diff options
92 files changed, 1431 insertions, 692 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 0f966f05fb0d..abfc724a2367 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2339,7 +2339,7 @@ F: drivers/phy/mediatek/ ARM/MICROCHIP (ARM64) SoC support M: Conor Dooley <conor@kernel.org> M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported T: git https://git.kernel.org/pub/scm/linux/kernel/git/at91/linux.git @@ -2348,7 +2348,7 @@ F: arch/arm64/boot/dts/microchip/ ARM/Microchip (AT91) SoC support M: Nicolas Ferre <nicolas.ferre@microchip.com> M: Alexandre Belloni <alexandre.belloni@bootlin.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported W: http://www.linux4sam.org @@ -3250,7 +3250,7 @@ F: include/uapi/linux/atm* ATMEL MACB ETHERNET DRIVER M: Nicolas Ferre <nicolas.ferre@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> S: Supported F: drivers/net/ethernet/cadence/ @@ -13786,7 +13786,7 @@ F: Documentation/devicetree/bindings/serial/atmel,at91-usart.yaml F: drivers/spi/spi-at91-usart.c MICROCHIP AUDIO ASOC DRIVERS -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/sound/atmel* @@ -13809,7 +13809,7 @@ S: Maintained F: drivers/crypto/atmel-ecc.* MICROCHIP EIC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/interrupt-controller/microchip,sama7g5-eic.yaml @@ -13882,7 +13882,7 @@ F: drivers/video/fbdev/atmel_lcdfb.c F: include/video/atmel_lcdc.h MICROCHIP MCP16502 PMIC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/regulator/mcp16502-regulator.txt @@ -13909,7 +13909,7 @@ F: Documentation/devicetree/bindings/mtd/atmel-nand.txt F: drivers/mtd/nand/raw/atmel/* MICROCHIP OTPC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/nvmem/microchip,sama7g5-otpc.yaml @@ -13948,7 +13948,7 @@ F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml F: drivers/fpga/microchip-spi.c MICROCHIP PWM DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-pwm@vger.kernel.org S: Supported @@ -13964,7 +13964,7 @@ F: drivers/iio/adc/at91-sama5d2_adc.c F: include/dt-bindings/iio/adc/at91-sama5d2_adc.h MICROCHIP SAMA5D2-COMPATIBLE SHUTDOWN CONTROLLER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> S: Supported F: Documentation/devicetree/bindings/power/reset/atmel,sama5d2-shdwc.yaml F: drivers/power/reset/at91-sama5d2_shdwc.c @@ -13981,7 +13981,7 @@ S: Supported F: drivers/spi/spi-atmel.* MICROCHIP SSC DRIVER -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported F: Documentation/devicetree/bindings/misc/atmel-ssc.txt @@ -14010,7 +14010,7 @@ F: drivers/usb/gadget/udc/atmel_usba_udc.* MICROCHIP WILC1000 WIFI DRIVER M: Ajay Singh <ajay.kathat@microchip.com> -M: Claudiu Beznea <claudiu.beznea@microchip.com> +M: Claudiu Beznea <claudiu.beznea@tuxon.dev> L: linux-wireless@vger.kernel.org S: Supported F: drivers/net/wireless/microchip/wilc1000/ @@ -18508,17 +18508,14 @@ RTL8180 WIRELESS DRIVER L: linux-wireless@vger.kernel.org S: Orphan W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8180/ RTL8187 WIRELESS DRIVER -M: Herton Ronaldo Krzesinski <herton@canonical.com> -M: Hin-Tak Leung <htl10@users.sourceforge.net> +M: Hin-Tak Leung <hintak.leung@gmail.com> M: Larry Finger <Larry.Finger@lwfinger.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git F: drivers/net/wireless/realtek/rtl818x/rtl8187/ RTL8XXXU WIRELESS DRIVER (rtl8xxxu) diff --git a/drivers/isdn/mISDN/dsp.h b/drivers/isdn/mISDN/dsp.h index fa09d511a8ed..baf31258f5c9 100644 --- a/drivers/isdn/mISDN/dsp.h +++ b/drivers/isdn/mISDN/dsp.h @@ -247,7 +247,7 @@ extern void dsp_cmx_hardware(struct dsp_conf *conf, struct dsp *dsp); extern int dsp_cmx_conf(struct dsp *dsp, u32 conf_id); extern void dsp_cmx_receive(struct dsp *dsp, struct sk_buff *skb); extern void dsp_cmx_hdlc(struct dsp *dsp, struct sk_buff *skb); -extern void dsp_cmx_send(void *arg); +extern void dsp_cmx_send(struct timer_list *arg); extern void dsp_cmx_transmit(struct dsp *dsp, struct sk_buff *skb); extern int dsp_cmx_del_conf_member(struct dsp *dsp); extern int dsp_cmx_del_conf(struct dsp_conf *conf); diff --git a/drivers/isdn/mISDN/dsp_cmx.c b/drivers/isdn/mISDN/dsp_cmx.c index 357b87592eb4..61cb45c5d0d8 100644 --- a/drivers/isdn/mISDN/dsp_cmx.c +++ b/drivers/isdn/mISDN/dsp_cmx.c @@ -1614,7 +1614,7 @@ static u16 dsp_count; /* last sample count */ static int dsp_count_valid; /* if we have last sample count */ void -dsp_cmx_send(void *arg) +dsp_cmx_send(struct timer_list *arg) { struct dsp_conf *conf; struct dsp_conf_member *member; diff --git a/drivers/isdn/mISDN/dsp_core.c b/drivers/isdn/mISDN/dsp_core.c index 386084530c2f..fae95f166688 100644 --- a/drivers/isdn/mISDN/dsp_core.c +++ b/drivers/isdn/mISDN/dsp_core.c @@ -1195,7 +1195,7 @@ static int __init dsp_init(void) } /* set sample timer */ - timer_setup(&dsp_spl_tl, (void *)dsp_cmx_send, 0); + timer_setup(&dsp_spl_tl, dsp_cmx_send, 0); dsp_spl_tl.expires = jiffies + dsp_tics; dsp_spl_jiffies = dsp_spl_tl.expires; add_timer(&dsp_spl_tl); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 484c9e3e5e82..447b06ea4fc9 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -5901,7 +5901,9 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features = BOND_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER; + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 8da46d284e35..bef879c6d500 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1625,8 +1625,10 @@ static void felix_teardown(struct dsa_switch *ds) struct felix *felix = ocelot_to_felix(ocelot); struct dsa_port *dp; + rtnl_lock(); if (felix->tag_proto_ops) felix->tag_proto_ops->teardown(ds); + rtnl_unlock(); dsa_switch_for_each_available_port(dp, ds) ocelot_deinit_port(ocelot, dp->index); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 1416262d4296..e0a4cb7e3f50 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1186,14 +1186,9 @@ static int enetc_init_port_rss_memory(struct enetc_si *si) static int enetc_pf_register_with_ierb(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; struct platform_device *ierb_pdev; struct device_node *ierb_node; - /* Don't register with the IERB if the PF itself is disabled */ - if (!node || !of_device_is_available(node)) - return 0; - ierb_node = of_find_compatible_node(NULL, NULL, "fsl,ls1028a-enetc-ierb"); if (!ierb_node || !of_device_is_available(ierb_node)) @@ -1208,56 +1203,81 @@ static int enetc_pf_register_with_ierb(struct pci_dev *pdev) return enetc_ierb_register_pf(ierb_pdev, pdev); } -static int enetc_pf_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static struct enetc_si *enetc_psi_create(struct pci_dev *pdev) { - struct device_node *node = pdev->dev.of_node; - struct enetc_ndev_priv *priv; - struct net_device *ndev; struct enetc_si *si; - struct enetc_pf *pf; int err; - err = enetc_pf_register_with_ierb(pdev); - if (err == -EPROBE_DEFER) - return err; - if (err) - dev_warn(&pdev->dev, - "Could not register with IERB driver: %pe, please update the device tree\n", - ERR_PTR(err)); - - err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); - if (err) - return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(struct enetc_pf)); + if (err) { + dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); + goto out; + } si = pci_get_drvdata(pdev); if (!si->hw.port || !si->hw.global) { err = -ENODEV; dev_err(&pdev->dev, "could not map PF space, probing a VF?\n"); - goto err_map_pf_space; + goto out_pci_remove; } err = enetc_setup_cbdr(&pdev->dev, &si->hw, ENETC_CBDR_DEFAULT_SIZE, &si->cbd_ring); if (err) - goto err_setup_cbdr; + goto out_pci_remove; err = enetc_init_port_rfs_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RFS memory\n"); - goto err_init_port_rfs; + goto out_teardown_cbdr; } err = enetc_init_port_rss_memory(si); if (err) { dev_err(&pdev->dev, "Failed to initialize RSS memory\n"); - goto err_init_port_rss; + goto out_teardown_cbdr; } - if (node && !of_device_is_available(node)) { - dev_info(&pdev->dev, "device is disabled, skipping\n"); - err = -ENODEV; - goto err_device_disabled; + return si; + +out_teardown_cbdr: + enetc_teardown_cbdr(&si->cbd_ring); +out_pci_remove: + enetc_pci_remove(pdev); +out: + return ERR_PTR(err); +} + +static void enetc_psi_destroy(struct pci_dev *pdev) +{ + struct enetc_si *si = pci_get_drvdata(pdev); + + enetc_teardown_cbdr(&si->cbd_ring); + enetc_pci_remove(pdev); +} + +static int enetc_pf_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_ndev_priv *priv; + struct net_device *ndev; + struct enetc_si *si; + struct enetc_pf *pf; + int err; + + err = enetc_pf_register_with_ierb(pdev); + if (err == -EPROBE_DEFER) + return err; + if (err) + dev_warn(&pdev->dev, + "Could not register with IERB driver: %pe, please update the device tree\n", + ERR_PTR(err)); + + si = enetc_psi_create(pdev); + if (IS_ERR(si)) { + err = PTR_ERR(si); + goto err_psi_create; } pf = enetc_si_priv(si); @@ -1339,15 +1359,9 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: -err_init_port_rss: -err_init_port_rfs: -err_device_disabled: err_setup_mac_addresses: - enetc_teardown_cbdr(&si->cbd_ring); -err_setup_cbdr: -err_map_pf_space: - enetc_pci_remove(pdev); - + enetc_psi_destroy(pdev); +err_psi_create: return err; } @@ -1370,12 +1384,29 @@ static void enetc_pf_remove(struct pci_dev *pdev) enetc_free_msix(priv); enetc_free_si_resources(priv); - enetc_teardown_cbdr(&si->cbd_ring); free_netdev(si->ndev); - enetc_pci_remove(pdev); + enetc_psi_destroy(pdev); +} + +static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct enetc_si *si; + + /* Only apply quirk for disabled functions. For the ones + * that are enabled, enetc_pf_probe() will apply it. + */ + if (node && of_device_is_available(node)) + return; + + si = enetc_psi_create(pdev); + if (si) + enetc_psi_destroy(pdev); } +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF, + enetc_fixup_clear_rss_rfs); static const struct pci_device_id enetc_pf_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 52546f625c8b..f276b5ecb431 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -464,9 +464,9 @@ static void hns3_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9f6890059666..b7b51e56b030 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -5854,6 +5854,9 @@ void hns3_external_lb_prepare(struct net_device *ndev, bool if_running) if (!if_running) return; + if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + netif_carrier_off(ndev); netif_tx_disable(ndev); @@ -5882,7 +5885,16 @@ void hns3_external_lb_restore(struct net_device *ndev, bool if_running) if (!if_running) return; - hns3_nic_reset_all_ring(priv->ae_handle); + if (hns3_nic_resetting(ndev)) + return; + + if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state)) + return; + + if (hns3_nic_reset_all_ring(priv->ae_handle)) + return; + + clear_bit(HNS3_NIC_STATE_DOWN, &priv->state); for (i = 0; i < priv->vector_num; i++) hns3_vector_enable(&priv->tqp_vector[i]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 409db2e70965..0fb2eaee3e8a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -111,9 +111,9 @@ static void hclge_dbg_fill_content(char *content, u16 len, if (result) { if (item_len < strlen(result[i])) break; - strscpy(pos, result[i], strlen(result[i])); + memcpy(pos, result[i], strlen(result[i])); } else { - strscpy(pos, items[i].name, strlen(items[i].name)); + memcpy(pos, items[i].name, strlen(items[i].name)); } pos += item_len; len -= item_len; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bf675c15fbb9..a940e35aef29 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -72,6 +72,8 @@ static void hclge_restore_hw_table(struct hclge_dev *hdev); static void hclge_sync_promisc_mode(struct hclge_dev *hdev); static void hclge_sync_fd_table(struct hclge_dev *hdev); static void hclge_update_fec_stats(struct hclge_dev *hdev); +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt); static struct hnae3_ae_algo ae_algo; @@ -7558,6 +7560,8 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) { +#define HCLGE_LINK_STATUS_WAIT_CNT 3 + struct hclge_desc desc; struct hclge_config_mac_mode_cmd *req = (struct hclge_config_mac_mode_cmd *)desc.data; @@ -7582,9 +7586,15 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "mac enable fail, ret =%d.\n", ret); + return; + } + + if (!enable) + hclge_mac_link_status_wait(hdev, HCLGE_LINK_STATUS_DOWN, + HCLGE_LINK_STATUS_WAIT_CNT); } static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, @@ -7647,10 +7657,9 @@ static void hclge_phy_link_status_wait(struct hclge_dev *hdev, } while (++i < HCLGE_PHY_LINK_STATUS_NUM); } -static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret, + int wait_cnt) { -#define HCLGE_MAC_LINK_STATUS_NUM 100 - int link_status; int i = 0; int ret; @@ -7663,13 +7672,15 @@ static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) return 0; msleep(HCLGE_LINK_STATUS_MS); - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + } while (++i < wait_cnt); return -EBUSY; } static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, bool is_phy) { +#define HCLGE_MAC_LINK_STATUS_NUM 100 + int link_ret; link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; @@ -7677,7 +7688,8 @@ static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, if (is_phy) hclge_phy_link_status_wait(hdev, link_ret); - return hclge_mac_link_status_wait(hdev, link_ret); + return hclge_mac_link_status_wait(hdev, link_ret, + HCLGE_MAC_LINK_STATUS_NUM); } static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) @@ -10915,9 +10927,12 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev) u32 rx_pause, tx_pause; u8 flowctl; - if (!phydev->link || !phydev->autoneg) + if (!phydev->link) return 0; + if (!phydev->autoneg) + return hclge_mac_pause_setup_hw(hdev); + local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising); if (phydev->pause) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index de509e5751a7..c58c31221762 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1553,7 +1553,7 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) return 0; } -static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev) { bool tx_en, rx_en; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h index 45dcfef3f90c..53eec6df5194 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h @@ -245,6 +245,7 @@ int hclge_pfc_pause_en_cfg(struct hclge_dev *hdev, u8 tx_rx_bitmap, u8 pfc_bitmap); int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx); int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr); +int hclge_mac_pause_setup_hw(struct hclge_dev *hdev); void hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats); void hclge_pfc_tx_stats_get(struct hclge_dev *hdev, u64 *stats); int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 763d613adbcc..df76cdaddcfb 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -97,6 +97,8 @@ static int pending_scrq(struct ibmvnic_adapter *, static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *, struct ibmvnic_sub_crq_queue *); static int ibmvnic_poll(struct napi_struct *napi, int data); +static int reset_sub_crq_queues(struct ibmvnic_adapter *adapter); +static inline void reinit_init_done(struct ibmvnic_adapter *adapter); static void send_query_map(struct ibmvnic_adapter *adapter); static int send_request_map(struct ibmvnic_adapter *, dma_addr_t, u32, u8); static int send_request_unmap(struct ibmvnic_adapter *, u8); @@ -114,6 +116,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); +static void flush_reset_queue(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1505,8 +1508,8 @@ static const char *adapter_state_to_string(enum vnic_state state) static int ibmvnic_login(struct net_device *netdev) { + unsigned long flags, timeout = msecs_to_jiffies(20000); struct ibmvnic_adapter *adapter = netdev_priv(netdev); - unsigned long timeout = msecs_to_jiffies(20000); int retry_count = 0; int retries = 10; bool retry; @@ -1527,11 +1530,9 @@ static int ibmvnic_login(struct net_device *netdev) if (!wait_for_completion_timeout(&adapter->init_done, timeout)) { - netdev_warn(netdev, "Login timed out, retrying...