diff options
45 files changed, 304 insertions, 195 deletions
diff --git a/Documentation/networking/packet_mmap.rst b/Documentation/networking/packet_mmap.rst index 6c009ceb1183..500ef60b1b82 100644 --- a/Documentation/networking/packet_mmap.rst +++ b/Documentation/networking/packet_mmap.rst @@ -8,7 +8,7 @@ Abstract ======== This file documents the mmap() facility available with the PACKET -socket interface on 2.4/2.6/3.x kernels. This type of sockets is used for +socket interface. This type of sockets is used for i) capture network traffic with utilities like tcpdump, ii) transmit network traffic, or any other that needs raw @@ -25,12 +25,12 @@ Please send your comments to Why use PACKET_MMAP =================== -In Linux 2.4/2.6/3.x if PACKET_MMAP is not enabled, the capture process is very +Non PACKET_MMAP capture process (plain AF_PACKET) is very inefficient. It uses very limited buffers and requires one system call to capture each packet, it requires two if you want to get packet's timestamp (like libpcap always does). -In the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size +On the other hand PACKET_MMAP is very efficient. PACKET_MMAP provides a size configurable circular buffer mapped in user space that can be used to either send or receive packets. This way reading packets just needs to wait for them, most of the time there is no need to issue a single system call. Concerning @@ -252,8 +252,7 @@ PACKET_MMAP setting constraints In kernel versions prior to 2.4.26 (for the 2.4 branch) and 2.6.5 (2.6 branch), the PACKET_MMAP buffer could hold only 32768 frames in a 32 bit architecture or -16384 in a 64 bit architecture. For information on these kernel versions -see http://pusa.uv.es/~ulisses/packet_mmap/packet_mmap.pre-2.4.26_2.6.5.txt +16384 in a 64 bit architecture. Block size limit ---------------- @@ -437,7 +436,7 @@ and the following flags apply: Capture process ^^^^^^^^^^^^^^^ - from include/linux/if_packet.h +From include/linux/if_packet.h:: #define TP_STATUS_COPY (1 << 1) #define TP_STATUS_LOSING (1 << 2) diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 85ebd2b7e446..708171c0d628 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -380,7 +380,7 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, goto free_dst; min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + - BAREUDP_BASE_HLEN + info->options_len + sizeof(struct iphdr); + BAREUDP_BASE_HLEN + info->options_len + sizeof(struct ipv6hdr); err = skb_cow_head(skb, min_headroom); if (unlikely(err)) @@ -534,6 +534,7 @@ static void bareudp_setup(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &bareudp_type); dev->features |= NETIF_F_SG | NETIF_F_HW_CSUM; dev->features |= NETIF_F_RXCSUM; + dev->features |= NETIF_F_LLTX; dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 09701c17f3f6..4b36d89bec06 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -92,9 +92,7 @@ GSWIP_MDIO_PHY_FDUP_MASK) /* GSWIP MII Registers */ -#define GSWIP_MII_CFG0 0x00 -#define GSWIP_MII_CFG1 0x02 -#define GSWIP_MII_CFG5 0x04 +#define GSWIP_MII_CFGp(p) (0x2 * (p)) #define GSWIP_MII_CFG_EN BIT(14) #define GSWIP_MII_CFG_LDCLKDIS BIT(12) #define GSWIP_MII_CFG_MODE_MIIP 0x0 @@ -392,17 +390,9 @@ static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set, static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set, int port) { - switch (port) { - case 0: - gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG0); - break; - case 1: - gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG1); - break; - case 5: - gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG5); - break; - } + /* There's no MII_CFG register for the CPU port */ + if (!dsa_is_cpu_port(priv->ds, port)) + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFGp(port)); } static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set, @@ -822,9 +812,8 @@ static int gswip_setup(struct dsa_switch *ds) gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); /* Disable the xMII link */ - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 0); - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 1); - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 5); + for (i = 0; i < priv->hw_info->max_ports; i++) + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i); /* enable special tag insertion on cpu port */ gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, @@ -1541,9 +1530,7 @@ static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, { struct gswip_priv *priv = ds->priv; - /* Enable the xMII interface only for the external PHY */ - if (interface != PHY_INTERFACE_MODE_INTERNAL) - gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); + gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); } static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset, diff --git a/drivers/net/ethernet/aquantia/Kconfig b/drivers/net/ethernet/aquantia/Kconfig index efb33c078a3c..cec2018c84a9 100644 --- a/drivers/net/ethernet/aquantia/Kconfig +++ b/drivers/net/ethernet/aquantia/Kconfig @@ -19,7 +19,6 @@ if NET_VENDOR_AQUANTIA config AQTION tristate "aQuantia AQtion(tm) Support" depends on PCI - depends on X86_64 || ARM64 || COMPILE_TEST depends on MACSEC || MACSEC=n help This enables the support for the aQuantia AQtion(tm) Ethernet card. