diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index 7c13b40915c0..ea7bac438cfd 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -63,6 +63,38 @@ If that changed setting can be transmitted to the switch through the dynamic reconfiguration interface, it is; otherwise the switch is reset and reprogrammed with the updated static configuration. +Traffic support +=============== + +The switches do not support switch tagging in hardware. But they do support +customizing the TPID by which VLAN traffic is identified as such. The switch +driver is leveraging ``CONFIG_NET_DSA_TAG_8021Q`` by requesting that special +VLANs (with a custom TPID of ``ETH_P_EDSA`` instead of ``ETH_P_8021Q``) are +installed on its ports when not in ``vlan_filtering`` mode. This does not +interfere with the reception and transmission of real 802.1Q-tagged traffic, +because the switch does no longer parse those packets as VLAN after the TPID +change. +The TPID is restored when ``vlan_filtering`` is requested by the user through +the bridge layer, and general IP termination becomes no longer possible through +the switch netdevices in this mode. + +The switches have two programmable filters for link-local destination MACs. +These are used to trap BPDUs and PTP traffic to the master netdevice, and are +further used to support STP and 1588 ordinary clock/boundary clock +functionality. + +The following traffic modes are supported over the switch netdevices: + ++--------------------+------------+------------------+------------------+ +| | Standalone | Bridged with | Bridged with | +| | ports | vlan_filtering 0 | vlan_filtering 1 | ++====================+============+==================+==================+ +| Regular traffic | Yes | Yes | No (use master) | ++--------------------+------------+------------------+------------------+ +| Management traffic | Yes | Yes | Yes | +| (BPDU, PTP) | | | | ++--------------------+------------+------------------+------------------+ + Switching features ================== @@ -92,6 +124,28 @@ that VLAN awareness is global at the switch level is that once a bridge with ``vlan_filtering`` enslaves at least one switch port, the other un-bridged ports are no longer available for standalone traffic termination. +Topology and loop detection through STP is supported. + +L2 FDB manipulation (add/delete/dump) is currently possible for the first +generation devices. Aging time of FDB entries, as well as enabling fully static +management (no address learning and no flooding of unknown traffic) is not yet +configurable in the driver. + +A special comment about bridging with other netdevices (illustrated with an +example): + +A board has eth0, eth1, swp0@eth1, swp1@eth1, swp2@eth1, swp3@eth1. +The switch ports (swp0-3) are under br0. +It is desired that eth0 is turned into another switched port that communicates +with swp0-3. + +If br0 has vlan_filtering 0, then eth0 can simply be added to br0 with the +intended results. +If br0 has vlan_filtering 1, then a new br1 interface needs to be created that +enslaves eth0 and eth1 (the DSA master of the switch ports). This is because in +this mode, the switch ports beneath br0 are not capable of regular traffic, and +are only used as a conduit for switchdev operations. + Device Tree bindings and board design ===================================== diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 038685bb9d57..757751a89819 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -1,6 +1,7 @@ config NET_DSA_SJA1105 tristate "NXP SJA1105 Ethernet switch family support" depends on NET_DSA && SPI + select NET_DSA_TAG_SJA1105 select PACKING select CRC32 help diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index b0a155b57e17..b043bfc408f2 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -7,6 +7,7 @@ #include #include +#include #include "sja1105_static_config.h" #define SJA1105_NUM_PORTS 5 @@ -65,6 +66,11 @@ struct sja1105_private { struct gpio_desc *reset_gpio; struct spi_device *spidev; struct dsa_switch *ds; + struct sja1105_port ports[SJA1105_NUM_PORTS]; + /* Serializes transmission of management frames so that + * the switch doesn't confuse them with one another. + */ + struct mutex mgmt_lock; }; #include "sja1105_dynamic_config.h" diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 74f8ff9e17e0..50ff625c85d6 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "sja1105.h" static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, @@ -91,8 +92,10 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) .drpuntag = false, /* Don't retag 802.1p (VID 0) traffic with the pvid */ .retag = false, - /* Enable learning and I/O on user ports by default. */ - .dyn_learn = true, + /* Disable learning and I/O on user ports by default - + * STP will enable it. + */ + .dyn_learn = false, .egress = false, .ingress = false, }; @@ -118,8 +121,17 @@ static int sja1105_init_mac_settings(struct sja1105_private *priv) mac = table->entries; - for (i = 0; i < SJA1105_NUM_PORTS; i++) + for (i = 0; i < SJA1105_NUM_PORTS; i++) { mac[i] = default_mac; + if (i == dsa_upstream_port(priv->ds, i)) { + /* STP doesn't get called for CPU port, so we need to + * set the I/O parameters