diff options
Diffstat (limited to 'net/dsa')
| -rw-r--r-- | net/dsa/Kconfig | 38 | ||||
| -rw-r--r-- | net/dsa/Makefile | 6 | ||||
| -rw-r--r-- | net/dsa/dsa.c | 118 | ||||
| -rw-r--r-- | net/dsa/dsa2.c | 523 | ||||
| -rw-r--r-- | net/dsa/dsa_priv.h | 226 | ||||
| -rw-r--r-- | net/dsa/master.c | 76 | ||||
| -rw-r--r-- | net/dsa/port.c | 400 | ||||
| -rw-r--r-- | net/dsa/slave.c | 717 | ||||
| -rw-r--r-- | net/dsa/switch.c | 344 | ||||
| -rw-r--r-- | net/dsa/tag_8021q.c | 173 | ||||
| -rw-r--r-- | net/dsa/tag_ar9331.c | 3 | ||||
| -rw-r--r-- | net/dsa/tag_brcm.c | 39 | ||||
| -rw-r--r-- | net/dsa/tag_dsa.c | 352 | ||||
| -rw-r--r-- | net/dsa/tag_edsa.c | 215 | ||||
| -rw-r--r-- | net/dsa/tag_gswip.c | 5 | ||||
| -rw-r--r-- | net/dsa/tag_hellcreek.c | 64 | ||||
| -rw-r--r-- | net/dsa/tag_ksz.c | 76 | ||||
| -rw-r--r-- | net/dsa/tag_lan9303.c | 9 | ||||
| -rw-r--r-- | net/dsa/tag_mtk.c | 13 | ||||
| -rw-r--r-- | net/dsa/tag_ocelot.c | 287 | ||||
| -rw-r--r-- | net/dsa/tag_ocelot_8021q.c | 102 | ||||
| -rw-r--r-- | net/dsa/tag_qca.c | 13 | ||||
| -rw-r--r-- | net/dsa/tag_rtl4_a.c | 54 | ||||
| -rw-r--r-- | net/dsa/tag_sja1105.c | 33 | ||||
| -rw-r--r-- | net/dsa/tag_trailer.c | 32 | ||||
| -rw-r--r-- | net/dsa/tag_xrs700x.c | 66 |
26 files changed, 2723 insertions, 1261 deletions
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 1f9b9b11008c..a45572cfb71a 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -56,20 +56,31 @@ config NET_DSA_TAG_BRCM_PREPEND Broadcom switches which places the tag before the Ethernet header (prepended). +config NET_DSA_TAG_HELLCREEK + tristate "Tag driver for Hirschmann Hellcreek TSN switches" + help + Say Y or M if you want to enable support for tagging frames + for the Hirschmann Hellcreek TSN switches. + config NET_DSA_TAG_GSWIP tristate "Tag driver for Lantiq / Intel GSWIP switches" help Say Y or M if you want to enable support for tagging frames for the Lantiq / Intel GSWIP switches. +config NET_DSA_TAG_DSA_COMMON + tristate + config NET_DSA_TAG_DSA tristate "Tag driver for Marvell switches using DSA headers" + select NET_DSA_TAG_DSA_COMMON help Say Y or M if you want to enable support for tagging frames for the Marvell switches which use DSA headers. config NET_DSA_TAG_EDSA tristate "Tag driver for Marvell switches using EtherType DSA headers" + select NET_DSA_TAG_DSA_COMMON help Say Y or M if you want to enable support for tagging frames for the Marvell switches which use EtherType DSA headers. @@ -94,11 +105,26 @@ config NET_DSA_TAG_RTL4_A the Realtek RTL8366RB. config NET_DSA_TAG_OCELOT - tristate "Tag driver for Ocelot family of switches" + tristate "Tag driver for Ocelot family of switches, using NPI port" select PACKING help - Say Y or M if you want to enable support for tagging frames for the - Ocelot switches (VSC7511, VSC7512, VSC7513, VSC7514, VSC9959). + Say Y or M if you want to enable NPI tagging for the Ocelot switches + (VSC7511, VSC7512, VSC7513, VSC7514, VSC9953, VSC9959). In this mode, + the frames over the Ethernet CPU port are prepended with a + hardware-defined injection/extraction frame header. Flow control + (PAUSE frames) over the CPU port is not supported when operating in + this mode. + +config NET_DSA_TAG_OCELOT_8021Q + tristate "Tag driver for Ocelot family of switches, using VLAN" + select NET_DSA_TAG_8021Q + help + Say Y or M if you want to enable support for tagging frames with a + custom VLAN-based header. Frames that require timestamping, such as + PTP, are not delivered over Ethernet but over register-based MMIO. + Flow control over the CPU port is functional in this mode. When using + this mode, less TCAM resources (VCAP IS1, IS2, ES0) are available for + use with tc-flower. config NET_DSA_TAG_QCA tristate "Tag driver for Qualcomm Atheros QCA8K switches" @@ -128,4 +154,10 @@ config NET_DSA_TAG_TRAILER Say Y or M if you want to enable support for tagging frames at with a trailed. e.g. Marvell 88E6060. +config NET_DSA_TAG_XRS700X + tristate "Tag driver for XRS700x switches" + help + Say Y or M if you want to enable support for tagging frames for + Arrow SpeedChips XRS700x switches that use a single byte tag trailer. + endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 4f47b2025ff5..44bc79952b8b 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -7,14 +7,16 @@ dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o -obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o -obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o +obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o +obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o obj-$(CONFIG_NET_DSA_TAG_QCA) += tag_qca.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1ce9ba8cf545..84cad1be9ce4 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -84,6 +84,32 @@ const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) return ops->name; }; +/* Function takes a reference on the module owning the tagger, + * so dsa_tag_driver_put must be called afterwards. + */ +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf) +{ + const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); + struct dsa_tag_driver *dsa_tag_driver; + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + const struct dsa_device_ops *tmp = dsa_tag_driver->ops; + + if (!sysfs_streq(buf, tmp->name)) + continue; + + if (!try_module_get(dsa_tag_driver->owner)) + break; + + ops = tmp; + break; + } + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol) { struct dsa_tag_driver *dsa_tag_driver; @@ -201,7 +227,6 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, { struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; - struct pcpu_sw_netstats *s; struct dsa_slave_priv *p; if (unlikely(!cpu_dp)) { @@ -220,16 +245,31 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, } skb = nskb; - p = netdev_priv(skb->dev); skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); - s = this_cpu_ptr(p->stats64); - u64_stats_update_begin(&s->syncp); - s->rx_packets++; - s->rx_bytes += skb->len; - u64_stats_update_end(&s->syncp); + if (unlikely(!dsa_slave_dev_check(skb->dev))) { + /* Packet is to be injected directly on an upper + * device, e.g. a team/bond, so skip all DSA-port + * specific actions. + */ + netif_rx(skb); + return 0; + } + + p = netdev_priv(skb->dev); + + if (unlikely(cpu_dp->ds->untag_bridge_pvid)) { + nskb = dsa_untag_bridge_pvid(skb); + if (!nskb) { + kfree_skb(skb); + return 0; + } + skb = nskb; + } + + dev_sw_netstats_rx_add(skb->dev, skb->len); if (dsa_skb_defer_rx_timestamp(p, skb)) return 0; @@ -305,36 +345,10 @@ bool dsa_schedule_work(struct work_struct *work) return queue_work(dsa_owq, work); } -static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); - -int register_dsa_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&dsa_notif_chain, nb); -} -EXPORT_SYMBOL_GPL(register_dsa_notifier); - -int unregister_dsa_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); -} -EXPORT_SYMBOL_GPL(unregister_dsa_notifier); - -int call_dsa_notifiers(unsigned long val, struct net_device *dev, - struct dsa_notifier_info *info) -{ - info->dev = dev; - return atomic_notifier_call_chain(&dsa_notif_chain, val, info); -} -EXPORT_SYMBOL_GPL(call_dsa_notifiers); - int dsa_devlink_param_get(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; - - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + struct dsa_switch *ds = dsa_devlink_to_ds(dl); if (!ds->ops->devlink_param_get) return -EOPNOTSUPP; @@ -346,11 +360,7 @@ EXPORT_SYMBOL_GPL(dsa_devlink_param_get); int dsa_devlink_param_set(struct devlink *dl, u32 id, struct devlink_param_gset_ctx *ctx) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; - - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + struct dsa_switch *ds = dsa_devlink_to_ds(dl); if (!ds->ops->devlink_param_set) return -EOPNOTSUPP; @@ -412,6 +422,36 @@ void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, } EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister); +struct devlink_region * +dsa_devlink_region_create(struct dsa_switch *ds, + const struct devlink_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + return devlink_region_create(ds->devlink, ops, region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_create); + +struct devlink_region * +dsa_devlink_port_region_create(struct dsa_switch *ds, + int port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + + return devlink_port_region_create(&dp->devlink_port, ops, + region_max_snapshots, + region_size); +} +EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create); + +void dsa_devlink_region_destroy(struct devlink_region *region) +{ + devlink_region_destroy(region); +} +EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy); + struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { if (!netdev || !dsa_slave_dev_check(netdev)) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c0ffc7a2b65f..4d4956ed303b 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -21,8 +21,107 @@ static DEFINE_MUTEX(dsa2_mutex); LIST_HEAD(dsa_tree_list); -static const struct devlink_ops dsa_devlink_ops = { -}; +/** + * dsa_tree_notify - Execute code for all switches in a DSA switch tree. + * @dst: collection of struct dsa_switch devices to notify. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Given a struct dsa_switch_tree, this can be used to run a function once for + * each member DSA switch. The other alternative of traversing the tree is only + * through its ports list, which does not uniquely list the switches. + */ +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v) +{ + struct raw_notifier_head *nh = &dst->nh; + int err; + + err = raw_notifier_call_chain(nh, e, v); + + return notifier_to_errno(err); +} + +/** + * dsa_broadcast - Notify all DSA trees in the system. + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Can be used to notify the switching fabric of events such as cross-chip + * bridging between disjoint trees (such as islands of tagger-compatible + * switches bridged by an incompatible middle switch). + */ +int dsa_broadcast(unsigned long e, void *v) +{ + struct dsa_switch_tree *dst; + int err = 0; + + list_for_each_entry(dst, &dsa_tree_list, list) { + err = dsa_tree_notify(dst, e, v); + if (err) + break; + } + + return err; +} + +/** + * dsa_lag_map() - Map LAG netdev to a linear LAG ID + * @dst: Tree in which to record the mapping. + * @lag: Netdev that is to be mapped to an ID. + * + * dsa_lag_id/dsa_lag_dev can then be used to translate between the + * two spaces. The size of the mapping space is determined by the + * driver by setting ds->num_lag_ids. It is perfectly legal to leave + * it unset if it is not needed, in which case these functions become + * no-ops. + */ +void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag) +{ + unsigned int id; + + if (dsa_lag_id(dst, lag) >= 0) + /* Already mapped */ + return; + + for (id = 0; id < dst->lags_len; id++) { + if (!dsa_lag_dev(dst, id)) { + dst->lags[id] = lag; + return; + } + } + + /* No IDs left, which is OK. Some drivers do not need it. The + * ones that do, e.g. mv88e6xxx, will discover that dsa_lag_id + * returns an error for this device when joining the LAG. The + * driver can then return -EOPNOTSUPP back to DSA, which will + * fall back to a software LAG. + */ +} + +/** + * dsa_lag_unmap() - Remove a LAG ID mapping + * @dst: Tree in which the mapping is recorded. + * @lag: Netdev that was mapped. + * + * As there may be multiple users of the mapping, it is only removed + * if there are no other references to it. + */ +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) +{ + struct dsa_port *dp; + unsigned int id; + + dsa_lag_foreach_port(dp, dst, lag) + /* There are remaining users of this mapping */ + return; + + dsa_lags_foreach_id(id, dst) { + if (dsa_lag_dev(dst, id) == lag) { + dst->lags[id] = NULL; + break; + } + } +} struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) { @@ -80,6 +179,8 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) static void dsa_tree_free(struct dsa_switch_tree *dst) { + if (dst->tag_ops) + dsa_tag_driver_put(dst->tag_ops); list_del(&dst->list); kfree(dst); } @@ -254,22 +355,11 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) static int dsa_port_setup(struct dsa_port *dp) { - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - const unsigned char *id = (const unsigned char *)&dst->index; - const unsigned char len = sizeof(dst->index); struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; - bool devlink_port_registered = false; - struct devlink_port_attrs attrs = {}; - struct devlink *dl = ds->devlink; bool dsa_port_enabled = false; int err = 0; - attrs.phys.port_number = dp->index; - memcpy(attrs.switch_id.id, id, len); - attrs.switch_id.id_len = len; - if (dp->setup) return 0; @@ -278,14 +368,6 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); break; case DSA_PORT_TYPE_CPU: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - err = dsa_port_link_register_of(dp); if (err) break; @@ -298,14 +380,6 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_DSA: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - err = dsa_port_link_register_of(dp); if (err) break; @@ -318,14 +392,6 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_USER: - memset(dlp, 0, sizeof(*dlp)); - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - devlink_port_attrs_set(dlp, &attrs); - err = devlink_port_register(dl, dlp, dp->index); - if (err) - break; - devlink_port_registered = true; - dp->mac = of_get_mac_address(dp->dn); err = dsa_slave_create(dp); if (err) @@ -339,8 +405,6 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); if (err && dsa_port_link_registered) dsa_port_link_unregister_of(dp); - if (err && devlink_port_registered) - devlink_port_unregister(dlp); if (err) return err; @@ -349,6 +413,48 @@ static int dsa_port_setup(struct dsa_port *dp) return 0; } +static int dsa_port_devlink_setup(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch_tree *dst = dp->ds->dst; + struct devlink_port_attrs attrs = {}; + struct devlink *dl = dp->ds->devlink; + const unsigned char *id; + unsigned char len; + int err; + + id = (const unsigned char *)&dst->index; + len = sizeof(dst->index); + + attrs.phys.port_number = dp->index; + memcpy(attrs.switch_id.id, id, len); + attrs.switch_id.id_len = len; + memset(dlp, 0, sizeof(*dlp)); + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED; + break; + case DSA_PORT_TYPE_CPU: + attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU; + break; + case DSA_PORT_TYPE_DSA: + attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA; + break; + case DSA_PORT_TYPE_USER: + attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; + break; + } + + devlink_port_attrs_set(dlp, &attrs); + err = devlink_port_register(dl, dlp, dp->index); + + if (!err) + dp->devlink_port_setup = true; + + return err; +} + static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; @@ -356,22 +462,20 @@ static void dsa_port_teardown(struct dsa_port *dp) if (!dp->setup) return; + devlink_port_type_clear(dlp); + switch (dp->type) { case DSA_PORT_TYPE_UNUSED: break; case DSA_PORT_TYPE_CPU: dsa_port_disable(dp); - dsa_tag_driver_put(dp->tag_ops); - devlink_port_unregister(dlp); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_DSA: dsa_port_disable(dp); - devlink_port_unregister(dlp); dsa_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - devlink_port_unregister(dlp); if (dp->slave) { dsa_slave_destroy(dp->slave); dp->slave = NULL; @@ -382,9 +486,192 @@ static void dsa_port_teardown(struct dsa_port *dp) dp->setup = false; } +static void dsa_port_devlink_teardown(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + + if (dp->devlink_port_setup) + devlink_port_unregister(dlp); + dp->devlink_port_setup = false; +} + +static int dsa_devlink_info_get(struct devlink *dl, + struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (ds->ops->devlink_info_get) + return ds->ops->devlink_info_get(ds, req, extack); + + return -EOPNOTSUPP; +} + +static int dsa_devlink_sb_pool_get(struct devlink *dl, + unsigned int sb_index, u16 pool_index, + struct devlink_sb_pool_info *pool_info) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_get(ds, sb_index, pool_index, + pool_info); +} + +static int dsa_devlink_sb_pool_set(struct devlink *dl, unsigned int sb_index, + u16 pool_index, u32 size, + enum devlink_sb_threshold_type threshold_type, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_pool_set(ds, sb_index, pool_index, size, + threshold_type, extack); +} + +static int dsa_devlink_sb_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_get(ds, port, sb_index, + pool_index, p_threshold); +} + +static int dsa_devlink_sb_port_pool_set(struct devlink_port *dlp, + unsigned int sb_index, u16 pool_index, + u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_port_pool_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_port_pool_set(ds, port, sb_index, + pool_index, threshold, extack); +} + +static int +dsa_devlink_sb_tc_pool_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 *p_pool_index, u32 *p_threshold) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_get(ds, port, sb_index, + tc_index, pool_type, + p_pool_index, p_threshold); +} + +static int +dsa_devlink_sb_tc_pool_bind_set(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u16 pool_index, u32 threshold, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_tc_pool_bind_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_tc_pool_bind_set(ds, port, sb_index, + tc_index, pool_type, + pool_index, threshold, + extack); +} + +static int dsa_devlink_sb_occ_snapshot(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_snapshot) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_snapshot(ds, sb_index); +} + +static int dsa_devlink_sb_occ_max_clear(struct devlink *dl, + unsigned int sb_index) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_sb_occ_max_clear) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_max_clear(ds, sb_index); +} + +static int dsa_devlink_sb_occ_port_pool_get(struct devlink_port *dlp, + unsigned int sb_index, + u16 pool_index, u32 *p_cur, + u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_port_pool_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_port_pool_get(ds, port, sb_index, + pool_index, p_cur, p_max); +} + +static int +dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp, + unsigned int sb_index, u16 