\n"); - retry = true; - adapter->init_done_rc = 0; - retry_count++; - continue; + netdev_warn(netdev, "Login timed out\n"); + adapter->login_pending = false; + goto partial_reset; } if (adapter->init_done_rc == ABORTED) { @@ -1573,10 +1574,69 @@ static int ibmvnic_login(struct net_device *netdev) "SCRQ irq initialization failed\n"); return rc; } + /* Default/timeout error handling, reset and start fresh */ } else if (adapter->init_done_rc) { netdev_warn(netdev, "Adapter login failed, init_done_rc = %d\n", adapter->init_done_rc); - return -EIO; + +partial_reset: + /* adapter login failed, so free any CRQs or sub-CRQs + * and register again before attempting to login again. + * If we don't do this then the VIOS may think that + * we are already logged in and reject any subsequent + * attempts + */ + netdev_warn(netdev, + "Freeing and re-registering CRQs before attempting to login again\n"); + retry = true; + adapter->init_done_rc = 0; + release_sub_crqs(adapter, true); + /* Much of this is similar logic as ibmvnic_probe(), + * we are essentially re-initializing communication + * with the server. We really should not run any + * resets/failovers here because this is already a form + * of reset and we do not want parallel resets occurring + */ + do { + reinit_init_done(adapter); + /* Clear any failovers we got in the previous + * pass since we are re-initializing the CRQ + */ + adapter->failover_pending = false; + release_crq_queue(adapter); + /* If we don't sleep here then we risk an + * unnecessary failover event from the VIOS. + * This is a known VIOS issue caused by a vnic + * device freeing and registering a CRQ too + * quickly. + */ + msleep(1500); + /* Avoid any resets, since we are currently + * resetting. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, + flags); + + rc = init_crq_queue(adapter); + if (rc) { + netdev_err(netdev, "login recovery: init CRQ failed %d\n", + rc); + return -EIO; + } + + rc = ibmvnic_reset_init(adapter, false); + if (rc) + netdev_err(netdev, "login recovery: Reset init failed %d\n", + rc); + /* IBMVNIC_CRQ_INIT will return EAGAIN if it + * fails, since ibmvnic_reset_init will free + * irq's in failure, we won't be able to receive + * new CRQs so we need to keep trying. probe() + * handles this similarly. + */ + } while (rc == -EAGAIN && retry_count++ < retries); } } while (retry); @@ -1588,12 +1648,22 @@ static int ibmvnic_login(struct net_device *netdev) static void release_login_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_buf_token, + adapter->login_buf_sz, DMA_TO_DEVICE); kfree(adapter->login_buf); adapter->login_buf = NULL; } static void release_login_rsp_buffer(struct ibmvnic_adapter *adapter) { + if (!adapter->login_rsp_buf) + return; + + dma_unmap_single(&adapter->vdev->dev, adapter->login_rsp_buf_token, + adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); kfree(adapter->login_rsp_buf); adapter->login_rsp_buf = NULL; } @@ -4830,11 +4900,14 @@ static int send_login(struct ibmvnic_adapter *adapter) if (rc) { adapter->login_pending = false; netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc); - goto buf_rsp_map_failed; + goto buf_send_failed; } return 0; +buf_send_failed: + dma_unmap_single(dev, rsp_buffer_token, rsp_buffer_size, + DMA_FROM_DEVICE); buf_rsp_map_failed: kfree(login_rsp_buffer); adapter->login_rsp_buf = NULL; @@ -5396,6 +5469,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, int num_tx_pools; int num_rx_pools; u64 *size_array; + u32 rsp_len; int i; /* CHECK: Test/set of login_pending does not need to be atomic @@ -5407,11 +5481,6 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, } adapter->login_pending = false; - dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz, - DMA_TO_DEVICE); - dma_unmap_single(dev, adapter->login_rsp_buf_token, - adapter->login_rsp_buf_sz, DMA_FROM_DEVICE); - /* If the number of queues requested can't be allocated by the * server, the login response will return with code 1. We will need * to resend the login buffer with fewer queues requested. @@ -5447,6 +5516,23 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq, ibmvnic_reset(adapter, VNIC_RESET_FATAL); return -EIO; } + + rsp_len = be32_to_cpu(login_rsp->len); + if (be32_to_cpu(login->login_rsp_len) < rsp_len || + rsp_len <= be32_to_cpu(login_rsp->off_txsubm_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_subcrqs) || + rsp_len <= be32_to_cpu(login_rsp->off_rxadd_buff_size) || + rsp_len <= be32_to_cpu(login_rsp->off_supp_tx_desc)) { + /* This can happen if a login request times out and there are + * 2 outstanding login requests sent, the LOGIN_RSP crq + * could have been for the older login request. So we are + * parsing the newer response buffer which may be incomplete + */ + dev_err(dev, "FATAL: Login rsp offsets/lengths invalid\n"); + ibmvnic_reset(adapter, VNIC_RESET_FATAL); + return -EIO; + } + size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) + be32_to_cpu(adapter->login_rsp_buf->off_rxadd_buff_size)); /* variable buffer sizes are not supported, so just read the diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 2f47cfa7f06e..460ca561819a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1401,14 +1401,15 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx if (fsp->flow_type & FLOW_MAC_EXT) return -EINVAL; + spin_lock_bh(&adapter->fdir_fltr_lock); if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { + spin_unlock_bh(&adapter->fdir_fltr_lock); dev_err(&adapter->pdev->dev, "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", IAVF_MAX_FDIR_FILTERS); return -ENOSPC; } - spin_lock_bh(&adapter->fdir_fltr_lock); if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1781,7 +1782,9 @@ static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLCNT: if (!FDIR_FLTR_SUPPORT(adapter)) break; + spin_lock_bh(&adapter->fdir_fltr_lock); cmd->rule_cnt = adapter->fdir_active_fltr; + spin_unlock_bh(&adapter->fdir_fltr_lock); cmd->data = IAVF_MAX_FDIR_FILTERS; ret = 0; break; diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 6146203efd84..505e82ebafe4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -722,7 +722,9 @@ void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *f bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *tmp; + bool ret = false; + spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { if (tmp->flow_type != fltr->flow_type) continue; @@ -732,11 +734,14 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * !memcmp(&tmp->ip_data, &fltr->ip_data, sizeof(fltr->ip_data)) && !memcmp(&tmp->ext_data, &fltr->ext_data, - sizeof(fltr->ext_data))) - return true; + sizeof(fltr->ext_data))) { + ret = true; + break; + } } + spin_unlock_bh(&adapter->fdir_fltr_lock); - return false; + return ret; } /** diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 9db384f66a8e..38901d2a4680 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -195,6 +195,10 @@ struct igc_adapter { u32 qbv_config_change_errors; bool qbv_transition; unsigned int qbv_count; + /* Access to oper_gate_closed, admin_gate_closed and qbv_transition + * are protected by the qbv_tx_lock. + */ + spinlock_t qbv_tx_lock; /* OS defined structs */ struct pci_dev *pdev; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index bdeb36790d77..6f557e843e49 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4801,6 +4801,7 @@ static int igc_sw_init(struct igc_adapter *adapter) adapter->nfc_rule_count = 0; spin_lock_init(&adapter->stats64_lock); + spin_lock_init(&adapter->qbv_tx_lock); /* Assume MSI-X interrupts, will be checked during IRQ allocation */ adapter->flags |= IGC_FLAG_HAS_MSIX; @@ -6119,15 +6120,15 @@ static int igc_tsn_enable_launchtime(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } -static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +static int igc_qbv_clear_schedule(struct igc_adapter *adapter) { + unsigned long flags; int i; adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; adapter->taprio_offload_enable = false; adapter->qbv_config_change_errors = 0; - adapter->qbv_transition = false; adapter->qbv_count = 0; for (i = 0; i < adapter->num_tx_queues; i++) { @@ -6136,10 +6137,28 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) ring->start_time = 0; ring->end_time = NSEC_PER_SEC; ring->max_sdu = 0; + } + + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + + adapter->qbv_transition = false; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + ring->oper_gate_closed = false; ring->admin_gate_closed = false; } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + + return 0; +} + +static int igc_tsn_clear_schedule(struct igc_adapter *adapter) +{ + igc_qbv_clear_schedule(adapter); + return 0; } @@ -6150,6 +6169,7 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; u32 start_time = 0, end_time = 0; struct timespec64 now; + unsigned long flags; size_t n; int i; @@ -6217,6 +6237,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, start_time += e->interval; } + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + /* Check whether a queue gets configured. * If not, set the start and end time to be end time. */ @@ -6241,6 +6263,8 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, } } + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; struct net_device *dev = adapter->netdev; @@ -6619,8 +6643,11 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) { struct igc_adapter *adapter = container_of(timer, struct igc_adapter, hrtimer); + unsigned long flags; unsigned int i; + spin_lock_irqsave(&adapter->qbv_tx_lock, flags); + adapter->qbv_transition = true; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *tx_ring = adapter->tx_ring[i]; @@ -6633,6 +6660,9 @@ static enum hrtimer_restart igc_qbv_scheduling_timer(struct hrtimer *timer) } } adapter->qbv_transition = false; + + spin_unlock_irqrestore(&adapter->qbv_tx_lock, flags); + return HRTIMER_NORESTART; } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_router.c b/drivers/net/ethernet/marvell/prestera/prestera_router.c index a9a1028cb17b..de317179a7dc 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_router.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_router.c @@ -166,11 +166,11 @@ prestera_util_neigh2nc_key(struct prestera_switch *sw, struct neighbour *n, static bool __prestera_fi_is_direct(struct fib_info *fi) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; if (fib_info_num_path(fi) == 1) { - fib_nh = fib_info_nh(fi, 0); - if (fib_nh->fib_nh_gw_family == AF_UNSPEC) + fib_nhc = fib_info_nhc(fi, 0); + if (fib_nhc->nhc_gw_family == AF_UNSPEC) return true; } @@ -261,7 +261,7 @@ static bool __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, struct net_device *dev) { - struct fib_nh *fib_nh; + struct fib_nh_common *fib_nhc; struct fib_result res; bool reachable; @@ -269,8 +269,8 @@ __prestera_util_kern_n_is_reachable_v4(u32 tb_id, __be32 *addr, if (!prestera_util_kern_get_route(&res, tb_id, addr)) if (prestera_fi_is_direct(res.fi)) { - fib_nh = fib_info_nh(res.fi, 0); - if (dev == fib_nh->fib_nh_dev) + fib_nhc = fib_info_nhc(res.fi, 0); + if (dev == fib_nhc->nhc_dev) reachable = true; } @@ -324,7 +324,7 @@ prestera_kern_fib_info_nhc(struct fib_notifier_info *info, int n) if (info->family == AF_INET) { fen4_info = container_of(info, struct fib_entry_notifier_info, info); - return &fib_info_nh(fen4_info->fi, n)->nh_common; + return fib_info_nhc(fen4_info->fi, n); } else if (info->family == AF_INET6) { fen6_info = container_of(info, struct fib6_entry_notifier_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c index b0128336ff01..e869c65d8e90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c @@ -2,6 +2,7 @@ /* Copyright (c) 2023, NVIDIA CORPORATION & AFFILIATES. */ #include "reporter_vnic.h" +#include "en_stats.h" #include "devlink.h" #define VNIC_ENV_GET64(vnic_env_stats, c) \ @@ -36,55 +37,72 @@ int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, if (err) return err; - err = devlink_fmsg_u64_pair_put(fmsg, "total_error_queues", - VNIC_ENV_GET64(&vnic, total_error_queues)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "send_queue_priority_update_flow", - VNIC_ENV_GET64(&vnic, send_queue_priority_update_flow)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "comp_eq_overrun", - VNIC_ENV_GET64(&vnic, comp_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "async_eq_overrun", - VNIC_ENV_GET64(&vnic, async_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "cq_overrun", - VNIC_ENV_GET64(&vnic, cq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "invalid_command", - VNIC_ENV_GET64(&vnic, invalid_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "quota_exceeded_command", - VNIC_ENV_GET64(&vnic, quota_exceeded_command)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", - VNIC_ENV_GET64(&vnic, nic_receive_steering_discard)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, generated_pkt_steering_fail)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); - if (err) - return err; + if (MLX5_CAP_GEN(dev, vnic_env_queue_counters)) { + err = devlink_fmsg_u32_pair_put(fmsg, "total_error_queues", + VNIC_ENV_GET(&vnic, total_error_queues)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow", + VNIC_ENV_GET(&vnic, + send_queue_priority_update_flow)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, eq_overrun_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun", + VNIC_ENV_GET(&vnic, comp_eq_overrun)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun", + VNIC_ENV_GET(&vnic, async_eq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) { + err = devlink_fmsg_u32_pair_put(fmsg, "cq_overrun", + VNIC_ENV_GET(&vnic, cq_overrun)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, invalid_command_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "invalid_command", + VNIC_ENV_GET(&vnic, invalid_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, quota_exceeded_count)) { + err = devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command", + VNIC_ENV_GET(&vnic, quota_exceeded_command)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) { + err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", + VNIC_ENV_GET64(&vnic, + nic_receive_steering_discard)); + if (err) + return err; + } + + if (MLX5_CAP_GEN(dev, vnic_env_cnt_steering_fail)) { + err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, + generated_pkt_steering_fail)); + if (err) + return err; + + err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); + if (err) + return err; + } err = devlink_fmsg_obj_nest_end(fmsg); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 0c88cf47af01..1730f6a716ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -1461,10 +1461,12 @@ static void mlx5e_invalidate_encap(struct mlx5e_priv *priv, attr = mlx5e_tc_get_encap_attr(flow); esw_attr = attr->esw_attr; - if (flow_flag_test(flow, SLOW)) + if (flow_flag_test(flow, SLOW)) { mlx5e_tc_unoffload_from_slow_path(esw, flow); - else + } else { mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->attr); + mlx5e_tc_unoffload_flow_post_acts(flow); + } mlx5e_tc_detach_mod_hdr(priv, flow, attr); attr->modify_hdr = NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1c820119e438..c27df14df145 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -5266,6 +5266,7 @@ void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) static int mlx5e_nic_init(struct mlx5_core_dev *mdev, struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_flow_steering *fs; int err; @@ -5294,9 +5295,19 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_health_create_reporters(priv); + + /* If netdev is already registered (e.g. move from uplink to nic profile), + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); + /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 92377632f9e0..31708d5aa608 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1943,9 +1943,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_flow_attr *attr = flow->attr; - struct mlx5_esw_flow_attr *esw_attr; - esw_attr = attr->esw_attr; mlx5e_put_flow_tunnel_id(flow); remove_unready_flow(flow); @@ -1966,12 +1964,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5_tc_ct_match_del(get_ct_priv(priv), &flow->attr->ct_attr); - if (esw_attr->int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->int_port); - - if (esw_attr->dest_int_port) - mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(priv), esw_attr->dest_int_port); - if (flow_flag_test(flow, L3_TO_L2_DECAP)) mlx5e_detach_decap(priv, flow); @@ -4268,6 +4260,7 @@ static void mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr) { struct mlx5_core_dev *counter_dev = get_flow_counter_dev(flow); + struct mlx5_esw_flow_attr *esw_attr; if (!attr) return; @@ -4285,6 +4278,18 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a mlx5e_tc_detach_mod_hdr(flow->priv, flow, attr); } + if (mlx5e_is_eswitch_flow(flow)) { + esw_attr = attr->esw_attr; + + if (esw_attr->int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->int_port); + + if (esw_attr->dest_int_port) + mlx5e_tc_int_port_put(mlx5e_get_int_port_priv(flow->priv), + esw_attr->dest_int_port); + } + mlx5_tc_ct_delete_flow(get_ct_priv(flow->priv), attr); free_branch_attr(flow, attr->branch_true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index af779c700278..fdf2be548e85 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -60,7 +60,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 } else if (mlx5_core_is_ec_vf_vport(esw->dev, vport_num)) { memcpy(dl_port->attrs.switch_id.id, ppid.id, ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; - devlink_port_attrs_pci_vf_set(dl_port, controller_num, pfnum, + devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum, vport_num - 1, false); } return dl_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c index d3a3fe4ce670..7d9bbb494d95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c @@ -574,7 +574,7 @@ static int __mlx5_lag_modify_definers_destinations(struct mlx5_lag *ldev, for (i = 0; i < ldev->ports; i++) { for (j = 0; j < ldev->buckets; j++) { idx = i * ldev->buckets + j; - if (ldev->v2p_map[i] == ports[i]) + if (ldev->v2p_map[idx] == ports[idx]) continue; dest.vport.vhca_id = MLX5_CAP_GEN(ldev->pf[ports[idx] - 1].dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 973babfaff25..377372f0578a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -227,10 +227,15 @@ static void mlx5_timestamp_overflow(struct work_struct *work) clock = container_of(timer, struct mlx5_clock, timer); mdev = container_of(clock, struct mlx5_core_dev, clock); + if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto out; + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&timer->tc); mlx5_update_clock_info_page(mdev); write_sequnlock_irqrestore(&clock->lock, flags); + +out: schedule_delayed_work(&timer->overflow_work, timer->overflow_period); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f42abc2ea73c..72ae560a1c68 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1989,7 +1989,7 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); - mlx5_unload_one(dev, true); + mlx5_unload_one(dev, false); mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c4be257c043d..682d3dc00dd1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -361,7 +361,7 @@ static inline bool mlx5_core_is_ec_vf_vport(const struct mlx5_core_dev *dev, u16 static inline int mlx5_vport_to_func_id(const struct mlx5_core_dev *dev, u16 vport, bool ec_vf_func) { - return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + return ec_vf_func ? vport - mlx5_core_ec_vf_vport_base(dev) + 1 : vport; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 4e42a3b9b8ee..a2fc937d5461 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -285,8 +285,7 @@ static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev) host_total_vfs = MLX5_GET(query_esw_functions_out, out, host_params_context.host_total_vfs); kvfree(out); - if (host_total_vfs) - return host_total_vfs; + return host_total_vfs; } done: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c index d6947fe13d56..8ca534ef5d03 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c @@ -82,7 +82,7 @@ dr_ptrn_alloc_pattern(struct mlx5dr_ptrn_mgr *mgr, u32 chunk_size; u32 index; - chunk_size = ilog2(num_of_actions); + chunk_size = ilog2(roundup_pow_of_two(num_of_actions)); /* HW modify action index granularity is at least 64B */ chunk_size = max_t(u32, chunk_size, DR_CHUNK_SIZE_8); diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a499e460594b..c2ad0921e893 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -8,6 +8,7 @@ #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/mm.h> +#include <linux/pci.h> #include <net/checksum.h> #include <net/ip6_checksum.h> @@ -2345,9 +2346,12 @@ int mana_attach(struct net_device *ndev) static int mana_dealloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); + unsigned long timeout = jiffies + 120 * HZ; struct gdma_dev *gd = apc->ac->gdma_dev; struct mana_txq *txq; + struct sk_buff *skb; int i, err; + u32 tsleep; if (apc->port_is_up) return -EINVAL; @@ -2363,15 +2367,40 @@ static int mana_dealloc_queues(struct net_device *ndev) * to false, but it doesn't matter since mana_start_xmit() drops any * new packets due to apc->port_is_up being false. * - * Drain all the in-flight TX packets + * Drain all the in-flight TX packets. + * A timeout of 120 seconds for all the queues is used. + * This will break the while loop when h/w is not responding. + * This value of 120 has been decided here considering max + * number of queues. */ + for (i = 0; i < apc->num_queues; i++) { txq = &apc->tx_qp[i].txq; - - while (atomic_read(&txq->pending_sends) > 0) - usleep_range(1000, 2000); + tsleep = 1000; + while (atomic_read(&txq->pending_sends) > 0 && + time_before(jiffies, timeout)) { + usleep_range(tsleep, tsleep + 1000); + tsleep <<= 1; + } + if (atomic_read(&txq->pending_sends)) { + err = pcie_flr(to_pci_dev(gd->gdma_context->dev)); + if (err) { + netdev_err(ndev, "flr failed %d with %d pkts pending in txq %u\n", + err, atomic_read(&txq->pending_sends), + txq->gdma_txq_id); + } + break; + } } + for (i = 0; i < apc->num_queues; i++) { + txq = &apc->tx_qp[i].txq; + while ((skb = skb_dequeue(&txq->pending_skbs))) { + mana_unmap_skb(skb, apc); + dev_kfree_skb_any(skb); + } + atomic_set(&txq->pending_sends, 0); + } /* We're 100% sure the queues can no longer be woken up, because * we're sure now mana_poll_tx_cq() can't be running. */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 612b0015dc43..432fb93aa801 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -1817,6 +1817,7 @@ static int ionic_change_mtu(struct net_device *netdev, int new_mtu) static void ionic_tx_timeout_work(struct work_struct *ws) { struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + int err; if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) return; @@ -1829,8 +1830,11 @@ static void ionic_tx_timeout_work(struct work_struct *ws) mutex_lock(&lif->queue_lock); ionic_stop_queues_reconfig(lif); - ionic_start_queues_reconfig(lif); + err = ionic_start_queues_reconfig(lif); mutex_unlock(&lif->queue_lock); + + if (err) + dev_err(lif->ionic->dev, "%s: Restarting queues failed\n", __func__); } static void ionic_tx_timeout(struct net_device *netdev, unsigned int txqueue) @@ -2800,17 +2804,22 @@ static int ionic_cmb_reconfig(struct ionic_lif *lif, if (err) { dev_err(lif->ionic->dev, "CMB restore failed: %d\n", err); - goto errout; + goto err_out; } } - ionic_start_queues_reconfig(lif); - } else { - /* This was detached in ionic_stop_queues_reconfig() */ - netif_device_attach(lif->netdev); + err = ionic_start_queues_reconfig(lif); + if (err) { + dev_err(lif->ionic->dev, + "CMB reconfig failed: %d\n", err); + goto err_out; + } } -errout: +err_out: + /* This was detached in ionic_stop_queues_reconfig() */ + netif_device_attach(lif->netdev); + return err; } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 984dfa5d6c11..144ec756c796 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -743,7 +743,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_dropped++; + DEV_STATS_INC(secy->netdev, rx_dropped); return false; } @@ -767,7 +767,7 @@ static bool macsec_post_decrypt(struct sk_buff *skb, struct macsec_secy *secy, u rxsc_stats->stats.InPktsNotValid++; u64_stats_update_end(&rxsc_stats->syncp); this_cpu_inc(rx_sa->stats->InPktsNotValid); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); return false; } @@ -1069,7 +1069,7 @@ static enum rx_handler_result handle_not_macsec(struct sk_buff *skb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoTag++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); continue; } @@ -1179,7 +1179,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsBadTag++; u64_stats_update_end(&secy_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); goto drop_nosa; } @@ -1196,7 +1196,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsNotUsingSA++; u64_stats_update_end(&rxsc_stats->syncp); - secy->netdev->stats.rx_errors++; + DEV_STATS_INC(secy->netdev, rx_errors); if (active_rx_sa) this_cpu_inc(active_rx_sa->stats->InPktsNotUsingSA); goto drop_nosa; @@ -1230,7 +1230,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) u64_stats_update_begin(&rxsc_stats->syncp); rxsc_stats->stats.InPktsLate++; u64_stats_update_end(&rxsc_stats->syncp); - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); goto drop; } } @@ -1271,7 +1271,7 @@ deliver: if (ret == NET_RX_SUCCESS) count_rx(dev, len); else - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); rcu_read_unlock(); @@ -1308,7 +1308,7 @@ nosci: u64_stats_update_begin(&secy_stats->syncp); secy_stats->stats.InPktsNoSCI++; u64_stats_update_end(&secy_stats->syncp); - macsec->secy.netdev->stats.rx_errors++; + DEV_STATS_INC(macsec->secy.netdev, rx_errors); continue; } @@ -1327,7 +1327,7 @@ nosci: secy_stats->stats.InPktsUnknownSCI++; u64_stats_update_end(&secy_stats->syncp); } else { - macsec->secy.netdev->stats.rx_dropped++; + DEV_STATS_INC(macsec->secy.netdev, rx_dropped); } } @@ -3422,7 +3422,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, if (!secy->operational) { kfree_skb(skb); - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3430,7 +3430,7 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, skb = macsec_encrypt(skb, dev); if (IS_ERR(skb)) { if (PTR_ERR(skb) != -EINPROGRESS) - dev->stats.tx_dropped++; + DEV_STATS_INC(dev, tx_dropped); return NETDEV_TX_OK; } @@ -3667,9 +3667,9 @@ static void macsec_get_stats64(struct net_device *dev, dev_fetch_sw_netstats(s, dev->tstats); - s->rx_dropped = dev->stats.rx_dropped; - s->tx_dropped = dev->stats.tx_dropped; - s->rx_errors = dev->stats.rx_errors; + s->rx_dropped = atomic_long_read(&dev->stats.__rx_dropped); + s->tx_dropped = atomic_long_read(&dev->stats.__tx_dropped); + s->rx_errors = atomic_long_read(&dev->stats.__rx_errors); } static int macsec_get_iflink(const struct net_device *dev) diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index c1f307d90518..8a77ec33b417 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -459,21 +459,27 @@ static int at803x_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, MDIO_MMD_PCS, offsets[i], mac[(i * 2) + 1] | (mac[(i * 2)] << 8)); - /* Enable WOL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - 0, AT803X_WOL_EN); - if (ret) - return ret; + /* Enable WOL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + 0, AT803X_WOL_EN); + if (ret) + return ret; + } /* Enable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, 0, AT803X_INTR_ENABLE_WOL); if (ret) return ret; } else { - /* Disable WoL function */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL, - AT803X_WOL_EN, 0); - if (ret) - return ret; + /* Disable WoL function for 1588 */ + if (phydev->drv->phy_id == ATH8031_PHY_ID) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) + return ret; + } /* Disable WOL interrupt */ ret = phy_modify(phydev, AT803X_INTR_ENABLE, AT803X_INTR_ENABLE_WOL, 0); if (ret) @@ -508,11 +514,11 @@ static void at803x_get_wol(struct phy_device *phydev, wol->supported = WAKE_MAGIC; wol->wolopts = 0; - value = phy_read_mmd(phydev, MDIO_MMD_PCS, AT803X_PHY_MMD3_WOL_CTRL); + value = phy_read(phydev, AT803X_INTR_ENABLE); if (value < 0) return; - if (value & AT803X_WOL_EN) + if (value & AT803X_INTR_ENABLE_WOL) wol->wolopts |= WAKE_MAGIC; } @@ -858,9 +864,6 @@ static int at803x_probe(struct phy_device *phydev) if (phydev->drv->phy_id == ATH8031_PHY_ID) { int ccr = phy_read(phydev, AT803X_REG_CHIP_CONFIG); int mode_cfg; - struct ethtool_wolinfo wol = { - .wolopts = 0, - }; if (ccr < 0) return ccr; @@ -877,12 +880,14 @@ static int at803x_probe(struct phy_device *phydev) break; } - /* Disable WOL by default */ - ret = at803x_set_wol(phydev, &wol); - if (ret < 0) { - phydev_err(phydev, "failed to disable WOL on probe: %d\n", ret); + /* Disable WoL in 1588 register which is enabled + * by default + */ + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + AT803X_PHY_MMD3_WOL_CTRL, + AT803X_WOL_EN, 0); + if (ret) return ret; - } } return 0; @@ -2059,8 +2064,6 @@ static struct phy_driver at803x_driver[] = { .flags = PHY_POLL_CABLE_TEST, .config_init = at803x_config_init, .link_change_notify = at803x_link_change_notify, - .set_wol = at803x_set_wol, - .get_wol = at803x_get_wol, .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 25f0191df00b..100339bc8b04 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1594,7 +1594,7 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, if (zerocopy) return false; - if (SKB_DATA_ALIGN(len + TUN_RX_PAD) + + if (SKB_DATA_ALIGN(len + TUN_RX_PAD + XDP_PACKET_HEADROOM) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) return false; diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index a3de081cda5e..c3ff30ab782e 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -713,6 +713,12 @@ static struct vxlan_vni_node *vxlan_vni_alloc(struct vxlan_dev *vxlan, return vninode; } +static void vxlan_vni_free(struct vxlan_vni_node *vninode) +{ + free_percpu(vninode->stats); + kfree(vninode); +} + static int vxlan_vni_add(struct vxlan_dev *vxlan, struct vxlan_vni_group *vg, u32 vni, union vxlan_addr *group, @@ -740,7 +746,7 @@ static int vxlan_vni_add(struct vxlan_dev *vxlan, &vninode->vnode, vxlan_vni_rht_params); if (err) { - kfree(vninode); + vxlan_vni_free(vninode); return err; } @@ -763,8 +769,7 @@ static void vxlan_vni_node_rcu_free(struct rcu_head *rcu) struct vxlan_vni_node *v; v = container_of(rcu, struct vxlan_vni_node, rcu); - free_percpu(v->stats); - kfree(v); + vxlan_vni_free(v); } static int vxlan_vni_del(struct vxlan_dev *vxlan, diff --git a/drivers/net/wireguard/allowedips.c b/drivers/net/wireguard/allowedips.c index 5bf7822c53f1..0ba714ca5185 100644 --- a/drivers/net/wireguard/allowedips.c +++ b/drivers/net/wireguard/allowedips.c @@ -6,7 +6,7 @@ #include "allowedips.h" #include "peer.h" -enum { MAX_ALLOWEDIPS_BITS = 128 }; +enum { MAX_ALLOWEDIPS_DEPTH = 129 }; static struct kmem_cache *node_cache; @@ -42,7 +42,7 @@ static void push_rcu(struct allowedips_node **stack, struct allowedips_node __rcu *p, unsigned int *len) { if (rcu_access_pointer(p)) { - if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_BITS)) + if (WARN_ON(IS_ENABLED(DEBUG) && *len >= MAX_ALLOWEDIPS_DEPTH)) return; stack[(*len)++] = rcu_dereference_raw(p); } @@ -55,7 +55,7 @@ static void node_free_rcu(struct rcu_head *rcu) static void root_free_rcu(struct rcu_head *rcu) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { container_of(rcu, struct allowedips_node, rcu) }; unsigned int len = 1; @@ -68,7 +68,7 @@ static void root_free_rcu(struct rcu_head *rcu) static void root_remove_peer_lists(struct allowedips_node *root) { - struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_BITS] = { root }; + struct allowedips_node *node, *stack[MAX_ALLOWEDIPS_DEPTH] = { root }; unsigned int len = 1; while (len > 0 && (node = stack[--len])) { diff --git a/drivers/net/wireguard/selftest/allowedips.c b/drivers/net/wireguard/selftest/allowedips.c index 78ebe2892a78..3d1f64ff2e12 100644 --- a/drivers/net/wireguard/selftest/allowedips.c +++ b/drivers/net/wireguard/selftest/allowedips.c @@ -593,16 +593,20 @@ bool __init wg_allowedips_selftest(void) wg_allowedips_remove_by_peer(&t, a, &mutex); test_negative(4, a, 192, 168, 0, 1); - /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_BITS) in free_node + /* These will hit the WARN_ON(len >= MAX_ALLOWEDIPS_DEPTH) in free_node * if something goes wrong. */ - for (i = 0; i < MAX_ALLOWEDIPS_BITS; ++i) { - part = cpu_to_be64(~(1LLU << (i % 64))); - memset(&ip, 0xff, 16); - memcpy((u8 *)&ip + (i < 64) * 8, &part, 8); + for (i = 0; i < 64; ++i) { + part = cpu_to_be64(~0LLU << i); + memset(&ip, 0xff, 8); + memcpy((u8 *)&ip + 8, &part, 8); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); + memcpy(&ip, &part, 8); + memset((u8 *)&ip + 8, 0, 8); wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); } - + memset(&ip, 0, 16); + wg_allowedips_insert_v6(&t, &ip, 128, a, &mutex); wg_allowedips_free(&t, &mutex); wg_allowedips_init(&t); diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 6512267ae4ca..4928e4e91660 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -2144,8 +2144,7 @@ int ath12k_wmi_send_scan_start_cmd(struct ath12k *ar, struct wmi_tlv *tlv; void *ptr; int i, ret, len; - u32 *tmp_ptr; - u8 extraie_len_with_pad = 0; + u32 *tmp_ptr, extraie_len_with_pad = 0; struct ath12k_wmi_hint_short_ssid_arg *s_ssid = NULL; struct ath12k_wmi_hint_bssid_arg *hint_bssid = NULL; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index de8a2e27f49c..2a90bb24ba77 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -1456,6 +1456,10 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, params_size -= BRCMF_SCAN_PARAMS_V2_FIXED_SIZE; params_size += BRCMF_SCAN_PARAMS_FIXED_SIZE; params_v1 = kzalloc(params_size, GFP_KERNEL); + if (!params_v1) { + err = -ENOMEM; + goto exit_params; + } params_v1->version = cpu_to_le32(BRCMF_ESCAN_REQ_VERSION); brcmf_scan_params_v2_to_v1(¶ms->params_v2_le, ¶ms_v1->params_le); kfree(params); @@ -1473,6 +1477,7 @@ brcmf_run_escan(struct brcmf_cfg80211_info *cfg, struct brcmf_if *ifp, bphy_err(drvr, "error (%d)\n", err); } +exit_params: kfree(params); exit: return err; diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c index b114babec698..c93e6250cb8b 100644 --- a/drivers/net/wireless/realtek/rtw89/mac.c +++ b/drivers/net/wireless/realtek/rtw89/mac.c @@ -2524,7 +2524,7 @@ static int cmac_dma_init(struct rtw89_dev *rtwdev, u8 mac_idx) u32 reg; int ret; - if (chip_id != RTL8852A && chip_id != RTL8852B) + if (chip_id != RTL8852B) return 0; ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL); diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 5bc81cc0a2de..46b252bbe500 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -11,6 +11,7 @@ #include <linux/pci.h> #include <linux/errno.h> #include <linux/ioport.h> +#include <linux/of.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -332,6 +333,7 @@ void __weak pcibios_bus_add_device(struct pci_dev *pdev) { } */ void pci_bus_add_device(struct pci_dev *dev) { + struct device_node *dn = dev->dev.of_node; int retval; /* @@ -344,7 +346,7 @@ void pci_bus_add_device(struct pci_dev *dev) pci_proc_attach_device(dev); pci_bridge_d3_update(dev); - dev->match_driver = true; + dev->match_driver = !dn || of_device_is_available(dn); retval = device_attach(&dev->dev); if (retval < 0 && retval != -EPROBE_DEFER) pci_warn(dev, "device attach failed (%d)\n", retval); diff --git a/drivers/pci/of.c b/drivers/pci/of.c index e51219f9f523..3c158b17dcb5 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -34,11 +34,6 @@ int pci_set_of_node(struct pci_dev *dev) if (!node) return 0; - if (!of_device_is_available(node)) { - of_node_put(node); - return -ENODEV; - } - device_set_node(&dev->dev, of_fwnode_handle(node)); return 0; } diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 054d7911bfc9..c1637515a8a4 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -62,6 +62,7 @@ struct sk_psock_progs { enum sk_psock_state_bits { SK_PSOCK_TX_ENABLED, + SK_PSOCK_RX_STRP_ENABLED, }; struct sk_psock_link { diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7c7d03aa9d06..d6fa7c8767ad 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -562,6 +562,9 @@ ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, if (WARN_ON(iftype >= NL80211_IFTYPE_MAX)) return NULL; + if (iftype == NL80211_IFTYPE_AP_VLAN) + iftype = NL80211_IFTYPE_AP; + for (i = 0; i < sband->n_iftype_data; i++) { const struct ieee80211_sband_iftype_data *data = &sband->iftype_data[i]; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 640441a2f926..35870858ddf2 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -512,6 +512,7 @@ struct nft_set_elem_expr { * * @list: table set list node * @bindings: list of set bindings + * @refs: internal refcounting for async set destruction * @table: table this set belongs to * @net: netnamespace this set belongs to * @name: name of the set @@ -541,6 +542,7 @@ struct nft_set_elem_expr { struct nft_set { struct list_head list; struct list_head bindings; + refcount_t refs; struct nft_table *table; possible_net_t net; char *name; @@ -562,7 +564,8 @@ struct nft_set { struct list_head pending_update; /* runtime data below here */ const struct nft_set_ops *ops ____cacheline_aligned; - u16 flags:14, + u16 flags:13, + dead:1, genmask:2; u8 klen; u8 dlen; @@ -596,7 +599,6 @@ struct nft_set *nft_set_lookup_global(const struct net *net, struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, const struct nft_set *set); -void *nft_set_catchall_gc(const struct nft_set *set); static inline unsigned long nft_set_gc_interval(const struct nft_set *set) { @@ -813,62 +815,6 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, const struct nft_set *set, void *elem); -/** - * struct nft_set_gc_batch_head - nf_tables set garbage collection batch - * - * @rcu: rcu head - * @set: set the elements belong to - * @cnt: count of elements - */ -struct nft_set_gc_batch_head { - struct rcu_head rcu; - const struct nft_set *set; - unsigned int cnt; -}; - -#define NFT_SET_GC_BATCH_SIZE ((PAGE_SIZE - \ - sizeof(struct nft_set_gc_batch_head)) / \ - sizeof(void *)) - -/** - * struct nft_set_gc_batch - nf_tables set garbage collection batch - * - * @head: GC batch head - * @elems: garbage collection elements - */ -struct nft_set_gc_batch { - struct nft_set_gc_batch_head head; - void *elems[NFT_SET_GC_BATCH_SIZE]; -}; - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp); -void nft_set_gc_batch_release(struct rcu_head *rcu); - -static inline void nft_set_gc_batch_complete(struct nft_set_gc_batch *gcb) -{ - if (gcb != NULL) - call_rcu(&gcb->head.rcu, nft_set_gc_batch_release); -} - -static inline struct nft_set_gc_batch * -nft_set_gc_batch_check(const struct nft_set *set, struct nft_set_gc_batch *gcb, - gfp_t gfp) -{ - if (gcb != NULL) { - if (gcb->head.cnt + 1 < ARRAY_SIZE(gcb->elems)) - return gcb; - nft_set_gc_batch_complete(gcb); - } - return nft_set_gc_batch_alloc(set, gfp); -} - -static inline void nft_set_gc_batch_add(struct nft_set_gc_batch *gcb, - void *elem) -{ - gcb->elems[gcb->head.cnt++] = elem; -} - struct nft_expr_ops; /** * struct nft_expr_type - nf_tables expression type @@ -1557,39 +1503,30 @@ static inline void nft_set_elem_change_active(const struct net *net, #endif /* IS_ENABLED(CONFIG_NF_TABLES) */ -/* - * We use a free bit in the genmask field to indicate the element - * is busy, meaning it is currently being processed either by - * the netlink API or GC. - * - * Even though the genmask is only a single byte wide, this works - * because the extension structure if fully constant once initialized, - * so there are no non-atomic write accesses unless it is already - * marked busy. - */ -#define NFT_SET_ELEM_BUSY_MASK (1 << 2) +#define NFT_SET_ELEM_DEAD_MASK (1 << 2) #if defined(__LITTLE_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT 2 +#define NFT_SET_ELEM_DEAD_BIT 2 #elif defined(__BIG_ENDIAN_BITFIELD) -#define NFT_SET_ELEM_BUSY_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) +#define NFT_SET_ELEM_DEAD_BIT (BITS_PER_LONG - BITS_PER_BYTE + 2) #else #error #endif -static inline int nft_set_elem_mark_busy(struct nft_set_ext *ext) +static inline void nft_set_elem_dead(struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); - return test_and_set_bit(NFT_SET_ELEM_BUSY_BIT, word); + set_bit(NFT_SET_ELEM_DEAD_BIT, word); } -static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) +static inline int nft_set_elem_is_dead(const struct nft_set_ext *ext) { unsigned long *word = (unsigned long *)ext; - clear_bit(NFT_SET_ELEM_BUSY_BIT, word); + BUILD_BUG_ON(offsetof(struct nft_set_ext, genmask) != 0); + return test_bit(NFT_SET_ELEM_DEAD_BIT, word); } /** @@ -1732,6 +1669,38 @@ struct nft_trans_flowtable { #define nft_trans_flowtable_flags(trans) \ (((struct nft_trans_flowtable *)trans->data)->flags) +#define NFT_TRANS_GC_BATCHCOUNT 256 + +struct nft_trans_gc { + struct list_head list; + struct net *net; + struct nft_set *set; + u32 seq; + u8 count; + void *priv[NFT_TRANS_GC_BATCHCOUNT]; + struct rcu_head rcu; +}; + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_destroy(struct nft_trans_gc *trans); + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp); +void nft_trans_gc_queue_async_done(struct nft_trans_gc *gc); + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp); +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans); + +void nft_trans_gc_elem_add(struct nft_trans_gc *gc, void *priv); + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq); + +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); @@ -1758,6 +1727,7 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; unsigned int base_seq; + unsigned int gc_seq; }; extern unsigned int nf_tables_net_id; diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index bf06db8d2046..7b1ddffa3dfc 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -381,6 +381,7 @@ TRACE_EVENT(tcp_cong_state_set, __field(const void *, skaddr) __field(__u16, sport) __field(__u16, dport) + __field(__u16, family) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) @@ -396,6 +397,7 @@ TRACE_EVENT(tcp_cong_state_set, __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); + __entry->family = sk->sk_family; p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; @@ -409,7 +411,8 @@ TRACE_EVENT(tcp_cong_state_set, __entry->cong_state = ca_state; ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + TP_printk("family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c cong_state=%u", + show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index e40aa3e3641c..b3662119ddbc 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -384,8 +384,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } - if (event == NETDEV_DOWN && - (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + if (event == NETDEV_DOWN) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); diff --git a/net/core/filter.c b/net/core/filter.c index 06ba0e56e369..28a59596987a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4116,12 +4116,6 @@ BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) if (unlikely(data_end > data_hard_end)) return -EINVAL; - /* ALL drivers MUST init xdp->frame_sz, chicken check below */ - if (unlikely(xdp->frame_sz > PAGE_SIZE)) { - WARN_ONCE(1, "Too BIG xdp->frame_sz = %d\n", xdp->frame_sz); - return -EINVAL; - } - if (unlikely(data_end < xdp->data + ETH_HLEN)) return -EINVAL; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a29508e1ff35..ef1a2eb6520b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1120,13 +1120,19 @@ static void sk_psock_strp_data_ready(struct sock *sk) int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) { + int ret; + static const struct strp_callbacks cb = { .rcv_msg = sk_psock_strp_read, .read_sock_done = sk_psock_strp_read_done, .parse_msg = sk_psock_strp_parse, }; - return strp_init(&psock->strp, sk, &cb); + ret = strp_init(&psock->strp, sk, &cb); + if (!ret) + sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + + return ret; } void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) @@ -1154,7 +1160,7 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) static void sk_psock_done_strp(struct sk_psock *psock) { /* Parser has been stopped */ - if (psock->progs.stream_parser) + if (sk_psock_test_state(psock, SK_PSOCK_RX_STRP_ENABLED)) strp_done(&psock->strp); } #else diff --git a/net/core/sock.c b/net/core/sock.c index 6d4f28efe29a..732fc37a4771 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1778,7 +1778,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, spin_unlock(&sk->sk_peer_lock); if (!peer_pid) - return -ESRCH; + return -ENODATA; pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file); put_pid(peer_pid); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 08ab108206bf..8f07fea39d9e 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -146,13 +146,13 @@ static void sock_map_del_link(struct sock *sk, list_for_each_entry_safe(link, tmp, &psock->link, list) { if (link->link_raw == link_raw) { struct bpf_map *map = link->map; - struct bpf_stab *stab = container_of(map, struct bpf_stab, - map); - if (psock->saved_data_ready && stab->progs.stream_parser) + struct sk_psock_progs *progs = sock_map_progs(map); + + if (psock->saved_data_ready && progs->stream_parser) strp_stop = true; - if (psock->saved_data_ready && stab->progs.stream_verdict) + if (psock->saved_data_ready && progs->stream_verdict) verdict_stop = true; - if (psock->saved_data_ready && stab->progs.skb_verdict) + if (psock->saved_data_ready && progs->skb_verdict) verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); diff --git a/net/dccp/output.c b/net/dccp/output.c index b8a24734385e..fd2eb148d24d 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -187,7 +187,7 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; - dp->dccps_mss_cache = cur_mps; + WRITE_ONCE(dp->dccps_mss_cache, cur_mps); return cur_mps; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index f331e5977a84..4e3266e4d7c3 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -630,7 +630,7 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, return dccp_getsockopt_service(sk, len, (__be32 __user *)optval, optlen); case DCCP_SOCKOPT_GET_CUR_MPS: - val = dp->dccps_mss_cache; + val = READ_ONCE(dp->dccps_mss_cache); break; case DCCP_SOCKOPT_AVAILABLE_CCIDS: return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); @@ -739,7 +739,7 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) trace_dccp_probe(sk, len); - if (len > dp->dccps_mss_cache) + if (len > READ_ONCE(dp->dccps_mss_cache)) return -EMSGSIZE; lock_sock(sk); @@ -772,6 +772,12 @@ int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) goto out_discard; } + /* We need to check dccps_mss_cache after socket is locked. */ + if (len > dp->dccps_mss_cache) { + rc = -EMSGSIZE; + goto out_discard; + } + skb_reserve(skb, sk->sk_prot->max_header); rc = memcpy_from_msg(skb_put(skb, len), msg, len); if (rc != 0) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 92c02c886fe7..586b1b3e35b8 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -224,7 +224,7 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) .un.frag.