statically. + */ + mac[i].dyn_learn = true; + mac[i].ingress = true; + mac[i].egress = true; + } + } return 0; } @@ -406,11 +418,14 @@ static int sja1105_init_general_params(struct sja1105_private *priv) .tpid2 = ETH_P_SJA1105, }; struct sja1105_table *table; - int i; + int i, k = 0; - for (i = 0; i < SJA1105_NUM_PORTS; i++) + for (i = 0; i < SJA1105_NUM_PORTS; i++) { if (dsa_is_dsa_port(priv->ds, i)) default_general_params.casc_port = i; + else if (dsa_is_user_port(priv->ds, i)) + priv->ports[i].mgmt_slot = k++; + } table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; @@ -651,12 +666,14 @@ static sja1105_speed_t sja1105_get_speed_cfg(unsigned int speed_mbps) * for a specific port. * * @speed_mbps: If 0, leave the speed unchanged, else adapt MAC to PHY speed. - * @enabled: Manage Rx and Tx settings for this port. Overrides the static - * configuration settings. + * @enabled: Manage Rx and Tx settings for this port. If false, overrides the + * settings from the STP state, but not persistently (does not + * overwrite the static MAC info for this port). */ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, int speed_mbps, bool enabled) { + struct sja1105_mac_config_entry dyn_mac; struct sja1105_xmii_params_entry *mii; struct sja1105_mac_config_entry *mac; struct device *dev = priv->ds->dev; @@ -689,12 +706,13 @@ static int sja1105_adjust_port_config(struct sja1105_private *priv, int port, * the code common, we'll use the static configuration tables as a * reasonable approximation for both E/T and P/Q/R/S. */ - mac[port].ingress = enabled; - mac[port].egress = enabled; + dyn_mac = mac[port]; + dyn_mac.ingress = enabled && mac[port].ingress; + dyn_mac.egress = enabled && mac[port].egress; /* Write to the dynamic reconfiguration tables */ rc = sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, - port, &mac[port], true); + port, &dyn_mac, true); if (rc < 0) { dev_err(dev, "Failed to write MAC config: %d\n", rc); return rc; @@ -982,6 +1000,50 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port, port, &l2_fwd[port], true); } +static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_mac_config_entry *mac; + + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + + switch (state) { + case BR_STATE_DISABLED: + case BR_STATE_BLOCKING: + /* From UM10944 description of DRPDTAG (why put this there?): + * "Management traffic flows to the port regardless of the state + * of the INGRESS flag". So BPDUs are still be allowed to pass. + * At the moment no difference between DISABLED and BLOCKING. + */ + mac[port].ingress = false; + mac[port].egress = false; + mac[port].dyn_learn = false; + break; + case BR_STATE_LISTENING: + mac[port].ingress = true; + mac[port].egress = false; + mac[port].dyn_learn = false; + break; + case BR_STATE_LEARNING: + mac[port].ingress = true; + mac[port].egress = false; + mac[port].dyn_learn = true; + break; + case BR_STATE_FORWARDING: + mac[port].ingress = true; + mac[port].egress = true; + mac[port].dyn_learn = true; + break; + default: + dev_err(ds->dev, "invalid STP state: %d\n", state); + return; + } + + sja1105_dynamic_config_write(priv, BLK_IDX_MAC_CONFIG, port, + &mac[port], true); +} + static int sja1105_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { @@ -994,6 +1056,23 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port, sja1105_bridge_member(ds, port, br, false); } +static u8 sja1105_stp_state_get(struct sja1105_private *priv, int port) +{ + struct sja1105_mac_config_entry *mac; + + mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; + + if (!mac[port].ingress && !mac[port].egress && !mac[port].dyn_learn) + return BR_STATE_BLOCKING; + if (mac[port].ingress && !mac[port].egress && !mac[port].dyn_learn) + return BR_STATE_LISTENING; + if (mac[port].ingress && !mac[port].egress && mac[port].dyn_learn) + return BR_STATE_LEARNING; + if (mac[port].ingress && mac[port].egress && mac[port].dyn_learn) + return BR_STATE_FORWARDING; + return -EINVAL; +} + /* For situations where we need to change a setting at runtime that is only * available through the static configuration, resetting the switch in order * to upload the new static config is unavoidable. Back up the settings we @@ -1004,16 +1083,27 @@ static int sja1105_static_config_reload(struct sja1105_private *priv) { struct sja1105_mac_config_entry *mac; int speed_mbps[SJA1105_NUM_PORTS]; + u8 stp_state[SJA1105_NUM_PORTS]; int rc, i; mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries; /* Back up settings changed by sja1105_adjust_port_config and - * and restore their defaults. + * sja1105_bridge_stp_state_set and restore their defaults. */ for (i = 0; i < SJA1105_NUM_PORTS; i++) { speed_mbps[i] = sja1105_speed[mac[i].speed]; mac[i].speed = SJA1105_SPEED_AUTO; + if (i == dsa_upstream_port(priv->ds, i)) { + mac[i].ingress = true; + mac[i].egress = true; + mac[i].dyn_learn = true; + } else { + stp_state[i] = sja1105_stp_state_get(priv, i); + mac[i].ingress = false; + mac[i].egress = false; + mac[i].dyn_learn = false; + } } /* Reset switch and send updated static configuration */ @@ -1032,6 +1122,9 @@ static int sja1105_static_config_reload(struct sja1105_private *priv) for (i = 0; i < SJA1105_NUM_PORTS; i++) { bool enabled = (speed_mbps[i] != 0); + if (i != dsa_upstream_port(priv->ds, i)) + sja1105_bridge_stp_state_set(priv->ds, i, stp_state[i]); + rc = sja1105_adjust_port_config(priv, i, speed_mbps[i], enabled); if (rc < 0) @@ -1146,10 +1239,27 @@ static int sja1105_vlan_apply(struct sja1105_private *priv, int port, u16 vid, return 0; } +static int sja1105_setup_8021q_tagging(struct dsa_switch *ds, bool enabled) +{ + int rc, i; + + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + rc = dsa_port_setup_8021q_tagging(ds, i, enabled); + if (rc < 0) { + dev_err(ds->dev, "Failed to setup VLAN tagging for port %d: %d\n", + i, rc); + return rc; + } + } + dev_info(ds->dev, "%s switch tagging\n", + enabled ? "Enabled" : "Disabled"); + return 0; +} + static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port) { - return DSA_TAG_PROTO_NONE; + return DSA_TAG_PROTO_SJA1105; } /* This callback needs to be present */ @@ -1173,7 +1283,11 @@ static int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled) if (rc) dev_err(ds->dev, "Failed to change VLAN Ethertype\n"); - return rc; + /* Switch port identification based on 802.1Q is only passable + * if we are not under a vlan_filtering bridge. So make sure + * the two configurations are mutually exclusive. + */ + return sja1105_setup_8021q_tagging(ds, !enabled); } static void sja1105_vlan_add(struct dsa_switch *ds, int port, @@ -1276,7 +1390,98 @@ static int sja1105_setup(struct dsa_switch *ds) */ ds->vlan_filtering_is_global = true; - return 0; + /* The DSA/switchdev model brings up switch ports in standalone mode by + * default, and that means vlan_filtering is 0 since they're not under + * a bridge, so it's safe to set up switch tagging at this time. + */ + return sja1105_setup_8021q_tagging(ds, true); +} + +static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, + struct sk_buff *skb) +{ + struct sja1105_mgmt_entry mgmt_route = {0}; + struct sja1105_private *priv = ds->priv; + struct ethhdr *hdr; + int timeout = 10; + int rc; + + hdr = eth_hdr(skb); + + mgmt_route.macaddr = ether_addr_to_u64(hdr->h_dest); + mgmt_route.destports = BIT(port); + mgmt_route.enfport = 1; + + rc = sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route, true); + if (rc < 0) { + kfree_skb(skb); + return rc; + } + + /* Transfer skb to the host port. */ + dsa_enqueue_skb(skb, ds->ports[port].slave); + + /* Wait until the switch has processed the frame */ + do { + rc = sja1105_dynamic_config_read(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route); + if (rc < 0) { + dev_err_ratelimited(priv->ds->dev, + "failed to poll for mgmt route\n"); + continue; + } + + /* UM10944: The ENFPORT flag of the respective entry is + * cleared when a match is found. The host can use this + * flag as an acknowledgment. + */ + cpu_relax(); + } while (mgmt_route.enfport && --timeout); + + if (!timeout) { + /* Clean up the management route so that a follow-up + * frame may not match on it by mistake. + */ + sja1105_dynamic_config_write(priv, BLK_IDX_MGMT_ROUTE, + slot, &mgmt_route, false); + dev_err_ratelimited(priv->ds->dev, "xmit timed out\n"); + } + + return NETDEV_TX_OK; +} + +/* Deferred work is unfortunately necessary because setting up the management + * route cannot be done from atomit context (SPI transfer takes a sleepable + * lock on the bus) + */ +static netdev_tx_t sja1105_port_deferred_xmit(struct dsa_switch *ds, int port, + struct sk_buff *skb) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_port *sp = &priv->ports[port]; + int slot = sp->mgmt_slot; + + /* The tragic fact about the switch having 4x2 slots for installing + * management routes is that all of them except one are actually + * useless. + * If 2 slots are simultaneously configured for two BPDUs sent to the + * same (multicast) DMAC but on different egress ports, the switch + * would confuse them and redirect first frame it receives on the CPU + * port towards the port configured on the numerically first slot + * (therefore wrong port), then second received frame on second slot + * (also wrong port). + * So for all practical purposes, there needs to be a lock that + * prevents that from happening. The slot used here is utterly useless + * (could have simply been 0 just as fine), but we are doing it + * nonetheless, in case a smarter idea ever comes up in the future. + */ + mutex_lock(&priv->mgmt_lock); + + sja1105_mgmt_xmit(ds, port, slot, skb); + + mutex_unlock(&priv->mgmt_lock); + return NETDEV_TX_OK; } /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, @@ -1317,6 +1522,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_fdb_del = sja1105_fdb_del, .port_bridge_join = sja1105_bridge_join, .port_bridge_leave = sja1105_bridge_leave, + .port_stp_state_set = sja1105_bridge_stp_state_set, .port_vlan_prepare = sja1105_vlan_prepare, .port_vlan_filtering = sja1105_vlan_filtering, .port_vlan_add = sja1105_vlan_add, @@ -1324,6 +1530,7 @@ static const struct dsa_switch_ops sja1105_switch_ops = { .port_mdb_prepare = sja1105_mdb_prepare, .port_mdb_add = sja1105_mdb_add, .port_mdb_del = sja1105_mdb_del, + .port_deferred_xmit = sja1105_port_deferred_xmit, }; static int sja1105_check_device_id(struct