diff options
Diffstat (limited to 'net/dsa')
49 files changed, 13955 insertions, 5695 deletions
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index d5bc6ac599ef..f86b30742122 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -1,34 +1,28 @@ # SPDX-License-Identifier: GPL-2.0-only -config HAVE_NET_DSA - def_bool y - depends on INET && NETDEVICES && !S390 - -# Drivers must select NET_DSA and the appropriate tagging format menuconfig NET_DSA tristate "Distributed Switch Architecture" - depends on HAVE_NET_DSA depends on BRIDGE || BRIDGE=n + depends on HSR || HSR=n + depends on INET && NETDEVICES select GRO_CELLS select NET_SWITCHDEV select PHYLINK select NET_DEVLINK + imply NET_SELFTESTS help Say Y if you want to enable support for the hardware switches supported by the Distributed Switch Architecture. if NET_DSA -# tagging formats -config NET_DSA_TAG_8021Q - tristate - select VLAN_8021Q - help - Unlike the other tagging protocols, the 802.1Q config option simply - provides helpers for other tagging implementations that might rely on - VLAN in one way or another. It is not a complete solution. +# Drivers must select the appropriate tagging format(s) - Drivers which use these helpers should select this as dependency. +config NET_DSA_TAG_NONE + tristate "No-op tag driver" + help + Say Y or M if you want to enable support for switches which don't tag + frames over the CPU port. config NET_DSA_TAG_AR9331 tristate "Tag driver for Atheros AR9331 SoC with built-in switch" @@ -47,6 +41,25 @@ config NET_DSA_TAG_BRCM Say Y if you want to enable support for tagging frames for the Broadcom switches which place the tag after the MAC source address. +config NET_DSA_TAG_BRCM_LEGACY + tristate "Tag driver for BCM63xx legacy switches using in-frame headers" + select NET_DSA_TAG_BRCM_COMMON + help + Say Y if you want to enable support for tagging frames for the + BCM63xx legacy switches which place the tag after the MAC source + address. + This tag is used in BCM63xx legacy switches which work without the + original FCS and length before the tag insertion. + +config NET_DSA_TAG_BRCM_LEGACY_FCS + tristate "Tag driver for BCM53xx legacy switches using in-frame headers" + select NET_DSA_TAG_BRCM_COMMON + help + Say Y if you want to enable support for tagging frames for the + BCM53xx legacy switches which place the tag after the MAC source + address. + This tag is used in BCM53xx legacy switches which expect original + FCS and length before the tag insertion to be present. config NET_DSA_TAG_BRCM_PREPEND tristate "Tag driver for Broadcom switches using prepended headers" @@ -56,20 +69,31 @@ 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. @@ -80,18 +104,40 @@ config NET_DSA_TAG_MTK Say Y or M if you want to enable support for tagging frames for Mediatek switches. +config NET_DSA_TAG_MXL_GSW1XX + tristate "Tag driver for MaxLinear GSW1xx switches" + help + The GSW1xx family of switches supports an 8-byte special tag which + can be used on the CPU port of the switch. + Say Y or M if you want to enable support for tagging frames for + MaxLinear GSW1xx switches. + config NET_DSA_TAG_KSZ - tristate "Tag driver for Microchip 8795/9477/9893 families of switches" + tristate "Tag driver for Microchip 8795/937x/9477/9893 families of switches" help Say Y if you want to enable support for tagging frames for the - Microchip 8795/9477/9893 families of switches. + Microchip 8795/937x/9477/9893 families of switches. 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" + 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" @@ -99,6 +145,26 @@ config NET_DSA_TAG_QCA Say Y or M if you want to enable support for tagging frames for the Qualcomm Atheros QCA8K switches. +config NET_DSA_TAG_RTL4_A + tristate "Tag driver for Realtek 4 byte protocol A tags" + help + Say Y or M if you want to enable support for tagging frames for the + Realtek switches with 4 byte protocol A tags, such as found in + the Realtek RTL8366RB. + +config NET_DSA_TAG_RTL8_4 + tristate "Tag driver for Realtek 8 byte protocol 4 tags" + help + Say Y or M if you want to enable support for tagging frames for Realtek + switches with 8 byte protocol 4 tags, such as the Realtek RTL8365MB-VC. + +config NET_DSA_TAG_RZN1_A5PSW + tristate "Tag driver for Renesas RZ/N1 A5PSW switch" + help + Say Y or M if you want to enable support for tagging frames for + Renesas RZ/N1 embedded switch that uses an 8 byte tag located after + destination MAC address. + config NET_DSA_TAG_LAN9303 tristate "Tag driver for SMSC/Microchip LAN9303 family of switches" help @@ -107,7 +173,6 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - select NET_DSA_TAG_8021Q select PACKING help Say Y or M if you want to enable support for tagging frames with the @@ -121,4 +186,22 @@ 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_VSC73XX_8021Q + tristate "Tag driver for Microchip/Vitesse VSC73xx family of switches, using VLAN" + help + Say Y or M if you want to enable support for tagging frames with a + custom VLAN-based header. + +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. + +config NET_DSA_TAG_YT921X + tristate "Tag driver for Motorcomm YT921x switches" + help + Say Y or M if you want to enable support for tagging frames for + Motorcomm YT921x switches. + endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 108486cfdeef..42d173f5a701 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,19 +1,46 @@ # SPDX-License-Identifier: GPL-2.0 + +# the stubs are built-in whenever DSA is built-in or module +ifdef CONFIG_NET_DSA +obj-y := stubs.o +endif + # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o +dsa_core-y += \ + conduit.o \ + devlink.o \ + dsa.o \ + netlink.o \ + port.o \ + switch.o \ + tag.o \ + tag_8021q.o \ + trace.o \ + user.o # tagging formats -obj-$(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-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +obj-$(CONFIG_NET_DSA_TAG_MXL_GSW1XX) += tag_mxl-gsw1xx.o +obj-$(CONFIG_NET_DSA_TAG_NONE) += tag_none.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_RTL4_A) += tag_rtl4_a.o +obj-$(CONFIG_NET_DSA_TAG_RTL8_4) += tag_rtl8_4.o +obj-$(CONFIG_NET_DSA_TAG_RZN1_A5PSW) += tag_rzn1_a5psw.o obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +obj-$(CONFIG_NET_DSA_TAG_VSC73XX_8021Q) += tag_vsc73xx_8021q.o +obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o +obj-$(CONFIG_NET_DSA_TAG_YT921X) += tag_yt921x.o + +# for tracing framework to find trace.h +CFLAGS_trace.o := -I$(src) diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c new file mode 100644 index 000000000000..a1b044467bd6 --- /dev/null +++ b/net/dsa/conduit.c @@ -0,0 +1,549 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Handling of a conduit device, switching frames via its switch fabric CPU port + * + * Copyright (c) 2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + */ + +#include <linux/ethtool.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <net/dsa.h> +#include <net/netdev_lock.h> + +#include "conduit.h" +#include "dsa.h" +#include "port.h" +#include "tag.h" + +static int dsa_conduit_get_regs_len(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int ret = 0; + int len; + + if (ops && ops->get_regs_len) { + netdev_lock_ops(dev); + len = ops->get_regs_len(dev); + netdev_unlock_ops(dev); + if (len < 0) + return len; + ret += len; + } + + ret += sizeof(struct ethtool_drvinfo); + ret += sizeof(struct ethtool_regs); + + if (ds->ops->get_regs_len) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return len; + ret += len; + } + + return ret; +} + +static void dsa_conduit_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_drvinfo *cpu_info; + struct ethtool_regs *cpu_regs; + int port = cpu_dp->index; + int len; + + if (ops && ops->get_regs_len && ops->get_regs) { + netdev_lock_ops(dev); + len = ops->get_regs_len(dev); + if (len < 0) { + netdev_unlock_ops(dev); + return; + } + regs->len = len; + ops->get_regs(dev, regs, data); + netdev_unlock_ops(dev); + data += regs->len; + } + + cpu_info = (struct ethtool_drvinfo *)data; + strscpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); + data += sizeof(*cpu_info); + cpu_regs = (struct ethtool_regs *)data; + data += sizeof(*cpu_regs); + + if (ds->ops->get_regs_len && ds->ops->get_regs) { + len = ds->ops->get_regs_len(ds, port); + if (len < 0) + return; + cpu_regs->len = len; + ds->ops->get_regs(ds, port, cpu_regs, data); + } +} + +static ssize_t dsa_conduit_append_port_stats(struct dsa_switch *ds, int port, + u64 *data, size_t start) +{ + int count; + + if (!ds->ops->get_sset_count) + return 0; + + count = ds->ops->get_sset_count(ds, port, ETH_SS_STATS); + if (count < 0) + return count; + + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, port, data + start); + + return count; +} + +static void dsa_conduit_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; + + if (ops && ops->get_sset_count && ops->get_ethtool_stats) { + netdev_lock_ops(dev); + mcount = ops->get_sset_count(dev, ETH_SS_STATS); + ops->get_ethtool_stats(dev, stats, data); + netdev_unlock_ops(dev); + } + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_stats(dp->ds, dp->index, + data, mcount); + if (count < 0) + return; + + mcount += count; + } +} + +static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, + struct ethtool_stats *stats, + u64 *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int count = 0; + + if (dev->phydev && (!ops || !ops->get_ethtool_phy_stats)) { + count = phy_ethtool_get_sset_count(dev->phydev); + if (count >= 0) + phy_ethtool_get_stats(dev->phydev, stats, data); + } else if (ops && ops->get_sset_count && ops->get_ethtool_phy_stats) { + netdev_lock_ops(dev); + count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); + ops->get_ethtool_phy_stats(dev, stats, data); + netdev_unlock_ops(dev); + } + + if (count < 0) + count = 0; + + if (ds->ops->get_ethtool_phy_stats) + ds->ops->get_ethtool_phy_stats(ds, port, data + count); +} + +static void dsa_conduit_append_port_sset_count(struct dsa_switch *ds, int port, + int sset, int *count) +{ + if (ds->ops->get_sset_count) + *count += ds->ops->get_sset_count(ds, port, sset); +} + +static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) +{ + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count = 0; + + netdev_lock_ops(dev); + if (sset == ETH_SS_PHY_STATS && dev->phydev && + (!ops || !ops->get_ethtool_phy_stats)) + count = phy_ethtool_get_sset_count(dev->phydev); + else if (ops && ops->get_sset_count) + count = ops->get_sset_count(dev, sset); + netdev_unlock_ops(dev); + + if (count < 0) + count = 0; + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + dsa_conduit_append_port_sset_count(dp->ds, dp->index, sset, + &count); + } + + return count; +} + +static ssize_t dsa_conduit_append_port_strings(struct dsa_switch *ds, int port, + u32 stringset, u8 *data, + size_t start) +{ + int len = ETH_GSTRING_LEN; + u8 pfx[8], *ndata; + int count, i; + + if (!ds->ops->get_strings) + return 0; + + snprintf(pfx, sizeof(pfx), "s%.2d_p%.2d", ds->index, port); + /* We do not want to be NULL-terminated, since this is a prefix */ + pfx[sizeof(pfx) - 1] = '_'; + ndata = data + start * len; + /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle + * the output after to prepend our CPU port prefix we + * constructed earlier + */ + ds->ops->get_strings(ds, port, stringset, ndata); + count = ds->ops->get_sset_count(ds, port, stringset); + if (count < 0) + return count; + + for (i = 0; i < count; i++) { + memmove(ndata + (i * len + sizeof(pfx)), + ndata + i * len, len - sizeof(pfx)); + memcpy(ndata + i * len, pfx, sizeof(pfx)); + } + + return count; +} + +static void dsa_conduit_get_strings(struct net_device *dev, u32 stringset, + u8 *data) +{ + struct dsa_port *dp, *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch_tree *dst = cpu_dp->dst; + int count, mcount = 0; + + netdev_lock_ops(dev); + if (stringset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) { + mcount = phy_ethtool_get_sset_count(dev->phydev); + if (mcount < 0) + mcount = 0; + else + phy_ethtool_get_strings(dev->phydev, data); + } else if (ops->get_sset_count && ops->get_strings) { + mcount = ops->get_sset_count(dev, stringset); + if (mcount < 0) + mcount = 0; + ops->get_strings(dev, stringset, data); + } + netdev_unlock_ops(dev); + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_dsa(dp) && !dsa_port_is_cpu(dp)) + continue; + + count = dsa_conduit_append_port_strings(dp->ds, dp->index, + stringset, data, + mcount); + if (count < 0) + return; + + mcount += count; + } +} + +/* Deny PTP operations on conduit if there is at least one switch in the tree + * that is PTP capable. + */ +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct dsa_switch_tree *dst; + struct dsa_port *dp; + + dst = ds->dst; + + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_supports_hwtstamp(dp)) { + NL_SET_ERR_MSG(extack, + "HW timestamping not allowed on DSA conduit when switch supports the operation"); + return -EBUSY; + } + } + + return 0; +} + +static int dsa_conduit_ethtool_setup(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct ethtool_ops *ops; + + if (netif_is_lag_master(dev)) + return 0; + + ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + cpu_dp->orig_ethtool_ops = dev->ethtool_ops; + if (cpu_dp->orig_ethtool_ops) + memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); + + ops->get_regs_len = dsa_conduit_get_regs_len; + ops->get_regs = dsa_conduit_get_regs; + ops->get_sset_count = dsa_conduit_get_sset_count; + ops->get_ethtool_stats = dsa_conduit_get_ethtool_stats; + ops->get_strings = dsa_conduit_get_strings; + ops->get_ethtool_phy_stats = dsa_conduit_get_ethtool_phy_stats; + + dev->ethtool_ops = ops; + + return 0; +} + +static void dsa_conduit_ethtool_teardown(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + if (netif_is_lag_master(dev)) + return; + + dev->ethtool_ops = cpu_dp->orig_ethtool_ops; + cpu_dp->orig_ethtool_ops = NULL; +} + +/* Keep the conduit always promiscuous if the tagging protocol requires that + * (garbles MAC DA) or if it doesn't support unicast filtering, case in which + * it would revert to promiscuous mode as soon as we call dev_uc_add() on it + * anyway. + */ +static void dsa_conduit_set_promiscuity(struct net_device *dev, int inc) +{ + const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; + + if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_conduit) + return; + + ASSERT_RTNL(); + + dev_set_promiscuity(dev, inc); +} + +static ssize_t tagging_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + + return sysfs_emit(buf, "%s\n", + dsa_tag_protocol_to_str(cpu_dp->tag_ops)); +} + +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; + const char *end = strchrnul(buf, '\n'), *name; + struct net_device *dev = to_net_dev(d); + struct dsa_port *cpu_dp = dev->dsa_ptr; + size_t len = end - buf; + int err; + + /* Empty string passed */ + if (!len) + return -ENOPROTOOPT; + + name = kstrndup(buf, len, GFP_KERNEL); + if (!name) + return -ENOMEM; + + old_tag_ops = cpu_dp->tag_ops; + new_tag_ops = dsa_tag_driver_get_by_name(name); + kfree(name); + /* Bad tagger name? */ + 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, 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_user_attrs[] = { + &dev_attr_tagging.attr, + NULL +}; + +static const struct attribute_group dsa_group = { + .name = "dsa", + .attrs = dsa_user_attrs, +}; + +static void dsa_conduit_reset_mtu(struct