diff options
41 files changed, 408 insertions, 237 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 1bb8cac61a28..148d7a32754e 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -103,4 +103,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index f824eeb0f2e4..2434d08ad8d6 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -96,4 +96,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _UAPI__ASM_AVR32_SOCKET_H */ diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index a8ad9bebfc47..1ccf45657472 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -96,5 +96,7 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 6af3253e4209..2c3f4b48042a 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -105,4 +105,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index e98b6bb897c0..ae6548d29a18 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -96,4 +96,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index ae2b62e39d4d..3418ec9c1c50 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -114,4 +114,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index e4ac1843ee01..4526e92301a6 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -96,4 +96,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f754c793e82a..514701840bd9 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -95,4 +95,6 @@ #define SO_INCOMING_NAPI_ID 0x4031 +#define SO_COOKIE 0x4032 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 5f84af7dcb2e..58e2ec0310fc 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -103,4 +103,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 25ac4960e707..e8e5ecf673fd 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -102,4 +102,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index b05513acd589..3f4ad19d9ec7 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -92,6 +92,8 @@ #define SO_INCOMING_NAPI_ID 0x003a +#define SO_COOKIE 0x003b + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 786606c81edd..1eb6d2fe70d3 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -107,4 +107,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* _XTENSA_SOCKET_H */ diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 7c6bc33a9516..b3fea55071e3 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -568,8 +568,9 @@ static int mv88e6xxx_g2_smi_phy_write_addr(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_smi_phy_cmd(chip, cmd); } -int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr, - int reg_c45, u16 *val, bool external) +static int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, + int addr, int reg_c45, u16 *val, + bool external) { int device = (reg_c45 >> 16) & 0x1f; int reg = reg_c45 & 0xffff; @@ -599,8 +600,9 @@ int mv88e6xxx_g2_smi_phy_read_c45(struct mv88e6xxx_chip *chip, int addr, return 0; } -int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, int addr, - int reg, u16 *val, bool external) +static int mv88e6xxx_g2_smi_phy_read_c22(struct mv88e6xxx_chip *chip, + int addr, int reg, u16 *val, + bool external) { u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_READ_DATA | (addr << 5) | reg; int err; @@ -632,8 +634,9 @@ int mv88e6xxx_g2_smi_phy_read(struct mv88e6xxx_chip *chip, return mv88e6xxx_g2_smi_phy_read_c22(chip, addr, reg, val, external); } -int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr, - int reg_c45, u16 val, bool external) +static int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, + int addr, int reg_c45, u16 val, + bool external) { int device = (reg_c45 >> 16) & 0x1f; int reg = reg_c45 & 0xffff; @@ -661,8 +664,9 @@ int mv88e6xxx_g2_smi_phy_write_c45(struct mv88e6xxx_chip *chip, int addr, return 0; } -int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, int addr, - int reg, u16 val, bool external) +static int mv88e6xxx_g2_smi_phy_write_c22(struct mv88e6xxx_chip *chip, + int addr, int reg, u16 val, + bool external) { u16 cmd = GLOBAL2_SMI_PHY_CMD_OP_22_WRITE_DATA | (addr << 5) | reg; int err; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 08676df6cef0..796c2cbc11f6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -127,6 +127,17 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) struct octeon_device *oct = lio->oct_dev; u8 *mac; + if (nctrl->completion && nctrl->response_code) { + /* Signal