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4edd6f8e017e..d10e4f85dd11 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6790,8 +6790,10 @@ static int bnxt_hwrm_func_backing_store_qcaps(struct bnxt *bp) ctx->tqm_fp_rings_count = resp->tqm_fp_rings_count; if (!ctx->tqm_fp_rings_count) ctx->tqm_fp_rings_count = bp->max_q; + else if (ctx->tqm_fp_rings_count > BNXT_MAX_TQM_FP_RINGS) + ctx->tqm_fp_rings_count = BNXT_MAX_TQM_FP_RINGS; - tqm_rings = ctx->tqm_fp_rings_count + 1; + tqm_rings = ctx->tqm_fp_rings_count + BNXT_MAX_TQM_SP_RINGS; ctx_pg = kcalloc(tqm_rings, sizeof(*ctx_pg), GFP_KERNEL); if (!ctx_pg) { kfree(ctx); @@ -6925,7 +6927,8 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables) pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl, pg_dir = &req.tqm_sp_page_dir, ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP; - i < 9; i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) { + i < BNXT_MAX_TQM_RINGS; + i++, num_entries++, pg_attr++, pg_dir++, ena <<= 1) { if (!(enables & ena)) continue; @@ -12887,10 +12890,10 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev, */ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) { + pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; struct net_device *netdev = pci_get_drvdata(pdev); struct bnxt *bp = netdev_priv(netdev); int err = 0, off; - pci_ers_result_t result = PCI_ERS_RESULT_DISCONNECT; netdev_info(bp->dev, "PCI Slot Reset\n"); @@ -12919,22 +12922,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) pci_save_state(pdev); err = bnxt_hwrm_func_reset(bp); - if (!err) { - err = bnxt_hwrm_func_qcaps(bp); - if (!err && netif_running(netdev)) - err = bnxt_open(netdev); - } - bnxt_ulp_start(bp, err); - if (!err) { - bnxt_reenable_sriov(bp); + if (!err) result = PCI_ERS_RESULT_RECOVERED; - } - } - - if (result != PCI_ERS_RESULT_RECOVERED) { - if (netif_running(netdev)) - dev_close(netdev); - pci_disable_device(pdev); } rtnl_unlock(); @@ -12952,10 +12941,21 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) static void bnxt_io_resume(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); + struct bnxt *bp = netdev_priv(netdev); + int err; + netdev_info(bp->dev, "PCI Slot Resume\n"); rtnl_lock(); - netif_device_attach(netdev); + err = bnxt_hwrm_func_qcaps(bp); + if (!err && netif_running(netdev)) + err = bnxt_open(netdev); + + bnxt_ulp_start(bp, err); + if (!err) { + bnxt_reenable_sriov(bp); + netif_device_attach(netdev); + } rtnl_unlock(); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 950ea26ae0d2..51996c85547e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1436,6 +1436,11 @@ struct bnxt_ctx_pg_info { struct bnxt_ctx_pg_info **ctx_pg_tbl; }; +#define BNXT_MAX_TQM_SP_RINGS 1 +#define BNXT_MAX_TQM_FP_RINGS 8 +#define BNXT_MAX_TQM_RINGS \ + (BNXT_MAX_TQM_SP_RINGS + BNXT_MAX_TQM_FP_RINGS) + struct bnxt_ctx_mem_info { u32 qp_max_entries; u16 qp_min_qp1_entries; @@ -1474,7 +1479,7 @@ struct bnxt_ctx_mem_info { struct bnxt_ctx_pg_info stat_mem; struct bnxt_ctx_pg_info mrav_mem; struct bnxt_ctx_pg_info tim_mem; - struct bnxt_ctx_pg_info *tqm_mem[9]; + struct bnxt_ctx_pg_info *tqm_mem[BNXT_MAX_TQM_RINGS]; }; struct bnxt_fw_health { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index d5d910916c2e..814a5b10141d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -467,7 +467,7 @@ static void macb_set_tx_clk(struct macb *bp, int speed) { long ferr, rate, rate_rounded; - if (!bp->tx_clk || !(bp->caps & MACB_CAPS_CLK_HW_CHG)) + if (!bp->tx_clk || (bp->caps & MACB_CAPS_CLK_HW_CHG)) return; switch (speed) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 7165da0ee9aa..a6e3f07caf99 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -415,6 +415,10 @@ static void __lb_other_process(struct hns_nic_ring_data *ring_data, /* for mutl buffer*/ new_skb = skb_copy(skb, GFP_ATOMIC); dev_kfree_skb_any(skb); + if (!new_skb) { + netdev_err(ndev, "skb alloc failed\n"); + return; + } skb = new_skb; check_ok = 0; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 91ebcde30292..9778c83150f1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2981,9 +2981,7 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter, int rc; if (!scrq) { - netdev_dbg(adapter->netdev, - "Invalid scrq reset. irq (%d) or msgs (%p).\n", - scrq->irq, scrq->msgs); + netdev_dbg(adapter->netdev, "Invalid scrq reset.\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index ba7a0f8f6937..5b2143f4b1f8 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -436,6 +436,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define FLAG2_DFLT_CRC_STRIPPING BIT(12) #define FLAG2_CHECK_RX_HWTSTAMP BIT(13) #define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14) +#define FLAG2_ENABLE_S0IX_FLOWS BIT(15) #define E1000_RX_DESC_PS(R, i) \ (&(((union e1000_rx_desc_packet_split *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 03215b0aee4b..06442e6bef73 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -23,6 +23,13 @@ struct e1000_stats { int stat_offset; }; +static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define E1000E_PRIV_FLAGS_S0IX_ENABLED BIT(0) + "s0ix-enabled", +}; + +#define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings) + #define E1000_STAT(str, m) { \ .stat_string = str, \ .type = E1000_STATS, \ @@ -1776,6 +1783,8 @@ static int e1000e_get_sset_count(struct net_device __always_unused *netdev, return E1000_TEST_LEN; case ETH_SS_STATS: return E1000_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return