sja1105_private *priv) @@ -1367,7 +1574,7 @@ static int sja1105_probe(struct spi_device *spi) struct device *dev = &spi->dev; struct sja1105_private *priv; struct dsa_switch *ds; - int rc; + int rc, i; if (!dev->of_node) { dev_err(dev, "No DTS bindings for SJA1105 driver\n"); @@ -1418,6 +1625,15 @@ static int sja1105_probe(struct spi_device *spi) ds->priv = priv; priv->ds = ds; + /* Connections between dsa_port and sja1105_port */ + for (i = 0; i < SJA1105_NUM_PORTS; i++) { + struct sja1105_port *sp = &priv->ports[i]; + + ds->ports[i].priv = sp; + sp->dp = &ds->ports[i]; + } + mutex_init(&priv->mgmt_lock); + return dsa_register_switch(priv->ds); } diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h new file mode 100644 index 000000000000..3911e0586478 --- /dev/null +++ b/include/linux/dsa/8021q.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2019, Vladimir Oltean + */ + +#ifndef _NET_DSA_8021Q_H +#define _NET_DSA_8021Q_H + +#include + +struct dsa_switch; +struct sk_buff; +struct net_device; +struct packet_type; + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) + +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, + bool enabled); + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci); + +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); + +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); + +int dsa_8021q_rx_switch_id(u16 vid); + +int dsa_8021q_rx_source_port(u16 vid); + +#else + +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int index, + bool enabled) +{ + return 0; +} + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci) +{ + return NULL; +} + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci) +{ + return NULL; +} + +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +{ + return 0; +} + +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +{ + return 0; +} + +int dsa_8021q_rx_switch_id(u16 vid) +{ + return 0; +} + +int dsa_8021q_rx_source_port(u16 vid) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ + +#endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index abf3977e34fd..603a02e5a8cb 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -2,22 +2,39 @@ * Copyright (c) 2019, Vladimir Oltean */ -/* Included by drivers/net/dsa/sja1105/sja1105.h */ +/* Included by drivers/net/dsa/sja1105/sja1105.h and net/dsa/tag_sja1105.c */ #ifndef _NET_DSA_SJA1105_H #define _NET_DSA_SJA1105_H +#include #include +#include #define ETH_P_SJA1105 ETH_P_DSA_8021Q -/* The switch can only be convinced to stay in unmanaged mode and not trap any - * link-local traffic by actually telling it to filter frames sent at the - * 00:00:00:00:00:00 destination MAC. - */ -#define SJA1105_LINKLOCAL_FILTER_A 0x000000000000ull -#define SJA1105_LINKLOCAL_FILTER_A_MASK 0xFFFFFFFFFFFFull -#define SJA1105_LINKLOCAL_FILTER_B 0x000000000000ull -#define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFFFFFFFFull +/* 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 +/* IEEE 1588 Annex F: Transport of PTP over Ethernet (01:1B:19:xx:xx:xx) */ +#define SJA1105_LINKLOCAL_FILTER_B 0x011B19000000ull +#define SJA1105_LINKLOCAL_FILTER_B_MASK 0xFFFFFF000000ull + +enum sja1105_frame_type { + SJA1105_FRAME_TYPE_NORMAL = 0, + SJA1105_FRAME_TYPE_LINK_LOCAL, +}; + +struct sja1105_skb_cb { + enum sja1105_frame_type type; +}; + +#define SJA1105_SKB_CB(skb) \ + ((struct sja1105_skb_cb *)DSA_SKB_CB_PRIV(skb)) + +struct sja1105_port { + struct dsa_port *dp; + int mgmt_slot; +}; #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 18db7b8e7a8e..6aaaadd6a413 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -42,6 +42,8 @@ struct phylink_link_state; #define DSA_TAG_PROTO_MTK_VALUE 9 #define DSA_TAG_PROTO_QCA_VALUE 10 #define DSA_TAG_PROTO_TRAILER_VALUE 11 +#define DSA_TAG_PROTO_8021Q_VALUE 12 +#define DSA_TAG_PROTO_SJA1105_VALUE 13 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -56,6 +58,8 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_MTK = DSA_TAG_PROTO_MTK_VALUE, DSA_TAG_PROTO_QCA = DSA_TAG_PROTO_QCA_VALUE, DSA_TAG_PROTO_TRAILER = DSA_TAG_PROTO_TRAILER_VALUE, + DSA_TAG_PROTO_8021Q = DSA_TAG_PROTO_8021Q_VALUE, + DSA_TAG_PROTO_SJA1105 = DSA_TAG_PROTO_SJA1105_VALUE, }; struct packet_type; @@ -67,6 +71,11 @@ struct dsa_device_ops { struct packet_type *pt); int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + /* Used to determine which traffic should match the DSA filter in + * eth_type_trans, and which, if any, should bypass it and be processed + * as regular on the master net device. + */ + bool (*filter)(const struct sk_buff *skb, struct net_device *dev); unsigned int overhead; const char *name; enum dsa_tag_protocol proto; @@ -76,6 +85,38 @@ struct dsa_device_ops { #define MODULE_ALIAS_DSA_TAG_DRIVER(__proto) \ MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __stringify(__proto##_VALUE)) +struct dsa_skb_cb { + struct sk_buff *clone; + bool deferred_xmit; +}; + +struct __dsa_skb_cb { + struct dsa_skb_cb cb; + u8 priv[48 - sizeof(struct dsa_skb_cb)]; +}; + +#define __DSA_SKB_CB(skb) ((struct __dsa_skb_cb *)((skb)->cb)) + +#define DSA_SKB_CB(skb) ((struct dsa_skb_cb *)((skb)->cb)) + +#define DSA_SKB_CB_COPY(nskb, skb) \ + { *__DSA_SKB_CB(nskb) = *__DSA_SKB_CB(skb); } + +#define