tc_index, + enum devlink_sb_pool_type pool_type, + u32 *p_cur, u32 *p_max) +{ + struct dsa_switch *ds = dsa_devlink_port_to_ds(dlp); + int port = dsa_devlink_port_to_port(dlp); + + if (!ds->ops->devlink_sb_occ_tc_port_bind_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_sb_occ_tc_port_bind_get(ds, port, + sb_index, tc_index, + pool_type, p_cur, + p_max); +} + +static const struct devlink_ops dsa_devlink_ops = { + .info_get = dsa_devlink_info_get, + .sb_pool_get = dsa_devlink_sb_pool_get, + .sb_pool_set = dsa_devlink_sb_pool_set, + .sb_port_pool_get = dsa_devlink_sb_port_pool_get, + .sb_port_pool_set = dsa_devlink_sb_port_pool_set, + .sb_tc_pool_bind_get = dsa_devlink_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = dsa_devlink_sb_tc_pool_bind_set, + .sb_occ_snapshot = dsa_devlink_sb_occ_snapshot, + .sb_occ_max_clear = dsa_devlink_sb_occ_max_clear, + .sb_occ_port_pool_get = dsa_devlink_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = dsa_devlink_sb_occ_tc_port_bind_get, +}; + static int dsa_switch_setup(struct dsa_switch *ds) { struct dsa_devlink_priv *dl_priv; + struct dsa_port *dp; int err; if (ds->setup) @@ -410,9 +697,22 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto free_devlink; + /* Setup devlink port instances now, so that the switch + * setup() can register regions etc, against the ports + */ + list_for_each_entry(dp, &ds->dst->ports, list) { + if (dp->ds == ds) { + err = dsa_port_devlink_setup(dp); + if (err) + goto unregister_devlink_ports; + } + } + err = dsa_switch_register_notifier(ds); if (err) - goto unregister_devlink; + goto unregister_devlink_ports; + + ds->configure_vlan_while_not_filtering = true; err = ds->ops->setup(ds); if (err < 0) @@ -424,23 +724,29 @@ static int dsa_switch_setup(struct dsa_switch *ds) ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); if (!ds->slave_mii_bus) { err = -ENOMEM; - goto unregister_notifier; + goto teardown; } dsa_slave_mii_bus_init(ds); err = mdiobus_register(ds->slave_mii_bus); if (err < 0) - goto unregister_notifier; + goto teardown; } ds->setup = true; return 0; +teardown: + if (ds->ops->teardown) + ds->ops->teardown(ds); unregister_notifier: dsa_switch_unregister_notifier(ds); -unregister_devlink: +unregister_devlink_ports: + list_for_each_entry(dp, &ds->dst->ports, list) + if (dp->ds == ds) + dsa_port_devlink_teardown(dp); devlink_unregister(ds->devlink); free_devlink: devlink_free(ds->devlink); @@ -451,6 +757,8 @@ free_devlink: static void dsa_switch_teardown(struct dsa_switch *ds) { + struct dsa_port *dp; + if (!ds->setup) return; @@ -463,6 +771,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds) ds->ops->teardown(ds); if (ds->devlink) { + list_for_each_entry(dp, &ds->dst->ports, list) + if (dp->ds == ds) + dsa_port_devlink_teardown(dp); devlink_unregister(ds->devlink); devlink_free(ds->devlink); ds->devlink = NULL; @@ -536,6 +847,32 @@ static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) dsa_master_teardown(dp->master); } +static int dsa_tree_setup_lags(struct dsa_switch_tree *dst) +{ + unsigned int len = 0; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->num_lag_ids > len) + len = dp->ds->num_lag_ids; + } + + if (!len) + return 0; + + dst->lags = kcalloc(len, sizeof(*dst->lags), GFP_KERNEL); + if (!dst->lags) + return -ENOMEM; + + dst->lags_len = len; + return 0; +} + +static void dsa_tree_teardown_lags(struct dsa_switch_tree *dst) +{ + kfree(dst->lags); +} + static int dsa_tree_setup(struct dsa_switch_tree *dst) { bool complete; @@ -563,12 +900,18 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_switches; + err = dsa_tree_setup_lags(dst); + if (err) + goto teardown_master; + dst->setup = true; pr_info("DSA: tree %d setup\n", dst->index); return 0; +teardown_master: + dsa_tree_teardown_master(dst); teardown_switches: dsa_tree_teardown_switches(dst); teardown_default_cpu: @@ -584,6 +927,8 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) if (!dst->setup) return; + dsa_tree_teardown_lags(dst); + dsa_tree_teardown_master(dst); dsa_tree_teardown_switches(dst); @@ -600,6 +945,57 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dst->setup = false; } +/* Since the dsa/tagging sysfs device attribute is per master, the assumption + * is that all DSA switches within a tree share the same tagger, otherwise + * they would have formed disjoint trees (different "dsa,member" values). + */ +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops) +{ + struct dsa_notifier_tag_proto_info info; + struct dsa_port *dp; + int err = -EBUSY; + + if (!rtnl_trylock()) + return restart_syscall(); + + /* At the moment we don't allow changing the tag protocol under + * traffic. The rtnl_mutex also happens to serialize concurrent + * attempts to change the tagging protocol. If we ever lift the IFF_UP + * restriction, there needs to be another mutex which serializes this. + */ + if (master->flags & IFF_UP) + goto out_unlock; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_is_user_port(dp->ds, dp->index)) + continue; + + if (dp->slave->flags & IFF_UP) + goto out_unlock; + } + + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); + if (err) + goto out_unwind_tagger; + + dst->tag_ops = tag_ops; + + rtnl_unlock(); + + return 0; + +out_unwind_tagger: + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); +out_unlock: + rtnl_unlock(); + return err; +} + static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) { struct dsa_switch_tree *dst = ds->dst; @@ -670,24 +1066,33 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; tag_protocol = dsa_get_tag_protocol(dp, master); - tag_ops = dsa_tag_driver_get(tag_protocol); - if (IS_ERR(tag_ops)) { - if (PTR_ERR(tag_ops) == -ENOPROTOOPT) - return -EPROBE_DEFER; - dev_warn(ds->dev, "No tagger for this switch\n"); - dp->master = NULL; - return PTR_ERR(tag_ops); + if (dst->tag_ops) { + if (dst->tag_ops->proto != tag_protocol) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + return -EINVAL; + } + /* In the case of multiple CPU ports per switch, the tagging + * protocol is still reference-counted only per switch tree, so + * nothing to do here. + */ + } else { + dst->tag_ops = dsa_tag_driver_get(tag_protocol); + if (IS_ERR(dst->tag_ops)) { + if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT) + return -EPROBE_DEFER; + dev_warn(ds->dev, "No tagger for this switch\n"); + dp->master = NULL; + return PTR_ERR(dst->tag_ops); + } } dp->master = master; dp->type = DSA_PORT_TYPE_CPU; - dp->filter = tag_ops->filter; - dp->rcv = tag_ops->rcv; - dp->tag_ops = tag_ops; + dsa_port_set_tag_protocol(dp, dst->tag_ops); dp->dst = dst; return 0; @@ -741,6 +1146,8 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, goto out_put_node; if (reg >= ds->num_ports) { + dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%zu)\n", + port, reg, ds->num_ports); err = -EINVAL; goto out_put_node; } diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 1653e3377cb3..2eeaa42f2e08 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -7,6 +7,7 @@ #ifndef __DSA_PRIV_H #define __DSA_PRIV_H +#include <linux/if_bridge.h> #include <linux/phy.h> #include <linux/netdevice.h> #include <linux/netpoll.h> @@ -19,16 +20,25 @@ enum { DSA_NOTIFIER_BRIDGE_LEAVE, DSA_NOTIFIER_FDB_ADD, DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HSR_JOIN, + DSA_NOTIFIER_HSR_LEAVE, + DSA_NOTIFIER_LAG_CHANGE, + DSA_NOTIFIER_LAG_JOIN, + DSA_NOTIFIER_LAG_LEAVE, DSA_NOTIFIER_MDB_ADD, DSA_NOTIFIER_MDB_DEL, DSA_NOTIFIER_VLAN_ADD, DSA_NOTIFIER_VLAN_DEL, DSA_NOTIFIER_MTU, + DSA_NOTIFIER_TAG_PROTO, + DSA_NOTIFIER_MRP_ADD, + DSA_NOTIFIER_MRP_DEL, + DSA_NOTIFIER_MRP_ADD_RING_ROLE, + DSA_NOTIFIER_MRP_DEL_RING_ROLE, }; /* DSA_NOTIFIER_AGEING_TIME */ struct dsa_notifier_ageing_time_info { - struct switchdev_trans *trans; unsigned int ageing_time; }; @@ -51,17 +61,25 @@ struct dsa_notifier_fdb_info { /* DSA_NOTIFIER_MDB_* */ struct dsa_notifier_mdb_info { const struct switchdev_obj_port_mdb *mdb; - struct switchdev_trans *trans; int sw_index; int port; }; +/* DSA_NOTIFIER_LAG_* */ +struct dsa_notifier_lag_info { + struct net_device *lag; + int sw_index; + int port; + + struct netdev_lag_upper_info *info; +}; + /* DSA_NOTIFIER_VLAN_* */ struct dsa_notifier_vlan_info { const struct switchdev_obj_port_vlan *vlan; - struct switchdev_trans *trans; int sw_index; int port; + struct netlink_ext_ack *extack; }; /* DSA_NOTIFIER_MTU */ @@ -72,13 +90,49 @@ struct dsa_notifier_mtu_info { int mtu; }; +/* DSA_NOTIFIER_TAG_PROTO_* */ +struct dsa_notifier_tag_proto_info { + const struct dsa_device_ops *tag_ops; +}; + +/* DSA_NOTIFIER_MRP_* */ +struct dsa_notifier_mrp_info { + const struct switchdev_obj_mrp *mrp; + int sw_index; + int port; +}; + +/* DSA_NOTIFIER_MRP_* */ +struct dsa_notifier_mrp_ring_role_info { + const struct switchdev_obj_ring_role_mrp *mrp; + int sw_index; + int port; +}; + +struct dsa_switchdev_event_work { + struct dsa_switch *ds; + int port; + struct work_struct work; + unsigned long event; + /* Specific for SWITCHDEV_FDB_ADD_TO_DEVICE and + * SWITCHDEV_FDB_DEL_TO_DEVICE + */ + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +/* DSA_NOTIFIER_HSR_* */ +struct dsa_notifier_hsr_info { + struct net_device *hsr; + int sw_index; + int port; +}; + struct dsa_slave_priv { /* Copy of CPU port xmit for faster access in slave transmit hot path */ struct sk_buff * (*xmit)(struct sk_buff *skb, struct net_device *dev); - struct pcpu_sw_netstats __percpu *stats64; - struct gro_cells gcells; /* DSA port data, such as switch, port index, etc. */ @@ -95,19 +149,11 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol); void dsa_tag_driver_put(const struct dsa_device_ops *ops); +const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); -int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack); -int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid); - /* master.c */ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); void dsa_master_teardown(struct net_device *dev); @@ -128,19 +174,24 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, } /* port.c */ -int dsa_port_set_state(struct dsa_port *dp, u8 state, - struct switchdev_trans *trans); +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops); +int dsa_port_set_state(struct dsa_port *dp, u8 state); int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy); int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy); void dsa_port_disable_rt(struct dsa_port *dp); void dsa_port_disable(struct dsa_port *dp); int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br); void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br); +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo); +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo); +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); bool dsa_port_skip_vlan_configuration(struct dsa_port *dp); -int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, - struct switchdev_trans *trans); +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock); int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, bool propagate_upstream); int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, @@ -149,37 +200,84 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); int dsa_port_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans); + const struct switchdev_obj_port_mdb *mdb); int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb); -int dsa_port_pre_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans); -int dsa_port_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans); +int dsa_port_pre_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans); + struct netlink_ext_ack *extack); int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan); -int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags); -int dsa_port_vid_del(struct dsa_port *dp, u16 vid); +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp); +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp); int dsa_port_link_register_of(struct dsa_port *dp); void dsa_port_link_unregister_of(struct dsa_port *dp); +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr); +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; +static inline bool dsa_port_offloads_netdev(struct dsa_port *dp, + struct net_device *dev) +{ + /* Switchdev offloading can be configured on: */ + + if (dev == dp->slave) + /* DSA ports directly connected to a bridge, and event + * was emitted for the ports themselves. + */ + return true; + + if (dp->bridge_dev == dev) + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return true; + + if (dp->lag_dev == dev) + /* DSA ports connected to a bridge via a LAG */ + return true; + + return false; +} + +/* Returns true if any port of this tree offloads the given net_device */ +static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst, + struct net_device *dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_netdev(dp, dev)) + return true; + + return false; +} + /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); -bool dsa_slave_dev_check(const struct net_device *dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); void dsa_slave_unregister_notifier(void); +void dsa_slave_setup_tagger(struct net_device *slave); +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) { @@ -196,11 +294,79 @@ dsa_slave_to_master(const struct net_device *dev) return dp->cpu_dp->master; } +/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged + * frames as untagged, since the bridge will not untag them. + */ +static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct net_device *br = dp->bridge_dev; + struct net_device *dev = skb->dev; + struct net_device *upper_dev; + u16 vid, pvid, proto; + int err; + + if (!br || br_vlan_enabled(br)) + return skb; + + err = br_vlan_get_proto(br, &proto); + if (err) + return skb; + + /* Move VLAN tag from data to hwaccel */ + if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) { + skb = skb_vlan_untag(skb); + if (!skb) + return NULL; + } + + if (!skb_vlan_tag_present(skb)) + return skb; + + vid = skb_vlan_tag_get_id(skb); + + /* We already run under an RCU read-side critical section since + * we are called from netif_receive_skb_list_internal(). + */ + err = br_vlan_get_pvid_rcu(dev, &pvid); + if (err) + return skb; + + if (vid != pvid) + return skb; + + /* The sad part about attempting to untag from DSA is that we + * don't know, unless we check, if the skb will end up in + * the bridge's data path - br_allowed_ingress() - or not. + * For example, there might be an 8021q upper for the + * default_pvid of the bridge, which will steal VLAN-tagged traffic + * from the bridge's data path. This is a configuration that DSA + * supports because vlan_filtering is 0. In that case, we should + * definitely keep the tag, to make sure it keeps working. + */ + upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid); + if (upper_dev) + return skb; + + __vlan_hwaccel_clear_tag(skb); + + return skb; +} + /* switch.c */ int dsa_switch_register_notifier(struct dsa_switch *ds); void dsa_switch_unregister_notifier(struct dsa_switch *ds); /* dsa2.c */ +void dsa_lag_map(struct dsa_switch_tree *dst, struct net_device *lag); +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag); +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); +int dsa_broadcast(unsigned long e, void *v); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + struct net_device *master, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); + extern struct list_head dsa_tree_list; #endif diff --git a/net/dsa/master.c b/net/dsa/master.c index 61615ebc70e9..052a977914a6 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -259,6 +259,18 @@ static void dsa_netdev_ops_set(struct net_device *dev, dev->dsa_ptr->netdev_ops = ops; } +static void dsa_master_set_promiscuity(struct net_device *dev, int inc) +{ + const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; + + if (!ops->promisc_on_master) + return; + + rtnl_lock(); + dev_set_promiscuity(dev, inc); + rtnl_unlock(); +} + static ssize_t tagging_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -268,7 +280,44 @@ static ssize_t tagging_show(struct device *d, struct device_attribute *attr, return sprintf(buf, "%s\n", dsa_tag_protocol_to_str(cpu_dp->tag_ops)); } -static DEVICE_ATTR_RO(tagging); + +static ssize_t tagging_store(struct device *d, struct device_attribute *attr, + const char *buf, size_t count) +{ + const struct dsa_device_ops *new_tag_ops, *old_tag_ops; + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + int err; + + old_tag_ops = cpu_dp->tag_ops; + new_tag_ops = dsa_find_tagger_by_name(buf); + /* Bad tagger name, or module is not loaded? */ + if (IS_ERR(new_tag_ops)) + return PTR_ERR(new_tag_ops); + + if (new_tag_ops == old_tag_ops) + /* Drop the temporarily held duplicate reference, since + * the DSA switch tree uses this tagger. + */ + goto out; + + err = dsa_tree_change_tag_proto(cpu_dp->ds->dst, dev, new_tag_ops, + old_tag_ops); + if (err) { + /* On failure the old tagger is restored, so we don't need the + * driver for the new one. + */ + dsa_tag_driver_put(new_tag_ops); + return err; + } + + /* On success we no longer need the module for the old tagging protocol + */ +out: + dsa_tag_driver_put(old_tag_ops); + return count; +} +static DEVICE_ATTR_RW(tagging); static struct attribute *dsa_slave_attrs[] = { &dev_attr_tagging.attr, @@ -296,14 +345,25 @@ static struct lock_class_key dsa_master_addr_list_lock_key; int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { + int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead; + struct dsa_switch *ds = cpu_dp->ds; + struct device_link *consumer_link; int ret; + /* The DSA master must use SET_NETDEV_DEV for this to work. */ + consumer_link = device_link_add(ds->dev, dev->dev.parent, + DL_FLAG_AUTOREMOVE_CONSUMER); + if (!consumer_link) + netdev_err(dev, + "Failed to create a device link to DSA switch %s\n", + dev_name(ds->dev)); + rtnl_lock(); - ret = dev_set_mtu(dev, ETH_DATA_LEN + cpu_dp->tag_ops->overhead); + ret = dev_set_mtu(dev, mtu); rtnl_unlock(); if (ret) - netdev_warn(dev, "error %d setting MTU to include DSA overhead\n", - ret); + netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n", + ret, mtu); /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get @@ -314,9 +374,12 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) dev->dsa_ptr = cpu_dp; lockdep_set_class(&dev->addr_list_lock, &dsa_master_addr_list_lock_key); + + dsa_master_set_promiscuity(dev, 1); + ret = dsa_master_ethtool_setup(dev); if (ret) - return ret; + goto out_err_reset_promisc; dsa_netdev_ops_set(dev, &dsa_netdev_ops); @@ -329,6 +392,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) out_err_ndo_teardown: dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); +out_err_reset_promisc: + dsa_master_set_promiscuity(dev, -1); return ret; } @@ -338,6 +403,7 @@ void dsa_master_teardown(struct net_device *dev) dsa_netdev_ops_set(dev, NULL); dsa_master_ethtool_teardown(dev); dsa_master_reset_mtu(dev); + dsa_master_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; diff --git a/net/dsa/port.c b/net/dsa/port.c index e23ece229c7e..c9c6d7ab3f47 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -13,44 +13,32 @@ #include "dsa_priv.h" -static int dsa_broadcast(unsigned long e, void *v) -{ - struct dsa_switch_tree *dst; - int err = 0; - - list_for_each_entry(dst, &dsa_tree_list, list) { - struct raw_notifier_head *nh = &dst->nh; - - err = raw_notifier_call_chain(nh, e, v); - err = notifier_to_errno(err); - if (err) - break; - } - - return err; -} - +/** + * dsa_port_notify - Notify the switching fabric of changes to a port + * @dp: port on which change occurred + * @e: event, must be of type DSA_NOTIFIER_* + * @v: event-specific value. + * + * Notify all switches in the DSA tree that this port's switch belongs to, + * including this switch itself, of an event. Allows the other switches to + * reconfigure themselves for cross-chip operations. Can also be used to + * reconfigure ports without net_devices (CPU ports, DSA links) whenever + * a user port's state changes. + */ static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) { - struct raw_notifier_head *nh = &dp->ds->dst->nh; - int err; - - err = raw_notifier_call_chain(nh, e, v); - - return notifier_to_errno(err); + return dsa_tree_notify(dp->ds->dst, e, v); } -int dsa_port_set_state(struct dsa_port *dp, u8 state, - struct switchdev_trans *trans) +int dsa_port_set_state(struct dsa_port *dp, u8 state) { struct dsa_switch *ds = dp->ds; int port = dp->index; - if (switchdev_trans_ph_prepare(trans)) - return ds->ops->port_stp_state_set ? 