net_device *dev) +{ + int err; + + err = dev_set_mtu(dev, ETH_DATA_LEN); + if (err) + netdev_dbg(dev, + "Unable to reset MTU to exclude DSA overheads\n"); +} + +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp) +{ + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; + struct dsa_switch *ds = cpu_dp->ds; + struct device_link *consumer_link; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); + + /* The DSA conduit must use SET_NETDEV_DEV for this to work. */ + if (!netif_is_lag_master(dev)) { + 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)); + } + + /* The switch driver may not implement ->port_change_mtu(), case in + * which dsa_user_change_mtu() will not update the conduit MTU either, + * so we need to do that here. + */ + ret = dev_set_mtu(dev, mtu); + if (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 + * sent to the tag format's receive function. + */ + wmb(); + + dev->dsa_ptr = cpu_dp; + + dsa_conduit_set_promiscuity(dev, 1); + + ret = dsa_conduit_ethtool_setup(dev); + if (ret) + goto out_err_reset_promisc; + + ret = sysfs_create_group(&dev->dev.kobj, &dsa_group); + if (ret) + goto out_err_ethtool_teardown; + + return ret; + +out_err_ethtool_teardown: + dsa_conduit_ethtool_teardown(dev); +out_err_reset_promisc: + dsa_conduit_set_promiscuity(dev, -1); + return ret; +} + +void dsa_conduit_teardown(struct net_device *dev) +{ + sysfs_remove_group(&dev->dev.kobj, &dsa_group); + dsa_conduit_ethtool_teardown(dev); + dsa_conduit_reset_mtu(dev); + dsa_conduit_set_promiscuity(dev, -1); + + dev->dsa_ptr = NULL; + + /* If we used a tagging format that doesn't have an ethertype + * field, make sure that all packets from this point get sent + * without the tag and go through the regular receive path. + */ + wmb(); +} + +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) +{ + bool conduit_setup = false; + int err; + + if (!netdev_uses_dsa(lag_dev)) { + err = dsa_conduit_setup(lag_dev, cpu_dp); + if (err) + return err; + + conduit_setup = true; + } + + err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack); + if (err) { + NL_SET_ERR_MSG_WEAK_MOD(extack, "CPU port failed to join LAG"); + goto out_conduit_teardown; + } + + return 0; + +out_conduit_teardown: + if (conduit_setup) + dsa_conduit_teardown(lag_dev); + return err; +} + +/* Tear down a conduit if there isn't any other user port on it, + * optionally also destroying LAG information. + */ +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp) +{ + struct net_device *upper; + struct list_head *iter; + + dsa_port_lag_leave(cpu_dp, lag_dev); + + netdev_for_each_upper_dev_rcu(lag_dev, upper, iter) + if (dsa_user_dev_check(upper)) + return; + + dsa_conduit_teardown(lag_dev); +} diff --git a/net/dsa/conduit.h b/net/dsa/conduit.h new file mode 100644 index 000000000000..31f8834f54bb --- /dev/null +++ b/net/dsa/conduit.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_CONDUIT_H +#define __DSA_CONDUIT_H + +struct dsa_port; +struct net_device; +struct netdev_lag_upper_info; +struct netlink_ext_ack; + +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp); +void dsa_conduit_teardown(struct net_device *dev); +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp); +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); + +#endif diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c new file mode 100644 index 000000000000..ed342f345692 --- /dev/null +++ b/net/dsa/devlink.c @@ -0,0 +1,402 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DSA devlink handling + */ + +#include <net/dsa.h> +#include <net/devlink.h> + +#include "devlink.h" + +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, +}; + +int dsa_devlink_param_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_param_get) + return -EOPNOTSUPP; + + return ds->ops->devlink_param_get(ds, id, ctx); +} +EXPORT_SYMBOL_GPL(dsa_devlink_param_get); + +int dsa_devlink_param_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_param_set) + return -EOPNOTSUPP; + + return ds->ops->devlink_param_set(ds, id, ctx); +} +EXPORT_SYMBOL_GPL(dsa_devlink_param_set); + +int dsa_devlink_params_register(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count) +{ + return devlink_params_register(ds->devlink, params, params_count); +} +EXPORT_SYMBOL_GPL(dsa_devlink_params_register); + +void dsa_devlink_params_unregister(struct dsa_switch *ds, + const struct devlink_param *params, + size_t params_count) +{ + devlink_params_unregister(ds->devlink, params, params_count); +} +EXPORT_SYMBOL_GPL(dsa_devlink_params_unregister); + +int dsa_devlink_resource_register(struct dsa_switch *ds, + const char *resource_name, + u64 resource_size, + u64 resource_id, + u64 parent_resource_id, + const struct devlink_resource_size_params *size_params) +{ + int ret; + + devl_lock(ds->devlink); + ret = devl_resource_register(ds->devlink, resource_name, resource_size, + resource_id, parent_resource_id, + size_params); + devl_unlock(ds->devlink); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_devlink_resource_register); + +void dsa_devlink_resources_unregister(struct dsa_switch *ds) +{ + devlink_resources_unregister(ds->devlink); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resources_unregister); + +void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, + u64 resource_id, + devlink_resource_occ_get_t *occ_get, + void *occ_get_priv) +{ + devl_lock(ds->devlink); + devl_resource_occ_get_register(ds->devlink, resource_id, occ_get, + occ_get_priv); + devl_unlock(ds->devlink); +} +EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_register); + +void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, + u64 resource_id) +{ + devl_lock(ds->devlink); + devl_resource_occ_get_unregister(ds->devlink, resource_id); + devl_unlock(ds->devlink); +} +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); + +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; + struct dsa_switch *ds = dp->ds; + const unsigned char *id; + unsigned char len; + int err; + + memset(dlp, 0, sizeof(*dlp)); + devlink_port_init(dl, dlp); + + if (ds->ops->port_setup) { + err = ds->ops->port_setup(ds, dp->index); + if (err) + return 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; + + 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) { + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + return err; + } + + return 0; +} + +void dsa_port_devlink_teardown(struct dsa_port *dp) +{ + struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch *ds = dp->ds; + + devlink_port_unregister(dlp); + + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + + devlink_port_fini(dlp); +} + +void dsa_switch_devlink_register(struct dsa_switch *ds) +{ + devlink_register(ds->devlink); +} + +void dsa_switch_devlink_unregister(struct dsa_switch *ds) +{ + devlink_unregister(ds->devlink); +} + +int dsa_switch_devlink_alloc(struct dsa_switch *ds) +{ + struct dsa_devlink_priv *dl_priv; + struct devlink *dl; + + /* Add the switch to devlink before calling setup, so that setup can + * add dpipe tables + */ + dl = devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv), ds->dev); + if (!dl) + return -ENOMEM; + + ds->devlink = dl; + + dl_priv = devlink_priv(ds->devlink); + dl_priv->ds = ds; + + return 0; +} + +void dsa_switch_devlink_free(struct dsa_switch *ds) +{ + devlink_free(ds->devlink); + ds->devlink = NULL; +} diff --git a/net/dsa/devlink.h b/net/dsa/devlink.h new file mode 100644 index 000000000000..4d9f4f23705b --- /dev/null +++ b/net/dsa/devlink.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_DEVLINK_H +#define __DSA_DEVLINK_H + +struct dsa_port; +struct dsa_switch; + +int dsa_port_devlink_setup(struct dsa_port *dp); +void dsa_port_devlink_teardown(struct dsa_port *dp); +void dsa_switch_devlink_register(struct dsa_switch *ds); +void dsa_switch_devlink_unregister(struct dsa_switch *ds); +int dsa_switch_devlink_alloc(struct dsa_switch *ds); +void dsa_switch_devlink_free(struct dsa_switch *ds); + +#endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 1ce9ba8cf545..a20efabe778f 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1,133 +1,1381 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * net/dsa/dsa.c - Hardware switch handling + * DSA topology and switch handling + * * Copyright (c) 2008-2009 Marvell Semiconductor * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> */ #include <linux/device.h> +#include <linux/err.h> +#include <linux/if_hsr.h> #include <linux/list.h> -#include <linux/platform_device.h> -#include <linux/slab.h> #include <linux/module.h> -#include <linux/notifier.h> +#include <linux/netdevice.h> +#include <linux/slab.h> +#include <linux/rtnetlink.h> #include <linux/of.h> -#include <linux/of_mdio.h> -#include <linux/of_platform.h> #include <linux/of_net.h> -#include <linux/netdevice.h> -#include <linux/sysfs.h> -#include <linux/phy_fixed.h> -#include <linux/ptp_classify.h> -#include <linux/etherdevice.h> +#include <net/dsa_stubs.h> +#include <net/sch_generic.h> -#include "dsa_priv.h" +#include "conduit.h" +#include "devlink.h" +#include "dsa.h" +#include "netlink.h" +#include "port.h" +#include "switch.h" +#include "tag.h" +#include "user.h" -static LIST_HEAD(dsa_tag_drivers_list); -static DEFINE_MUTEX(dsa_tag_drivers_lock); +#define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG -static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +static DEFINE_MUTEX(dsa2_mutex); +LIST_HEAD(dsa_tree_list); + +static struct workqueue_struct *dsa_owq; + +/* Track the bridges with forwarding offload enabled */ +static unsigned long dsa_fwd_offloading_bridges; + +bool dsa_schedule_work(struct work_struct *work) { - /* Just return the original SKB */ - return skb; + return queue_work(dsa_owq, work); } -static const struct dsa_device_ops none_ops = { - .name = "none", - .proto = DSA_TAG_PROTO_NONE, - .xmit = dsa_slave_notag_xmit, - .rcv = NULL, -}; +void dsa_flush_workqueue(void) +{ + flush_workqueue(dsa_owq); +} +EXPORT_SYMBOL_GPL(dsa_flush_workqueue); -DSA_TAG_DRIVER(none_ops); +/** + * dsa_lag_map() - Map LAG structure to a linear LAG array + * @dst: Tree in which to record the mapping. + * @lag: LAG structure that is to be mapped to the tree's array. + * + * dsa_lag_id/dsa_lag_by_id 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 dsa_lag *lag) +{ + unsigned int id; -static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, - struct module *owner) + for (id = 1; id <= dst->lags_len; id++) { + if (!dsa_lag_by_id(dst, id)) { + dst->lags[id - 1] = lag; + lag->id = id; + 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: LAG structure 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 dsa_lag *lag) { - dsa_tag_driver->owner = owner; + unsigned int id; - mutex_lock(&dsa_tag_drivers_lock); - list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); - mutex_unlock(&dsa_tag_drivers_lock); + dsa_lags_foreach_id(id, dst) { + if (dsa_lag_by_id(dst, id) == lag) { + dst->lags[id - 1] = NULL; + lag->id = 0; + break; + } + } } -void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count, struct module *owner) +struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev) { - unsigned int i; + struct dsa_port *dp; - for (i = 0; i < count; i++) - dsa_tag_driver_register(dsa_tag_driver_array[i], owner); + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_lag_dev_get(dp) == lag_dev) + return dp->lag; + + return NULL; } -static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br) { - mutex_lock(&dsa_tag_drivers_lock); - list_del(&dsa_tag_driver->list); - mutex_unlock(&dsa_tag_drivers_lock); + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_bridge_dev_get(dp) == br) + return dp->bridge; + + return NULL; } -EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); -void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], - unsigned int count) +static int dsa_bridge_num_find(const struct net_device *bridge_dev) { - unsigned int i; + struct dsa_switch_tree *dst; + + list_for_each_entry(dst, &dsa_tree_list, list) { + struct dsa_bridge *bridge; + + bridge = dsa_tree_bridge_find(dst, bridge_dev); + if (bridge) + return bridge->num; + } - for (i = 0; i < count; i++) - dsa_tag_driver_unregister(dsa_tag_driver_array[i]); + return 0; } -EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); -const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) { - return ops->name; -}; + unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); + + /* Switches without FDB isolation support don't get unique + * bridge numbering + */ + if (!max) + return 0; + + if (!bridge_num) { + /* First port that requests FDB isolation or TX forwarding + * offload for this bridge + */ + bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, + DSA_MAX_NUM_OFFLOADING_BRIDGES, + 1); + if (bridge_num >= max) + return 0; + + set_bit(bridge_num, &dsa_fwd_offloading_bridges); + } + + return bridge_num; +} + +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num) +{ + /* Since we refcount bridges, we know that when we call this function + * it is no longer in use, so we can just go ahead and remove it from + * the bit mask. + */ + clear_bit(bridge_num, &dsa_fwd_offloading_bridges); +} + +struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) +{ + struct dsa_switch_tree *dst; + struct dsa_port *dp; + + list_for_each_entry(dst, &dsa_tree_list, list) { + if (dst->index != tree_index) + continue; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->index != sw_index) + continue; + + return dp->ds; + } + } + + return NULL; +} +EXPORT_SYMBOL_GPL(dsa_switch_find); + +static struct dsa_switch_tree *dsa_tree_find(int index) +{ + struct dsa_switch_tree *dst; + + list_for_each_entry(dst, &dsa_tree_list, list) + if (dst->index == index) + return dst; + + return NULL; +} + +static struct dsa_switch_tree *dsa_tree_alloc(int index) +{ + struct dsa_switch_tree *dst; + + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (!dst) + return NULL; + + dst->index = index; + + INIT_LIST_HEAD(&dst->rtable); + + INIT_LIST_HEAD(&dst->ports); + + INIT_LIST_HEAD(&dst->list); + list_add_tail(&dst->list, &dsa_tree_list); + + kref_init(&dst->refcount); + + return dst; +} + +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); +} + +static struct dsa_switch_tree *dsa_tree_get(struct dsa_switch_tree *dst) +{ + if (dst) + kref_get(&dst->refcount); + + return dst; +} + +static struct dsa_switch_tree *dsa_tree_touch(int index) +{ + struct dsa_switch_tree *dst; + + dst = dsa_tree_find(index); + if (dst) + return dsa_tree_get(dst); + else + return dsa_tree_alloc(index); +} + +static void dsa_tree_release(struct kref *ref) +{ + struct dsa_switch_tree *dst; + + dst = container_of(ref, struct dsa_switch_tree, refcount); + + dsa_tree_free(dst); +} + +static void dsa_tree_put(struct dsa_switch_tree *dst) +{ + if (dst) + kref_put(&dst->refcount, dsa_tree_release); +} + +static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, + struct device_node *dn) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dp->dn == dn) + return dp; + + return NULL; +} + +static struct dsa_link *dsa_link_touch(struct dsa_port *dp, + struct dsa_port *link_dp) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst; + struct dsa_link *dl; + + dst = ds->dst; + + list_for_each_entry(dl, &dst->rtable, list) + if (dl->dp == dp && dl->link_dp == link_dp) + return dl; + + dl = kzalloc(sizeof(*dl), GFP_KERNEL); + if (!dl) + return NULL; + + dl->dp = dp; + dl->link_dp = link_dp; + + INIT_LIST_HEAD(&dl->list); + list_add_tail(&dl->list, &dst->rtable); + + return