DSA_SKB_CB_ZERO(skb) \ + { *__DSA_SKB_CB(skb) = (struct __dsa_skb_cb) {0}; } + +#define DSA_SKB_CB_PRIV(skb) \ + ((void *)(skb)->cb + offsetof(struct __dsa_skb_cb, priv)) + +#define DSA_SKB_CB_CLONE(_clone, _skb) \ + { \ + struct sk_buff *clone = _clone; \ + struct sk_buff *skb = _skb; \ + \ + DSA_SKB_CB_COPY(clone, skb); \ + DSA_SKB_CB(skb)->clone = clone; \ + } + struct dsa_switch_tree { struct list_head list; @@ -146,6 +187,7 @@ struct dsa_port { struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); + bool (*filter)(const struct sk_buff *skb, struct net_device *dev); enum { DSA_PORT_TYPE_UNUSED = 0, @@ -166,6 +208,16 @@ struct dsa_port { struct net_device *bridge_dev; struct devlink_port devlink_port; struct phylink *pl; + + struct work_struct xmit_work; + struct sk_buff_head xmit_queue; + + /* + * Give the switch driver somewhere to hang its per-port private data + * structures (accessible from the tagger). + */ + void *priv; + /* * Original copy of the master netdev ethtool_ops */ @@ -500,6 +552,12 @@ struct dsa_switch_ops { struct sk_buff *clone, unsigned int type); bool (*port_rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type); + + /* + * Deferred frame Tx + */ + netdev_tx_t (*port_deferred_xmit)(struct dsa_switch *ds, int port, + struct sk_buff *skb); }; struct dsa_switch_driver { @@ -518,6 +576,15 @@ static inline bool netdev_uses_dsa(struct net_device *dev) return false; } +static inline bool dsa_can_decode(const struct sk_buff *skb, + struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_NET_DSA) + return !dev->dsa_ptr->filter || dev->dsa_ptr->filter(skb, dev); +#endif + return false; +} + struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); @@ -586,6 +653,7 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, #define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) +netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev); int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data); int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data); int dsa_port_get_phy_sset_count(struct dsa_port *dp); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index c0734028c7dc..cf855352a440 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -17,6 +17,17 @@ menuconfig NET_DSA if NET_DSA +# tagging formats +config NET_DSA_TAG_8021Q + tristate "Tag driver for switches using custom 802.1Q VLAN headers" + select VLAN_8021Q + help + Unlike the other tagging protocols, the 802.1Q config option simply + provides helpers for other tagging implementations that might rely on + VLAN in one way or another. It is not a complete solution. + + Drivers which use these helpers should select this as dependency. + config NET_DSA_TAG_BRCM_COMMON tristate default n @@ -91,6 +102,15 @@ config NET_DSA_TAG_LAN9303 Say Y or M if you want to enable support for tagging frames for the SMSC/Microchip LAN9303 family of switches. +config NET_DSA_TAG_SJA1105 + tristate "Tag driver for NXP SJA1105 switches" + select NET_DSA_TAG_8021Q + help + Say Y or M if you want to enable support for tagging frames with the + NXP SJA1105 switch family. Both the native tagging protocol (which + is only for link-local traffic) as well as non-native tagging (based + on a custom 802.1Q VLAN header) are available. + config NET_DSA_TAG_TRAILER tristate "Tag driver for switches using a trailer tag" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 8a737b6ee94c..c342f54715ba 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -4,6 +4,7 @@ obj-$(CONFIG_NET_DSA) += dsa_core.o dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o # tagging formats +obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o @@ -12,4 +13,5 @@ obj-$(CONFIG_NET_DSA_TAG_KSZ_COMMON) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o +obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index bbc9f56e89b9..3b5f434cad3f 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -371,14 +371,14 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) return err; - err = ds->ops->setup(ds); - if (err < 0) - return err; - err = dsa_switch_register_notifier(ds); if (err) return err; + err = ds->ops->setup(ds); + if (err < 0) + return err; + if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) @@ -586,6 +586,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) } dp->type = DSA_PORT_TYPE_CPU; + dp->filter = tag_ops->filter; dp->rcv = tag_ops->rcv; dp->tag_ops = tag_ops; dp->master = master; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index b434f5ff55ab..8f1222324646 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -174,6 +174,8 @@ int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev); + static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); diff --git a/net/dsa/port.c b/net/dsa/port.c index 1ed287b2badd..ed8ba9daa3ba 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -389,6 +389,7 @@ int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags) trans.ph_prepare = false; return dsa_port_vlan_add(dp, &vlan, &trans); } +EXPORT_SYMBOL(dsa_port_vid_add); int dsa_port_vid_del(struct dsa_port *dp, u16 vid) { @@ -400,6 +401,7 @@ int dsa_port_vid_del(struct dsa_port *dp, u16 vid) return