diff options
42 files changed, 2234 insertions, 810 deletions
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d757d9dcba51..d0cba2d1cd68 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1600,6 +1600,21 @@ mt7530_hw_vlan_update(struct mt7530_priv *priv, u16 vid, } static int +mt7530_setup_vlan0(struct mt7530_priv *priv) +{ + u32 val; + + /* Validate the entry with independent learning, keep the original + * ingress tag attribute. + */ + val = IVL_MAC | EG_CON | PORT_MEM(MT7530_ALL_MEMBERS) | FID(FID_BRIDGED) | + VLAN_VALID; + mt7530_write(priv, MT7530_VAWD1, val); + + return mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, 0); +} + +static int mt7530_port_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) @@ -2174,6 +2189,11 @@ mt7530_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Setup VLAN ID 0 for VLAN-unaware bridges */ + ret = mt7530_setup_vlan0(priv); + if (ret) + return ret; + /* Setup port 5 */ priv->p5_intf_sel = P5_DISABLED; interface = PHY_INTERFACE_MODE_NA; @@ -2346,6 +2366,11 @@ mt7531_setup(struct dsa_switch *ds) PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); } + /* Setup VLAN ID 0 for VLAN-unaware bridges */ + ret = mt7530_setup_vlan0(priv); + if (ret) + return ret; + ds->assisted_learning_on_cpu_port = true; ds->mtu_enforcement_ingress = true; diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index fe4cd2ac26d0..91508e2feef9 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -145,6 +145,8 @@ enum mt7530_vlan_cmd { #define PORT_STAG BIT(31) /* Independent VLAN Learning */ #define IVL_MAC BIT(30) +/* Egress Tag Consistent */ +#define EG_CON BIT(29) /* Per VLAN Egress Tag Control */ #define VTAG_EN BIT(28) /* VLAN Member Control */ diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 2e899c9f036d..5e5d24e7c02b 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -115,12 +115,6 @@ struct sja1105_info { const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; const struct sja1105_regs *regs; - /* Both E/T and P/Q/R/S have quirks when it comes to popping the S-Tag - * from double-tagged frames. E/T will pop it only when it's equal to - * TPID from the General Parameters Table, while P/Q/R/S will only - * pop it when it's equal to TPID2. - */ - u16 qinq_tpid; bool can_limit_mcast_flood; int (*reset_cmd)(struct dsa_switch *ds); int (*setup_rgmii_delay)(const void *ctx, int port); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 05ba65042b5f..2f8cc6686c38 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -26,7 +26,6 @@ #include "sja1105_tas.h" #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull -#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, unsigned int startup_delay) @@ -120,11 +119,23 @@ static int sja1105_commit_pvid(struct dsa_switch *ds, int port) if (rc) return rc; - vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries; + /* Only force dropping of untagged packets when the port is under a + * VLAN-aware bridge. When the tag_8021q pvid is used, we are + * deliberately removing the RX VLAN from the port's VMEMB_PORT list, + * to prevent DSA tag spoofing from the link partner. Untagged packets + * are the only ones that should be received with tag_8021q, so + * definitely don't drop them. + */ + if (pvid == priv->bridge_pvid[port]) { + vlan = priv->static_config.tables[BLK_IDX_VLAN_LOOKUP].entries; - match = sja1105_is_vlan_configured(priv, pvid); + match = sja1105_is_vlan_configured(priv, pvid); - if (match < 0 || !(vlan[match].vmemb_port & BIT(port))) + if (match < 0 || !(vlan[match].vmemb_port & BIT(port))) + drop_untagged = true; + } + + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) drop_untagged = true; return sja1105_drop_untagged(ds, port, drop_untagged); @@ -208,6 +219,12 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) */ if (dsa_port_is_dsa(dp)) dp->learning = true; + + /* Disallow untagged packets from being received on the + * CPU and DSA ports. + */ + if (dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp)) + mac[dp->index].drpuntag = true; } return 0; @@ -2278,15 +2295,6 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, tpid2 = ETH_P_SJA1105; } - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; - - if (enabled) - sp->xmit_tpid = priv->info->qinq_tpid; - else - sp->xmit_tpid = ETH_P_SJA1105; - } - if (priv->vlan_aware == enabled) return 0; @@ -2343,7 +2351,7 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, } static int sja1105_vlan_add(struct sja1105_private *priv, int port, u16 vid, - u16 flags) + u16 flags, bool allowed_ingress) { struct sja1105_vlan_lookup_entry *vlan; struct sja1105_table *table; @@ -2365,7 +2373,12 @@ static int sja1105_vlan_add(struct sja1105_private *priv, int port, u16 vid, vlan[match].type_entry = SJA1110_VLAN_D_TAG; vlan[match].vlanid = vid; vlan[match].vlan_bc |= BIT(port); - vlan[match].vmemb_port |= BIT(port); + + if (allowed_ingress) + vlan[match].vmemb_port |= BIT(port); + else + vlan[match].vmemb_port &= ~BIT(port); + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) vlan[match].tag_port &= ~BIT(port); else @@ -2437,7 +2450,7 @@ static int sja1105_bridge_vlan_add(struct dsa_switch *ds, int port, if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) flags = 0; - rc = sja1105_vlan_add(priv, port, vlan->vid, flags); + rc = sja1105_vlan_add(priv, port, vlan->vid, flags, true); if (rc) return rc; @@ -2467,9 +2480,16 @@ static int sja1105_dsa_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid, u16 flags) { struct sja1105_private *priv = ds->priv; + bool allowed_ingress = true; int rc; - rc = sja1105_vlan_add(priv, port, vid, flags); + /* Prevent attackers from trying to inject a DSA tag from + * the outside world. + */ + if (dsa_is_user_port(ds, port)) + allowed_ingress = false; + + rc = sja1105_vlan_add(priv, port, vid, flags, allowed_ingress); if (rc) return rc; @@ -2959,7 +2979,6 @@ static int sja1105_setup_ports(struct sja1105_private *priv) } sp->xmit_worker = worker; skb_queue_head_init(&sp->xmit_queue); - sp->xmit_tpid = ETH_P_SJA1105; } return 0; diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 08cc5dbf2fa6..d60a530d0272 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -575,7 +575,6 @@ const struct sja1105_info sja1105e_info = { .part_no = SJA1105ET_PART_NO, .static_ops = sja1105e_table_ops, .dyn_ops = sja1105et_dyn_ops, - .qinq_tpid = ETH_P_8021Q, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, @@ -608,7 +607,6 @@ const struct sja1105_info sja1105t_info = { .part_no = SJA1105ET_PART_NO, .static_ops = sja1105t_table_ops, .dyn_ops = sja1105et_dyn_ops, - .qinq_tpid = ETH_P_8021Q, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, @@ -641,7 +639,6 @@ const struct sja1105_info sja1105p_info = { .part_no = SJA1105P_PART_NO, .static_ops = sja1105p_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -675,7 +672,6 @@ const struct sja1105_info sja1105q_info = { .part_no = SJA1105Q_PART_NO, .static_ops = sja1105q_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -709,7 +705,6 @@ const struct sja1105_info sja1105r_info = { .part_no = SJA1105R_PART_NO, .static_ops = sja1105r_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -747,7 +742,6 @@ const struct sja1105_info sja1105s_info = { .static_ops = sja1105s_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .regs = &sja1105pqrs_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, @@ -784,7 +778,6 @@ const struct sja1105_info sja1110a_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -835,7 +828,6 @@ const struct sja1105_info sja1110b_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -886,7 +878,6 @@ const struct sja1105_info sja1110c_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, @@ -937,7 +928,6 @@ const struct sja1105_info sja1110d_info = { .static_ops = sja1110_table_ops, .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, - .qinq_tpid = ETH_P_8021AD, .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, .multiple_cascade_ports = true, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index ecea3cdd30b3..9058f09f921e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -84,6 +84,7 @@ extern struct mutex uld_mutex; enum { MAX_NPORTS = 4, /* max # of ports */ SERNUM_LEN = 24, /* Serial # length */ + EC_LEN = 16, /* E/C length */ ID_LEN = 16, /* ID length */ PN_LEN = 16, /* Part Number length */ MACADDR_LEN = 12, /* MAC Address length */ @@ -390,6 +391,7 @@ struct tp_params { struct vpd_params { unsigned int cclk; + u8 ec[EC_LEN + 1]; u8 sn[SERNUM_LEN + 1]; u8 id[ID_LEN + 1]; u8 pn[PN_LEN + 1]; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 70bb057320e4..6606fb8b3e42 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2744,6 +2744,7 @@ int t4_seeprom_wp(struct adapter *adapter, bool enable) int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) { int i, ret = 0, addr; + int ec, sn, pn, na; u8 *vpd, csum, base_val = 0; unsigned int vpdr_len, kw_offset, id_len; @@ -2771,6 +2772,23 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) } id_len = pci_vpd_lrdt_size(vpd); + if (id_len > ID_LEN) + id_len = ID_LEN; + + i = pci_vpd_find_tag(vpd, VPD_LEN, PCI_VPD_LRDT_RO_DATA); + if (i < 0) { + dev_err(adapter->pdev_dev, "missing VPD-R section\n"); + ret = -EINVAL; + goto out; + } + + vpdr_len = pci_vpd_lrdt_size(&vpd[i]); + kw_offset = i + PCI_VPD_LRDT_TAG_SIZE; + if (vpdr_len + kw_offset > VPD_LEN) { + dev_err(adapter->pdev_dev, "bad VPD-R length %u\n", vpdr_len); + ret = -EINVAL; + goto out; + } #define FIND_VPD_KW(var, name) do { \ var = pci_vpd_find_info_keyword(vpd, kw_offset, vpdr_len, name); \ @@ -2793,14 +2811,28 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) goto out; } + FIND_VPD_KW(ec, "EC"); + FIND_VPD_KW(sn, "SN"); + FIND_VPD_KW(pn, "PN"); + FIND_VPD_KW(na, "NA"); +#undef FIND_VPD_KW + + memcpy(p->id, vpd + PCI_VPD_LRDT_TAG_SIZE, id_len); + strim(p->id); + memcpy(p->ec, vpd + ec, EC_LEN); + strim(p->ec); + i = pci_vpd_info_field_size(vpd + sn - PCI_VPD_INFO_FLD_HDR_SIZE); + memcpy(p->sn, vpd + sn, min(i, SERNUM_LEN)); + strim(p->sn); + i = pci_vpd_info_field_size(vpd + pn - PCI_VPD_INFO_FLD_HDR_SIZE); + memcpy(p->pn, vpd + pn, min(i, PN_LEN)); + strim(p->pn); + memcpy(p->na, vpd + na, min(i, MACADDR_LEN)); + strim((char *)p->na); + out: vfree(vpd); - if (ret < 0) { - dev_err(adapter->pdev_dev, "error reading VPD\n"); - return ret; - } - - return 0; + return ret < 0 ? ret : 0; } /** diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index a0ecfe5a4078..2d17a6da63cf 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -227,6 +227,7 @@ struct igc_adapter { struct timecounter tc; struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */ ktime_t ptp_reset_start; /* Reset time in clock mono */ + struct system_time_snapshot snapshot; char fw_version[32]; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index c6315690e20f..c40563350a5e 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -523,6 +523,37 @@ #define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */ #define IGC_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ +/* PCIe PTM Control */ +#define IGC_PTM_CTRL_START_NOW BIT(29) /* Start PTM Now */ +#define IGC_PTM_CTRL_EN BIT(30) /* Enable PTM */ +#define IGC_PTM_CTRL_TRIG BIT(31) /* PTM Cycle trigger */ +#define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x2f) << 2) +#define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8) + +#define IGC_PTM_SHORT_CYC_DEFAULT 10 /* Default Short/interrupted cycle interval */ +#define IGC_PTM_CYC_TIME_DEFAULT 5 /* Default PTM cycle time */ +#define IGC_PTM_TIMEOUT_DEFAULT 255 /* Default timeout for PTM errors */ + +/* PCIe Digital Delay */ +#define IGC_PCIE_DIG_DELAY_DEFAULT 0x01440000 + +/* PCIe PHY Delay */ +#define IGC_PCIE_PHY_DELAY_DEFAULT 0x40900000 + +#define IGC_TIMADJ_ADJUST_METH 0x40000000 + +/* PCIe PTM Status */ +#define IGC_PTM_STAT_VALID BIT(0) /* PTM Status */ +#define IGC_PTM_STAT_RET_ERR BIT(1) /* Root port timeout */ +#define IGC_PTM_STAT_BAD_PTM_RES BIT(2) /* PTM Response msg instead of PTM Response Data */ +#define IGC_PTM_STAT_T4M1_OVFL BIT(3) /* T4 minus T1 overflow */ +#define IGC_PTM_STAT_ADJUST_1ST BIT(4) /* 1588 timer adjusted during 1st PTM cycle */ +#define IGC_PTM_STAT_ADJUST_CYC BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */ + +/* PCIe PTM Cycle Control */ +#define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec) ((msec) & 0x3ff) /* PTM Cycle Time (msec) */ +#define IGC_PTM_CYCLE_CTRL_AUTO_CYC_EN BIT(31) /* PTM Cycle Control */ + /* GPY211 - I225 defines */ #define GPY_MMD_MASK 0xFFFF0000 #define GPY_MMD_SHIFT 16 diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index b7aab35c1132..db1c63e8802a 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -12,6 +12,8 @@ #include <net/pkt_sched.h> #include <linux/bpf_trace.h> #include <net/xdp_sock_drv.h> +#include <linux/pci.h> + #include <net/ipv6.h> #include "igc.h" @@ -6174,6 +6176,10 @@ static int igc_probe(struct pci_dev *pdev, pci_enable_pcie_error_reporting(pdev); + err = pci_enable_ptm(pdev, NULL); + if (err < 0) + dev_info(&pdev->dev, "PCIe PTM not supported by PCIe bus/controller\n"); + pci_set_master(pdev); err = -ENOMEM; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 69617d2c1be2..f6848181cdbd 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -9,6 +9,8 @@ #include <linux/ptp_classify.h> #include <linux/clocksource.h> #include <linux/ktime.h> +#include <linux/delay.h> +#include <linux/iopoll.h> #define INCVALUE_MASK 0x7fffffff #define ISGN 0x80000000 @@ -16,6 +18,9 @@ #define IGC_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) #define IGC_PTP_TX_TIMEOUT (HZ * 15) +#define IGC_PTM_STAT_SLEEP 2 +#define IGC_PTM_STAT_TIMEOUT 100 + /* SYSTIM read access for I225 */ void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts) { @@ -752,6 +757,147 @@ int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr) -EFAULT : 0; } +/* The two conditions below must be met for cross timestamping via + * PCIe PTM: + * + * 1. We have an way to convert the timestamps in the PTM messages + * to something related to the system clocks (right now, only + * X86 systems with support for the Always Running Timer allow that); + * + * 2. We have PTM enabled in the path from the device to the PCIe root port. + */ +static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) +{ + return IS_ENABLED(CONFIG_X86_TSC) ? pcie_ptm_enabled(adapter->pdev) : false; +} + +static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) +{ +#if IS_ENABLED(CONFIG_X86_TSC) + return convert_art_ns_to_tsc(tstamp); +#else + return (struct system_counterval_t) { }; +#endif +} + +static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat) +{ + struct net_device *netdev = adapter->netdev; + + switch (ptm_stat) { + case IGC_PTM_STAT_RET_ERR: + netdev_err(netdev, "PTM Error: Root port timeout\n"); + break; + case IGC_PTM_STAT_BAD_PTM_RES: + netdev_err(netdev, "PTM Error: Bad response, PTM Response Data expected\n"); + break; + case IGC_PTM_STAT_T4M1_OVFL: + netdev_err(netdev, "PTM Error: T4 minus T1 overflow\n"); + break; + case IGC_PTM_STAT_ADJUST_1ST: + netdev_err(netdev, "PTM Error: 1588 timer adjusted during first PTM cycle\n"); + break; + case IGC_PTM_STAT_ADJUST_CYC: + netdev_err(netdev, "PTM Error: 1588 timer adjusted during non-first PTM cycle\n"); + break; + default: + netdev_err(netdev, "PTM Error: Unknown error (%#x)\n", ptm_stat); + break; + } +} + +static int igc_phc_get_syncdevicetime(ktime_t *device, + struct system_counterval_t *system, + void *ctx) +{ + u32 stat, t2_curr_h, t2_curr_l, ctrl; + struct igc_adapter *adapter = ctx; + struct igc_hw *hw = &adapter->hw; + int err, count = 100; + ktime_t t1, t2_curr; + + /* Get a snapshot of system clocks to use as historic value. */ + ktime_get_snapshot(&adapter->snapshot); + + do { + /* Doing this in a loop because in the event of a + * badly timed (ha!) system clock adjustment, we may + * get PTM errors from the PCI root, but these errors + * are transitory. Repeating the process returns valid + * data eventually. + */ + + /* To "manually" start the PTM cycle we need to clear and + * then set again the TRIG bit. + */ + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + ctrl |= IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + + /* The cycle only starts "for real" when software notifies + * that it has read the registers, this is done by setting + * VALID bit. + */ + wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + + err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat, + stat, IGC_PTM_STAT_SLEEP, + IGC_PTM_STAT_TIMEOUT); + if (err < 0) { + netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n"); + return err; + } + + if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID) + break; + + if (stat & ~IGC_PTM_STAT_VALID) { + /* An error occurred, log it. */ + igc_ptm_log_error(adapter, stat); + /* The STAT register is write-1-to-clear (W1C), + * so write the previous error status to clear it. + */ + wr32(IGC_PTM_STAT, stat); + continue; + } + } while (--count); + + if (!count) { + netdev_err(adapter->netdev, "Exceeded number of tries for PTM cycle\n"); + return -ETIMEDOUT; + } + + t1 = ktime_set(rd32(IGC_PTM_T1_TIM0_H), rd32(IGC_PTM_T1_TIM0_L)); + + t2_curr_l = rd32(IGC_PTM_CURR_T2_L); + t2_curr_h = rd32(IGC_PTM_CURR_T2_H); + + /* FIXME: When the register that tells the endianness of the + * PTM registers are implemented, check them here and add the + * appropriate conversion. + */ + t2_curr_h = swab32(t2_curr_h); + + t2_curr = ((s64)t2_curr_h << 32 | t2_curr_l); + + *device = t1; + *system = igc_device_tstamp_to_system(t2_curr); + + return 0; +} + +static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp, + struct system_device_crosststamp *cts) +{ + struct igc_adapter *adapter = container_of(ptp, struct igc_adapter, + ptp_caps); + + return get_device_system_crosststamp(igc_phc_get_syncdevicetime, + adapter, &adapter->snapshot, cts); +} + /** * igc_ptp_init - Initialize PTP functionality * @adapter: Board private structure @@ -788,6 +934,11 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->ptp_caps.n_per_out = IGC_N_PEROUT; adapter->ptp_caps.n_pins = IGC_N_SDP; adapter->ptp_caps.verify = igc_ptp_verify_pin; + + if (!igc_is_crosststamp_supported(adapter)) + break; + + adapter->ptp_caps.getcrosststamp = igc_ptp_getcrosststamp; break; default: adapter->ptp_clock = NULL; @@ -878,7 +1029,9 @@ void igc_ptp_stop(struct igc_adapter *adapter) void igc_ptp_reset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + u32 cycle_ctrl, ctrl; unsigned long flags; + u32 timadj; /* reset the tstamp_config */ igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); @@ -887,12 +1040,38 @@ void igc_ptp_reset(struct igc_adapter *adapter) switch (adapter->hw.mac.type) { case igc_i225: + timadj = rd32(IGC_TIMADJ); + timadj |= IGC_TIMADJ_ADJUST_METH; + wr32(IGC_TIMADJ, timadj); + wr32(IGC_TSAUXC, 0x0); wr32(IGC_TSSDP, 0x0); wr32(IGC_TSIM, IGC_TSICR_INTERRUPTS | (adapter->pps_sys_wrap_on ? IGC_TSICR_SYS_WRAP : 0)); wr32(IGC_IMS, IGC_IMS_TS); + + if (!igc_is_crosststamp_supported(adapter)) + break; + + wr32(IGC_PCIE_DIG_DELAY, IGC_PCIE_DIG_DELAY_DEFAULT); + wr32(IGC_PCIE_PHY_DELAY, IGC_PCIE_PHY_DELAY_DEFAULT); + + cycle_ctrl = IGC_PTM_CYCLE_CTRL_CYC_TIME(IGC_PTM_CYC_TIME_DEFAULT); + + wr32(IGC_PTM_CYCLE_CTRL, cycle_ctrl); + + ctrl = IGC_PTM_CTRL_EN | + IGC_PTM_CTRL_START_NOW | + IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) | + IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) | + IGC_PTM_CTRL_TRIG; + + wr32(IGC_PTM_CTRL, ctrl); + + /* Force the first cycle to run. */ + wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + break; default: /* No work to do. */ diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index 828c3501c448..dbba2eb2a247 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -245,6 +245,29 @@ #define IGC_TXSTMPL 0x0B618 /* Tx timestamp value Low - RO */ #define IGC_TXSTMPH 0x0B61C /* Tx timestamp value High - RO */ +#define IGC_TIMADJ 0x0B60C /* Time Adjustment Offset Register */ + +/* PCIe Registers */ +#define IGC_PTM_CTRL 0x12540 /* PTM Control */ +#define IGC_PTM_STAT 0x12544 /* PTM Status */ +#define IGC_PTM_CYCLE_CTRL 0x1254C /* PTM Cycle Control */ + +/* PTM Time registers */ +#define IGC_PTM_T1_TIM0_L 0x12558 /* T1 on Timer 0 Low */ +#define IGC_PTM_T1_TIM0_H 0x1255C /* T1 on Timer 0 High */ + +#define IGC_PTM_CURR_T2_L 0x1258C /* Current T2 Low */ +#define IGC_PTM_CURR_T2_H 0x12590 /* Current T2 High */ +#define IGC_PTM_PREV_T2_L 0x12584 /* Previous T2 Low */ +#define IGC_PTM_PREV_T2_H 0x12588 /* Previous T2 High */ +#define IGC_PTM_PREV_T4M1 0x12578 /* T4 Minus T1 on previous PTM Cycle */ +#define IGC_PTM_CURR_T4M1 0x1257C /* T4 Minus T1 on this PTM Cycle */ +#define IGC_PTM_PREV_T3M2 0x12580 /* T3 Minus T2 on previous PTM Cycle */ +#define IGC_PTM_TDELAY 0x12594 /* PTM PCIe Link Delay */ + +#define IGC_PCIE_DIG_DELAY 0x12550 /* PCIe Digital Delay */ +#define IGC_PCIE_PHY_DELAY 0x12554 /* PCIe PHY Delay */ + /* Management registers */ #define IGC_MANC 0x05820 /* Management Control - RW */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h index 33e53d32e891..41ecd156e95f 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ b/drivers/net/ethernet/microsoft/mana/gdma.h @@ -239,10 +239,8 @@ struct gdma_event { struct gdma_queue; -#define CQE_POLLING_BUFFER 512 struct mana_eq { struct gdma_queue *eq; - struct gdma_comp cqe_poll[CQE_POLLING_BUFFER]; }; typedef void gdma_eq_callback(void *context, struct gdma_queue *q, @@ -291,11 +289,6 @@ struct gdma_queue { unsigned int msix_index; u32 log2_throttle_limit; - - /* NAPI data */ - struct napi_struct napi; - int work_done; - int budget; } eq; struct { @@ -319,9 +312,6 @@ struct gdma_queue_spec { void *context; unsigned long log2_throttle_limit; - - /* Only used by the MANA device. */ - struct net_device *ndev; } eq; struct { @@ -406,7 +396,7 @@ void mana_gd_destroy_queue(struct gdma_context *gc, struct gdma_queue *queue); int mana_gd_poll_cq(struct gdma_queue *cq, struct gdma_comp *comp, int num_cqe); -void mana_gd_arm_cq(struct gdma_queue *cq); +void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit); struct gdma_wqe { u32 reserved :24; @@ -496,16 +486,28 @@ enum { GDMA_PROTOCOL_LAST = GDMA_PROTOCOL_V1, }; +#define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) + +#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT + +#define GDMA_DRV_CAP_FLAGS2 0 + +#define GDMA_DRV_CAP_FLAGS3 0 + +#define GDMA_DRV_CAP_FLAGS4 0 + struct gdma_verify_ver_req { struct gdma_req_hdr hdr; /* Mandatory fields required for protocol establishment */ u64 protocol_ver_min; u64 protocol_ver_max; - u64 drv_cap_flags1; - u64 drv_cap_flags2; - u64 drv_cap_flags3; - u64 drv_cap_flags4; + + /* Gdma Driver Capability Flags */ + u64 gd_drv_cap_flags1; + u64 gd_drv_cap_flags2; + u64 gd_drv_cap_flags3; + u64 gd_drv_cap_flags4; /* Advisory fields */ u64 drv_ver; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 2f87bf90f8ec..cee75b561f59 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -67,6 +67,10 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev) if (gc->max_num_queues > resp.max_rq) gc->max_num_queues = resp.max_rq; + /* The Hardware Channel (HWC) used 1 MSI-X */ + if (gc->max_num_queues > gc->num_msix_usable - 1) + gc->max_num_queues = gc->num_msix_usable - 1; + return 0; } @@ -267,7 +271,7 @@ void mana_gd_wq_ring_doorbell(struct gdma_context *gc, struct gdma_queue *queue) queue->id, queue->head * GDMA_WQE_BU_SIZE, 1); } -void mana_gd_arm_cq(struct gdma_queue *cq) +void mana_gd_ring_cq(struct gdma_queue *cq, u8 arm_bit) { struct gdma_context *gc = cq->gdma_dev->gdma_context; @@ -276,7 +280,7 @@ void mana_gd_arm_cq(struct gdma_queue *cq) u32 head = cq->head % (num_cqe << GDMA_CQE_OWNER_BITS); mana_gd_ring_doorbell(gc, cq->gdma_dev->doorbell, cq->type, cq->id, - head, SET_ARM_BIT); + head, arm_bit); } static void mana_gd_process_eqe(struct gdma_queue *eq) @@ -339,7 +343,6 @@ static void mana_gd_process_eq_events(void *arg) struct gdma_queue *eq = arg; struct gdma_context *gc; struct gdma_eqe *eqe; - unsigned int arm_bit; u32 head, num_eqe; int i; @@ -370,92 +373,54 @@ static void mana_gd_process_eq_events(void *arg) eq->head++; } - /* Always rearm the EQ for HWC. For MANA, rearm it when NAPI is done. */ - if (mana_gd_is_hwc(eq->gdma_dev)) { - arm_bit = SET_ARM_BIT; - } else if (eq->eq.work_done < eq->eq.budget && - napi_complete_done(&eq->eq.napi, eq->eq.work_done)) { - arm_bit = SET_ARM_BIT; - } else { - arm_bit = 0; - } - head = eq->head % (num_eqe << GDMA_EQE_OWNER_BITS); mana_gd_ring_doorbell(gc, eq->gdma_dev->doorbell, eq->type, eq->id, - head, arm_bit); -} - -static int mana_poll(struct napi_struct *napi, int budget) -{ - struct gdma_queue *eq = container_of(napi, struct gdma_queue, eq.napi); - - eq->eq.work_done = 0; - eq->eq.budget = budget; - - mana_gd_process_eq_events(eq); - - return min(eq->eq.work_done, budget); -} - -static void mana_gd_schedule_napi(void *arg) -{ - struct gdma_queue *eq = arg; - struct napi_struct *napi; - - napi = &eq->eq.napi; - napi_schedule_irqoff(napi); + head, SET_ARM_BIT); } static int mana_gd_register_irq(struct gdma_queue *queue, const struct gdma_queue_spec *spec) { struct gdma_dev *gd = queue->gdma_dev; - bool is_mana = mana_gd_is_mana(gd); struct gdma_irq_context *gic; struct gdma_context *gc; struct gdma_resource *r; unsigned int msi_index; unsigned long flags; - int err; + struct device *dev; + int err = 0; gc = gd->gdma_context; r = &gc->msix_resource; + dev = gc->dev; spin_lock_irqsave(&r->lock, flags); msi_index = find_first_zero_bit(r->map, r->size); - if (msi_index >= r->size) { + if (msi_index >= r->size || msi_index >= gc->num_msix_usable) { err = -ENOSPC; } else { bitmap_set(r->map, msi_index, 1); queue->eq.msix_index = msi_index; - err = 0; } spin_unlock_irqrestore(&r->lock, flags); - if (err) - return err; + if (err) { + dev_err(dev, "Register IRQ err:%d, msi:%u rsize:%u, nMSI:%u", + err, msi_index, r->size, gc->num_msix_usable); - WARN_ON(msi_index >= gc->num_msix_usable); + return err; + } gic = &gc->irq_contexts[msi_index]; - if (is_mana) { - netif_napi_add(spec->eq.ndev, &queue->eq.napi, mana_poll, - NAPI_POLL_WEIGHT); - napi_enable(&queue->eq.napi); - } - WARN_ON(gic->handler || gic->arg); gic->arg = queue; - if (is_mana) - gic->handler = mana_gd_schedule_napi; - else - gic->handler = mana_gd_process_eq_events; + gic->handler = mana_gd_process_eq_events; return 0; } @@ -549,11 +514,6 @@ static void mana_gd_destroy_eq(struct gdma_context *gc, bool flush_evenets, mana_gd_deregiser_irq(queue); - if (mana_gd_is_mana(queue->gdma_dev)) { - napi_disable(&queue->eq.napi); - netif_napi_del(&queue->eq.napi); - } - if (queue->eq.disable_needed) mana_gd_disable_queue(queue); } @@ -883,6 +843,11 @@ int mana_gd_verify_vf_version(struct pci_dev *pdev) req.protocol_ver_min = GDMA_PROTOCOL_FIRST; req.protocol_ver_max = GDMA_PROTOCOL_LAST; + req.gd_drv_cap_flags1 = GDMA_DRV_CAP_FLAGS1; + req.gd_drv_cap_flags2 = GDMA_DRV_CAP_FLAGS2; + req.gd_drv_cap_flags3 = GDMA_DRV_CAP_FLAGS3; + req.gd_drv_cap_flags4 = GDMA_DRV_CAP_FLAGS4; + err = mana_gd_send_request(gc, sizeof(req), &req, sizeof(resp), &resp); if (err || resp.hdr.status) { dev_err(gc->dev, "VfVerifyVersionOutput: %d, status=0x%x\n", @@ -1128,7 +1093,7 @@ static int mana_gd_read_cqe(struct gdma_queue *cq, struct gdma_comp *comp) new_bits = (cq->head / num_cqe) & GDMA_CQE_OWNER_MASK; /* Return -1 if overflow detected. */ - if (owner_bits != new_bits) + if (WARN_ON_ONCE(owner_bits != new_bits)) return -1; comp->wq_num = cqe->cqe_info.wq_num; @@ -1201,10 +1166,8 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) if (max_queues_per_port > MANA_MAX_NUM_QUEUES) max_queues_per_port = MANA_MAX_NUM_QUEUES; - max_irqs = max_queues_per_port * MAX_PORTS_IN_MANA_DEV; - /* Need 1 interrupt for the Hardware communication Channel (HWC) */ - max_irqs++; + max_irqs = max_queues_per_port + 1; nvec = pci_alloc_irq_vectors(pdev, 2, max_irqs, PCI_IRQ_MSIX); if (nvec < 0) @@ -1291,6 +1254,9 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int bar = 0; int err; + /* Each port has 2 CQs, each CQ has at most 1 EQE at a time */ + BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE); + err = pci_enable_device(pdev); if (err) return -ENXIO; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index 1a923fd99990..c1310ea1c216 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -304,7 +304,7 @@ static void mana_hwc_comp_event(void *ctx, struct gdma_queue *q_self) &comp_data); } - mana_gd_arm_cq(q_self); + mana_gd_ring_cq(q_self, SET_ARM_BIT); } static void mana_hwc_destroy_cq(struct gdma_context *gc, struct hwc_cq *hwc_cq) diff --git a/drivers/net/ethernet/microsoft/mana/mana.h b/drivers/net/ethernet/microsoft/mana/mana.h index a2c3f826f022..fc98a5ba5ed0 100644 --- a/drivers/net/ethernet/microsoft/mana/mana.h +++ b/drivers/net/ethernet/microsoft/mana/mana.h @@ -46,7 +46,7 @@ enum TRI_STATE { #define EQ_SIZE (8 * PAGE_SIZE) #define LOG2_EQ_THROTTLE 3 -#define MAX_PORTS_IN_MANA_DEV 16 +#define MAX_PORTS_IN_MANA_DEV 256 struct mana_stats { u64 packets; @@ -225,6 +225,8 @@ struct mana_tx_comp_oob { struct mana_rxq; +#define CQE_POLLING_BUFFER 512 + struct mana_cq { struct gdma_queue *gdma_cq; @@ -244,8 +246,13 @@ struct mana_cq { */ struct mana_txq *txq; - /* Pointer to a buffer which the CQ handler can copy the CQE's into. */ - struct gdma_comp *gdma_comp_buf; + /* Buffer which the CQ handler can copy the CQE's into. */ + struct gdma_comp gdma_comp_buf[CQE_POLLING_BUFFER]; + + /* NAPI data */ + struct napi_struct napi; + int work_done; + int budget; }; #define GDMA_MAX_RQE_SGES 15 @@ -315,6 +322,8 @@ struct mana_context { u16 num_ports; + struct mana_eq *eqs; + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; }; @@ -324,8 +333,6 @@ struct mana_port_context { u8 mac_addr[ETH_ALEN]; - struct mana_eq *eqs; - enum TRI_STATE rss_state; mana_handle_t default_rxobj; @@ -395,11 +402,11 @@ enum mana_command_code { struct mana_query_device_cfg_req { struct gdma_req_hdr hdr; - /* Driver Capability flags */ - u64 drv_cap_flags1; - u64 drv_cap_flags2; - u64 drv_cap_flags3; - u64 drv_cap_flags4; + /* MANA Nic Driver Capability flags */ + u64 mn_drv_cap_flags1; + u64 mn_drv_cap_flags2; + u64 mn_drv_cap_flags3; + u64 mn_drv_cap_flags4; u32 proto_major_ver; u32 proto_minor_ver; @@ -516,7 +523,7 @@ struct mana_cfg_rx_steer_resp { struct gdma_resp_hdr hdr; }; /* HW DATA */ -#define MANA_MAX_NUM_QUEUES 16 +#define MANA_MAX_NUM_QUEUES 64 #define MANA_SHORT_VPORT_OFFSET_MAX ((1U << 8) - 1) diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index fff78900fc8a..1b21030308e5 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -696,66 +696,56 @@ static void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type, resp.hdr.status); } -static void mana_init_cqe_poll_buf(struct gdma_comp *cqe_poll_buf) -{ - int i; - - for (i = 0; i < CQE_POLLING_BUFFER; i++) - memset(&cqe_poll_buf[i], 0, sizeof(struct gdma_comp)); -} - -static void mana_destroy_eq(struct gdma_context *gc, - struct mana_port_context *apc) +static void mana_destroy_eq(struct mana_context *ac) { + struct gdma_context *gc = ac->gdma_dev->gdma_context; struct gdma_queue *eq; int i; - if (!apc->eqs) + if (!ac->eqs) return; - for (i = 0; i < apc->num_queues; i++) { - eq = apc->eqs[i].eq; + for (i = 0; i < gc->max_num_queues; i++) { + eq = ac->eqs[i].eq; if (!eq) continue; mana_gd_destroy_queue(gc, eq); } - kfree(apc->eqs); - apc->eqs = NULL; + kfree(ac->eqs); + ac->eqs = NULL; } -static int mana_create_eq(struct mana_port_context *apc) +static int mana_create_eq(struct mana_context *ac) { - struct gdma_dev *gd = apc->ac->gdma_dev; + struct gdma_dev *gd = ac->gdma_dev; + struct gdma_context *gc = gd->gdma_context; struct gdma_queue_spec spec = {}; int err; int i; - apc->eqs = kcalloc(apc->num_queues, sizeof(struct mana_eq), - GFP_KERNEL); - if (!apc->eqs) + ac->eqs = kcalloc(gc->max_num_queues, sizeof(struct mana_eq), + GFP_KERNEL); + if (!ac->eqs) return -ENOMEM; spec.type = GDMA_EQ; spec.monitor_avl_buf = false; spec.queue_size = EQ_SIZE; spec.eq.callback = NULL; - spec.eq.context = apc->eqs; + spec.eq.context = ac->eqs; spec.eq.log2_throttle_limit = LOG2_EQ_THROTTLE; - spec.eq.ndev = apc->ndev; - - for (i = 0; i < apc->num_queues; i++) { - mana_init_cqe_poll_buf(apc->eqs[i].cqe_poll); - err = mana_gd_create_mana_eq(gd, &spec, &apc->eqs[i].eq); + for (i = 0; i < gc->max_num_queues; i++) { + err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq); if (err) goto out; } return 0; out: - mana_destroy_eq(gd->gdma_context, apc); + mana_destroy_eq(ac); return err; } @@ -790,7 +780,6 @@ static void mana_unmap_skb(struct sk_buff *skb, struct mana_port_context *apc) static void mana_poll_tx_cq(struct mana_cq *cq) { - struct gdma_queue *gdma_eq = cq->gdma_cq->cq.parent; struct gdma_comp *completions = cq->gdma_comp_buf; struct gdma_posted_wqe_info *wqe_info; unsigned int pkt_transmitted = 0; @@ -812,6 +801,9 @@ static void mana_poll_tx_cq(struct mana_cq *cq) comp_read = mana_gd_poll_cq(cq->gdma_cq, completions, CQE_POLLING_BUFFER); + if (comp_read < 1) + return; + for (i = 0; i < comp_read; i++) { struct mana_tx_comp_oob *cqe_oob; @@ -861,7 +853,7 @@ static void mana_poll_tx_cq(struct mana_cq *cq) mana_unmap_skb(skb, apc); - napi_consume_skb(skb, gdma_eq->eq.budget); + napi_consume_skb(skb, cq->budget); pkt_transmitted++; } @@ -890,6 +882,8 @@ static void mana_poll_tx_cq(struct mana_cq *cq) if (atomic_sub_return(pkt_transmitted, &txq->pending_sends) < 0) WARN_ON_ONCE(1); + + cq->work_done = pkt_transmitted; } static void mana_post_pkt_rxq(struct mana_rxq *rxq) @@ -918,17 +912,13 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe, struct mana_stats *rx_stats = &rxq->stats; struct net_device *ndev = rxq->ndev; uint pkt_len = cqe->ppi[0].pkt_len; - struct mana_port_context *apc; u16 rxq_idx = rxq->rxq_idx; struct napi_struct *napi; - struct gdma_queue *eq; struct sk_buff *skb; u32 hash_value; - apc = netdev_priv(ndev); - eq = apc->eqs[rxq_idx].eq; - eq->eq.work_done++; - napi = &eq->eq.napi; + rxq->rx_cq.work_done++; + napi = &rxq->rx_cq.napi; if (!buf_va) { ++ndev->stats.rx_dropped; @@ -1081,6 +1071,7 @@ static void mana_poll_rx_cq(struct mana_cq *cq) static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; + u8 arm_bit; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1089,7 +1080,33 @@ static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) else mana_poll_tx_cq(cq); - mana_gd_arm_cq(gdma_queue); + if (cq->work_done < cq->budget && + napi_complete_done(&cq->napi, cq->work_done)) { + arm_bit = SET_ARM_BIT; + } else { + arm_bit = 0; + } + + mana_gd_ring_cq(gdma_queue, arm_bit); +} + +static int mana_poll(struct napi_struct *napi, int budget) +{ + struct mana_cq *cq = container_of(napi, struct mana_cq, napi); + + cq->work_done = 0; + cq->budget = budget; + + mana_cq_handler(cq, cq->gdma_cq); + + return min(cq->work_done, budget); +} + +static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue) +{ + struct mana_cq *cq = context; + + napi_schedule_irqoff(&cq->napi); } static void mana_deinit_cq(struct mana_port_context *apc, struct mana_cq *cq) @@ -1114,12 +1131,18 @@ static void mana_deinit_txq(struct mana_port_context *apc, struct mana_txq *txq) static void mana_destroy_txq(struct mana_port_context *apc) { + struct napi_struct *napi; int i; if (!apc->tx_qp) return; for (i = 0; i < apc->num_queues; i++) { + napi = &apc->tx_qp[i].tx_cq.napi; + napi_synchronize(napi); + napi_disable(napi); + netif_napi_del(napi); + mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object); mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq); @@ -1134,7 +1157,8 @@ static void mana_destroy_txq(struct mana_port_context *apc) static int mana_create_txq(struct mana_port_context *apc, struct net_device *net) { - struct gdma_dev *gd = apc->ac->gdma_dev; + struct mana_context *ac = apc->ac; + struct gdma_dev *gd = ac->gdma_dev; struct mana_obj_spec wq_spec; struct mana_obj_spec cq_spec; struct gdma_queue_spec spec; @@ -1186,7 +1210,6 @@ static int mana_create_txq(struct mana_port_context *apc, /* Create SQ's CQ */ cq = &apc->tx_qp[i].tx_cq; - cq->gdma_comp_buf = apc->eqs[i].cqe_poll; cq->type = MANA_CQ_TYPE_TX; cq->txq = txq; @@ -1195,8 +1218,8 @@ static int mana_create_txq(struct mana_port_context *apc, spec.type = GDMA_CQ; spec.monitor_avl_buf = false; spec.queue_size = cq_size; - spec.cq.callback = mana_cq_handler; - spec.cq.parent_eq = apc->eqs[i].eq; + spec.cq.callback = mana_schedule_napi; + spec.cq.parent_eq = ac->eqs[i].eq; spec.cq.context = cq; err = mana_gd_create_mana_wq_cq(gd, &spec, &cq->gdma_cq); if (err) @@ -1237,7 +1260,10 @@ static int mana_create_txq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - mana_gd_arm_cq(cq->gdma_cq); + netif_tx_napi_add(net, &cq->napi, mana_poll, NAPI_POLL_WEIGHT); + napi_enable(&cq->napi); + + mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); } return 0; @@ -1246,21 +1272,6 @@ out: return err; } -static void mana_napi_sync_for_rx(struct mana_rxq *rxq) -{ - struct net_device *ndev = rxq->ndev; - struct mana_port_context *apc; - u16 rxq_idx = rxq->rxq_idx; - struct napi_struct *napi; - struct gdma_queue *eq; - - apc = netdev_priv(ndev); - eq = apc->eqs[rxq_idx].eq; - napi = &eq->eq.napi; - - napi_synchronize(napi); -} - static void mana_destroy_rxq(struct mana_port_context *apc, struct mana_rxq *rxq, bool validate_state) @@ -1268,13 +1279,19 @@ static void mana_destroy_rxq(struct mana_port_context *apc, struct gdma_context *gc = apc->ac->gdma_dev->gdma_context; struct mana_recv_buf_oob *rx_oob; struct device *dev = gc->dev; + struct napi_struct *napi; int i; if (!rxq) return; + napi = &rxq->rx_cq.napi; + if (validate_state) - mana_napi_sync_for_rx(rxq); + napi_synchronize(napi); + + napi_disable(napi); + netif_napi_del(napi); mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj); @@ -1418,7 +1435,6 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, /* Create RQ's CQ */ cq = &rxq->rx_cq; - cq->gdma_comp_buf = eq->cqe_poll; cq->type = MANA_CQ_TYPE_RX; cq->rxq = rxq; @@ -1426,7 +1442,7 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, spec.type = GDMA_CQ; spec.monitor_avl_buf = false; spec.queue_size = cq_size; - spec.cq.callback = mana_cq_handler; + spec.cq.callback = mana_schedule_napi; spec.cq.parent_eq = eq->eq; spec.cq.context = cq; err = mana_gd_create_mana_wq_cq(gd, &spec, &cq->gdma_cq); @@ -1466,7 +1482,10 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc, gc->cq_table[cq->gdma_id] = cq->gdma_cq; - mana_gd_arm_cq(cq->gdma_cq); + netif_napi_add(ndev, &cq->napi, mana_poll, 1); + napi_enable(&cq->napi); + + mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT); out: if (!err) return rxq; @@ -1484,12 +1503,13 @@ out: static int mana_add_rx_queues(struct mana_port_context *apc, struct net_device *ndev) { + struct mana_context *ac = apc->ac; struct mana_rxq *rxq; int err = 0; int i; for (i = 0; i < apc->num_queues; i++) { - rxq = mana_create_rxq(apc, i, &apc->eqs[i], ndev); + rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev); if (!rxq) { err = -ENOMEM; goto out; @@ -1601,16 +1621,11 @@ reset_apc: int mana_alloc_queues(struct net_device *ndev) { struct mana_port_context *apc = netdev_priv(ndev); - struct gdma_dev *gd = apc->ac->gdma_dev; int err; - err = mana_create_eq(apc); - if (err) - return err; - err = mana_create_vport(apc, ndev); if (err) - goto destroy_eq; + return err; err = netif_set_real_num_tx_queues(ndev, apc->num_queues); if (err) @@ -1636,8 +1651,6 @@ int mana_alloc_queues(struct net_device *ndev) destroy_vport: mana_destroy_vport(apc); -destroy_eq: - mana_destroy_eq(gd->gdma_context, apc); return err; } @@ -1714,8 +1727,6 @@ static int mana_dealloc_queues(struct net_device *ndev) mana_destroy_vport(apc); - mana_destroy_eq(apc->ac->gdma_dev->gdma_context, apc); - return 0; } @@ -1768,7 +1779,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, apc->ac = ac; apc->ndev = ndev; apc->max_queues = gc->max_num_queues; - apc->num_queues = min_t(uint, gc->max_num_queues, MANA_MAX_NUM_QUEUES); + apc->num_queues = gc->max_num_queues; apc->port_handle = INVALID_MANA_HANDLE; apc->port_idx = port_idx; @@ -1839,6 +1850,10 @@ int mana_probe(struct gdma_dev *gd) ac->num_ports = 1; gd->driver_data = ac; + err = mana_create_eq(ac); + if (err) + goto out; + err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION, MANA_MICRO_VERSION, &ac->num_ports); if (err) @@ -1888,6 +1903,9 @@ void mana_remove(struct gdma_dev *gd) free_netdev(ndev); } + + mana_destroy_eq(ac); + out: mana_gd_deregister_device(gd); gd->driver_data = NULL; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h index e5c51256243a..f13fa7396aef 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic.h +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic.h @@ -1863,7 +1863,6 @@ static inline u32 netxen_tx_avail(struct nx_host_tx_ring *tx_ring) int netxen_get_flash_mac_addr(struct netxen_adapter *adapter, u64 *mac); int netxen_p3_get_mac_addr(struct netxen_adapter *adapter, u64 *mac); void netxen_change_ringparam(struct netxen_adapter *adapter); -int netxen_rom_fast_read(struct netxen_adapter *adapter, int addr, int *valp); extern const struct ethtool_ops netxen_nic_ethtool_ops; diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index 4c7501b9c284..78070682f2df 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -93,7 +93,7 @@ static const struct devlink_health_reporter_ops qed_fw_fatal_reporter_ops = { .dump = qed_fw_fatal_reporter_dump, }; -#define QED_REPORTER_FW_GRACEFUL_PERIOD 1200000 +#define QED_REPORTER_FW_GRACEFUL_PERIOD 0 void qed_fw_reporters_create(struct devlink *devlink) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index ab6d4f737316..f78e6055f654 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -351,6 +351,9 @@ static int qed_fw_assertion(struct qed_hwfn *p_hwfn) qed_hw_err_notify(p_hwfn, p_hwfn->p_dpc_ptt, QED_HW_ERR_FW_ASSERT, "FW assertion!\n"); + /* Clear assert indications */ + qed_wr(p_hwfn, p_hwfn->p_dpc_ptt, MISC_REG_AEU_GENERAL_ATTN_32, 0); + return -EINVAL; } @@ -953,6 +956,13 @@ qed_int_deassertion_aeu_bit(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "`%s' - Disabled future attentions\n", p_bit_name); + /* Re-enable FW aassertion (Gen 32) interrupts */ + val = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt, + MISC_REG_AEU_ENABLE4_IGU_OUT_0); + val |= MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32; + qed_wr(p_hwfn, p_hwfn->p_dpc_ptt, + MISC_REG_AEU_ENABLE4_IGU_OUT_0, val); + out: return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 9db22be42476..da1b7fdcbda7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -504,6 +504,8 @@ 0x180824UL #define MISC_REG_AEU_GENERAL_ATTN_0 \ 0x008400UL +#define MISC_REG_AEU_GENERAL_ATTN_32 \ + 0x008480UL #define MISC_REG_AEU_GENERAL_ATTN_35 \ 0x00848cUL #define CAU_REG_SB_ADDR_MEMORY \ @@ -518,6 +520,12 @@ 0x180804UL #define MISC_REG_AEU_ENABLE1_IGU_OUT_0 \ 0x00849cUL +#define MISC_REG_AEU_ENABLE4_IGU_OUT_0 \ + 0x0084a8UL +#define MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32 \ + (0x1UL << 0) +#define MISC_REG_AEU_ENABLE4_IGU_OUT_0_GENERAL_ATTN32_SHIFT \ + 0 #define MISC_REG_AEU_AFTER_INVERT_1_IGU \ 0x0087b4UL #define MISC_REG_AEU_MASK_ATTN_IGU \ diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index d400e9b235bf..4877cb88c31a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1898,6 +1898,12 @@ static int qede_req_msix_irqs(struct qede_dev *edev) &edev->fp_array[i]); if (rc) { DP_ERR(edev, "Request fp %d irq failed\n", i); +#ifdef CONFIG_RFS_ACCEL + if (edev->ndev->rx_cpu_rmap) + free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); + + edev->ndev->rx_cpu_rmap = NULL; +#endif qede_sync_free_irqs(edev); return rc; } @@ -2290,6 +2296,15 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, rc = qede_stop_queues(edev); if (rc) { +#ifdef CONFIG_RFS_ACCEL + if (edev->dev_info.common.b_arfs_capable) { + qede_poll_for_freeing_arfs_filters(edev); + if (edev->ndev->rx_cpu_rmap) + free_irq_cpu_rmap(edev->ndev->rx_cpu_rmap); + + edev->ndev->rx_cpu_rmap = NULL; + } +#endif qede_sync_free_irqs(edev); goto out; } @@ -2620,8 +2635,10 @@ static void qede_generic_hw_err_handler(struct qede_dev *edev) "Generic sleepable HW error handling started - err_flags 0x%lx\n", edev->err_flags); - if (edev->devlink) + if (edev->devlink) { + DP_NOTICE(edev, "Reporting fatal error to devlink\n"); edev->ops->common->report_fatal_error(edev->devlink, edev->last_err_type); + } clear_bit(QEDE_ERR_IS_HANDLED, &edev->err_flags); @@ -2643,6 +2660,8 @@ static void qede_set_hw_err_flags(struct qede_dev *edev, case QED_HW_ERR_FW_ASSERT: set_bit(QEDE_ERR_ATTN_CLR_EN, &err_flags); set_bit(QEDE_ERR_GET_DBG_INFO, &err_flags); + /* make this error as recoverable and start recovery*/ + set_bit(QEDE_ERR_IS_RECOVERABLE, &err_flags); break; default: diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 37ad0f8aaf3c..47c5377e4f42 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -956,10 +956,6 @@ enum RAVB_QUEUE { #define RX_BUF_SZ (2048 - ETH_FCS_LEN + sizeof(__sum16)) -/* TX descriptors per packet */ -#define NUM_TX_DESC_GEN2 2 -#define NUM_TX_DESC_GEN3 1 - struct ravb_tstamp_skb { struct list_head list; struct sk_buff *skb; @@ -983,17 +979,19 @@ struct ravb_ptp { struct ravb_ptp_perout perout[N_PER_OUT]; }; -enum ravb_chip_id { - RCAR_GEN2, - RCAR_GEN3, -}; - struct ravb_hw_info { + void (*rx_ring_free)(struct net_device *ndev, int q); + void (*rx_ring_format)(struct net_device *ndev, int q); + void *(*alloc_rx_desc)(struct net_device *ndev, int q); + bool (*receive)(struct net_device *ndev, int *quota, int q); + void (*set_rate)(struct net_device *ndev); + int (*set_rx_csum_feature)(struct net_device *ndev, netdev_features_t features); + void (*dmac_init)(struct net_device *ndev); + void (*emac_init)(struct net_device *ndev); const char (*gstrings_stats)[ETH_GSTRING_LEN]; size_t gstrings_size; netdev_features_t net_hw_features; netdev_features_t net_features; - enum ravb_chip_id chip_id; int stats_len; size_t max_rx_len; unsigned aligned_tx: 1; @@ -1001,6 +999,9 @@ struct ravb_hw_info { /* hardware features */ unsigned internal_delay:1; /* AVB-DMAC has internal delays */ unsigned tx_counters:1; /* E-MAC has TX counters */ + unsigned multi_irqs:1; /* AVB-DMAC and E-MAC has multiple irqs */ + unsigned no_ptp_cfg_active:1; /* AVB-DMAC does not support gPTP active in config mode */ + unsigned ptp_cfg_active:1; /* AVB-DMAC has gPTP support active in config mode */ }; struct ravb_private { @@ -1044,7 +1045,6 @@ struct ravb_private { int msg_enable; int speed; int emac_irq; - enum ravb_chip_id chip_id; int rx_irqs[NUM_RX_QUEUE]; int tx_irqs[NUM_TX_QUEUE]; @@ -1057,6 +1057,7 @@ struct ravb_private { unsigned int num_tx_desc; /* TX descriptors per packet */ const struct ravb_hw_info *info; + struct reset_control *rstc; }; static inline u32 ravb_read(struct net_device *ndev, enum ravb_reg reg) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 02842b980a7f..0f85f2d97b18 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/sys_soc.h> +#include <linux/reset.h> #include <asm/div64.h> @@ -216,31 +217,42 @@ static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only) return free_num; } +static void ravb_rx_ring_free(struct net_device *ndev, int q) +{ + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + unsigned int i; + + if (!priv->rx_ring[q]) + return; + + for (i = 0; i < priv->num_rx_ring[q]; i++) { + struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; + + if (!dma_mapping_error(ndev->dev.parent, + le32_to_cpu(desc->dptr))) + dma_unmap_single(ndev->dev.parent, + le32_to_cpu(desc->dptr), + RX_BUF_SZ, + DMA_FROM_DEVICE); + } + ring_size = sizeof(struct ravb_ex_rx_desc) * + (priv->num_rx_ring[q] + 1); + dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], + priv->rx_desc_dma[q]); + priv->rx_ring[q] = NULL; +} + /* Free skb's and DMA buffers for Ethernet AVB */ static void ravb_ring_free(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; unsigned int num_tx_desc = priv->num_tx_desc; unsigned int ring_size; unsigned int i; - if (priv->rx_ring[q]) { - for (i = 0; i < priv->num_rx_ring[q]; i++) { - struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i]; - - if (!dma_mapping_error(ndev->dev.parent, - le32_to_cpu(desc->dptr))) - dma_unmap_single(ndev->dev.parent, - le32_to_cpu(desc->dptr), - RX_BUF_SZ, - DMA_FROM_DEVICE); - } - ring_size = sizeof(struct ravb_ex_rx_desc) * - (priv->num_rx_ring[q] + 1); - dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q], - priv->rx_desc_dma[q]); - priv->rx_ring[q] = NULL; - } + info->rx_ring_free(ndev, q); if (priv->tx_ring[q]) { ravb_tx_free(ndev, q, false); @@ -271,25 +283,14 @@ static void ravb_ring_free(struct net_device *ndev, int q) priv->tx_skb[q] = NULL; } -/* Format skb and descriptor buffer for Ethernet AVB */ -static void ravb_ring_format(struct net_device *ndev, int q) +static void ravb_rx_ring_format(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); - unsigned int num_tx_desc = priv->num_tx_desc; struct ravb_ex_rx_desc *rx_desc; - struct ravb_tx_desc *tx_desc; - struct ravb_desc *desc; unsigned int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q]; - unsigned int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] * - num_tx_desc; dma_addr_t dma_addr; unsigned int i; - priv->cur_rx[q] = 0; - priv->cur_tx[q] = 0; - priv->dirty_rx[q] = 0; - priv->dirty_tx[q] = 0; - memset(priv->rx_ring[q], 0, rx_ring_size); /* Build RX ring buffer */ for (i = 0; i < priv->num_rx_ring[q]; i++) { @@ -310,6 +311,26 @@ static void ravb_ring_format(struct net_device *ndev, int q) rx_desc = &priv->rx_ring[q][i]; rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]); rx_desc->die_dt = DT_LINKFIX; /* type */ +} + +/* Format skb and descriptor buffer for Ethernet AVB */ +static void ravb_ring_format(struct net_device *ndev, int q) +{ + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + unsigned int num_tx_desc = priv->num_tx_desc; + struct ravb_tx_desc *tx_desc; + struct ravb_desc *desc; + unsigned int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q] * + num_tx_desc; + unsigned int i; + + priv->cur_rx[q] = 0; + priv->cur_tx[q] = 0; + priv->dirty_rx[q] = 0; + priv->dirty_tx[q] = 0; + + info->rx_ring_format(ndev, q); memset(priv->tx_ring[q], 0, tx_ring_size); /* Build TX ring buffer */ @@ -335,6 +356,19 @@ static void ravb_ring_format(struct net_device *ndev, int q) desc->dptr = cpu_to_le32((u32)priv->tx_desc_dma[q]); } +static void *ravb_alloc_rx_desc(struct net_device *ndev, int q) +{ + struct ravb_private *priv = netdev_priv(ndev); + unsigned int ring_size; + + ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); + + priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size, + &priv->rx_desc_dma[q], + GFP_KERNEL); + return priv->rx_ring[q]; +} + /* Init skb and descriptor buffer for Ethernet AVB */ static int ravb_ring_init(struct net_device *ndev, int q) { @@ -370,11 +404,7 @@ static int ravb_ring_init(struct net_device *ndev, int q) } /* Allocate all RX descriptors. */ - ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1); - priv->rx_ring[q] = dma_alloc_coherent(ndev->dev.parent, ring_size, - &priv->rx_desc_dma[q], - GFP_KERNEL); - if (!priv->rx_ring[q]) + if (!info->alloc_rx_desc(ndev, q)) goto error; priv->dirty_rx[q] = 0; @@ -396,8 +426,7 @@ error: return -ENOMEM; } -/* E-MAC init function */ -static void ravb_emac_init(struct net_device *ndev) +static void ravb_rcar_emac_init(struct net_device *ndev) { /* Receive frame limit set register */ ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR); @@ -423,29 +452,19 @@ static void ravb_emac_init(struct net_device *ndev) ravb_write(ndev, ECSIPR_ICDIP | ECSIPR_MPDIP | ECSIPR_LCHNGIP, ECSIPR); } -/* Device init function for Ethernet AVB */ -static int ravb_dmac_init(struct net_device *ndev) +/* E-MAC init function */ +static void ravb_emac_init(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); - int error; - - /* Set CONFIG mode */ - error = ravb_config(ndev); - if (error) - return error; + const struct ravb_hw_info *info = priv->info; - error = ravb_ring_init(ndev, RAVB_BE); - if (error) - return error; - error = ravb_ring_init(ndev, RAVB_NC); - if (error) { - ravb_ring_free(ndev, RAVB_BE); - return error; - } + info->emac_init(ndev); +} - /* Descriptor format */ - ravb_ring_format(ndev, RAVB_BE); - ravb_ring_format(ndev, RAVB_NC); +static void ravb_rcar_dmac_init(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; /* Set AVB RX */ ravb_write(ndev, @@ -458,7 +477,7 @@ static int ravb_dmac_init(struct net_device *ndev) ravb_write(ndev, TCCR_TFEN, TCCR); /* Interrupt init: */ - if (priv->chip_id == RCAR_GEN3) { + if (info->multi_irqs) { /* Clear DIL.DPLx */ ravb_write(ndev, 0, DIL); /* Set queue specific interrupt */ @@ -472,6 +491,34 @@ static int ravb_dmac_init(struct net_device *ndev) ravb_write(ndev, RIC2_QFE0 | RIC2_QFE1 | RIC2_RFFE, RIC2); /* Frame transmitted, timestamp FIFO updated */ ravb_write(ndev, TIC_FTE0 | TIC_FTE1 | TIC_TFUE, TIC); +} + +/* Device init function for Ethernet AVB */ +static int ravb_dmac_init(struct net_device *ndev) +{ + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + int error; + + /* Set CONFIG mode */ + error = ravb_config(ndev); + if (error) + return error; + + error = ravb_ring_init(ndev, RAVB_BE); + if (error) + return error; + error = ravb_ring_init(ndev, RAVB_NC); + if (error) { + ravb_ring_free(ndev, RAVB_BE); + return error; + } + + /* Descriptor format */ + ravb_ring_format(ndev, RAVB_BE); + ravb_ring_format(ndev, RAVB_NC); + + info->dmac_init(ndev); /* Setting the control will start the AVB-DMAC process. */ ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_OPERATION); @@ -532,8 +579,7 @@ static void ravb_rx_csum(struct sk_buff *skb) skb_trim(skb, skb->len - sizeof(__sum16)); } -/* Packet receive function for Ethernet AVB */ -static bool ravb_rx(struct net_device *ndev, int *quota, int q) +static bool ravb_rcar_rx(struct net_device *ndev, int *quota, int q) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; @@ -647,6 +693,15 @@ static bool ravb_rx(struct net_device *ndev, int *quota, int q) return boguscnt <= 0; } +/* Packet receive function for Ethernet AVB */ +static bool ravb_rx(struct net_device *ndev, int *quota, int q) +{ + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + + return info->receive(ndev, quota, q); +} + static void ravb_rcv_snd_disable(struct net_device *ndev) { /* Disable TX and RX */ @@ -758,6 +813,7 @@ static void ravb_error_interrupt(struct net_device *ndev) static bool ravb_queue_interrupt(struct net_device *ndev, int q) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; u32 ris0 = ravb_read(ndev, RIS0); u32 ric0 = ravb_read(ndev, RIC0); u32 tis = ravb_read(ndev, TIS); @@ -766,7 +822,7 @@ static bool ravb_queue_interrupt(struct net_device *ndev, int q) if (((ris0 & ric0) & BIT(q)) || ((tis & tic) & BIT(q))) { if (napi_schedule_prep(&priv->napi[q])) { /* Mask RX and TX interrupts */ - if (priv->chip_id == RCAR_GEN2) { + if (!info->multi_irqs) { ravb_write(ndev, ric0 & ~BIT(q), RIC0); ravb_write(ndev, tic & ~BIT(q), TIC); } else { @@ -909,6 +965,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) { struct net_device *ndev = napi->dev; struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; unsigned long flags; int q = napi - priv->napi; int mask = BIT(q); @@ -932,7 +989,7 @@ static int ravb_poll(struct napi_struct *napi, int budget) /* Re-enable RX/TX interrupts */ spin_lock_irqsave(&priv->lock, flags); - if (priv->chip_id == RCAR_GEN2) { + if (!info->multi_irqs) { ravb_modify(ndev, RIC0, mask, mask); ravb_modify(ndev, TIC, mask, mask); } else { @@ -956,6 +1013,7 @@ out: static void ravb_adjust_link(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; struct phy_device *phydev = ndev->phydev; bool new_state = false; unsigned long flags; @@ -970,7 +1028,7 @@ static void ravb_adjust_link(struct net_device *ndev) if (phydev->speed != priv->speed) { new_state = true; priv->speed = phydev->speed; - ravb_set_rate(ndev); + info->set_rate(ndev); } if (!priv->link) { ravb_modify(ndev, ECMR, ECMR_TXF, 0); @@ -1202,6 +1260,7 @@ static int ravb_set_ringparam(struct net_device *ndev, struct ethtool_ringparam *ring) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; int error; if (ring->tx_pending > BE_TX_RING_MAX || @@ -1215,7 +1274,7 @@ static int ravb_set_ringparam(struct net_device *ndev, if (netif_running(ndev)) { netif_device_detach(ndev); /* Stop PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_stop(ndev); /* Wait for DMA stopping */ error = ravb_stop_dma(ndev); @@ -1247,7 +1306,7 @@ static int ravb_set_ringparam(struct net_device *ndev, ravb_emac_init(ndev); /* Initialise PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_init(ndev, priv->pdev); netif_device_attach(ndev); @@ -1338,6 +1397,7 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, static int ravb_open(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; struct platform_device *pdev = priv->pdev; struct device *dev = &pdev->dev; int error; @@ -1345,7 +1405,7 @@ static int ravb_open(struct net_device *ndev) napi_enable(&priv->napi[RAVB_BE]); napi_enable(&priv->napi[RAVB_NC]); - if (priv->chip_id == RCAR_GEN2) { + if (!info->multi_irqs) { error = request_irq(ndev->irq, ravb_interrupt, IRQF_SHARED, ndev->name, ndev); if (error) { @@ -1386,7 +1446,7 @@ static int ravb_open(struct net_device *ndev) ravb_emac_init(ndev); /* Initialise PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_init(ndev, priv->pdev); netif_tx_start_all_queues(ndev); @@ -1400,10 +1460,10 @@ static int ravb_open(struct net_device *ndev) out_ptp_stop: /* Stop PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_stop(ndev); out_free_irq_nc_tx: - if (priv->chip_id == RCAR_GEN2) + if (!info->multi_irqs) goto out_free_irq; free_irq(priv->tx_irqs[RAVB_NC], ndev); out_free_irq_nc_rx: @@ -1441,13 +1501,14 @@ static void ravb_tx_timeout_work(struct work_struct *work) { struct ravb_private *priv = container_of(work, struct ravb_private, work); + const struct ravb_hw_info *info = priv->info; struct net_device *ndev = priv->ndev; int error; netif_tx_stop_all_queues(ndev); /* Stop PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_stop(ndev); /* Wait for DMA stopping */ @@ -1482,7 +1543,7 @@ static void ravb_tx_timeout_work(struct work_struct *work) out: /* Initialise PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_init(ndev, priv->pdev); netif_tx_start_all_queues(ndev); @@ -1680,6 +1741,7 @@ static int ravb_close(struct net_device *ndev) { struct device_node *np = ndev->dev.parent->of_node; struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; struct ravb_tstamp_skb *ts_skb, *ts_skb2; netif_tx_stop_all_queues(ndev); @@ -1690,7 +1752,7 @@ static int ravb_close(struct net_device *ndev) ravb_write(ndev, 0, TIC); /* Stop PTP Clock driver */ - if (priv->chip_id == RCAR_GEN2) + if (info->no_ptp_cfg_active) ravb_ptp_stop(ndev); /* Set the config mode to stop the AVB-DMAC's processes */ @@ -1713,7 +1775,7 @@ static int ravb_close(struct net_device *ndev) of_phy_deregister_fixed_link(np); } - if (priv->chip_id != RCAR_GEN2) { + if (info->multi_irqs) { free_irq(priv->tx_irqs[RAVB_NC], ndev); free_irq(priv->rx_irqs[RAVB_NC], ndev); free_irq(priv->tx_irqs[RAVB_BE], ndev); @@ -1856,8 +1918,8 @@ static void ravb_set_rx_csum(struct net_device *ndev, bool enable) spin_unlock_irqrestore(&priv->lock, flags); } -static int ravb_set_features(struct net_device *ndev, - netdev_features_t features) +static int ravb_set_features_rx_csum(struct net_device *ndev, + netdev_features_t features) { netdev_features_t changed = ndev->features ^ features; @@ -1869,6 +1931,15 @@ static int ravb_set_features(struct net_device *ndev, return 0; } +static int ravb_set_features(struct net_device *ndev, + netdev_features_t features) +{ + struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; + + return info->set_rx_csum_feature(ndev, features); +} + static const struct net_device_ops ravb_netdev_ops = { .ndo_open = ravb_open, .ndo_stop = ravb_close, @@ -1930,26 +2001,43 @@ static int ravb_mdio_release(struct ravb_private *priv) } static const struct ravb_hw_info ravb_gen3_hw_info = { + .rx_ring_free = ravb_rx_ring_free, + .rx_ring_format = ravb_rx_ring_format, + .alloc_rx_desc = ravb_alloc_rx_desc, + .receive = ravb_rcar_rx, + .set_rate = ravb_set_rate, + .set_rx_csum_feature = ravb_set_features_rx_csum, + .dmac_init = ravb_rcar_dmac_init, + .emac_init = ravb_rcar_emac_init, .gstrings_stats = ravb_gstrings_stats, .gstrings_size = sizeof(ravb_gstrings_stats), .net_hw_features = NETIF_F_RXCSUM, .net_features = NETIF_F_RXCSUM, - .chip_id = RCAR_GEN3, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .internal_delay = 1, .tx_counters = 1, + .multi_irqs = 1, + .ptp_cfg_active = 1, }; static const struct ravb_hw_info ravb_gen2_hw_info = { + .rx_ring_free = ravb_rx_ring_free, + .rx_ring_format = ravb_rx_ring_format, + .alloc_rx_desc = ravb_alloc_rx_desc, + .receive = ravb_rcar_rx, + .set_rate = ravb_set_rate, + .set_rx_csum_feature = ravb_set_features_rx_csum, + .dmac_init = ravb_rcar_dmac_init, + .emac_init = ravb_rcar_emac_init, .gstrings_stats = ravb_gstrings_stats, .gstrings_size = sizeof(ravb_gstrings_stats), .net_hw_features = NETIF_F_RXCSUM, .net_features = NETIF_F_RXCSUM, - .chip_id = RCAR_GEN2, .stats_len = ARRAY_SIZE(ravb_gstrings_stats), .max_rx_len = RX_BUF_SZ + RAVB_ALIGN - 1, .aligned_tx = 1, + .no_ptp_cfg_active = 1, }; static const struct of_device_id ravb_match_table[] = { @@ -1990,8 +2078,9 @@ static int ravb_set_gti(struct net_device *ndev) static void ravb_set_config_mode(struct net_device *ndev) { struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; - if (priv->chip_id == RCAR_GEN2) { + if (info->no_ptp_cfg_active) { ravb_modify(ndev, CCC, CCC_OPC, CCC_OPC_CONFIG); /* Set CSEL value */ ravb_modify(ndev, CCC, CCC_CSEL, CCC_CSEL_HPB); @@ -2052,6 +2141,7 @@ static int ravb_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; const struct ravb_hw_info *info; + struct reset_control *rstc; struct ravb_private *priv; struct net_device *ndev; int error, irq, q; @@ -2064,6 +2154,11 @@ static int ravb_probe(struct platform_device *pdev) return -EINVAL; } + rstc = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL); + if (IS_ERR(rstc)) + return dev_err_probe(&pdev->dev, PTR_ERR(rstc), + "failed to get cpg reset\n"); + ndev = alloc_etherdev_mqs(sizeof(struct ravb_private), NUM_TX_QUEUE, NUM_RX_QUEUE); if (!ndev) @@ -2074,10 +2169,11 @@ static int ravb_probe(struct platform_device *pdev) ndev->features = info->net_features; ndev->hw_features = info->net_hw_features; + reset_control_deassert(rstc); pm_runtime_enable(&pdev->dev); pm_runtime_get_sync(&pdev->dev); - if (info->chip_id == RCAR_GEN3) + if (info->multi_irqs) irq = platform_get_irq_byname(pdev, "ch22"); else irq = platform_get_irq(pdev, 0); @@ -2091,6 +2187,7 @@ static int ravb_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->info = info; + priv->rstc = rstc; priv->ndev = ndev; priv->pdev = pdev; priv->num_tx_ring[RAVB_BE] = BE_TX_RING_SIZE; @@ -2117,7 +2214,7 @@ static int ravb_probe(struct platform_device *pdev) priv->avb_link_active_low = of_property_read_bool(np, "renesas,ether-link-active-low"); - if (info->chip_id == RCAR_GEN3) { + if (info->multi_irqs) { irq = platform_get_irq_byname(pdev, "ch24"); if (irq < 0) { error = irq; @@ -2142,8 +2239,6 @@ static int ravb_probe(struct platform_device *pdev) } } - priv->chip_id = info->chip_id; - priv->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(priv->clk)) { error = PTR_ERR(priv->clk); @@ -2160,8 +2255,12 @@ static int ravb_probe(struct platform_device *pdev) ndev->max_mtu = 2048 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; - priv->num_tx_desc = info->aligned_tx ? - NUM_TX_DESC_GEN2 : NUM_TX_DESC_GEN3; + /* FIXME: R-Car Gen2 has 4byte alignment restriction for tx buffer + * Use two descriptor to handle such situation. First descriptor to + * handle aligned data buffer and second descriptor to handle the + * overflow data because of alignment. + */ + priv->num_tx_desc = info->aligned_tx ? 2 : 1; /* Set function */ ndev->netdev_ops = &ravb_netdev_ops; @@ -2202,7 +2301,7 @@ static int ravb_probe(struct platform_device *pdev) INIT_LIST_HEAD(&priv->ts_skb_list); /* Initialise PTP Clock driver */ - if (info->chip_id != RCAR_GEN2) + if (info->ptp_cfg_active) ravb_ptp_init(ndev, pdev); /* Debug message level */ @@ -2250,7 +2349,7 @@ out_dma_free: priv->desc_bat_dma); /* Stop PTP Clock driver */ - if (info->chip_id != RCAR_GEN2) + if (info->ptp_cfg_active) ravb_ptp_stop(ndev); out_disable_refclk: clk_disable_unprepare(priv->refclk); @@ -2259,6 +2358,7 @@ out_release: pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); + reset_control_assert(rstc); return error; } @@ -2266,9 +2366,10 @@ static int ravb_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct ravb_private *priv = netdev_priv(ndev); + const struct ravb_hw_info *info = priv->info; /* Stop PTP Clock driver */ - if (priv->chip_id != RCAR_GEN2) + if (info->ptp_cfg_active) ravb_ptp_stop(ndev); clk_disable_unprepare(priv->refclk); @@ -2283,6 +2384,7 @@ static int ravb_remove(struct platform_device *pdev) netif_napi_del(&priv->napi[RAVB_BE]); ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); + reset_control_assert(priv->rstc); free_netdev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index 6984bd5b7da9..c099656dd75b 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -179,6 +179,7 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp, { struct ravb_private *priv = container_of(ptp, struct ravb_private, ptp.info); + const struct ravb_hw_info *info = priv->info; struct net_device *ndev = priv->ndev; unsigned long flags; @@ -197,7 +198,7 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp, priv->ptp.extts[req->index] = on; spin_lock_irqsave(&priv->lock, flags); - if (priv->chip_id == RCAR_GEN2) + if (!info->multi_irqs) ravb_modify(ndev, GIC, GIC_PTCE, on ? GIC_PTCE : 0); else if (on) ravb_write(ndev, GIE_PTCS, GIE); @@ -213,6 +214,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, { struct ravb_private *priv = container_of(ptp, struct ravb_private, ptp.info); + const struct ravb_hw_info *info = priv->info; struct net_device *ndev = priv->ndev; struct ravb_ptp_perout *perout; unsigned long flags; @@ -252,7 +254,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, error = ravb_ptp_update_compare(priv, (u32)start_ns); if (!error) { /* Unmask interrupt */ - if (priv->chip_id == RCAR_GEN2) + if (!info->multi_irqs) ravb_modify(ndev, GIC, GIC_PTME, GIC_PTME); else ravb_write(ndev, GIE_PTMS0, GIE); @@ -264,7 +266,7 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, perout->period = 0; /* Mask interrupt */ - if (priv->chip_id == RCAR_GEN2) + if (!info->multi_irqs) ravb_modify(ndev, GIC, GIC_PTME, 0); else ravb_write(ndev, GID_PTMD0, GID); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 4e8d3c28f73e..793f8fbe0069 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -46,6 +46,19 @@ #define MAX_RX_FIFO_SIZE (12 * 1024) #define MAX_TX_FIFO_SIZE (12 * 1024) + +#define FLOW_THRESHOLD(n) ((((n) + 511) / 512) & 0x7F) +#define FLOW_CTRL_THRESHOLD(on, off) ((FLOW_THRESHOLD(on) << 0) | \ + (FLOW_THRESHOLD(off) << 8)) + +/* Flow control turned on when Rx FIFO level rises above this level (bytes) */ +#define FLOW_ON_SS 9216 +#define FLOW_ON_HS 8704 + +/* Flow control turned off when Rx FIFO level falls below this level (bytes) */ +#define FLOW_OFF_SS 4096 +#define FLOW_OFF_HS 1024 + #define DEFAULT_BURST_CAP_SIZE (MAX_TX_FIFO_SIZE) #define DEFAULT_BULK_IN_DELAY (0x0800) #define MAX_SINGLE_PACKET_SIZE (9000) @@ -87,6 +100,12 @@ /* statistic update interval (mSec) */ #define STAT_UPDATE_TIMER (1 * 1000) +/* time to wait for MAC or FCT to stop (jiffies) */ +#define HW_DISABLE_TIMEOUT (HZ / 10) + +/* time to wait between polling MAC or FCT state (ms) */ +#define HW_DISABLE_DELAY_MS 1 + /* defines interrupts from interrupt EP */ #define MAX_INT_EP (32) #define INT_EP_INTEP (31) @@ -341,6 +360,7 @@ struct usb_context { #define EVENT_DEV_ASLEEP 7 #define EVENT_DEV_OPEN 8 #define EVENT_STAT_UPDATE 9 +#define EVENT_DEV_DISCONNECT 10 struct statstage { struct mutex access_lock; /* for stats access */ @@ -370,7 +390,6 @@ struct lan78xx_net { struct sk_buff_head rxq; struct sk_buff_head txq; struct sk_buff_head done; - struct sk_buff_head rxq_pause; struct sk_buff_head txq_pend; struct tasklet_struct bh; @@ -381,8 +400,9 @@ struct lan78xx_net { struct urb *urb_intr; struct usb_anchor deferred; + struct mutex dev_mutex; /* serialise open/stop wrt suspend/resume */ struct mutex phy_mutex; /* for phy access */ - unsigned pipe_in, pipe_out, pipe_intr; + unsigned int pipe_in, pipe_out, pipe_intr; u32 hard_mtu; /* count any extra framing */ size_t rx_urb_size; /* size for rx urbs */ @@ -392,8 +412,7 @@ struct lan78xx_net { wait_queue_head_t *wait; unsigned char suspend_count; - unsigned maxpacket; - struct timer_list delay; + unsigned int maxpacket; struct timer_list stat_monitor; unsigned long data[5]; @@ -426,9 +445,13 @@ MODULE_PARM_DESC(msg_level, "Override default message level"); static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data) { - u32 *buf = kmalloc(sizeof(u32), GFP_KERNEL); + u32 *buf; int ret; + if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) + return -ENODEV; + + buf = kmalloc(sizeof(u32), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -439,7 +462,7 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data) if (likely(ret >= 0)) { le32_to_cpus(buf); *data = *buf; - } else { + } else if (net_ratelimit()) { netdev_warn(dev->net, "Failed to read register index 0x%08x. ret = %d", index, ret); @@ -452,9 +475,13 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data) static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) { - u32 *buf = kmalloc(sizeof(u32), GFP_KERNEL); + u32 *buf; int ret; + if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) + return -ENODEV; + + buf = kmalloc(sizeof(u32), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -465,7 +492,8 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) USB_VENDOR_REQUEST_WRITE_REGISTER, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, buf, 4, USB_CTRL_SET_TIMEOUT); - if (unlikely(ret < 0)) { + if (unlikely(ret < 0) && + net_ratelimit()) { netdev_warn(dev->net, "Failed to write register index 0x%08x. ret = %d", index, ret); @@ -476,6 +504,26 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data) return ret; } +static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask, + u32 data) +{ + int ret; + u32 buf; + + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + buf &= ~mask; + buf |= (mask & data); + + ret = lan78xx_write_reg(dev, reg, buf); + if (ret < 0) + return ret; + + return 0; +} + static int lan78xx_read_stats(struct lan78xx_net *dev, struct lan78xx_statstage *data) { @@ -501,7 +549,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, if (likely(ret >= 0)) { src = (u32 *)stats; dst = (u32 *)data; - for (i = 0; i < sizeof(*stats)/sizeof(u32); i++) { + for (i = 0; i < sizeof(*stats) / sizeof(u32); i++) { le32_to_cpus(&src[i]); dst[i] = src[i]; } @@ -515,10 +563,11 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, return ret; } -#define check_counter_rollover(struct1, dev_stats, member) { \ - if (struct1->member < dev_stats.saved.member) \ - dev_stats.rollover_count.member++; \ - } +#define check_counter_rollover(struct1, dev_stats, member) \ + do { \ + if ((struct1)->member < (dev_stats).saved.member) \ + (dev_stats).rollover_count.member++; \ + } while (0) static void lan78xx_check_stat_rollover(struct lan78xx_net *dev, struct lan78xx_statstage *stats) @@ -844,9 +893,9 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, for (i = 0; i < length; i++) { lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); + ((offset + i) >> 8) & OTP_ADDR1_15_11); lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); + ((offset + i) & OTP_ADDR2_10_3)); lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); @@ -900,9 +949,9 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, for (i = 0; i < length; i++) { lan78xx_write_reg(dev, OTP_ADDR1, - ((offset + i) >> 8) & OTP_ADDR1_15_11); + ((offset + i) >> 8) & OTP_ADDR1_15_11); lan78xx_write_reg(dev, OTP_ADDR2, - ((offset + i) & OTP_ADDR2_10_3)); + ((offset + i) & OTP_ADDR2_10_3)); lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); @@ -959,7 +1008,7 @@ static int lan78xx_dataport_wait_not_busy(struct lan78xx_net *dev) usleep_range(40, 100); } - netdev_warn(dev->net, "lan78xx_dataport_wait_not_busy timed out"); + netdev_warn(dev->net, "%s timed out", __func__); return -EIO; } @@ -972,7 +1021,7 @@ static int lan78xx_dataport_write(struct lan78xx_net *dev, u32 ram_select, int i, ret; if (usb_autopm_get_interface(dev->intf) < 0) - return 0; + return 0; mutex_lock(&pdata->dataport_mutex); @@ -1045,9 +1094,9 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) for (i = 1; i < NUM_OF_MAF; i++) { lan78xx_write_reg(dev, MAF_HI(i), 0); lan78xx_write_reg(dev, MAF_LO(i), - pdata->pfilter_table[i][1]); + pdata->pfilter_table[i][1]); lan78xx_write_reg(dev, MAF_HI(i), - pdata->pfilter_table[i][0]); + pdata->pfilter_table[i][0]); } lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); @@ -1066,11 +1115,12 @@ static void lan78xx_set_multicast(struct net_device *netdev) RFE_CTL_DA_PERFECT_ | RFE_CTL_MCAST_HASH_); for (i = 0; i < DP_SEL_VHF_HASH_LEN; i++) - pdata->mchash_table[i] = 0; + pdata->mchash_table[i] = 0; + /* pfilter_table[0] has own HW address */ for (i = 1; i < NUM_OF_MAF; i++) { - pdata->pfilter_table[i][0] = - pdata->pfilter_table[i][1] = 0; + pdata->pfilter_table[i][0] = 0; + pdata->pfilter_table[i][1] = 0; } pdata->rfe_ctl |= RFE_CTL_BCAST_EN_; @@ -1134,9 +1184,9 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, flow |= FLOW_CR_RX_FCEN_; if (dev->udev->speed == USB_SPEED_SUPER) - fct_flow = 0x817; + fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS); else if (dev->udev->speed == USB_SPEED_HIGH) - fct_flow = 0x211; + fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS); netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s", (cap & FLOW_CTRL_RX ? "enabled" : "disabled"), @@ -1150,6 +1200,52 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, return 0; } +static int lan78xx_mac_reset(struct lan78xx_net *dev) +{ + unsigned long start_time = jiffies; + u32 val; + int ret; + + mutex_lock(&dev->phy_mutex); + + /* Resetting the device while there is activity on the MDIO + * bus can result in the MAC interface locking up and not + * completing register access transactions. + */ + ret = lan78xx_phy_wait_not_busy(dev); + if (ret < 0) + goto done; + + ret = lan78xx_read_reg(dev, MAC_CR, &val); + if (ret < 0) + goto done; + + val |= MAC_CR_RST_; + ret = lan78xx_write_reg(dev, MAC_CR, val); + if (ret < 0) + goto done; + + /* Wait for the reset to complete before allowing any further + * MAC register accesses otherwise the MAC may lock up. + */ + do { + ret = lan78xx_read_reg(dev, MAC_CR, &val); + if (ret < 0) + goto done; + + if (!