dl; +} + +static bool dsa_port_setup_routing_table(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + struct device_node *dn = dp->dn; + struct of_phandle_iterator it; + struct dsa_port *link_dp; + struct dsa_link *dl; + int err; + + of_for_each_phandle(&it, err, dn, "link", NULL, 0) { + link_dp = dsa_tree_find_port_by_node(dst, it.node); + if (!link_dp) { + of_node_put(it.node); + return false; + } + + dl = dsa_link_touch(dp, link_dp); + if (!dl) { + of_node_put(it.node); + return false; + } + } + + return true; +} + +static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst) +{ + bool complete = true; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_dsa(dp)) { + complete = dsa_port_setup_routing_table(dp); + if (!complete) + break; + } + } + + return complete; +} + +static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_cpu(dp)) + return dp; + + return NULL; +} + +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst) +{ + struct device_node *ethernet; + struct net_device *conduit; + struct dsa_port *cpu_dp; + + cpu_dp = dsa_tree_find_first_cpu(dst); + ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); + conduit = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); + + return conduit; +} + +/* Assign the default CPU port (the first one in the tree) to all ports of the + * fabric which don't already have one as part of their own switch. + */ +static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp, *dp; + + cpu_dp = dsa_tree_find_first_cpu(dst); + if (!cpu_dp) { + pr_err("DSA: tree %d has no CPU port\n", dst->index); + return -EINVAL; + } + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->cpu_dp) + continue; + + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = cpu_dp; + } + + return 0; +} -const struct dsa_device_ops *dsa_tag_driver_get(int tag_protocol) +static struct dsa_port * +dsa_switch_preferred_default_local_cpu_port(struct dsa_switch *ds) { - struct dsa_tag_driver *dsa_tag_driver; - const struct dsa_device_ops *ops; - bool found = false; + struct dsa_port *cpu_dp; - request_module("%s%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); + if (!ds->ops->preferred_default_local_cpu_port) + return NULL; - mutex_lock(&dsa_tag_drivers_lock); - list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { - ops = dsa_tag_driver->ops; - if (ops->proto == tag_protocol) { - found = true; + cpu_dp = ds->ops->preferred_default_local_cpu_port(ds); + if (!cpu_dp) + return NULL; + + if (WARN_ON(!dsa_port_is_cpu(cpu_dp) || cpu_dp->ds != ds)) + return NULL; + + return cpu_dp; +} + +/* Perform initial assignment of CPU ports to user ports and DSA links in the + * fabric, giving preference to CPU ports local to each switch. Default to + * using the first CPU port in the switch tree if the port does not have a CPU + * port local to this switch. + */ +static int dsa_tree_setup_cpu_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *preferred_cpu_dp, *cpu_dp, *dp; + + list_for_each_entry(cpu_dp, &dst->ports, list) { + if (!dsa_port_is_cpu(cpu_dp)) + continue; + + preferred_cpu_dp = dsa_switch_preferred_default_local_cpu_port(cpu_dp->ds); + if (preferred_cpu_dp && preferred_cpu_dp != cpu_dp) + continue; + + /* Prefer a local CPU port */ + dsa_switch_for_each_port(dp, cpu_dp->ds) { + /* Prefer the first local CPU port found */ + if (dp->cpu_dp) + continue; + + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = cpu_dp; + } + } + + return dsa_tree_setup_default_cpu(dst); +} + +static void dsa_tree_teardown_cpu_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) + dp->cpu_dp = NULL; +} + +static int dsa_port_setup(struct dsa_port *dp) +{ + bool dsa_port_link_registered = false; + struct dsa_switch *ds = dp->ds; + bool dsa_port_enabled = false; + int err = 0; + + if (dp->setup) + return 0; + + err = dsa_port_devlink_setup(dp); + if (err) + return err; + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + dsa_port_disable(dp); + break; + case DSA_PORT_TYPE_CPU: + if (dp->dn) { + err = dsa_shared_port_link_register_of(dp); + if (err) + break; + dsa_port_link_registered = true; + } else { + dev_warn(ds->dev, + "skipping link registration for CPU port %d\n", + dp->index); + } + + err = dsa_port_enable(dp, NULL); + if (err) break; + dsa_port_enabled = true; + + break; + case DSA_PORT_TYPE_DSA: + if (dp->dn) { + err = dsa_shared_port_link_register_of(dp); + if (err) + break; + dsa_port_link_registered = true; + } else { + dev_warn(ds->dev, + "skipping link registration for DSA port %d\n", + dp->index); } + + err = dsa_port_enable(dp, NULL); + if (err) + break; + dsa_port_enabled = true; + + break; + case DSA_PORT_TYPE_USER: + of_get_mac_address(dp->dn, dp->mac); + err = dsa_user_create(dp); + break; } - if (found) { - if (!try_module_get(dsa_tag_driver->owner)) - ops = ERR_PTR(-ENOPROTOOPT); - } else { - ops = ERR_PTR(-ENOPROTOOPT); + if (err && dsa_port_enabled) + dsa_port_disable(dp); + if (err && dsa_port_link_registered) + dsa_shared_port_link_unregister_of(dp); + if (err) { + dsa_port_devlink_teardown(dp); + return err; } - mutex_unlock(&dsa_tag_drivers_lock); + dp->setup = true; - return ops; + return 0; } -void dsa_tag_driver_put(const struct dsa_device_ops *ops) +static void dsa_port_teardown(struct dsa_port *dp) { - struct dsa_tag_driver *dsa_tag_driver; + if (!dp->setup) + return; + + switch (dp->type) { + case DSA_PORT_TYPE_UNUSED: + break; + case DSA_PORT_TYPE_CPU: + dsa_port_disable(dp); + if (dp->dn) + dsa_shared_port_link_unregister_of(dp); + break; + case DSA_PORT_TYPE_DSA: + dsa_port_disable(dp); + if (dp->dn) + dsa_shared_port_link_unregister_of(dp); + break; + case DSA_PORT_TYPE_USER: + if (dp->user) { + dsa_user_destroy(dp->user); + dp->user = NULL; + } + break; + } + + dsa_port_devlink_teardown(dp); + + dp->setup = false; +} + +static int dsa_port_setup_as_unused(struct dsa_port *dp) +{ + dp->type = DSA_PORT_TYPE_UNUSED; + return dsa_port_setup(dp); +} + +static int dsa_switch_setup_tag_protocol(struct dsa_switch *ds) +{ + const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; + struct dsa_switch_tree *dst = ds->dst; + int err; + + if (tag_ops->proto == dst->default_proto) + goto connect; + + rtnl_lock(); + err = ds->ops->change_tag_protocol(ds, tag_ops->proto); + rtnl_unlock(); + if (err) { + dev_err(ds->dev, "Unable to use tag protocol \"%s\": %pe\n", + tag_ops->name, ERR_PTR(err)); + return err; + } + +connect: + if (tag_ops->connect) { + err = tag_ops->connect(ds); + if (err) + return err; + } + + if (ds->ops->connect_tag_protocol) { + err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); + if (err) { + dev_err(ds->dev, + "Unable to connect to tag protocol \"%s\": %pe\n", + tag_ops->name, ERR_PTR(err)); + goto disconnect; + } + } + + return 0; + +disconnect: + if (tag_ops->disconnect) + tag_ops->disconnect(ds); + + return err; +} + +static void dsa_switch_teardown_tag_protocol(struct dsa_switch *ds) +{ + const struct dsa_device_ops *tag_ops = ds->dst->tag_ops; + + if (tag_ops->disconnect) + tag_ops->disconnect(ds); +} + +static int dsa_switch_setup(struct dsa_switch *ds) +{ + int err; + + if (ds->setup) + return 0; + + /* Initialize ds->phys_mii_mask before registering the user MDIO bus + * driver and before ops->setup() has run, since the switch drivers and + * the user MDIO bus driver rely on these values for probing PHY + * devices or not + */ + ds->phys_mii_mask |= dsa_user_ports(ds); + + err = dsa_switch_devlink_alloc(ds); + if (err) + return err; + + err = dsa_switch_register_notifier(ds); + if (err) + goto devlink_free; + + ds->configure_vlan_while_not_filtering = true; + + err = ds->ops->setup(ds); + if (err < 0) + goto unregister_notifier; + + err = dsa_switch_setup_tag_protocol(ds); + if (err) + goto teardown; + + if (!ds->user_mii_bus && ds->ops->phy_read) { + ds->user_mii_bus = mdiobus_alloc(); + if (!ds->user_mii_bus) { + err = -ENOMEM; + goto teardown; + } + + dsa_user_mii_bus_init(ds); + + err = mdiobus_register(ds->user_mii_bus); + if (err < 0) + goto free_user_mii_bus; + } + + dsa_switch_devlink_register(ds); - mutex_lock(&dsa_tag_drivers_lock); - list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { - if (dsa_tag_driver->ops == ops) { - module_put(dsa_tag_driver->owner); + ds->setup = true; + return 0; + +free_user_mii_bus: + if (ds->user_mii_bus && ds->ops->phy_read) + mdiobus_free(ds->user_mii_bus); +teardown: + if (ds->ops->teardown) + ds->ops->teardown(ds); +unregister_notifier: + dsa_switch_unregister_notifier(ds); +devlink_free: + dsa_switch_devlink_free(ds); + return err; +} + +static void dsa_switch_teardown(struct dsa_switch *ds) +{ + if (!ds->setup) + return; + + dsa_switch_devlink_unregister(ds); + + if (ds->user_mii_bus && ds->ops->phy_read) { + mdiobus_unregister(ds->user_mii_bus); + mdiobus_free(ds->user_mii_bus); + ds->user_mii_bus = NULL; + } + + dsa_switch_teardown_tag_protocol(ds); + + if (ds->ops->teardown) + ds->ops->teardown(ds); + + dsa_switch_unregister_notifier(ds); + + dsa_switch_devlink_free(ds); + + ds->setup = false; +} + +/* First tear down the non-shared, then the shared ports. This ensures that + * all work items scheduled by our switchdev handlers for user ports have + * completed before we destroy the refcounting kept on the shared ports. + */ +static void dsa_tree_teardown_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) + dsa_port_teardown(dp); + + dsa_flush_workqueue(); + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) + dsa_port_teardown(dp); +} + +static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + dsa_switch_teardown(dp->ds); +} + +/* Bring shared ports up first, then non-shared ports */ +static int dsa_tree_setup_ports(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + int err = 0; + + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp)) { + err = dsa_port_setup(dp); + if (err) + goto teardown; + } + } + + list_for_each_entry(dp, &dst->ports, list) { + if (dsa_port_is_user(dp) || dsa_port_is_unused(dp)) { + err = dsa_port_setup(dp); + if (err) { + err = dsa_port_setup_as_unused(dp); + if (err) + goto teardown; + } + } + } + + return 0; + +teardown: + dsa_tree_teardown_ports(dst); + + return err; +} + +static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) +{ + struct dsa_port *dp; + int err = 0; + + list_for_each_entry(dp, &dst->ports, list) { + err = dsa_switch_setup(dp->ds); + if (err) { + dsa_tree_teardown_switches(dst); + break; + } + } + + return err; +} + +static int dsa_tree_setup_conduit(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp; + int err = 0; + + rtnl_lock(); + + dsa_tree_for_each_cpu_port(cpu_dp, dst) { + struct net_device *conduit = cpu_dp->conduit; + bool admin_up = (conduit->flags & IFF_UP) && + !qdisc_tx_is_noop(conduit); + + err = dsa_conduit_setup(conduit, cpu_dp); + if (err) break; + + /* Replay conduit state event */ + dsa_tree_conduit_admin_state_change(dst, conduit, admin_up); + dsa_tree_conduit_oper_state_change(dst, conduit, + netif_oper_up(conduit)); + } + + rtnl_unlock(); + + return err; +} + +static void dsa_tree_teardown_conduit(struct dsa_switch_tree *dst) +{ + struct dsa_port *cpu_dp; + + rtnl_lock(); + + dsa_tree_for_each_cpu_port(cpu_dp, dst) { + struct net_device *conduit = cpu_dp->conduit; + + /* Synthesizing an "admin down" state is sufficient for + * the switches to get a notification if the conduit is + * currently up and running. + */ + dsa_tree_conduit_admin_state_change(dst, conduit, false); + + dsa_conduit_teardown(conduit); + } + + rtnl_unlock(); +} + +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 void dsa_tree_teardown_routing_table(struct dsa_switch_tree *dst) +{ + struct dsa_link *dl, *next; + + list_for_each_entry_safe(dl, next, &dst->rtable, list) { + list_del(&dl->list); + kfree(dl); + } +} + +static int dsa_tree_setup(struct dsa_switch_tree *dst) +{ + bool complete; + int err; + + if (dst->setup) { + pr_err("DSA: tree %d already setup! Disjoint trees?\n", + dst->index); + return -EEXIST; + } + + complete = dsa_tree_setup_routing_table(dst); + if (!complete) + return 0; + + err = dsa_tree_setup_cpu_ports(dst); + if (err) + goto teardown_rtable; + + err = dsa_tree_setup_switches(dst); + if (err) + goto teardown_cpu_ports; + + err = dsa_tree_setup_ports(dst); + if (err) + goto teardown_switches; + + err = dsa_tree_setup_conduit(dst); + if (err) + goto teardown_ports; + + err = dsa_tree_setup_lags(dst); + if (err) + goto teardown_conduit; + + dst->setup = true; + + pr_info("DSA: tree %d setup\n", dst->index); + + return 0; + +teardown_conduit: + dsa_tree_teardown_conduit(dst); +teardown_ports: + dsa_tree_teardown_ports(dst); +teardown_switches: + dsa_tree_teardown_switches(dst); +teardown_cpu_ports: + dsa_tree_teardown_cpu_ports(dst); +teardown_rtable: + dsa_tree_teardown_routing_table(dst); + + return err; +} + +static void dsa_tree_teardown(struct dsa_switch_tree *dst) +{ + if (!dst->setup) + return; + + dsa_tree_teardown_lags(dst); + + dsa_tree_teardown_conduit(dst); + + dsa_tree_teardown_ports(dst); + + dsa_tree_teardown_switches(dst); + + dsa_tree_teardown_cpu_ports(dst); + + dsa_tree_teardown_routing_table(dst); + + pr_info("DSA: tree %d torn down\n", dst->index); + + dst->setup = false; +} + +static int dsa_tree_bind_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops) +{ + const struct dsa_device_ops *old_tag_ops = dst->tag_ops; + struct dsa_notifier_tag_proto_info info; + int err; + + dst->tag_ops = tag_ops; + + /* Notify the switches from this tree about the connection + * to the new tagger + */ + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_CONNECT, &info); + if (err && err != -EOPNOTSUPP) + goto out_disconnect; + + /* Notify the old tagger about the disconnection from this tree */ + info.tag_ops = old_tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + + return 0; + +out_disconnect: + info.tag_ops = tag_ops; + dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO_DISCONNECT, &info); + dst->tag_ops = old_tag_ops; + + return err; +} + +/* Since the dsa/tagging sysfs device attribute is per conduit, 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, + 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. + */ + dsa_tree_for_each_user_port(dp, dst) { + if (dsa_port_to_conduit(dp)->flags & IFF_UP) + goto out_unlock; + + if (dp->user->flags & IFF_UP) + goto out_unlock; + } + + /* Notify the tag protocol change */ + info.tag_ops = tag_ops; + err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); + if (err) + goto out_unwind_tagger; + + err = dsa_tree_bind_tag_proto(dst, tag_ops); + if (err) + goto out_unwind_tagger; + + 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 void dsa_tree_conduit_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit) +{ + struct dsa_notifier_conduit_state_info info; + struct dsa_port *cpu_dp = conduit->dsa_ptr; + + info.conduit = conduit; + info.operational = dsa_port_conduit_is_operational(cpu_dp); + + dsa_tree_notify(dst, DSA_NOTIFIER_CONDUIT_STATE_CHANGE, &info); +} + +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) +{ + struct dsa_port *cpu_dp = conduit->dsa_ptr; + bool notify = false; + + /* Don't keep track of admin state on LAG DSA conduits, + * but rather just of physical DSA conduits + */ + if (netif_is_lag_master(conduit)) + return; + + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (up && cpu_dp->conduit_oper_up)) + notify = true; + + cpu_dp->conduit_admin_up = up; + + if (notify) + dsa_tree_conduit_state_change(dst, conduit); +} + +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) +{ + struct dsa_port *cpu_dp = conduit->dsa_ptr; + bool notify = false; + + /* Don't keep track of oper state on LAG DSA conduits, + * but rather just of physical DSA conduits + */ + if (netif_is_lag_master(conduit)) + return; + + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (cpu_dp->conduit_admin_up && up)) + notify = true; + + cpu_dp->conduit_oper_up = up; + + if (notify) + dsa_tree_conduit_state_change(dst, conduit); +} + +static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) +{ + struct dsa_switch_tree *dst = ds->dst; + struct dsa_port *dp; + + dsa_switch_for_each_port(dp, ds) + if (dp->index == index) + return dp; + + dp = kzalloc(sizeof(*dp), GFP_KERNEL); + if (!dp) + return NULL; + + dp->ds = ds; + dp->index = index; + + mutex_init(&dp->addr_lists_lock); + mutex_init(&dp->vlans_lock); + INIT_LIST_HEAD(&dp->fdbs); + INIT_LIST_HEAD(&dp->mdbs); + INIT_LIST_HEAD(&dp->vlans); /* also initializes &dp->user_vlans */ + INIT_LIST_HEAD(&dp->list); + list_add_tail(&dp->list, &dst->ports); + + return dp; +} + +static int dsa_port_parse_user(struct dsa_port *dp, const char *name) +{ + dp->type = DSA_PORT_TYPE_USER; + dp->name = name; + + return 0; +} + +static int dsa_port_parse_dsa(struct dsa_port *dp) +{ + dp->type = DSA_PORT_TYPE_DSA; + + return 0; +} + +static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, + struct net_device *conduit) +{ + enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; + struct dsa_switch *mds, *ds = dp->ds; + unsigned int mdp_upstream; + struct dsa_port *mdp; + + /* It is possible to stack DSA switches onto one another when that + * happens the switch driver may want to know if its tagging protocol + * is going to work in such a configuration. + */ + if (dsa_user_dev_check(conduit)) { + mdp = dsa_user_to_port(conduit); + mds = mdp->ds; + mdp_upstream = dsa_upstream_port(mds, mdp->index); + tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, + DSA_TAG_PROTO_NONE); + } + + /* If the conduit device is not itself a DSA user in a disjoint DSA + * tree, then return immediately. + */ + return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); +} + +static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *conduit, + const char *user_protocol) +{ + const struct dsa_device_ops *tag_ops = NULL; + struct dsa_switch *ds = dp->ds; + struct dsa_switch_tree *dst = ds->dst; + enum dsa_tag_protocol default_proto; + + /* Find out which protocol the switch would prefer. */ + default_proto = dsa_get_tag_protocol(dp, conduit); + if (dst->default_proto) { + if (dst->default_proto != default_proto) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + return -EINVAL; + } + } else { + dst->default_proto = default_proto; + } + + /* See if the user wants to override that preference. */ + if (user_protocol) { + if (!ds->ops->change_tag_protocol) { + dev_err(ds->dev, "Tag protocol cannot be modified\n"); + return -EINVAL; + } + + tag_ops = dsa_tag_driver_get_by_name(user_protocol); + if (IS_ERR(tag_ops)) { + dev_warn(ds->dev, + "Failed to find a tagging driver for protocol %s, using default\n", + user_protocol); + tag_ops = NULL; } } - mutex_unlock(&dsa_tag_drivers_lock); + + if (!tag_ops) + tag_ops = dsa_tag_driver_get_by_id(default_proto); + + if (IS_ERR(tag_ops)) { + if (PTR_ERR(tag_ops) == -ENOPROTOOPT) + return -EPROBE_DEFER; + + dev_warn(ds->dev, "No tagger for this switch\n"); + return PTR_ERR(tag_ops); + } + + if (dst->tag_ops) { + if (dst->tag_ops != tag_ops) { + dev_err(ds->dev, + "A DSA switch tree can have only one tagging protocol\n"); + + dsa_tag_driver_put(tag_ops); + return -EINVAL; + } + + /* In the case of multiple CPU ports per switch, the tagging + * protocol is still reference-counted only per switch tree. + */ + dsa_tag_driver_put(tag_ops); + } else { + dst->tag_ops = tag_ops; + } + + dp->conduit = conduit; + dp->type = DSA_PORT_TYPE_CPU; + dsa_port_set_tag_protocol(dp, dst->tag_ops); + dp->dst = dst; + + /* At this point, the tree may be configured to use a different + * tagger than the one chosen by the switch driver during + * .setup, in the case when a user selects a custom protocol + * through the DT. + * + * This is resolved by syncing the driver with the tree in + * dsa_switch_setup_tag_protocol once .setup has run and the + * driver is ready to accept calls to .change_tag_protocol. If + * the driver does not support the custom protocol at that + * point, the tree is wholly rejected, thereby ensuring that the + * tree and driver are always in agreement on the protocol to + * use. + */ + return 0; +} + +static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) +{ + struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0); + const char *name = of_get_property(dn, "label", NULL); + bool link = of_property_read_bool(dn, "link"); + + dp->dn = dn; + + if (ethernet) { + struct net_device *conduit; + const char *user_protocol; + + conduit = of_find_net_device_by_node(ethernet); + of_node_put(ethernet); + if (!conduit) + return -EPROBE_DEFER; + + user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); + return dsa_port_parse_cpu(dp, conduit, user_protocol); + } + + if (link) + return dsa_port_parse_dsa(dp); + + return dsa_port_parse_user(dp, name); +} + +static int dsa_switch_parse_ports_of(struct dsa_switch *ds, + struct device_node *dn) +{ + struct device_node *ports, *port; + struct dsa_port *dp; + int err = 0; + u32 reg; + + ports = of_get_child_by_name(dn, "ports"); + if (!ports) { + /* The second possibility is "ethernet-ports" */ + ports = of_get_child_by_name(dn, "ethernet-ports"); + if (!ports) { + dev_err(ds->dev, "no ports child node found\n"); + return -EINVAL; + } + } + + for_each_available_child_of_node(ports, port) { + err = of_property_read_u32(port, "reg", ®); + if (err) { + of_node_put(port); + goto out_put_node; + } + + if (reg >= ds->num_ports) { + dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%u)\n", + port, reg, ds->num_ports); + of_node_put(port); + err = -EINVAL; + goto out_put_node; + } + + dp = dsa_to_port(ds, reg); + + err = dsa_port_parse_of(dp, port); + if (err) { + of_node_put(port); + goto out_put_node; + } + } + +out_put_node: + of_node_put(ports); + return err; } -static int dev_is_class(struct device *dev, void *class) +static int dsa_switch_parse_member_of(struct dsa_switch *ds, + struct device_node *dn) +{ + u32 m[2] = { 0, 0 }; + int sz; + + /* Don't error out if this optional property isn't found */ + sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2); + if (sz < 0 && sz != -EINVAL) + return sz; + + ds->index = m[1]; + + ds->dst = dsa_tree_touch(m[0]); + if (!ds->dst) + return -ENOMEM; + + if (dsa_switch_find(ds->dst->index, ds->index)) { + dev_err(ds->dev, + "A DSA switch with index %d already exists in tree %d\n", + ds->index, ds->dst->index); + return -EEXIST; + } + + if (ds->dst->last_switch < ds->index) + ds->dst->last_switch = ds->index; + + return 0; +} + +static int dsa_switch_touch_ports(struct dsa_switch *ds) +{ + struct dsa_port *dp; + int port; + + for (port = 0; port < ds->num_ports; port++) { + dp = dsa_port_touch(ds, port); + if (!dp) + return -ENOMEM; + } + + return 0; +} + +static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) +{ + int err; + + err = dsa_switch_parse_member_of(ds, dn); + if (err) + return err; + + err = dsa_switch_touch_ports(ds); + if (err) + return err; + + return dsa_switch_parse_ports_of(ds, dn); +} + +static int dev_is_class(struct device *dev, const void *class) { if (dev->class != NULL && !strcmp(dev->class->name, class)) return 1; @@ -145,7 +1393,7 @@ static struct device *dev_find_class(struct device *parent, char *class) return device_find_child(parent, class, dev_is_class); } -struct net_device *dsa_dev_to_net_device(struct device *dev) +static struct net_device *dsa_dev_to_net_device(struct device *dev) { struct device *d; @@ -162,101 +1410,257 @@ struct net_device *dsa_dev_to_net_device(struct device *dev) return NULL; } -EXPORT_SYMBOL_GPL(dsa_dev_to_net_device); -/* Determine if we should defer delivery of skb until we have a rx timestamp. - * - * Called from dsa_switch_rcv. For now, this will only work if tagging is - * enabled on the switch. Normally the MAC driver would retrieve the hardware - * timestamp when it reads the packet out of the hardware. However in a DSA - * switch, the DSA driver owning the interface to which the packet is - * delivered is never notified unless we do so here. - */ -static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, - struct sk_buff *skb) +static int dsa_port_parse(struct dsa_port *dp, const char *name, + struct device *dev) { - struct dsa_switch *ds = p->dp->ds; - unsigned int type; + if (!strcmp(name, "cpu")) { + struct net_device *conduit; - if (skb_headroom(skb) < ETH_HLEN) - return false; + conduit = dsa_dev_to_net_device(dev); + if (!conduit) + return -EPROBE_DEFER; - __skb_push(skb, ETH_HLEN); + dev_put(conduit); - type = ptp_classify_raw(skb); + return dsa_port_parse_cpu(dp, conduit, NULL); + } - __skb_pull(skb, ETH_HLEN); + if (!strcmp(name, "dsa")) + return dsa_port_parse_dsa(dp); - if (type == PTP_CLASS_NONE) - return false; + return dsa_port_parse_user(dp, name); +} - if (likely(ds->ops->port_rxtstamp)) - return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); +static int dsa_switch_parse_ports(struct dsa_switch *ds, + struct dsa_chip_data *cd) +{ + bool valid_name_found = false; + struct dsa_port *dp; + struct device *dev; + const char *name; + unsigned int i; + int err; - return false; + for (i = 0; i < DSA_MAX_PORTS; i++) { + name = cd->port_names[i]; + dev = cd->netdev[i]; + dp = dsa_to_port(ds, i); + + if (!name) + continue; + + err = dsa_port_parse(dp, name, dev); + if (err) + return err; + + valid_name_found = true; + } + + if (!valid_name_found && i == DSA_MAX_PORTS) + return -EINVAL; + + return 0; } -static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *unused) +static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) { - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct sk_buff *nskb = NULL; - struct pcpu_sw_netstats *s; - struct dsa_slave_priv *p; + int err; - if (unlikely(!cpu_dp)) { - kfree_skb(skb); - return 0; + ds->cd = cd; + + /* We don't support interconnected switches nor multiple trees via + * platform data, so this is the unique switch of the tree. + */ + ds->index = 0; + ds->dst = dsa_tree_touch(0); + if (!ds->dst) + return -ENOMEM; + + err = dsa_switch_touch_ports(ds); + if (err) + return err; + + return dsa_switch_parse_ports(ds, cd); +} + +static void dsa_switch_release_ports(struct dsa_switch *ds) +{ + struct dsa_mac_addr *a, *tmp; + struct dsa_port *dp, *next; + struct dsa_vlan *v, *n; + + dsa_switch_for_each_port_safe(dp, next, ds) { + /* These are either entries that upper layers lost track of + * (probably due to bugs), or installed through interfaces + * where one does not necessarily have to remove them, like + * ndo_dflt_fdb_add(). + */ + list_for_each_entry_safe(a, tmp, &dp->fdbs, list) { + dev_info(ds->dev, + "Cleaning up unicast address %pM vid %u from port %d\n", + a->addr, a->vid, dp->index); + list_del(&a->list); + kfree(a); + } + + list_for_each_entry_safe(a, tmp, &dp->mdbs, list) { + dev_info(ds->dev, + "Cleaning up multicast address %pM vid %u from port %d\n", + a->addr, a->vid, dp->index); + list_del(&a->list); + kfree(a); + } + + /* These are entries that upper layers have lost track of, + * probably due to bugs, but also due to dsa_port_do_vlan_del() + * having failed and the VLAN entry still lingering on. + */ + list_for_each_entry_safe(v, n, &dp->vlans, list) { + dev_info(ds->dev, + "Cleaning up vid %u from port %d\n", + v->vid, dp->index); + list_del(&v->list); + kfree(v); + } + + list_del(&dp->list); + kfree(dp); } +} - skb = skb_unshare(skb, GFP_ATOMIC); - if (!skb) - return 0; +static int dsa_switch_probe(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst; + struct dsa_chip_data *pdata; + struct device_node *np; + int err; + + if (!ds->dev) + return -ENODEV; + + pdata = ds->dev->platform_data; + np = ds->dev->of_node; + + if (!ds->num_ports) + return -EINVAL; + + if (np) { + err = dsa_switch_parse_of(ds, np); + if (err) + dsa_switch_release_ports(ds); + } else if (pdata) { + err = dsa_switch_parse(ds, pdata); + if (err) + dsa_switch_release_ports(ds); + } else { + err = -ENODEV; + } - nskb = cpu_dp->rcv(skb, dev, pt); - if (!nskb) { - kfree_skb(skb); - return 0; + if (err) + return err; + + dst = ds->dst; + dsa_tree_get(dst); + err = dsa_tree_setup(dst); + if (err) { + dsa_switch_release_ports(ds); + dsa_tree_put(dst); } - 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); + return err; +} + +int dsa_register_switch(struct dsa_switch *ds) +{ + int err; - 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); + mutex_lock(&dsa2_mutex); + err = dsa_switch_probe(ds); + dsa_tree_put(ds->dst); + mutex_unlock(&dsa2_mutex); - if (dsa_skb_defer_rx_timestamp(p, skb)) - return 0; + return err; +} +EXPORT_SYMBOL_GPL(dsa_register_switch); - gro_cells_receive(&p->gcells, skb); +static void dsa_switch_remove(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst = ds->dst; - return 0; + dsa_tree_teardown(dst); + dsa_switch_release_ports(ds); + dsa_tree_put(dst); } -#ifdef CONFIG_PM_SLEEP -static bool dsa_is_port_initialized(struct dsa_switch *ds, int p) +void dsa_unregister_switch(struct dsa_switch *ds) { - const struct dsa_port *dp = dsa_to_port(ds, p); + mutex_lock(&dsa2_mutex); + dsa_switch_remove(ds); + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_unregister_switch); - return dp->type == DSA_PORT_TYPE_USER && dp->slave; +/* If the DSA conduit chooses to unregister its net_device on .shutdown, DSA is + * blocking that operation from completion, due to the dev_hold taken inside + * netdev_upper_dev_link. Unlink the DSA user interfaces from being uppers of + * the DSA conduit, so that the system can reboot successfully. + */ +void dsa_switch_shutdown(struct dsa_switch *ds) +{ + struct net_device *conduit, *user_dev; + LIST_HEAD(close_list); + struct dsa_port *dp; + + mutex_lock(&dsa2_mutex); + + if (!ds->setup) + goto out; + + rtnl_lock(); + + dsa_switch_for_each_cpu_port(dp, ds) + list_add(&dp->conduit->close_list, &close_list); + + netif_close_many(&close_list, true); + + dsa_switch_for_each_user_port(dp, ds) { + conduit = dsa_port_to_conduit(dp); + user_dev = dp->user; + + netif_device_detach(user_dev); + netdev_upper_dev_unlink(conduit, user_dev); + } + + /* Disconnect from further netdevice notifiers on the conduit, + * since netdev_uses_dsa() will now return false. + */ + dsa_switch_for_each_cpu_port(dp, ds) + dp->conduit->dsa_ptr = NULL; + + rtnl_unlock(); +out: + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_switch_shutdown); + +#ifdef CONFIG_PM_SLEEP +static bool dsa_port_is_initialized(const struct dsa_port *dp) +{ + return dp->type == DSA_PORT_TYPE_USER && dp->user; } int dsa_switch_suspend(struct dsa_switch *ds) { - int i, ret = 0; + struct dsa_port *dp; + int ret = 0; - /* Suspend slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) + /* Suspend user network devices */ + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_suspend(dsa_to_port(ds, i)->slave); + ret = dsa_user_suspend(dp->user); if (ret) return ret; } @@ -270,7 +1674,8 @@ EXPORT_SYMBOL_GPL(dsa_switch_suspend); int dsa_switch_resume(struct dsa_switch *ds) { - int i, ret = 0; + struct