dsa_port_vlan_del(dp, &vlan); } +EXPORT_SYMBOL(dsa_port_vid_del); static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 6ce2fdb64db0..316bce9e0fbf 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -120,6 +120,9 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + cancel_work_sync(&dp->xmit_work); + skb_queue_purge(&dp->xmit_queue); + phylink_stop(dp->pl); dsa_port_disable(dp); @@ -430,6 +433,24 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, kfree_skb(clone); } +netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) +{ + /* SKB for netpoll still need to be mangled with the protocol-specific + * tag to be successfully transmitted + */ + if (unlikely(netpoll_tx_running(dev))) + return dsa_slave_netpoll_send_skb(dev, skb); + + /* Queue the SKB for transmission on the parent interface, but + * do not modify its EtherType + */ + skb->dev = dsa_slave_to_master(dev); + dev_queue_xmit(skb); + + return NETDEV_TX_OK; +} +EXPORT_SYMBOL_GPL(dsa_enqueue_skb); + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -452,23 +473,37 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) */ nskb = p->xmit(skb, dev); if (!nskb) { - kfree_skb(skb); + if (!DSA_SKB_CB(skb)->deferred_xmit) + kfree_skb(skb); return NETDEV_TX_OK; } - /* SKB for netpoll still need to be mangled with the protocol-specific - * tag to be successfully transmitted - */ - if (unlikely(netpoll_tx_running(dev))) - return dsa_slave_netpoll_send_skb(dev, nskb); + return dsa_enqueue_skb(nskb, dev); +} - /* Queue the SKB for transmission on the parent interface, but - * do not modify its EtherType - */ - nskb->dev = dsa_slave_to_master(dev); - dev_queue_xmit(nskb); +void *dsa_defer_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); - return NETDEV_TX_OK; + DSA_SKB_CB(skb)->deferred_xmit = true; + + skb_queue_tail(&dp->xmit_queue, skb); + schedule_work(&dp->xmit_work); + return NULL; +} +EXPORT_SYMBOL_GPL(dsa_defer_xmit); + +static void dsa_port_xmit_work(struct work_struct *work) +{ + struct dsa_port *dp = container_of(work, struct dsa_port, xmit_work); + struct dsa_switch *ds = dp->ds; + struct sk_buff *skb; + + if (unlikely(!ds->ops->port_deferred_xmit)) + return; + + while ((skb = skb_dequeue(&dp->xmit_queue)) != NULL) + ds->ops->port_deferred_xmit(ds, dp->index, skb); } /* ethtool operations *******************************************************/ @@ -1318,6 +1353,9 @@ int dsa_slave_suspend(struct net_device *slave_dev) if (!netif_running(slave_dev)) return 0; + cancel_work_sync(&dp->xmit_work); + skb_queue_purge(&dp->xmit_queue); + netif_device_detach(slave_dev); rtnl_lock(); @@ -1405,6 +1443,8 @@ int dsa_slave_create(struct dsa_port *port) } p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); + INIT_WORK(&port->xmit_work, dsa_port_xmit_work); + skb_queue_head_init(&port->xmit_queue); p->xmit = cpu_dp->tag_ops->xmit; port->slave = slave_dev; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c new file mode 100644 index 000000000000..8ae48c7e1e76 --- /dev/null +++ b/net/dsa/tag_8021q.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Vladimir Oltean + * + * This module is not a complete tagger implementation. It only provides + * primitives for taggers that rely on 802.1Q VLAN tags to use. The + * dsa_8021q_netdev_ops is registered for API compliance and not used + * directly by callers. + */ +#include +#include + +#include "dsa_priv.h" + +/* Allocating two VLAN tags per port - one for the RX VID and + * the other for the TX VID - see below + */ +#define DSA_8021Q_VID_RANGE (DSA_MAX_SWITCHES * DSA_MAX_PORTS) +#define DSA_8021Q_VID_BASE (VLAN_N_VID - 2 * DSA_8021Q_VID_RANGE - 1) +#define DSA_8021Q_RX_VID_BASE (DSA_8021Q_VID_BASE) +#define DSA_8021Q_TX_VID_BASE (DSA_8021Q_VID_BASE + DSA_8021Q_VID_RANGE) + +/* Returns the VID to be inserted into the frame from xmit for switch steering + * instructions on egress. Encodes switch ID and port ID. + */ +u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +{ + return DSA_8021Q_TX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port; +} +EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid); + +/* Returns the VID that will be installed as pvid for this switch port, sent as + * tagged egress towards the CPU port and decoded by the rcv function. + */ +u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +{ + return DSA_8021Q_RX_VID_BASE + (DSA_MAX_PORTS * ds->index) + port; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); + +/* Returns the decoded switch ID from the RX VID. */ +int dsa_8021q_rx_switch_id(u16 vid) +{ + return ((vid - DSA_8021Q_RX_VID_BASE) / DSA_MAX_PORTS); +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_switch_id); + +/* Returns the decoded port ID from the RX VID. */ +int dsa_8021q_rx_source_port(u16 vid) +{ + return ((vid - DSA_8021Q_RX_VID_BASE) % DSA_MAX_PORTS); +} +EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port); + +/* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single + * front-panel switch port (here swp0). + * + * Port identification through VLAN (802.1Q) tags has different requirements + * for it to work effectively: + * - On RX (ingress from network): each front-panel port must have a pvid + * that uniquely identifies it, and the egress