E1000E_PRIV_FLAGS_STR_LEN; default: return -EOPNOTSUPP; } @@ -2097,6 +2106,10 @@ static void e1000_get_strings(struct net_device __always_unused *netdev, p += ETH_GSTRING_LEN; } break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, e1000e_priv_flags_strings, + E1000E_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -2305,6 +2318,37 @@ static int e1000e_get_ts_info(struct net_device *netdev, return 0; } +static u32 e1000e_get_priv_flags(struct net_device *netdev) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) + priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED; + + return priv_flags; +} + +static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct e1000_adapter *adapter = netdev_priv(netdev); + unsigned int flags2 = adapter->flags2; + + flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS; + if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) { + struct e1000_hw *hw = &adapter->hw; + + if (hw->mac.type < e1000_pch_cnp) + return -EINVAL; + flags2 |= FLAG2_ENABLE_S0IX_FLOWS; + } + + if (flags2 != adapter->flags2) + adapter->flags2 = flags2; + + return 0; +} + static const struct ethtool_ops e1000_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS, .get_drvinfo = e1000_get_drvinfo, @@ -2336,6 +2380,8 @@ static const struct ethtool_ops e1000_ethtool_ops = { .set_eee = e1000e_set_eee, .get_link_ksettings = e1000_get_link_ksettings, .set_link_ksettings = e1000_set_link_ksettings, + .get_priv_flags = e1000e_get_priv_flags, + .set_priv_flags = e1000e_set_priv_flags, }; void e1000e_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 9aa6fad8ed47..6fb46682b058 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1240,6 +1240,9 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) return 0; if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + struct e1000_adapter *adapter = hw->adapter; + bool firmware_bug = false; + if (force) { /* Request ME un-configure ULP mode in the PHY */ mac_reg = er32(H2ME); @@ -1248,16 +1251,24 @@ static s32 e1000_disable_ulp_lpt_lp(struct e1000_hw *hw, bool force) ew32(H2ME, mac_reg); } - /* Poll up to 300msec for ME to clear ULP_CFG_DONE. */ + /* Poll up to 2.5 seconds for ME to clear ULP_CFG_DONE. + * If this takes more than 1 second, show a warning indicating a + * firmware bug + */ while (er32(FWSM) & E1000_FWSM_ULP_CFG_DONE) { - if (i++ == 30) { + if (i++ == 250) { ret_val = -E1000_ERR_PHY; goto out; } + if (i > 100 && !firmware_bug) + firmware_bug = true; usleep_range(10000, 11000); } - e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10); + if (firmware_bug) + e_warn("ULP_CONFIG_DONE took %dmsec. This is a firmware bug\n", i * 10); + else + e_dbg("ULP_CONFIG_DONE cleared after %dmsec\n", i * 10); if (force) { mac_reg = er32(H2ME); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 128ab6898070..e9b82c209c2d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -103,45 +103,6 @@ static const struct e1000_reg_info e1000_reg_info_tbl[] = { {0, NULL} }; -struct e1000e_me_supported { - u16 device_id; /* supported device ID */ -}; - -static const struct e1000e_me_supported me_supported[] = { - {E1000_DEV_ID_PCH_LPT_I217_LM}, - {E1000_DEV_ID_PCH_LPTLP_I218_LM}, - {E1000_DEV_ID_PCH_I218_LM2}, - {E1000_DEV_ID_PCH_I218_LM3}, - {E1000_DEV_ID_PCH_SPT_I219_LM}, - {E1000_DEV_ID_PCH_SPT_I219_LM2}, - {E1000_DEV_ID_PCH_LBG_I219_LM3}, - {E1000_DEV_ID_PCH_SPT_I219_LM4}, - {E1000_DEV_ID_PCH_SPT_I219_LM5}, - {E1000_DEV_ID_PCH_CNP_I219_LM6}, - {E1000_DEV_ID_PCH_CNP_I219_LM7}, - {E1000_DEV_ID_PCH_ICP_I219_LM8}, - {E1000_DEV_ID_PCH_ICP_I219_LM9}, - {E1000_DEV_ID_PCH_CMP_I219_LM10}, - {E1000_DEV_ID_PCH_CMP_I219_LM11}, - {E1000_DEV_ID_PCH_CMP_I219_LM12}, - {E1000_DEV_ID_PCH_TGP_I219_LM13}, - {E1000_DEV_ID_PCH_TGP_I219_LM14}, - {E1000_DEV_ID_PCH_TGP_I219_LM15}, - {0} -}; - -static bool e1000e_check_me(u16 device_id) -{ - struct e1000e_me_supported *id; - - for (id = (struct e1000e_me_supported *)me_supported; - id->device_id; id++) - if (device_id == id->device_id) - return true; - - return false; -} - /** * __ew32_prepare - prepare to write to MAC CSR register on certain parts * @hw: pointer to the HW structure @@ -6962,7 +6923,6 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; int rc; e1000e_flush_lpic(pdev); @@ -6970,13 +6930,13 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) e1000e_pm_freeze(dev); rc = __e1000_shutdown(pdev, false); - if (rc) + if (rc) { e1000e_pm_thaw(dev); - - /* Introduce S0ix implementation */ - if (hw->mac.type >= e1000_pch_cnp && - !e1000e_check_me(hw->adapter->pdev->device)) - e1000e_s0ix_entry_flow(adapter); + } else { + /* Introduce S0ix implementation */ + if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) + e1000e_s0ix_entry_flow(adapter); + } return rc; } @@ -6986,12 +6946,10 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); - struct e1000_hw *hw = &adapter->hw; int rc; /* Introduce S0ix implementation */ - if (hw->mac.type >= e1000_pch_cnp && - !e1000e_check_me(hw->adapter->pdev->device)) + if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) e1000e_s0ix_exit_flow(adapter); rc = __e1000_resume(pdev); @@ -7655,6 +7613,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!