dsa_port *dp; + int ret = 0; if (ds->ops->resume) ret = ds->ops->resume(ds); @@ -278,12 +1683,12 @@ int dsa_switch_resume(struct dsa_switch *ds) if (ret) return ret; - /* Resume slave network devices */ - for (i = 0; i < ds->num_ports; i++) { - if (!dsa_is_port_initialized(ds, i)) + /* Resume user network devices */ + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_resume(dsa_to_port(ds, i)->slave); + ret = dsa_user_resume(dp->user); if (ret) return ret; } @@ -293,133 +1698,152 @@ int dsa_switch_resume(struct dsa_switch *ds) EXPORT_SYMBOL_GPL(dsa_switch_resume); #endif -static struct packet_type dsa_pack_type __read_mostly = { - .type = cpu_to_be16(ETH_P_XDSA), - .func = dsa_switch_rcv, -}; - -static struct workqueue_struct *dsa_owq; - -bool dsa_schedule_work(struct work_struct *work) +struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { - return queue_work(dsa_owq, work); -} - -static ATOMIC_NOTIFIER_HEAD(dsa_notif_chain); + if (!netdev || !dsa_user_dev_check(netdev)) + return ERR_PTR(-ENODEV); -int register_dsa_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&dsa_notif_chain, nb); + return dsa_user_to_port(netdev); } -EXPORT_SYMBOL_GPL(register_dsa_notifier); +EXPORT_SYMBOL_GPL(dsa_port_from_netdev); -int unregister_dsa_notifier(struct notifier_block *nb) +bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b) { - return atomic_notifier_chain_unregister(&dsa_notif_chain, nb); + if (a->type != b->type) + return false; + + switch (a->type) { + case DSA_DB_PORT: + return a->dp == b->dp; + case DSA_DB_LAG: + return a->lag.dev == b->lag.dev; + case DSA_DB_BRIDGE: + return a->bridge.num == b->bridge.num; + default: + WARN_ON(1); + return false; + } } -EXPORT_SYMBOL_GPL(unregister_dsa_notifier); -int call_dsa_notifiers(unsigned long val, struct net_device *dev, - struct dsa_notifier_info *info) +bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db) { - info->dev = dev; - return atomic_notifier_call_chain(&dsa_notif_chain, val, info); + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; + + lockdep_assert_held(&dp->addr_lists_lock); + + list_for_each_entry(a, &dp->fdbs, list) { + if (!ether_addr_equal(a->addr, addr) || a->vid != vid) + continue; + + if (a->db.type == db.type && !dsa_db_equal(&a->db, &db)) + return true; + } + + return false; } -EXPORT_SYMBOL_GPL(call_dsa_notifiers); +EXPORT_SYMBOL_GPL(dsa_fdb_present_in_other_db); -int dsa_devlink_param_get(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) +bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; + struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_mac_addr *a; - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + lockdep_assert_held(&dp->addr_lists_lock); - if (!ds->ops->devlink_param_get) - return -EOPNOTSUPP; + list_for_each_entry(a, &dp->mdbs, list) { + if (!ether_addr_equal(a->addr, mdb->addr) || a->vid != mdb->vid) + continue; - return ds->ops->devlink_param_get(ds, id, ctx); + if (a->db.type == db.type && !dsa_db_equal(&a->db, &db)) + return true; + } + + return false; } -EXPORT_SYMBOL_GPL(dsa_devlink_param_get); +EXPORT_SYMBOL_GPL(dsa_mdb_present_in_other_db); -int dsa_devlink_param_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) +/* Helpers for switches without specific HSR offloads, but which can implement + * NETIF_F_HW_HSR_DUP because their tagger uses dsa_xmit_port_mask() + */ +int dsa_port_simple_hsr_validate(struct dsa_switch *ds, int port, + struct net_device *hsr, + struct netlink_ext_ack *extack) { - struct dsa_devlink_priv *dl_priv; - struct dsa_switch *ds; + enum hsr_port_type type; + int err; - dl_priv = devlink_priv(dl); - ds = dl_priv->ds; + err = hsr_get_port_type(hsr, dsa_to_port(ds, port)->user, &type); + if (err) + return err; - if (!ds->ops->devlink_param_set) + if (type != HSR_PT_SLAVE_A && type != HSR_PT_SLAVE_B) { + NL_SET_ERR_MSG_MOD(extack, + "Only HSR slave ports can be offloaded"); return -EOPNOTSUPP; + } - return ds->ops->devlink_param_set(ds, id, ctx); + return 0; } -EXPORT_SYMBOL_GPL(dsa_devlink_param_set); +EXPORT_SYMBOL_GPL(dsa_port_simple_hsr_validate); -int dsa_devlink_params_register(struct dsa_switch *ds, - const struct devlink_param *params, - size_t params_count) +int dsa_port_simple_hsr_join(struct dsa_switch *ds, int port, + struct net_device *hsr, + struct netlink_ext_ack *extack) { - return devlink_params_register(ds->devlink, params, params_count); -} -EXPORT_SYMBOL_GPL(dsa_devlink_params_register); + struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; + int err; -void dsa_devlink_params_unregister(struct dsa_switch *ds, - const struct devlink_param *params, - size_t params_count) -{ - devlink_params_unregister(ds->devlink, params, params_count); -} -EXPORT_SYMBOL_GPL(dsa_devlink_params_unregister); + err = dsa_port_simple_hsr_validate(ds, port, hsr, extack); + if (err) + return err; -int dsa_devlink_resource_register(struct dsa_switch *ds, - const char *resource_name, - u64 resource_size, - u64 resource_id, - u64 parent_resource_id, - const struct devlink_resource_size_params *size_params) -{ - return devlink_resource_register(ds->devlink, resource_name, - resource_size, resource_id, - parent_resource_id, - size_params); -} -EXPORT_SYMBOL_GPL(dsa_devlink_resource_register); + dsa_hsr_foreach_port(other_dp, ds, hsr) { + if (other_dp != dp) { + dp->user->features |= NETIF_F_HW_HSR_DUP; + other_dp->user->features |= NETIF_F_HW_HSR_DUP; + break; + } + } -void dsa_devlink_resources_unregister(struct dsa_switch *ds) -{ - devlink_resources_unregister(ds->devlink, NULL); + return 0; } -EXPORT_SYMBOL_GPL(dsa_devlink_resources_unregister); +EXPORT_SYMBOL_GPL(dsa_port_simple_hsr_join); -void dsa_devlink_resource_occ_get_register(struct dsa_switch *ds, - u64 resource_id, - devlink_resource_occ_get_t *occ_get, - void *occ_get_priv) +int dsa_port_simple_hsr_leave(struct dsa_switch *ds, int port, + struct net_device *hsr) { - return devlink_resource_occ_get_register(ds->devlink, resource_id, - occ_get, occ_get_priv); + struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; + + dsa_hsr_foreach_port(other_dp, ds, hsr) { + if (other_dp != dp) { + dp->user->features &= ~NETIF_F_HW_HSR_DUP; + other_dp->user->features &= ~NETIF_F_HW_HSR_DUP; + break; + } + } + + return 0; } -EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_register); +EXPORT_SYMBOL_GPL(dsa_port_simple_hsr_leave); + +static const struct dsa_stubs __dsa_stubs = { + .conduit_hwtstamp_validate = __dsa_conduit_hwtstamp_validate, +}; -void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds, - u64 resource_id) +static void dsa_register_stubs(void) { - devlink_resource_occ_get_unregister(ds->devlink, resource_id); + dsa_stubs = &__dsa_stubs; } -EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister); -struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) +static void dsa_unregister_stubs(void) { - if (!netdev || !dsa_slave_dev_check(netdev)) - return ERR_PTR(-ENODEV); - - return dsa_slave_to_port(netdev); + dsa_stubs = NULL; } -EXPORT_SYMBOL_GPL(dsa_port_from_netdev); static int __init dsa_init_module(void) { @@ -430,17 +1854,23 @@ static int __init dsa_init_module(void) if (!dsa_owq) return -ENOMEM; - rc = dsa_slave_register_notifier(); + rc = dsa_user_register_notifier(); if (rc) goto register_notifier_fail; dev_add_pack(&dsa_pack_type); - dsa_tag_driver_register(&DSA_TAG_DRIVER_NAME(none_ops), - THIS_MODULE); + rc = rtnl_link_register(&dsa_link_ops); + if (rc) + goto netlink_register_fail; + + dsa_register_stubs(); return 0; +netlink_register_fail: + dsa_user_unregister_notifier(); + dev_remove_pack(&dsa_pack_type); register_notifier_fail: destroy_workqueue(dsa_owq); @@ -450,9 +1880,11 @@ module_init(dsa_init_module); static void __exit dsa_cleanup_module(void) { - dsa_tag_driver_unregister(&DSA_TAG_DRIVER_NAME(none_ops)); + dsa_unregister_stubs(); + + rtnl_link_unregister(&dsa_link_ops); - dsa_slave_unregister_notifier(); + dsa_user_unregister_notifier(); dev_remove_pack(&dsa_pack_type); destroy_workqueue(dsa_owq); } @@ -462,3 +1894,4 @@ MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>"); MODULE_DESCRIPTION("Driver for Distributed Switch Architecture switch chips"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:dsa"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/net/dsa/dsa.h b/net/dsa/dsa.h new file mode 100644 index 000000000000..3cc7823e9ef3 --- /dev/null +++ b/net/dsa/dsa.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_H +#define __DSA_H + +#include <linux/list.h> +#include <linux/types.h> + +struct dsa_db; +struct dsa_device_ops; +struct dsa_lag; +struct dsa_switch_tree; +struct net_device; +struct work_struct; + +extern struct list_head dsa_tree_list; + +bool dsa_db_equal(const struct dsa_db *a, const struct dsa_db *b); +bool dsa_schedule_work(struct work_struct *work); +void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); +void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); +struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, + const struct net_device *lag_dev); +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst); +int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, + const struct dsa_device_ops *tag_ops, + const struct dsa_device_ops *old_tag_ops); +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num); +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br); + +#endif diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c deleted file mode 100644 index 076908fdd29b..000000000000 --- a/net/dsa/dsa2.c +++ /dev/null @@ -1,956 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/dsa/dsa2.c - Hardware switch handling, binding version 2 - * Copyright (c) 2008-2009 Marvell Semiconductor - * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> - * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> - */ - -#include <linux/device.h> -#include <linux/err.h> -#include <linux/list.h> -#include <linux/netdevice.h> -#include <linux/slab.h> -#include <linux/rtnetlink.h> -#include <linux/of.h> -#include <linux/of_net.h> -#include <net/devlink.h> - -#include "dsa_priv.h" - -static DEFINE_MUTEX(dsa2_mutex); -LIST_HEAD(dsa_tree_list); - -static const struct devlink_ops dsa_devlink_ops = { -}; - -struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) -{ - struct dsa_switch_tree *dst; - struct dsa_port *dp; - - list_for_each_entry(dst, &dsa_tree_list, list) { - if (dst->index != tree_index) - continue; - - list_for_each_entry(dp, &dst->ports, list) { - if (dp->ds->index != sw_index) - continue; - - return dp->ds; - } - } - - return NULL; -} -EXPORT_SYMBOL_GPL(dsa_switch_find); - -static struct dsa_switch_tree *dsa_tree_find(int index) -{ - struct dsa_switch_tree *dst; - - list_for_each_entry(dst, &dsa_tree_list, list) - if (dst->index == index) - return dst; - - return NULL; -} - -static struct dsa_switch_tree *dsa_tree_alloc(int index) -{ - struct dsa_switch_tree *dst; - - dst = kzalloc(sizeof(*dst), GFP_KERNEL); - if (!dst) - return NULL; - - dst->index = index; - - INIT_LIST_HEAD(&dst->rtable); - - INIT_LIST_HEAD(&dst->ports); - - INIT_LIST_HEAD(&dst->list); - list_add_tail(&dst->list, &dsa_tree_list); - - kref_init(&dst->refcount); - - return dst; -} - -static void dsa_tree_free(struct dsa_switch_tree *dst) -{ - list_del(&dst->list); - kfree(dst); -} - -static struct dsa_switch_tree *dsa_tree_get(struct dsa_switch_tree *dst) -{ - if (dst) - kref_get(&dst->refcount); - - return dst; -} - -static struct dsa_switch_tree *dsa_tree_touch(int index) -{ - struct dsa_switch_tree *dst; - - dst = dsa_tree_find(index); - if (dst) - return dsa_tree_get(dst); - else - return dsa_tree_alloc(index); -} - -static void dsa_tree_release(struct kref *ref) -{ - struct dsa_switch_tree *dst; - - dst = container_of(ref, struct dsa_switch_tree, refcount); - - dsa_tree_free(dst); -} - -static void dsa_tree_put(struct dsa_switch_tree *dst) -{ - if (dst) - kref_put(&dst->refcount, dsa_tree_release); -} - -static bool dsa_port_is_dsa(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_DSA; -} - -static bool dsa_port_is_cpu(struct dsa_port *port) -{ - return port->type == DSA_PORT_TYPE_CPU; -} - -static bool dsa_port_is_user(struct dsa_port *dp) -{ - return dp->type == DSA_PORT_TYPE_USER; -} - -static struct dsa_port *dsa_tree_find_port_by_node(struct dsa_switch_tree *dst, - struct device_node *dn) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dp->dn == dn) - return dp; - - return NULL; -} - -static struct dsa_link *dsa_link_touch(struct dsa_port *dp, - struct dsa_port *link_dp) -{ - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst; - struct dsa_link *dl; - - dst = ds->dst; - - list_for_each_entry(dl, &dst->rtable, list) - if (dl->dp == dp && dl->link_dp == link_dp) - return dl; - - dl = kzalloc(sizeof(*dl), GFP_KERNEL); - if (!dl) - return NULL; - - dl->dp = dp; - dl->link_dp = link_dp; - - INIT_LIST_HEAD(&dl->list); - list_add_tail(&dl->list, &dst->rtable); - - return dl; -} - -static bool dsa_port_setup_routing_table(struct dsa_port *dp) -{ - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - struct device_node *dn = dp->dn; - struct of_phandle_iterator it; - struct dsa_port *link_dp; - struct dsa_link *dl; - int err; - - of_for_each_phandle(&it, err, dn, "link", NULL, 0) { - link_dp = dsa_tree_find_port_by_node(dst, it.node); - if (!link_dp) { - of_node_put(it.node); - return false; - } - - dl = dsa_link_touch(dp, link_dp); - if (!dl) { - of_node_put(it.node); - return false; - } - } - - return true; -} - -static bool dsa_tree_setup_routing_table(struct dsa_switch_tree *dst) -{ - bool complete = true; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_is_dsa(dp)) { - complete = dsa_port_setup_routing_table(dp); - if (!complete) - break; - } - } - - return complete; -} - -static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - return dp; - - return NULL; -} - -static int dsa_tree_setup_default_cpu(struct dsa_switch_tree *dst) -{ - struct dsa_port *cpu_dp, *dp; - - cpu_dp = dsa_tree_find_first_cpu(dst); - if (!cpu_dp) { - pr_err("DSA: tree %d has no CPU port\n", dst->index); - return -EINVAL; - } - - /* Assign the default CPU port to all ports of the fabric */ - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) - dp->cpu_dp = cpu_dp; - - return 0; -} - -static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_user(dp) || dsa_port_is_dsa(dp)) - dp->cpu_dp = NULL; -} - -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 *dl = ds->devlink; - bool dsa_port_enabled = false; - int err = 0; - - if (dp->setup) - return 0; - - switch (dp->type) { - case DSA_PORT_TYPE_UNUSED: - dsa_port_disable(dp); - break; - case DSA_PORT_TYPE_CPU: - memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_CPU, - dp->index, false, 0, id, len); - 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; - dsa_port_link_registered = true; - - err = dsa_port_enable(dp, NULL); - if (err) - break; - dsa_port_enabled = true; - - break; - case DSA_PORT_TYPE_DSA: - memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_DSA, - dp->index, false, 0, id, len); - 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; - dsa_port_link_registered = true; - - err = dsa_port_enable(dp, NULL); - if (err) - break; - dsa_port_enabled = true; - - break; - case DSA_PORT_TYPE_USER: - memset(dlp, 0, sizeof(*dlp)); - devlink_port_attrs_set(dlp, DEVLINK_PORT_FLAVOUR_PHYSICAL, - dp->index, false, 0, id, len); - 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) - break; - - devlink_port_type_eth_set(dlp, dp->slave); - break; - } - - if (err && dsa_port_enabled) - 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; - - dp->setup = true; - - return 0; -} - -static void dsa_port_teardown(struct dsa_port *dp) -{ - struct devlink_port *dlp = &dp->devlink_port; - - if (!dp->setup) - return; - - 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; - } - break; - } - - dp->setup = false; -} - -static int dsa_switch_setup(struct dsa_switch *ds) -{ - struct dsa_devlink_priv *dl_priv; - int err; - - if (ds->setup) - return 0; - - /* Initialize ds->phys_mii_mask before registering the slave MDIO bus - * driver and before ops->setup() has run, since the switch drivers and - * the slave MDIO bus driver rely on these values for probing PHY - * devices or not - */ - ds->phys_mii_mask |= dsa_user_ports(ds); - - /* Add the switch to devlink before calling setup, so that setup can - * add dpipe tables - */ - ds->devlink = devlink_alloc(&dsa_devlink_ops, sizeof(*dl_priv)); - if (!ds->devlink) - return -ENOMEM; - dl_priv = devlink_priv(ds->devlink); - dl_priv->ds = ds; - - err = devlink_register(ds->devlink, ds->dev); - if (err) - goto free_devlink; - - err = dsa_switch_register_notifier(ds); - if (err) - goto unregister_devlink; - - err = ds->ops->setup(ds); - if (err < 0) - goto unregister_notifier; - - devlink_params_publish(ds->devlink); - - if (!ds->slave_mii_bus && ds->ops->phy_read) { - ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); - if (!ds->slave_mii_bus) { - err = -ENOMEM; - goto unregister_notifier; - } - - dsa_slave_mii_bus_init(ds); - - err = mdiobus_register(ds->slave_mii_bus); - if (err < 0) - goto unregister_notifier; - } - - ds->setup = true; - - return 0; - -unregister_notifier: - dsa_switch_unregister_notifier(ds); -unregister_devlink: - devlink_unregister(ds->devlink); -free_devlink: - devlink_free(ds->devlink); - ds->devlink = NULL; - - return err; -} - -static void dsa_switch_teardown(struct dsa_switch *ds) -{ - if (!ds->setup) - return; - - if (ds->slave_mii_bus && ds->ops->phy_read) - mdiobus_unregister(ds->slave_mii_bus); - - dsa_switch_unregister_notifier(ds); - - if (ds->ops->teardown) - ds->ops->teardown(ds); - - if (ds->devlink) { - devlink_unregister(ds->devlink); - devlink_free(ds->devlink); - ds->devlink = NULL; - } - - ds->setup = false; -} - -static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - int err; - - list_for_each_entry(dp, &dst->ports, list) { - err = dsa_switch_setup(dp->ds); - if (err) - goto teardown; - } - - list_for_each_entry(dp, &dst->ports, list) { - err = dsa_port_setup(dp); - if (err) - continue; - } - - return 0; - -teardown: - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); - - return err; -} - -static void dsa_tree_teardown_switches(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - dsa_port_teardown(dp); - - list_for_each_entry(dp, &dst->ports, list) - dsa_switch_teardown(dp->ds); -} - -static int dsa_tree_setup_master(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - int err; - - list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_is_cpu(dp)) { - err = dsa_master_setup(dp->master, dp); - if (err) - return err; - } - } - - return 0; -} - -static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) -{ - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dsa_port_is_cpu(dp)) - dsa_master_teardown(dp->master); -} - -static int dsa_tree_setup(struct dsa_switch_tree *dst) -{ - bool complete; - int err; - - if (dst->setup) { - pr_err("DSA: tree %d already setup! Disjoint trees?\n", - dst->index); - return -EEXIST; - } - - complete = dsa_tree_setup_routing_table(dst); - if (!complete) - return 0; - - err = dsa_tree_setup_default_cpu(dst); - if (err) - return err; - - err = dsa_tree_setup_switches(dst); - if (err) - goto teardown_default_cpu; - - err = dsa_tree_setup_master(dst); - if (err) - goto teardown_switches; - - dst->setup = true; - - pr_info("DSA: tree %d setup\n", dst->index); - - return 0; - -teardown_switches: - dsa_tree_teardown_switches(dst); -teardown_default_cpu: - dsa_tree_teardown_default_cpu(dst); - - return err; -} - -static void dsa_tree_teardown(struct dsa_switch_tree *dst) -{ - struct dsa_link *dl, *next; - - if (!dst->setup) - return; - - dsa_tree_teardown_master(dst); - - dsa_tree_teardown_switches(dst); - - dsa_tree_teardown_default_cpu(dst); - - list_for_each_entry_safe(dl, next, &dst->rtable, list) { - list_del(&dl->list); - kfree(dl); - } - - pr_info("DSA: tree %d torn down\n", dst->index); - - dst->setup = false; -} - -static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) -{ - struct dsa_switch_tree *dst = ds->dst; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds == ds && dp->index == index) - return dp; - - dp = kzalloc(sizeof(*dp), GFP_KERNEL); - if (!dp) - return NULL; - - dp->ds = ds; - dp->index = index; - - INIT_LIST_HEAD(&dp->list); - list_add_tail(&dp->list, &dst->ports); - - return dp; -} - -static int dsa_port_parse_user(struct dsa_port *dp, const char *name) -{ - if (!name) - name = "eth%d"; - - dp->type = DSA_PORT_TYPE_USER; - dp->name = name; - - return 0; -} - -static int dsa_port_parse_dsa(struct dsa_port *dp) -{ - dp->type = DSA_PORT_TYPE_DSA; - - return 0; -} - -static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, - struct net_device *master) -{ - enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; - struct dsa_switch *mds, *ds = dp->ds; - unsigned int mdp_upstream; - struct dsa_port *mdp; - - /* It is possible to stack DSA switches onto one another when that - * happens the switch driver may want to know if its tagging protocol - * is going to work in such a configuration. - */ - if (dsa_slave_dev_check(master)) { - mdp = dsa_slave_to_port(master); - mds = mdp->ds; - mdp_upstream = dsa_upstream_port(mds, mdp->index); - tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, - DSA_TAG_PROTO_NONE); - } - - /* If the master device is not itself a DSA slave in a disjoint DSA - * tree, then return immediately. - */ - return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); -} - -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); - } - - dp->master = master; - dp->type = DSA_PORT_TYPE_CPU; - dp->filter = tag_ops->filter; - dp->rcv = tag_ops->rcv; - dp->tag_ops = tag_ops; - dp->dst = dst; - - return 0; -} - -static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) -{ - struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0); - const char *name = of_get_property(dn, "label", NULL); - bool link = of_property_read_bool(dn, "link"); - - dp->dn = dn; - - if (ethernet) { - struct net_device *master; - - master = of_find_net_device_by_node(ethernet); - if (!master) - return -EPROBE_DEFER; - - return dsa_port_parse_cpu(dp, master); - } - - if (link) - return dsa_port_parse_dsa(dp); - - return dsa_port_parse_user(dp, name); -} - -static int dsa_switch_parse_ports_of(struct dsa_switch *ds, - struct device_node *dn) -{ - struct device_node *ports, *port; - struct dsa_port *dp; - int err = 0; - u32 reg; - - ports = of_get_child_by_name(dn, "ports"); - if (!ports) { - dev_err(ds->dev, "no ports child node found\n"); - return -EINVAL; - } - - for_each_available_child_of_node(ports, port) { - err = of_property_read_u32(port, "reg", ®); - if (err) - goto out_put_node; - - if (reg >= ds->num_ports) { - err = -EINVAL; - goto out_put_node; - } - - dp = dsa_to_port(ds, reg); - - err = dsa_port_parse_of(dp, port); - if (err) - goto out_put_node; - } - -out_put_node: - of_node_put(ports); - return err; -} - -static int dsa_switch_parse_member_of(struct dsa_switch *ds, - struct device_node *dn) -{ - u32 m[2] = { 0, 0 }; - int sz; - - /* Don't error out if this optional property isn't found */ - sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2); - if (sz < 0 && sz != -EINVAL) - return sz; - - ds->index = m[1]; - - ds->dst = dsa_tree_touch(m[0]); - if (!ds->dst) - return -ENOMEM; - - return 0; -} - -static int dsa_switch_touch_ports(struct dsa_switch *ds) -{ - struct dsa_port *dp; - int port; - - for (port = 0; port < ds->num_ports; port++) { - dp = dsa_port_touch(ds, port); - if (!dp) - return -ENOMEM; - } - - return 0; -} - -static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn) -{ - int err; - - err = dsa_switch_parse_member_of(ds, dn); - if (err) - return err; - - err = dsa_switch_touch_ports(ds); - if (err) - return err; - - return dsa_switch_parse_ports_of(ds, dn); -} - -static int dsa_port_parse(struct dsa_port *dp, const char *name, - struct device *dev) -{ - if (!strcmp(name, "cpu")) { - struct net_device *master; - - master = dsa_dev_to_net_device(dev); - if (!master) - return -EPROBE_DEFER; - - dev_put(master); - - return dsa_port_parse_cpu(dp, master); - } - - if (!strcmp(name, "dsa")) - return dsa_port_parse_dsa(dp); - - return dsa_port_parse_user(dp, name); -} - -static int dsa_switch_parse_ports(struct dsa_switch *ds, - struct dsa_chip_data *cd) -{ - bool valid_name_found = false; - struct dsa_port *dp; - struct device *dev; - const char *name; - unsigned int i; - int err; - - for (i = 0; i < DSA_MAX_PORTS; i++) { - name = cd->port_names[i]; - dev = cd->netdev[i]; - dp = dsa_to_port(ds, i); - - if (!name) - continue; - - err = dsa_port_parse(dp, name, dev); - if (err) - return err; - - valid_name_found = true; - } - - if (!valid_name_found && i == DSA_MAX_PORTS) - return -EINVAL; - - return 0; -} - -static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd) -{ - int err; - - ds->cd = cd; - - /* We don't support interconnected switches nor multiple trees via - * platform data, so this is the unique switch of the tree. - */ - ds->index = 0; - ds->dst = dsa_tree_touch(0); - if (!ds->dst) - return -ENOMEM; - - err = dsa_switch_touch_ports(ds); - if (err) - return err; - - return dsa_switch_parse_ports(ds, cd); -} - -static void dsa_switch_release_ports(struct dsa_switch *ds) -{ - struct dsa_switch_tree *dst = ds->dst; - struct dsa_port *dp, *next; - - list_for_each_entry_safe(dp, next, &dst->ports, list) { - if (dp->ds != ds) - continue; - list_del(&dp->list); - kfree(dp); - } -} - -static int dsa_switch_probe(struct dsa_switch *ds) -{ - struct dsa_switch_tree *dst; - struct dsa_chip_data *pdata; - struct device_node *np; - int err; - - if (!ds->dev) - return -ENODEV; - - pdata = ds->dev->platform_data; - np = ds->dev->of_node; - - if (!ds->num_ports) - return -EINVAL; - - if (np) { - err = dsa_switch_parse_of(ds, np); - if (err) - dsa_switch_release_ports(ds); - } else if (pdata) { - err = dsa_switch_parse(ds, pdata); - if (err) - dsa_switch_release_ports(ds); - } else { - err = -ENODEV; - } - - if (err) - return err; - - dst = ds->dst; - dsa_tree_get(dst); - err = dsa_tree_setup(dst); - if (err) { - dsa_switch_release_ports(ds); - dsa_tree_put(dst); - } - - return err; -} - -int dsa_register_switch(struct dsa_switch *ds) -{ - int err; - - mutex_lock(&dsa2_mutex); - err = dsa_switch_probe(ds); - dsa_tree_put(ds->dst); - mutex_unlock(&dsa2_mutex); - - return err; -} -EXPORT_SYMBOL_GPL(dsa_register_switch); - -static void dsa_switch_remove(struct dsa_switch *ds) -{ - struct dsa_switch_tree *dst = ds->dst; - - dsa_tree_teardown(dst); - dsa_switch_release_ports(ds); - dsa_tree_put(dst); -} - -void dsa_unregister_switch(struct dsa_switch *ds) -{ - mutex_lock(&dsa2_mutex); - dsa_switch_remove(ds); - mutex_unlock(&dsa2_mutex); -} -EXPORT_SYMBOL_GPL(dsa_unregister_switch); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h deleted file mode 100644 index adecf73bd608..000000000000 --- a/net/dsa/dsa_priv.h +++ /dev/null @@ -1,206 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/dsa/dsa_priv.h - Hardware switch handling - * Copyright (c) 2008-2009 Marvell Semiconductor - */ - -#ifndef __DSA_PRIV_H -#define __DSA_PRIV_H - -#include <linux/phy.h> -#include <linux/netdevice.h> -#include <linux/netpoll.h> -#include <net/dsa.h> -#include <net/gro_cells.h> - -enum { - DSA_NOTIFIER_AGEING_TIME, - DSA_NOTIFIER_BRIDGE_JOIN, - DSA_NOTIFIER_BRIDGE_LEAVE, - DSA_NOTIFIER_FDB_ADD, - DSA_NOTIFIER_FDB_DEL, - DSA_NOTIFIER_MDB_ADD, - DSA_NOTIFIER_MDB_DEL, - DSA_NOTIFIER_VLAN_ADD, - DSA_NOTIFIER_VLAN_DEL, - DSA_NOTIFIER_MTU, -}; - -/* DSA_NOTIFIER_AGEING_TIME */ -struct dsa_notifier_ageing_time_info { - struct switchdev_trans *trans; - unsigned int ageing_time; -}; - -/* DSA_NOTIFIER_BRIDGE_* */ -struct dsa_notifier_bridge_info { - struct net_device *br; - int tree_index; - int sw_index; - int port; -}; - -/* DSA_NOTIFIER_FDB_* */ -struct dsa_notifier_fdb_info { - int sw_index; - int port; - const unsigned char *addr; - u16 vid; -}; - -/* 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_VLAN_* */ -struct dsa_notifier_vlan_info { - const struct switchdev_obj_port_vlan *vlan; - struct switchdev_trans *trans; - int sw_index; - int port; -}; - -/* DSA_NOTIFIER_MTU */ -struct dsa_notifier_mtu_info { - bool propagate_upstream; - int sw_index; - int port; - int mtu; -}; - -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 *stats64; - - struct gro_cells gcells; - - /* DSA port data, such as switch, port index, etc. */ - struct dsa_port *dp; - -#ifdef CONFIG_NET_POLL_CONTROLLER - struct netpoll *netpoll; -#endif - - /* TC context */ - struct list_head mall_tc_list; -}; - -/* 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); - -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); - -static inline struct net_device *dsa_master_find_slave(struct net_device *dev, - int device, int port) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct dsa_switch_tree *dst = cpu_dp->dst; - struct dsa_port *dp; - - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds->index == device && dp->index == port && - dp->type == DSA_PORT_TYPE_USER) - return dp->slave; - - return NULL; -} - -/* port.c */ -int dsa_port_set_state(struct dsa_port *dp, u8 state, - struct switchdev_trans *trans); -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_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, - struct switchdev_trans *trans); -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_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, - u16 vid); -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); -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_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans); -int dsa_port_vlan_add(struct dsa_port *dp, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans); -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_link_register_of(struct dsa_port *dp); -void dsa_port_link_unregister_of(struct dsa_port *dp); -extern const struct phylink_mac_ops dsa_port_phylink_mac_ops; - -/* 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); - -static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->dp; -} - -static inline struct net_device * -dsa_slave_to_master(const struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dp->cpu_dp->master; -} - -/* switch.c */ -int dsa_switch_register_notifier(struct dsa_switch *ds); -void dsa_switch_unregister_notifier(struct dsa_switch *ds); - -/* dsa2.c */ -extern struct list_head dsa_tree_list; - -#endif diff --git a/net/dsa/master.c b/net/dsa/master.c deleted file mode 100644 index 480a61460c23..000000000000 --- a/net/dsa/master.c +++ /dev/null @@ -1,387 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * Handling of a master device, switching frames via its switch fabric CPU port - * - * Copyright (c) 2017 Savoir-faire Linux Inc. - * Vivien Didelot <vivien.didelot@savoirfairelinux.com> - */ - -#include "dsa_priv.h" - -static int dsa_master_get_regs_len(struct net_device *dev) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int ret = 0; - int len; - - if (ops->get_regs_len) { - len = ops->get_regs_len(dev); - if (len < 0) - return len; - ret += len; - } - - ret += sizeof(struct ethtool_drvinfo); - ret += sizeof(struct ethtool_regs); - - if (ds->ops->get_regs_len) { - len = ds->ops->get_regs_len(ds, port); - if (len < 0) - return len; - ret += len; - } - - return ret; -} - -static void dsa_master_get_regs(struct net_device *dev, - struct ethtool_regs *regs, void *data) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - struct ethtool_drvinfo *cpu_info; - struct ethtool_regs *cpu_regs; - int port = cpu_dp->index; - int len; - - if (ops->get_regs_len && ops->get_regs) { - len = ops->get_regs_len(dev); - if (len < 0) - return; - regs->len = len; - ops->get_regs(dev, regs, data); - data += regs->len; - } - - cpu_info = (struct ethtool_drvinfo *)data; - strlcpy(cpu_info->driver, "dsa", sizeof(cpu_info->driver)); - data += sizeof(*cpu_info); - cpu_regs = (struct ethtool_regs *)data; - data += sizeof(*cpu_regs); - - if (ds->ops->get_regs_len && ds->ops->get_regs) { - len = ds->ops->get_regs_len(ds, port); - if (len < 0) - return; - cpu_regs->len = len; - ds->ops->get_regs(ds, port, cpu_regs, data); - } -} - -static void dsa_master_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int count = 0; - - if (ops->get_sset_count && ops->get_ethtool_stats) { - count = ops->get_sset_count(dev, ETH_SS_STATS); - ops->get_ethtool_stats(dev, stats, data); - } - - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, port, data + count); -} - -static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int count = 0; - - if (dev->phydev && !ops->get_ethtool_phy_stats) { - count = phy_ethtool_get_sset_count(dev->phydev); - if (count >= 0) - phy_ethtool_get_stats(dev->phydev, stats, data); - } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) { - count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); - ops->get_ethtool_phy_stats(dev, stats, data); - } - - if (count < 0) - count = 0; - - if (ds->ops->get_ethtool_phy_stats) - ds->ops->get_ethtool_phy_stats(ds, port, data + count); -} - -static int dsa_master_get_sset_count(struct net_device *dev, int sset) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int count = 0; - - if (sset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) - count = phy_ethtool_get_sset_count(dev->phydev); - else if (ops->get_sset_count) - count = ops->get_sset_count(dev, sset); - - if (count < 0) - count = 0; - - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, cpu_dp->index, sset); - - return count; -} - -static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; - struct dsa_switch *ds = cpu_dp->ds; - int port = cpu_dp->index; - int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; - uint8_t pfx[4]; - uint8_t *ndata; - - snprintf(pfx, sizeof(pfx), "p%.2d", port); - /* We do not want to be NULL-terminated, since this is a prefix */ - pfx[sizeof(pfx) - 1] = '_'; - - if (stringset == ETH_SS_PHY_STATS && dev->phydev && - !ops->get_ethtool_phy_stats) { - mcount = phy_ethtool_get_sset_count(dev->phydev); - if (mcount < 0) - mcount = 0; - else - phy_ethtool_get_strings(dev->phydev, data); - } else if (ops->get_sset_count && ops->get_strings) { - mcount = ops->get_sset_count(dev, stringset); - if (mcount < 0) - mcount = 0; - ops->get_strings(dev, stringset, data); - } - - if (ds->ops->get_strings) { - ndata = data + mcount * len; - /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle - * the output after to prepend our CPU port prefix we - * constructed earlier - */ - ds->ops->get_strings(ds, port, stringset, ndata); - count = ds->ops->get_sset_count(ds, port, stringset); - for (i = 0; i < count; i++) { - memmove(ndata + (i * len + sizeof(pfx)), - ndata + i * len, len - sizeof(pfx)); - memcpy(ndata + i * len, pfx, sizeof(pfx)); - } - } -} - -static int dsa_master_get_phys_port_name(struct net_device *dev, - char *name, size_t len) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - - if (snprintf(name, len, "p%d", cpu_dp->index) >= len) - return -EINVAL; - - return 0; -} - -static int dsa_master_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct dsa_switch *ds = cpu_dp->ds; - struct dsa_switch_tree *dst; - int err = -EOPNOTSUPP; - struct dsa_port *dp; - - dst = ds->dst; - - switch (cmd) { - case SIOCGHWTSTAMP: - case SIOCSHWTSTAMP: - /* Deny PTP operations on master if there is at least one - * switch in the tree that is PTP capable. - */ - list_for_each_entry(dp, &dst->ports, list) - if (dp->ds->ops->port_hwtstamp_get || - dp->ds->ops->port_hwtstamp_set) - return -EBUSY; - break; - } - - if (cpu_dp->orig_ndo_ops && cpu_dp->orig_ndo_ops->ndo_do_ioctl) - err = cpu_dp->orig_ndo_ops->ndo_do_ioctl(dev, ifr, cmd); - - return err; -} - -static int dsa_master_ethtool_setup(struct net_device *dev) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct dsa_switch *ds = cpu_dp->ds; - struct ethtool_ops *ops; - - ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); - if (!ops) - return -ENOMEM; - - cpu_dp->orig_ethtool_ops = dev->ethtool_ops; - if (cpu_dp->orig_ethtool_ops) - memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); - - ops->get_regs_len = dsa_master_get_regs_len; - ops->get_regs = dsa_master_get_regs; - ops->get_sset_count = dsa_master_get_sset_count; - ops->get_ethtool_stats = dsa_master_get_ethtool_stats; - ops->get_strings = dsa_master_get_strings; - ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats; - - dev->ethtool_ops = ops; - - return 0; -} - -static void dsa_master_ethtool_teardown(struct net_device *dev) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - - dev->ethtool_ops = cpu_dp->orig_ethtool_ops; - cpu_dp->orig_ethtool_ops = NULL; -} - -static int dsa_master_ndo_setup(struct net_device *dev) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - struct dsa_switch *ds = cpu_dp->ds; - struct net_device_ops *ops; - - if (dev->netdev_ops->ndo_get_phys_port_name) - return 0; - - ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); - if (!ops) - return -ENOMEM; - - cpu_dp->orig_ndo_ops = dev->netdev_ops; - if (cpu_dp->orig_ndo_ops) - memcpy(ops, cpu_dp->orig_ndo_ops, sizeof(*ops)); - - ops->ndo_get_phys_port_name = dsa_master_get_phys_port_name; - ops->ndo_do_ioctl = dsa_master_ioctl; - - dev->netdev_ops = ops; - - return 0; -} - -static void dsa_master_ndo_teardown(struct net_device *dev) -{ - struct dsa_port *cpu_dp = dev->dsa_ptr; - - if (cpu_dp->orig_ndo_ops) - dev->netdev_ops = cpu_dp->orig_ndo_ops; - cpu_dp->orig_ndo_ops = NULL; -} - -static ssize_t tagging_show(struct device *d, struct device_attribute *attr, - char *buf) -{ - struct net_device *dev = to_net_dev(d); - struct dsa_port *cpu_dp = dev->dsa_ptr; - - return sprintf(buf, "%s\n", - dsa_tag_protocol_to_str(cpu_dp->tag_ops)); -} -static DEVICE_ATTR_RO(tagging); - -static struct attribute *dsa_slave_attrs[] = { - &dev_attr_tagging.attr, - NULL -}; - -static const struct attribute_group dsa_group = { - .name = "dsa", - .attrs = dsa_slave_attrs, -}; - -static void dsa_master_reset_mtu(struct net_device *dev) -{ - int err; - - rtnl_lock(); - err = dev_set_mtu(dev, ETH_DATA_LEN); - if (err) - netdev_dbg(dev, - "Unable to reset MTU to exclude DSA overheads\n"); - rtnl_unlock(); -} - -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 ret; - - rtnl_lock(); - ret = dev_set_mtu(dev, ETH_DATA_LEN + cpu_dp->tag_ops->overhead); - rtnl_unlock(); - if (ret) - netdev_warn(dev, "error %d setting MTU to include DSA overhead\n", - ret); - - /* If we use a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point on get - * sent to the tag format's receive function. - */ - wmb(); - - dev->dsa_ptr = cpu_dp; - lockdep_set_class(&dev->addr_list_lock, - &dsa_master_addr_list_lock_key); - ret = dsa_master_ethtool_setup(dev); - if (ret) - return ret; - - ret = dsa_master_ndo_setup(dev); - if (ret) - goto out_err_ethtool_teardown; - - ret = sysfs_create_group(&dev->dev.kobj, &dsa_group); - if (ret) - goto out_err_ndo_teardown; - - return ret; - -out_err_ndo_teardown: - dsa_master_ndo_teardown(dev); -out_err_ethtool_teardown: - dsa_master_ethtool_teardown(dev); - return ret; -} - -void dsa_master_teardown(struct net_device *dev) -{ - sysfs_remove_group(&dev->dev.kobj, &dsa_group); - dsa_master_ndo_teardown(dev); - dsa_master_ethtool_teardown(dev); - dsa_master_reset_mtu(dev); - - dev->dsa_ptr = NULL; - - /* If we used a tagging format that doesn't have an ethertype - * field, make sure that all packets from this point get sent - * without the tag and go through the regular receive path. - */ - wmb(); -} diff --git a/net/dsa/netlink.c b/net/dsa/netlink.c new file mode 100644 index 000000000000..1332e56349e5 --- /dev/null +++ b/net/dsa/netlink.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2022 NXP + */ +#include <linux/netdevice.h> +#include <net/rtnetlink.h> + +#include "netlink.h" +#include "user.h" + +static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = { + [IFLA_DSA_CONDUIT] = { .type = NLA_U32 }, +}; + +static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + int err; + + if (!data) + return 0; + + if (data[IFLA_DSA_CONDUIT]) { + u32 ifindex = nla_get_u32(data[IFLA_DSA_CONDUIT]); + struct net_device *conduit; + + conduit = __dev_get_by_index(dev_net(dev), ifindex); + if (!conduit) + return -EINVAL; + + err = dsa_user_change_conduit(dev, conduit, extack); + if (err) + return err; + } + + return 0; +} + +static size_t dsa_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(u32)) + /* IFLA_DSA_CONDUIT */ + 0; +} + +static int dsa_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + + if (nla_put_u32(skb, IFLA_DSA_CONDUIT, conduit->ifindex)) + return -EMSGSIZE; + + return 0; +} + +struct rtnl_link_ops dsa_link_ops __read_mostly = { + .kind = "dsa", + .priv_size = sizeof(struct dsa_port), + .maxtype = IFLA_DSA_MAX, + .policy = dsa_policy, + .changelink = dsa_changelink, + .get_size = dsa_get_size, + .fill_info = dsa_fill_info, + .netns_refund = true, +}; diff --git a/net/dsa/netlink.h b/net/dsa/netlink.h new file mode 100644 index 000000000000..7eda2fa15722 --- /dev/null +++ b/net/dsa/netlink.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_NETLINK_H +#define __DSA_NETLINK_H + +extern struct rtnl_link_ops dsa_link_ops __read_mostly; + +#endif diff --git a/net/dsa/port.c b/net/dsa/port.c index e23ece229c7e..ca3a7f52229b 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -7,55 +7,145 @@ */ #include <linux/if_bridge.h> +#include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include "dsa_priv.h" +#include "dsa.h" +#include "port.h" +#include "switch.h" +#include "tag_8021q.h" +#include "user.h" + +/** + * 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) +{ + return dsa_tree_notify(dp->ds->dst, e, v); +} + +static void dsa_port_notify_bridge_fdb_flush(const struct dsa_port *dp, u16 vid) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + struct switchdev_notifier_fdb_info info = { + .vid = vid, + }; + + /* When the port becomes standalone it has already left the bridge. + * Don't notify the bridge in that case. + */ + if (!brport_dev) + return; + + call_switchdev_notifiers(SWITCHDEV_FDB_FLUSH_TO_BRIDGE, + brport_dev, &info.info, NULL); +} + +static void dsa_port_fast_age(const struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->port_fast_age) + return; + + ds->ops->port_fast_age(ds, dp->index); -static int dsa_broadcast(unsigned long e, void *v) + /* flush all VLANs */ + dsa_port_notify_bridge_fdb_flush(dp, 0); +} + +static int dsa_port_vlan_fast_age(const struct dsa_port *dp, u16 vid) +{ + struct dsa_switch *ds = dp->ds; + int err; + + if (!ds->ops->port_vlan_fast_age) + return -EOPNOTSUPP; + + err = ds->ops->port_vlan_fast_age(ds, dp->index, vid); + + if (!err) + dsa_port_notify_bridge_fdb_flush(dp, vid); + + return err; +} + +static int dsa_port_msti_fast_age(const struct dsa_port *dp, u16 msti) { - struct dsa_switch_tree *dst; - int err = 0; + DECLARE_BITMAP(vids, VLAN_N_VID) = { 0 }; + int err, vid; - list_for_each_entry(dst, &dsa_tree_list, list) { - struct raw_notifier_head *nh = &dst->nh; + err = br_mst_get_info(dsa_port_bridge_dev_get(dp), msti, vids); + if (err) + return err; - err = raw_notifier_call_chain(nh, e, v); - err = notifier_to_errno(err); + for_each_set_bit(vid, vids, VLAN_N_VID) { + err = dsa_port_vlan_fast_age(dp, vid); if (err) - break; + return err; } - return err; + return 0; } -static int dsa_port_notify(const struct dsa_port *dp, unsigned long e, void *v) +static bool dsa_port_can_configure_learning(struct dsa_port *dp) { - struct raw_notifier_head *nh = &dp->ds->dst->nh; + struct switchdev_brport_flags flags = { + .mask = BR_LEARNING, + }; + struct dsa_switch *ds = dp->ds; + int err; + + if (!ds->ops->port_bridge_flags || !ds->ops->port_pre_bridge_flags) + return false; + + err = ds->ops->port_pre_bridge_flags(ds, dp->index, flags, NULL); + return !err; +} + +bool dsa_port_supports_hwtstamp(struct dsa_port *dp) +{ + struct kernel_hwtstamp_config config = {}; + struct dsa_switch *ds = dp->ds; int err; - err = raw_notifier_call_chain(nh, e, v); + if (!ds->ops->port_hwtstamp_get || !ds->ops->port_hwtstamp_set) + return false; - return notifier_to_errno(err); + /* "See through" shim implementations of the "get" method. */ + err = ds->ops->port_hwtstamp_get(ds, dp->index, &config); + return err != -EOPNOTSUPP; } -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, bool do_fast_age) { 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) { + if (!dsa_port_can_configure_learning(dp) || + (do_fast_age && dp->learning)) { /* Fast age FDB entries or flush appropriate forwarding database * for the given port, if we are moving it from Learning or * Forwarding state, to Disabled or Blocking or Listening state. + * Ports that were standalone before the STP state change don't + * need to fast age the FDB, since address learning is off in + * standalone mode. */ if ((dp->stp_state == BR_STATE_LEARNING || @@ -63,7 +153,7 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, (state == BR_STATE_DISABLED || state == BR_STATE_BLOCKING || state == BR_STATE_LISTENING)) - ds->ops->port_fast_age(ds, port); + dsa_port_fast_age(dp); } dp->stp_state = state; @@ -71,13 +161,53 @@ int dsa_port_set_state(struct dsa_port *dp, u8 state, return 0; } -static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) +static void dsa_port_set_state_now(struct dsa_port *dp, u8 state, + bool do_fast_age) +{ + struct dsa_switch *ds = dp->ds; + int err; + + err = dsa_port_set_state(dp, state, do_fast_age); + if (err && err != -EOPNOTSUPP) { + dev_err(ds->dev, "port %d failed to set STP state %u: %pe\n", + dp->index, state, ERR_PTR(err)); + } +} + +int dsa_port_set_mst_state(struct dsa_port *dp, + const struct switchdev_mst_state *state, + struct netlink_ext_ack *extack) { + struct dsa_switch *ds = dp->ds; + u8 prev_state; int err; - err = dsa_port_set_state(dp, state, NULL); + if (!ds->ops->port_mst_state_set) + return -EOPNOTSUPP; + + err = br_mst_get_state(dsa_port_to_bridge_port(dp), state->msti, + &prev_state); + if (err) + return err; + + err = ds->ops->port_mst_state_set(ds, dp->index, state); + if (err) + return err; + + if (!