0 : -EOPNOTSUPP; + if (!ds->ops->port_stp_state_set) + return -EOPNOTSUPP; - if (ds->ops->port_stp_state_set) - ds->ops->port_stp_state_set(ds, port, state); + ds->ops->port_stp_state_set(ds, port, state); if (ds->ops->port_fast_age) { /* Fast age FDB entries or flush appropriate forwarding database @@ -75,7 +63,7 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) { int err; - err = dsa_port_set_state(dp, state, NULL); + err = dsa_port_set_state(dp, state); if (err) pr_err("DSA: failed to set STP state %u (%d)\n", state, err); } @@ -134,6 +122,28 @@ void dsa_port_disable(struct dsa_port *dp) rtnl_unlock(); } +static void dsa_port_change_brport_flags(struct dsa_port *dp, + bool bridge_offload) +{ + struct switchdev_brport_flags flags; + int flag; + + flags.mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; + if (bridge_offload) + flags.val = flags.mask; + else + flags.val = flags.mask & ~BR_LEARNING; + + for_each_set_bit(flag, &flags.mask, 32) { + struct switchdev_brport_flags tmp; + + tmp.val = flags.val & BIT(flag); + tmp.mask = BIT(flag); + + dsa_port_bridge_flags(dp, tmp, NULL); + } +} + int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { @@ -144,10 +154,10 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) }; int err; - /* Set the flooding mode before joining the port in the switch */ - err = dsa_port_bridge_flags(dp, BR_FLOOD | BR_MCAST_FLOOD, NULL); - if (err) - return err; + /* Notify the port driver to set its configurable flags in a way that + * matches the initial settings of a bridge port. + */ + dsa_port_change_brport_flags(dp, true); /* Here the interface is already bridged. Reflect the current * configuration so that drivers can program their chips accordingly. @@ -158,7 +168,7 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) /* The bridging is rolled back on error */ if (err) { - dsa_port_bridge_flags(dp, 0, NULL); + dsa_port_change_brport_flags(dp, false); dp->bridge_dev = NULL; } @@ -184,8 +194,18 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) if (err) pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); - /* Port is leaving the bridge, disable flooding */ - dsa_port_bridge_flags(dp, 0, NULL); + /* Configure the port for standalone mode (no address learning, + * flood everything). + * The bridge only emits SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS events + * when the user requests it through netlink or sysfs, but not + * automatically at port join or leave, so we need to handle resetting + * the brport flags ourselves. But we even prefer it that way, because + * otherwise, some setups might never get the notification they need, + * for example, when a port leaves a LAG that offloads the bridge, + * it becomes standalone, but as far as the bridge is concerned, no + * port ever left. + */ + dsa_port_change_brport_flags(dp, false); /* Port left the bridge, put in BR_STATE_DISABLED by the bridge layer, * so allow it to be in BR_STATE_FORWARDING to be kept functional @@ -193,11 +213,124 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) dsa_port_set_state_now(dp, BR_STATE_FORWARDING); } +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + }; + bool tx_enabled; + + if (!dp->lag_dev) + return 0; + + /* On statically configured aggregates (e.g. loadbalance + * without LACP) ports will always be tx_enabled, even if the + * link is down. Thus we require both link_up and tx_enabled + * in order to include it in the tx set. + */ + tx_enabled = linfo->link_up && linfo->tx_enabled; + + if (tx_enabled == dp->lag_tx_enabled) + return 0; + + dp->lag_tx_enabled = tx_enabled; + + return dsa_port_notify(dp, DSA_NOTIFIER_LAG_CHANGE, &info); +} + +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag, + struct netdev_lag_upper_info *uinfo) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .lag = lag, + .info = uinfo, + }; + int err; + + dsa_lag_map(dp->ds->dst, lag); + dp->lag_dev = lag; + + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_JOIN, &info); + if (err) { + dp->lag_dev = NULL; + dsa_lag_unmap(dp->ds->dst, lag); + } + + return err; +} + +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag) +{ + struct dsa_notifier_lag_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .lag = lag, + }; + int err; + + if (!dp->lag_dev) + return; + + /* Port might have been part of a LAG that in turn was + * attached to a bridge. + */ + if (dp->bridge_dev) + dsa_port_bridge_leave(dp, dp->bridge_dev); + + dp->lag_tx_enabled = false; + dp->lag_dev = NULL; + + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); + if (err) + pr_err("DSA: failed to notify DSA_NOTIFIER_LAG_LEAVE: %d\n", + err); + + dsa_lag_unmap(dp->ds->dst, lag); +} + +/* Must be called under rcu_read_lock() */ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, - bool vlan_filtering) + bool vlan_filtering, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int i; + int err, i; + + /* VLAN awareness was off, so the question is "can we turn it on". + * We may have had 8021q uppers, those need to go. Make sure we don't + * enter an inconsistent state: deny changing the VLAN awareness state + * as long as we have 8021q uppers. + */ + if (vlan_filtering && dsa_is_user_port(ds, dp->index)) { + struct net_device *upper_dev, *slave = dp->slave; + struct net_device *br = dp->bridge_dev; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + struct bridge_vlan_info br_info; + u16 vid; + + if (!is_vlan_dev(upper_dev)) + continue; + + vid = vlan_dev_vlan_id(upper_dev); + + /* br_vlan_get_info() returns -EINVAL or -ENOENT if the + * device, respectively the VID is not found, returning + * 0 means success, which is a failure for us here. + */ + err = br_vlan_get_info(br, vid, &br_info); + if (err == 0) { + NL_SET_ERR_MSG_MOD(extack, + "Must first remove VLAN uppers having VIDs also present in bridge"); + return false; + } + } + } if (!ds->vlan_filtering_is_global) return true; @@ -219,7 +352,8 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, if (other_bridge == dp->bridge_dev) continue; if (br_vlan_enabled(other_bridge) != vlan_filtering) { - dev_err(ds->dev, "VLAN filtering is a global setting\n"); + NL_SET_ERR_MSG_MOD(extack, + "VLAN filtering is a global setting"); return false; } } @@ -227,26 +361,30 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, } int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; + bool apply; int err; - /* bridge skips -EOPNOTSUPP, so skip the prepare phase */ - if (switchdev_trans_ph_prepare(trans)) - return 0; - if (!ds->ops->port_vlan_filtering) - return 0; + return -EOPNOTSUPP; - if (!dsa_port_can_apply_vlan_filtering(dp, vlan_filtering)) + /* We are called from dsa_slave_switchdev_blocking_event(), + * which is not under rcu_read_lock(), unlike + * dsa_slave_switchdev_event(). + */ + rcu_read_lock(); + apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering, extack); + rcu_read_unlock(); + if (!apply) return -EINVAL; if (dsa_port_is_vlan_filtering(dp) == vlan_filtering) return 0; - err = ds->ops->port_vlan_filtering(ds, dp->index, - vlan_filtering); + err = ds->ops->port_vlan_filtering(ds, dp->index, vlan_filtering, + extack); if (err) return err; @@ -254,6 +392,7 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, ds->vlan_filtering = vlan_filtering; else dp->vlan_filtering = vlan_filtering; + return 0; } @@ -271,63 +410,57 @@ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) !br_vlan_enabled(dp->bridge_dev)); } -int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock, - struct switchdev_trans *trans) +int dsa_port_ageing_time(struct dsa_port *dp, clock_t ageing_clock) { unsigned long ageing_jiffies = clock_t_to_jiffies(ageing_clock); unsigned int ageing_time = jiffies_to_msecs(ageing_jiffies); - struct dsa_notifier_ageing_time_info info = { - .ageing_time = ageing_time, - .trans = trans, - }; + struct dsa_notifier_ageing_time_info info; + int err; - if (switchdev_trans_ph_prepare(trans)) - return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + info.ageing_time = ageing_time; + + err = dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + if (err) + return err; dp->ageing_time = ageing_time; - return dsa_port_notify(dp, DSA_NOTIFIER_AGEING_TIME, &info); + return 0; } -int dsa_port_pre_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans) +int dsa_port_pre_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - if (!ds->ops->port_egress_floods || - (flags & ~(BR_FLOOD | BR_MCAST_FLOOD))) + if (!ds->ops->port_pre_bridge_flags) return -EINVAL; - return 0; + return ds->ops->port_pre_bridge_flags(ds, dp->index, flags, extack); } -int dsa_port_bridge_flags(const struct dsa_port *dp, unsigned long flags, - struct switchdev_trans *trans) +int dsa_port_bridge_flags(const struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int port = dp->index; - int err = 0; - - if (switchdev_trans_ph_prepare(trans)) - return 0; - if (ds->ops->port_egress_floods) - err = ds->ops->port_egress_floods(ds, port, flags & BR_FLOOD, - flags & BR_MCAST_FLOOD); + if (!ds->ops->port_bridge_flags) + return -EINVAL; - return err; + return ds->ops->port_bridge_flags(ds, dp->index, flags, extack); } int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - int port = dp->index; - if (switchdev_trans_ph_prepare(trans)) - return ds->ops->port_egress_floods ? 0 : -EOPNOTSUPP; + if (!ds->ops->port_set_mrouter) + return -EOPNOTSUPP; - return ds->ops->port_egress_floods(ds, port, true, mrouter); + return ds->ops->port_set_mrouter(ds, dp->index, mrouter, extack); } int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, @@ -382,13 +515,11 @@ int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) } int dsa_port_mdb_add(const struct dsa_port *dp, - const struct switchdev_obj_port_mdb *mdb, - struct switchdev_trans *trans) + const struct switchdev_obj_port_mdb *mdb) { struct dsa_notifier_mdb_info info = { .sw_index = dp->ds->index, .port = dp->index, - .trans = trans, .mdb = mdb, }; @@ -409,13 +540,13 @@ int dsa_port_mdb_del(const struct dsa_port *dp, int dsa_port_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_notifier_vlan_info info = { .sw_index = dp->ds->index, .port = dp->index, - .trans = trans, .vlan = vlan, + .extack = extack, }; return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); @@ -433,38 +564,61 @@ int dsa_port_vlan_del(struct dsa_port *dp, return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info); } -int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags) +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) { - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = flags, - .vid_begin = vid, - .vid_end = vid, + struct dsa_notifier_mrp_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, }; - struct switchdev_trans trans; - int err; - trans.ph_prepare = true; - err = dsa_port_vlan_add(dp, &vlan, &trans); - if (err) - return err; + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_ADD, &info); +} - trans.ph_prepare = false; - return dsa_port_vlan_add(dp, &vlan, &trans); +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) +{ + struct dsa_notifier_mrp_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_DEL, &info); } -EXPORT_SYMBOL(dsa_port_vid_add); -int dsa_port_vid_del(struct dsa_port *dp, u16 vid) +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) { - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, + struct dsa_notifier_mrp_ring_role_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_ADD_RING_ROLE, &info); +} + +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) +{ + struct dsa_notifier_mrp_ring_role_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .mrp = mrp, }; - return dsa_port_vlan_del(dp, &vlan); + return dsa_port_notify(dp, DSA_NOTIFIER_MRP_DEL_RING_ROLE, &info); +} + +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops) +{ + cpu_dp->filter = tag_ops->filter; + cpu_dp->rcv = tag_ops->rcv; + cpu_dp->tag_ops = tag_ops; } -EXPORT_SYMBOL(dsa_port_vid_del); static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { @@ -800,3 +954,37 @@ int dsa_port_get_phy_sset_count(struct dsa_port *dp) return ret; } EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count); + +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr) +{ + struct dsa_notifier_hsr_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .hsr = hsr, + }; + int err; + + dp->hsr_dev = hsr; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HSR_JOIN, &info); + if (err) + dp->hsr_dev = NULL; + + return err; +} + +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr) +{ + struct dsa_notifier_hsr_info info = { + .sw_index = dp->ds->index, + .port = dp->index, + .hsr = hsr, + }; + int err; + + dp->hsr_dev = NULL; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HSR_LEAVE, &info); + if (err) + pr_err("DSA: failed to notify DSA_NOTIFIER_HSR_LEAVE\n"); +} diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 16e5f98d4882..491e3761b5f4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -17,6 +17,7 @@ #include <net/pkt_cls.h> #include <net/tc_act/tc_mirred.h> #include <linux/if_bridge.h> +#include <linux/if_hsr.h> #include <linux/netpoll.h> #include <linux/ptp_classify.h> @@ -68,8 +69,11 @@ static int dsa_slave_open(struct net_device *dev) struct dsa_port *dp = dsa_slave_to_port(dev); int err; - if (!(master->flags & IFF_UP)) - return -ENETDOWN; + err = dev_open(master, NULL); + if (err < 0) { + netdev_err(dev, "failed to open master %s\n", master->name); + goto out; + } if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { err = dev_uc_add(master, dev->dev_addr); @@ -269,31 +273,34 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int dsa_slave_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int ret; + if (!dsa_port_offloads_netdev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + switch (attr->id) { case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - ret = dsa_port_set_state(dp, attr->u.stp_state, trans); + ret = dsa_port_set_state(dp, attr->u.stp_state); break; case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, - trans); + extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - ret = dsa_port_ageing_time(dp, attr->u.ageing_time, trans); + ret = dsa_port_ageing_time(dp, attr->u.ageing_time); break; case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, - trans); + extack); break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, trans); + ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); break; case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: - ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, trans); + ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack); break; default: ret = -EOPNOTSUPP; @@ -303,23 +310,62 @@ static int dsa_slave_port_attr_set(struct net_device *dev, return ret; } +/* Must be called under rcu_read_lock() */ +static int +dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, + const struct switchdev_obj_port_vlan *vlan) +{ + struct net_device *upper_dev; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + u16 vid; + + if (!is_vlan_dev(upper_dev)) + continue; + + vid = vlan_dev_vlan_id(upper_dev); + if (vid == vlan->vid) + return -EBUSY; + } + + return 0; +} + static int dsa_slave_vlan_add(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans) + struct netlink_ext_ack *extack) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); struct switchdev_obj_port_vlan vlan; int err; - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; - if (dsa_port_skip_vlan_configuration(dp)) + if (dsa_port_skip_vlan_configuration(dp)) { + NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN"); return 0; + } vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); - err = dsa_port_vlan_add(dp, &vlan, trans); + /* Deny adding a bridge VLAN when there is already an 802.1Q upper with + * the same VID. + */ + if (br_vlan_enabled(dp->bridge_dev)) { + rcu_read_lock(); + err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan); + rcu_read_unlock(); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Port already has a VLAN upper with this VID"); + return err; + } + } + + err = dsa_port_vlan_add(dp, &vlan, extack); if (err) return err; @@ -329,41 +375,45 @@ static int dsa_slave_vlan_add(struct net_device *dev, */ vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; - err = dsa_port_vlan_add(dp->cpu_dp, &vlan, trans); + err = dsa_port_vlan_add(dp->cpu_dp, &vlan, extack); if (err) return err; - return 0; + return vlan_vid_add(master, htons(ETH_P_8021Q), vlan.vid); } static int dsa_slave_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, - struct switchdev_trans *trans, struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); int err; - /* For the prepare phase, ensure the full set of changes is feasable in - * one go in order to signal a failure properly. If an operation is not - * supported, return -EOPNOTSUPP. - */ - switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; - err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_HOST_MDB: /* DSA can directly translate this to a normal MDB add, * but on the CPU port. */ - err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj), - trans); + err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_vlan_add(dev, obj, trans); + err = dsa_slave_vlan_add(dev, obj, extack); + break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj)); + break; + case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_add_ring_role(dp, + SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); break; default: err = -EOPNOTSUPP; @@ -376,18 +426,29 @@ static int dsa_slave_port_obj_add(struct net_device *dev, static int dsa_slave_vlan_del(struct net_device *dev, const struct switchdev_obj *obj) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); + struct switchdev_obj_port_vlan *vlan; + int err; - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; if (dsa_port_skip_vlan_configuration(dp)) return 0; + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + /* Do not deprogram the CPU port as it may be shared with other user * ports which can be members of this VLAN as well. */ - return dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj)); + err = dsa_port_vlan_del(dp, vlan); + if (err) + return err; + + vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid); + + return 0; } static int dsa_slave_port_obj_del(struct net_device *dev, @@ -398,7 +459,7 @@ static int dsa_slave_port_obj_del(struct net_device *dev, switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_MDB: - if (obj->orig_dev != dev) + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) return -EOPNOTSUPP; err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); break; @@ -411,6 +472,17 @@ static int dsa_slave_port_obj_del(struct net_device *dev, case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_vlan_del(dev, obj); break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj)); + break; + case SWITCHDEV_OBJ_ID_RING_ROLE_MRP: + if (!dsa_port_offloads_netdev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + err = dsa_port_mrp_del_ring_role(dp, + SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); + break; default: err = -EOPNOTSUPP; break; @@ -470,10 +542,10 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, if (!clone) return; - DSA_SKB_CB(skb)->clone = clone; - - if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) + if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) { + DSA_SKB_CB(skb)->clone = clone; return; + } kfree_skb(clone); } @@ -496,17 +568,36 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); +static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) +{ + int needed_headroom = dev->needed_headroom; + int needed_tailroom = dev->needed_tailroom; + + /* For tail taggers, we need to pad short frames ourselves, to ensure + * that the tail tag does not fail at its role of being at the end of + * the packet, once the master interface pads the frame. Account for + * that pad length here, and pad later. + */ + if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) + needed_tailroom += ETH_ZLEN - skb->len; + /* skb_headroom() returns unsigned int... */ + needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); + needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); + + if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) + /* No reallocation needed, yay! */ + return 0; + + return pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); +} + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); - struct pcpu_sw_netstats *s; struct sk_buff *nskb; - s = this_cpu_ptr(p->stats64); - u64_stats_update_begin(&s->syncp); - s->tx_packets++; - s->tx_bytes += skb->len; - u64_stats_update_end(&s->syncp); + dev_sw_netstats_tx_add(dev, 1, skb->len); DSA_SKB_CB(skb)->clone = NULL; @@ -515,6 +606,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) */ dsa_skb_tx_timestamp(p, skb); + if (dsa_realloc_skb(skb, dev)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* needed_tailroom should still be 'warm' in the cache line from + * dsa_realloc_skb(), which has also ensured that padding is safe. + */ + if (dev->needed_tailroom) + eth_skb_pad(skb); + /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ @@ -627,7 +729,6 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, uint64_t *data) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; @@ -636,7 +737,7 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, for_each_possible_cpu(i) { u64 tx_packets, tx_bytes, rx_packets, rx_bytes; - s = per_cpu_ptr(p->stats64, i); + s = per_cpu_ptr(dev->tstats, i); do { start = u64_stats_fetch_begin_irq(&s->syncp); tx_packets = s->tx_packets; @@ -1165,34 +1266,6 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } -static void dsa_slave_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct pcpu_sw_netstats *s; - unsigned int start; - int i; - - netdev_stats_to_stats64(stats, &dev->stats); - for_each_possible_cpu(i) { - u64 tx_packets, tx_bytes, rx_packets, rx_bytes; - - s = per_cpu_ptr(p->stats64, i); - do { - start = u64_stats_fetch_begin_irq(&s->syncp); - tx_packets = s->tx_packets; - tx_bytes = s->tx_bytes; - rx_packets = s->rx_packets; - rx_bytes = s->rx_bytes; - } while (u64_stats_fetch_retry_irq(&s->syncp, start)); - - stats->tx_packets += tx_packets; - stats->tx_bytes += tx_bytes; - stats->rx_packets += rx_packets; - stats->rx_bytes += rx_bytes; - } -} - static int dsa_slave_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { @@ -1232,64 +1305,59 @@ static int dsa_slave_get_ts_info(struct net_device *dev, static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - struct bridge_vlan_info info; + struct switchdev_obj_port_vlan vlan = { + .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, + .vid = vid, + /* This API only allows programming tagged, non-PVID VIDs */ + .flags = 0, + }; + struct netlink_ext_ack extack = {0}; int ret; - /* Check for a possible bridge VLAN entry now since there is no - * need to emulate the switchdev prepare + commit phase. - */ - if (dp->bridge_dev) { - if (dsa_port_skip_vlan_configuration(dp)) - return 0; - - /* br_vlan_get_info() returns -EINVAL or -ENOENT if the - * device, respectively the VID is not found, returning - * 0 means success, which is a failure for us here. - */ - ret = br_vlan_get_info(dp->bridge_dev, vid, &info); - if (ret == 0) - return -EBUSY; - } - - ret = dsa_port_vid_add(dp, vid, 0); - if (ret) + /* User port... */ + ret = dsa_port_vlan_add(dp, &vlan, &extack); + if (ret) { + if (extack._msg) + netdev_err(dev, "%s\n", extack._msg); return ret; + } - ret = dsa_port_vid_add(dp->cpu_dp, vid, 0); - if (ret) + /* And CPU port... */ + ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &extack); + if (ret) { + if (extack._msg) + netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, + extack._msg); return ret; + } - return 0; + return vlan_vid_add(master, proto, vid); } static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { + struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - struct bridge_vlan_info info; - int ret; - - /* Check for a possible bridge VLAN entry now since there is no - * need to emulate the switchdev prepare + commit phase. - */ - if (dp->bridge_dev) { - if (dsa_port_skip_vlan_configuration(dp)) - return 0; - - /* br_vlan_get_info() returns -EINVAL or -ENOENT if the - * device, respectively the VID is not found, returning - * 0 means success, which is a failure for us here. - */ - ret = br_vlan_get_info(dp->bridge_dev, vid, &info); - if (ret == 0) - return -EBUSY; - } + struct switchdev_obj_port_vlan vlan = { + .vid = vid, + /* This API only allows programming tagged, non-PVID VIDs */ + .flags = 0, + }; + int err; /* Do not deprogram the CPU port as it may be shared with other user * ports which can be members of this VLAN as well. */ - return dsa_port_vid_del(dp, vid); + err = dsa_port_vlan_del(dp, &vlan); + if (err) + return err; + + vlan_vid_del(master, proto, vid); + + return 0; } struct dsa_hw_port { @@ -1402,7 +1470,7 @@ out: dsa_hw_port_list_free(&hw_port_list); } -static int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) +int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) { struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1520,20 +1588,20 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { }; /* legacy way, bypassing the bridge *****************************************/ -int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid, - u16 flags, - struct netlink_ext_ack *extack) +static int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); return dsa_port_fdb_add(dp, addr, vid); } -int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], - struct net_device *dev, - const unsigned char *addr, u16 vid) +static int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1547,6 +1615,18 @@ static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) return dp->ds->devlink ? &dp->devlink_port : NULL; } +static void dsa_slave_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_stats64) + ds->ops->get_stats64(ds, dp->index, s); + else + dev_get_tstats64(dev, s); +} + static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_open = dsa_slave_open, .ndo_stop = dsa_slave_close, @@ -1668,6 +1748,27 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } +void dsa_slave_setup_tagger(struct net_device *slave) +{ + struct dsa_port *dp = dsa_slave_to_port(slave); + struct dsa_slave_priv *p = netdev_priv(slave); + const struct dsa_port *cpu_dp = dp->cpu_dp; + struct net_device *master = cpu_dp->master; + + if (cpu_dp->tag_ops->tail_tag) + slave->needed_tailroom = cpu_dp->tag_ops->overhead; + else + slave->needed_headroom = cpu_dp->tag_ops->overhead; + /* Try to save one extra realloc later in the TX path (in the master) + * by also inheriting the master's needed headroom and tailroom. + * The 8021q driver also does this. + */ + slave->needed_headroom += master->needed_headroom; + slave->needed_tailroom += master->needed_tailroom; + + p->xmit = cpu_dp->tag_ops->xmit; +} + static struct lock_class_key dsa_slave_netdev_xmit_lock_key; static void dsa_slave_set_lockdep_class_one(struct net_device *dev, struct netdev_queue *txq, @@ -1709,20 +1810,6 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -static void dsa_slave_notify(struct net_device *dev, unsigned long val) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_notifier_register_info rinfo = { - .switch_number = dp->ds->index, - .port_number = dp->index, - .master = master, - .info.dev = dev, - }; - - call_dsa_notifiers(val, dev, &rinfo.info); -} - int dsa_slave_create(struct dsa_port *port) { const struct dsa_port *cpu_dp = port->cpu_dp; @@ -1766,8 +1853,8 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->vlan_features = master->vlan_features; p = netdev_priv(slave_dev); - p->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!p->stats64) { + slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!slave_dev->tstats) { free_netdev(slave_dev); return -ENOMEM; } @@ -1778,27 +1865,26 @@ int dsa_slave_create(struct dsa_port *port) p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = cpu_dp->tag_ops->xmit; port->slave = slave_dev; + dsa_slave_setup_tagger(slave_dev); rtnl_lock(); ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); rtnl_unlock(); - if (ret) - dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n", - ret, port->index); + if (ret && ret != -EOPNOTSUPP) + dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", + ret, ETH_DATA_LEN, port->index); netif_carrier_off(slave_dev); ret = dsa_slave_phy_setup(slave_dev); if (ret) { - netdev_err(master, "error %d setting up slave PHY for %s\n", - ret, slave_dev->name); + netdev_err(slave_dev, + "error %d setting up PHY for tree %d, switch %d, port %d\n", + ret, ds->dst->index, ds->index, port->index); goto out_gcells; } - dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); - rtnl_lock(); ret = register_netdevice(slave_dev); @@ -1828,7 +1914,7 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(p->stats64); + free_percpu(slave_dev->tstats); free_netdev(slave_dev); port->slave = NULL; return ret; @@ -1847,10 +1933,9 @@ void dsa_slave_destroy(struct net_device *slave_dev) phylink_disconnect_phy(dp->pl); rtnl_unlock(); - dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); phylink_destroy(dp->pl); gro_cells_destroy(&p->gcells); - free_percpu(p->stats64); + free_percpu(slave_dev->tstats); free_netdev(slave_dev); } @@ -1858,6 +1943,7 @@ bool dsa_slave_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_slave_netdev_ops; } +EXPORT_SYMBOL_GPL(dsa_slave_dev_check); static int dsa_slave_changeupper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) @@ -1875,14 +1961,67 @@ static int dsa_slave_changeupper(struct net_device *dev, dsa_port_bridge_leave(dp, info->upper_dev); err = NOTIFY_OK; } + } else if (netif_is_lag_master(info->upper_dev)) { + if (info->linking) { + err = dsa_port_lag_join(dp, info->upper_dev, + info->upper_info); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(info->info.extack, + "Offloading not supported"); + err = 0; + } + err = notifier_from_errno(err); + } else { + dsa_port_lag_leave(dp, info->upper_dev); + err = NOTIFY_OK; + } + } else if (is_hsr_master(info->upper_dev)) { + if (info->linking) { + err = dsa_port_hsr_join(dp, info->upper_dev); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(info->info.extack, + "Offloading not supported"); + err = 0; + } + err = notifier_from_errno(err); + } else { + dsa_port_hsr_leave(dp, info->upper_dev); + err = NOTIFY_OK; + } + } + + return err; +} + +static int +dsa_slave_lag_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = NOTIFY_DONE; + struct dsa_port *dp; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_slave_dev_check(lower)) + continue; + + dp = dsa_slave_to_port(lower); + if (!dp->lag_dev) + /* Software LAG */ + continue; + + err = dsa_slave_changeupper(lower, info); + if (notifier_to_errno(err)) + break; } return err; } -static int dsa_slave_upper_vlan_check(struct net_device *dev, - struct netdev_notifier_changeupper_info * - info) +static int +dsa_prevent_bridging_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; struct net_device *slave; @@ -1912,134 +2051,284 @@ static int dsa_slave_upper_vlan_check(struct net_device *dev, return NOTIFY_DONE; } +static int +dsa_slave_check_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *br = dp->bridge_dev; + struct bridge_vlan_info br_info; + struct netlink_ext_ack *extack; + int err = NOTIFY_DONE; + u16 vid; + + if (!br || !br_vlan_enabled(br)) + return NOTIFY_DONE; + + extack = netdev_notifier_info_to_extack(&info->info); + vid = vlan_dev_vlan_id(info->upper_dev); + + /* br_vlan_get_info() returns -EINVAL or -ENOENT if the + * device, respectively the VID is not found, returning + * 0 means success, which is a failure for us here. + */ + err = br_vlan_get_info(br, vid, &br_info); + if (err == 0) { + NL_SET_ERR_MSG_MOD(extack, + "This VLAN is already configured by the bridge"); + return notifier_from_errno(-EBUSY); + } + + return NOTIFY_DONE; +} + static int dsa_slave_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (event == NETDEV_CHANGEUPPER) { + switch (event) { + case NETDEV_PRECHANGEUPPER: { + struct netdev_notifier_changeupper_info *info = ptr; + struct dsa_switch *ds; + struct dsa_port *dp; + int err; + + if (!dsa_slave_dev_check(dev)) + return dsa_prevent_bridging_8021q_upper(dev, ptr); + + dp = dsa_slave_to_port(dev); + ds = dp->ds; + + if (ds->ops->port_prechangeupper) { + err = ds->ops->port_prechangeupper(ds, dp->index, info); + if (err) + return notifier_from_errno(err); + } + + if (is_vlan_dev(info->upper_dev)) + return dsa_slave_check_8021q_upper(dev, ptr); + break; + } + case NETDEV_CHANGEUPPER: + if (dsa_slave_dev_check(dev)) + return dsa_slave_changeupper(dev, ptr); + + if (netif_is_lag_master(dev)) + return dsa_slave_lag_changeupper(dev, ptr); + + break; + case NETDEV_CHANGELOWERSTATE: { + struct netdev_notifier_changelowerstate_info *info = ptr; + struct dsa_port *dp; + int err; + if (!dsa_slave_dev_check(dev)) - return dsa_slave_upper_vlan_check(dev, ptr); + break; + + dp = dsa_slave_to_port(dev); + + err = dsa_port_lag_change(dp, info->lower_state_info); + return notifier_from_errno(err); + } + case NETDEV_GOING_DOWN: { + struct dsa_port *dp, *cpu_dp; + struct dsa_switch_tree *dst; + LIST_HEAD(close_list); + + if (!netdev_uses_dsa(dev)) + return NOTIFY_DONE; + + cpu_dp = dev->dsa_ptr; + dst = cpu_dp->ds->dst; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_is_user_port(dp->ds, dp->index)) + continue; + + list_add(&dp->slave->close_list, &close_list); + } + + dev_close_many(&close_list, true); - return dsa_slave_changeupper(dev, ptr); + return NOTIFY_OK; + } + default: + break; } return NOTIFY_DONE; } -struct dsa_switchdev_event_work { - struct work_struct work; - struct switchdev_notifier_fdb_info fdb_info; - struct net_device *dev; - unsigned long event; -}; +static void +dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) +{ + struct dsa_switch *ds = switchdev_work->ds; + struct switchdev_notifier_fdb_info info; + struct dsa_port *dp; + + if (!dsa_is_user_port(ds, switchdev_work->port)) + return; + + info.addr = switchdev_work->addr; + info.vid = switchdev_work->vid; + info.offloaded = true; + dp = dsa_to_port(ds, switchdev_work->port); + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, + dp->slave, &info.info, NULL); +} static void dsa_slave_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); - struct net_device *dev = switchdev_work->dev; - struct switchdev_notifier_fdb_info *fdb_info; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = switchdev_work->ds; + struct dsa_port *dp; int err; + dp = dsa_to_port(ds, switchdev_work->port); + rtnl_lock(); switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: - fdb_info = &switchdev_work->fdb_info; - if (!fdb_info->added_by_user) - break; - - err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_add(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { - netdev_dbg(dev, "fdb add failed err=%d\n", err); + dev_err(ds->dev, + "port %d failed to add %pM vid %d to fdb: %d\n", + dp->index, switchdev_work->addr, + switchdev_work->vid, err); break; } - fdb_info->offloaded = true; - call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, - &fdb_info->info, NULL); + dsa_fdb_offload_notify(switchdev_work); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: - fdb_info = &switchdev_work->fdb_info; - if (!fdb_info->added_by_user) - break; - - err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); + err = dsa_port_fdb_del(dp, switchdev_work->addr, + switchdev_work->vid); if (err) { - netdev_dbg(dev, "fdb del failed err=%d\n", err); - dev_close(dev); + dev_err(ds->dev, + "port %d failed to delete %pM vid %d from fdb: %d\n", + dp->index, switchdev_work->addr, + switchdev_work->vid, err); } + break; } rtnl_unlock(); - kfree(switchdev_work->fdb_info.addr); kfree(switchdev_work); - dev_put(dev); + if (dsa_is_user_port(ds, dp->index)) + dev_put(dp->slave); } -static int -dsa_slave_switchdev_fdb_work_init(struct dsa_switchdev_event_work * - switchdev_work, - const struct switchdev_notifier_fdb_info * - fdb_info) -{ - memcpy(&switchdev_work->fdb_info, fdb_info, - sizeof(switchdev_work->fdb_info)); - switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); - if (!switchdev_work->fdb_info.addr) - return -ENOMEM; - ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, - fdb_info->addr); +static int dsa_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + if (dsa_slave_dev_check(lower_dev)) { + priv->data = (void *)netdev_priv(lower_dev); + return 1; + } + return 0; } +static struct dsa_slave_priv *dsa_slave_dev_lower_find(struct net_device *dev) +{ + struct netdev_nested_priv priv = { + .data = NULL, + }; + + netdev_walk_all_lower_dev_rcu(dev, dsa_lower_dev_walk, &priv); + + return (struct dsa_slave_priv *)priv.data; +} + /* Called under rcu_read_lock() */ static int dsa_slave_switchdev_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + const struct switchdev_notifier_fdb_info *fdb_info; struct dsa_switchdev_event_work *switchdev_work; + struct dsa_port *dp; int err; - if (event == SWITCHDEV_PORT_ATTR_SET) { + switch (event) { + case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, dsa_slave_dev_check, dsa_slave_port_attr_set); return notifier_from_errno(err); - } + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb_info = ptr; - if (!dsa_slave_dev_check(dev)) - return NOTIFY_DONE; + if (dsa_slave_dev_check(dev)) { + if (!fdb_info->added_by_user) + return NOTIFY_OK; + + dp = dsa_slave_to_port(dev); + } else { + /* Snoop addresses learnt on foreign interfaces + * bridged with us, for switches that don't + * automatically learn SA from CPU-injected traffic + */ + struct net_device *br_dev; + struct dsa_slave_priv *p; + + br_dev = netdev_master_upper_dev_get_rcu(dev); + if (!br_dev) + return NOTIFY_DONE; + + if (!netif_is_bridge_master(br_dev)) + return NOTIFY_DONE; + + p = dsa_slave_dev_lower_find(br_dev); + if (!p) + return NOTIFY_DONE; + + dp = p->dp->cpu_dp; + + if (!dp->ds->assisted_learning_on_cpu_port) + return NOTIFY_DONE; + + /* When the bridge learns an address on an offloaded + * LAG we don't want to send traffic to the CPU, the + * other ports bridged with the LAG should be able to + * autonomously forward towards it. + */ + if (dsa_tree_offloads_netdev(dp->ds->dst, dev)) + return NOTIFY_DONE; + } - switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); - if (!switchdev_work) - return NOTIFY_BAD; + if (!dp->ds->ops->port_fdb_add || !dp->ds->ops->port_fdb_del) + return NOTIFY_DONE; - INIT_WORK(&switchdev_work->work, - dsa_slave_switchdev_event_work); - switchdev_work->dev = dev; - switchdev_work->event = event; + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return NOTIFY_BAD; - switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: - case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) - goto err_fdb_work_init; - dev_hold(dev); + INIT_WORK(&switchdev_work->work, + dsa_slave_switchdev_event_work); + switchdev_work->ds = dp->ds; + switchdev_work->port = dp->index; + switchdev_work->event = event; + + ether_addr_copy(switchdev_work->addr, + fdb_info->addr); + switchdev_work->vid = fdb_info->vid; + + /* Hold a reference on the slave for dsa_fdb_offload_notify */ + if (dsa_is_user_port(dp->ds, dp->index)) + dev_hold(dev); + dsa_schedule_work(&switchdev_work->work); break; default: - kfree(switchdev_work); return NOTIFY_DONE; } - dsa_schedule_work(&switchdev_work->work); return NOTIFY_OK; - -err_fdb_work_init: - kfree(switchdev_work); - return NOTIFY_BAD; } static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 86c8dc5c32a0..4b5da89dc27a 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -33,15 +33,12 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, struct dsa_notifier_ageing_time_info *info) { unsigned int ageing_time = info->ageing_time; - struct switchdev_trans *trans = info->trans; - - if (switchdev_trans_ph_prepare(trans)) { - if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) - return -ERANGE; - if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) - return -ERANGE; - return 0; - } + + if (ds->ageing_time_min && ageing_time < ds->ageing_time_min) + return -ERANGE; + + if (ds->ageing_time_max && ageing_time > ds->ageing_time_max) + return -ERANGE; /* Program the fastest ageing time in case of multiple bridges */ ageing_time = dsa_switch_fastest_ageing_time(ds, ageing_time); @@ -109,6 +106,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, { bool unset_vlan_filtering = br_vlan_enabled(info->br); struct dsa_switch_tree *dst = ds->dst; + struct netlink_ext_ack extack = {0}; int err, i; if (dst->index == info->tree_index && ds->index == info->sw_index && @@ -139,10 +137,11 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, } } if (unset_vlan_filtering) { - struct switchdev_trans trans = {0}; - err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), - false, &trans); + false, &extack); + if (extack._msg) + dev_err(ds->dev, "port %d: %s\n", info->port, + extack._msg); if (err && err != EOPNOTSUPP) return err; } @@ -171,6 +170,65 @@ static int dsa_switch_fdb_del(struct dsa_switch *ds, return ds->ops->port_fdb_del(ds, port, info->addr, info->vid); } +static int dsa_switch_hsr_join(struct dsa_switch *ds, + struct dsa_notifier_hsr_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_hsr_join) + return ds->ops->port_hsr_join(ds, info->port, info->hsr); + + return -EOPNOTSUPP; +} + +static int dsa_switch_hsr_leave(struct dsa_switch *ds, + struct dsa_notifier_hsr_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_hsr_leave) + return ds->ops->port_hsr_leave(ds, info->port, info->hsr); + + return -EOPNOTSUPP; +} + +static int dsa_switch_lag_change(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_change) + return ds->ops->port_lag_change(ds, info->port); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_change) + return ds->ops->crosschip_lag_change(ds, info->sw_index, + info->port); + + return 0; +} + +static int dsa_switch_lag_join(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_join) + return ds->ops->port_lag_join(ds, info->port, info->lag, + info->info); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_join) + return ds->ops->crosschip_lag_join(ds, info->sw_index, + info->port, info->lag, + info->info); + + return 0; +} + +static int dsa_switch_lag_leave(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (ds->index == info->sw_index && ds->ops->port_lag_leave) + return ds->ops->port_lag_leave(ds, info->port, info->lag); + + if (ds->index != info->sw_index && ds->ops->crosschip_lag_leave) + return ds->ops->crosschip_lag_leave(ds, info->sw_index, + info->port, info->lag); + + return 0; +} + static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, struct dsa_notifier_mdb_info *info) { @@ -183,94 +241,139 @@ static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, return false; } -static int dsa_switch_mdb_prepare(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { - int port, err; + int err = 0; + int port; - if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) + if (!ds->ops->port_mdb_add) return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { if (dsa_switch_mdb_match(ds, port, info)) { - err = ds->ops->port_mdb_prepare(ds, port, info->mdb); + err = ds->ops->port_mdb_add(ds, port, info->mdb); if (err) - return err; + break; } } - return 0; + return err; } -static int dsa_switch_mdb_add(struct dsa_switch *ds, +static int dsa_switch_mdb_del(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { - int port; + if (!ds->ops->port_mdb_del) + return -EOPNOTSUPP; - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_mdb_prepare(ds, info); + if (ds->index == info->sw_index) + return ds->ops->port_mdb_del(ds, info->port, info->mdb); - if (!ds->ops->port_mdb_add) - return 0; + return 0; +} - for (port = 0; port < ds->num_ports; port++) - if (dsa_switch_mdb_match(ds, port, info)) - ds->ops->port_mdb_add(ds, port, info->mdb); +static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, + struct dsa_notifier_vlan_info *info) +{ + if (ds->index == info->sw_index && port == info->port) + return true; - return 0; + if (dsa_is_dsa_port(ds, port)) + return true; + + return false; } -static int dsa_switch_mdb_del(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { - if (!ds->ops->port_mdb_del) + int port, err; + + if (!ds->ops->port_vlan_add) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_mdb_del(ds, info->port, info->mdb); + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_vlan_match(ds, port, info)) { + err = ds->ops->port_vlan_add(ds, port, info->vlan, + info->extack); + if (err) + return err; + } + } return 0; } -static int dsa_port_vlan_device_check(struct net_device *vlan_dev, - int vlan_dev_vid, - void *arg) +static int dsa_switch_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { - struct switchdev_obj_port_vlan *vlan = arg; - u16 vid; + if (!ds->ops->port_vlan_del) + return -EOPNOTSUPP; - for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { - if (vid == vlan_dev_vid) - return -EBUSY; - } + if (ds->index == info->sw_index) + return ds->ops->port_vlan_del(ds, info->port, info->vlan); + /* Do not deprogram the DSA links as they may be used as conduit + * for other VLAN members in the fabric. + */ return 0; } -static int dsa_port_vlan_check(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan) +static bool dsa_switch_tag_proto_match(struct dsa_switch *ds, int port, + struct dsa_notifier_tag_proto_info *info) { - const struct dsa_port *dp = dsa_to_port(ds, port); - int err = 0; + if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port)) + return true; - /* Device is not bridged, let it proceed with the VLAN device - * creation. - */ - if (!dp->bridge_dev) - return err; - - /* dsa_slave_vlan_rx_{add,kill}_vid() cannot use the prepare phase and - * already checks whether there is an overlapping bridge VLAN entry - * with the same VID, so here we only need to check that if we are - * adding a bridge VLAN entry there is not an overlapping VLAN device - * claiming that VID. + return false; +} + +static int dsa_switch_change_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + int port, err; + + if (!ds->ops->change_tag_protocol) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_tag_proto_match(ds, port, info)) { + err = ds->ops->change_tag_protocol(ds, port, + tag_ops->proto); + if (err) + return err; + + if (dsa_is_cpu_port(ds, port)) + dsa_port_set_tag_protocol(dsa_to_port(ds, port), + tag_ops); + } + } + + /* Now that changing the tag protocol can no longer fail, let's update + * the remaining bits which are "duplicated for faster access", and the + * bits that depend on the tagger, such as the MTU. */ - return vlan_for_each(dp->slave, dsa_port_vlan_device_check, - (void *)vlan); + for (port = 0; port < ds->num_ports; port++) { + if (dsa_is_user_port(ds, port)) { + struct net_device *slave; + + slave = dsa_to_port(ds, port)->slave; + dsa_slave_setup_tagger(slave); + + /* rtnl_mutex is held in dsa_tree_change_tag_proto */ + dsa_slave_change_mtu(slave, slave->mtu); + } + } + + return 0; } -static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, - struct dsa_notifier_vlan_info *info) +static bool dsa_switch_mrp_match(struct dsa_switch *ds, int port, + struct dsa_notifier_mrp_info *info) { if (ds->index == info->sw_index && port == info->port) return true; @@ -281,59 +384,84 @@ static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, return false; } -static int dsa_switch_vlan_prepare(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int dsa_switch_mrp_add(struct dsa_switch *ds, + struct dsa_notifier_mrp_info *info) { - int port, err; + int err = 0; + int port; - if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) + if (!ds->ops->port_mrp_add) return -EOPNOTSUPP; for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_vlan_match(ds, port, info)) { - err = dsa_port_vlan_check(ds, port, info->vlan); + if (dsa_switch_mrp_match(ds, port, info)) { + err = ds->ops->port_mrp_add(ds, port, info->mrp); if (err) - return err; - - err = ds->ops->port_vlan_prepare(ds, port, info->vlan); - if (err) - return err; + break; } } + return err; +} + +static int dsa_switch_mrp_del(struct dsa_switch *ds, + struct dsa_notifier_mrp_info *info) +{ + if (!ds->ops->port_mrp_del) + return -EOPNOTSUPP; + + if (ds->index == info->sw_index) + return ds->ops->port_mrp_del(ds, info->port, info->mrp); + return 0; } -static int dsa_switch_vlan_add(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static bool +dsa_switch_mrp_ring_role_match(struct dsa_switch *ds, int port, + struct dsa_notifier_mrp_ring_role_info *info) { - int port; + if (ds->index == info->sw_index && port == info->port) + return true; - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_vlan_prepare(ds, info); + if (dsa_is_dsa_port(ds, port)) + return true; - if (!ds->ops->port_vlan_add) - return 0; + return false; +} - for (port = 0; port < ds->num_ports; port++) - if (dsa_switch_vlan_match(ds, port, info)) - ds->ops->port_vlan_add(ds, port, info->vlan); +static int +dsa_switch_mrp_add_ring_role(struct dsa_switch *ds, + struct dsa_notifier_mrp_ring_role_info *info) +{ + int err = 0; + int port; - return 0; + if (!ds->ops->port_mrp_add) + return -EOPNOTSUPP; + + for (port = 0; port < ds->num_ports; port++) { + if (dsa_switch_mrp_ring_role_match(ds, port, info)) { + err = ds->ops->port_mrp_add_ring_role(ds, port, + info->mrp); + if (err) + break; + } + } + + return err; } -static int dsa_switch_vlan_del(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int +dsa_switch_mrp_del_ring_role(struct dsa_switch *ds, + struct dsa_notifier_mrp_ring_role_info *info) { - if (!ds->ops->port_vlan_del) + if (!ds->ops->port_mrp_del) return -EOPNOTSUPP; if (ds->index == info->sw_index) - return ds->ops->port_vlan_del(ds, info->port, info->vlan); + return ds->ops->port_mrp_del_ring_role(ds, info->port, + info->mrp); - /* Do not deprogram the DSA links as they may be used as conduit - * for other VLAN members in the fabric. - */ return 0; } @@ -359,6 +487,21 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_FDB_DEL: err = dsa_switch_fdb_del(ds, info); break; + case DSA_NOTIFIER_HSR_JOIN: + err = dsa_switch_hsr_join(ds, info); + break; + case DSA_NOTIFIER_HSR_LEAVE: + err = dsa_switch_hsr_leave(ds, info); + break; + case DSA_NOTIFIER_LAG_CHANGE: + err = dsa_switch_lag_change(ds, info); + break; + case DSA_NOTIFIER_LAG_JOIN: + err = dsa_switch_lag_join(ds, info); + break; + case DSA_NOTIFIER_LAG_LEAVE: + err = dsa_switch_lag_leave(ds, info); + break; case DSA_NOTIFIER_MDB_ADD: err = dsa_switch_mdb_add(ds, info); break; @@ -374,15 +517,26 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_MTU: err = dsa_switch_mtu(ds, info); break; + case DSA_NOTIFIER_TAG_PROTO: + err = dsa_switch_change_tag_proto(ds, info); + break; + case DSA_NOTIFIER_MRP_ADD: + err = dsa_switch_mrp_add(ds, info); + break; + case DSA_NOTIFIER_MRP_DEL: + err = dsa_switch_mrp_del(ds, info); + break; + case DSA_NOTIFIER_MRP_ADD_RING_ROLE: + err = dsa_switch_mrp_add_ring_role(ds, info); + break; + case DSA_NOTIFIER_MRP_DEL_RING_ROLE: + err = dsa_switch_mrp_del_ring_role(ds, info); + break; default: err = -EOPNOTSUPP; break; } - /* Non-switchdev operations cannot be rolled back. If a DSA driver - * returns an error during the chained call, switch chips may be in an - * inconsistent state. - */ if (err) dev_dbg(ds->dev, "breaking chain for DSA event %lu (%d)\n", event, err); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 780b2a15ac9b..008c1ec6e20c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -133,10 +133,21 @@ u16 dsa_8021q_rx_subvlan(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); +bool vid_is_dsa_8021q_rxvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_rxvlan); + +bool vid_is_dsa_8021q_txvlan(u16 vid) +{ + return (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX; +} +EXPORT_SYMBOL_GPL(vid_is_dsa_8021q_txvlan); + bool vid_is_dsa_8021q(u16 vid) { - return ((vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_RX || - (vid & DSA_8021Q_DIR_MASK) == DSA_8021Q_DIR_TX); + return vid_is_dsa_8021q_rxvlan(vid) || vid_is_dsa_8021q_txvlan(vid); } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); @@ -146,15 +157,15 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); * user explicitly configured this @vid through the bridge core, then the @vid * is installed again, but this time with the flags from the bridge layer. */ -static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, +static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid, u16 flags, bool enabled) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_port *dp = dsa_to_port(ctx->ds, port); if (enabled) - return dsa_port_vid_add(dp, vid, flags); + return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags); - return dsa_port_vid_del(dp, vid); + return ctx->ops->vlan_del(ctx->ds, dp->index, vid); } /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single @@ -209,25 +220,29 