(adapter->flags & FLAG_HAS_AMT)) e1000e_get_hw_control(adapter); + if (hw->mac.type >= e1000_pch_cnp) + adapter->flags2 |= FLAG2_ENABLE_S0IX_FLOWS; + strlcpy(netdev->name, "eth%d", sizeof(netdev->name)); err = register_netdev(netdev); if (err) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index f20b31327027..4b1808acef58 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2370,17 +2370,18 @@ static void mvpp2_rx_pkts_coal_set(struct mvpp2_port *port, static void mvpp2_tx_pkts_coal_set(struct mvpp2_port *port, struct mvpp2_tx_queue *txq) { - unsigned int thread = mvpp2_cpu_to_thread(port->priv, get_cpu()); + unsigned int thread; u32 val; if (txq->done_pkts_coal > MVPP2_TXQ_THRESH_MASK) txq->done_pkts_coal = MVPP2_TXQ_THRESH_MASK; val = (txq->done_pkts_coal << MVPP2_TXQ_THRESH_OFFSET); - mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); - mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val); - - put_cpu(); + /* PKT-coalescing registers are per-queue + per-thread */ + for (thread = 0; thread < MVPP2_MAX_THREADS; thread++) { + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_NUM_REG, txq->id); + mvpp2_thread_write(port->priv, thread, MVPP2_TXQ_THRESH_REG, val); + } } static u32 mvpp2_usec_to_cycles(u32 usec, unsigned long clk_hz) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 46d8510b2fe2..a569abe7f5ef 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2207,7 +2207,8 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) } switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26: + case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_37: case RTL_GIGA_MAC_VER_39: case RTL_GIGA_MAC_VER_43: @@ -2233,7 +2234,8 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) static void rtl_pll_power_up(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_26: + case RTL_GIGA_MAC_VER_32 ... RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_37: case RTL_GIGA_MAC_VER_39: case RTL_GIGA_MAC_VER_43: diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index d1fc7955d422..43222a34cba0 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -599,6 +599,7 @@ void cpts_unregister(struct cpts *cpts) ptp_clock_unregister(cpts->clock); cpts->clock = NULL; + cpts->phc_index = -1; cpts_write32(cpts, 0, int_enable); cpts_write32(cpts, 0, control); @@ -784,6 +785,7 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, cpts->cc.read = cpts_systim_read; cpts->cc.mask = CLOCKSOURCE_MASK(32); cpts->info = cpts_info; + cpts->phc_index = -1; if (n_ext_ts) cpts->info.n_ext_ts = n_ext_ts; diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 579cc3e51677..14d9a791924b 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -326,8 +326,8 @@ gsi_evt_ring_state(struct gsi *gsi, u32 evt_ring_id) } /* Issue an event ring command and wait for it to complete */ -static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id, - enum gsi_evt_cmd_opcode opcode) +static void evt_ring_command(struct gsi *gsi, u32 evt_ring_id, + enum gsi_evt_cmd_opcode opcode) { struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id]; struct completion *completion = &evt_ring->completion; @@ -361,19 +361,16 @@ static int evt_ring_command(struct gsi *gsi, u32 evt_ring_id, iowrite32(0, gsi->virt + GSI_CNTXT_SRC_EV_CH_IRQ_MSK_OFFSET); if (success) - return 0; + return; dev_err(dev, "GSI command %u for event ring %u timed out, state %u\n", opcode, evt_ring_id, evt_ring->state); - - return -ETIMEDOUT; } /* Allocate an event ring in NOT_ALLOCATED state */ static int gsi_evt_ring_alloc_command(struct gsi *gsi, u32 evt_ring_id) { struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id]; - int ret; /* Get initial event ring state */ evt_ring->state = gsi_evt_ring_state(gsi, evt_ring_id); @@ -383,7 +380,7 @@ static int gsi_evt_ring_alloc_command(struct gsi *gsi, u32 evt_ring_id) return -EINVAL; } - ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE); + evt_ring_command(gsi, evt_ring_id, GSI_EVT_ALLOCATE); /* If successful the event ring state will have changed */ if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED) @@ -400,7 +397,6 @@ static void gsi_evt_ring_reset_command(struct gsi *gsi, u32 evt_ring_id) { struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id]; enum gsi_evt_ring_state state = evt_ring->state; - int ret; if (state != GSI_EVT_RING_STATE_ALLOCATED && state != GSI_EVT_RING_STATE_ERROR) { @@ -409,7 +405,7 @@ static void gsi_evt_ring_reset_command(struct gsi *gsi, u32 evt_ring_id) return; } - ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET); + evt_ring_command(gsi, evt_ring_id, GSI_EVT_RESET); /* If successful the event ring state will have changed */ if (evt_ring->state == GSI_EVT_RING_STATE_ALLOCATED) @@ -423,7 +419,6 @@ static void gsi_evt_ring_reset_command(struct gsi *gsi, u32 evt_ring_id) static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id) { struct gsi_evt_ring *evt_ring = &gsi->evt_ring[evt_ring_id]; - int ret; if (evt_ring->state != GSI_EVT_RING_STATE_ALLOCATED) { dev_err(gsi->dev, "event ring %u state %u before dealloc\n", @@ -431,7 +426,7 @@ static void gsi_evt_ring_de_alloc_command(struct gsi *gsi, u32 evt_ring_id) return; } - ret = evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC); + evt_ring_command(gsi, evt_ring_id, GSI_EVT_DE_ALLOC); /* If successful the event ring state will have changed */ if (evt_ring->state == GSI_EVT_RING_STATE_NOT_ALLOCATED) @@ -454,7 +449,7 @@ static enum gsi_channel_state gsi_channel_state(struct gsi_channel *channel) } /* Issue a channel command and wait for it to complete */ -static int +static void gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode) { struct completion *completion = &channel->completion; @@ -489,12 +484,10 @@ gsi_channel_command(struct gsi_channel *channel, enum gsi_ch_cmd_opcode opcode) iowrite32(0, gsi->virt + GSI_CNTXT_SRC_CH_IRQ_MSK_OFFSET); if (success) - return 0; + return; dev_err(dev, "GSI command %u for channel %u timed out, state %u\n", opcode, channel_id, gsi_channel_state(channel)); - - return -ETIMEDOUT; } /* Allocate GSI channel in NOT_ALLOCATED state */ @@ -503,7 +496,6 @@ static int gsi_channel_alloc_command(struct gsi *gsi, u32 channel_id) struct gsi_channel *channel = &gsi->channel[channel_id]; struct device *dev = gsi->dev; enum gsi_channel_state state; - int ret; /* Get initial channel state */ state = gsi_channel_state(channel); @@ -513,7 +505,7 @@ static int gsi_channel_alloc_command(struct gsi *gsi, u32 channel_id) return -EINVAL; } - ret = gsi_channel_command(channel, GSI_CH_ALLOCATE); + gsi_channel_command(channel, GSI_CH_ALLOCATE); /* If successful the channel state will have changed */ state = gsi_channel_state(channel); @@ -531,7 +523,6 @@ static int gsi_channel_start_command(struct gsi_channel *channel) { struct device *dev = channel->gsi->dev; enum gsi_channel_state state; - int ret; state = gsi_channel_state(channel); if (state != GSI_CHANNEL_STATE_ALLOCATED && @@ -541,7 +532,7 @@ static int gsi_channel_start_command(struct gsi_channel *channel) return -EINVAL; } - ret = gsi_channel_command(channel, GSI_CH_START); + gsi_channel_command(channel, GSI_CH_START); /* If successful the channel state will have changed */ state = gsi_channel_state(channel); @@ -559,7 +550,6 @@ static int gsi_channel_stop_command(struct gsi_channel *channel) { struct device *dev = channel->gsi->dev; enum gsi_channel_state state; - int ret; state = gsi_channel_state(channel); @@ -576,7 +566,7 @@ static int gsi_channel_stop_command(struct gsi_channel *channel) return -EINVAL; } - ret = gsi_channel_command(channel, GSI_CH_STOP); + gsi_channel_command(channel, GSI_CH_STOP); /* If successful the channel state will have changed */ state = gsi_channel_state(channel); @@ -598,7 +588,6 @@ static void gsi_channel_reset_command(struct gsi_channel *channel) { struct device *dev = channel->gsi->dev; enum gsi_channel_state state; - int ret; msleep(1); /* A short delay is required before a RESET command */ @@ -612,7 +601,7 @@ static void gsi_channel_reset_command(struct gsi_channel *channel) return; } - ret = gsi_channel_command(channel, GSI_CH_RESET); + gsi_channel_command(channel, GSI_CH_RESET); /* If successful the channel state will have changed */ state = gsi_channel_state(channel); @@ -627,7 +616,6 @@ static void gsi_channel_de_alloc_command(struct gsi *gsi, u32 channel_id) struct gsi_channel *channel = &gsi->channel[channel_id]; struct device *dev = gsi->dev; enum gsi_channel_state state; - int ret; state = gsi_channel_state(channel); if (state != GSI_CHANNEL_STATE_ALLOCATED) { @@ -636,7 +624,7 @@ static void gsi_channel_de_alloc_command(struct gsi *gsi, u32 channel_id) return; } - ret = gsi_channel_command(channel, GSI_CH_DE_ALLOC); + gsi_channel_command(channel, GSI_CH_DE_ALLOC); /* If successful the channel state will have changed */ state = gsi_channel_state(channel); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fbed05ae7b0f..978ac0981d16 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1365,7 +1365,7 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, int i; if (it->nr_segs > MAX_SKB_FRAGS + 1) - return ERR_PTR(-ENOMEM); + return ERR_PTR(-EMSGSIZE); local_bh_disable(); skb = napi_get_frags(&tfile->napi); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 2bac57d5e8d5..3b816a4731f2 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1863,9 +1863,6 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) * USB_CDC_NOTIFY_NETWORK_CONNECTION notification shall be * sent by device after USB_CDC_NOTIFY_SPEED_CHANGE. */ - netif_info(dev, link, dev->net, - "network connection: %sconnected\n", - !!event->wValue ? "" : "dis"); usbnet_link_change(dev, !!event->wValue, 0); break; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d166c321ee9b..af19513a9f75 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1013,6 +1013,7 @@ static const struct usb_device_id products[] = { {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0125)}, /* Quectel EC25, EC20 R2.0 Mini PCIe */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0306)}, /* Quectel EP06/EG06/EM06 */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0512)}, /* Quectel EG12/EM12 */ + {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0620)}, /* Quectel EM160R-GL */ {QMI_MATCH_FF_FF_FF(0x2c7c, 0x0800)}, /* Quectel RM500Q-GL */ /* 3. Combined interface devices matching on interface number */ diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 64f855651336..261b53fc8e04 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -569,6 +569,13 @@ static void ppp_timer(struct timer_list *t) unsigned long flags; spin_lock_irqsave(&ppp->lock, flags); + /* mod_timer could be called after we entered this function but + * before we got the lock. + */ + if (timer_pending(&proto->timer)) { + spin_unlock_irqrestore(&ppp->lock, flags); + return; + } switch (proto->state) { case STOPPING: case REQ_SENT: diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 531a00d703cd..c8784dfafdd7 