napi(adapter); @@ -2024,10 +2033,14 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", + rc); goto out; rc = reset_rx_pools(adapter); if (rc) + netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", + rc); goto out; } ibmvnic_disable_irqs(adapter); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 9b17bbbe102f..4a65edc5a375 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1116,7 +1116,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, HOST_PORT_NUM, ALE_VLAN, vid); ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, 0, ALE_VLAN, vid); - ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret |= cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 1247d35d42ef..8ed78577cded 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1032,19 +1032,34 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev, return ret; } + /* reset the return code as pm_runtime_get_sync() can return + * non zero values as well. + */ + ret = 0; for (i = 0; i < cpsw->data.slaves; i++) { if (cpsw->slaves[i].ndev && - vid == cpsw->slaves[i].port_vlan) + vid == cpsw->slaves[i].port_vlan) { + ret = -EINVAL; goto err; + } } dev_dbg(priv->dev, "removing vlanid %d from vlan filter\n", vid); - cpsw_ale_del_vlan(cpsw->ale, vid, 0); - cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, - HOST_PORT_NUM, ALE_VLAN, vid); - cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, - 0, ALE_VLAN, vid); - cpsw_ale_flush_multicast(cpsw->ale, 0, vid); + ret = cpsw_ale_del_vlan(cpsw->ale, vid, 0); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_vlan() failed: ret %d\n", ret); + ret = cpsw_ale_del_ucast(cpsw->ale, priv->mac_addr, + HOST_PORT_NUM, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_ucast() failed: ret %d\n", + ret); + ret = cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast, + 0, ALE_VLAN, vid); + if (ret) + dev_err(priv->dev, "cpsw_ale_del_mcast failed. ret %d\n", + ret); + cpsw_ale_flush_multicast(cpsw->ale, ALE_PORT_HOST, vid); + ret = 0; err: pm_runtime_put(cpsw->dev); return ret; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 21640a035d7d..8e47d0112e5d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1179,6 +1179,7 @@ static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, goto nlmsg_failure; if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) || + nla_put_u32(skb, GTPA_LINK, pctx->dev->ifindex) || nla_put_be32(skb, GTPA_PEER_ADDRESS, pctx->peer_addr_ip4.s_addr) || nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr)) goto nla_put_failure; diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c index 58103152c601..6b98d74b5102 100644 --- a/drivers/net/phy/dp83869.c +++ b/drivers/net/phy/dp83869.c @@ -427,18 +427,18 @@ static int dp83869_config_init(struct phy_device *phydev) return ret; val = phy_read_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL); - val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val |= (DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID) - val |= (DP83869_RGMII_TX_CLK_DELAY_EN | - DP83869_RGMII_RX_CLK_DELAY_EN); + val &= ~(DP83869_RGMII_TX_CLK_DELAY_EN | + DP83869_RGMII_RX_CLK_DELAY_EN); if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) - val |= DP83869_RGMII_TX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_TX_CLK_DELAY_EN; if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) - val |= DP83869_RGMII_RX_CLK_DELAY_EN; + val &= ~DP83869_RGMII_RX_CLK_DELAY_EN; ret = phy_write_mmd(phydev, DP83869_DEVADDR, DP83869_RGMIICTL, val); diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index a7fbc3ccd29e..c7bcfca7d70b 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -252,6 +252,7 @@ config USB_NET_CDC_EEM config USB_NET_CDC_NCM tristate "CDC NCM support" depends on USB_USBNET + select USB_NET_CDCETHER default y help This driver provides support for CDC NCM (Network Control Model diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index e39f41efda3e..7bc6e8f856fe 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -296,7 +296,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal) netdev_dbg(dev->net, "asix_get_phy_addr()\n"); - if (ret < 0) { + if (ret < 2) { netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret); goto out; } diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index cc297ea9c6ec..e61616b0b91c 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -210,6 +210,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) skb->dev = dev = lapbeth->ethdev; + skb_reset_network_header(skb); + dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); dev_queue_xmit(skb); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index 5d9ef517cf81..e7e98ad63a91 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -161,8 +161,8 @@ responded: } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; server->rtt = rtt_us; alist->preferred = index; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 792ac711985e..18042b7dab6a 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -401,22 +401,24 @@ struct afs_vlserver { #define AFS_VLSERVER_FL_PROBED 0 /* The VL server has been probed */ #define AFS_VLSERVER_FL_PROBING 1 /* VL server is being probed */ #define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ +#define AFS_VLSERVER_FL_RESPONDING 3 /* VL server is responding */ rwlock_t lock; /* Lock on addresses */ atomic_t usage; + unsigned int rtt; /* Server's current RTT in uS */ /* Probe state */ wait_queue_head_t probe_wq; atomic_t probe_outstanding; spinlock_t probe_lock; struct { - unsigned int rtt; /* RTT as ktime/64 */ + unsigned int rtt; /* RTT in uS */ u32 abort_code; short error; - bool have_result; - bool responded:1; - bool is_yfs:1; - bool not_yfs:1; - bool local_failure:1; + unsigned short flags; +#define AFS_VLSERVER_PROBE_RESPONDED 0x01 /* At least once response (may be abort) */ +#define AFS_VLSERVER_PROBE_IS_YFS 0x02 /* The peer appears to be YFS */ +#define AFS_VLSERVER_PROBE_NOT_YFS 0x04 /* The peer appears not to be YFS */ +#define AFS_VLSERVER_PROBE_LOCAL_FAILURE 0x08 /* A local failure prevented a probe */ } probe; u16 port; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index e817fc740ba0..e8babb62ed44 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -310,6 +310,11 @@ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) alist->preferred == i ? '>' : '-', &alist->addrs[i].transport); } + seq_printf(m, " info: fl=%lx rtt=%d\n", vlserver->flags, vlserver->rtt); + seq_printf(m, " probe: fl=%x e=%d ac=%d out=%d\n", + vlserver->probe.flags, vlserver->probe.error, + vlserver->probe.abort_code, + atomic_read(&vlserver->probe_outstanding)); return 0; } diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c index 8fea54eba0c2..38b2ba1d9ec0 100644 --- a/fs/afs/vl_list.c +++ b/fs/afs/vl_list.c @@ -21,6 +21,7 @@ struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len, rwlock_init(&vlserver->lock); init_waitqueue_head(&vlserver->probe_wq); spin_lock_init(&vlserver->probe_lock); + vlserver->rtt = UINT_MAX; vlserver->name_len = name_len; vlserver->port = port; memcpy(vlserver->name, name, name_len); diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index e3aa013c2177..d1c7068b4346 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -11,15 +11,33 @@ #include "internal.h" #include "protocol_yfs.h" -static bool afs_vl_probe_done(struct afs_vlserver *server) + +/* + * Handle the completion of a set of probes. + */ +static void afs_finished_vl_probe(struct afs_vlserver *server) { - if (!atomic_dec_and_test(&server->probe_outstanding)) - return false; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { + server->rtt = UINT_MAX; + clear_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + } - wake_up_var(&server->probe_outstanding); clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags); wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING); - return true; +} + +/* + * Handle the completion of a probe RPC call. + */ +static void afs_done_one_vl_probe(struct afs_vlserver *server, bool wake_up) +{ + if (atomic_dec_and_test(&server->probe_outstanding)) { + afs_finished_vl_probe(server); + wake_up = true; + } + + if (wake_up) + wake_up_all(&server->probe_wq); } /* @@ -45,15 +63,20 @@ void afs_vlserver_probe_result(struct afs_call *call) server->probe.error = 0; goto responded; case -ECONNABORTED: - if (!server->probe.responded) { + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED)) { server->probe.abort_code = call->abort_code; server->probe.error = ret; } goto responded; case -ENOMEM: case -ENONET: - server->probe.local_failure = true; - afs_io_error(call, afs_io_error_vl_probe_fail); + case -EKEYEXPIRED: + case -EKEYREVOKED: + case -EKEYREJECTED: + server->probe.flags |= AFS_VLSERVER_PROBE_LOCAL_FAILURE; + if (server->probe.error == 0) + server->probe.error = ret; + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ case -ERFKILL: @@ -67,12 +90,12 @@ void afs_vlserver_probe_result(struct afs_call *call) default: clear_bit(index, &alist->responded); set_bit(index, &alist->failed); - if (!server->probe.responded && + if (!(server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) && (server->probe.error == 0 || server->probe.error == -ETIMEDOUT || server->probe.error == -ETIME)) server->probe.error = ret; - afs_io_error(call, afs_io_error_vl_probe_fail); + trace_afs_io_error(call->debug_id, ret, afs_io_error_vl_probe_fail); goto out; } @@ -81,39 +104,36 @@ responded: clear_bit(index, &alist->failed); if (call->service_id == YFS_VL_SERVICE) { - server->probe.is_yfs = true; + server->probe.flags |= AFS_VLSERVER_PROBE_IS_YFS; set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } else { - server->probe.not_yfs = true; - if (!server->probe.is_yfs) { + server->probe.flags |= AFS_VLSERVER_PROBE_NOT_YFS; + if (!(server->probe.flags & AFS_VLSERVER_PROBE_IS_YFS)) { clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); alist->addrs[index].srx_service = call->service_id; } } - rtt_us = rxrpc_kernel_get_srtt(call->net->socket, call->rxcall); - if (rtt_us < server->probe.rtt) { + if (rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us) && + rtt_us < server->probe.rtt) { server->probe.rtt = rtt_us; + server->rtt = rtt_us; alist->preferred = index; - have_result = true; } smp_wmb(); /* Set rtt before responded. */ - server->probe.responded = true; + server->probe.flags |= AFS_VLSERVER_PROBE_RESPONDED; set_bit(AFS_VLSERVER_FL_PROBED, &server->flags); + set_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags); + have_result = true; out: spin_unlock(&server->probe_lock); _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", server_index, index, &alist->addrs[index].transport, rtt_us, ret); - have_result |= afs_vl_probe_done(server); - if (have_result) { - server->probe.have_result = true; - wake_up_var(&server->probe.have_result); - wake_up_all(&server->probe_wq); - } + afs_done_one_vl_probe(server, have_result); } /* @@ -151,11 +171,10 @@ static bool afs_do_probe_vlserver(struct afs_net *net, in_progress = true; } else { afs_prioritise_error(_e, PTR_ERR(call), ac.abort_code); + afs_done_one_vl_probe(server, false); } } - if (!in_progress) - afs_vl_probe_done(server); return in_progress; } @@ -193,7 +212,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, { struct wait_queue_entry *waits; struct afs_vlserver *server; - unsigned int rtt = UINT_MAX; + unsigned int rtt = UINT_MAX, rtt_s; bool have_responders = false; int pref = -1, i; @@ -205,7 +224,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, server = vllist->servers[i].server; if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) __clear_bit(i, &untried); - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) have_responders = true; } } @@ -231,7 +250,7 @@ int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded) + if (server->probe.flags & AFS_VLSERVER_PROBE_RESPONDED) goto stop; if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) still_probing = true; @@ -249,10 +268,11 @@ stop: for (i = 0; i < vllist->nr_servers; i++) { if (test_bit(i, &untried)) { server = vllist->servers[i].server; - if (server->probe.responded && - server->probe.rtt < rtt) { + rtt_s = READ_ONCE(server->rtt); + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &server->flags) && + rtt_s < rtt) { pref = i; - rtt = server->probe.rtt; + rtt = rtt_s; } remove_wait_queue(&server->probe_wq, &waits[i]); diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index f405ca8b240a..c0458c903b31 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -192,7 +192,8 @@ pick_server: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; - if (!test_bit(i, &vc->untried) || !s->probe.responded) + if (!test_bit(i, &vc->untried) || + !test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) continue; if (s->probe.rtt < rtt) { vc->index = i; @@ -262,10 +263,14 @@ no_more_servers: for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; + if (test_bit(AFS_VLSERVER_FL_RESPONDING, &s->flags)) + e.responded = true; afs_prioritise_error(&e, READ_ONCE(s->probe.error), s->probe.abort_code); } + error = e.error; + failed_set_error: vc->error = error; failed: diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8bca74857a3..8d9ab50b08c9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -71,7 +71,7 @@ * NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain * TCP or UDP packets over IPv6. These are specifically * unencapsulated packets of the form IPv6|TCP or - * IPv4|UDP where the Next Header field in the IPv6 + * IPv6|UDP where the Next Header field in the IPv6 * header is either TCP or UDP. IPv6 extension headers * are not supported with this feature. This feature * cannot be set in features for a device with @@ -2667,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len) * * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS) * to reduce average number of cache lines per packet. - * get_rps_cpus() for example only access one 64 bytes aligned block : + * get_rps_cpu() for example only access one 64 bytes aligned block : * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8) */ #ifndef NET_SKB_PAD diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 91eacbdcf33d..f6abcc0bbd6e 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -59,7 +59,7 @@ bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); -u32 rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *); +bool rxrpc_kernel_get_srtt(struct socket *, struct rxrpc_call *, u32 *); int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 059b6e45a028..c33079b986e8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -138,11 +138,16 @@ enum rxrpc_recvmsg_trace { }; enum rxrpc_rtt_tx_trace { + rxrpc_rtt_tx_cancel, rxrpc_rtt_tx_data, + rxrpc_rtt_tx_no_slot, rxrpc_rtt_tx_ping, }; enum rxrpc_rtt_rx_trace { + rxrpc_rtt_rx_cancel, + rxrpc_rtt_rx_lost, + rxrpc_rtt_rx_obsolete, rxrpc_rtt_rx_ping_response, rxrpc_rtt_rx_requested_ack, }; @@ -339,10 +344,15 @@ enum rxrpc_tx_point { E_(rxrpc_recvmsg_wait, "WAIT") #define rxrpc_rtt_tx_traces \ + EM(rxrpc_rtt_tx_cancel, "CNCE") \ EM(rxrpc_rtt_tx_data, "DATA") \ + EM(rxrpc_rtt_tx_no_slot, "FULL") \ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ + EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_obsolete, "OBSL") \ + EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ E_(rxrpc_rtt_rx_requested_ack, "RACK") @@ -1087,38 +1097,43 @@ TRACE_EVENT(rxrpc_recvmsg, TRACE_EVENT(rxrpc_rtt_tx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_tx_trace why, - rxrpc_serial_t send_serial), + int slot, rxrpc_serial_t send_serial), - TP_ARGS(call, why, send_serial), + TP_ARGS(call, why, slot, send_serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_tx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; ), - TP_printk("c=%08x %s sr=%08x", + TP_printk("c=%08x [%d] %s sr=%08x", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_tx_traces), __entry->send_serial) ); TRACE_EVENT(rxrpc_rtt_rx, TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, u32 rtt, u32 rto), - TP_ARGS(call, why, send_serial, resp_serial, rtt, rto), + TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_rtt_rx_trace, why ) + __field(int, slot ) __field(rxrpc_serial_t, send_serial ) __field(rxrpc_serial_t, resp_serial ) __field(u32, rtt ) @@ -1128,14 +1143,16 @@ TRACE_EVENT(rxrpc_rtt_rx, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; + __entry->slot = slot; __entry->send_serial = send_serial; __entry->resp_serial = resp_serial; __entry->rtt = rtt; __entry->rto = rto; ), - TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%u rto=%u", + TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u", __entry->call, + __entry->slot, __print_symbolic(__entry->why, rxrpc_rtt_rx_traces), __entry->send_serial, __entry->resp_serial, diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 3d0d8231dc19..7d6687618d80 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -135,7 +135,7 @@ struct in_addr { * this socket to prevent accepting spoofed ones. */ #define IP_PMTUDISC_INTERFACE 4 -/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get +/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get * fragmented if they exeed the interface mtu */ #define IP_PMTUDISC_OMIT 5 diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index ce2767e9cec6..7b0af33bdb97 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -116,7 +116,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) if (segmented) { if (rfml->incomplete_frm == NULL) { /* Initial Segment */ - if (cfpkt_peek_head(pkt, rfml->seghead, 6) < 0) + if (cfpkt_peek_head(pkt, rfml->seghead, 6) != 0) goto out; rfml->pdu_size = get_unaligned_le16(rfml->seghead+4); @@ -233,7 +233,7 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) if (cfpkt_getlen(pkt) > rfml->fragment_size + RFM_HEAD_SIZE) err = cfpkt_peek_head(pkt, head, 6); - if (err < 0) + if (err != 0) goto out; while (cfpkt_getlen(frontpkt) > rfml->fragment_size + RFM_HEAD_SIZE) { diff --git a/net/core/dev.c b/net/core/dev.c index d42c9ea0c3c0..95ac7568f693 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6612,12 +6612,13 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; - list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif set_bit(NAPI_STATE_SCHED, &napi->state); + set_bit(NAPI_STATE_NPSVC, &napi->state); + list_add_rcu(&napi->dev_list, &dev->napi_list); napi_hash_add(napi); } EXPORT_SYMBOL(netif_napi_add); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 093e90e52bc2..2338753e936b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -162,7 +162,7 @@ static void poll_napi(struct net_device *dev) struct napi_struct *napi; int cpu = smp_processor_id(); - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (cmpxchg(&napi->poll_owner, -1, cpu) == -1) { poll_one_napi(napi); smp_store_release(&napi->poll_owner, -1); diff --git a/net/core/sock.c b/net/core/sock.c index e4f40b175acb..8eb2c924805a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3254,7 +3254,7 @@ void sk_common_release(struct sock *sk) sk->sk_prot->destroy(sk); /* - * Observation: when sock_common_release is called, processes have + * Observation: when sk_common_release is called, processes have * no access to socket. But net still has. * Step one, detach it from networking: * diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c89b46fec153..ffc5332f1390 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2121,7 +2121,8 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist) + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 6fd4330287c2..407956be7deb 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) { ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { - /* oif is set, packet is to local broadcast and + /* oif is set, packet is to local broadcast * and uc_index is set. oif is most likely set * by sk_bound_dev_if. If uc_index != oif check if the * oif is an L3 master and uc_index is an L3 slave. diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index e71ca5aec684..864326f150e2 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** - * l3mdev_fib_table - get FIB table id associated with an L3 + * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 366f76c9003d..314973033d03 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -405,18 +405,14 @@ ieee80211_calc_legacy_rate_duration(u16 bitrate, bool short_pre, return duration; } -u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, - struct ieee80211_rx_status *status, - int len) +static u32 ieee80211_get_rate_duration(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + u32 *overhead) { - struct ieee80211_supported_band *sband; - const struct ieee80211_rate *rate; bool sgi = status->enc_flags & RX_ENC_FLAG_SHORT_GI; - bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; int bw, streams; int group, idx; u32 duration; - bool cck; switch (status->bw) { case RATE_INFO_BW_20: @@ -437,20 +433,6 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, } switch (status->encoding) { - case RX_ENC_LEGACY: - if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) - return 0; - - sband = hw->wiphy->bands[status->band]; - if (!sband || status->rate_idx >= sband->n_bitrates) - return 0; - - rate = &sband->bitrates[status->rate_idx]; - cck = rate->flags & IEEE80211_RATE_MANDATORY_B; - - return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, - cck, len); - case RX_ENC_VHT: streams = status->nss; idx = status->rate_idx; @@ -477,51 +459,144 @@ u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, duration = airtime_mcs_groups[group].duration[idx]; duration <<= airtime_mcs_groups[group].shift; + *overhead = 36 + (streams << 2); + + return duration; +} + + +u32 ieee80211_calc_rx_airtime(struct ieee80211_hw *hw, + struct ieee80211_rx_status *status, + int len) +{ + struct ieee80211_supported_band *sband; + u32 duration, overhead = 0; + + if (status->encoding == RX_ENC_LEGACY) { + const struct ieee80211_rate *rate; + bool sp = status->enc_flags & RX_ENC_FLAG_SHORTPRE; + bool cck; + + if (WARN_ON_ONCE(status->band > NL80211_BAND_5GHZ)) + return 0; + + sband = hw->wiphy->bands[status->band]; + if (!sband || status->rate_idx >= sband->n_bitrates) + return 0; + + rate = &sband->bitrates[status->rate_idx]; + cck = rate->flags & IEEE80211_RATE_MANDATORY_B; + + return ieee80211_calc_legacy_rate_duration(rate->bitrate, sp, + cck, len); + } + + duration = ieee80211_get_rate_duration(hw, status, &overhead); + if (!duration) + return 0; + duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; - duration += 36 + (streams << 2); - - return duration; + return duration + overhead; } EXPORT_SYMBOL_GPL(ieee80211_calc_rx_airtime); -static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, - struct ieee80211_tx_rate *rate, - u8 band, int len) +static bool ieee80211_fill_rate_info(struct ieee80211_hw *hw, + struct ieee80211_rx_status *stat, u8 band, + struct rate_info *ri) { - struct ieee80211_rx_status stat = { - .band = band, - }; + struct ieee80211_supported_band *sband = hw->wiphy->bands[band]; + int i; - if (rate->idx < 0 || !rate->count) + if (!ri || !sband) + return false; + + stat->bw = ri->bw; + stat->nss = ri->nss; + stat->rate_idx = ri->mcs; + + if (ri->flags & RATE_INFO_FLAGS_HE_MCS) + stat->encoding = RX_ENC_HE; + else if (ri->flags & RATE_INFO_FLAGS_VHT_MCS) + stat->encoding = RX_ENC_VHT; + else if (ri->flags & RATE_INFO_FLAGS_MCS) + stat->encoding = RX_ENC_HT; + else + stat->encoding = RX_ENC_LEGACY; + + if (ri->flags & RATE_INFO_FLAGS_SHORT_GI) + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; + + stat->he_gi = ri->he_gi; + + if (stat->encoding != RX_ENC_LEGACY) + return true; + + stat->rate_idx = 0; + for (i = 0; i < sband->n_bitrates; i++) { + if (ri->legacy != sband->bitrates[i].bitrate) + continue; + + stat->rate_idx = i; + return true; + } + + return false; +} + +static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, + struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, u8 band, int len) +{ + memset(stat, 0, sizeof(*stat)); + stat->band = band; + + if (ieee80211_fill_rate_info(hw, stat, band, ri)) return 0; + if (rate->idx < 0 || !rate->count) + return -1; + if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_80; + stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) - stat.bw = RATE_INFO_BW_40; + stat->bw = RATE_INFO_BW_40; else - stat.bw = RATE_INFO_BW_20; + stat->bw = RATE_INFO_BW_20; - stat.enc_flags = 0; + stat->enc_flags = 0; if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE) - stat.enc_flags |= RX_ENC_FLAG_SHORTPRE; + stat->enc_flags |= RX_ENC_FLAG_SHORTPRE; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) - stat.enc_flags |= RX_ENC_FLAG_SHORT_GI; + stat->enc_flags |= RX_ENC_FLAG_SHORT_GI; - stat.rate_idx = rate->idx; + stat->rate_idx = rate->idx; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { - stat.encoding = RX_ENC_VHT; - stat.rate_idx = ieee80211_rate_get_vht_mcs(rate); - stat.nss = ieee80211_rate_get_vht_nss(rate); + stat->encoding = RX_ENC_VHT; + stat->rate_idx = ieee80211_rate_get_vht_mcs(rate); + stat->nss = ieee80211_rate_get_vht_nss(rate); } else if (rate->flags & IEEE80211_TX_RC_MCS) { - stat.encoding = RX_ENC_HT; + stat->encoding = RX_ENC_HT; } else { - stat.encoding = RX_ENC_LEGACY; + stat->encoding = RX_ENC_LEGACY; } + return 0; +} + +static u32 ieee80211_calc_tx_airtime_rate(struct ieee80211_hw *hw, + struct ieee80211_tx_rate *rate, + struct rate_info *ri, + u8 band, int len) +{ + struct ieee80211_rx_status stat; + + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + return ieee80211_calc_rx_airtime(hw, &stat, len); } @@ -536,7 +611,7 @@ u32 ieee80211_calc_tx_airtime(struct ieee80211_hw *hw, struct ieee80211_tx_rate *rate = &info->status.rates[i]; u32 cur_duration; - cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, + cur_duration = ieee80211_calc_tx_airtime_rate(hw, rate, NULL, info->band, len); if (!cur_duration) break; @@ -572,26 +647,41 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, if (pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_rx_status stat; struct ieee80211_tx_rate *rate = &sta->tx_stats.last_rate; - u32 airtime; + struct rate_info *ri = &sta->tx_stats.last_rate_info; + u32 duration, overhead; + u8 agg_shift; - if (!