(val & MAC_CR_RST_)) { + ret = 0; + goto done; + } + } while (!time_after(jiffies, start_time + HZ)); + + ret = -ETIMEDOUT; +done: + mutex_unlock(&dev->phy_mutex); + + return ret; +} + static int lan78xx_link_reset(struct lan78xx_net *dev) { struct phy_device *phydev = dev->net->phydev; @@ -1160,7 +1256,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) /* clear LAN78xx interrupt status */ ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_); if (unlikely(ret < 0)) - return -EIO; + return ret; mutex_lock(&phydev->lock); phy_read_status(phydev); @@ -1171,13 +1267,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) dev->link_on = false; /* reset MAC */ - ret = lan78xx_read_reg(dev, MAC_CR, &buf); - if (unlikely(ret < 0)) - return -EIO; - buf |= MAC_CR_RST_; - ret = lan78xx_write_reg(dev, MAC_CR, buf); - if (unlikely(ret < 0)) - return -EIO; + ret = lan78xx_mac_reset(dev); + if (ret < 0) + return ret; del_timer(&dev->stat_monitor); } else if (link && !dev->link_on) { @@ -1189,18 +1281,30 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (ecmd.base.speed == 1000) { /* disable U2 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf &= ~USB_CFG1_DEV_U2_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; /* enable U1 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf |= USB_CFG1_DEV_U1_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; } else { /* enable U1 & U2 */ ret = lan78xx_read_reg(dev, USB_CFG1, &buf); + if (ret < 0) + return ret; buf |= USB_CFG1_DEV_U2_INIT_EN_; buf |= USB_CFG1_DEV_U1_INIT_EN_; ret = lan78xx_write_reg(dev, USB_CFG1, buf); + if (ret < 0) + return ret; } } @@ -1218,6 +1322,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ret = lan78xx_update_flowcontrol(dev, ecmd.base.duplex, ladv, radv); + if (ret < 0) + return ret; if (!timer_pending(&dev->stat_monitor)) { dev->delta = 1; @@ -1228,7 +1334,7 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) tasklet_schedule(&dev->bh); } - return ret; + return 0; } /* some work can't be done in tasklets, so we use keventd @@ -1264,9 +1370,10 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb) generic_handle_irq(dev->domain_data.phyirq); local_irq_enable(); } - } else + } else { netdev_warn(dev->net, "unexpected interrupt: 0x%08x\n", intdata); + } } static int lan78xx_ethtool_get_eeprom_len(struct net_device *netdev) @@ -1355,7 +1462,7 @@ static void lan78xx_get_wol(struct net_device *netdev, struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); if (usb_autopm_get_interface(dev->intf) < 0) - return; + return; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); if (unlikely(ret < 0)) { @@ -2003,7 +2110,7 @@ static int lan8835_fixup(struct phy_device *phydev) /* RGMII MAC TXC Delay Enable */ lan78xx_write_reg(dev, MAC_RGMII_ID, - MAC_RGMII_ID_TXC_DELAY_EN_); + MAC_RGMII_ID_TXC_DELAY_EN_); /* RGMII TX DLL Tune Adjust */ lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); @@ -2267,11 +2374,16 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) int ll_mtu = new_mtu + netdev->hard_header_len; int old_hard_mtu = dev->hard_mtu; int old_rx_urb_size = dev->rx_urb_size; + int ret; /* no second zero-length packet read wanted after mtu-sized packets */ if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; + ret = usb_autopm_get_interface(dev->intf); + if (ret < 0) + return ret; + lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2287,6 +2399,8 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) } } + usb_autopm_put_interface(dev->intf); + return 0; } @@ -2443,26 +2557,186 @@ static void lan78xx_init_ltm(struct lan78xx_net *dev) lan78xx_write_reg(dev, LTM_INACTIVE1, regs[5]); } +static int lan78xx_start_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enable) +{ + return lan78xx_update_reg(dev, reg, hw_enable, hw_enable); +} + +static int lan78xx_stop_hw(struct lan78xx_net *dev, u32 reg, u32 hw_enabled, + u32 hw_disabled) +{ + unsigned long timeout; + bool stopped = true; + int ret; + u32 buf; + + /* Stop the h/w block (if not already stopped) */ + + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_enabled) { + buf &= ~hw_enabled; + + ret = lan78xx_write_reg(dev, reg, buf); + if (ret < 0) + return ret; + + stopped = false; + timeout = jiffies + HW_DISABLE_TIMEOUT; + do { + ret = lan78xx_read_reg(dev, reg, &buf); + if (ret < 0) + return ret; + + if (buf & hw_disabled) + stopped = true; + else + msleep(HW_DISABLE_DELAY_MS); + } while (!stopped && !time_after(jiffies, timeout)); + } + + ret = stopped ? 0 : -ETIME; + + return ret; +} + +static int lan78xx_flush_fifo(struct lan78xx_net *dev, u32 reg, u32 fifo_flush) +{ + return lan78xx_update_reg(dev, reg, fifo_flush, fifo_flush); +} + +static int lan78xx_start_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start tx path"); + + /* Start the MAC transmitter */ + + ret = lan78xx_start_hw(dev, MAC_TX, MAC_TX_TXEN_); + if (ret < 0) + return ret; + + /* Start the Tx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_tx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop tx path"); + + /* Stop the Tx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_TX_CTL, FCT_TX_CTL_EN_, FCT_TX_CTL_DIS_); + if (ret < 0) + return ret; + + /* Stop the MAC transmitter */ + + ret = lan78xx_stop_hw(dev, MAC_TX, MAC_TX_TXEN_, MAC_TX_TXD_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Tx path is stopped before calling + * lan78xx_flush_tx_fifo(). + */ +static int lan78xx_flush_tx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_TX_CTL, FCT_TX_CTL_RST_); +} + +static int lan78xx_start_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "start rx path"); + + /* Start the Rx FIFO */ + + ret = lan78xx_start_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_); + if (ret < 0) + return ret; + + /* Start the MAC receiver*/ + + ret = lan78xx_start_hw(dev, MAC_RX, MAC_RX_RXEN_); + if (ret < 0) + return ret; + + return 0; +} + +static int lan78xx_stop_rx_path(struct lan78xx_net *dev) +{ + int ret; + + netif_dbg(dev, drv, dev->net, "stop rx path"); + + /* Stop the MAC receiver */ + + ret = lan78xx_stop_hw(dev, MAC_RX, MAC_RX_RXEN_, MAC_RX_RXD_); + if (ret < 0) + return ret; + + /* Stop the Rx FIFO */ + + ret = lan78xx_stop_hw(dev, FCT_RX_CTL, FCT_RX_CTL_EN_, FCT_RX_CTL_DIS_); + if (ret < 0) + return ret; + + return 0; +} + +/* The caller must ensure the Rx path is stopped before calling + * lan78xx_flush_rx_fifo(). + */ +static int lan78xx_flush_rx_fifo(struct lan78xx_net *dev) +{ + return lan78xx_flush_fifo(dev, FCT_RX_CTL, FCT_RX_CTL_RST_); +} + static int lan78xx_reset(struct lan78xx_net *dev) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); - u32 buf; - int ret = 0; unsigned long timeout; + int ret; + u32 buf; u8 sig; ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + buf |= HW_CFG_LRST_; + ret = lan78xx_write_reg(dev, HW_CFG, buf); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on completion of LiteReset"); - return -EIO; + ret = -ETIMEDOUT; + return ret; } } while (buf & HW_CFG_LRST_); @@ -2470,13 +2744,22 @@ static int lan78xx_reset(struct lan78xx_net *dev) /* save DEVID for later usage */ ret = lan78xx_read_reg(dev, ID_REV, &buf); + if (ret < 0) + return ret; + dev->chipid = (buf & ID_REV_CHIP_ID_MASK_) >> 16; dev->chiprev = buf & ID_REV_CHIP_REV_MASK_; /* Respond to the IN token with a NAK */ ret = lan78xx_read_reg(dev, USB_CFG0, &buf); + if (ret < 0) + return ret; + buf |= USB_CFG_BIR_; + ret = lan78xx_write_reg(dev, USB_CFG0, buf); + if (ret < 0) + return ret; /* Init LTM */ lan78xx_init_ltm(dev); @@ -2499,53 +2782,105 @@ static int lan78xx_reset(struct lan78xx_net *dev) } ret = lan78xx_write_reg(dev, BURST_CAP, buf); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, BULK_IN_DLY, DEFAULT_BULK_IN_DELAY); + if (ret < 0) + return ret; ret = lan78xx_read_reg(dev, HW_CFG, &buf); + if (ret < 0) + return ret; + buf |= HW_CFG_MEF_; + ret = lan78xx_write_reg(dev, HW_CFG, buf); + if (ret < 0) + return ret; ret = lan78xx_read_reg(dev, USB_CFG0, &buf); + if (ret < 0) + return ret; + buf |= USB_CFG_BCE_; + ret = lan78xx_write_reg(dev, USB_CFG0, buf); + if (ret < 0) + return ret; /* set FIFO sizes */ buf = (MAX_RX_FIFO_SIZE - 512) / 512; + ret = lan78xx_write_reg(dev, FCT_RX_FIFO_END, buf); + if (ret < 0) + return ret; buf = (MAX_TX_FIFO_SIZE - 512) / 512; + ret = lan78xx_write_reg(dev, FCT_TX_FIFO_END, buf); + if (ret < 0) + return ret; ret = lan78xx_write_reg(dev, INT_STS, INT_STS_CLEAR_ALL_); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, FLOW, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, FCT_FLOW, 0); + if (ret < 0) + return ret; /* Don't need rfe_ctl_lock during initialisation */ ret = lan78xx_read_reg(dev, RFE_CTL, &pdata->rfe_ctl); + if (ret < 0) + return ret; + pdata->rfe_ctl |= RFE_CTL_BCAST_EN_ | RFE_CTL_DA_PERFECT_; + ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + if (ret < 0) + return ret; /* Enable or disable checksum offload engines */ - lan78xx_set_features(dev->net, dev->net->features); + ret = lan78xx_set_features(dev->net, dev->net->features); + if (ret < 0) + return ret; lan78xx_set_multicast(dev->net); /* reset PHY */ ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + buf |= PMT_CTL_PHY_RST_; + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; timeout = jiffies + HZ; do { mdelay(1); ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout waiting for PHY Reset"); - return -EIO; + ret = -ETIMEDOUT; + return ret; } } while ((buf & PMT_CTL_PHY_RST_) || !(buf & PMT_CTL_READY_)); ret = lan78xx_read_reg(dev, MAC_CR, &buf); + if (ret < 0) + return ret; + /* LAN7801 only has RGMII mode */ if (dev->chipid == ID_REV_CHIP_ID_7801_) buf &= ~MAC_CR_GMII_EN_; @@ -2559,27 +2894,13 @@ static int lan78xx_reset(struct lan78xx_net *dev) } } ret = lan78xx_write_reg(dev, MAC_CR, buf); - - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf |= MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - - ret = lan78xx_read_reg(dev, FCT_TX_CTL, &buf); - buf |= FCT_TX_CTL_EN_; - ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf); + if (ret < 0) + return ret; ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + VLAN_ETH_HLEN); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); - - ret = lan78xx_read_reg(dev, FCT_RX_CTL, &buf); - buf |= FCT_RX_CTL_EN_; - ret = lan78xx_write_reg(dev, FCT_RX_CTL, buf); - - return 0; + return ret; } static void lan78xx_init_stats(struct lan78xx_net *dev) @@ -2613,9 +2934,13 @@ static int lan78xx_open(struct net_device *net) struct lan78xx_net *dev = netdev_priv(net); int ret; + netif_dbg(dev, ifup, dev->net, "open device"); + ret = usb_autopm_get_interface(dev->intf); if (ret < 0) - goto out; + return ret; + + mutex_lock(&dev->dev_mutex); phy_start(net->phydev); @@ -2631,6 +2956,20 @@ static int lan78xx_open(struct net_device *net) } } + ret = lan78xx_flush_rx_fifo(dev); + if (ret < 0) + goto done; + ret = lan78xx_flush_tx_fifo(dev); + if (ret < 0) + goto done; + + ret = lan78xx_start_tx_path(dev); + if (ret < 0) + goto done; + ret = lan78xx_start_rx_path(dev); + if (ret < 0) + goto done; + lan78xx_init_stats(dev); set_bit(EVENT_DEV_OPEN, &dev->flags); @@ -2641,9 +2980,10 @@ static int lan78xx_open(struct net_device *net) lan78xx_defer_kevent(dev, EVENT_LINK_RESET); done: + mutex_unlock(&dev->dev_mutex); + usb_autopm_put_interface(dev->intf); -out: return ret; } @@ -2660,53 +3000,74 @@ static void lan78xx_terminate_urbs(struct lan78xx_net *dev) temp = unlink_urbs(dev, &dev->txq) + unlink_urbs(dev, &dev->rxq); /* maybe wait for deletions to finish. */ - while (!skb_queue_empty(&dev->rxq) && - !skb_queue_empty(&dev->txq) && - !skb_queue_empty(&dev->done)) { + while (!skb_queue_empty(&dev->rxq) || + !skb_queue_empty(&dev->txq)) { schedule_timeout(msecs_to_jiffies(UNLINK_TIMEOUT_MS)); set_current_state(TASK_UNINTERRUPTIBLE); netif_dbg(dev, ifdown, dev->net, - "waited for %d urb completions\n", temp); + "waited for %d urb completions", temp); } set_current_state(TASK_RUNNING); dev->wait = NULL; remove_wait_queue(&unlink_wakeup, &wait); + + while (!skb_queue_empty(&dev->done)) { + struct skb_data *entry; + struct sk_buff *skb; + + skb = skb_dequeue(&dev->done); + entry = (struct skb_data *)(skb->cb); + usb_free_urb(entry->urb); + dev_kfree_skb(skb); + } } static int lan78xx_stop(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); + netif_dbg(dev, ifup, dev->net, "stop device"); + + mutex_lock(&dev->dev_mutex); + if (timer_pending(&dev->stat_monitor)) del_timer_sync(&dev->stat_monitor); - if (net->phydev) - phy_stop(net->phydev); - clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue(net); + tasklet_kill(&dev->bh); + + lan78xx_terminate_urbs(dev); netif_info(dev, ifdown, dev->net, "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n", net->stats.rx_packets, net->stats.tx_packets, net->stats.rx_errors, net->stats.tx_errors); - lan78xx_terminate_urbs(dev); + /* ignore errors that occur stopping the Tx and Rx data paths */ + lan78xx_stop_tx_path(dev); + lan78xx_stop_rx_path(dev); - usb_kill_urb(dev->urb_intr); + if (net->phydev) + phy_stop(net->phydev); - skb_queue_purge(&dev->rxq_pause); + usb_kill_urb(dev->urb_intr); /* deferred work (task, timer, softirq) must also stop. * can't flush_scheduled_work() until we drop rtnl (later), * else workers could deadlock; so make workers a NOP. */ - dev->flags = 0; + clear_bit(EVENT_TX_HALT, &dev->flags); + clear_bit(EVENT_RX_HALT, &dev->flags); + clear_bit(EVENT_LINK_RESET, &dev->flags); + clear_bit(EVENT_STAT_UPDATE, &dev->flags); + cancel_delayed_work_sync(&dev->wq); - tasklet_kill(&dev->bh); usb_autopm_put_interface(dev->intf); + mutex_unlock(&dev->dev_mutex); + return 0; } @@ -2795,16 +3156,23 @@ static void tx_complete(struct urb *urb) /* software-driven interface shutdown */ case -ECONNRESET: case -ESHUTDOWN: + netif_dbg(dev, tx_err, dev->net, + "tx err interface gone %d\n", + entry->urb->status); break; case -EPROTO: case -ETIME: case -EILSEQ: netif_stop_queue(dev->net); + netif_dbg(dev, tx_err, dev->net, + "tx err queue stopped %d\n", + entry->urb->status); break; default: netif_dbg(dev, tx_err, dev->net, - "tx err %d\n", entry->urb->status); + "unknown tx err %d\n", + entry->urb->status); break; } } @@ -2829,6 +3197,9 @@ lan78xx_start_xmit(struct sk_buff *skb, struct net_device *net) struct lan78xx_net *dev = netdev_priv(net); struct sk_buff *skb2 = NULL; + if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) + schedule_delayed_work(&dev->wq, 0); + if (skb) { skb_tx_timestamp(skb); skb2 = lan78xx_tx_prep(dev, skb, GFP_ATOMIC); @@ -2988,11 +3359,6 @@ static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { int status; - if (test_bit(EVENT_RX_PAUSED, &dev->flags)) { - skb_queue_tail(&dev->rxq_pause, skb); - return; - } - dev->net->stats.rx_packets++; dev->net->stats.rx_bytes += skb->len; @@ -3140,6 +3506,7 @@ static int rx_submit(struct lan78xx_net *dev, struct urb *urb, gfp_t flags) lan78xx_defer_kevent(dev, EVENT_RX_HALT); break; case -ENODEV: + case -ENOENT: netif_dbg(dev, ifdown, dev->net, "device gone\n"); netif_device_detach(dev->net); break; @@ -3340,6 +3707,12 @@ gso_skb: lan78xx_defer_kevent(dev, EVENT_TX_HALT); usb_autopm_put_interface_async(dev->intf); break; + case -ENODEV: + case -ENOENT: + netif_dbg(dev, tx_err, dev->net, + "tx: submit urb err %d (disconnected?)", ret); + netif_device_detach(dev->net); + break; default: usb_autopm_put_interface_async(dev->intf); netif_dbg(dev, tx_err, dev->net, @@ -3356,9 +3729,10 @@ drop: if (skb) dev_kfree_skb_any(skb); usb_free_urb(urb); - } else + } else { netif_dbg(dev, tx_queued, dev->net, "> tx, len %d, type 0x%x\n", length, skb->protocol); + } } static void lan78xx_rx_bh(struct lan78xx_net *dev) @@ -3421,8 +3795,7 @@ static void lan78xx_bh(struct tasklet_struct *t) if (!skb_queue_empty(&dev->txq_pend)) lan78xx_tx_bh(dev); - if (!timer_pending(&dev->delay) && - !test_bit(EVENT_RX_HALT, &dev->flags)) + if (!test_bit(EVENT_RX_HALT, &dev->flags)) lan78xx_rx_bh(dev); } } @@ -3434,18 +3807,20 @@ static void lan78xx_delayedwork(struct work_struct *work) dev = container_of(work, struct lan78xx_net, wq.work); + if (test_bit(EVENT_DEV_DISCONNECT, &dev->flags)) + return; + + if (usb_autopm_get_interface(dev->intf) < 0) + return; + if (test_bit(EVENT_TX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->txq); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto fail_pipe; + status = usb_clear_halt(dev->udev, dev->pipe_out); - usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_tx_err(dev)) -fail_pipe: netdev_err(dev->net, "can't clear tx halt, status %d\n", status); @@ -3455,18 +3830,14 @@ fail_pipe: netif_wake_queue(dev->net); } } + if (test_bit(EVENT_RX_HALT, &dev->flags)) { unlink_urbs(dev, &dev->rxq); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto fail_halt; status = usb_clear_halt(dev->udev, dev->pipe_in); - usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { if (netif_msg_rx_err(dev)) -fail_halt: netdev_err(dev->net, "can't clear rx halt, status %d\n", status); @@ -3480,16 +3851,9 @@ fail_halt: int ret = 0; clear_bit(EVENT_LINK_RESET, &dev->flags); - status = usb_autopm_get_interface(dev->intf); - if (status < 0) - goto skip_reset; if (lan78xx_link_reset(dev) < 0) { - usb_autopm_put_interface(dev->intf); -skip_reset: netdev_info(dev->net, "link reset failed (%d)\n", ret); - } else { - usb_autopm_put_interface(dev->intf); } } @@ -3503,6 +3867,8 @@ skip_reset: dev->delta = min((dev->delta * 2), 50); } + + usb_autopm_put_interface(dev->intf); } static void intr_complete(struct urb *urb) @@ -3518,6 +3884,7 @@ static void intr_complete(struct urb *urb) /* software-driven interface shutdown */ case -ENOENT: /* urb killed */ + case -ENODEV: /* hardware gone */ case -ESHUTDOWN: /* hardware gone */ netif_dbg(dev, ifdown, dev->net, "intr shutdown, code %d\n", status); @@ -3531,14 +3898,29 @@ static void intr_complete(struct urb *urb) break; } - if (!netif_running(dev->net)) + if (!netif_device_present(dev->net) || + !netif_running(dev->net)) { + netdev_warn(dev->net, "not submitting new status URB"); return; + } memset(urb->transfer_buffer, 0, urb->transfer_buffer_length); status = usb_submit_urb(urb, GFP_ATOMIC); - if (status != 0) + + switch (status) { + case 0: + break; + case -ENODEV: + case -ENOENT: + netif_dbg(dev, timer, dev->net, + "intr resubmit %d (disconnect?)", status); + netif_device_detach(dev->net); + break; + default: netif_err(dev, timer, dev->net, "intr resubmit --> %d\n", status); + break; + } } static void lan78xx_disconnect(struct usb_interface *intf) @@ -3553,8 +3935,15 @@ static void lan78xx_disconnect(struct usb_interface *intf) if (!dev) return; + set_bit(EVENT_DEV_DISCONNECT, &dev->flags); + udev = interface_to_usbdev(intf); net = dev->net; + + unregister_netdev(net); + + cancel_delayed_work_sync(&dev->wq); + phydev = net->phydev; phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0); @@ -3565,12 +3954,11 @@ static void lan78xx_disconnect(struct usb_interface *intf) if (phy_is_pseudo_fixed_link(phydev)) fixed_phy_unregister(phydev); - unregister_netdev(net); - - cancel_delayed_work_sync(&dev->wq); - usb_scuttle_anchored_urbs(&dev->deferred); + if (timer_pending(&dev->stat_monitor)) + del_timer_sync(&dev->stat_monitor); + lan78xx_unbind(dev, intf); usb_kill_urb(dev->urb_intr); @@ -3632,8 +4020,8 @@ static int lan78xx_probe(struct usb_interface *intf, struct net_device *netdev; struct usb_device *udev; int ret; - unsigned maxp; - unsigned period; + unsigned int maxp; + unsigned int period; u8 *buf = NULL; udev = interface_to_usbdev(intf); @@ -3659,9 +4047,9 @@ static int lan78xx_probe(struct usb_interface *intf, skb_queue_head_init(&dev->rxq); skb_queue_head_init(&dev->txq); skb_queue_head_init(&dev->done); - skb_queue_head_init(&dev->rxq_pause); skb_queue_head_init(&dev->txq_pend); mutex_init(&dev->phy_mutex); + mutex_init(&dev->dev_mutex); tasklet_setup(&dev->bh, lan78xx_bh); INIT_DELAYED_WORK(&dev->wq, lan78xx_delayedwork); @@ -3798,37 +4186,119 @@ static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len) return crc; } -static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) +static int lan78xx_set_auto_suspend(struct lan78xx_net *dev) { u32 buf; - int mask_index; - u16 crc; - u32 temp_wucsr; - u32 temp_pmt_ctl; + int ret; + + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + return ret; + + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + return ret; + + /* auto suspend (selective suspend) */ + + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + return ret; + + /* set goodframe wakeup */ + + ret = lan78xx_read_reg(dev, WUCSR, &buf); + if (ret < 0) + return ret; + + buf |= WUCSR_RFE_WAKE_EN_; + buf |= WUCSR_STORE_WAKE_; + + ret = lan78xx_write_reg(dev, WUCSR, buf); + if (ret < 0) + return ret; + + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + + buf &= ~PMT_CTL_RES_CLR_WKP_EN_; + buf |= PMT_CTL_RES_CLR_WKP_STS_; + buf |= PMT_CTL_PHY_WAKE_EN_; + buf |= PMT_CTL_WOL_EN_; + buf &= ~PMT_CTL_SUS_MODE_MASK_; + buf |= PMT_CTL_SUS_MODE_3_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; + + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + + buf |= PMT_CTL_WUPS_MASK_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; + + ret = lan78xx_start_rx_path(dev); + + return ret; +} + +static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) +{ const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E }; const u8 ipv6_multicast[3] = { 0x33, 0x33 }; const u8 arp_type[2] = { 0x08, 0x06 }; + u32 temp_pmt_ctl; + int mask_index; + u32 temp_wucsr; + u32 buf; + u16 crc; + int ret; - lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - lan78xx_write_reg(dev, MAC_TX, buf); - lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + return ret; + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUCSR, 0); - lan78xx_write_reg(dev, WUCSR2, 0); - lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + return ret; temp_wucsr = 0; temp_pmt_ctl = 0; - lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + + ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + if (ret < 0) + return ret; + temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_; temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_; - for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) - lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) { + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + if (ret < 0) + return ret; + } mask_index = 0; if (wol & WAKE_PHY) { @@ -3857,30 +4327,52 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) /* set WUF_CFG & WUF_MASK for IPv4 Multicast */ crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; /* for IPv6 Multicast */ crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3901,16 +4393,27 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) * for packettype (offset 12,13) = ARP (0x0806) */ crc = lan78xx_wakeframe_crc16(arp_type, 2); - lan78xx_write_reg(dev, WUF_CFG(mask_index), + ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_ALL_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); + if (ret < 0) + return ret; + + ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + if (ret < 0) + return ret; + ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + if (ret < 0) + return ret; - lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); - lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3918,7 +4421,9 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - lan78xx_write_reg(dev, WUCSR, temp_wucsr); + ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr); + if (ret < 0) + return ret; /* when multiple WOL bits are set */ if (hweight_long((unsigned long)wol) > 1) { @@ -3926,33 +4431,45 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + if (ret < 0) + return ret; /* clear WUPS */ - lan78xx_read_reg(dev, PMT_CTL, &buf); + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + return ret; + buf |= PMT_CTL_WUPS_MASK_; - lan78xx_write_reg(dev, PMT_CTL, buf); - lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + return ret; - return 0; + ret = lan78xx_start_rx_path(dev); + + return ret; } static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) { struct lan78xx_net *dev = usb_get_intfdata(intf); - struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); - u32 buf; + bool dev_open; int ret; - if (!dev->suspend_count++) { + mutex_lock(&dev->dev_mutex); + + netif_dbg(dev, ifdown, dev->net, + "suspending: pm event %#x", message.event); + + dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); + + if (dev_open) { spin_lock_irq(&dev->txq.lock); /* don't autosuspend while transmitting */ if ((skb_queue_len(&dev->txq) || skb_queue_len(&dev->txq_pend)) && - PMSG_IS_AUTO(message)) { + PMSG_IS_AUTO(message)) { spin_unlock_irq(&dev->txq.lock); ret = -EBUSY; goto out; @@ -3961,129 +4478,207 @@ static int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) spin_unlock_irq(&dev->txq.lock); } - /* stop TX & RX */ - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + /* stop RX */ + ret = lan78xx_stop_rx_path(dev); + if (ret < 0) + goto out; + + ret = lan78xx_flush_rx_fifo(dev); + if (ret < 0) + goto out; + + /* stop Tx */ + ret = lan78xx_stop_tx_path(dev); + if (ret < 0) + goto out; - /* empty out the rx and queues */ + /* empty out the Rx and Tx queues */ netif_device_detach(dev->net); lan78xx_terminate_urbs(dev); usb_kill_urb(dev->urb_intr); /* reattach */ netif_device_attach(dev->net); - } - if (test_bit(EVENT_DEV_ASLEEP, &dev->flags)) { del_timer(&dev->stat_monitor); if (PMSG_IS_AUTO(message)) { - /* auto suspend (selective suspend) */ - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + ret = lan78xx_set_auto_suspend(dev); + if (ret < 0) + goto out; + } else { + struct lan78xx_priv *pdata; - ret = lan78xx_write_reg(dev, WUCSR, 0); - ret = lan78xx_write_reg(dev, WUCSR2, 0); - ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + pdata = (struct lan78xx_priv *)(dev->data[0]); + netif_carrier_off(dev->net); + ret = lan78xx_set_suspend(dev, pdata->wol); + if (ret < 0) + goto out; + } + } else { + /* Interface is down; don't allow WOL and PHY + * events to wake up the host + */ + u32 buf; - /* set goodframe wakeup */ - ret = lan78xx_read_reg(dev, WUCSR, &buf); + set_bit(EVENT_DEV_ASLEEP, &dev->flags); - buf |= WUCSR_RFE_WAKE_EN_; - buf |= WUCSR_STORE_WAKE_; + ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + goto out; + ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + goto out; - ret = lan78xx_write_reg(dev, WUCSR, buf); + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + goto out; + + buf &= ~PMT_CTL_RES_CLR_WKP_EN_; + buf |= PMT_CTL_RES_CLR_WKP_STS_; + buf &= ~PMT_CTL_SUS_MODE_MASK_; + buf |= PMT_CTL_SUS_MODE_3_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + goto out; - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + if (ret < 0) + goto out; + + buf |= PMT_CTL_WUPS_MASK_; + + ret = lan78xx_write_reg(dev, PMT_CTL, buf); + if (ret < 0) + goto out; + } - buf &= ~PMT_CTL_RES_CLR_WKP_EN_; - buf |= PMT_CTL_RES_CLR_WKP_STS_; + ret = 0; +out: + mutex_unlock(&dev->dev_mutex); - buf |= PMT_CTL_PHY_WAKE_EN_; - buf |= PMT_CTL_WOL_EN_; - buf &= ~PMT_CTL_SUS_MODE_MASK_; - buf |= PMT_CTL_SUS_MODE_3_; + return ret; +} - ret = lan78xx_write_reg(dev, PMT_CTL, buf); +static bool lan78xx_submit_deferred_urbs(struct lan78xx_net *dev) +{ + bool pipe_halted = false; + struct urb *urb; - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + while ((urb = usb_get_from_anchor(&dev->deferred))) { + struct sk_buff *skb = urb->context; + int ret; - buf |= PMT_CTL_WUPS_MASK_; + if (!netif_device_present(dev->net) || + !netif_carrier_ok(dev->net) || + pipe_halted) { + usb_free_urb(urb); + dev_kfree_skb(skb); + continue; + } - ret = lan78xx_write_reg(dev, PMT_CTL, buf); + ret = usb_submit_urb(urb, GFP_ATOMIC); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); - buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + if (ret == 0) { + netif_trans_update(dev->net); + lan78xx_queue_skb(&dev->txq, skb, tx_start); } else { - lan78xx_set_suspend(dev, pdata->wol); + usb_free_urb(urb); + dev_kfree_skb(skb); + + if (ret == -EPIPE) { + netif_stop_queue(dev->net); + pipe_halted = true; + } else if (ret == -ENODEV) { + netif_device_detach(dev->net); + } } } - ret = 0; -out: - return ret; + return pipe_halted; } static int lan78xx_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); - struct sk_buff *skb; - struct urb *res; + bool dev_open; int ret; - u32 buf; - if (!timer_pending(&dev->stat_monitor)) { - dev->delta = 1; - mod_timer(&dev->stat_monitor, - jiffies + STAT_UPDATE_TIMER); - } + mutex_lock(&dev->dev_mutex); - if (!--dev->suspend_count) { - /* resume interrupt URBs */ - if (dev->urb_intr && test_bit(EVENT_DEV_OPEN, &dev->flags)) - usb_submit_urb(dev->urb_intr, GFP_NOIO); + netif_dbg(dev, ifup, dev->net, "resuming device"); + + dev_open = test_bit(EVENT_DEV_OPEN, &dev->flags); + + if (dev_open) { + bool pipe_halted = false; + + ret = lan78xx_flush_tx_fifo(dev); + if (ret < 0) + goto out; + + if (dev->urb_intr) { + int ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL); - spin_lock_irq(&dev->txq.lock); - while ((res = usb_get_from_anchor(&dev->deferred))) { - skb = (struct sk_buff *)res->context; - ret = usb_submit_urb(res, GFP_ATOMIC); if (ret < 0) { - dev_kfree_skb_any(skb); - usb_free_urb(res); - usb_autopm_put_interface_async(dev->intf); - } else { - netif_trans_update(dev->net); - lan78xx_queue_skb(&dev->txq, skb, tx_start); + if (ret == -ENODEV) + netif_device_detach(dev->net); + + netdev_warn(dev->net, "Failed to submit intr URB"); } } + spin_lock_irq(&dev->txq.lock); + + if (netif_device_present(dev->net)) { + pipe_halted = lan78xx_submit_deferred_urbs(dev); + + if (pipe_halted) + lan78xx_defer_kevent(dev, EVENT_TX_HALT); + } + clear_bit(EVENT_DEV_ASLEEP, &dev->flags); + spin_unlock_irq(&dev->txq.lock); - if (test_bit(EVENT_DEV_OPEN, &dev->flags)) { - if (!(skb_queue_len(&dev->txq) >= dev->tx_qlen)) - netif_start_queue(dev->net); - tasklet_schedule(&dev->bh); + if (!pipe_halted && + netif_device_present(dev->net) && + (skb_queue_len(&dev->txq) < dev->tx_qlen)) + netif_start_queue(dev->net); + + ret = lan78xx_start_tx_path(dev); + if (ret < 0) + goto out; + + tasklet_schedule(&dev->bh); + + if (!timer_pending(&dev->stat_monitor)) { + dev->delta = 1; + mod_timer(&dev->stat_monitor, + jiffies + STAT_UPDATE_TIMER); } + + } else { + clear_bit(EVENT_DEV_ASLEEP, &dev->flags); } ret = lan78xx_write_reg(dev, WUCSR2, 0); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR, 0); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR2, WUCSR2_NS_RCD_ | WUCSR2_ARP_RCD_ | WUCSR2_IPV6_TCPSYN_RCD_ | WUCSR2_IPV4_TCPSYN_RCD_); + if (ret < 0) + goto out; ret = lan78xx_write_reg(dev, WUCSR, WUCSR_EEE_TX_WAKE_ | WUCSR_EEE_RX_WAKE_ | @@ -4092,23 +4687,32 @@ static int lan78xx_resume(struct usb_interface *intf) WUCSR_WUFR_ | WUCSR_MPR_ | WUCSR_BCST_FR_); + if (ret < 0) + goto out; - ret = lan78xx_read_reg(dev, MAC_TX, &buf); - buf |= MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); + ret = 0; +out: + mutex_unlock(&dev->dev_mutex); - return 0; + return ret; } static int lan78xx_reset_resume(struct usb_interface *intf) { struct lan78xx_net *dev = usb_get_intfdata(intf); + int ret; - lan78xx_reset(dev); + netif_dbg(dev, ifup, dev->net, "(reset) resuming device"); + + ret = lan78xx_reset(dev); + if (ret < 0) + return ret; phy_start(dev->net->phydev); - return lan78xx_resume(intf); + ret = lan78xx_resume(intf); + + return ret; } static const struct usb_device_id products[] = { diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 44275908d61a..e31b98403f31 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -126,21 +126,17 @@ struct netfront_queue { /* * {tx,rx}_skbs store outstanding skbuffs. Free tx_skb entries - * are linked from tx_skb_freelist through skb_entry.link. - * - * NB. Freelist index entries are always going to be less than - * PAGE_OFFSET, whereas pointers to skbs will always be equal or - * greater than PAGE_OFFSET: we use this property to distinguish - * them. + * are linked from tx_skb_freelist through tx_link. */ - union skb_entry { - struct sk_buff *skb; - unsigned long link; - } tx_skbs[NET_TX_RING_SIZE]; + struct sk_buff *tx_skbs[NET_TX_RING_SIZE]; + unsigned short tx_link[NET_TX_RING_SIZE]; +#define TX_LINK_NONE 0xffff +#define TX_PENDING 0xfffe grant_ref_t gref_tx_head; grant_ref_t grant_tx_ref[NET_TX_RING_SIZE]; struct page *grant_tx_page[NET_TX_RING_SIZE]; unsigned tx_skb_freelist; + unsigned int tx_pend_queue; spinlock_t rx_lock ____cacheline_aligned_in_smp; struct xen_netif_rx_front_ring rx; @@ -173,6 +169,9 @@ struct netfront_info { bool netback_has_xdp_headroom; bool netfront_xdp_enabled; + /* Is device behaving sane? */ + bool broken; + atomic_t rx_gso_checksum_fixup; }; @@ -181,33 +180,25 @@ struct netfront_rx_info { struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX - 1]; }; -static void skb_entry_set_link(union skb_entry *list, unsigned short id) -{ - list->link = id; -} - -static int skb_entry_is_link(const union skb_entry *list) -{ - BUILD_BUG_ON(sizeof(list->skb) != sizeof(list->link)); - return (unsigned long)list->skb < PAGE_OFFSET; -} - /* * Access macros for acquiring freeing slots in tx_skbs[]. */ -static void add_id_to_freelist(unsigned *head, union skb_entry *list, - unsigned short id) +static void add_id_to_list(unsigned *head, unsigned short *list, + unsigned short id) { - skb_entry_set_link(&list[id], *head); + list[id] = *head; *head = id; } -static unsigned short get_id_from_freelist(unsigned *head, - union skb_entry *list) +static unsigned short get_id_from_list(unsigned *head, unsigned short *list) { unsigned int id = *head; - *head = list[id].link; + + if (id != TX_LINK_NONE) { + *head = list[id]; + list[id] = TX_LINK_NONE; + } return id; } @@ -363,7 +354,7 @@ static int xennet_open(struct net_device *dev) unsigned int i = 0; struct netfront_queue *queue = NULL; - if (!np->queues) + if (!np->queues || np->broken) return -ENODEV; for (i = 0; i < num_queues; ++i) { @@ -391,27 +382,47 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) unsigned short id; struct sk_buff *skb; bool more_to_do; + const struct device *dev = &queue->info->netdev->dev; BUG_ON(!netif_carrier_ok(queue->info->netdev)); do { prod = queue->tx.sring->rsp_prod; + if (RING_RESPONSE_PROD_OVERFLOW(&queue->tx, prod)) { + dev_alert(dev, "Illegal number of responses %u\n", + prod - queue->tx.rsp_cons); + goto err; + } rmb(); /* Ensure we see responses up to 'rp'. */ for (cons = queue->tx.rsp_cons; cons != prod; cons++) { - struct xen_netif_tx_response *txrsp; + struct xen_netif_tx_response txrsp; - txrsp = RING_GET_RESPONSE(&queue->tx, cons); - if (txrsp->status == XEN_NETIF_RSP_NULL) + RING_COPY_RESPONSE(&queue->tx, cons, &txrsp); + if (txrsp.status == XEN_NETIF_RSP_NULL) continue; - id = txrsp->id; - skb = queue->tx_skbs[id].skb; + id = txrsp.id; + if (id >= RING_SIZE(&queue->tx)) { + dev_alert(dev, + "Response has incorrect id (%u)\n", + id); + goto err; + } + if (queue->tx_link[id] != TX_PENDING) { + dev_alert(dev, + "Response for inactive request\n"); + goto err; + } + + queue->tx_link[id] = TX_LINK_NONE; + skb = queue->tx_skbs[id]; + queue->tx_skbs[id] = NULL; if (unlikely(gnttab_query_foreign_access( queue->grant_tx_ref[id]) != 0)) { - pr_alert("%s: warning -- grant still in use by backend domain\n", - __func__); - BUG(); + dev_alert(dev, + "Grant still in use by backend domain\n"); + goto err; } gnttab_end_foreign_access_ref( queue->grant_tx_ref[id], GNTMAP_readonly); @@ -419,7 +430,7 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) &queue->gref_tx_head, queue->grant_tx_ref[id]); queue->grant_tx_ref[id] = GRANT_INVALID_REF; queue->grant_tx_page[id] = NULL; - add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, id); + add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, id); dev_kfree_skb_irq(skb); } @@ -429,13 +440,20 @@ static void xennet_tx_buf_gc(struct netfront_queue *queue) } while (more_to_do); xennet_maybe_wake_tx(queue); + + return; + + err: + queue->info->broken = true; + dev_alert(dev, "Disabled for further use\n"); } struct xennet_gnttab_make_txreq { struct netfront_queue *queue; struct sk_buff *skb; struct page *page; - struct xen_netif_tx_request *tx; /* Last request */ + struct xen_netif_tx_request *tx; /* Last request on ring page */ + struct xen_netif_tx_request tx_local; /* Last request local copy*/ unsigned int size; }; @@ -451,7 +469,7 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, struct netfront_queue *queue = info->queue; struct sk_buff *skb = info->skb; - id = get_id_from_freelist(&queue->tx_skb_freelist, queue->tx_skbs); + id = get_id_from_list(&queue->tx_skb_freelist, queue->tx_link); tx = RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); ref = gnttab_claim_grant_reference(&queue->gref_tx_head); WARN_ON_ONCE(IS_ERR_VALUE((unsigned long)(int)ref)); @@ -459,34 +477,37 @@ static void xennet_tx_setup_grant(unsigned long gfn, unsigned int offset, gnttab_grant_foreign_access_ref(ref, queue->info->xbdev->otherend_id, gfn, GNTMAP_readonly); - queue->tx_skbs[id].skb = skb; + queue->tx_skbs[id] = skb; queue->grant_tx_page[id] = page; queue->grant_tx_ref[id] = ref; - tx->id = id; - tx->gref = ref; - tx->offset = offset; - tx->size = len; - tx->flags = 0; + info->tx_local.id = id; + info->tx_local.gref = ref; + info->tx_local.offset = offset; + info->tx_local.size = len; + info->tx_local.flags = 0; + + *tx = info->tx_local; + + /* + * Put the request in the pending queue, it will be set to be pending + * when the producer index is about to be raised. + */ + add_id_to_list(&queue->tx_pend_queue, queue->tx_link, id); info->tx = tx; - info->size += tx->size; + info->size += info->tx_local.size; } static struct xen_netif_tx_request *xennet_make_first_txreq( - struct netfront_queue *queue, struct sk_buff *skb, - struct page *page, unsigned int offset, unsigned int len) + struct xennet_gnttab_make_txreq *info, + unsigned int offset, unsigned int len) { - struct xennet_gnttab_make_txreq info = { - .queue = queue, - .skb = skb, - .page = page, - .size = 0, - }; + info->size = 0; - gnttab_for_one_grant(page, offset, len, xennet_tx_setup_grant, &info); + gnttab_for_one_grant(info->page, offset, len, xennet_tx_setup_grant, info); - return info.tx; + return info->tx; } static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset, @@ -499,35 +520,27 @@ static void xennet_make_one_txreq(unsigned long gfn, unsigned int offset, xennet_tx_setup_grant(gfn, offset, len, data); } -static struct xen_netif_tx_request *xennet_make_txreqs( - struct netfront_queue *queue, struct xen_netif_tx_request *tx, - struct sk_buff *skb, struct page *page, +static void xennet_make_txreqs( + struct xennet_gnttab_make_txreq *info, + struct page *page, unsigned int offset, unsigned int len) { - struct xennet_gnttab_make_txreq info = { - .queue = queue, - .skb = skb, - .tx = tx, - }; - /* Skip unused frames from start of page */ page += offset >> PAGE_SHIFT; offset &= ~PAGE_MASK; while (len) { - info.page = page; - info.size = 0; + info->page = page; + info->size = 0; gnttab_foreach_grant_in_range(page, offset, len, xennet_make_one_txreq, - &info); + info); page++; offset = 0; - len -= info.size; + len -= info->size; } - - return info.tx; } /* @@ -574,19 +587,34 @@ static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb, return queue_idx; } +static void xennet_mark_tx_pending(struct netfront_queue *queue) +{ + unsigned int i; + + while ((i = get_id_from_list(&queue->tx_pend_queue, queue->tx_link)) != + TX_LINK_NONE) + queue->tx_link[i] = TX_PENDING; +} + static int xennet_xdp_xmit_one(struct net_device *dev, struct netfront_queue *queue, struct xdp_frame *xdpf) { struct netfront_info *np = netdev_priv(dev); struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats); + struct xennet_gnttab_make_txreq info = { + .queue = queue, + .skb = NULL, + .page = virt_to_page(xdpf->data), + }; int notify; - xennet_make_first_txreq(queue, NULL, - virt_to_page(xdpf->data), + xennet_make_first_txreq(&info, offset_in_page(xdpf->data), xdpf->len); + xennet_mark_tx_pending(queue); + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) notify_remote_via_irq(queue->tx_irq); @@ -611,6 +639,8 @@ static int xennet_xdp_xmit(struct net_device *dev, int n, int nxmit = 0; int i; + if (unlikely(np->broken)) + return -ENODEV; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; @@ -638,7 +668,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev { struct netfront_info *np = netdev_priv(dev); struct netfront_stats *tx_stats = this_cpu_ptr(np->tx_stats); - struct xen_netif_tx_request *tx, *first_tx; + struct xen_netif_tx_request *first_tx; unsigned int i; int notify; int slots; @@ -647,6 +677,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev unsigned int len; unsigned long flags; struct netfront_queue *queue = NULL; + struct xennet_gnttab_make_txreq info = { }; unsigned int num_queues = dev->real_num_tx_queues; u16 queue_index; struct sk_buff *nskb; @@ -654,6 +685,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev /* Drop the packet if no queues are set up */ if (num_queues < 1) goto drop; + if (unlikely(np->broken)) + goto drop; /* Determine which queue to transmit this SKB on */ queue_index = skb_get_queue_mapping(skb); queue = &np->queues[queue_index]; @@ -704,21 +737,24 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev } /* First request for the linear area. */ - first_tx = tx = xennet_make_first_txreq(queue, skb, - page, offset, len); - offset += tx->size; + info.queue = queue; + info.skb = skb; + info.page = page; + first_tx = xennet_make_first_txreq(&info, offset, len); + offset += info.tx_local.size; if (offset == PAGE_SIZE) { page++; offset = 0; } - len -= tx->size; + len -= info.tx_local.size; if (skb->ip_summed == CHECKSUM_PARTIAL) /* local packet? */ - tx->flags |= XEN_NETTXF_csum_blank | XEN_NETTXF_data_validated; + first_tx->flags |= XEN_NETTXF_csum_blank | + XEN_NETTXF_data_validated; else if (skb->ip_summed == CHECKSUM_UNNECESSARY) /* remote but checksummed. */ - tx->flags |= XEN_NETTXF_data_validated; + first_tx->flags |= XEN_NETTXF_data_validated; /* Optional extra info after the first request. */ if (skb_shinfo(skb)->gso_size) { @@ -727,7 +763,7 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev gso = (struct xen_netif_extra_info *) RING_GET_REQUEST(&queue->tx, queue->tx.req_prod_pvt++); - tx->flags |= XEN_NETTXF_extra_info; + first_tx->flags |= XEN_NETTXF_extra_info; gso->u.gso.size = skb_shinfo(skb)->gso_size; gso->u.gso.type = (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) ? @@ -741,12 +777,12 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev } /* Requests for the rest of the linear area. */ - tx = xennet_make_txreqs(queue, tx, skb, page, offset, len); + xennet_make_txreqs(&info, page, offset, len); /* Requests for all the frags. */ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - tx = xennet_make_txreqs(queue, tx, skb, skb_frag_page(frag), + xennet_make_txreqs(&info, skb_frag_page(frag), skb_frag_off(frag), skb_frag_size(frag)); } @@ -757,6 +793,8 @@ static netdev_tx_t xennet_start_xmit(struct sk_buff *skb, struct net_device *dev /* timestamp packet in software */ skb_tx_timestamp(skb); + xennet_mark_tx_pending(queue); + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&queue->tx, notify); if (notify) notify_remote_via_irq(queue->tx_irq); @@ -814,7 +852,7 @@ static int xennet_get_extras(struct netfront_queue *queue, RING_IDX rp) { - struct xen_netif_extra_info *extra; + struct xen_netif_extra_info extra; struct device *dev = &queue->info->netdev->dev; RING_IDX cons = queue->rx.rsp_cons; int err = 0; @@ -830,24 +868,22 @@ static int xennet_get_extras(struct netfront_queue *queue, break; } - extra = (struct xen_netif_extra_info *) - RING_GET_RESPONSE(&queue->rx, ++cons); + RING_COPY_RESPONSE(&queue->rx, ++cons, &extra); - if (unlikely(!extra->type || - extra->type >= XEN_NETIF_EXTRA_TYPE_MAX)) { + if (unlikely(!extra.type || + extra.type >= XEN_NETIF_EXTRA_TYPE_MAX)) { if (net_ratelimit()) dev_warn(dev, "Invalid extra type: %d\n", - extra->type); + extra.type); err = -EINVAL; } else { - memcpy(&extras[extra->type - 1], extra, - sizeof(*extra)); + extras[extra.type - 1] = extra; } skb = xennet_get_rx_skb(queue, cons); ref = xennet_get_rx_ref(queue, cons); xennet_move_rx_slot(queue, skb, ref); - } while (extra->flags & XEN_NETIF_EXTRA_FLAG_MORE); + } while (extra.flags & XEN_NETIF_EXTRA_FLAG_MORE); queue->rx.rsp_cons = cons; return err; @@ -905,7 +941,7 @@ static int xennet_get_responses(struct netfront_queue *queue, struct sk_buff_head *list, bool *need_xdp_flush) { - struct xen_netif_rx_response *rx = &rinfo->rx; + struct xen_netif_rx_response *rx = &rinfo->rx, rx_local; int max = XEN_NETIF_NR_SLOTS_MIN + (rx->status <= RX_COPY_THRESHOLD); RING_IDX cons = queue->rx.rsp_cons; struct sk_buff *skb = xennet_get_rx_skb(queue, cons); @@ -989,7 +1025,8 @@ next: break; } - rx = RING_GET_RESPONSE(&queue->rx, cons + slots); + RING_COPY_RESPONSE(&queue->rx, cons + slots, &rx_local); + rx = &rx_local; skb = xennet_get_rx_skb(queue, cons + slots); ref = xennet_get_rx_ref(queue, cons + slots); slots++; @@ -1044,10 +1081,11 @@ static int xennet_fill_frags(struct netfront_queue *queue, struct sk_buff *nskb; while ((nskb = __skb_dequeue(list))) { - struct xen_netif_rx_response *rx = - RING_GET_RESPONSE(&queue->rx, ++cons); + struct xen_netif_rx_response rx; skb_frag_t *nfrag = &skb_shinfo(nskb)->frags[0]; + RING_COPY_RESPONSE(&queue->rx, ++cons, &rx); + if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; @@ -1062,7 +1100,7 @@ static int xennet_fill_frags(struct netfront_queue *queue, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), - rx->offset, rx->status, PAGE_SIZE); + rx.offset, rx.status, PAGE_SIZE); skb_shinfo(nskb)->nr_frags = 0; kfree_skb(nskb); @@ -1156,12 +1194,19 @@ static int xennet_poll(struct napi_struct *napi, int budget) skb_queue_head_init(&tmpq); rp = queue->rx.sring->rsp_prod; + if (RING_RESPONSE_PROD_OVERFLOW(&queue->rx, rp)) { + dev_alert(&dev->dev, "Illegal number of responses %u\n", + rp - queue->rx.rsp_cons); + queue->info->broken = true; + spin_unlock(&queue->rx_lock); + return 0; + } rmb(); /* Ensure we see queued responses up to 'rp'. */ i = queue->rx.rsp_cons; work_done = 0; while ((i != rp) && (work_done < budget)) { - memcpy(rx, RING_GET_RESPONSE(&queue->rx, i), sizeof(*rx)); + RING_COPY_RESPONSE(&queue->rx, i, rx); memset(extras, 0, sizeof(rinfo.extras)); err = xennet_get_responses(queue, &rinfo, rp, &tmpq, @@ -1286,17 +1331,18 @@ static void xennet_release_tx_bufs(struct netfront_queue *queue) for (i = 0; i < NET_TX_RING_SIZE; i++) { /* Skip over entries which are actually freelist references */ - if (skb_entry_is_link(&queue->tx_skbs[i])) + if (!queue->tx_skbs[i]) continue; - skb = queue->tx_skbs[i].skb; + skb = queue->tx_skbs[i]; + queue->tx_skbs[i] = NULL; get_page(queue->grant_tx_page[i]); gnttab_end_foreign_access(queue->grant_tx_ref[i], GNTMAP_readonly, (unsigned long)page_address(queue->grant_tx_page[i])); queue->grant_tx_page[i] = NULL; queue->grant_tx_ref[i] = GRANT_INVALID_REF; - add_id_to_freelist(&queue->tx_skb_freelist, queue->tx_skbs, i); + add_id_to_list(&queue->tx_skb_freelist, queue->tx_link, i); dev_kfree_skb_irq(skb); } } @@ -1376,6 +1422,9 @@ static irqreturn_t xennet_tx_interrupt(int irq, void *dev_id) struct netfront_queue *queue = dev_id; unsigned long flags; + if (queue->info->broken) + return IRQ_HANDLED; + spin_lock_irqsave(&queue->tx_lock, flags); xennet_tx_buf_gc(queue); spin_unlock_irqrestore(&queue->tx_lock, flags); @@ -1388,6 +1437,9 @@ static irqreturn_t xennet_rx_interrupt(int irq, void *dev_id) struct netfront_queue *queue = dev_id; struct net_device *dev = queue->info->netdev; + if (queue->info->broken) + return IRQ_HANDLED; + if (likely(netif_carrier_ok(dev) && RING_HAS_UNCONSUMED_RESPONSES(&queue->rx))) napi_schedule(&queue->napi); @@ -1409,6 +1461,10 @@ static void xennet_poll_controller(struct net_device *dev) struct netfront_info *info = netdev_priv(dev); unsigned int num_queues = dev->real_num_tx_queues; unsigned int i; + + if (info->broken) + return; + for (i = 0; i < num_queues; ++i) xennet_interrupt(0, &info->queues[i]); } @@ -1480,6 +1536,11 @@ static int xennet_xdp_set(struct net_device *dev, struct bpf_prog *prog, static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp) { + struct netfront_info *np = netdev_priv(dev); + + if (np->broken) + return -ENODEV; + switch (xdp->command) { case XDP_SETUP_PROG: return xennet_xdp_set(dev, xdp->prog, xdp->extack); @@ -1853,13 +1914,15 @@ static int xennet_init_queue(struct netfront_queue *queue) snprintf(queue->name, sizeof(queue->name), "vif%s-q%u", devid, queue->id); - /* Initialise tx_skbs as a free chain containing every entry. */ + /* Initialise tx_skb_freelist as a free chain containing every entry. */ queue->tx_skb_freelist = 0; + queue->tx_pend_queue = TX_LINK_NONE; for (i = 0; i < NET_TX_RING_SIZE; i++) { - skb_entry_set_link(&queue->tx_skbs[i], i+1); + queue->tx_link[i] = i + 1; queue->grant_tx_ref[i] = GRANT_INVALID_REF; queue->grant_tx_page[i] = NULL; } + queue->tx_link[NET_TX_RING_SIZE - 1] = TX_LINK_NONE; /* Clear out rx_skbs */ for (i = 0; i < NET_RX_RING_SIZE; i++) { @@ -2128,6 +2191,9 @@ static int talk_to_netback(struct xenbus_device *dev, if (info->queues) xennet_destroy_queues(info); + /* For the case of a reconnect reset the "broken" indicator. */ + info->broken = false; + err = xennet_create_queues(info, &num_queues); if (err < 0) { xenbus_dev_fatal(dev, err, "creating queues"); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 93dcdd431072..2f52110cac97 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -597,11 +597,8 @@ static inline void pcie_ecrc_get_policy(char *str) { } #ifdef CONFIG_PCIE_PTM void pci_ptm_init(struct pci_dev *dev); -int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); #else static inline void pci_ptm_init(struct pci_dev *dev) { } -static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) -{ return -EINVAL; } #endif struct pci_dev_reset_methods { diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 95d4eef2c9e8..8a4ad974c5ac 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -204,3 +204,12 @@ int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) return 0; } EXPORT_SYMBOL(pci_enable_ptm); + +bool pcie_ptm_enabled(struct pci_dev *dev) +{ + if (!dev) + return false; + + return dev->ptm_enabled; +} +EXPORT_SYMBOL(pcie_ptm_enabled); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 6b0dc9ff92d1..171106202fe5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -16,6 +16,8 @@ #define ETH_P_SJA1105_META 0x0008 #define ETH_P_SJA1110 0xdadc +#define SJA1105_DEFAULT_VLAN (VLAN_N_VID - 1) + /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull #define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFF000000ull @@ -65,7 +67,6 @@ struct sja1105_port { struct sja1105_tagger_data *data; struct dsa_port *dp; bool hwts_tx_en; - u16 xmit_tpid; }; enum sja1110_meta_tstamp { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b88ad5aef7fe..6fd3a4d42668 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,6 +47,7 @@ #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> +#include <linux/rbtree.h> struct netpoll_info; struct device; @@ -208,6 +209,7 @@ struct sk_buff; struct netdev_hw_addr { struct list_head list; + struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 @@ -224,6 +226,9 @@ struct netdev_hw_addr { struct netdev_hw_addr_list { struct list_head list; int count; + + /* Auxiliary tree for faster lookup on addition and deletion */ + struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) diff --git a/include/linux/pci.h b/include/linux/pci.h index 540b377ca8f6..947430637cac 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1620,6 +1620,16 @@ static inline bool pci_aer_available(void) { return false; } bool pci_ats_disabled(void); +#ifdef CONFIG_PCIE_PTM +int pci_enable_ptm(struct pci_dev *dev, u8 *granularity); +bool pcie_ptm_enabled(struct pci_dev *dev); +#else +static inline int pci_enable_ptm(struct pci_dev *dev, u8 *granularity) +{ return -EINVAL; } +static inline bool pcie_ptm_enabled(struct pci_dev *dev) +{ return false; } +#endif + void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 8b5af683a818..6026bbefbffd 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -58,10 +58,6 @@ struct mptcp_addr_info { struct mptcp_out_options { #if IS_ENABLED(CONFIG_MPTCP) u16 suboptions; - u64 sndr_key; - u64 rcvr_key; - u64 ahmac; - struct mptcp_addr_info addr; struct mptcp_rm_list rm_list; u8 join_id; u8 backup; @@ -69,11 +65,26 @@ struct mptcp_out_options { reset_transient:1, csum_reqd:1, allow_join_id0:1; - u32 nonce; - u64 thmac; - u32 token; - u8 hmac[20]; - struct mptcp_ext ext_copy; + union { + struct { + u64 sndr_key; + u64 rcvr_key; + }; + struct { + struct mptcp_addr_info addr; + u64 ahmac; + }; + struct { + struct mptcp_ext ext_copy; + u64 fail_seq; + }; + struct { + u32 nonce; + u32 token; + u64 thmac; + u8 hmac[20]; + }; + }; #endif }; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 45ae6eeb2964..8c39283c26ae 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -16,10 +16,9 @@ * General list handling functions */ -static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, - const unsigned char *addr, int addr_len, - unsigned char addr_type, bool global, - bool sync) +static struct netdev_hw_addr* +__hw_addr_create(const unsigned char *addr, int addr_len, + unsigned char addr_type, bool global, bool sync) { struct netdev_hw_addr *ha; int alloc_size; @@ -29,32 +28,44 @@ static int __hw_addr_create_ex(struct netdev_hw_addr_list *list, alloc_size = L1_CACHE_BYTES; ha = kmalloc(alloc_size, GFP_ATOMIC); if (!ha) - return -ENOMEM; + return NULL; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; ha->global_use = global; ha->synced = sync ? 1 : 0; ha->sync_cnt = 0; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; + return ha; } static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync, - int sync_count) + int sync_count, bool exclusive) { + struct rb_node **ins_point = &list->tree.rb_node, *parent = NULL; struct netdev_hw_addr *ha; if (addr_len > MAX_ADDR_LEN) return -EINVAL; - list_for_each_entry(ha, &list->list, list) { - if (ha->type == addr_type && - !memcmp(ha->addr, addr, addr_len)) { + while (*ins_point) { + int diff; + + ha = rb_entry(*ins_point, struct netdev_hw_addr, node); + diff = memcmp(addr, ha->addr, addr_len); + if (diff == 0) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + parent = *ins_point; + if (diff < 0) { + ins_point = &parent->rb_left; + } else if (diff > 0) { + ins_point = &parent->rb_right; + } else { + if (exclusive) + return -EEXIST; if (global) { /* check if addr is already used as global */ if (ha->global_use) @@ -73,8 +84,25 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, } } - return __hw_addr_create_ex(list, addr, addr_len, addr_type, global, - sync); + ha = __hw_addr_create(addr, addr_len, addr_type, global, sync); + if (!ha) + return -ENOMEM; + + /* The first address in dev->dev_addrs is pointed to by dev->dev_addr + * and mutated freely by device drivers and netdev ops, so if we insert + * it into the tree we'll end up with an invalid rbtree. + */ + if (list->count > 0) { + rb_link_node(&ha->node, parent, ins_point); + rb_insert_color(&ha->node, &list->tree); + } else { + RB_CLEAR_NODE(&ha->node); + } + + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + + return 0; } static int __hw_addr_add(struct netdev_hw_addr_list *list, @@ -82,7 +110,7 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char addr_type) { return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false, - 0); + 0, false); } static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, @@ -103,24 +131,61 @@ static int __hw_addr_del_entry(struct netdev_hw_addr_list *list, if (--ha->refcount) return 0; + + if (!RB_EMPTY_NODE(&ha->node)) + rb_erase(&ha->node, &list->tree); + list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); list->count--; return 0; } +static struct netdev_hw_addr *__hw_addr_lookup(struct netdev_hw_addr_list *list, + const unsigned char *addr, int addr_len, + unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + struct rb_node *node; + + /* The first address isn't inserted into the tree because in the dev->dev_addrs + * list it's the address pointed to by dev->dev_addr which is freely mutated + * in place, so we need to check it separately. + */ + ha = list_first_entry(&list->list, struct netdev_hw_addr, list); + if (ha && !memcmp(addr, ha->addr, addr_len) && + (!addr_type || addr_type == ha->type)) + return ha; + + node = list->tree.rb_node; + + while (node) { + struct netdev_hw_addr *ha = rb_entry(node, struct netdev_hw_addr, node); + int diff = memcmp(addr, ha->addr, addr_len); + + if (diff == 0 && addr_type) + diff = memcmp(&addr_type, &ha->type, sizeof(addr_type)); + + if (diff < 0) + node = node->rb_left; + else if (diff > 0) + node = node->rb_right; + else + return ha; + } + + return NULL; +} + static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, const unsigned char *addr, int addr_len, unsigned char addr_type, bool global, bool sync) { - struct netdev_hw_addr *ha; + struct netdev_hw_addr *ha = __hw_addr_lookup(list, addr, addr_len, addr_type); - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) - return __hw_addr_del_entry(list, ha, global, sync); - } - return -ENOENT; + if (!ha) + return -ENOENT; + return __hw_addr_del_entry(list, ha, global, sync); } static int __hw_addr_del(struct netdev_hw_addr_list *list, @@ -137,7 +202,7 @@ static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list, int err; err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type, - false, true, ha->sync_cnt); + false, true, ha->sync_cnt, false); if (err && err != -EEXIST) return err; @@ -407,6 +472,7 @@ static void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; + list->tree = RB_ROOT; list_for_each_entry_safe(ha, tmp, &list->list, list) { list_del_rcu(&ha->list); kfree_rcu(ha, rcu_head); @@ -418,6 +484,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; + list->tree = RB_ROOT; } EXPORT_SYMBOL(__hw_addr_init); @@ -552,22 +619,14 @@ EXPORT_SYMBOL(dev_addr_del); */ int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->uc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_UNICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST, true, false); + err = __hw_addr_add_ex(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -745,22 +804,14 @@ EXPORT_SYMBOL(dev_uc_init); */ int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr) { - struct netdev_hw_addr *ha; int err; netif_addr_lock_bh(dev); - list_for_each_entry(ha, &dev->mc.list, list) { - if (!memcmp(ha->addr, addr, dev->addr_len) && - ha->type == NETDEV_HW_ADDR_T_MULTICAST) { - err = -EEXIST; - goto out; - } - } - err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, true, false); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, true, false, + 0, true); if (!err) __dev_set_rx_mode(dev); -out: netif_addr_unlock_bh(dev); return err; } @@ -773,7 +824,8 @@ static int __dev_mc_add(struct net_device *dev, const unsigned char *addr, netif_addr_lock_bh(dev); err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_MULTICAST, global, false, 0); + NETDEV_HW_ADDR_T_MULTICAST, global, false, + 0, false); if (!err) __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 5b80a9049e2c..c054f48541c8 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -133,14 +133,44 @@ static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, return NULL; } +/* Send VLAN tags with a TPID that blends in with whatever VLAN protocol a + * bridge spanning ports of this switch might have. + */ static u16 sja1105_xmit_tpid(struct dsa_port *dp) { - struct sja1105_port *sp = dp->priv; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + u16 proto; + + /* Since VLAN awareness is global, then if this port is VLAN-unaware, + * all ports are. Use the VLAN-unaware TPID used for tag_8021q. + */ + if (!dsa_port_is_vlan_filtering(dp)) + return ETH_P_SJA1105; + + /* Port is VLAN-aware, so there is a bridge somewhere (a single one, + * we're sure about that). It may not be on this port though, so we + * need to find it. + */ + list_for_each_entry(other_dp, &ds->dst->ports, list) { + if (other_dp->ds != ds) + continue; + + if (!other_dp->bridge_dev) + continue; + + /* Error is returned only if CONFIG_BRIDGE_VLAN_FILTERING, + * which seems pointless to handle, as our port cannot become + * VLAN-aware in that case. + */ + br_vlan_get_proto(other_dp->bridge_dev, &proto); + + return proto; + } - if (unlikely(!dsa_port_is_sja1105(dp))) - return ETH_P_8021Q; + WARN_ONCE(1, "Port is VLAN-aware but cannot find associated bridge!