whoever is interested that the response code from the + * firmware has arrived. + */ + WRITE_ONCE(*nctrl->response_code, nctrl->status); + complete(nctrl->completion); + } + + if (nctrl->status) + return; + switch (nctrl->ncmd.s.cmd) { case OCTNET_CMD_CHANGE_DEVFLAGS: case OCTNET_CMD_SET_MULTI_LIST: diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index fa673a1de24d..927617cbf6a9 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3499,6 +3499,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; @@ -3532,6 +3534,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.more = vxlan_cmd_bit; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 174d748b5928..34c77821fad9 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2484,6 +2484,8 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; + struct completion compl; + u16 response_code; int ret = 0; memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); @@ -2495,14 +2497,25 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; + init_completion(&compl); + nctrl.completion = &compl; + nctrl.response_code = &response_code; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); if (ret < 0) { dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n", ret); + return -EIO; } - return ret; + if (!wait_for_completion_timeout(&compl, + msecs_to_jiffies(nctrl.wait_time))) + return -EPERM; + + if (READ_ONCE(response_code)) + return -EPERM; + + return 0; } static int @@ -2547,6 +2560,8 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; @@ -2579,6 +2594,8 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, struct octnic_ctrl_pkt nctrl; int ret = 0; + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.more = vxlan_cmd_bit; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c index 0243be8dd56f..b457cf23fce6 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c @@ -100,14 +100,16 @@ static void octnet_link_ctrl_callback(struct octeon_device *oct, nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr; - /* Call the callback function if status is OK. - * Status is OK only if a response was expected and core returned - * success. + /* Call the callback function if status is zero (meaning OK) or status + * contains a firmware status code bigger than zero (meaning the + * firmware is reporting an error). * If no response was expected, status is OK if the command was posted * successfully. */ - if (!status && nctrl->cb_fn) + if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) { + nctrl->status = status; nctrl->cb_fn(nctrl); + } octeon_free_soft_command(oct, sc); } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h index 0c7a5c9b2932..6480ef863441 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h @@ -62,6 +62,10 @@ struct octnic_ctrl_pkt { /** Callback function called when the command has been fetched */ octnic_ctrl_pkt_cb_fn_t cb_fn; + + u32 status; + u16 *response_code; + struct completion *completion; }; #define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 150fb52a0737..b7feecfbb5a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -221,6 +221,7 @@ struct mlx5e_params { u8 toeplitz_hash_key[40]; u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE]; bool vlan_strip_disable; + bool scatter_fcs_en; bool rx_am_enabled; u32 lro_timeout; u32 pflags; @@ -842,8 +843,6 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, void mlx5e_enable_vlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv); -int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd); - struct mlx5e_redirect_rqt_param { bool is_rss; union { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index af039b6c0799..ce7b09d72ff6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -42,8 +42,9 @@ static void mlx5e_get_drvinfo(struct net_device *dev, strlcpy(drvinfo->version, DRIVER_VERSION " (" DRIVER_RELDATE ")", sizeof(drvinfo->version)); snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "%d.%d.%d", - fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev)); + "%d.%d.