__unused = 0, .un.frag.mtu = htons(mtu), }; - icmph->checksum = ip_compute_csum(icmph, len); + icmph->checksum = csum_fold(skb_checksum(skb, 0, len, 0)); skb_reset_transport_header(skb); niph = skb_push(skb, sizeof(*niph)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index f95142e56da0..be5498f5dd31 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3221,13 +3221,9 @@ static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb) &rtm_dump_nexthop_cb, &filter); if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; @@ -3367,25 +3363,19 @@ static int rtm_dump_nexthop_bucket_nh(struct sk_buff *skb, dd->filter.res_bucket_nh_id != nhge->nh->id) continue; + dd->ctx->bucket_index = bucket_index; err = nh_fill_res_bucket(skb, nh, bucket, bucket_index, RTM_NEWNEXTHOPBUCKET, portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); - if (err < 0) { - if (likely(skb->len)) - goto out; - goto out_err; - } + if (err) + return err; } dd->ctx->done_nh_idx = dd->ctx->nh.idx + 1; - bucket_index = 0; + dd->ctx->bucket_index = 0; -out: - err = skb->len; -out_err: - dd->ctx->bucket_index = bucket_index; - return err; + return 0; } static int rtm_dump_nexthop_bucket_cb(struct sk_buff *skb, @@ -3434,13 +3424,9 @@ static int rtm_dump_nexthop_bucket(struct sk_buff *skb, if (err < 0) { if (likely(skb->len)) - goto out; - goto out_err; + err = skb->len; } -out: - err = skb->len; -out_err: cb->seq = net->nexthop.seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); return err; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 18634ebd20a4..a42be96ae209 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -197,7 +197,8 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { - return opt->nd_opt_type == ND_OPT_RDNSS || + return opt->nd_opt_type == ND_OPT_PREFIX_INFO || + opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL || opt->nd_opt_type == ND_OPT_PREF64 || diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 3317d1cca156..d80658547836 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2335,7 +2335,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); - if (flags & MPTCP_CF_FASTCLOSE) { + if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { /* be sure to force the tcp_disconnect() path, * to generate the egress reset */ @@ -3328,7 +3328,7 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags)) __mptcp_clean_una_wakeup(sk); - if (unlikely(&msk->cb_flags)) { + if (unlikely(msk->cb_flags)) { /* be sure to set the current sk state before tacking actions * depending on sk_state, that is processing MPTCP_ERROR_REPORT */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 37fbe22e2433..ba2a873a4d2e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -325,7 +325,6 @@ struct mptcp_sock { u32 subflow_id; u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; - struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9ee3b7abbaf6..94ae7dd01c65 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1793,16 +1793,31 @@ static void subflow_state_change(struct sock *sk) void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) { struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - struct sock *sk; + struct request_sock *req, *head, *tail; + struct mptcp_subflow_context *subflow; + struct sock *sk, *ssk; - /* build a list of all unaccepted mptcp sockets */ + /* Due to lock dependencies no relevant lock can be acquired under rskq_lock. + * Splice the req list, so that accept() can not reach the pending ssk after + * the listener socket is released below. + */ spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; + head = queue->rskq_accept_head; + tail = queue->rskq_accept_tail; + queue->rskq_accept_head = NULL; + queue->rskq_accept_tail = NULL; + spin_unlock_bh(&queue->rskq_lock); + + if (!head) + return; + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (req = head; req; req = req->dl_next) { + ssk = req->sk; if (!sk_is_mptcp(ssk)) continue; @@ -1810,32 +1825,10 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s if (!subflow || !subflow->conn) continue; - /* skip if already in list */ sk = subflow->conn; - msk = mptcp_sk(sk); - if (msk->dl_next || msk == head) - continue; - sock_hold(sk); - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - sk = (struct sock *)msk; lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->dl_next = NULL; - __mptcp_unaccepted_force_close(sk); release_sock(sk); @@ -1859,6 +1852,13 @@ void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_s /* we are still under the listener msk socket lock */ lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); + + /* restore the listener queue, to let the TCP code clean it up */ + spin_lock_bh(&queue->rskq_lock); + WARN_ON_ONCE(queue->rskq_accept_head); + queue->rskq_accept_head = head; + queue->rskq_accept_tail = tail; + spin_unlock_bh(&queue->rskq_lock); } static int subflow_ulp_init(struct sock *sk) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d3c6ecd1f5a6..c62227ae7746 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -31,7 +31,9 @@ static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); static LIST_HEAD(nf_tables_destroy_list); +static LIST_HEAD(nf_tables_gc_list); static DEFINE_SPINLOCK(nf_tables_destroy_list_lock); +static DEFINE_SPINLOCK(nf_tables_gc_list_lock); enum { NFT_VALIDATE_SKIP = 0, @@ -120,6 +122,9 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); +static void nft_trans_gc_work(struct work_struct *work); +static DECLARE_WORK(trans_gc_work, nft_trans_gc_work); + static void nft_ctx_init(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, @@ -582,10 +587,6 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, return __nft_trans_set_add(ctx, msg_type, set, NULL); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem); - static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, @@ -5055,6 +5056,7 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, INIT_LIST_HEAD(&set->bindings); INIT_LIST_HEAD(&set->catchall_list); + refcount_set(&set->refs, 1); set->table = table; write_pnet(&set->net, net); set->ops = ops; @@ -5122,6 +5124,14 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, } } +static void nft_set_put(struct nft_set *set) +{ + if (refcount_dec_and_test(&set->refs)) { + kfree(set->name); + kvfree(set); + } +} + static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) { int i; @@ -5134,8 +5144,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) set->ops->destroy(ctx, set); nft_set_catchall_destroy(ctx, set); - kfree(set->name); - kvfree(set); + nft_set_put(set); } static int nf_tables_delset(struct sk_buff *skb, const struct nfnl_info *info, @@ -5602,8 +5611,12 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx, const struct nft_set_iter *iter, struct nft_set_elem *elem) { + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); struct nft_set_dump_args *args; + if (nft_set_elem_expired(ext)) + return 0; + args = container_of(iter, struct nft_set_dump_args, iter); return nf_tables_fill_setelem(args->skb, set, elem, args->reset); } @@ -6274,7 +6287,8 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask) && - !nft_set_elem_expired(ext)) + !nft_set_elem_expired(ext) && + !nft_set_elem_is_dead(ext)) return ext; } @@ -6282,29 +6296,6 @@ struct nft_set_ext *nft_set_catchall_lookup(const struct net *net, } EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); -void *nft_set_catchall_gc(const struct nft_set *set) -{ - struct nft_set_elem_catchall *catchall, *next; - struct nft_set_ext *ext; - void *elem = NULL; - - list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - ext = nft_set_elem_ext(set, catchall->elem); - - if (!nft_set_elem_expired(ext) || - nft_set_elem_mark_busy(ext)) - continue; - - elem = catchall->elem; - list_del_rcu(&catchall->list); - kfree_rcu(catchall, rcu); - break; - } - - return elem; -} -EXPORT_SYMBOL_GPL(nft_set_catchall_gc); - static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, @@ -6366,7 +6357,6 @@ static void nft_setelem_activate(struct net *net, struct nft_set *set, if (nft_setelem_is_catchall(set, elem)) { nft_set_elem_change_active(net, set, ext); - nft_set_elem_clear_busy(ext); } else { set->ops->activate(net, set, elem); } @@ -6381,8 +6371,7 @@ static int nft_setelem_catchall_deactivate(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_is_active(net, ext) || - nft_set_elem_mark_busy(ext)) + if (!nft_is_active(net, ext)) continue; kfree(elem->priv); @@ -6777,7 +6766,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_elem_free; } - ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; + ext->genmask = nft_genmask_cur(ctx->net); err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); if (err) { @@ -6929,9 +6918,9 @@ static void nft_setelem_data_activate(const struct net *net, nft_use_inc_restore(&(*nft_set_ext_obj(ext))->use); } -static void nft_setelem_data_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -7095,8 +7084,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, list_for_each_entry_rcu(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); - if (!nft_set_elem_active(ext, genmask) || - nft_set_elem_mark_busy(ext)) + if (!nft_set_elem_active(ext, genmask)) continue; elem.priv = catchall->elem; @@ -7170,29 +7158,6 @@ static int nf_tables_delsetelem(struct sk_buff *skb, return err; } -void nft_set_gc_batch_release(struct rcu_head *rcu) -{ - struct nft_set_gc_batch *gcb; - unsigned int i; - - gcb = container_of(rcu, struct nft_set_gc_batch, head.rcu); - for (i = 0; i < gcb->head.cnt; i++) - nft_set_elem_destroy(gcb->head.set, gcb->elems[i], true); - kfree(gcb); -} - -struct nft_set_gc_batch *nft_set_gc_batch_alloc(const struct nft_set *set, - gfp_t gfp) -{ - struct nft_set_gc_batch *gcb; - - gcb = kzalloc(sizeof(*gcb), gfp); - if (gcb == NULL) - return gcb; - gcb->head.set = set; - return gcb; -} - /* * Stateful objects */ @@ -9414,6 +9379,207 @@ void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, + struct nft_trans_gc *trans) +{ + void **priv = trans->priv; + unsigned int i; + + for (i = 0; i < trans->count; i++) { + struct nft_set_elem elem = { + .priv = priv[i], + }; + + nft_setelem_data_deactivate(ctx->net, trans->set, &elem); + nft_setelem_remove(ctx->net, trans->set, &elem); + } +} + +void nft_trans_gc_destroy(struct nft_trans_gc *trans) +{ + nft_set_put(trans->set); + put_net(trans->net); + kfree(trans); +} + +static void nft_trans_gc_trans_free(struct rcu_head *rcu) +{ + struct nft_set_elem elem = {}; + struct nft_trans_gc *trans; + struct nft_ctx ctx = {}; + unsigned int i; + + trans = container_of(rcu, struct nft_trans_gc, rcu); + ctx.net = read_pnet(&trans->set->net); + + for (i = 0; i < trans->count; i++) { + elem.priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, &elem)) + atomic_dec(&trans->set->nelems); + + nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + } + + nft_trans_gc_destroy(trans); +} + +static bool nft_trans_gc_work_done(struct nft_trans_gc *trans) +{ + struct nftables_pernet *nft_net; + struct nft_ctx ctx = {}; + + nft_net = nft_pernet(trans->net); + + mutex_lock(&nft_net->commit_mutex); + + /* Check for race with transaction, otherwise this batch refers to + * stale objects that might not be there anymore. Skip transaction if + * set has been destroyed from control plane transaction in case gc + * worker loses race. + */ + if (READ_ONCE(nft_net->gc_seq) != trans->seq || trans->set->dead) { + mutex_unlock(&nft_net->commit_mutex); + return false; + } + + ctx.net = trans->net; + ctx.table = trans->set->table; + + nft_trans_gc_setelem_remove(&ctx, trans); + mutex_unlock(&nft_net->commit_mutex); + + return true; +} + +static void nft_trans_gc_work(struct work_struct *work) +{ + struct nft_trans_gc *trans, *next; + LIST_HEAD(trans_gc_list); + + spin_lock(&nf_tables_destroy_list_lock); + list_splice_init(&nf_tables_gc_list, &trans_gc_list); + spin_unlock(&nf_tables_destroy_list_lock); + + list_for_each_entry_safe(trans, next, &trans_gc_list, list) { + list_del(&trans->list); + if (!nft_trans_gc_work_done(trans)) { + nft_trans_gc_destroy(trans); + continue; + } + call_rcu(&trans->rcu, nft_trans_gc_trans_free); + } +} + +struct nft_trans_gc *nft_trans_gc_alloc(struct nft_set *set, + unsigned int gc_seq, gfp_t gfp) +{ + struct net *net = read_pnet(&set->net); + struct nft_trans_gc *trans; + + trans = kzalloc(sizeof(*trans), gfp); + if (!trans) + return NULL; + + refcount_inc(&set->refs); + trans->set = set; + trans->net = get_net(net); + trans->seq = gc_seq; + + return trans; +} + +void nft_trans_gc_elem_add(struct nft_trans_gc *trans, void *priv) +{ + trans->priv[trans->count++] = priv; +} + +static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) +{ + spin_lock(&nf_tables_gc_list_lock); + list_add_tail(&trans->list, &nf_tables_gc_list); + spin_unlock(&nf_tables_gc_list_lock); + + schedule_work(&trans_gc_work); +} + +static int nft_trans_gc_space(struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + +struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, + unsigned int gc_seq, gfp_t gfp) +{ + if (nft_trans_gc_space(gc)) + return gc; + + nft_trans_gc_queue_work(gc); + + return nft_trans_gc_alloc(gc->set, gc_seq, gfp); +} + +void nft_trans_gc_queue_async_done(struct nft_trans_gc *trans) +{ + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + nft_trans_gc_queue_work(trans); +} + +struct nft_trans_gc *nft_trans_gc_queue_sync(struct nft_trans_gc *gc, gfp_t gfp) +{ + if (WARN_ON_ONCE(!lockdep_commit_lock_is_held(gc->net))) + return NULL; + + if (nft_trans_gc_space(gc)) + return gc; + + call_rcu(&gc->rcu, nft_trans_gc_trans_free); + + return nft_trans_gc_alloc(gc->set, 0, gfp); +} + +void nft_trans_gc_queue_sync_done(struct nft_trans_gc *trans) +{ + WARN_ON_ONCE(!lockdep_commit_lock_is_held(trans->net)); + + if (trans->count == 0) { + nft_trans_gc_destroy(trans); + return; + } + + call_rcu(&trans->rcu, nft_trans_gc_trans_free); +} + +struct nft_trans_gc *nft_trans_gc_catchall(struct nft_trans_gc *gc, + unsigned int gc_seq) +{ + struct nft_set_elem_catchall *catchall; + const struct nft_set *set = gc->set; + struct nft_set_ext *ext; + + list_for_each_entry_rcu(catchall, &set->catchall_list, list) { + ext = nft_set_elem_ext(set, catchall->elem); + + if (!nft_set_elem_expired(ext)) + continue; + if (nft_set_elem_is_dead(ext)) + goto dead_elem; + + nft_set_elem_dead(ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + return NULL; + + nft_trans_gc_elem_add(gc, catchall->elem); + } + + return gc; +} + static void nf_tables_module_autoload_cleanup(struct net *net) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -9576,11 +9742,11 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nftables_pernet *nft_net = nft_pernet(net); struct nft_trans *trans, *next; + unsigned int base_seq, gc_seq; LIST_HEAD(set_update_list); struct nft_trans_elem *te; struct nft_chain *chain; struct nft_table *table; - unsigned int base_seq; LIST_HEAD(adl); int err; @@ -9657,6 +9823,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) WRITE_ONCE(nft_net->base_seq, base_seq); + /* Bump gc counter, it becomes odd, this is the busy mark. */ + gc_seq = READ_ONCE(nft_net->gc_seq); + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); + /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); @@ -9764,6 +9934,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_DELSET: case NFT_MSG_DESTROYSET: + nft_trans_set(trans)->dead = 1; list_del_rcu(&nft_trans_set(trans)->list); nf_tables_set_notify(&trans->ctx, nft_trans_set(trans), trans->msg_type, GFP_KERNEL); @@ -9866,6 +10037,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_audit_log(&adl, nft_net->base_seq); + + WRITE_ONCE(nft_net->gc_seq, ++gc_seq); nf_tables_commit_release(net); return 0; @@ -10915,6 +11088,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); nft_net->base_seq = 1; + nft_net->gc_seq = 0; return 0; } @@ -10943,10 +11117,16 @@ static void __net_exit nf_tables_exit_net(struct net *net) WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } +static void nf_tables_exit_batch(struct list_head *net_exit_list) +{ + flush_work(&trans_gc_work); +} + static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .exit_batch = nf_tables_exit_batch, .id = &nf_tables_net_id, .size = sizeof(struct nftables_pernet), }; @@ -11018,6 +11198,7 @@ static void __exit nf_tables_module_exit(void) nft_chain_filter_fini(); nft_chain_route_fini(); unregister_pernet_subsys(&nf_tables_net_ops); + cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); rcu_barrier(); rhltable_destroy(&nft_objname_ht); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 0b73cb0e752f..cef5df846000 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -59,6 +59,8 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg, if (memcmp(nft_set_ext_key(&he->ext), x->key, x->set->klen)) return 1; + if (nft_set_elem_is_dead(&he->ext)) + return 1; if (nft_set_elem_expired(&he->ext)) return 1; if (!nft_set_elem_active(&he->ext, x->genmask)) @@ -188,7 +190,6 @@ static void nft_rhash_activate(const struct net *net, const struct nft_set *set, struct nft_rhash_elem *he = elem->priv; nft_set_elem_change_active(net, set, &he->ext); - nft_set_elem_clear_busy(&he->ext); } static bool nft_rhash_flush(const struct net *net, @@ -196,12 +197,9 @@ static bool nft_rhash_flush(const struct net *net, { struct nft_rhash_elem *he = priv; - if (!nft_set_elem_mark_busy(&he->ext) || - !nft_is_active(net, &he->ext)) { - nft_set_elem_change_active(net, set, &he->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &he->ext); + + return true; } static void *nft_rhash_deactivate(const struct net *net, @@ -218,9 +216,8 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_lock(); he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); - if (he != NULL && - !nft_rhash_flush(net, set, he)) - he = NULL; + if (he) + nft_set_elem_change_active(net, set, &he->ext); rcu_read_unlock(); @@ -252,7 +249,9 @@ static bool nft_rhash_delete(const struct nft_set *set, if (he == NULL) return false; - return rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params) == 0; + nft_set_elem_dead(&he->ext); + + return true; } static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, @@ -278,8 +277,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&he->ext)) - goto cont; if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; @@ -314,25 +311,48 @@ static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set, static void nft_rhash_gc(struct work_struct *work) { + struct nftables_pernet *nft_net; struct nft_set *set; struct nft_rhash_elem *he; struct nft_rhash *priv; - struct nft_set_gc_batch *gcb = NULL; struct rhashtable_iter hti; + struct nft_trans_gc *gc; + struct net *net; + u32 gc_seq; priv = container_of(work, struct nft_rhash, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); while ((he = rhashtable_walk_next(&hti))) { if (IS_ERR(he)) { - if (PTR_ERR(he) != -EAGAIN) - break; + if (PTR_ERR(he) != -EAGAIN) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } continue; } + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + + if (nft_set_elem_is_dead(&he->ext)) + goto dead_elem; + if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) && nft_rhash_expr_needs_gc_run(set, &he->ext)) goto needs_gc_run; @@ -340,26 +360,26 @@ static void nft_rhash_gc(struct work_struct *work) if (!nft_set_elem_expired(&he->ext)) continue; needs_gc_run: - if (nft_set_elem_mark_busy(&he->ext)) - continue; + nft_set_elem_dead(&he->ext); +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb == NULL) - break; - rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, he); + nft_trans_gc_elem_add(gc, he); } + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: + /* catchall list iteration requires rcu read side lock. */ rhashtable_walk_stop(&hti); rhashtable_walk_exit(&hti); - he = nft_set_catchall_gc(set); - if (he) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, he); - } - nft_set_gc_batch_complete(gcb); + if (gc) + nft_trans_gc_queue_async_done(gc); + +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } @@ -394,7 +414,7 @@ static int nft_rhash_init(const struct nft_set *set, return err; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rhash_gc); - if (set->flags & NFT_SET_TIMEOUT) + if (set->flags & (NFT_SET_TIMEOUT | NFT_SET_EVAL)) nft_rhash_gc_init(set); return 0; @@ -422,7 +442,6 @@ static void nft_rhash_destroy(const struct nft_ctx *ctx, }; cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)&rhash_ctx); } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 49915a2a58eb..a5b8301afe4a 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -566,8 +566,7 @@ next_match: goto out; if (last) { - if (nft_set_elem_expired(&f->mt[b].e->ext) || - (genmask && + if ((genmask && !nft_set_elem_active(&f->mt[b].e->ext, genmask))) goto next_match; @@ -601,8 +600,17 @@ out: static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + struct nft_pipapo_elem *ret; + + ret = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(ret)) + return ret; + + if (nft_set_elem_expired(&ret->ext)) + return ERR_PTR(-ENOENT); + + return ret; } /** @@ -1528,16 +1536,34 @@ static void pipapo_drop(struct nft_pipapo_match *m, } } +static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, + struct nft_pipapo_elem *e) + +{ + struct nft_set_elem elem = { + .priv = e, + }; + + nft_setelem_data_deactivate(net, set, &elem); +} + /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) { + struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); + struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; struct nft_pipapo_elem *e; + struct nft_trans_gc *gc; + + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; @@ -1561,13 +1587,20 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) f--; i--; e = f->mt[rulemap[i].to].e; - if (nft_set_elem_expired(&e->ext) && - !nft_set_elem_mark_busy(&e->ext)) { + + /* synchronous gc never fails, there is no need to set on + * NFT_SET_ELEM_DEAD_BIT. + */ + if (nft_set_elem_expired(&e->ext)) { priv->dirty = true; - pipapo_drop(m, rulemap); - rcu_barrier(); - nft_set_elem_destroy(set, e, true); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (!gc) + break; + + nft_pipapo_gc_deactivate(net, set, e); + pipapo_drop(m, rulemap); + nft_trans_gc_elem_add(gc, e); /* And check again current first rule, which is now the * first we haven't checked. @@ -1577,11 +1610,11 @@ static void pipapo_gc(const struct nft_set *set, struct nft_pipapo_match *m) } } - e = nft_set_catchall_gc(set); - if (e) - nft_set_elem_destroy(set, e, true); - - priv->last_gc = jiffies; + gc = nft_trans_gc_catchall(gc, 0); + if (gc) { + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } /** @@ -1706,7 +1739,6 @@ static void nft_pipapo_activate(const struct net *net, return; nft_set_elem_change_active(net, set, &e->ext); - nft_set_elem_clear_busy(&e->ext); } /** @@ -2005,8 +2037,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, goto cont; e = f->mt[r].e; - if (nft_set_elem_expired(&e->ext)) - goto cont; elem.priv = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 8d73fffd2d09..f9d4c8fcbbf8 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -46,6 +46,12 @@ static int nft_rbtree_cmp(const struct nft_set *set, set->klen); } +static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) +{ + return nft_set_elem_expired(&rbe->ext) || + nft_set_elem_is_dead(&rbe->ext); +} + static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext, unsigned int seq) @@ -80,7 +86,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set continue; } - if (nft_set_elem_expired(&rbe->ext)) + if (nft_rbtree_elem_expired(rbe)) return false; if (nft_rbtree_interval_end(rbe)) { @@ -98,7 +104,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_set_elem_expired(&interval->ext) && + !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -215,6 +221,18 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set_elem elem = { + .priv = rbe, + }; + + nft_setelem_data_deactivate(net, set, &elem); + rb_erase(&rbe->node, &priv->root); +} + static int nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, struct nft_rbtree_elem *rbe, @@ -222,11 +240,12 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); + struct net *net = read_pnet(&set->net); struct nft_rbtree_elem *rbe_prev; - struct nft_set_gc_batch *gcb; + struct nft_trans_gc *gc; - gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); - if (!gcb) + gc = nft_trans_gc_alloc(set, 0, GFP_ATOMIC); + if (!gc) return -ENOMEM; /* search for end interval coming before this element. @@ -244,17 +263,28 @@ static int nft_rbtree_gc_elem(const struct nft_set *__set, if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + nft_rbtree_gc_remove(net, set, priv, rbe_prev); - rb_erase(&rbe_prev->node, &priv->root); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_prev); + /* There is always room in this trans gc for this element, + * memory allocation never actually happens, hence, the warning + * splat in such case. No need to set NFT_SET_ELEM_DEAD_BIT, + * this is synchronous gc which never fails. + */ + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe_prev); } - rb_erase(&rbe->node, &priv->root); - atomic_dec(&set->nelems); + nft_rbtree_gc_remove(net, set, priv, rbe); + gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); + if (WARN_ON_ONCE(!gc)) + return -ENOMEM; + + nft_trans_gc_elem_add(gc, rbe); - nft_set_gc_batch_add(gcb, rbe); - nft_set_gc_batch_complete(gcb); + nft_trans_gc_queue_sync_done(gc); return 0; } @@ -482,7 +512,6 @@ static void nft_rbtree_activate(const struct net *net, struct nft_rbtree_elem *rbe = elem->priv; nft_set_elem_change_active(net, set, &rbe->ext); - nft_set_elem_clear_busy(&rbe->ext); } static bool nft_rbtree_flush(const struct net *net, @@ -490,12 +519,9 @@ static bool nft_rbtree_flush(const struct net *net, { struct nft_rbtree_elem *rbe = priv; - if (!nft_set_elem_mark_busy(&rbe->ext) || - !nft_is_active(net, &rbe->ext)) { - nft_set_elem_change_active(net, set, &rbe->ext); - return true; - } - return false; + nft_set_elem_change_active(net, set, &rbe->ext); + + return true; } static void *nft_rbtree_deactivate(const struct net *net, @@ -552,8 +578,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; - if (nft_set_elem_expired(&rbe->ext)) - goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; @@ -572,26 +596,40 @@ cont: static void nft_rbtree_gc(struct work_struct *work) { - struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL; - struct nft_set_gc_batch *gcb = NULL; + struct nft_rbtree_elem *rbe, *rbe_end = NULL; + struct nftables_pernet *nft_net; struct nft_rbtree *priv; + struct nft_trans_gc *gc; struct rb_node *node; struct nft_set *set; + unsigned int gc_seq; struct net *net; - u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); - genmask = nft_genmask_cur(net); + nft_net = nft_pernet(net); + gc_seq = READ_ONCE(nft_net->gc_seq); + + gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + if (!gc) + goto done; write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + + /* Ruleset has been updated, try later. */ + if (READ_ONCE(nft_net->gc_seq) != gc_seq) { + nft_trans_gc_destroy(gc); + gc = NULL; + goto try_later; + } + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (!nft_set_elem_active(&rbe->ext, genmask)) - continue; + if (nft_set_elem_is_dead(&rbe->ext)) + goto dead_elem; /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is @@ -604,46 +642,36 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) { - rbe_end = NULL; + nft_set_elem_dead(&rbe->ext); + + if (!rbe_end) continue; - } - if (rbe_prev) { - rb_erase(&rbe_prev->node, &priv->root); - rbe_prev = NULL; - } - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (!gcb) - break; + nft_set_elem_dead(&rbe_end->ext); - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe); - rbe_prev = rbe; + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; - if (rbe_end) { - atomic_dec(&set->nelems); - nft_set_gc_batch_add(gcb, rbe_end); - rb_erase(&rbe_end->node, &priv->root); - rbe_end = NULL; - } - node = rb_next(node); - if (!node) - break; + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; +dead_elem: + gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + if (!gc) + goto try_later; + + nft_trans_gc_elem_add(gc, rbe); } - if (rbe_prev) - rb_erase(&rbe_prev->node, &priv->root); + + gc = nft_trans_gc_catchall(gc, gc_seq); + +try_later: write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); - rbe = nft_set_catchall_gc(set); - if (rbe) { - gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); - if (gcb) - nft_set_gc_batch_add(gcb, rbe); - } - nft_set_gc_batch_complete(gcb); - + if (gc) + nft_trans_gc_queue_async_done(gc); +done: queue_delayed_work(system_power_efficient_wq, &priv->gc_work, nft_set_gc_interval(set)); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a4631cb457a9..a2935bd18ed9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -401,18 +401,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; + /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: - h.h1->tp_status = status; + WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: - h.h2->tp_status = status; + WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: - h.h3->tp_status = status; + WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: @@ -429,17 +431,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame) smp_rmb(); + /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ + h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); - return h.h1->tp_status; + return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); - return h.h2->tp_status; + return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); - return h.h3->tp_status; + return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0c013d2b5d8f..f5834af5fad5 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -378,8 +378,8 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_state = SMC_INIT; sk->sk_destruct = smc_destruct; sk->sk_protocol = protocol; - WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(net->smc.sysctl_wmem)); - WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(net->smc.sysctl_rmem)); + WRITE_ONCE(sk->sk_sndbuf, 2 * READ_ONCE(net->smc.sysctl_wmem)); + WRITE_ONCE(sk->sk_rcvbuf, 2 * READ_ONCE(net->smc.sysctl_rmem)); smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); INIT_WORK(&smc->connect_work, smc_connect_work); @@ -436,13 +436,60 @@ out: return rc; } +/* copy only relevant settings and flags of SOL_SOCKET level from smc to + * clc socket (since smc is not called for these options from net/core) + */ + +#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ + (1UL << SOCK_KEEPOPEN) | \ + (1UL << SOCK_LINGER) | \ + (1UL << SOCK_BROADCAST) | \ + (1UL << SOCK_TIMESTAMP) | \ + (1UL << SOCK_DBG) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_RCVTSTAMPNS) | \ + (1UL << SOCK_LOCALROUTE) | \ + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ + (1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_WIFI_STATUS) | \ + (1UL << SOCK_NOFCS) | \ + (1UL << SOCK_FILTER_LOCKED) | \ + (1UL << SOCK_TSTAMP_NEW)) + +/* if set, use value set by setsockopt() - else use IPv4 or SMC sysctl value */ +static void smc_adjust_sock_bufsizes(struct sock *nsk, struct sock *osk, + unsigned long mask) +{ + struct net *nnet = sock_net(nsk); + + nsk->sk_userlocks = osk->sk_userlocks; + if (osk->sk_userlocks & SOCK_SNDBUF_LOCK) { + nsk->sk_sndbuf = osk->sk_sndbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_sndbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_wmem[1])); + else + WRITE_ONCE(nsk->sk_sndbuf, + 2 * READ_ONCE(nnet->smc.sysctl_wmem)); + } + if (osk->sk_userlocks & SOCK_RCVBUF_LOCK) { + nsk->sk_rcvbuf = osk->sk_rcvbuf; + } else { + if (mask == SK_FLAGS_SMC_TO_CLC) + WRITE_ONCE(nsk->sk_rcvbuf, + READ_ONCE(nnet->ipv4.sysctl_tcp_rmem[1])); + else + WRITE_ONCE(nsk->sk_rcvbuf, + 2 * READ_ONCE(nnet->smc.sysctl_rmem)); + } +} + static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, unsigned long mask) { /* options we don't get control via setsockopt for */ nsk->sk_type = osk->sk_type; - nsk->sk_sndbuf = osk->sk_sndbuf; - nsk->sk_rcvbuf = osk->sk_rcvbuf; nsk->sk_sndtimeo = osk->sk_sndtimeo; nsk->sk_rcvtimeo = osk->sk_rcvtimeo; nsk->sk_mark = READ_ONCE(osk->sk_mark); @@ -453,26 +500,10 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, nsk->sk_flags &= ~mask; nsk->sk_flags |= osk->sk_flags & mask; + + smc_adjust_sock_bufsizes(nsk, osk, mask); } -#define SK_FLAGS_SMC_TO_CLC ((1UL << SOCK_URGINLINE) | \ - (1UL << SOCK_KEEPOPEN) | \ - (1UL << SOCK_LINGER) | \ - (1UL << SOCK_BROADCAST) | \ - (1UL << SOCK_TIMESTAMP) | \ - (1UL << SOCK_DBG) | \ - (1UL << SOCK_RCVTSTAMP) | \ - (1UL << SOCK_RCVTSTAMPNS) | \ - (1UL << SOCK_LOCALROUTE) | \ - (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ - (1UL << SOCK_RXQ_OVFL) | \ - (1UL << SOCK_WIFI_STATUS) | \ - (1UL << SOCK_NOFCS) | \ - (1UL << SOCK_FILTER_LOCKED) | \ - (1UL << SOCK_TSTAMP_NEW)) -/* copy only relevant settings and flags of SOL_SOCKET level from smc to - * clc socket (since smc is not called for these options from net/core) - */ static void smc_copy_sock_settings_to_clc(struct smc_sock *smc) { smc_copy_sock_settings(smc->clcsock->sk, &smc->sk, SK_FLAGS_SMC_TO_CLC); @@ -2479,8 +2510,6 @@ static void smc_tcp_listen_work(struct work_struct *work) sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); - new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf; - new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf; sock_hold(&new_smc->sk); /* sock_put in passive closing */ if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work)) sock_put(&new_smc->sk); diff --git a/net/smc/smc.h b/net/smc/smc.h index 2eeea4cdc718..1f2b912c43d1 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -161,7 +161,7 @@ struct smc_connection { struct smc_buf_desc *sndbuf_desc; /* send buffer descriptor */ struct smc_buf_desc *rmb_desc; /* RMBE descriptor */ - int rmbe_size_short;/* compressed notation */ + int rmbe_size_comp; /* compressed notation */ int rmbe_update_limit; /* lower limit for consumer * cursor update diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index b9b8b07aa702..c90d9e5dda54 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -1007,7 +1007,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->d0.gid = conn->lgr->smcd->ops->get_local_gid(conn->lgr->smcd); clc->d0.token = conn->rmb_desc->token; - clc->d0.dmbe_size = conn->rmbe_size_short; + clc->d0.dmbe_size = conn->rmbe_size_comp; clc->d0.dmbe_idx = 0; memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE); if (version == SMC_V1) { @@ -1050,7 +1050,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu); break; } - clc->r0.rmbe_size = conn->rmbe_size_short; + clc->r0.rmbe_size = conn->rmbe_size_comp; clc->r0.rmb_dma_addr = conn->rmb_desc->is_vm ? cpu_to_be64((uintptr_t)conn->rmb_desc->cpu_addr) : cpu_to_be64((u64)sg_dma_address diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 3f465faf2b68..6b78075404d7 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -2309,31 +2309,30 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_connection *conn = &smc->conn; struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; - int bufsize, bufsize_short; + int bufsize, bufsize_comp; struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - int sk_buf_size; if (is_rmb) /* use socket recv buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_rcvbuf; + bufsize = smc->sk.sk_rcvbuf / 2; else /* use socket send buffer size (w/o overhead) as start value */ - sk_buf_size = smc->sk.sk_sndbuf; + bufsize = smc->sk.sk_sndbuf / 2; - for (bufsize_short = smc_compress_bufsize(sk_buf_size, is_smcd, is_rmb); - bufsize_short >= 0; bufsize_short--) { + for (bufsize_comp = smc_compress_bufsize(bufsize, is_smcd, is_rmb); + bufsize_comp >= 0; bufsize_comp--) { if (is_rmb) { lock = &lgr->rmbs_lock; - buf_list = &lgr->rmbs[bufsize_short]; + buf_list = &lgr->rmbs[bufsize_comp]; } else { lock = &lgr->sndbufs_lock; - buf_list = &lgr->sndbufs[bufsize_short]; + buf_list = &lgr->sndbufs[bufsize_comp]; } - bufsize = smc_uncompress_bufsize(bufsize_short); + bufsize = smc_uncompress_bufsize(bufsize_comp); /* check for reusable slot in the link group */ - buf_desc = smc_buf_get_slot(bufsize_short, lock, buf_list); + buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list); if (buf_desc) { buf_desc->is_dma_need_sync = 0; SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); @@ -2377,8 +2376,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) if (is_rmb) { conn->rmb_desc = buf_desc; - conn->rmbe_size_short = bufsize_short; - smc->sk.sk_rcvbuf = bufsize; + conn->rmbe_size_comp = bufsize_comp; + smc->sk.sk_rcvbuf = bufsize * 2; atomic_set(&conn->bytes_to_rcv, 0); conn->rmbe_update_limit = smc_rmb_wnd_update_limit(buf_desc->len); @@ -2386,7 +2385,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */ } else { conn->sndbuf_desc = buf_desc; - smc->sk.sk_sndbuf = bufsize; + smc->sk.sk_sndbuf = bufsize * 2; atomic_set(&conn->sndbuf_space, bufsize); } return 0; diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index b6f79fabb9d3..0b2a957ca5f5 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -21,6 +21,10 @@ static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; +static int max_sndbuf = INT_MAX / 2; +static int max_rcvbuf = INT_MAX / 2; +static const int net_smc_wmem_init = (64 * 1024); +static const int net_smc_rmem_init = (64 * 1024); static struct ctl_table smc_table[] = { { @@ -53,6 +57,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_sndbuf, + .extra2 = &max_sndbuf, }, { .procname = "rmem", @@ -61,6 +66,7 @@ static struct ctl_table smc_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &min_rcvbuf, + .extra2 = &max_rcvbuf, }, { } }; @@ -88,8 +94,8 @@ int __net_init smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_smcr_buf_type = SMCR_PHYS_CONT_BUFS; net->smc.sysctl_smcr_testlink_time = SMC_LLC_TESTLINK_DEFAULT_TIME; - WRITE_ONCE(net->smc.sysctl_wmem, READ_ONCE(net->ipv4.sysctl_tcp_wmem[1])); - WRITE_ONCE(net->smc.sysctl_rmem, READ_ONCE(net->ipv4.sysctl_tcp_rmem[1])); + WRITE_ONCE(net->smc.sysctl_wmem, net_smc_wmem_init); + WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); return 0; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 2021fe557e50..529101eb20bd 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -52,6 +52,8 @@ static LIST_HEAD(tls_device_list); static LIST_HEAD(tls_device_down_list); static DEFINE_SPINLOCK(tls_device_lock); +static struct page *dummy_page; + static void tls_device_free_ctx(struct tls_context *ctx) { if (ctx->tx_conf == TLS_HW) { @@ -312,36 +314,33 @@ static int tls_push_record(struct sock *sk, return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); } -static int tls_device_record_close(struct sock *sk, - struct tls_context *ctx, - struct tls_record_info *record, - struct page_frag *pfrag, - unsigned char record_type) +static void tls_device_record_close(struct sock *sk, + struct tls_context *ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + unsigned char record_type) { struct tls_prot_info *prot = &ctx->prot_info; - int ret; + struct page_frag dummy_tag_frag; /* append tag * device will fill in the tag, we just need to append a placeholder * use socket memory to improve coalescing (re-using a single buffer * increases frag count) - * if we can't allocate memory now, steal some back from data + * if we can't allocate memory now use the dummy page */ - if (likely(skb_page_frag_refill(prot->tag_size, pfrag, - sk->sk_allocation))) { - ret = 0; - tls_append_frag(record, pfrag, prot->tag_size); - } else { - ret = prot->tag_size; - if (record->len <= prot->overhead_size) - return -ENOMEM; + if (unlikely(pfrag->size - pfrag->offset < prot->tag_size) && + !skb_page_frag_refill(prot->tag_size, pfrag, sk->sk_allocation)) { + dummy_tag_frag.page = dummy_page; + dummy_tag_frag.offset = 0; + pfrag = &dummy_tag_frag; } + tls_append_frag(record, pfrag, prot->tag_size); /* fill prepend */ tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]), record->len - prot->overhead_size, record_type); - return ret; } static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx, @@ -541,18 +540,8 @@ last_record: if (done || record->len >= max_open_record_len || (record->num_frags >= MAX_SKB_FRAGS - 1)) { - rc = tls_device_record_close(sk, tls_ctx, record, - pfrag, record_type); - if (rc) { - if (rc > 0) { - size += rc; - } else { - size = orig_size; - destroy_record(record); - ctx->open_record = NULL; - break; - } - } + tls_device_record_close(sk, tls_ctx, record, + pfrag, record_type); rc = tls_push_record(sk, tls_ctx, @@ -1450,14 +1439,26 @@ int __init tls_device_init(void) { int err; - destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); - if (!destruct_wq) + dummy_page = alloc_page(GFP_KERNEL); + if (!dummy_page) return -ENOMEM; + destruct_wq = alloc_workqueue("ktls_device_destruct", 0, 0); + if (!destruct_wq) { + err = -ENOMEM; + goto err_free_dummy; + } + err = register_netdevice_notifier(&tls_dev_notifier); if (err) - destroy_workqueue(destruct_wq); + goto err_destroy_wq; + return 0; + +err_destroy_wq: + destroy_workqueue(destruct_wq); +err_free_dummy: + put_page(dummy_page); return err; } @@ -1466,4 +1467,5 @@ void __exit tls_device_cleanup(void) unregister_netdevice_notifier(&tls_dev_notifier); destroy_workqueue(destruct_wq); clean_acked_data_flush(); + put_page(dummy_page); } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b6896126bb92..4a8ee2f6badb 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -139,9 +139,6 @@ int tls_push_sg(struct sock *sk, ctx->splicing_pages = true; while (1) { - if (sg_is_last(sg)) - msg.msg_flags = flags; - /* is sending application-limited? */ tcp_rate_check_app_limited(sk); p = sg_page(sg); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0da2e6a2a7ea..8bcf8e293308 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5430,8 +5430,11 @@ nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) if (!wiphy->mbssid_max_interfaces) return ERR_PTR(-EINVAL); - nla_for_each_nested(nl_elems, attrs, rem_elems) + nla_for_each_nested(nl_elems, attrs, rem_elems) { + if (num_elems >= 255) + return ERR_PTR(-EINVAL); num_elems++; + } elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); if (!elems) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b89adb52a977..10ea85c03147 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -994,6 +994,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) err = xp_alloc_tx_descs(xs->pool, xs); if (err) { xp_put_pool(xs->pool); + xs->pool = NULL; sockfd_put(sock); goto out_unlock; } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index b4f6f3a50ae5..5674a9d0cacf 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -869,6 +869,77 @@ static void test_msg_redir_to_listening(struct test_sockmap_listen *skel, xbpf_prog_detach2(verdict, sock_map, BPF_SK_MSG_VERDICT); } +static void redir_partial(int family, int sotype, int sock_map, int parser_map) +{ + int s, c0, c1, p0, p1; + int err, n, key, value; + char buf[] = "abc"; + + key = 0; + value = sizeof(buf) - 1; + err = xbpf_map_update_elem(parser_map, &key, &value, 0); + if (err) + return; + + s = socket_loopback(family, sotype | SOCK_NONBLOCK); + if (s < 0) + goto clean_parser_map; + + err = create_socket_pairs(s, family, sotype, &c0, &c1, &p0, &p1); + if (err) + goto close_srv; + + err = add_to_sockmap(sock_map, p0, p1); + if (err) + goto close; + + n = xsend(c1, buf, sizeof(buf), 0); + if (n < sizeof(buf)) + FAIL("incomplete write"); + + n = xrecv_nonblock(c0, buf, sizeof(buf), 0); + if (n != sizeof(buf) - 1) + FAIL("expect %zu, received %d", sizeof(buf) - 1, n); + +close: + xclose(c0); + xclose(p0); + xclose(c1); + xclose(p1); +close_srv: + xclose(s); + +clean_parser_map: + key = 0; + value = 0; + xbpf_map_update_elem(parser_map, &key, &value, 0); +} + +static void test_skb_redir_partial(struct test_sockmap_listen *skel, + struct bpf_map *inner_map, int family, + int sotype) +{ + int verdict = bpf_program__fd(skel->progs.prog_stream_verdict); + int parser = bpf_program__fd(skel->progs.prog_stream_parser); + int parser_map = bpf_map__fd(skel->maps.parser_map); + int sock_map = bpf_map__fd(inner_map); + int err; + + err = xbpf_prog_attach(parser, sock_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (err) + return; + + err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (err) + goto detach; + + redir_partial(family, sotype, sock_map, parser_map); + + xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_STREAM_VERDICT); +detach: + xbpf_prog_detach2(parser, sock_map, BPF_SK_SKB_STREAM_PARSER); +} + static void test_reuseport_select_listening(int family, int sotype, int sock_map, int verd_map, int reuseport_prog) @@ -1243,6 +1314,7 @@ static void test_redir(struct test_sockmap_listen *skel, struct bpf_map *map, } tests[] = { TEST(test_skb_redir_to_connected), TEST(test_skb_redir_to_listening), + TEST(test_skb_redir_partial), TEST(test_msg_redir_to_connected), TEST(test_msg_redir_to_listening), }; @@ -1432,7 +1504,7 @@ static void vsock_unix_redir_connectible(int sock_mapfd, int verd_mapfd, if (n < 1) goto out; - n = recv(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), MSG_DONTWAIT); + n = xrecv_nonblock(mode == REDIR_INGRESS ? u0 : u1, &b, sizeof(b), 0); if (n < 0) FAIL("%s: recv() err, errno=%d", log_prefix, errno); if (n == 0) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c index 325c9f193432..464d35bd57c7 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c @@ -28,12 +28,26 @@ struct { __type(value, unsigned int); } verdict_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} parser_map SEC(".maps"); + bool test_sockmap = false; /* toggled by user-space */ bool test_ingress = false; /* toggled by user-space */ SEC("sk_skb/stream_parser") int prog_stream_parser(struct __sk_buff *skb) { + int *value; + __u32 key = 0; + + value = bpf_map_lookup_elem(&parser_map, &key); + if (value && *value) + return *value; + return skb->len; } diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0f5e88c8f4ff..df8d90b51867 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1981,6 +1981,11 @@ basic() run_cmd "$IP link set dev lo up" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) blackhole" + run_cmd "timeout 5 $IP nexthop" + log_test $? 0 "Maximum nexthop ID dump" + # # groups # @@ -2201,6 +2206,11 @@ basic_res() run_cmd "$IP nexthop bucket list fdb" log_test $? 255 "Dump all nexthop buckets with invalid 'fdb' keyword" + # Dump should not loop endlessly when maximum nexthop ID is configured. + run_cmd "$IP nexthop add id $((2**32-1)) group 1/2 type resilient buckets 4" + run_cmd "timeout 5 $IP nexthop bucket" + log_test $? 