of this pvid must be tagged + * towards the CPU port, so that software can recover the source port based + * on the VID in the frame. But this would only work for standalone ports; + * if bridged, this VLAN setup would break autonomous forwarding and would + * force all switched traffic to pass through the CPU. So we must also make + * the other front-panel ports members of this VID we're adding, albeit + * we're not making it their PVID (they'll still have their own). + * By the way - just because we're installing the same VID in multiple + * switch ports doesn't mean that they'll start to talk to one another, even + * while not bridged: the final forwarding decision is still an AND between + * the L2 forwarding information (which is limiting forwarding in this case) + * and the VLAN-based restrictions (of which there are none in this case, + * since all ports are members). + * - On TX (ingress from CPU and towards network) we are faced with a problem. + * If we were to tag traffic (from within DSA) with the port's pvid, all + * would be well, assuming the switch ports were standalone. Frames would + * have no choice but to be directed towards the correct front-panel port. + * But because we also want the RX VLAN to not break bridging, then + * inevitably that means that we have to give them a choice (of what + * front-panel port to go out on), and therefore we cannot steer traffic + * based on the RX VID. So what we do is simply install one more VID on the + * front-panel and CPU ports, and profit off of the fact that steering will + * work just by virtue of the fact that there is only one other port that's + * a member of the VID we're tagging the traffic with - the desired one. + * + * So at the end, each front-panel port will have one RX VID (also the PVID), + * the RX VID of all other front-panel ports, and one TX VID. Whereas the CPU + * port will have the RX and TX VIDs of all front-panel ports, and on top of + * that, is also tagged-input and tagged-output (VLAN trunk). + * + * CPU port CPU port + * +-------------+-----+-------------+ +-------------+-----+-------------+ + * | RX VID | | | | TX VID | | | + * | of swp0 | | | | of swp0 | | | + * | +-----+ | | +-----+ | + * | ^ T | | | Tagged | + * | | | | | ingress | + * | +-------+---+---+-------+ | | +-----------+ | + * | | | | | | | | Untagged | + * | | U v U v U v | | v egress | + * | +-----+ +-----+ +-----+ +-----+ | | +-----+ +-----+ +-----+ +-----+ | + * | | | | | | | | | | | | | | | | | | | | + * | |PVID | | | | | | | | | | | | | | | | | | + * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ + * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 + */ +int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) +{ + int upstream = dsa_upstream_port(ds, port); + struct dsa_port *dp = &ds->ports[port]; + struct dsa_port *upstream_dp = &ds->ports[upstream]; + u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ds, port); + int i, err; + + /* The CPU port is implicitly configured by + * configuring the front-panel ports + */ + if (!dsa_is_user_port(ds, port)) + return 0; + + /* Add this user port's RX VID to the membership list of all others + * (including itself). This is so that bridging will not be hindered. + * L2 forwarding rules still take precedence when there are no VLAN + * restrictions, so there are no concerns about leaking traffic. + */ + for (i = 0; i < ds->num_ports; i++) { + struct dsa_port *other_dp = &ds->ports[i]; + u16 flags; + + if (i == upstream) + /* CPU port needs to see this port's RX VID + * as tagged egress. + */ + flags = 0; + else if (i == port) + /* The RX VID is pvid on this port */ + flags = BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_PVID; + else + /* The RX VID is a regular VLAN on all others */ + flags = BRIDGE_VLAN_INFO_UNTAGGED; + + if (enabled) + err = dsa_port_vid_add(other_dp, rx_vid, flags); + else + err = dsa_port_vid_del(other_dp, rx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + rx_vid, port, err); + return err; + } + } + /* Finally apply the TX VID on this port and on the CPU port */ + if (enabled) + err = dsa_port_vid_add(dp, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED); + else + err = dsa_port_vid_del(dp, tx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + tx_vid, port, err); + return err; + } + if (enabled) + err = dsa_port_vid_add(upstream_dp, tx_vid, 0); + else + err = dsa_port_vid_del(upstream_dp, tx_vid); + if (err) { + dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + tx_vid, upstream, err); + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging); + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci) +{ + /* skb->data points at skb_mac_header, which + * is fine for vlan_insert_tag. + */ + return vlan_insert_tag(skb, htons(tpid), tci); +} +EXPORT_SYMBOL_GPL(dsa_8021q_xmit); + +struct sk_buff *dsa_8021q_rcv(struct sk_buff *skb, struct net_device *netdev, + struct packet_type *pt, u16 *tpid, u16 *tci) +{ + struct vlan_ethhdr *tag; + + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + return NULL; + + tag = vlan_eth_hdr(skb); + *tpid = ntohs(tag->h_vlan_proto); + *tci = ntohs(tag->h_vlan_TCI); + + /* skb->data points in the middle of