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid, * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 */ -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) +static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port, + bool enabled) { - int upstream = dsa_upstream_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); - int i, err; + int upstream = dsa_upstream_port(ctx->ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); + u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port); + struct net_device *master; + int i, err, subvlan; /* The CPU port is implicitly configured by * configuring the front-panel ports */ - if (!dsa_is_user_port(ds, port)) + if (!dsa_is_user_port(ctx->ds, port)) return 0; + master = dsa_to_port(ctx->ds, port)->cpu_dp->master; + /* 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++) { + for (i = 0; i < ctx->ds->num_ports; i++) { u16 flags; if (i == upstream) @@ -240,9 +255,10 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) /* The RX VID is a regular VLAN on all others */ flags = BRIDGE_VLAN_INFO_UNTAGGED; - err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled); + err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled); if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply RX VID %d to port %d: %d\n", rx_vid, port, err); return err; } @@ -251,80 +267,115 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) /* CPU port needs to see this port's RX VID * as tagged egress. */ - err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled); if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply RX VID %d to port %d: %d\n", rx_vid, port, err); return err; } + /* Add to the master's RX filter not only @rx_vid, but in fact + * the entire subvlan range, just in case this DSA switch might + * want to use sub-VLANs. + */ + for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) { + u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan); + + if (enabled) + vlan_vid_add(master, ctx->proto, vid); + else + vlan_vid_del(master, ctx->proto, vid); + } + /* Finally apply the TX VID on this port and on the CPU port */ - err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, + err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply TX VID %d on port %d: %d\n", tx_vid, port, err); return err; } - err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled); + err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", + dev_err(ctx->ds->dev, + "Failed to apply TX VID %d on port %d: %d\n", tx_vid, upstream, err); return err; } return err; } -EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging); -static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, +int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) +{ + int rc, port; + + ASSERT_RTNL(); + + for (port = 0; port < ctx->ds->num_ports; port++) { + rc = dsa_8021q_setup_port(ctx, port, enabled); + if (rc < 0) { + dev_err(ctx->ds->dev, + "Failed to setup VLAN tagging for port %d: %d\n", + port, rc); + return rc; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_8021q_setup); + +static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx, + int port, + struct dsa_8021q_context *other_ctx, int other_port, bool enabled) { - u16 rx_vid = dsa_8021q_rx_vid(ds, port); + u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port); /* @rx_vid of local @ds port @port goes to @other_port of * @other_ds */ - return dsa_8021q_vid_apply(other_ds, other_port, rx_vid, + return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid, BRIDGE_VLAN_INFO_UNTAGGED, enabled); } -static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { struct dsa_8021q_crosschip_link *c; - list_for_each_entry(c, crosschip_links, list) { - if (c->port == port && c->other_ds == other_ds && + list_for_each_entry(c, &ctx->crosschip_links, list) { + if (c->port == port && c->other_ctx == other_ctx && c->other_port == other_port) { refcount_inc(&c->refcount); return 0; } } - dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ds->dev), other_port); + dev_dbg(ctx->ds->dev, + "adding crosschip link from port %d to %s port %d\n", + port, dev_name(other_ctx->ds->dev), other_port); c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; c->port = port; - c->other_ds = other_ds; + c->other_ctx = other_ctx; c->other_port = other_port; refcount_set(&c->refcount, 1); - list_add(&c->list, crosschip_links); + list_add(&c->list, &ctx->crosschip_links); return 0; } -static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, +static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx, struct dsa_8021q_crosschip_link *c, - struct list_head *crosschip_links, bool *keep) { *keep = !refcount_dec_and_test(&c->refcount); @@ -332,9 +383,9 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, if (*keep) return; - dev_dbg(ds->dev, + dev_dbg(ctx->ds->dev, "deleting crosschip link from port %d to %s port %d\n", - c->port, dev_name(c->other_ds->dev), c->other_port); + c->port, dev_name(c->other_ctx->ds->dev), c->other_port); list_del(&c->list); kfree(c); @@ -347,64 +398,58 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, * or untagged: it doesn't matter, since it should never egress a frame having * our @rx_vid. */ -int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { /* @other_upstream is how @other_ds reaches us. If we are part * of disjoint trees, then we are probably connected through * our CPU ports. If we're part of the same tree though, we should * probably use dsa_towards_port. */ - int other_upstream = dsa_upstream_port(other_ds, other_port); + int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); int rc; - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_port, crosschip_links); + rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port); if (rc) return rc; - rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds, + rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, other_port, true); if (rc) return rc; - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_upstream, - crosschip_links); + rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream); if (rc) return rc; - return dsa_8021q_crosschip_link_apply(ds, port, other_ds, + return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx, other_upstream, true); } EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); -int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_switch *other_ds, - int other_port, - struct list_head *crosschip_links) +int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, + struct dsa_8021q_context *other_ctx, + int other_port) { - int other_upstream = dsa_upstream_port(other_ds, other_port); + int other_upstream = dsa_upstream_port(other_ctx->ds, other_port); struct dsa_8021q_crosschip_link *c, *n; - list_for_each_entry_safe(c, n, crosschip_links, list) { - if (c->port == port && c->other_ds == other_ds && + list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) { + if (c->port == port && c->other_ctx == other_ctx && (c->other_port == other_port || c->other_port == other_upstream)) { - struct dsa_switch *other_ds = c->other_ds; + struct dsa_8021q_context *other_ctx = c->other_ctx; int other_port = c->other_port; bool keep; int rc; - dsa_8021q_crosschip_link_del(ds, c, crosschip_links, - &keep); + dsa_8021q_crosschip_link_del(ctx, c, &keep); if (keep) continue; - rc = dsa_8021q_crosschip_link_apply(ds, port, - other_ds, + rc = dsa_8021q_crosschip_link_apply(ctx, port, + other_ctx, other_port, false); if (rc) diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 55b00694cdba..002cf7f952e2 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -31,9 +31,6 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, __le16 *phdr; u16 hdr; - if (skb_cow_head(skb, AR9331_HDR_LEN) < 0) - return NULL; - phdr = skb_push(skb, AR9331_HDR_LEN); hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cc8512b5f9e2..e2577a7dcbca 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -5,6 +5,7 @@ * Copyright (C) 2014 Broadcom Corporation */ +#include <linux/dsa/brcm.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> @@ -66,9 +67,6 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; - if (skb_cow_head(skb, BRCM_TAG_LEN) < 0) - return NULL; - /* The Ethernet switch we are interfaced with needs packets to be at * least 64 bytes (including FCS) otherwise they will be discarded when * they enter the switch port logic. When Broadcom tags are enabled, we @@ -107,6 +105,18 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, return skb; } +/* Frames with this tag have one of these two layouts: + * ----------------------------------- + * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM + * ----------------------------------- + * ----------------------------------- + * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND + * ----------------------------------- + * In both cases, at receive time, skb->data points 2 bytes before the actual + * Ethernet type field and we have an offset of 4bytes between where skb->data + * and where the payload starts. So the same low-level receive function can be + * used. + */ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -144,27 +154,6 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, return skb; } - -static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - /* We have been called on the DSA master network device after - * eth_type_trans() which pulled the Ethernet header already. - * Frames have one of these two layouts: - * ----------------------------------- - * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM - * ----------------------------------- - * ----------------------------------- - * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND - * ----------------------------------- - * skb->data points 2 bytes before the actual Ethernet type field and - * we have an offset of 4bytes between where skb->data and where the - * payload starts. - */ - *offset = BRCM_TAG_LEN; - *proto = ((__be16 *)skb->data)[1]; - return 0; -} #endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM) @@ -200,7 +189,6 @@ static const struct dsa_device_ops brcm_netdev_ops = { .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, }; DSA_TAG_DRIVER(brcm_netdev_ops); @@ -229,7 +217,6 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7ddec9794477..7e7b7decdf39 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -1,7 +1,48 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * net/dsa/tag_dsa.c - (Non-ethertype) DSA tagging + * Regular and Ethertype DSA tagging * Copyright (c) 2008-2009 Marvell Semiconductor + * + * Regular DSA + * ----------- + + * For untagged (in 802.1Q terms) packets, the switch will splice in + * the tag between the SA and the ethertype of the original + * packet. Tagged frames will instead have their outermost .1Q tag + * converted to a DSA tag. It expects the same layout when receiving + * packets from the CPU. + * + * Example: + * + * .----.----.----.--------- + * Pu: | DA | SA | ET | Payload ... + * '----'----'----'--------- + * 6 6 2 N + * .----.----.--------.-----.----.--------- + * Pt: | DA | SA | 0x8100 | TCI | ET | Payload ... + * '----'----'--------'-----'----'--------- + * 6 6 2 2 2 N + * .----.----.-----.----.--------- + * Pd: | DA | SA | DSA | ET | Payload ... + * '----'----'-----'----'--------- + * 6 6 4 2 N + * + * No matter if a packet is received untagged (Pu) or tagged (Pt), + * they will both have the same layout (Pd) when they are sent to the + * CPU. This is done by ignoring 802.3, replacing the ethertype field + * with more metadata, among which is a bit to signal if the original + * packet was tagged or not. + * + * Ethertype DSA + * ------------- + * Uses the exact same tag format as regular DSA, but also includes a + * proper ethertype field (which the mv88e6xxx driver sets to + * ETH_P_EDSA/0xdada) followed by two zero bytes: + * + * .----.----.--------.--------.-----.----.--------- + * | DA | SA | 0xdada | 0x0000 | DSA | ET | Payload ... + * '----'----'--------'--------'-----'----'--------- + * 6 6 2 2 4 2 N */ #include <linux/etherdevice.h> @@ -12,46 +53,104 @@ #define DSA_HLEN 4 -static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) +/** + * enum dsa_cmd - DSA Command + * @DSA_CMD_TO_CPU: Set on packets that were trapped or mirrored to + * the CPU port. This is needed to implement control protocols, + * e.g. STP and LLDP, that must not allow those control packets to + * be switched according to the normal rules. + * @DSA_CMD_FROM_CPU: Used by the CPU to send a packet to a specific + * port, ignoring all the barriers that the switch normally + * enforces (VLANs, STP port states etc.). No source address + * learning takes place. "sudo send packet" + * @DSA_CMD_TO_SNIFFER: Set on the copies of packets that matched some + * user configured ingress or egress monitor criteria. These are + * forwarded by the switch tree to the user configured ingress or + * egress monitor port, which can be set to the CPU port or a + * regular port. If the destination is a regular port, the tag + * will be removed before egressing the port. If the destination + * is the CPU port, the tag will not be removed. + * @DSA_CMD_FORWARD: This tag is used on all bulk traffic passing + * through the switch tree, including the flows that are directed + * towards the CPU. Its device/port tuple encodes the original + * source port on which the packet ingressed. It can also be used + * on transmit by the CPU to defer the forwarding decision to the + * hardware, based on the current config of PVT/VTU/ATU + * etc. Source address learning takes places if enabled on the + * receiving DSA/CPU port. + */ +enum dsa_cmd { + DSA_CMD_TO_CPU = 0, + DSA_CMD_FROM_CPU = 1, + DSA_CMD_TO_SNIFFER = 2, + DSA_CMD_FORWARD = 3 +}; + +/** + * enum dsa_code - TO_CPU Code + * + * @DSA_CODE_MGMT_TRAP: DA was classified as a management + * address. Typical examples include STP BPDUs and LLDP. + * @DSA_CODE_FRAME2REG: Response to a "remote management" request. + * @DSA_CODE_IGMP_MLD_TRAP: IGMP/MLD signaling. + * @DSA_CODE_POLICY_TRAP: Frame matched some policy configuration on + * the device. Typical examples are matching on DA/SA/VID and DHCP + * snooping. + * @DSA_CODE_ARP_MIRROR: The name says it all really. + * @DSA_CODE_POLICY_MIRROR: Same as @DSA_CODE_POLICY_TRAP, but the + * particular policy was set to trigger a mirror instead of a + * trap. + * @DSA_CODE_RESERVED_6: Unused on all devices up to at least 6393X. + * @DSA_CODE_RESERVED_7: Unused on all devices up to at least 6393X. + * + * A 3-bit code is used to relay why a particular frame was sent to + * the CPU. We only use this to determine if the packet was mirrored + * or trapped, i.e. whether the packet has been forwarded by hardware + * or not. + * + * This is the superset of all possible codes. Any particular device + * may only implement a subset. + */ +enum dsa_code { + DSA_CODE_MGMT_TRAP = 0, + DSA_CODE_FRAME2REG = 1, + DSA_CODE_IGMP_MLD_TRAP = 2, + DSA_CODE_POLICY_TRAP = 3, + DSA_CODE_ARP_MIRROR = 4, + DSA_CODE_POLICY_MIRROR = 5, + DSA_CODE_RESERVED_6 = 6, + DSA_CODE_RESERVED_7 = 7 +}; + +static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, + u8 extra) { struct dsa_port *dp = dsa_slave_to_port(dev); u8 *dsa_header; - /* - * Convert the outermost 802.1q tag to a DSA tag for tagged - * packets, or insert a DSA tag between the addresses and - * the ethertype field for untagged packets. - */ if (skb->protocol == htons(ETH_P_8021Q)) { - if (skb_cow_head(skb, 0) < 0) - return NULL; + if (extra) { + skb_push(skb, extra); + memmove(skb->data, skb->data + extra, 2 * ETH_ALEN); + } - /* - * Construct tagged FROM_CPU DSA tag from 802.1q tag. - */ - dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x60 | dp->ds->index; + /* Construct tagged FROM_CPU DSA tag from 802.1Q tag. */ + dsa_header = skb->data + 2 * ETH_ALEN + extra; + dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | 0x20 | dp->ds->index; dsa_header[1] = dp->index << 3; - /* - * Move CFI field from byte 2 to byte 1. - */ + /* Move CFI field from byte 2 to byte 1. */ if (dsa_header[2] & 0x10) { dsa_header[1] |= 0x01; dsa_header[2] &= ~0x10; } } else { - if (skb_cow_head(skb, DSA_HLEN) < 0) - return NULL; - skb_push(skb, DSA_HLEN); - - memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); + skb_push(skb, DSA_HLEN + extra); + memmove(skb->data, skb->data + DSA_HLEN + extra, 2 * ETH_ALEN); - /* - * Construct untagged FROM_CPU DSA tag. - */ - dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x40 | dp->ds->index; + /* Construct untagged FROM_CPU DSA tag. */ + dsa_header = skb->data + 2 * ETH_ALEN + extra; + dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | dp->ds->index; dsa_header[1] = dp->index << 3; dsa_header[2] = 0x00; dsa_header[3] = 0x00; @@ -60,47 +159,91 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) return skb; } -static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, + u8 extra) { + int source_device, source_port; + bool trunk = false; + enum dsa_code code; + enum dsa_cmd cmd; u8 *dsa_header; - int source_device; - int source_port; - - if (unlikely(!pskb_may_pull(skb, DSA_HLEN))) - return NULL; - /* - * The ethertype field is part of the DSA header. - */ + /* The ethertype field is part of the DSA header. */ dsa_header = skb->data - 2; - /* - * Check that frame type is either TO_CPU or FORWARD. - */ - if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0) + cmd = dsa_header[0] >> 6; + switch (cmd) { + case DSA_CMD_FORWARD: + skb->offload_fwd_mark = 1; + + trunk = !!