0 "Maximum nexthop ID dump" + # # resilient nexthop buckets get requests # diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index ae3f9462a2b6..d0c6c499d5da 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -617,7 +617,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not added as \"permanent\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "\"permanent\" entry has a pending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -626,7 +626,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not added as \"temp\" when should" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "\"temp\" entry has an unpending group timer" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -659,7 +659,7 @@ __cfg_test_port_ip_sg() grep -q "permanent" check_err $? "Entry not marked as \"permanent\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_err $? "Entry has a pending group timer after replace" bridge mdb replace dev br0 port $swp1 $grp_key vid 10 temp @@ -667,7 +667,7 @@ __cfg_test_port_ip_sg() grep -q "temp" check_err $? "Entry not marked as \"temp\" after replace" bridge -d -s mdb show dev br0 vid 10 | grep "$grp_key" | \ - grep -q "0.00" + grep -q " 0.00" check_fail $? "Entry has an unpending group timer after replace" bridge mdb del dev br0 port $swp1 $grp_key vid 10 @@ -850,6 +850,7 @@ cfg_test() __fwd_test_host_ip() { local grp=$1; shift + local dmac=$1; shift local src=$1; shift local mode=$1; shift local name @@ -872,27 +873,27 @@ __fwd_test_host_ip() # Packet should only be flooded to multicast router ports when there is # no matching MDB entry. The bridge is not configured as a multicast # router port. - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after flood" # Install a regular port group entry and expect the packet to not be # locally received. bridge mdb add dev br0 port $swp2 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 0 check_err $? "Packet locally received after installing a regular entry" # Add a host entry and expect the packet to be locally received. bridge mdb add dev br0 port br0 grp $grp temp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet not locally received after adding a host entry" # Remove the host entry and expect the packet to not be locally # received. bridge mdb del dev br0 port br0 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $src -B $grp -t udp -q tc_check_packets "dev br0 ingress" 1 1 check_err $? "Packet locally received after removing a host entry" @@ -905,8 +906,8 @@ __fwd_test_host_ip() fwd_test_host_ip() { - __fwd_test_host_ip "239.1.1.1" "192.0.2.1" "-4" - __fwd_test_host_ip "ff0e::1" "2001:db8:1::1" "-6" + __fwd_test_host_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "-4" + __fwd_test_host_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "-6" } fwd_test_host_l2() @@ -966,6 +967,7 @@ fwd_test_host() __fwd_test_port_ip() { local grp=$1; shift + local dmac=$1; shift local valid_src=$1; shift local invalid_src=$1; shift local mode=$1; shift @@ -999,43 +1001,43 @@ __fwd_test_port_ip() vlan_ethtype $eth_type vlan_id 10 dst_ip $grp \ src_ip $invalid_src action drop - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 0 check_err $? "Packet from valid source received on H2 before adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 before adding entry" bridge mdb add dev br0 port $swp2 grp $grp vid 10 \ filter_mode $filter_mode source_list $src_list - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 1 check_err $? "Packet from valid source not received on H2 after adding entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 0 check_err $? "Packet from invalid source received on H2 after adding entry" bridge mdb replace dev br0 port $swp2 grp $grp vid 10 \ filter_mode exclude - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source not received on H2 after allowing all sources" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source not received on H2 after allowing all sources" bridge mdb del dev br0 port $swp2 grp $grp vid 10 - $MZ $mode $h1.10 -c 1 -p 128 -A $valid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $valid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 1 2 check_err $? "Packet from valid source received on H2 after deleting entry" - $MZ $mode $h1.10 -c 1 -p 128 -A $invalid_src -B $grp -t udp -q + $MZ $mode $h1.10 -a own -b $dmac -c 1 -p 128 -A $invalid_src -B $grp -t udp -q tc_check_packets "dev $h2 ingress" 2 1 check_err $? "Packet from invalid source received on H2 after deleting entry" @@ -1047,11 +1049,11 @@ __fwd_test_port_ip() fwd_test_port_ip() { - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "exclude" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "exclude" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "exclude" - __fwd_test_port_ip "239.1.1.1" "192.0.2.1" "192.0.2.2" "-4" "include" - __fwd_test_port_ip "ff0e::1" "2001:db8:1::1" "2001:db8:1::2" "-6" \ + __fwd_test_port_ip "239.1.1.1" "01:00:5e:01:01:01" "192.0.2.1" "192.0.2.2" "-4" "include" + __fwd_test_port_ip "ff0e::1" "33:33:00:00:00:01" "2001:db8:1::1" "2001:db8:1::2" "-6" \ "include" } @@ -1127,7 +1129,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -c 1 -a own -b 01:00:5e:01:01:01 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 @@ -1140,7 +1142,7 @@ ctrl_igmpv3_is_in_test() filter_mode include source_list 192.0.2.1 # IS_IN ( 192.0.2.2 ) - $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ + $MZ $h1.10 -a own -b 01:00:5e:01:01:01 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ @@ -1167,7 +1169,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ @@ -1181,7 +1183,7 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) - $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ + $MZ -6 $h1.10 -a own -b 33:33:00:00:00:01 -c 1 -A fe80::1 -B ff0e::1 \ -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ @@ -1206,6 +1208,11 @@ ctrl_test() ctrl_mldv2_is_in_test } +if ! bridge mdb help 2>&1 | grep -q "replace"; then + echo "SKIP: iproute2 too old, missing bridge mdb replace support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh index ae255b662ba3..3da9d93ab36f 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -252,7 +252,8 @@ ctl4_entries_add() local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + local dmac=01:00:5e:01:01:$(printf "%02x" $grp) + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B $GRP \ -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q sleep 1 @@ -272,7 +273,8 @@ ctl4_entries_del() local peer=$(locus_dev_peer $locus) local GRP=239.1.1.${grp} - $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + local dmac=01:00:5e:00:00:02 + $MZ $peer -a own -b $dmac -c 1 -A 192.0.2.1 -B 224.0.0.2 \ -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP @@ -289,8 +291,10 @@ ctl6_entries_add() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv2_is_in_get $SIP $GRP $IPs) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) @@ -310,8 +314,10 @@ ctl6_entries_del() local peer=$(locus_dev_peer $locus) local SIP=fe80::1 local GRP=ff0e::${grp} + local dmac=33:33:00:00:00:$(printf "%02x" $grp) local p=$(mldv1_done_get $SIP $GRP) - $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + $MZ -6 $peer -a own -b $dmac -c 1 -A $SIP -B $GRP \ + -t ip hop=1,next=0,p="$p" -q sleep 1 ! bridge mdb show dev br0 | grep -q $GRP } @@ -1328,6 +1334,11 @@ test_8021qvs() switch_destroy } +if ! bridge link help 2>&1 | grep -q "mcast_max_groups"; then + echo "SKIP: iproute2 too old, missing bridge \"mcast_max_groups\" support" + exit $ksft_skip +fi + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool.sh b/tools/testing/selftests/net/forwarding/ethtool.sh index dbb9fcf759e0..aa2eafb7b243 100755 --- a/tools/testing/selftests/net/forwarding/ethtool.sh +++ b/tools/testing/selftests/net/forwarding/ethtool.sh @@ -286,6 +286,8 @@ different_speeds_autoneg_on() ethtool -s $h1 autoneg on } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh index 072faa77f53b..17f89c3b7c02 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_extended_state.sh @@ -108,6 +108,8 @@ no_cable() ip link set dev $swp3 down } +skip_on_veth + setup_prepare tests_run diff --git a/tools/testing/selftests/net/forwarding/ethtool_mm.sh b/tools/testing/selftests/net/forwarding/ethtool_mm.sh index c580ad623848..39e736f30322 100755 --- a/tools/testing/selftests/net/forwarding/ethtool_mm.sh +++ b/tools/testing/selftests/net/forwarding/ethtool_mm.sh @@ -258,11 +258,6 @@ h2_destroy() setup_prepare() { - check_ethtool_mm_support - check_tc_fp_support - require_command lldptool - bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" - h1=${NETIFS[p1]} h2=${NETIFS[p2]} @@ -278,6 +273,19 @@ cleanup() h1_destroy } +check_ethtool_mm_support +check_tc_fp_support +require_command lldptool +bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually" + +for netif in ${NETIFS[@]}; do + ethtool --show-mm $netif 2>&1 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: $netif does not support MAC Merge" + exit $ksft_skip + fi +done + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh index eb9ec4a68f84..7594bbb49029 100755 --- a/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh +++ b/tools/testing/selftests/net/forwarding/hw_stats_l3_gre.sh @@ -99,6 +99,8 @@ test_stats_rx() test_stats g2a rx } +skip_on_veth + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh index 9f5b3e2e5e95..49fa94b53a1c 100755 --- a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh +++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh @@ -14,6 +14,8 @@ ALL_TESTS=" NUM_NETIFS=4 source lib.sh +require_command $TROUTE6 + h1_create() { simple_if_init $h1 2001:1:1::2/64 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9ddb68dd6a08..f69015bf2dea 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -30,6 +30,7 @@ REQUIRE_MZ=${REQUIRE_MZ:=yes} REQUIRE_MTOOLS=${REQUIRE_MTOOLS:=no} STABLE_MAC_ADDRS=${STABLE_MAC_ADDRS:=no} TCPDUMP_EXTRA_FLAGS=${TCPDUMP_EXTRA_FLAGS:=} +TROUTE6=${TROUTE6:=traceroute6} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -163,6 +164,17 @@ check_port_mab_support() fi } +skip_on_veth() +{ + local kind=$(ip -j -d link show dev ${NETIFS[p1]} | + jq -r '.[].linkinfo.info_kind') + + if [[ $kind == veth ]]; then + echo "SKIP: Test cannot be run with veth pairs" + exit $ksft_skip + fi +} + if [[ "$(id -u)" -ne 0 ]]; then echo "SKIP: need root privileges" exit $ksft_skip @@ -225,6 +237,11 @@ create_netif_veth() for ((i = 1; i <= NUM_NETIFS; ++i)); do local j=$((i+1)) + if [ -z ${NETIFS[p$i]} ]; then + echo "SKIP: Cannot create interface. Name not specified" + exit $ksft_skip + fi + ip link show dev ${NETIFS[p$i]} &> /dev/null if [[ $? -ne 0 ]]; then ip link add ${NETIFS[p$i]} type veth \ diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings new file mode 100644 index 000000000000..e7b9417537fb --- /dev/null +++ b/tools/testing/selftests/net/forwarding/settings @@ -0,0 +1 @@ +timeout=0 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index a96cff8e7219..b0f5e55d2d0b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -9,6 +9,8 @@ NUM_NETIFS=4 source tc_common.sh source lib.sh +require_command ncat + tcflags="skip_hw" h1_create() @@ -220,9 +222,9 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & local rpid=$! - ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 wait -n $rpid cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 check_err $? "server output check failed" diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 683711f41aa9..b1daad19b01e 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -52,8 +52,8 @@ match_dst_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower @@ -78,8 +78,8 @@ match_src_mac_test() tc_check_packets "dev $h2 ingress" 101 1 check_fail $? "Matched on a wrong filter" - tc_check_packets "dev $h2 ingress" 102 1 - check_err $? "Did not match on correct filter" + tc_check_packets "dev $h2 ingress" 102 0 + check_fail $? "Did not match on correct filter" tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower diff --git a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh index e22c2d28b6eb..20a7cb7222b8 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_l2_miss.sh @@ -127,6 +127,7 @@ test_l2_miss_multicast_common() local proto=$1; shift local sip=$1; shift local dip=$1; shift + local dmac=$1; shift local mode=$1; shift local name=$1; shift @@ -142,7 +143,7 @@ test_l2_miss_multicast_common() action pass # Before adding MDB entry. - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was not hit before adding MDB entry" @@ -153,7 +154,7 @@ test_l2_miss_multicast_common() # Adding MDB entry. bridge mdb replace dev br1 port $swp2 grp $dip permanent - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 1 check_err $? "Unregistered multicast filter was hit after adding MDB entry" @@ -164,7 +165,7 @@ test_l2_miss_multicast_common() # Deleting MDB entry. bridge mdb del dev br1 port $swp2 grp $dip - $MZ $mode $h1 -t ip -A $sip -B $dip -c 1 -p 100 -q + $MZ $mode $h1 -a own -b $dmac -t ip -A $sip -B $dip -c 1 -p 100 -q tc_check_packets "dev $swp2 egress" 101 2 check_err $? "Unregistered multicast filter was not hit after deleting MDB entry" @@ -183,10 +184,11 @@ test_l2_miss_multicast_ipv4() local proto="ipv4" local sip=192.0.2.1 local dip=239.1.1.1 + local dmac=01:00:5e:01:01:01 local mode="-4" local name="IPv4" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast_ipv6() @@ -194,10 +196,11 @@ test_l2_miss_multicast_ipv6() local proto="ipv6" local sip=2001:db8:1::1 local dip=ff0e::1 + local dmac=33:33:00:00:00:01 local mode="-6" local name="IPv6" - test_l2_miss_multicast_common $proto $sip $dip $mode $name + test_l2_miss_multicast_common $proto $sip $dip $dmac $mode $name } test_l2_miss_multicast() diff --git a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh index 5ac184d51809..5a5dd9034819 100755 --- a/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh +++ b/tools/testing/selftests/net/forwarding/tc_tunnel_key.sh @@ -104,11 +104,14 @@ tunnel_key_nofrag_test() local i tc filter add dev $swp1 ingress protocol ip pref 100 handle 100 \ - flower ip_flags nofrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofrag action drop tc filter add dev $swp1 ingress protocol ip pref 101 handle 101 \ - flower ip_flags firstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags firstfrag action drop tc filter add dev $swp1 ingress protocol ip pref 102 handle 102 \ - flower ip_flags nofirstfrag action drop + flower src_ip 192.0.2.1 dst_ip 192.0.2.2 ip_proto udp \ + ip_flags nofirstfrag action drop # test 'nofrag' set tc filter add dev h1-et egress protocol all pref 1 handle 1 matchall $tcflags \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 3c2096ac97ef..d01b73a8ed0f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -705,6 +705,7 @@ pm_nl_del_endpoint() local addr=$3 if [ $ip_mptcp -eq 1 ]; then + [ $id -ne 0 ] && addr='' ip -n $ns mptcp endpoint delete id $id $addr else ip netns exec $ns ./pm_nl_ctl del $id $addr @@ -795,10 +796,11 @@ pm_nl_check_endpoint() fi if [ $ip_mptcp -eq 1 ]; then + # get line and trim trailing whitespace line=$(ip -n $ns mptcp endpoint show $id) + line="${line% }" # the dump order is: address id flags port dev - expected_line="$addr" - [ -n "$addr" ] && expected_line="$expected_line $addr" + [ -n "$addr" ] && expected_line="$addr" expected_line="$expected_line $id" [ -n "$_flags" ] && expected_line="$expected_line ${_flags//","/" "}" [ -n "$dev" ] && expected_line="$expected_line $dev" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index dfe3d287f01d..f838dd370f6a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -361,6 +361,7 @@ err_buf= tcpdump_pids= nettest_pids= socat_pids= +tmpoutfile= err() { err_buf="${err_buf}${1} @@ -951,6 +952,7 @@ cleanup() { ip link del veth_A-R1 2>/dev/null ovs-vsctl --if-exists del-port vxlan_a 2>/dev/null ovs-vsctl --if-exists del-br ovs_br0 2>/dev/null + rm -f "$tmpoutfile" } mtu() { @@ -1328,6 +1330,39 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() { check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on bridged ${type} interface" pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on locally bridged ${type} interface" + + tmpoutfile=$(mktemp) + + # Flush Exceptions, retry with TCP + run_cmd ${ns_a} ip route flush cached ${dst} + run_cmd ${ns_b} ip route flush cached ${dst} + run_cmd ${ns_c} ip route flush cached ${dst} + + for target in "${ns_a}" "${ns_c}" ; do + if [ ${family} -eq 4 ]; then + TCPDST=TCP:${dst}:50000 + else + TCPDST="TCP:[${dst}]:50000" + fi + ${ns_b} socat -T 3 -u -6 TCP-LISTEN:50000 STDOUT > $tmpoutfile & + + sleep 1 + + dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3 + + size=$(du -sb $tmpoutfile) + size=${size%%/tmp/*} + + [ $size -ne 1048576 ] && err "File size $size mismatches exepcted value in locally bridged vxlan test" && return 1 + done + + rm -f "$tmpoutfile" + + # Check that exceptions were created + pmtu="$(route_get_dst_pmtu_from_exception "${ns_c}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp: exceeding link layer MTU on bridged ${type} interface" + pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" + check_pmtu_value ${exp_mtu} "${pmtu}" "tcp exceeding link layer MTU on locally bridged ${type} interface" } test_pmtu_ipv4_br_vxlan4_exception() { |