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -863,6 +863,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *ubufs; + struct ubuf_info *ubuf; bool zcopy_used; int sent_pkts = 0; @@ -895,9 +896,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) /* use msg_control to pass vhost zerocopy ubuf info to skb */ if (zcopy_used) { - struct ubuf_info *ubuf; ubuf = nvq->ubuf_info + nvq->upend_idx; - vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS; ubuf->callback = vhost_zerocopy_callback; @@ -927,7 +926,8 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) err = sock->ops->sendmsg(sock, &msg, len); if (unlikely(err < 0)) { if (zcopy_used) { - vhost_net_ubuf_put(ubufs); + if (vq->heads[ubuf->desc].len == VHOST_DMA_IN_PROGRESS) + vhost_net_ubuf_put(ubufs); nvq->upend_idx = ((unsigned)nvq->upend_idx - 1) % UIO_MAXIOV; } diff --git a/include/net/red.h b/include/net/red.h index fc455445f4b2..932f0d79d60c 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -168,12 +168,14 @@ static inline void red_set_vars(struct red_vars *v) v->qcount = -1; } -static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog) +static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log) { if (fls(qth_min) + Wlog > 32) return false; if (fls(qth_max) + Wlog > 32) return false; + if (Scell_log >= 32) + return false; if (qth_max < qth_min) return false; return true; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 4f4e93bf814c..cc17bc957548 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -58,10 +58,6 @@ struct xdp_sock { struct xsk_queue *tx ____cacheline_aligned_in_smp; struct list_head tx_list; - /* Mutual exclusion of NAPI TX thread and sendmsg error paths - * in the SKB destructor callback. - */ - spinlock_t tx_completion_lock; /* Protects generic receive. */ spinlock_t rx_lock; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index 01755b838c74..eaa8386dbc63 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -73,6 +73,11 @@ struct xsk_buff_pool { bool dma_need_sync; bool unaligned; void *addrs; + /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: + * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when + * sockets share a single cq when the same netdev and queue id is shared. + */ + spinlock_t cq_lock; struct xdp_buff_xsk *free_heads[]; }; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 7e848200cd26..c1ac7f964bc9 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,6 +152,7 @@ static void htab_init_buckets(struct bpf_htab *htab) lockdep_set_class(&htab->buckets[i].lock, &htab->lockdep_key); } + cond_resched(); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4caf06fe4152..c3bb03c8371f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -17,7 +17,6 @@ #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> -#include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e73c07593024..3efe38191d1c 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -37,7 +37,7 @@ retry: if (!task) { ++*tid; goto retry; - } else if (skip_if_dup_files && task->tgid != task->pid && + } else if (skip_if_dup_files && !thread_group_leader(task) && task->files == task->group_leader->files) { put_task_struct(task); task = NULL; @@ -151,14 +151,14 @@ again: curr_task = info->task; curr_fd = info->fd; } else { - curr_task = task_seq_get_next(ns, &curr_tid, true); - if (!curr_task) { - info->task = NULL; - return NULL; - } - - /* set info->task and info->tid */ - info->task = curr_task; + curr_task = task_seq_get_next(ns, &curr_tid, true); + if (!curr_task) { + info->task = NULL; + info->tid = curr_tid; + return NULL; + } + + /* set info->task and info->tid */ if (curr_tid == info->tid) { curr_fd = info->fd; } else { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9500d28a43b0..277ed854aef1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1569,10 +1569,8 @@ static void neigh_proxy_process(struct timer_list *t) void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb) { - unsigned long now = jiffies; - - unsigned long sched_next = now + (prandom_u32() % - NEIGH_VAR(p, PROXY_DELAY)); + unsigned long sched_next = jiffies + + prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY)); if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) { kfree_skb(skb); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 999b70c59761..daf502c13d6d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1317,8 +1317,8 @@ static const struct attribute_group dql_group = { static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf) { + int cpu, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; - int cpu, len, num_tc = 1, tc = 0; struct xps_dev_maps *dev_maps; cpumask_var_t mask; unsigned long index; @@ -1328,22 +1328,31 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, index = get_netdev_queue_index(queue); + if (!rtnl_trylock()) + return restart_syscall(); + if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; - if (num_tc < 0) - return -EINVAL; + if (num_tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); - if (tc < 0) - return -EINVAL; + if (tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } } - if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { + ret = -ENOMEM; + goto err_rtnl_unlock; + } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_cpus_map); @@ -1366,9 +1375,15 