the VLAN tag, + * after tpid and before tci. This is because so far, + * ETH_HLEN (DMAC, SMAC, EtherType) bytes were pulled. + * There are 2 bytes of VLAN tag left in skb->data, and upper + * layers expect the 'real' EtherType to be consumed as well. + * Coincidentally, a VLAN header is also of the same size as + * the number of bytes that need to be pulled. + */ + skb_pull_rcsum(skb, VLAN_HLEN); + + return skb; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + +static const struct dsa_device_ops dsa_8021q_netdev_ops = { + .name = "8021q", + .proto = DSA_TAG_PROTO_8021Q, + .overhead = VLAN_HLEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_8021Q); + +module_dsa_tag_driver(dsa_8021q_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c new file mode 100644 index 000000000000..969402c7dbf1 --- /dev/null +++ b/net/dsa/tag_sja1105.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Vladimir Oltean + */ +#include +#include +#include +#include +#include "dsa_priv.h" + +/* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ +static inline bool sja1105_is_link_local(const struct sk_buff *skb) +{ + const struct ethhdr *hdr = eth_hdr(skb); + u64 dmac = ether_addr_to_u64(hdr->h_dest); + + if ((dmac & SJA1105_LINKLOCAL_FILTER_A_MASK) == + SJA1105_LINKLOCAL_FILTER_A) + return true; + if ((dmac & SJA1105_LINKLOCAL_FILTER_B_MASK) == + SJA1105_LINKLOCAL_FILTER_B) + return true; + return false; +} + +/* This is the first time the tagger sees the frame on RX. + * Figure out if we can decode it, and if we can, annotate skb->cb with how we + * plan to do that, so we don't need to check again in the rcv function. + */ +static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev) +{ + if (sja1105_is_link_local(skb)) { + SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_LINK_LOCAL; + return true; + } + if (!dsa_port_is_vlan_filtering(dev->dsa_ptr)) { + SJA1105_SKB_CB(skb)->type = SJA1105_FRAME_TYPE_NORMAL; + return true; + } + return false; +} + +static struct sk_buff *sja1105_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_switch *ds = dp->ds; + u16 tx_vid = dsa_8021q_tx_vid(ds, dp->index); + u8 pcp = skb->priority; + + /* Transmitting management traffic does not rely upon switch tagging, + * but instead SPI-installed management routes. Part 2 of this + * is the .port_deferred_xmit driver callback. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_defer_xmit(skb, netdev); + + /* If we are under a vlan_filtering bridge, IP termination on + * switch ports based on 802.1Q tags is simply too brittle to + * be passable. So just defer to the dsa_slave_notag_xmit + * implementation. + */ + if (dsa_port_is_vlan_filtering(dp)) + return skb; + + return dsa_8021q_xmit(skb, netdev, ETH_P_SJA1105, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff *sja1105_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + struct ethhdr *hdr = eth_hdr(skb); + u64 source_port, switch_id; + struct sk_buff *nskb; + u16 tpid, vid, tci; + bool is_tagged; + + nskb = dsa_8021q_rcv(skb, netdev, pt, &tpid, &tci); + is_tagged = (nskb && tpid == ETH_P_SJA1105); + + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + vid = tci & VLAN_VID_MASK; + + skb->offload_fwd_mark = 1; + + if (SJA1105_SKB_CB(skb)->type == SJA1105_FRAME_TYPE_LINK_LOCAL) { + /* Management traffic path. Switch embeds the switch ID and + * port ID into bytes of the destination MAC, courtesy of + * the incl_srcpt options. + */ + source_port = hdr->h_dest[3]; + switch_id = hdr->h_dest[4]; + /* Clear the DMAC bytes that were mangled by the switch */ + hdr->h_dest[3] = 0; + hdr->h_dest[4] = 0; + } else { + /* Normal traffic path. */ + source_port = dsa_8021q_rx_source_port(vid); + switch_id = dsa_8021q_rx_switch_id(vid); + } + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, "Couldn't decode source port\n"); + return NULL; + } + + /* Delete/overwrite fake VLAN header, DSA expects to not find + * it there, see dsa_switch_rcv: skb_push(skb, ETH_HLEN). + */ + if (is_tagged) + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - VLAN_HLEN, + ETH_HLEN - VLAN_HLEN); + + return skb; +} + +static struct dsa_device_ops sja1105_netdev_ops = { + .name = "sja1105", + .proto = DSA_TAG_PROTO_SJA1105, + .xmit = sja1105_xmit, + .rcv = sja1105_rcv, + .filter = sja1105_filter, + .overhead = VLAN_HLEN, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); + +module_dsa_tag_driver(sja1105_netdev_ops); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 0f9863dc4d44..fddcee38c1da 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -185,8 +185,12 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) * at all, so we check here whether one of those tagging * variants has been configured on the receiving interface, * and if so, set skb->protocol without looking at the packet. + * The DSA tagging protocol may be able to decode some but not all + * traffic (for example only for management). In that case give it the + * option to filter the packets from which it can decode source port + * information. */ - if (unlikely(netdev_uses_dsa(dev))) + if (unlikely(netdev_uses_dsa(dev)) && dsa_can_decode(skb, dev)) return htons(ETH_P_XDSA); if (likely(eth_proto_is_802_3(eth->h_proto)))