%04d (%.16s)", + fw_rev_maj(mdev), fw_rev_min(mdev), fw_rev_sub(mdev), + mdev->board_id); strlcpy(drvinfo->bus_info, pci_name(mdev->pdev), sizeof(drvinfo->bus_info)); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d5248637d44f..8b7b7e604ea0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -760,6 +760,37 @@ static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, return err; } +static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) +{ + struct mlx5e_channel *c = rq->channel; + struct mlx5e_priv *priv = c->priv; + struct mlx5_core_dev *mdev = priv->mdev; + + void *in; + void *rqc; + int inlen; + int err; + + inlen = MLX5_ST_SZ_BYTES(modify_rq_in); + in = mlx5_vzalloc(inlen); + if (!in) + return -ENOMEM; + + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); + + MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); + MLX5_SET64(modify_rq_in, in, modify_bitmask, + MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); + MLX5_SET(rqc, rqc, scatter_fcs, enable); + MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); + + err = mlx5_core_modify_rq(mdev, rq->rqn, in, inlen); + + kvfree(in); + + return err; +} + static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5e_channel *c = rq->channel; @@ -1388,21 +1419,16 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) mlx5e_free_xdpsq(sq); } -static int mlx5e_alloc_cq(struct mlx5e_channel *c, - struct mlx5e_cq_param *param, - struct mlx5e_cq *cq) +static int mlx5e_alloc_cq_common(struct mlx5_core_dev *mdev, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq) { - struct mlx5_core_dev *mdev = c->mdev; struct mlx5_core_cq *mcq = &cq->mcq; int eqn_not_used; unsigned int irqn; int err; u32 i; - param->wq.buf_numa_node = cpu_to_node(c->cpu); - param->wq.db_numa_node = cpu_to_node(c->cpu); - param->eq_ix = c->ix; - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, &cq->wq_ctrl); if (err) @@ -1410,8 +1436,6 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - cq->napi = &c->napi; - mcq->cqe_sz = 64; mcq->set_ci_db = cq->wq_ctrl.db.db; mcq->arm_db = cq->wq_ctrl.db.db + 1; @@ -1428,12 +1452,30 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, cqe->op_own = 0xf1; } - cq->channel = c; cq->mdev = mdev; return 0; } +static int mlx5e_alloc_cq(struct mlx5e_channel *c, + struct mlx5e_cq_param *param, + struct mlx5e_cq *cq) +{ + struct mlx5_core_dev *mdev = c->priv->mdev; + int err; + + param->wq.buf_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = cpu_to_node(c->cpu); + param->eq_ix = c->ix; + + err = mlx5e_alloc_cq_common(mdev, param, cq); + + cq->napi = &c->napi; + cq->channel = c; + + return err; +} + static void mlx5e_free_cq(struct mlx5e_cq *cq) { mlx5_cqwq_destroy(&cq->wq_ctrl); @@ -1834,6 +1876,7 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, MLX5_SET(wq, wq, pd, priv->mdev->mlx5e_res.pdn); MLX5_SET(rqc, rqc, counter_set_id, priv->q_counter); MLX5_SET(rqc, rqc, vsd, params->vlan_strip_disable); + MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); param->wq.buf_numa_node = dev_to_node(&priv->mdev->pdev->dev); param->wq.linear = 1; @@ -1901,10 +1944,6 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, } mlx5e_build_common_cq_param(priv, param); - - if (params->rx_am_enabled) - params->rx_cq_moderation = - mlx5e_am_get_def_profile(params->rx_cq_period_mode); } static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, @@ -2665,31 +2704,7 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, struct mlx5e_cq *cq, struct mlx5e_cq_param *param) { - struct mlx5_core_cq *mcq = &cq->mcq; - int eqn_not_used; - unsigned int irqn; - int err; - - err = mlx5_cqwq_create(mdev, ¶m->wq, param->cqc, &cq->wq, - &cq->wq_ctrl); - if (err) - return err; - - mlx5_vector2eqn(mdev, param->eq_ix, &eqn_not_used, &irqn); - - mcq->cqe_sz = 64; - mcq->set_ci_db = cq->wq_ctrl.db.db; - mcq->arm_db = cq->wq_ctrl.db.db + 1; - *mcq->set_ci_db = 0; - *mcq->arm_db = 0; - mcq->vector = param->eq_ix; - mcq->comp = mlx5e_completion_event; - mcq->event = mlx5e_cq_error_event; - mcq->irqn = irqn; - - cq->mdev = mdev; - - return 0; + return mlx5e_alloc_cq_common(mdev, param, cq); } static int mlx5e_open_drop_rq(struct mlx5_core_dev *mdev, @@ -2904,7 +2919,21 @@ void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv) mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]); } -int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) +static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) +{ + int err = 0; + int i; + + for (i = 0; i < chs->num; i++) { + err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); + if (err) + return err; + } + + return 0; +} + +static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err = 0; int i; @@ -3121,6 +3150,23 @@ static int set_feature_rx_all(struct net_device *netdev, bool enable) return mlx5_set_port_fcs(mdev, !enable); } +static int set_feature_rx_fcs(struct net_device *netdev, bool enable) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + int err; + + mutex_lock(&priv->state_lock); + + priv->channels.params.scatter_fcs_en = enable; + err = mlx5e_modify_channels_scatter_fcs(&priv->channels, enable); + if (err) + priv->channels.params.scatter_fcs_en = !enable; + + mutex_unlock(&priv->state_lock); + + return err; +} + static int set_feature_rx_vlan(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -3194,6 +3240,8 @@ static int mlx5e_set_features(struct net_device *netdev, set_feature_tc_num_filters); err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL, set_feature_rx_all); + err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS, + set_feature_rx_fcs); err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan); #ifdef CONFIG_RFS_ACCEL @@ -3735,6 +3783,10 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) params->rx_cq_moderation.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; + if (params->rx_am_enabled) + params->rx_cq_moderation = + mlx5e_am_get_def_profile(params->rx_cq_period_mode); + MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER, params->rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE); } @@ -3908,6 +3960,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (fcs_supported) netdev->hw_features |= NETIF_F_RXALL; + if (MLX5_CAP_ETH(mdev, scatter_fcs)) + netdev->hw_features |= NETIF_F_RXFCS; + netdev->features = netdev->hw_features; if (!priv->channels.params.lro_en) netdev->features &= ~NETIF_F_LRO; @@ -3915,6 +3970,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) if (fcs_enabled) netdev->features &= ~NETIF_F_RXALL; + if (!priv->channels.params.scatter_fcs_en) + netdev->features &= ~NETIF_F_RXFCS; + #define FT_CAP(f) MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.f) if (FT_CAP(flow_modify_en) && FT_CAP(modify_root) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 60154a175bd3..9c2bec732af9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1514,8 +1514,10 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x1016), MLX5_PCI_DEV_IS_VF}, /* ConnectX-4LX VF */ { PCI_VDEVICE(MELLANOX, 0x1017) }, /* ConnectX-5, PCIe 3.0 */ { PCI_VDEVICE(MELLANOX, 0x1018), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 VF */ - { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5, PCIe 4.0 */ - { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5, PCIe 4.0 VF */ + { PCI_VDEVICE(MELLANOX, 0x1019) }, /* ConnectX-5 Ex */ + { PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF}, /* ConnectX-5 Ex VF */ + { PCI_VDEVICE(MELLANOX, 0x101b) }, /* ConnectX-6 */ + { PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF}, /* ConnectX-6 VF */ { 0, } }; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 3e1f97e88710..4c6863a072d3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -495,8 +495,7 @@ static void nfp_net_refresh_netdevs(struct work_struct *work) list_for_each_entry_safe(nn, next, &pf->ports, port_list) { if (!nn->eth_port) { - nfp_warn(pf->cpp, "Warning: port %d not present after reconfig\n", - nn->eth_port->eth_index); + nfp_warn(pf->cpp, "Warning: port not present after reconfig\n"); continue; } if (!nn->eth_port->override_changed) diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index e998e2f7a619..7ab06b338a14 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1289,6 +1289,21 @@ int netvsc_device_add(struct hv_device *device, */ set_channel_read_mode(device->channel, HV_CALL_ISR); + /* If we're reopening the device we may have multiple queues, fill the + * chn_table with the default channel to use it before subchannels are + * opened. + * Initialize the channel state before we open; + * we can be interrupted as soon as we open the channel. + */ + + for (i = 0; i < VRSS_CHANNEL_MAX; i++) { + struct netvsc_channel *nvchan = &net_device->chan_table[i]; + + nvchan->channel = device->channel; + netif_napi_add(ndev, &nvchan->napi, + netvsc_poll, NAPI_POLL_WEIGHT); + } + /* Open the channel */ ret = vmbus_open(device->channel, ring_size * PAGE_SIZE, ring_size * PAGE_SIZE, NULL, 0, @@ -1303,18 +1318,6 @@ int netvsc_device_add(struct hv_device *device, /* Channel is opened */ netdev_dbg(ndev, "hv_netvsc channel opened successfully\n"); - /* If we're reopening the device we may have multiple queues, fill the - * chn_table with the default channel to use it before subchannels are - * opened. - */ - for (i = 0; i < VRSS_CHANNEL_MAX; i++) { - struct netvsc_channel *nvchan = &net_device->chan_table[i]; - - nvchan->channel = device->channel; - netif_napi_add(ndev, &nvchan->napi, - netvsc_poll, NAPI_POLL_WEIGHT); - } - /* Enable NAPI handler for init callbacks */ napi_enable(&net_device->chan_table[0].napi); diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 983582526b37..1e9445bc4539 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1007,12 +1007,13 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc) */ set_channel_read_mode(new_sc, HV_CALL_ISR); + /* Set the channel before opening.*/ + nvchan->channel = new_sc; + ret = vmbus_open(new_sc, nvscdev->ring_size * PAGE_SIZE, nvscdev->ring_size * PAGE_SIZE, NULL, 0, netvsc_channel_cb, nvchan); - if (ret == 0) - nvchan->channel = new_sc; napi_enable(&nvchan->napi); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 56bc842b0620..1993adbd2c82 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5122,6 +5122,7 @@ struct mlx5_ifc_modify_rq_out_bits { enum { MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_VSD = 1ULL << 1, + MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS = 1ULL << 2, MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_RQ_COUNTER_SET_ID = 1ULL << 3, }; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c776abd86937..741d75cfc686 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -413,14 +413,15 @@ struct ubuf_info { * the end of the header data, ie. at skb->end. */ struct skb_shared_info { + unsigned short _unused; unsigned char nr_frags; __u8 tx_flags; unsigned short gso_size; /* Warning: this field is not always filled in (UFO)! */ unsigned short gso_segs; - unsigned short gso_type; struct sk_buff *frag_list; struct skb_shared_hwtstamps hwtstamps; + unsigned int gso_type; u32 tskey; __be32 ip6_frag_id; diff --git a/include/net/dsa.h b/include/net/dsa.h index 7ba9b1fb565c..9b1c1eb4147a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -124,7 +124,7 @@ struct dsa_switch_tree { * protocol to use. */ struct net_device *master_netdev; - int (*rcv)(struct sk_buff *skb, + struct sk_buff * (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index c98a52fb572a..2b488565599d 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -98,4 +98,6 @@ #define SO_INCOMING_NAPI_ID 56 +#define SO_COOKIE 57 + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index f3946a27bd07..b2c9c26ea30f 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -50,12 +50,12 @@ struct nlmsghdr { /* Flags values */ -#define NLM_F_REQUEST 1 /* It is request message. */ -#define NLM_F_MULTI 2 /* Multipart message, terminated by NLMSG_DONE */ -#define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ -#define NLM_F_ECHO 8 /* Echo this request */ -#define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ -#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */ +#define NLM_F_REQUEST 0x01 /* It is request message. */ +#define NLM_F_MULTI 0x02 /* Multipart message, terminated by NLMSG_DONE */ +#define NLM_F_ACK 0x04 /* Reply with ack, with zero or error code */ +#define NLM_F_ECHO 0x08 /* Echo this request */ +#define NLM_F_DUMP_INTR 0x10 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 0x20 /* Dump was filtered as requested */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ diff --git a/net/core/sock.c b/net/core/sock.c index 392f9b6f96e2..a06bb7a2a689 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1083,6 +1083,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, union { int val; + u64 val64; struct linger ling; struct timeval tm; } v; @@ -1340,6 +1341,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; #endif + case SO_COOKIE: + lv = sizeof(u64); + if (len < lv) + return -EINVAL; + v.val64 = sock_gen_cookie(sk); + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 6cad15da5892..1fb9cf7aaaf4 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -23,6 +23,7 @@ #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/gpio/consumer.h> +#include <linux/etherdevice.h> #include <net/dsa.h> #include "dsa_priv.h" @@ -900,13 +901,34 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; + struct sk_buff *nskb = NULL; if (unlikely(dst == NULL)) { kfree_skb(skb); return 0; } - return dst->rcv(skb, dev, pt, orig_dev); + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + return 0; + + nskb = dst->rcv(skb, dev, pt, orig_dev); + if (!nskb) { + kfree_skb(skb); + return 0; + } + + skb = nskb; + skb_push(skb, ETH_HLEN); + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, skb->dev); + + skb->dev->stats.rx_packets++; + skb->dev->stats.rx_bytes += skb->len; + + netif_receive_skb(skb); + + return 0; } static struct packet_type dsa_pack_type __read_mostly = { diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 2a3139921811..107138a55bd8 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -17,8 +17,9 @@ struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); - int (*rcv)(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev); + struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev); }; struct dsa_slave_priv { diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index e2ed6cf68261..2a9b52c5af86 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -92,23 +92,17 @@ out_free: return NULL; } -static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; int source_port; u8 *brcm_tag; - if (unlikely(dst == NULL)) - goto out_drop; - ds = dst->cpu_switch; - skb = skb_unshare(skb, GFP_ATOMIC); - if (skb == NULL) - goto out; - if (unlikely(!pskb_may_pull(skb, BRCM_TAG_LEN))) goto out_drop; @@ -140,22 +134,12 @@ static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb->data - ETH_HLEN - BRCM_TAG_LEN, 2 * ETH_ALEN); - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; skb->dev = ds->ports[source_port].netdev; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops brcm_netdev_ops = { diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index e42ba906100c..1c6633f0de01 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -68,8 +68,9 @@ out_free: return NULL; } -static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; @@ -77,13 +78,6 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, int source_device; int source_port; - if (unlikely(dst == NULL)) - goto out_drop; - - skb = skb_unshare(skb, GFP_ATOMIC); - if (skb == NULL) - goto out; - if (unlikely(!pskb_may_pull(skb, DSA_HLEN))) goto out_drop; @@ -165,21 +159,11 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, } skb->dev = ds->ports[source_port].netdev; - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops dsa_netdev_ops = { diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 6a9b7a9e4e15..d9c668aa5e54 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -81,8 +81,9 @@ out_free: return NULL; } -static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; @@ -90,13 +91,6 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, int source_device; int source_port; - if (unlikely(dst == NULL)) - goto out_drop; - - skb = skb_unshare(skb, GFP_ATOMIC); - if (skb == NULL) - goto out; - if (unlikely(!pskb_may_pull(skb, EDSA_HLEN))) goto out_drop; @@ -184,21 +178,11 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, } skb->dev = ds->ports[source_port].netdev; - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops edsa_netdev_ops = { diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 44ae6353a521..837cdddb53f0 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -47,21 +47,15 @@ out_free: return NULL; } -static int mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; int port; __be16 *phdr, hdr; - if (unlikely(!dst)) - goto out_drop; - - skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) - goto out; - if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) goto out_drop; @@ -92,24 +86,12 @@ static int mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!ds->ports[port].netdev) goto out_drop; - /* Update skb & forward the frame accordingly */ - skb_push(skb, ETH_HLEN); - - skb->pkt_type = PACKET_HOST; skb->dev = ds->ports[port].netdev; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops mtk_netdev_ops = { diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 4e0dad759d04..3ba3f59f7a34 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -66,8 +66,9 @@ out_free: return NULL; } -static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; @@ -75,13 +76,6 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, int port; __be16 *phdr, hdr; - if (unlikely(!dst)) - goto out_drop; - - skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) - goto out; - if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) goto out_drop; @@ -115,22 +109,12 @@ static int qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, goto out_drop; /* Update skb & forward the frame accordingly */ - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; skb->dev = ds->ports[port].netdev; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops qca_netdev_ops = { diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 74c948512550..aafc2fc74c30 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -58,22 +58,17 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) return nskb; } -static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, + struct net_device *orig_dev) { struct dsa_switch_tree *dst = dev->dsa_ptr; struct dsa_switch *ds; u8 *trailer; int source_port; - if (unlikely(dst == NULL)) - goto out_drop; ds = dst->cpu_switch; - skb = skb_unshare(skb, GFP_ATOMIC); - if (skb == NULL) - goto out; - if (skb_linearize(skb)) goto out_drop; @@ -89,21 +84,11 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, pskb_trim_rcsum(skb, skb->len - 4); skb->dev = ds->ports[source_port].netdev; - skb_push(skb, ETH_HLEN); - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, skb->dev); - - skb->dev->stats.rx_packets++; - skb->dev->stats.rx_bytes += skb->len; - netif_receive_skb(skb); - - return 0; + return skb; out_drop: - kfree_skb(skb); -out: - return 0; + return NULL; } const struct dsa_device_ops trailer_netdev_ops = { diff --git a/samples/bpf/cookie_uid_helper_example.c b/samples/bpf/cookie_uid_helper_example.c index f6e5e58931c5..ad5afedf2e70 100644 --- a/samples/bpf/cookie_uid_helper_example.c +++ b/samples/bpf/cookie_uid_helper_example.c @@ -4,10 +4,11 @@ * program into the xt_bpf match. * * TEST: - * ./run_cookie_uid_helper_example.sh - * Then generate some traffic in variate ways. ping 0 -c 10 would work - * but the cookie and uid in this case could both be 0. A sample output - * with some traffic generated by web browser is shown below: + * ./run_cookie_uid_helper_example.sh -option + * option: + * -t: do traffic monitoring test, the program will continuously + * print out network traffic happens after program started A sample + * output is shown below: * * cookie: 877, uid: 0x3e8, Pakcet Count: 20, Bytes Count: 11058 * cookie: 132, uid: 0x0, Pakcet Count: 2, Bytes Count: 286 @@ -18,6 +19,10 @@ * cookie: 0, uid: 0x0, Pakcet Count: 6, Bytes Count: 712 * cookie: 880, uid: 0xfffe, Pakcet Count: 1, Bytes Count: 70 * + * -s: do getsockopt SO_COOKIE test, the program will set up a pair of + * UDP sockets and send packets between them. And read out the traffic data + * directly from the ebpf map based on the socket cookie. + * * Clean up: if using shell script, the script file will delete the iptables * rule and unmount the bpf program when exit. Else the iptables rule need * to be deleted by hand, see run_cookie_uid_helper_example.sh for detail. @@ -34,6 +39,8 @@ #include <limits.h> #include <linux/bpf.h> #include <linux/if_ether.h> +#include <net/if.h> +#include <signal.h> #include <stdbool.h> #include <stdint.h> #include <stdio.h> @@ -46,6 +53,8 @@ #include <bpf/bpf.h> #include "libbpf.h" +#define PORT 8888 + struct stats { uint32_t uid; uint64_t packets; @@ -54,6 +63,8 @@ struct stats { static int map_fd, prog_fd; +static bool test_finish; + static void maps_create(void) { map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(uint32_t), @@ -164,7 +175,7 @@ static void prog_attach_iptables(char *file) printf("file path too long: %s\n", file); exit(1); } - sprintf(rules, "iptables -A INPUT -m bpf --object-pinned %s -j ACCEPT", + sprintf(rules, "iptables -A OUTPUT -m bpf --object-pinned %s -j ACCEPT", file); ret = system(rules); if (ret < 0) { @@ -177,7 +188,8 @@ static void print_table(void) { struct stats curEntry; uint32_t curN = UINT32_MAX; - uint32_t nextN, res; + uint32_t nextN; + int res; while (bpf_map_get_next_key(map_fd, &curN, &nextN) > -1) { curN = nextN; @@ -193,25 +205,117 @@ static void print_table(void) } } -int main(int argc, char *argv[]) +static void udp_client(void) { - if (argc > 2) { - printf("Too many argument provided\n"); - return 1; - } else if (argc < 2) { - printf("Usage: %s bpfObjName\n", argv[0]); - return 1; + struct sockaddr_in si_other = {0}; + struct sockaddr_in si_me = {0}; + struct stats dataEntry; + int s_rcv, s_send, i, recv_len; + char message = 'a'; + char buf; + uint64_t cookie; + int res; + socklen_t cookie_len = sizeof(cookie); + socklen_t slen = sizeof(si_other); + + s_rcv = socket(PF_INET, SOCK_DGRAM, 0); + if (s_rcv < 0) + error(1, errno, "rcv socket creat failed!\n"); + si_other.sin_family = AF_INET; + si_other.sin_port = htons(PORT); + if (inet_aton("127.0.0.1", &si_other.sin_addr) == 0) + error(1, errno, "inet_aton\n"); + if (bind(s_rcv, (struct sockaddr *)&si_other, sizeof(si_other)) == -1) + error(1, errno, "bind\n"); + s_send = socket(PF_INET, SOCK_DGRAM, 0); + if (s_send < 0) + error(1, errno, "send socket creat failed!\n"); + res = getsockopt(s_send, SOL_SOCKET, SO_COOKIE, &cookie, &cookie_len); + if (res < 0) + printf("get cookie failed: %s\n", strerror(errno)); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res != -1) + error(1, errno, "socket stat found while flow not active\n"); + for (i = 0; i < 10; i++) { + res = sendto(s_send, &message, sizeof(message), 0, + (struct sockaddr *)&si_other, slen); + if (res == -1) + error(1, errno, "send\n"); + if (res != sizeof(message)) + error(1, 0, "%uB != %luB\n", res, sizeof(message)); + recv_len = recvfrom(s_rcv, &buf, sizeof(buf), 0, + (struct sockaddr *)&si_me, &slen); + if (recv_len < 0) + error(1, errno, "revieve\n"); + res = memcmp(&(si_other.sin_addr), &(si_me.sin_addr), + sizeof(si_me.sin_addr)); + if (res != 0) + error(1, EFAULT, "sender addr error: %d\n", res); + printf("Message received: %c\n", buf); + res = bpf_map_lookup_elem(map_fd, &cookie, &dataEntry); + if (res < 0) + error(1, errno, "lookup sk stat failed, cookie: %lu\n", + cookie); + printf("cookie: %lu, uid: 0x%x, Packet Count: %lu," + " Bytes Count: %lu\n\n", cookie, dataEntry.uid, + dataEntry.packets, dataEntry.bytes); } + close(s_send); + close(s_rcv); +} - maps_create(); - prog_load(); - prog_attach_iptables(argv[1]); +static int usage(void) +{ + printf("Usage: ./run_cookie_uid_helper_example.sh" + " bpfObjName -option\n" + " -t traffic monitor test\n" + " -s getsockopt cookie test\n"); + return 1; +} - while (true) { - print_table(); - printf("\n"); - sleep(1); - }; +void finish(int ret) +{ + test_finish = true; +} + +int main(int argc, char *argv[]) +{ + int opt; + bool cfg_test_traffic = false; + bool cfg_test_cookie = false; + + if (argc != 3) + return usage(); + while ((opt = getopt(argc, argv, "ts")) != -1) { + switch (opt) { + case 't': + cfg_test_traffic = true; + break; + case 's': + cfg_test_cookie = true; + break; + default: + printf("unknown option %c\n", opt); + usage(); + return -1; + } + } + maps_create(); + prog_load(); + prog_attach_iptables(argv[2]); + if (cfg_test_traffic) { + if (signal(SIGINT, finish) == SIG_ERR) + error(1, errno, "register handler failed"); + while (!test_finish) { + print_table(); + printf("\n"); + sleep(1); + }; + } else if (cfg_test_cookie) { + udp_client(); + } + close(prog_fd); + close(map_fd); return 0; } diff --git a/samples/bpf/run_cookie_uid_helper_example.sh b/samples/bpf/run_cookie_uid_helper_example.sh index 40da8aa75c44..f898cfa2b1aa 100644..100755 --- a/samples/bpf/run_cookie_uid_helper_example.sh +++ b/samples/bpf/run_cookie_uid_helper_example.sh @@ -4,11 +4,11 @@ root_dir=$local_dir/../.. mnt_dir=$(mktemp -d --tmp) on_exit() { - iptables -D INPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT + iptables -D OUTPUT -m bpf --object-pinned ${mnt_dir}/bpf_prog -j ACCEPT umount ${mnt_dir} rm -r ${mnt_dir} } trap on_exit EXIT mount -t bpf bpf ${mnt_dir} -./per_socket_stats_example ${mnt_dir}/bpf_prog +./per_socket_stats_example ${mnt_dir}/bpf_prog $1 |