\n"); - return sp->xmit_tpid; + return ETH_P_SJA1105; } static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, @@ -168,6 +198,36 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } +/* Transform untagged control packets into pvid-tagged control packets so that + * all packets sent by this tagger are VLAN-tagged and we can configure the + * switch to drop untagged packets coming from the DSA master. + */ +static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, + struct sk_buff *skb, u8 pcp) +{ + __be16 xmit_tpid = htons(sja1105_xmit_tpid(dp)); + struct vlan_ethhdr *hdr; + + /* If VLAN tag is in hwaccel area, move it to the payload + * to deal with both cases uniformly and to ensure that + * the VLANs are added in the right order. + */ + if (unlikely(skb_vlan_tag_present(skb))) { + skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return NULL; + } + + hdr = (struct vlan_ethhdr *)skb_mac_header(skb); + + /* If skb is already VLAN-tagged, leave that VLAN ID in place */ + if (hdr->h_vlan_proto == xmit_tpid) + return skb; + + return vlan_insert_tag(skb, xmit_tpid, (pcp << VLAN_PRIO_SHIFT) | + SJA1105_DEFAULT_VLAN); +} + static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { @@ -183,8 +243,13 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, * but instead SPI-installed management routes. Part 2 of this * is the .port_deferred_xmit driver callback. */ - if (unlikely(sja1105_is_link_local(skb))) + if (unlikely(sja1105_is_link_local(skb))) { + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + return sja1105_defer_xmit(dp, skb); + } return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); @@ -213,6 +278,10 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + skb_push(skb, SJA1110_HEADER_LEN); dsa_alloc_etype_header(skb, SJA1110_HEADER_LEN); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 3a7c4e7b2d79..b21ff9be04c6 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -44,6 +44,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), + SNMP_MIB_ITEM("MPFailTx", MPTCP_MIB_MPFAILTX), + SNMP_MIB_ITEM("MPFailRx", MPTCP_MIB_MPFAILRX), SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED), SNMP_MIB_ITEM("SubflowStale", MPTCP_MIB_SUBFLOWSTALE), SNMP_MIB_ITEM("SubflowRecover", MPTCP_MIB_SUBFLOWRECOVER), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 8ec16c991aac..ecd3d8b117e0 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -37,6 +37,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ + MPTCP_MIB_MPFAILTX, /* Transmit a MP_FAIL */ + MPTCP_MIB_MPFAILRX, /* Received a MP_FAIL */ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */ MPTCP_MIB_SUBFLOWSTALE, /* Subflows entered 'stale' status */ MPTCP_MIB_SUBFLOWRECOVER, /* Subflows returned to active status after being stale */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4c37f4b215ee..bec3ed82e253 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -336,6 +336,16 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->reset_reason = *ptr; break; + case MPTCPOPT_MP_FAIL: + if (opsize != TCPOLEN_MPTCP_FAIL) + break; + + ptr += 2; + mp_opt->mp_fail = 1; + mp_opt->fail_seq = get_unaligned_be64(ptr); + pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq); + break; + default: break; } @@ -364,6 +374,7 @@ void mptcp_get_options(const struct sock *sk, mp_opt->reset = 0; mp_opt->csum_reqd = READ_ONCE(msk->csum_enabled); mp_opt->deny_join_id0 = 0; + mp_opt->mp_fail = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); @@ -592,6 +603,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, dss_size = map_size; if (skb && snd_data_fin_enable) mptcp_write_data_fin(subflow, skb, &opts->ext_copy); + opts->suboptions = OPTION_MPTCP_DSS; ret = true; } @@ -615,6 +627,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; + opts->suboptions = OPTION_MPTCP_DSS; WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ @@ -686,8 +699,13 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * if (drop_other_suboptions) { pr_debug("drop other suboptions"); opts->suboptions = 0; - opts->ext_copy.use_ack = 0; - opts->ext_copy.use_map = 0; + + /* note that e.g. DSS could have written into the memory + * aliased by ahmac, we must reset the field here + * to avoid appending the hmac even for ADD_ADDR echo + * options + */ + opts->ahmac = 0; *size -= opt_size; } opts->suboptions |= OPTION_MPTCP_ADD_ADDR; @@ -739,7 +757,12 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - if (!subflow->send_mp_prio) + /* can't send MP_PRIO with MPC, as they share the same option space: + * 'backup'. Also it makes no sense at all + */ + if (!subflow->send_mp_prio || + ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | + OPTION_MPTCP_MPC_ACK) & opts->suboptions)) return false; /* account for the trailing 'nop' option */ @@ -755,7 +778,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, return true; } -static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb, +static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb, unsigned int *size, unsigned int remaining, struct mptcp_out_options *opts) @@ -763,12 +786,36 @@ static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_bu const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); if (remaining < TCPOLEN_MPTCP_RST) - return; + return false; *size = TCPOLEN_MPTCP_RST; opts->suboptions |= OPTION_MPTCP_RST; opts->reset_transient = subflow->reset_transient; opts->reset_reason = subflow->reset_reason; + + return true; +} + +static bool mptcp_established_options_mp_fail(struct sock *sk, + unsigned int *size, + unsigned int remaining, + struct mptcp_out_options *opts) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + + if (likely(!subflow->send_mp_fail)) + return false; + + if (remaining < TCPOLEN_MPTCP_FAIL) + return false; + + *size = TCPOLEN_MPTCP_FAIL; + opts->suboptions |= OPTION_MPTCP_FAIL; + opts->fail_seq = subflow->map_seq; + + pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + + return true; } bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, @@ -787,15 +834,28 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, return false; if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) { - mptcp_established_options_rst(sk, skb, size, remaining, opts); + if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + } + if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + } return true; } snd_data_fin = mptcp_data_fin_enabled(msk); if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts)) ret = true; - else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) + else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts)) { ret = true; + if (mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { + *size += opt_size; + remaining -= opt_size; + return true; + } + } /* we reserved enough space for the above options, and exceeding the * TCP option space would be fatal @@ -1096,6 +1156,12 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mp_opt.mp_prio = 0; } + if (mp_opt.mp_fail) { + mptcp_pm_mp_fail_received(sk, mp_opt.fail_seq); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILRX); + mp_opt.mp_fail = 0; + } + if (mp_opt.reset) { subflow->reset_seen = 1; subflow->reset_reason = mp_opt.reset_reason; @@ -1198,8 +1264,88 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext) void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts) { - if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | - OPTION_MPTCP_MPC_ACK) & opts->suboptions) { + if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) { + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_fail = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_FAIL, + TCPOLEN_MPTCP_FAIL, + 0, 0); + put_unaligned_be64(opts->fail_seq, ptr); + ptr += 2; + } + + /* RST is mutually exclusive with everything else */ + if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) { + *ptr++ = mptcp_option(MPTCPOPT_RST, + TCPOLEN_MPTCP_RST, + opts->reset_transient, + opts->reset_reason); + return; + } + + /* DSS, MPC, MPJ and ADD_ADDR are mutually exclusive, see + * mptcp_established_options*() + */ + if (likely(OPTION_MPTCP_DSS & opts->suboptions)) { + struct mptcp_ext *mpext = &opts->ext_copy; + u8 len = TCPOLEN_MPTCP_DSS_BASE; + u8 flags = 0; + + if (mpext->use_ack) { + flags = MPTCP_DSS_HAS_ACK; + if (mpext->ack64) { + len += TCPOLEN_MPTCP_DSS_ACK64; + flags |= MPTCP_DSS_ACK64; + } else { + len += TCPOLEN_MPTCP_DSS_ACK32; + } + } + + if (mpext->use_map) { + len += TCPOLEN_MPTCP_DSS_MAP64; + + /* Use only 64-bit mapping flags for now, add + * support for optional 32-bit mappings later. + */ + flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; + if (mpext->data_fin) + flags |= MPTCP_DSS_DATA_FIN; + + if (opts->csum_reqd) + len += TCPOLEN_MPTCP_DSS_CHECKSUM; + } + + *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); + + if (mpext->use_ack) { + if (mpext->ack64) { + put_unaligned_be64(mpext->data_ack, ptr); + ptr += 2; + } else { + put_unaligned_be32(mpext->data_ack32, ptr); + ptr += 1; + } + } + + if (mpext->use_map) { + put_unaligned_be64(mpext->data_seq, ptr); + ptr += 2; + put_unaligned_be32(mpext->subflow_seq, ptr); + ptr += 1; + if (opts->csum_reqd) { + put_unaligned_be32(mpext->data_len << 16 | + mptcp_make_csum(mpext), ptr); + } else { + put_unaligned_be32(mpext->data_len << 16 | + TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); + } + } + } else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | + OPTION_MPTCP_MPC_ACK) & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { @@ -1246,10 +1392,31 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } ptr += 1; - } -mp_capable_done: - if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) { + /* MPC is additionally mutually exclusive with MP_PRIO */ + goto mp_capable_done; + } else if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_SYN, + opts->backup, opts->join_id); + put_unaligned_be32(opts->token, ptr); + ptr += 1; + put_unaligned_be32(opts->nonce, ptr); + ptr += 1; + } else if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_SYNACK, + opts->backup, opts->join_id); + put_unaligned_be64(opts->thmac, ptr); + ptr += 2; + put_unaligned_be32(opts->nonce, ptr); + ptr += 1; + } else if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) { + *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, + TCPOLEN_MPTCP_MPJ_ACK, 0, 0); + memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN); + ptr += 5; + } else if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) { u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE; u8 echo = MPTCP_ADDR_ECHO; @@ -1307,6 +1474,19 @@ mp_capable_done: } } + if (OPTION_MPTCP_PRIO & opts->suboptions) { + const struct sock *ssk = (const struct sock *)tp; + struct mptcp_subflow_context *subflow; + + subflow = mptcp_subflow_ctx(ssk); + subflow->send_mp_prio = 0; + + *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, + TCPOLEN_MPTCP_PRIO, + opts->backup, TCPOPT_NOP); + } + +mp_capable_done: if (OPTION_MPTCP_RM_ADDR & opts->suboptions) { u8 i = 1; @@ -1327,107 +1507,6 @@ mp_capable_done: } } - if (OPTION_MPTCP_PRIO & opts->suboptions) { - const struct sock *ssk = (const struct sock *)tp; - struct mptcp_subflow_context *subflow; - - subflow = mptcp_subflow_ctx(ssk); - subflow->send_mp_prio = 0; - - *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, - TCPOLEN_MPTCP_PRIO, - opts->backup, TCPOPT_NOP); - } - - if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_SYN, - opts->backup, opts->join_id); - put_unaligned_be32(opts->token, ptr); - ptr += 1; - put_unaligned_be32(opts->nonce, ptr); - ptr += 1; - } - - if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_SYNACK, - opts->backup, opts->join_id); - put_unaligned_be64(opts->thmac, ptr); - ptr += 2; - put_unaligned_be32(opts->nonce, ptr); - ptr += 1; - } - - if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) { - *ptr++ = mptcp_option(MPTCPOPT_MP_JOIN, - TCPOLEN_MPTCP_MPJ_ACK, 0, 0); - memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN); - ptr += 5; - } - - if (OPTION_MPTCP_RST & opts->suboptions) - *ptr++ = mptcp_option(MPTCPOPT_RST, - TCPOLEN_MPTCP_RST, - opts->reset_transient, - opts->reset_reason); - - if (opts->ext_copy.use_ack || opts->ext_copy.use_map) { - struct mptcp_ext *mpext = &opts->ext_copy; - u8 len = TCPOLEN_MPTCP_DSS_BASE; - u8 flags = 0; - - if (mpext->use_ack) { - flags = MPTCP_DSS_HAS_ACK; - if (mpext->ack64) { - len += TCPOLEN_MPTCP_DSS_ACK64; - flags |= MPTCP_DSS_ACK64; - } else { - len += TCPOLEN_MPTCP_DSS_ACK32; - } - } - - if (mpext->use_map) { - len += TCPOLEN_MPTCP_DSS_MAP64; - - /* Use only 64-bit mapping flags for now, add - * support for optional 32-bit mappings later. - */ - flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64; - if (mpext->data_fin) - flags |= MPTCP_DSS_DATA_FIN; - - if (opts->csum_reqd) - len += TCPOLEN_MPTCP_DSS_CHECKSUM; - } - - *ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags); - - if (mpext->use_ack) { - if (mpext->ack64) { - put_unaligned_be64(mpext->data_ack, ptr); - ptr += 2; - } else { - put_unaligned_be32(mpext->data_ack32, ptr); - ptr += 1; - } - } - - if (mpext->use_map) { - put_unaligned_be64(mpext->data_seq, ptr); - ptr += 2; - put_unaligned_be32(mpext->subflow_seq, ptr); - ptr += 1; - if (opts->csum_reqd) { - put_unaligned_be32(mpext->data_len << 16 | - mptcp_make_csum(mpext), ptr); - } else { - put_unaligned_be32(mpext->data_len << 16 | - TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); - } - } - } - if (tp) mptcp_set_rwin(tp); } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index da0c4c925350..6ab386ff3294 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -249,6 +249,11 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup) mptcp_event(MPTCP_EVENT_SUB_PRIORITY, mptcp_sk(subflow->conn), sk, GFP_ATOMIC); } +void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) +{ + pr_debug("fail_seq=%llu", fail_seq); +} + /* path manager helpers */ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, struct sk_buff *skb, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 7cd3d5979bcd..57a50b1194a9 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -26,6 +26,8 @@ #define OPTION_MPTCP_FASTCLOSE BIT(8) #define OPTION_MPTCP_PRIO BIT(9) #define OPTION_MPTCP_RST BIT(10) +#define OPTION_MPTCP_DSS BIT(11) +#define OPTION_MPTCP_FAIL BIT(12) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 @@ -67,6 +69,7 @@ #define TCPOLEN_MPTCP_PRIO_ALIGN 4 #define TCPOLEN_MPTCP_FASTCLOSE 12 #define TCPOLEN_MPTCP_RST 4 +#define TCPOLEN_MPTCP_FAIL 12 #define TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM (TCPOLEN_MPTCP_DSS_CHECKSUM + TCPOLEN_MPTCP_MPC_ACK_DATA) @@ -137,6 +140,7 @@ struct mptcp_options_received { add_addr : 1, rm_addr : 1, mp_prio : 1, + mp_fail : 1, echo : 1, csum_reqd : 1, backup : 1, @@ -158,6 +162,7 @@ struct mptcp_options_received { u64 ahmac; u8 reset_reason:4; u8 reset_transient:1; + u64 fail_seq; }; static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) @@ -428,6 +433,7 @@ struct mptcp_subflow_context { mpc_map : 1, backup : 1, send_mp_prio : 1, + send_mp_fail : 1, rx_eof : 1, can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ @@ -608,6 +614,19 @@ static inline void mptcp_subflow_tcp_fallback(struct sock *sk, inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops; } +static inline bool mptcp_has_another_subflow(struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk), *tmp; + struct mptcp_sock *msk = mptcp_sk(subflow->conn); + + mptcp_for_each_subflow(msk, tmp) { + if (tmp != subflow) + return true; + } + + return false; +} + void __init mptcp_proto_init(void); #if IS_ENABLED(CONFIG_MPTCP_IPV6) int __init mptcp_proto_v6_init(void); @@ -722,6 +741,7 @@ void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *addr, u8 bkup); +void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8c43aa14897a..54b7ffc21861 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -910,6 +910,8 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * csum = csum_partial(&header, sizeof(header), subflow->map_data_csum); if (unlikely(csum_fold(csum))) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); + subflow->send_mp_fail = 1; + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; } @@ -1157,6 +1159,20 @@ no_data: fallback: /* RFC 8684 section 3.7. */ + if (subflow->send_mp_fail) { + if (mptcp_has_another_subflow(ssk)) { + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + } + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; + tcp_send_active_reset(ssk, GFP_ATOMIC); + WRITE_ONCE(subflow->data_avail, 0); + return true; + } + if (subflow->mp_join || subflow->fully_established) { /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 7b3e6cc56935..255793c5ac4f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -578,6 +578,43 @@ chk_csum_nr() fi } +chk_fail_nr() +{ + local mp_fail_nr_tx=$1 + local mp_fail_nr_rx=$2 + local count + local dump_stats + + printf "%-39s %s" " " "ftx" + count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mp_fail_nr_tx" ]; then + echo "[fail] got $count MP_FAIL[s] TX expected $mp_fail_nr_tx" + ret=1 + dump_stats=1 + else + echo -n "[ ok ]" + fi + + echo -n " - frx " + count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}'` + [ -z "$count" ] && count=0 + if [ "$count" != "$mp_fail_nr_rx" ]; then + echo "[fail] got $count MP_FAIL[s] RX expected $mp_fail_nr_rx" + ret=1 + dump_stats=1 + else + echo "[ ok ]" + fi + + if [ "${dump_stats}" = 1 ]; then + echo Server ns stats + ip netns exec $ns1 nstat -as | grep MPTcp + echo Client ns stats + ip netns exec $ns2 nstat -as | grep MPTcp + fi +} + chk_join_nr() { local msg="$1" @@ -627,6 +664,7 @@ chk_join_nr() fi if [ $checksum -eq 1 ]; then chk_csum_nr + chk_fail_nr 0 0 fi } |