(rate->flags & (IEEE80211_TX_RC_VHT_MCS | - IEEE80211_TX_RC_MCS))) - ampdu = false; + if (ieee80211_fill_rx_status(&stat, hw, rate, ri, band, len)) + return 0; + if (stat.encoding == RX_ENC_LEGACY || !ampdu) + return ieee80211_calc_rx_airtime(hw, &stat, len); + + duration = ieee80211_get_rate_duration(hw, &stat, &overhead); /* * Assume that HT/VHT transmission on any AC except VO will * use aggregation. Since we don't have reliable reporting - * of aggregation length, assume an average of 16. + * of aggregation length, assume an average size based on the + * tx rate. * This will not be very accurate, but much better than simply - * assuming un-aggregated tx. + * assuming un-aggregated tx in all cases. */ - airtime = ieee80211_calc_tx_airtime_rate(hw, rate, band, - ampdu ? len * 16 : len); - if (ampdu) - airtime /= 16; - - return airtime; + if (duration > 400) /* <= VHT20 MCS2 1S */ + agg_shift = 1; + else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + agg_shift = 2; + else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + agg_shift = 3; + else + agg_shift = 4; + + duration *= len; + duration /= AVG_PKT_SIZE; + duration /= 1024; + + return duration + (overhead >> agg_shift); } if (!conf) diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 9d398c9daa4c..d5010116cf4d 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -524,7 +524,7 @@ struct ieee80211_sta_rx_stats { * @status_stats.retry_failed: # of frames that failed after retry * @status_stats.retry_count: # of retries attempted * @status_stats.lost_packets: # of lost packets - * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.last_pkt_time: timestamp of last ACKed packet * @status_stats.msdu_retries: # of MSDU retries * @status_stats.msdu_failed: # of failed MSDUs * @status_stats.last_ack: last ack timestamp (jiffies) @@ -597,7 +597,7 @@ struct sta_info { unsigned long filtered; unsigned long retry_failed, retry_count; unsigned int lost_packets; - unsigned long last_tdls_pkt_time; + unsigned long last_pkt_time; u64 msdu_retries[IEEE80211_NUM_TIDS + 1]; u64 msdu_failed[IEEE80211_NUM_TIDS + 1]; unsigned long last_ack; @@ -611,6 +611,7 @@ struct sta_info { u64 packets[IEEE80211_NUM_ACS]; u64 bytes[IEEE80211_NUM_ACS]; struct ieee80211_tx_rate last_rate; + struct rate_info last_rate_info; u64 msdu[IEEE80211_NUM_TIDS + 1]; } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; diff --git a/net/mac80211/status.c b/net/mac80211/status.c index adb1d30ce06e..0794396a7988 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -755,12 +755,16 @@ static void ieee80211_report_used_skb(struct ieee80211_local *local, * - current throughput (higher value for higher tpt)? */ #define STA_LOST_PKT_THRESHOLD 50 +#define STA_LOST_PKT_TIME HZ /* 1 sec since last ACK */ #define STA_LOST_TDLS_PKT_THRESHOLD 10 #define STA_LOST_TDLS_PKT_TIME (10*HZ) /* 10secs since last ACK */ static void ieee80211_lost_packet(struct sta_info *sta, struct ieee80211_tx_info *info) { + unsigned long pkt_time = STA_LOST_PKT_TIME; + unsigned int pkt_thr = STA_LOST_PKT_THRESHOLD; + /* If driver relies on its own algorithm for station kickout, skip * mac80211 packet loss mechanism. */ @@ -773,21 +777,20 @@ static void ieee80211_lost_packet(struct sta_info *sta, return; sta->status_stats.lost_packets++; - if (!sta->sta.tdls && - sta->status_stats.lost_packets < STA_LOST_PKT_THRESHOLD) - return; + if (sta->sta.tdls) { + pkt_time = STA_LOST_TDLS_PKT_TIME; + pkt_thr = STA_LOST_PKT_THRESHOLD; + } /* * If we're in TDLS mode, make sure that all STA_LOST_TDLS_PKT_THRESHOLD * of the last packets were lost, and that no ACK was received in the * last STA_LOST_TDLS_PKT_TIME ms, before triggering the CQM packet-loss * mechanism. + * For non-TDLS, use STA_LOST_PKT_THRESHOLD and STA_LOST_PKT_TIME */ - if (sta->sta.tdls && - (sta->status_stats.lost_packets < STA_LOST_TDLS_PKT_THRESHOLD || - time_before(jiffies, - sta->status_stats.last_tdls_pkt_time + - STA_LOST_TDLS_PKT_TIME))) + if (sta->status_stats.lost_packets < pkt_thr || + !time_after(jiffies, sta->status_stats.last_pkt_time + pkt_time)) return; cfg80211_cqm_pktloss_notify(sta->sdata->dev, sta->sta.addr, @@ -1033,9 +1036,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, sta->status_stats.lost_packets = 0; /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = - jiffies; + sta->status_stats.last_pkt_time = jiffies; } else if (noack_success) { /* nothing to do here, do not account as lost */ } else { @@ -1137,9 +1138,17 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, struct ieee80211_tx_info *info = status->info; struct ieee80211_sta *pubsta = status->sta; struct ieee80211_supported_band *sband; + struct sta_info *sta; int retry_count; bool acked, noack_success; + if (pubsta) { + sta = container_of(pubsta, struct sta_info, sta); + + if (status->rate) + sta->tx_stats.last_rate_info = *status->rate; + } + if (status->skb) return __ieee80211_tx_status(hw, status); @@ -1154,10 +1163,6 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED); if (pubsta) { - struct sta_info *sta; - - sta = container_of(pubsta, struct sta_info, sta); - if (!acked && !noack_success) sta->status_stats.retry_failed++; sta->status_stats.retry_count += retry_count; @@ -1168,9 +1173,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - /* Track when last TDLS packet was ACKed */ - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + /* Track when last packet was ACKed */ + sta->status_stats.last_pkt_time = jiffies; } else if (test_sta_flag(sta, WLAN_STA_PS_STA)) { return; } else if (noack_success) { @@ -1259,8 +1263,7 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw, if (sta->status_stats.lost_packets) sta->status_stats.lost_packets = 0; - if (test_sta_flag(sta, WLAN_STA_TDLS_PEER_AUTH)) - sta->status_stats.last_tdls_pkt_time = jiffies; + sta->status_stats.last_pkt_time = jiffies; } else { ieee80211_lost_packet(sta, info); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1aad411a0e46..8ccd4a151dcb 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -892,7 +892,6 @@ restart: goto out; } -wait_for_sndbuf: __mptcp_flush_join_list(msk); ssk = mptcp_subflow_get_send(msk); while (!sk_stream_memory_free(sk) || @@ -982,7 +981,7 @@ wait_for_sndbuf: */ mptcp_set_timeout(sk, ssk); release_sock(ssk); - goto wait_for_sndbuf; + goto restart; } } } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b5f30d7d30d0..d2d1448274f5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -353,7 +353,7 @@ static void netlink_rcv_wake(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) clear_bit(NETLINK_S_CONGESTED, &nlk->state); if (!test_bit(NETLINK_S_CONGESTED, &nlk->state)) wake_up_interruptible(&nlk->wait); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6d29a3603a3e..884cff7bb169 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -488,7 +488,6 @@ enum rxrpc_call_flag { RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ - RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ @@ -673,9 +672,13 @@ struct rxrpc_call { rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - /* ping management */ - rxrpc_serial_t ping_serial; /* Last ping sent */ - ktime_t ping_time; /* Time last ping sent */ + /* RTT management */ + rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ + ktime_t rtt_sent_at[4]; /* Time packet sent */ + unsigned long rtt_avail; /* Mask of available slots in bits 0-3, + * Mask of pending samples in 8-11 */ +#define RXRPC_CALL_RTT_AVAIL_MASK 0xf +#define RXRPC_CALL_RTT_PEND_SHIFT 8 /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -1037,7 +1040,7 @@ static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, /* * rtt.c */ -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); void rxrpc_peer_init_rtt(struct rxrpc_peer *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 38a46167523f..a40fae013942 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -153,6 +153,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; call->rxnet = rxnet; + call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; atomic_inc(&rxnet->nr_calls); return call; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 767579328a06..19ddfc9807e8 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -608,36 +608,57 @@ unlock: } /* - * Process a requested ACK. + * See if there's a cached RTT probe to complete. */ -static void rxrpc_input_requested_ack(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t orig_serial, - rxrpc_serial_t ack_serial) +static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, + ktime_t resp_time, + rxrpc_serial_t acked_serial, + rxrpc_serial_t ack_serial, + enum rxrpc_rtt_rx_trace type) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + rxrpc_serial_t orig_serial; + unsigned long avail; ktime_t sent_at; - int ix; + bool matched = false; + int i; - for (ix = 0; ix < RXRPC_RXTX_BUFF_SIZE; ix++) { - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; + avail = READ_ONCE(call->rtt_avail); + smp_rmb(); /* Read avail bits before accessing data. */ - sent_at = skb->tstamp; - smp_rmb(); /* Read timestamp before serial. */ - sp = rxrpc_skb(skb); - if (sp->hdr.serial != orig_serial) + for (i = 0; i < ARRAY_SIZE(call->rtt_serial); i++) { + if (!test_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &avail)) continue; - goto found; - } - return; + sent_at = call->rtt_sent_at[i]; + orig_serial = call->rtt_serial[i]; + + if (orig_serial == acked_serial) { + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_mb(); /* Read data before setting avail bit */ + set_bit(i, &call->rtt_avail); + if (type != rxrpc_rtt_rx_cancel) + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); + else + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, + orig_serial, acked_serial, 0, 0); + matched = true; + } + + /* If a later serial is being acked, then mark this slot as + * being available. + */ + if (after(acked_serial, orig_serial)) { + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_obsolete, i, + orig_serial, acked_serial, 0, 0); + clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); + set_bit(i, &call->rtt_avail); + } + } -found: - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_requested_ack, - orig_serial, ack_serial, sent_at, resp_time); + if (!matched) + trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } /* @@ -682,27 +703,11 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) */ static void rxrpc_input_ping_response(struct rxrpc_call *call, ktime_t resp_time, - rxrpc_serial_t orig_serial, + rxrpc_serial_t acked_serial, rxrpc_serial_t ack_serial) { - rxrpc_serial_t ping_serial; - ktime_t ping_time; - - ping_time = call->ping_time; - smp_rmb(); - ping_serial = READ_ONCE(call->ping_serial); - - if (orig_serial == call->acks_lost_ping) + if (acked_serial == call->acks_lost_ping) rxrpc_input_check_for_lost_ack(call); - - if (before(orig_serial, ping_serial) || - !test_and_clear_bit(RXRPC_CALL_PINGING, &call->flags)) - return; - if (after(orig_serial, ping_serial)) - return; - - rxrpc_peer_add_rtt(call, rxrpc_rtt_rx_ping_response, - orig_serial, ack_serial, ping_time, resp_time); } /* @@ -843,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackinfo info; u8 acks[RXRPC_MAXACKS]; } buf; - rxrpc_serial_t acked_serial; + rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -856,6 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } offset += sizeof(buf.ack); + ack_serial = sp->hdr.serial; acked_serial = ntohl(buf.ack.serial); first_soft_ack = ntohl(buf.ack.firstPacket); prev_pkt = ntohl(buf.ack.previousPacket); @@ -864,31 +870,42 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? buf.ack.reason : RXRPC_ACK__INVALID); - trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial, + trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE) + switch (buf.ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - sp->hdr.serial); - if (buf.ack.reason == RXRPC_ACK_REQUESTED) - rxrpc_input_requested_ack(call, skb->tstamp, acked_serial, - sp->hdr.serial); + ack_serial); + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + if (acked_serial != 0) + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_cancel); + break; + } if (buf.ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", sp->hdr.serial); + _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - sp->hdr.serial, true, true, + ack_serial, true, true, rxrpc_propose_ack_respond_to_ack); } /* Discard any out-of-order or duplicate ACKs (outside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); return; @@ -904,7 +921,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) /* Discard any out-of-order or duplicate ACKs (inside lock). */ if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->ackr_first_seq, prev_pkt, call->ackr_prev_seq); goto out; @@ -964,7 +981,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 1ba43c3df4ad..3cfff7922ba8 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -124,6 +124,49 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, } /* + * Record the beginning of an RTT probe. + */ +static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_rtt_tx_trace why) +{ + unsigned long avail = call->rtt_avail; + int rtt_slot = 9; + + if (!(avail & RXRPC_CALL_RTT_AVAIL_MASK)) + goto no_slot; + + rtt_slot = __ffs(avail & RXRPC_CALL_RTT_AVAIL_MASK); + if (!test_and_clear_bit(rtt_slot, &call->rtt_avail)) + goto no_slot; + + call->rtt_serial[rtt_slot] = serial; + call->rtt_sent_at[rtt_slot] = ktime_get_real(); + smp_wmb(); /* Write data before avail bit */ + set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + + trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); + return rtt_slot; + +no_slot: + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); + return -1; +} + +/* + * Cancel an RTT probe. + */ +static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, + rxrpc_serial_t serial, int rtt_slot) +{ + if (rtt_slot != -1) { + clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); + smp_wmb(); /* Clear pending bit before setting slot */ + set_bit(rtt_slot, &call->rtt_avail); + trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); + } +} + +/* * Send an ACK call packet. */ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, @@ -136,7 +179,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - int ret; + int ret, rtt_slot = -1; u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -196,18 +239,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (_serial) *_serial = serial; - if (ping) { - call->ping_serial = serial; - smp_wmb(); - /* We need to stick a time in before we send the packet in case - * the reply gets back before kernel_sendmsg() completes - but - * asking UDP to send the packet can take a relatively long - * time. - */ - call->ping_time = ktime_get_real(); - set_bit(RXRPC_CALL_PINGING, &call->flags); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); - } + if (ping) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); conn->params.peer->last_tx_at = ktime_get_seconds(); @@ -221,8 +254,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - if (ping) - clear_bit(RXRPC_CALL_PINGING, &call->flags); + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_propose_ACK(call, pkt->ack.reason, ntohl(pkt->ack.serial), false, true, @@ -321,7 +353,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, struct kvec iov[2]; rxrpc_serial_t serial; size_t len; - int ret; + int ret, rtt_slot = -1; _enter(",{%d}", skb->len); @@ -397,6 +429,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet @@ -408,12 +442,15 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_seconds(); up_read(&conn->params.local->defrag_sem); - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + } + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -422,7 +459,6 @@ done: if (ret >= 0) { if (whdr.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = skb->tstamp; - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -469,6 +505,8 @@ send_fragmentable: sp->hdr.serial = serial; smp_wmb(); /* Set serial before timestamp */ skb->tstamp = ktime_get_real(); + if (whdr.flags & RXRPC_REQUEST_ACK) + rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: @@ -487,12 +525,14 @@ send_fragmentable: BUG(); } - if (ret < 0) + if (ret < 0) { + rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); - else + } else { trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + } rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index ca29976bb193..68396d052052 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -502,11 +502,21 @@ EXPORT_SYMBOL(rxrpc_kernel_get_peer); * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer smoothed RTT. + * Get the call's peer smoothed RTT in uS. */ -u32 rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->srtt_us >> 3; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index 928d8b34a3ee..1221b0637a7e 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -146,6 +146,7 @@ static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) * exclusive access to the peer RTT data. */ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + int rtt_slot, rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, ktime_t send_time, ktime_t resp_time) { @@ -162,7 +163,7 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, peer->rtt_count++; spin_unlock(&peer->rtt_input_lock); - trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, + trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, peer->srtt_us >> 3, peer->rto_j); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 52a24d4ef5d8..e08130e5746b 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1137,7 +1137,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = -ENOMEM; ticket = kmalloc(ticket_len, GFP_NOFS); if (!ticket) - goto temporary_error; + goto temporary_error_free_resp; eproto = tracepoint_string("rxkad_tkt_short"); abort_code = RXKADPACKETSHORT; @@ -1230,6 +1230,7 @@ protocol_error: temporary_error_free_ticket: kfree(ticket); +temporary_error_free_resp: kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index deac82f3ad7b..e89fab6ccb34 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -353,23 +353,11 @@ static int red_init(struct Qdisc *sch, struct nlattr *opt, FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP, tb[TCA_RED_EARLY_DROP_BLOCK], extack); if (err) - goto err_early_drop_init; - - err = tcf_qevent_init(&q->qe_mark, sch, - FLOW_BLOCK_BINDER_TYPE_RED_MARK, - tb[TCA_RED_MARK_BLOCK], extack); - if (err) - goto err_mark_init; - - return 0; + return err; -err_mark_init: - tcf_qevent_destroy(&q->qe_early_drop, sch); -err_early_drop_init: - del_timer_sync(&q->adapt_timer); - red_offload(sch, false); - qdisc_put(q->qdisc); - return err; + return tcf_qevent_init(&q->qe_mark, sch, + FLOW_BLOCK_BINDER_TYPE_RED_MARK, + tb[TCA_RED_MARK_BLOCK], extack); } static int red_change(struct Qdisc *sch, struct nlattr *opt, diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index e981992634dd..fe53c1e38c7d 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1176,9 +1176,27 @@ static void taprio_offload_config_changed(struct taprio_sched *q) spin_unlock(&q->current_entry_lock); } -static void taprio_sched_to_offload(struct taprio_sched *q, +static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) +{ + u32 i, queue_mask = 0; + + for (i = 0; i < dev->num_tc; i++) { + u32 offset, count; + + if (!(tc_mask & BIT(i))) + continue; + + offset = dev->tc_to_txq[i].offset; + count = dev->tc_to_txq[i].count; + + queue_mask |= GENMASK(offset + count - 1, offset); + } + + return queue_mask; +} + +static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - const struct tc_mqprio_qopt *mqprio, struct tc_taprio_qopt_offload *offload) { struct sched_entry *entry; @@ -1193,7 +1211,8 @@ static void taprio_sched_to_offload(struct taprio_sched *q, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = entry->gate_mask; + e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + i++; } @@ -1201,7 +1220,6 @@ static void taprio_sched_to_offload(struct taprio_sched *q, } static int taprio_enable_offload(struct net_device *dev, - struct tc_mqprio_qopt *mqprio, struct taprio_sched *q, struct sched_gate_list *sched, struct netlink_ext_ack *extack) @@ -1223,7 +1241,7 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(q, sched, mqprio, offload); + taprio_sched_to_offload(dev, sched, offload); err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload); if (err < 0) { @@ -1485,7 +1503,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } if (FULL_OFFLOAD_IS_ENABLED(q->flags)) - err = taprio_enable_offload(dev, mqprio, q, new_admin, extack); + err = taprio_enable_offload(dev, q, new_admin, extack); else err = taprio_disable_offload(dev, q, extack); if (err) diff --git a/net/socket.c b/net/socket.c index dbbe8ea7d395..0c0144604f81 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3610,7 +3610,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) EXPORT_SYMBOL(kernel_getsockname); /** - * kernel_peername - get the address which the socket is connected (kernel space) + * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * @@ -3671,7 +3671,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, EXPORT_SYMBOL(kernel_sendpage_locked); /** - * kernel_shutdown - shut down part of a full-duplex connection (kernel space) + * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * diff --git a/net/wireless/chan.c b/net/wireless/chan.c index 90f0f82cd9ca..edee3a645c06 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -10,6 +10,7 @@ */ #include <linux/export.h> +#include <linux/bitfield.h> #include <net/cfg80211.h> #include "core.h" #include "rdev-ops.h" @@ -912,6 +913,7 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, struct ieee80211_sta_vht_cap *vht_cap; struct ieee80211_edmg *edmg_cap; u32 width, control_freq, cap; + bool support_80_80 = false; if (WARN_ON(!cfg80211_chandef_valid(chandef))) return false; @@ -979,9 +981,13 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; break; case NL80211_CHAN_WIDTH_80P80: - cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; - if (chandef->chan->band != NL80211_BAND_6GHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap = vht_cap->cap; + support_80_80 = + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + u32_get_bits(cap, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) > 1; + if (chandef->chan->band != NL80211_BAND_6GHZ && !support_80_80) return false; /* fall through */ case NL80211_CHAN_WIDTH_80: @@ -1001,7 +1007,8 @@ bool cfg80211_chandef_usable(struct wiphy *wiphy, return false; cap = vht_cap->cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK; if (cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && - cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) + cap != IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ && + !(vht_cap->cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)) return false; break; default: diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c04fc6cf6583..19dc0ee807f6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6011,7 +6011,7 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]) params.he_6ghz_capa = - nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]); + nla_data(info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY]); if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) params.airtime_weight = diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 35b8847a2f6d..d8a90d397423 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2946,6 +2946,9 @@ int regulatory_hint_user(const char *alpha2, if (WARN_ON(!alpha2)) return -EINVAL; + if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) + return -EINVAL; + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; diff --git a/net/wireless/util.c b/net/wireless/util.c index dfad1c0f57ad..c62eb3d9ab3d 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -123,11 +123,13 @@ int ieee80211_freq_khz_to_channel(u32 freq) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; - else if (freq < 5945) + else if (freq < 5925) return (freq - 5000) / 5; + else if (freq == 5935) + return 2; else if (freq <= 45000) /* DMG band lower limit */ - /* see 802.11ax D4.1 27.3.22.2 */ - return (freq - 5940) / 5; + /* see 802.11ax D6.1 27.3.22.2 */ + return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else |