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, } rcu_read_unlock(); + rtnl_unlock(); + len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); free_cpumask_var(mask); return len < PAGE_SIZE ? len : -EINVAL; + +err_rtnl_unlock: + rtnl_unlock(); + return ret; } static ssize_t xps_cpus_store(struct netdev_queue *queue, @@ -1396,7 +1411,13 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue, return err; } + if (!rtnl_trylock()) { + free_cpumask_var(mask); + return restart_syscall(); + } + err = netif_set_xps_queue(dev, mask, index); + rtnl_unlock(); free_cpumask_var(mask); @@ -1408,22 +1429,29 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) { + int j, len, ret, num_tc = 1, tc = 0; struct net_device *dev = queue->dev; struct xps_dev_maps *dev_maps; unsigned long *mask, index; - int j, len, num_tc = 1, tc = 0; index = get_netdev_queue_index(queue); + if (!rtnl_trylock()) + return restart_syscall(); + if (dev->num_tc) { num_tc = dev->num_tc; tc = netdev_txq_to_tc(dev, index); - if (tc < 0) - return -EINVAL; + if (tc < 0) { + ret = -EINVAL; + goto err_rtnl_unlock; + } } mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL); - if (!mask) - return -ENOMEM; + if (!mask) { + ret = -ENOMEM; + goto err_rtnl_unlock; + } rcu_read_lock(); dev_maps = rcu_dereference(dev->xps_rxqs_map); @@ -1449,10 +1477,16 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf) out_no_maps: rcu_read_unlock(); + rtnl_unlock(); + len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues); bitmap_free(mask); return len < PAGE_SIZE ? len : -EINVAL; + +err_rtnl_unlock: + rtnl_unlock(); + return ret; } static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, @@ -1478,10 +1512,17 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf, return err; } + if (!rtnl_trylock()) { + bitmap_free(mask); + return restart_syscall(); + } + cpus_read_lock(); err = __netif_set_xps_queue(dev, mask, index, true); cpus_read_unlock(); + rtnl_unlock(); + bitmap_free(mask); return err ? : len; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index cdf6ec5aa45d..84bb707bd88d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -292,7 +292,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, - .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), + .flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK, .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 66fdbfe5447c..5d1e6fe9d838 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -128,7 +128,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * to 0 and sets the configured key in the * inner erspan header field */ - if (greh->protocol == htons(ETH_P_ERSPAN) || + if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) || greh->protocol == htons(ETH_P_ERSPAN2)) { struct erspan_base_hdr *ershdr; diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index 213ea7abc9ab..40961889e9c0 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -489,6 +489,7 @@ static int lapb_device_event(struct notifier_block *this, unsigned long event, break; } + lapb_put(lapb); return NOTIFY_DONE; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 09b19aa2f205..6628d8d74203 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -877,6 +877,9 @@ static void __mptcp_wmem_reserve(struct sock *sk, int size) struct mptcp_sock *msk = mptcp_sk(sk); WARN_ON_ONCE(msk->wmem_reserved); + if (WARN_ON_ONCE(amount < 0)) + amount = 0; + if (amount <= sk->sk_forward_alloc) goto reserve; @@ -1587,7 +1590,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -EOPNOTSUPP; - mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, len)); + mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, min_t(size_t, 1 << 20, len))); timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index bd618b00d319..50f680f03a54 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -362,7 +362,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, ctl = nla_data(tb[TCA_CHOKE_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 8599c6f31b05..e0bc77533acc 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) { + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index e89fab6ccb34..b4ae34d7aa96 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -250,7 +250,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) return -EINVAL; err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index bca2be57d9fc..b25e51440623 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) } if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog)) + ctl_v1->Wlog, ctl_v1->Scell_log)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index ac4a317038f1..8037b04a9edd 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -423,9 +423,9 @@ static void xsk_destruct_skb(struct sk_buff *skb) struct xdp_sock *xs = xdp_sk(skb->sk); unsigned long flags; - spin_lock_irqsave(&xs->tx_completion_lock, flags); + spin_lock_irqsave(&xs->pool->cq_lock, flags); xskq_prod_submit_addr(xs->pool->cq, addr); - spin_unlock_irqrestore(&xs->tx_completion_lock, flags); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); sock_wfree(skb); } @@ -437,6 +437,7 @@ static int xsk_generic_xmit(struct sock *sk) bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; + unsigned long flags; int err = 0; mutex_lock(&xs->mutex); @@ -468,10 +469,13 @@ static int xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ + spin_lock_irqsave(&xs->pool->cq_lock, flags); if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) { + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); kfree_skb(skb); goto out; } + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); skb->dev = xs->dev; skb->priority = sk->sk_priority; @@ -483,6 +487,9 @@ static int xsk_generic_xmit(struct sock *sk) if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ skb->destructor = sock_wfree; + spin_lock_irqsave(&xs->pool->cq_lock, flags); + xskq_prod_cancel(xs->pool->cq); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); /* Free skb without triggering the perf drop trace */ consume_skb(skb); err = -EAGAIN; @@ -878,6 +885,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) } } + /* FQ and CQ are now owned by the buffer pool and cleaned up with it. */ + xs->fq_tmp = NULL; + xs->cq_tmp = NULL; + xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; @@ -1299,7 +1310,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, xs->state = XSK_READY; mutex_init(&xs->mutex); spin_lock_init(&xs->rx_lock); - spin_lock_init(&xs->tx_completion_lock); INIT_LIST_HEAD(&xs->map_list); spin_lock_init(&xs->map_list_lock); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 67a4494d63b6..20598eea658c 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -71,12 +71,11 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, INIT_LIST_HEAD(&pool->free_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); + spin_lock_init(&pool->cq_lock); refcount_set(&pool->users, 1); pool->fq = xs->fq_tmp; pool->cq = xs->cq_tmp; - xs->fq_tmp = NULL; - xs->cq_tmp = NULL; for (i = 0; i < pool->free_heads_cnt; i++) { xskb = &pool->heads[i]; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 4a9663aa7afe..2823b7c3302d 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -334,6 +334,11 @@ static inline bool xskq_prod_is_full(struct xsk_queue *q) return xskq_prod_nb_free(q, 1) ? false : true; } +static inline void xskq_prod_cancel(struct xsk_queue *q) +{ + q->cached_prod--; +} + static inline int xskq_prod_reserve(struct xsk_queue *q) { if (xskq_prod_is_full(q)) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 8c33e999319a..c51df6b91bef 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -121,6 +121,9 @@ VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ /sys/kernel/btf/vmlinux \ /boot/vmlinux-$(shell uname -r) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) +ifeq ($(VMLINUX_BTF),) +$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)") +endif # Define simple and short `make test_progs`, `make test_sysctl`, etc targets # to build individual tests. diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 0ad3e6305ff0..51adc42b2b40 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -1312,22 +1312,58 @@ static void test_map_stress(void) #define DO_UPDATE 1 #define DO_DELETE 0 +#define MAP_RETRIES 20 + +static int map_update_retriable(int map_fd, const void *key, const void *value, + int flags, int attempts) +{ + while (bpf_map_update_elem(map_fd, key, value, flags)) { + if (!attempts || (errno != EAGAIN && errno != EBUSY)) + return -errno; + + usleep(1); + attempts--; + } + + return 0; +} + +static int map_delete_retriable(int map_fd, const void *key, int attempts) +{ + while (bpf_map_delete_elem(map_fd, key)) { + if (!attempts || (errno != EAGAIN && errno != EBUSY)) + return -errno; + + usleep(1); + attempts--; + } + + return 0; +} + static void test_update_delete(unsigned int fn, void *data) { int do_update = ((int *)data)[1]; int fd = ((int *)data)[0]; - int i, key, value; + int i, key, value, err; for (i = fn; i < MAP_SIZE; i += TASKS) { key = value = i; if (do_update) { - assert(bpf_map_update_elem(fd, &key, &value, - BPF_NOEXIST) == 0); - assert(bpf_map_update_elem(fd, &key, &value, - BPF_EXIST) == 0); + err = map_update_retriable(fd, &key, &value, BPF_NOEXIST, MAP_RETRIES); + if (err) + printf("error %d %d\n", err, errno); + assert(err == 0); + err = map_update_retriable(fd, &key, &value, BPF_EXIST, MAP_RETRIES); + if (err) + printf("error %d %d\n", err, errno); + assert(err == 0); } else { - assert(bpf_map_delete_elem(fd, &key) == 0); + err = map_delete_retriable(fd, &key, MAP_RETRIES); + if (err) + printf("error %d %d\n", err, errno); + assert(err == 0); } } } diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index 014dedaa4dd2..1e722ee76b1f 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -715,7 +715,7 @@ static void worker_pkt_dump(void) int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE)); if (payload == EOT) { - ksft_print_msg("End-of-tranmission frame received\n"); + ksft_print_msg("End-of-transmission frame received\n"); fprintf(stdout, "---------------------------------------\n"); break; } @@ -747,7 +747,7 @@ static void worker_pkt_validate(void) } if (payloadseqnum == EOT) { - ksft_print_msg("End-of-tranmission frame received: PASS\n"); + ksft_print_msg("End-of-transmission frame received: PASS\n"); sigvar = 1; break; } diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh index 4d900bc1f76c..5c7700212f75 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_pfc.sh @@ -230,7 +230,7 @@ switch_create() __mlnx_qos -i $swp4 --pfc=0,1,0,0,0,0,0,0 >/dev/null # PG0 will get autoconfigured to Xoff, give PG1 arbitrarily 100K, which # is (-2*MTU) about 80K of delay provision. - __mlnx_qos -i $swp3 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null + __mlnx_qos -i $swp4 --buffer_size=0,$_100KB,0,0,0,0,0,0 >/dev/null # bridges # ------- |