(dsa_header[1] & 7); + break; + + case DSA_CMD_TO_CPU: + code = (dsa_header[1] & 0x6) | ((dsa_header[2] >> 4) & 1); + + switch (code) { + case DSA_CODE_FRAME2REG: + /* Remote management is not implemented yet, + * drop. + */ + return NULL; + case DSA_CODE_ARP_MIRROR: + case DSA_CODE_POLICY_MIRROR: + /* Mark mirrored packets to notify any upper + * device (like a bridge) that forwarding has + * already been done by hardware. + */ + skb->offload_fwd_mark = 1; + break; + case DSA_CODE_MGMT_TRAP: + case DSA_CODE_IGMP_MLD_TRAP: + case DSA_CODE_POLICY_TRAP: + /* Traps have, by definition, not been + * forwarded by hardware, so don't mark them. + */ + break; + default: + /* Reserved code, this could be anything. Drop + * seems like the safest option. + */ + return NULL; + } + + break; + + default: return NULL; + } - /* - * Determine source device and port. - */ source_device = dsa_header[0] & 0x1f; source_port = (dsa_header[1] >> 3) & 0x1f; - skb->dev = dsa_master_find_slave(dev, source_device, source_port); + if (trunk) { + struct dsa_port *cpu_dp = dev->dsa_ptr; + + /* The exact source port is not available in the tag, + * so we inject the frame directly on the upper + * team/bond. + */ + skb->dev = dsa_lag_dev(cpu_dp->dst, source_port); + } else { + skb->dev = dsa_master_find_slave(dev, source_device, + source_port); + } + if (!skb->dev) return NULL; - /* - * Convert the DSA header to an 802.1q header if the 'tagged' - * bit in the DSA header is set. If the 'tagged' bit is clear, - * delete the DSA header entirely. + /* If the 'tagged' bit is set; convert the DSA tag to a 802.1Q + * tag, and delete the ethertype (extra) if applicable. If the + * 'tagged' bit is cleared; delete the DSA tag, and ethertype + * if applicable. */ if (dsa_header[0] & 0x20) { u8 new_header[4]; - /* - * Insert 802.1q ethertype and copy the VLAN-related + /* Insert 802.1Q ethertype and copy the VLAN-related * fields, but clear the bit that will hold CFI (since * DSA uses that bit location for another purpose). */ @@ -109,16 +252,13 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, new_header[2] = dsa_header[2] & ~0x10; new_header[3] = dsa_header[3]; - /* - * Move CFI bit from its place in the DSA header to - * its 802.1q-designated place. + /* Move CFI bit from its place in the DSA header to + * its 802.1Q-designated place. */ if (dsa_header[1] & 0x01) new_header[2] |= 0x10; - /* - * Update packet checksum if skb is CHECKSUM_COMPLETE. - */ + /* Update packet checksum if skb is CHECKSUM_COMPLETE. */ if (skb->ip_summed == CHECKSUM_COMPLETE) { __wsum c = skb->csum; c = csum_add(c, csum_partial(new_header + 2, 2, 0)); @@ -127,39 +267,101 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, } memcpy(dsa_header, new_header, DSA_HLEN); + + if (extra) + memmove(skb->data - ETH_HLEN, + skb->data - ETH_HLEN - extra, + 2 * ETH_ALEN); } else { - /* - * Remove DSA tag and update checksum. - */ skb_pull_rcsum(skb, DSA_HLEN); memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - DSA_HLEN, + skb->data - ETH_HLEN - DSA_HLEN - extra, 2 * ETH_ALEN); } - skb->offload_fwd_mark = 1; - return skb; } -static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) +#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA) + +static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) { - *offset = 4; - *proto = ((__be16 *)skb->data)[1]; - return 0; + return dsa_xmit_ll(skb, dev, 0); +} + +static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + if (unlikely(!pskb_may_pull(skb, DSA_HLEN))) + return NULL; + + return dsa_rcv_ll(skb, dev, 0); } static const struct dsa_device_ops dsa_netdev_ops = { - .name = "dsa", - .proto = DSA_TAG_PROTO_DSA, - .xmit = dsa_xmit, - .rcv = dsa_rcv, - .flow_dissect = dsa_tag_flow_dissect, + .name = "dsa", + .proto = DSA_TAG_PROTO_DSA, + .xmit = dsa_xmit, + .rcv = dsa_rcv, .overhead = DSA_HLEN, }; -MODULE_LICENSE("GPL"); +DSA_TAG_DRIVER(dsa_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA); +#endif /* CONFIG_NET_DSA_TAG_DSA */ + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA) + +#define EDSA_HLEN 8 + +static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) +{ + u8 *edsa_header; -module_dsa_tag_driver(dsa_netdev_ops); + skb = dsa_xmit_ll(skb, dev, EDSA_HLEN - DSA_HLEN); + if (!skb) + return NULL; + + edsa_header = skb->data + 2 * ETH_ALEN; + edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff; + edsa_header[1] = ETH_P_EDSA & 0xff; + edsa_header[2] = 0x00; + edsa_header[3] = 0x00; + return skb; +} + +static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + if (unlikely(!pskb_may_pull(skb, EDSA_HLEN))) + return NULL; + + skb_pull_rcsum(skb, EDSA_HLEN - DSA_HLEN); + + return dsa_rcv_ll(skb, dev, EDSA_HLEN - DSA_HLEN); +} + +static const struct dsa_device_ops edsa_netdev_ops = { + .name = "edsa", + .proto = DSA_TAG_PROTO_EDSA, + .xmit = edsa_xmit, + .rcv = edsa_rcv, + .overhead = EDSA_HLEN, +}; + +DSA_TAG_DRIVER(edsa_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA); +#endif /* CONFIG_NET_DSA_TAG_EDSA */ + +static struct dsa_tag_driver *dsa_tag_drivers[] = { +#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA) + &DSA_TAG_DRIVER_NAME(dsa_netdev_ops), +#endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA) + &DSA_TAG_DRIVER_NAME(edsa_netdev_ops), +#endif +}; + +module_dsa_tag_drivers(dsa_tag_drivers); + +MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c deleted file mode 100644 index d6200ff98200..000000000000 --- a/net/dsa/tag_edsa.c +++ /dev/null @@ -1,215 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0+ -/* - * net/dsa/tag_edsa.c - Ethertype DSA tagging - * Copyright (c) 2008-2009 Marvell Semiconductor - */ - -#include <linux/etherdevice.h> -#include <linux/list.h> -#include <linux/slab.h> - -#include "dsa_priv.h" - -#define DSA_HLEN 4 -#define EDSA_HLEN 8 - -#define FRAME_TYPE_TO_CPU 0x00 -#define FRAME_TYPE_FORWARD 0x03 - -#define TO_CPU_CODE_MGMT_TRAP 0x00 -#define TO_CPU_CODE_FRAME2REG 0x01 -#define TO_CPU_CODE_IGMP_MLD_TRAP 0x02 -#define TO_CPU_CODE_POLICY_TRAP 0x03 -#define TO_CPU_CODE_ARP_MIRROR 0x04 -#define TO_CPU_CODE_POLICY_MIRROR 0x05 - -static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - u8 *edsa_header; - - /* - * Convert the outermost 802.1q tag to a DSA tag and prepend - * a DSA ethertype field is the packet is tagged, or insert - * a DSA ethertype plus DSA tag between the addresses and the - * current ethertype field if the packet is untagged. - */ - if (skb->protocol == htons(ETH_P_8021Q)) { - if (skb_cow_head(skb, DSA_HLEN) < 0) - return NULL; - skb_push(skb, DSA_HLEN); - - memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); - - /* - * Construct tagged FROM_CPU DSA tag from 802.1q tag. - */ - edsa_header = skb->data + 2 * ETH_ALEN; - edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff; - edsa_header[1] = ETH_P_EDSA & 0xff; - edsa_header[2] = 0x00; - edsa_header[3] = 0x00; - edsa_header[4] = 0x60 | dp->ds->index; - edsa_header[5] = dp->index << 3; - - /* - * Move CFI field from byte 6 to byte 5. - */ - if (edsa_header[6] & 0x10) { - edsa_header[5] |= 0x01; - edsa_header[6] &= ~0x10; - } - } else { - if (skb_cow_head(skb, EDSA_HLEN) < 0) - return NULL; - skb_push(skb, EDSA_HLEN); - - memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN); - - /* - * Construct untagged FROM_CPU DSA tag. - */ - edsa_header = skb->data + 2 * ETH_ALEN; - edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff; - edsa_header[1] = ETH_P_EDSA & 0xff; - edsa_header[2] = 0x00; - edsa_header[3] = 0x00; - edsa_header[4] = 0x40 | dp->ds->index; - edsa_header[5] = dp->index << 3; - edsa_header[6] = 0x00; - edsa_header[7] = 0x00; - } - - return skb; -} - -static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) -{ - u8 *edsa_header; - int frame_type; - int code; - int source_device; - int source_port; - - if (unlikely(!pskb_may_pull(skb, EDSA_HLEN))) - return NULL; - - /* - * Skip the two null bytes after the ethertype. - */ - edsa_header = skb->data + 2; - - /* - * Check that frame type is either TO_CPU or FORWARD. - */ - frame_type = edsa_header[0] >> 6; - - switch (frame_type) { - case FRAME_TYPE_TO_CPU: - code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1); - - /* - * Mark the frame to never egress on any port of the same switch - * unless it's a trapped IGMP/MLD packet, in which case the - * bridge might want to forward it. - */ - if (code != TO_CPU_CODE_IGMP_MLD_TRAP) - skb->offload_fwd_mark = 1; - - break; - - case FRAME_TYPE_FORWARD: - skb->offload_fwd_mark = 1; - break; - - default: - return NULL; - } - - /* - * Determine source device and port. - */ - source_device = edsa_header[0] & 0x1f; - source_port = (edsa_header[1] >> 3) & 0x1f; - - skb->dev = dsa_master_find_slave(dev, source_device, source_port); - if (!skb->dev) - return NULL; - - /* - * If the 'tagged' bit is set, convert the DSA tag to a 802.1q - * tag and delete the ethertype part. If the 'tagged' bit is - * clear, delete the ethertype and the DSA tag parts. - */ - if (edsa_header[0] & 0x20) { - u8 new_header[4]; - - /* - * Insert 802.1q ethertype and copy the VLAN-related - * fields, but clear the bit that will hold CFI (since - * DSA uses that bit location for another purpose). - */ - new_header[0] = (ETH_P_8021Q >> 8) & 0xff; - new_header[1] = ETH_P_8021Q & 0xff; - new_header[2] = edsa_header[2] & ~0x10; - new_header[3] = edsa_header[3]; - - /* - * Move CFI bit from its place in the DSA header to - * its 802.1q-designated place. - */ - if (edsa_header[1] & 0x01) - new_header[2] |= 0x10; - - skb_pull_rcsum(skb, DSA_HLEN); - - /* - * Update packet checksum if skb is CHECKSUM_COMPLETE. - */ - if (skb->ip_summed == CHECKSUM_COMPLETE) { - __wsum c = skb->csum; - c = csum_add(c, csum_partial(new_header + 2, 2, 0)); - c = csum_sub(c, csum_partial(edsa_header + 2, 2, 0)); - skb->csum = c; - } - - memcpy(edsa_header, new_header, DSA_HLEN); - - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - DSA_HLEN, - 2 * ETH_ALEN); - } else { - /* - * Remove DSA tag and update checksum. - */ - skb_pull_rcsum(skb, EDSA_HLEN); - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - EDSA_HLEN, - 2 * ETH_ALEN); - } - - return skb; -} - -static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = 8; - *proto = ((__be16 *)skb->data)[3]; - return 0; -} - -static const struct dsa_device_ops edsa_netdev_ops = { - .name = "edsa", - .proto = DSA_TAG_PROTO_EDSA, - .xmit = edsa_xmit, - .rcv = edsa_rcv, - .flow_dissect = edsa_tag_flow_dissect, - .overhead = EDSA_HLEN, -}; - -MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA); - -module_dsa_tag_driver(edsa_netdev_ops); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 408d4af390a0..2f5bd5e338ab 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -60,13 +60,8 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - int err; u8 *gswip_tag; - err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN); - if (err) - return NULL; - skb_push(skb, GSWIP_TX_HEADER_LEN); gswip_tag = skb->data; diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c new file mode 100644 index 000000000000..a09805c8e1ab --- /dev/null +++ b/net/dsa/tag_hellcreek.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * net/dsa/tag_hellcreek.c - Hirschmann Hellcreek switch tag format handling + * + * Copyright (C) 2019,2020 Linutronix GmbH + * Author Kurt Kanzenbach <[email protected]> + * + * Based on tag_ksz.c. + */ + +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "dsa_priv.h" + +#define HELLCREEK_TAG_LEN 1 + +static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + u8 *tag; + + /* Tag encoding */ + tag = skb_put(skb, HELLCREEK_TAG_LEN); + *tag = BIT(dp->index); + + return skb; +} + +static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + /* Tag decoding */ + u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; + unsigned int port = tag[0] & 0x03; + + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) { + netdev_warn(dev, "Failed to get source port: %d\n", port); + return NULL; + } + + pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN); + + skb->offload_fwd_mark = true; + + return skb; +} + +static const struct dsa_device_ops hellcreek_netdev_ops = { + .name = "hellcreek", + .proto = DSA_TAG_PROTO_HELLCREEK, + .xmit = hellcreek_xmit, + .rcv = hellcreek_rcv, + .overhead = HELLCREEK_TAG_LEN, + .tail_tag = true, +}; + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK); + +module_dsa_tag_driver(hellcreek_netdev_ops); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index bd1a3158d79a..4820dbcedfa2 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -14,46 +14,6 @@ #define KSZ_EGRESS_TAG_LEN 1 #define KSZ_INGRESS_TAG_LEN 1 -static struct sk_buff *ksz_common_xmit(struct sk_buff *skb, - struct net_device *dev, int len) -{ - struct sk_buff *nskb; - int padlen; - - padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; - - if (skb_tailroom(skb) >= padlen + len) { - /* Let dsa_slave_xmit() free skb */ - if (__skb_put_padto(skb, skb->len + padlen, false)) - return NULL; - - nskb = skb; - } else { - nskb = alloc_skb(NET_IP_ALIGN + skb->len + - padlen + len, GFP_ATOMIC); - if (!nskb) - return NULL; - skb_reserve(nskb, NET_IP_ALIGN); - - skb_reset_mac_header(nskb); - skb_set_network_header(nskb, - skb_network_header(skb) - skb->head); - skb_set_transport_header(nskb, - skb_transport_header(skb) - skb->head); - skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - - /* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free - * skb - */ - if (skb_put_padto(nskb, nskb->len + padlen)) - return NULL; - - consume_skb(skb); - } - - return nskb; -} - static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) @@ -90,23 +50,18 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); *tag = 1 << dp->index; if (is_link_local_ether_addr(addr)) *tag |= KSZ8795_TAIL_TAG_OVERRIDE; - return nskb; + return skb; } static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, @@ -123,6 +78,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, .overhead = KSZ_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); @@ -155,18 +111,13 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; __be16 *tag; u8 *addr; u16 val; - nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); val = BIT(dp->index); @@ -175,7 +126,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, *tag = cpu_to_be16(val); - return nskb; + return skb; } static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev, @@ -199,6 +150,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, .overhead = KSZ9477_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -211,24 +163,19 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; u8 *addr; u8 *tag; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); *tag = BIT(dp->index); if (is_link_local_ether_addr(addr)) *tag |= KSZ9893_TAIL_TAG_OVERRIDE; - return nskb; + return skb; } static const struct dsa_device_ops ksz9893_netdev_ops = { @@ -237,6 +184,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, .overhead = KSZ_INGRESS_TAG_LEN, + .tail_tag = true, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index ccfb6f641bbf..aa1318dccaf0 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -58,15 +58,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) __be16 *lan9303_tag; u16 tag; - /* insert a special VLAN tag between the MAC addresses - * and the current ethertype field. - */ - if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) { - dev_dbg(&dev->dev, - "Cannot make room for the special tag. Dropping packet\n"); - return NULL; - } - /* provide 'LAN9303_TAG_LEN' bytes additional space */ skb_push(skb, LAN9303_TAG_LEN); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index f602fc758d68..38dcdded74c0 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -34,9 +34,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * table with VID. */ if (!skb_vlan_tagged(skb)) { - if (skb_cow_head(skb, MTK_HDR_LEN) < 0) - return NULL; - skb_push(skb, MTK_HDR_LEN); memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); is_vlan_skb = false; @@ -105,21 +102,11 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = 4; - *proto = ((__be16 *)skb->data)[1]; - - return 0; -} - static const struct dsa_device_ops mtk_netdev_ops = { .name = "mtk", .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .flow_dissect = mtk_tag_flow_dissect, .overhead = MTK_HDR_LEN, }; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index b4fc05cafaa6..743809b5806b 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,176 +1,74 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright 2019 NXP Semiconductors */ +#include <linux/dsa/ocelot.h> #include <soc/mscc/ocelot.h> -#include <linux/packing.h> #include "dsa_priv.h" -/* The CPU injection header and the CPU extraction header can have 3 types of - * prefixes: long, short and no prefix. The format of the header itself is the - * same in all 3 cases. - * - * Extraction with long prefix: - * - * +-------------------+-------------------+------+------+------------+-------+ - * | ff:ff:ff:ff:ff:ff | ff:ff:ff:ff:ff:ff | 8880 | 000a | extraction | frame | - * | | | | | header | | - * +-------------------+-------------------+------+------+------------+-------+ - * 48 bits 48 bits 16 bits 16 bits 128 bits - * - * Extraction with short prefix: - * - * +------+------+------------+-------+ - * | 8880 | 000a | extraction | frame | - * | | | header | | - * +------+------+------------+-------+ - * 16 bits 16 bits 128 bits - * - * Extraction with no prefix: - * - * +------------+-------+ - * | extraction | frame | - * | header | | - * +------------+-------+ - * 128 bits - * - * - * Injection with long prefix: - * - * +-------------------+-------------------+------+------+------------+-------+ - * | any dmac | any smac | 8880 | 000a | injection | frame | - * | | | | | header | | - * +-------------------+-------------------+------+------+------------+-------+ - * 48 bits 48 bits 16 bits 16 bits 128 bits - * - * Injection with short prefix: - * - * +------+------+------------+-------+ - * | 8880 | 000a | injection | frame | - * | | | header | | - * +------+------+------------+-------+ - * 16 bits 16 bits 128 bits - * - * Injection with no prefix: - * - * +------------+-------+ - * | injection | frame | - * | header | | - * +------------+-------+ - * 128 bits - * - * The injection header looks like this (network byte order, bit 127 - * is part of lowest address byte in memory, bit 0 is part of highest - * address byte): - * - * +------+------+------+------+------+------+------+------+ - * 127:120 |BYPASS| MASQ | MASQ_PORT |REW_OP|REW_OP| - * +------+------+------+------+------+------+------+------+ - * 119:112 | REW_OP | - * +------+------+------+------+------+------+------+------+ - * 111:104 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 103: 96 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 95: 88 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 87: 80 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 79: 72 | RSV | - * +------+------+------+------+------+------+------+------+ - * 71: 64 | RSV | DEST | - * +------+------+------+------+------+------+------+------+ - * 63: 56 | DEST | - * +------+------+------+------+------+------+------+------+ - * 55: 48 | RSV | - * +------+------+------+------+------+------+------+------+ - * 47: 40 | RSV | SRC_PORT | RSV |TFRM_TIMER| - * +------+------+------+------+------+------+------+------+ - * 39: 32 | TFRM_TIMER | RSV | - * +------+------+------+------+------+------+------+------+ - * 31: 24 | RSV | DP | POP_CNT | CPUQ | - * +------+------+------+------+------+------+------+------+ - * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| - * +------+------+------+------+------+------+------+------+ - * 15: 8 | PCP | DEI | VID | - * +------+------+------+------+------+------+------+------+ - * 7: 0 | VID | - * +------+------+------+------+------+------+------+------+ - * - * And the extraction header looks like this: - * - * +------+------+------+------+------+------+------+------+ - * 127:120 | RSV | REW_OP | - * +------+------+------+------+------+------+------+------+ - * 119:112 | REW_OP | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 111:104 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 103: 96 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 95: 88 | REW_VAL | - * +------+------+------+------+------+------+------+------+ - * 87: 80 | REW_VAL | LLEN | - * +------+------+------+------+------+------+------+------+ - * 79: 72 | LLEN | WLEN | - * +------+------+------+------+------+------+------+------+ - * 71: 64 | WLEN | RSV | - * +------+------+------+------+------+------+------+------+ - * 63: 56 | RSV | - * +------+------+------+------+------+------+------+------+ - * 55: 48 | RSV | - * +------+------+------+------+------+------+------+------+ - * 47: 40 | RSV | SRC_PORT | ACL_ID | - * +------+------+------+------+------+------+------+------+ - * 39: 32 | ACL_ID | RSV | SFLOW_ID | - * +------+------+------+------+------+------+------+------+ - * 31: 24 |ACL_HIT| DP | LRN_FLAGS | CPUQ | - * +------+------+------+------+------+------+------+------+ - * 23: 16 | CPUQ | QOS_CLASS |TAG_TYPE| - * +------+------+------+------+------+------+------+------+ - * 15: 8 | PCP | DEI | VID | - * +------+------+------+------+------+------+------+------+ - * 7: 0 | VID | - * +------+------+------+------+------+------+------+------+ - */ +static void ocelot_xmit_ptp(struct dsa_port *dp, void *injection, + struct sk_buff *clone) +{ + struct ocelot *ocelot = dp->ds->priv; + struct ocelot_port *ocelot_port; + u64 rew_op; -static struct sk_buff *ocelot_xmit(struct sk_buff *skb, - struct net_device *netdev) + ocelot_port = ocelot->ports[dp->index]; + rew_op = ocelot_port->ptp_cmd; + + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; + + ocelot_ifh_set_rew_op(injection, rew_op); +} + +static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, + __be32 ifh_prefix, void **ifh) { struct dsa_port *dp = dsa_slave_to_port(netdev); + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; struct dsa_switch *ds = dp->ds; - struct ocelot *ocelot = ds->priv; - struct ocelot_port *ocelot_port; - u64 qos_class, rew_op; - u8 *injection; + void *injection; + __be32 *prefix; - if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) { - netdev_err(netdev, "Cannot make room for tag.\n"); - return NULL; - } + injection = skb_push(skb, OCELOT_TAG_LEN); + prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN); - ocelot_port = ocelot->ports[dp->index]; + *prefix = ifh_prefix; + memset(injection, 0, OCELOT_TAG_LEN); + ocelot_ifh_set_bypass(injection, 1); + ocelot_ifh_set_src(injection, ds->num_ports); + ocelot_ifh_set_qos_class(injection, skb->priority); - injection = skb_push(skb, OCELOT_TAG_LEN); + /* TX timestamping was requested */ + if (clone) + ocelot_xmit_ptp(dp, injection, clone); - memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN); - /* Fix up the fields which are not statically determined - * in the template - */ - qos_class = skb->priority; - packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); + *ifh = injection; +} - if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - struct sk_buff *clone = DSA_SKB_CB(skb)->clone; +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + void *injection; - rew_op = ocelot_port->ptp_cmd; - /* Retrieve timestamp ID populated inside skb->cb[0] of the - * clone by ocelot_port_add_txtstamp_skb - */ - if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) - rew_op |= clone->cb[0] << 3; + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x8880000a), &injection); + ocelot_ifh_set_dest(injection, BIT_ULL(dp->index)); - packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); - } + return skb; +} + +static struct sk_buff *seville_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + void *injection; + + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x88800005), &injection); + seville_ifh_set_dest(injection, BIT_ULL(dp->index)); return skb; } @@ -180,18 +78,22 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct packet_type *pt) { u64 src_port, qos_class; + u64 vlan_tci, tag_type; u8 *start = skb->data; + struct dsa_port *dp; u8 *extraction; + u16 vlan_tpid; + u64 cpuq; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. */ skb_push(skb, ETH_HLEN); - /* We don't care about the long prefix, it is just for easy entrance + /* We don't care about the short prefix, it is just for easy entrance * into the DSA master's RX filter. Discard it now by moving it into * the headroom. */ - skb_pull(skb, OCELOT_LONG_PREFIX_LEN); + skb_pull(skb, OCELOT_SHORT_PREFIX_LEN); /* And skb->data now points to the extraction frame header. * Keep a pointer to it. */ @@ -205,10 +107,13 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb_pull(skb, ETH_HLEN); /* Remove from inet csum the extraction header */ - skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN); + skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN); - packing(extraction, &src_port, 46, 43, OCELOT_TAG_LEN, UNPACK, 0); - packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0); + ocelot_xfh_get_src_port(extraction, &src_port); + ocelot_xfh_get_qos_class(extraction, &qos_class); + ocelot_xfh_get_tag_type(extraction, &tag_type); + ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); + ocelot_xfh_get_cpuq(extraction, &cpuq); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -223,6 +128,40 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, skb->offload_fwd_mark = 1; skb->priority = qos_class; +#if IS_ENABLED(CONFIG_BRIDGE_MRP) + if (eth_hdr(skb)->h_proto == cpu_to_be16(ETH_P_MRP) && + cpuq & BIT(OCELOT_MRP_CPUQ)) + skb->offload_fwd_mark = 0; +#endif + + /* Ocelot switches copy frames unmodified to the CPU. However, it is + * possible for the user to request a VLAN modification through + * VCAP_IS1_ACT_VID_REPLACE_ENA. In this case, what will happen is that + * the VLAN ID field from the Extraction Header gets updated, but the + * 802.1Q header does not (the classified VLAN only becomes visible on + * egress through the "port tag" of front-panel ports). + * So, for traffic extracted by the CPU, we want to pick up the + * classified VLAN and manually replace the existing 802.1Q header from + * the packet with it, so that the operating system is always up to + * date with the result of tc-vlan actions. + * NOTE: In VLAN-unaware mode, we don't want to do that, we want the + * frame to remain unmodified, because the classified VLAN is always + * equal to the pvid of the ingress port and should not be used for + * processing. + */ + dp = dsa_slave_to_port(skb->dev); + vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q; + + if (dsa_port_is_vlan_filtering(dp) && + eth_hdr(skb)->h_proto == htons(vlan_tpid)) { + u16 dummy_vlan_tci; + + skb_push_rcsum(skb, ETH_HLEN); + __skb_vlan_pop(skb, &dummy_vlan_tci); + skb_pull_rcsum(skb, ETH_HLEN); + __vlan_hwaccel_put_tag(skb, htons(vlan_tpid), vlan_tci); + } + return skb; } @@ -231,10 +170,30 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN, + .overhead = OCELOT_TOTAL_TAG_LEN, + .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(ocelot_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT); -module_dsa_tag_driver(ocelot_netdev_ops); +static const struct dsa_device_ops seville_netdev_ops = { + .name = "seville", + .proto = DSA_TAG_PROTO_SEVILLE, + .xmit = seville_xmit, + .rcv = ocelot_rcv, + .overhead = OCELOT_TOTAL_TAG_LEN, + .promisc_on_master = true, +}; + +DSA_TAG_DRIVER(seville_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SEVILLE); + +static struct dsa_tag_driver *ocelot_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(ocelot_netdev_ops), + &DSA_TAG_DRIVER_NAME(seville_netdev_ops), +}; + +module_dsa_tag_drivers(ocelot_tag_driver_array); + +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c new file mode 100644 index 000000000000..5f3e8e124a82 --- /dev/null +++ b/net/dsa/tag_ocelot_8021q.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2020-2021 NXP Semiconductors + * + * An implementation of the software-defined tag_8021q.c tagger format, which + * also preserves full functionality under a vlan_filtering bridge. It does + * this by using the TCAM engines for: + * - pushing the RX VLAN as a second, outer tag, on egress towards the CPU port + * - redirecting towards the correct front port based on TX VLAN and popping + * that on egress + */ +#include <linux/dsa/8021q.h> +#include <soc/mscc/ocelot.h> +#include <soc/mscc/ocelot_ptp.h> +#include "dsa_priv.h" + +static struct sk_buff *ocelot_xmit_ptp(struct dsa_port *dp, + struct sk_buff *skb, + struct sk_buff *clone) +{ + struct ocelot *ocelot = dp->ds->priv; + struct ocelot_port *ocelot_port; + int port = dp->index; + u32 rew_op; + + if (!ocelot_can_inject(ocelot, 0)) + return NULL; + + ocelot_port = ocelot->ports[port]; + rew_op = ocelot_port->ptp_cmd; + + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + return NULL; +} + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_slave_to_port(netdev); + u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; + + /* TX timestamping was requested, so inject through MMIO */ + if (clone) + return ocelot_xmit_ptp(dp, skb, clone); + + return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff *ocelot_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int src_port, switch_id, qos_class; + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + src_port = dsa_8021q_rx_source_port(vid); + switch_id = dsa_8021q_rx_switch_id(vid); + qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + + skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); + if (!skb->dev) + return NULL; + + skb->offload_fwd_mark = 1; + skb->priority = qos_class; + + return skb; +} + +static const struct dsa_device_ops ocelot_8021q_netdev_ops = { + .name = "ocelot-8021q", + .proto = DSA_TAG_PROTO_OCELOT_8021Q, + .xmit = ocelot_xmit, + .rcv = ocelot_rcv, + .overhead = VLAN_HLEN, + .promisc_on_master = true, +}; + +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q); + +module_dsa_tag_driver(ocelot_8021q_netdev_ops); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 7066f5e697d7..88181b52f480 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -34,9 +34,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) __be16 *phdr; u16 hdr; - if (skb_cow_head(skb, QCA_HDR_LEN) < 0) - return NULL; - skb_push(skb, QCA_HDR_LEN); memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN); @@ -89,21 +86,11 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, return skb; } -static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = QCA_HDR_LEN; - *proto = ((__be16 *)skb->data)[0]; - - return 0; -} - static const struct dsa_device_ops qca_netdev_ops = { .name = "qca", .proto = DSA_TAG_PROTO_QCA, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .flow_dissect = qca_tag_flow_dissect, .overhead = QCA_HDR_LEN, }; diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index 7b63010fa87b..c17d39b4a1a0 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -12,9 +12,7 @@ * * The 2 bytes tag form a 16 bit big endian word. The exact * meaning has been guessed from packet dumps from ingress - * frames, as no working egress traffic has been available - * we do not know the format of the egress tags or if they - * are even supported. + * frames. */ #include <linux/etherdevice.h> @@ -36,17 +34,34 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - /* - * Just let it pass thru, we don't know if it is possible - * to tag a frame with the 0x8899 ethertype and direct it - * to a specific port, all attempts at reverse-engineering have - * ended up with the frames getting dropped. - * - * The VLAN set-up needs to restrict the frames to the right port. - * - * If you have documentation on the tagging format for RTL8366RB - * (tag type A) then please contribute. - */ + struct dsa_port *dp = dsa_slave_to_port(dev); + u8 *tag; + u16 *p; + u16 out; + + /* Pad out to at least 60 bytes */ + if (unlikely(eth_skb_pad(skb))) + return NULL; + if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0) + return NULL; + + netdev_dbg(dev, "add realtek tag to package to port %d\n", + dp->index); + skb_push(skb, RTL4_A_HDR_LEN); + + memmove(skb->data, skb->data + RTL4_A_HDR_LEN, 2 * ETH_ALEN); + tag = skb->data + 2 * ETH_ALEN; + + /* Set Ethertype */ + p = (u16 *)tag; + *p = htons(RTL4_A_ETHERTYPE); + + out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8); + /* The lower bits is the port numer */ + out |= (u8)dp->index; + p = (u16 *)(tag + 2); + *p = htons(out); + return skb; } @@ -106,22 +121,11 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, return skb; } -static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) -{ - *offset = RTL4_A_HDR_LEN; - /* Skip past the tag and fetch the encapsulated Ethertype */ - *proto = ((__be16 *)skb->data)[1]; - - return 0; -} - static const struct dsa_device_ops rtl4a_netdev_ops = { .name = "rtl4a", .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, - .flow_dissect = rtl4a_tag_flow_dissect, .overhead = RTL4_A_HDR_LEN, }; module_dsa_tag_driver(rtl4a_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9b4a4d719291..50496013cdb7 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -72,14 +72,21 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static bool sja1105_can_use_vlan_as_tags(const struct sk_buff *skb) { struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); + u16 vlan_tci; if (hdr->h_vlan_proto == htons(ETH_P_SJA1105)) return true; - if (hdr->h_vlan_proto != htons(ETH_P_8021Q)) + if (hdr->h_vlan_proto != htons(ETH_P_8021Q) && + !skb_vlan_tag_present(skb)) return false; - return vid_is_dsa_8021q(ntohs(hdr->h_vlan_TCI) & VLAN_VID_MASK); + if (skb_vlan_tag_present(skb)) + vlan_tci = skb_vlan_tag_get(skb); + else + vlan_tci = ntohs(hdr->h_vlan_TCI); + + return vid_is_dsa_8021q(vlan_tci & VLAN_VID_MASK); } /* This is the first time the tagger sees the frame on RX. @@ -283,7 +290,8 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, hdr = eth_hdr(skb); tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q); + is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); @@ -292,7 +300,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, if (is_tagged) { /* Normal traffic path. */ skb_push_rcsum(skb, ETH_HLEN); - __skb_vlan_pop(skb, &tci); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } skb_pull_rcsum(skb, ETH_HLEN); skb_reset_network_header(skb); skb_reset_transport_header(skb); @@ -333,6 +346,16 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* No tag added for management frames, all ok */ + if (unlikely(sja1105_is_link_local(skb))) + return; + + dsa_tag_generic_flow_dissect(skb, proto, offset); +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, @@ -340,6 +363,8 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .rcv = sja1105_rcv, .filter = sja1105_filter, .overhead = VLAN_HLEN, + .flow_dissect = sja1105_flow_dissect, + .promisc_on_master = true, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 4f8ab62f0208..5b97ede56a0f 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -13,42 +13,15 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; - int padlen; u8 *trailer; - /* - * We have to make sure that the trailer ends up as the very - * last 4 bytes of the packet. This means that we have to pad - * the packet to the minimum ethernet frame size, if necessary, - * before adding the trailer. - */ - padlen = 0; - if (skb->len < 60) - padlen = 60 - skb->len; - - nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC); - if (!nskb) - return NULL; - skb_reserve(nskb, NET_IP_ALIGN); - - skb_reset_mac_header(nskb); - skb_set_network_header(nskb, skb_network_header(skb) - skb->head); - skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head); - skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - consume_skb(skb); - - if (padlen) { - skb_put_zero(nskb, padlen); - } - - trailer = skb_put(nskb, 4); + trailer = skb_put(skb, 4); trailer[0] = 0x80; trailer[1] = 1 << dp->index; trailer[2] = 0x10; trailer[3] = 0x00; - return nskb; + return skb; } static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, @@ -83,6 +56,7 @@ static const struct dsa_device_ops trailer_netdev_ops = { .xmit = trailer_xmit, .rcv = trailer_rcv, .overhead = 4, + .tail_tag = true, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c new file mode 100644 index 000000000000..858cdf9d2913 --- /dev/null +++ b/net/dsa/tag_xrs700x.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * XRS700x tag format handling + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2020 NovaTech LLC + */ + +#include <linux/bitops.h> + +#include "dsa_priv.h" + +static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_port *partner, *dp = dsa_slave_to_port(dev); + u8 *trailer; + + trailer = skb_put(skb, 1); + trailer[0] = BIT(dp->index); + + if (dp->hsr_dev) + dsa_hsr_foreach_port(partner, dp->ds, dp->hsr_dev) + if (partner != dp) + trailer[0] |= BIT(partner->index); + + return skb; +} + +static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt) +{ + int source_port; + u8 *trailer; + + trailer = skb_tail_pointer(skb) - 1; + + source_port = ffs((int)trailer[0]) - 1; + + if (source_port < 0) + return NULL; + + skb->dev = dsa_master_find_slave(dev, 0, source_port); + if (!skb->dev) + return NULL; + + if (pskb_trim_rcsum(skb, skb->len - 1)) + return NULL; + + /* Frame is forwarded by hardware, don't forward in software. */ + skb->offload_fwd_mark = 1; + + return skb; +} + +static const struct dsa_device_ops xrs700x_netdev_ops = { + .name = "xrs700x", + .proto = DSA_TAG_PROTO_XRS700X, + .xmit = xrs700x_xmit, + .rcv = xrs700x_rcv, + .overhead = 1, + .tail_tag = true, +}; + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X); + +module_dsa_tag_driver(xrs700x_netdev_ops); |