(dp->learning && + (prev_state == BR_STATE_LEARNING || + prev_state == BR_STATE_FORWARDING) && + (state->state == BR_STATE_DISABLED || + state->state == BR_STATE_BLOCKING || + state->state == BR_STATE_LISTENING))) + return 0; + + err = dsa_port_msti_fast_age(dp, state->msti); if (err) - pr_err("DSA: failed to set STP state %u (%d)\n", state, err); + NL_SET_ERR_MSG_MOD(extack, + "Unable to flush associated VLANs"); + + return 0; } int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) @@ -92,8 +222,8 @@ int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) return err; } - if (!dp->bridge_dev) - dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + if (!dp->bridge) + dsa_port_set_state_now(dp, BR_STATE_FORWARDING, false); if (dp->pl) phylink_start(dp->pl); @@ -120,8 +250,8 @@ void dsa_port_disable_rt(struct dsa_port *dp) if (dp->pl) phylink_stop(dp->pl); - if (!dp->bridge_dev) - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + if (!dp->bridge) + dsa_port_set_state_now(dp, BR_STATE_DISABLED, false); if (ds->ops->port_disable) ds->ops->port_disable(ds, port); @@ -134,70 +264,503 @@ void dsa_port_disable(struct dsa_port *dp) rtnl_unlock(); } -int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br) +static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, + struct dsa_bridge bridge) { - struct dsa_notifier_bridge_info info = { - .tree_index = dp->ds->dst->index, - .sw_index = dp->ds->index, - .port = dp->index, - .br = br, - }; + struct netlink_ext_ack extack = {0}; + bool change_vlan_filtering = false; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + bool vlan_filtering; + int err; + + if (ds->needs_standalone_vlan_filtering && + !br_vlan_enabled(bridge.dev)) { + change_vlan_filtering = true; + vlan_filtering = true; + } else if (!ds->needs_standalone_vlan_filtering && + br_vlan_enabled(bridge.dev)) { + change_vlan_filtering = true; + vlan_filtering = false; + } + + /* If the bridge was vlan_filtering, the bridge core doesn't trigger an + * event for changing vlan_filtering setting upon user ports leaving + * it. That is a good thing, because that lets us handle it and also + * handle the case where the switch's vlan_filtering setting is global + * (not per port). When that happens, the correct moment to trigger the + * vlan_filtering callback is only when the last port leaves the last + * VLAN-aware bridge. + */ + if (change_vlan_filtering && ds->vlan_filtering_is_global) { + dsa_switch_for_each_port(other_dp, ds) { + struct net_device *br = dsa_port_bridge_dev_get(other_dp); + + if (br && br_vlan_enabled(br)) { + change_vlan_filtering = false; + break; + } + } + } + + if (!change_vlan_filtering) + return; + + err = dsa_port_vlan_filtering(dp, vlan_filtering, &extack); + if (extack._msg) { + dev_err(ds->dev, "port %d: %s\n", dp->index, + extack._msg); + } + if (err && err != -EOPNOTSUPP) { + dev_err(ds->dev, + "port %d failed to reset VLAN filtering to %d: %pe\n", + dp->index, vlan_filtering, ERR_PTR(err)); + } +} + +static int dsa_port_inherit_brport_flags(struct dsa_port *dp, + struct netlink_ext_ack *extack) +{ + const unsigned long mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_BCAST_FLOOD | BR_PORT_LOCKED; + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + int flag, err; + + for_each_set_bit(flag, &mask, 32) { + struct switchdev_brport_flags flags = {0}; + + flags.mask = BIT(flag); + + if (br_port_flag_is_set(brport_dev, BIT(flag))) + flags.val = BIT(flag); + + err = dsa_port_bridge_flags(dp, flags, extack); + if (err && err != -EOPNOTSUPP) + return err; + } + + return 0; +} + +static void dsa_port_clear_brport_flags(struct dsa_port *dp) +{ + const unsigned long val = BR_FLOOD | BR_MCAST_FLOOD | BR_BCAST_FLOOD; + const unsigned long mask = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD | + BR_BCAST_FLOOD | BR_PORT_LOCKED; + int flag, err; + + for_each_set_bit(flag, &mask, 32) { + struct switchdev_brport_flags flags = {0}; + + flags.mask = BIT(flag); + flags.val = val & BIT(flag); + + err = dsa_port_bridge_flags(dp, flags, NULL); + if (err && err != -EOPNOTSUPP) + dev_err(dp->ds->dev, + "failed to clear bridge port flag %lu: %pe\n", + flags.val, ERR_PTR(err)); + } +} + +static int dsa_port_switchdev_sync_attrs(struct dsa_port *dp, + struct netlink_ext_ack *extack) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + struct net_device *br = dsa_port_bridge_dev_get(dp); 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); + err = dsa_port_inherit_brport_flags(dp, extack); if (err) return err; + err = dsa_port_set_state(dp, br_port_get_stp_state(brport_dev), false); + if (err && err != -EOPNOTSUPP) + return err; + + err = dsa_port_vlan_filtering(dp, br_vlan_enabled(br), extack); + if (err && err != -EOPNOTSUPP) + return err; + + err = dsa_port_ageing_time(dp, br_get_ageing_time(br)); + if (err && err != -EOPNOTSUPP) + return err; + + return 0; +} + +static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp, + struct dsa_bridge bridge) +{ + /* 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_clear_brport_flags(dp); + + /* 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 + */ + dsa_port_set_state_now(dp, BR_STATE_FORWARDING, true); + + dsa_port_reset_vlan_filtering(dp, bridge); + + /* Ageing time may be global to the switch chip, so don't change it + * here because we have no good reason (or value) to change it to. + */ +} + +static int dsa_port_bridge_create(struct dsa_port *dp, + struct net_device *br, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_bridge *bridge; + + bridge = dsa_tree_bridge_find(ds->dst, br); + if (bridge) { + refcount_inc(&bridge->refcount); + dp->bridge = bridge; + return 0; + } + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return -ENOMEM; + + refcount_set(&bridge->refcount, 1); + + bridge->dev = br; + + bridge->num = dsa_bridge_num_get(br, ds->max_num_bridges); + if (ds->max_num_bridges && !bridge->num) { + NL_SET_ERR_MSG_MOD(extack, + "Range of offloadable bridges exceeded"); + kfree(bridge); + return -EOPNOTSUPP; + } + + dp->bridge = bridge; + + return 0; +} + +static void dsa_port_bridge_destroy(struct dsa_port *dp, + const struct net_device *br) +{ + struct dsa_bridge *bridge = dp->bridge; + + dp->bridge = NULL; + + if (!refcount_dec_and_test(&bridge->refcount)) + return; + + if (bridge->num) + dsa_bridge_num_put(br, bridge->num); + + kfree(bridge); +} + +static bool dsa_port_supports_mst(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + return ds->ops->vlan_msti_set && + ds->ops->port_mst_state_set && + ds->ops->port_vlan_fast_age && + dsa_port_can_configure_learning(dp); +} + +int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, + struct netlink_ext_ack *extack) +{ + struct dsa_notifier_bridge_info info = { + .dp = dp, + .extack = extack, + }; + struct net_device *dev = dp->user; + struct net_device *brport_dev; + int err; + + if (br_mst_enabled(br) && !dsa_port_supports_mst(dp)) + return -EOPNOTSUPP; + /* Here the interface is already bridged. Reflect the current * configuration so that drivers can program their chips accordingly. */ - dp->bridge_dev = br; + err = dsa_port_bridge_create(dp, br, extack); + if (err) + return err; + brport_dev = dsa_port_to_bridge_port(dp); + + info.bridge = *dp->bridge; err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); + if (err) + goto out_rollback; - /* The bridging is rolled back on error */ - if (err) { - dsa_port_bridge_flags(dp, 0, NULL); - dp->bridge_dev = NULL; - } + /* Drivers which support bridge TX forwarding should set this */ + dp->bridge->tx_fwd_offload = info.tx_fwd_offload; + + err = switchdev_bridge_port_offload(brport_dev, dev, dp, + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier, + dp->bridge->tx_fwd_offload, extack); + if (err) + goto out_rollback_unbridge; + err = dsa_port_switchdev_sync_attrs(dp, extack); + if (err) + goto out_rollback_unoffload; + + return 0; + +out_rollback_unoffload: + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); + dsa_flush_workqueue(); +out_rollback_unbridge: + dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); +out_rollback: + dsa_port_bridge_destroy(dp, br); return err; } +void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) +{ + struct net_device *brport_dev = dsa_port_to_bridge_port(dp); + + /* Don't try to unoffload something that is not offloaded */ + if (!brport_dev) + return; + + switchdev_bridge_port_unoffload(brport_dev, dp, + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); + + dsa_flush_workqueue(); +} + void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) { struct dsa_notifier_bridge_info info = { - .tree_index = dp->ds->dst->index, - .sw_index = dp->ds->index, - .port = dp->index, - .br = br, + .dp = dp, }; int err; + /* If the port could not be offloaded to begin with, then + * there is nothing to do. + */ + if (!dp->bridge) + return; + + info.bridge = *dp->bridge; + /* Here the port is already unbridged. Reflect the current configuration * so that drivers can program their chips accordingly. */ - dp->bridge_dev = NULL; + dsa_port_bridge_destroy(dp, br); err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); if (err) - pr_err("DSA: failed to notify DSA_NOTIFIER_BRIDGE_LEAVE\n"); + dev_err(dp->ds->dev, + "port %d failed to notify DSA_NOTIFIER_BRIDGE_LEAVE: %pe\n", + dp->index, ERR_PTR(err)); - /* Port is leaving the bridge, disable flooding */ - dsa_port_bridge_flags(dp, 0, NULL); + dsa_port_switchdev_unsync_attrs(dp, info.bridge); +} - /* 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 +int dsa_port_lag_change(struct dsa_port *dp, + struct netdev_lag_lower_state_info *linfo) +{ + struct dsa_notifier_lag_info info = { + .dp = dp, + }; + bool tx_enabled; + + if (!dp->lag) + 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. */ - dsa_port_set_state_now(dp, BR_STATE_FORWARDING); + 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); } +static int dsa_port_lag_create(struct dsa_port *dp, + struct net_device *lag_dev) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_lag *lag; + + lag = dsa_tree_lag_find(ds->dst, lag_dev); + if (lag) { + refcount_inc(&lag->refcount); + dp->lag = lag; + return 0; + } + + lag = kzalloc(sizeof(*lag), GFP_KERNEL); + if (!lag) + return -ENOMEM; + + refcount_set(&lag->refcount, 1); + mutex_init(&lag->fdb_lock); + INIT_LIST_HEAD(&lag->fdbs); + lag->dev = lag_dev; + dsa_lag_map(ds->dst, lag); + dp->lag = lag; + + return 0; +} + +static void dsa_port_lag_destroy(struct dsa_port *dp) +{ + struct dsa_lag *lag = dp->lag; + + dp->lag = NULL; + dp->lag_tx_enabled = false; + + if (!refcount_dec_and_test(&lag->refcount)) + return; + + WARN_ON(!list_empty(&lag->fdbs)); + dsa_lag_unmap(dp->ds->dst, lag); + kfree(lag); +} + +int dsa_port_lag_join(struct dsa_port *dp, struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) +{ + struct dsa_notifier_lag_info info = { + .dp = dp, + .info = uinfo, + .extack = extack, + }; + struct net_device *bridge_dev; + int err; + + err = dsa_port_lag_create(dp, lag_dev); + if (err) + goto err_lag_create; + + info.lag = *dp->lag; + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_JOIN, &info); + if (err) + goto err_lag_join; + + bridge_dev = netdev_master_upper_dev_get(lag_dev); + if (!bridge_dev || !netif_is_bridge_master(bridge_dev)) + return 0; + + err = dsa_port_bridge_join(dp, bridge_dev, extack); + if (err) + goto err_bridge_join; + + return 0; + +err_bridge_join: + dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); +err_lag_join: + dsa_port_lag_destroy(dp); +err_lag_create: + return err; +} + +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev) +{ + struct net_device *br = dsa_port_bridge_dev_get(dp); + + if (br) + dsa_port_pre_bridge_leave(dp, br); +} + +void dsa_port_lag_leave(struct dsa_port *dp, struct net_device *lag_dev) +{ + struct net_device *br = dsa_port_bridge_dev_get(dp); + struct dsa_notifier_lag_info info = { + .dp = dp, + }; + int err; + + if (!dp->lag) + return; + + /* Port might have been part of a LAG that in turn was + * attached to a bridge. + */ + if (br) + dsa_port_bridge_leave(dp, br); + + info.lag = *dp->lag; + + dsa_port_lag_destroy(dp); + + err = dsa_port_notify(dp, DSA_NOTIFIER_LAG_LEAVE, &info); + if (err) + dev_err(dp->ds->dev, + "port %d failed to notify DSA_NOTIFIER_LAG_LEAVE: %pe\n", + dp->index, ERR_PTR(err)); +} + +/* 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; + struct dsa_port *other_dp; + int err; + + /* 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_port_is_user(dp)) { + struct net_device *br = dsa_port_bridge_dev_get(dp); + struct net_device *upper_dev, *user = dp->user; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(user, 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; @@ -207,19 +770,18 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, * different ports of the same switch device and one of them has a * different setting than what is being requested. */ - for (i = 0; i < ds->num_ports; i++) { - struct net_device *other_bridge; + dsa_switch_for_each_port(other_dp, ds) { + struct net_device *other_br = dsa_port_bridge_dev_get(other_dp); - other_bridge = dsa_to_port(ds, i)->bridge_dev; - if (!other_bridge) - continue; /* If it's the same bridge, it also has same * vlan_filtering setting => no need to check */ - if (other_bridge == dp->bridge_dev) + if (!other_br || other_br == dsa_port_bridge_dev_get(dp)) continue; - if (br_vlan_enabled(other_bridge) != vlan_filtering) { - dev_err(ds->dev, "VLAN filtering is a global setting\n"); + + if (br_vlan_enabled(other_br) != vlan_filtering) { + NL_SET_ERR_MSG_MOD(extack, + "VLAN filtering is a global setting"); return false; } } @@ -227,116 +789,184 @@ 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) { + bool old_vlan_filtering = dsa_port_is_vlan_filtering(dp); 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_user_switchdev_blocking_event(), + * which is not under rcu_read_lock(), unlike + * dsa_user_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; - if (ds->vlan_filtering_is_global) + if (ds->vlan_filtering_is_global) { + struct dsa_port *other_dp; + ds->vlan_filtering = vlan_filtering; - else + + dsa_switch_for_each_user_port(other_dp, ds) { + struct net_device *user = other_dp->user; + + /* We might be called in the unbind path, so not + * all user devices might still be registered. + */ + if (!user) + continue; + + err = dsa_user_manage_vlan_filtering(user, + vlan_filtering); + if (err) + goto restore; + } + } else { dp->vlan_filtering = vlan_filtering; + + err = dsa_user_manage_vlan_filtering(dp->user, + vlan_filtering); + if (err) + goto restore; + } + return 0; + +restore: + ds->ops->port_vlan_filtering(ds, dp->index, old_vlan_filtering, NULL); + + if (ds->vlan_filtering_is_global) + ds->vlan_filtering = old_vlan_filtering; + else + dp->vlan_filtering = old_vlan_filtering; + + return err; } /* This enforces legacy behavior for switch drivers which assume they can't - * receive VLAN configuration when enslaved to a bridge with vlan_filtering=0 + * receive VLAN configuration when joining a bridge with vlan_filtering=0 */ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) { + struct net_device *br = dsa_port_bridge_dev_get(dp); struct dsa_switch *ds = dp->ds; - if (!dp->bridge_dev) + if (!br) return false; - return (!ds->configure_vlan_while_not_filtering && - !br_vlan_enabled(dp->bridge_dev)); + return !ds->configure_vlan_while_not_filtering && !br_vlan_enabled(br); } -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_mst_enable(struct dsa_port *dp, bool on, + struct netlink_ext_ack *extack) +{ + if (on && !dsa_port_supports_mst(dp)) { + NL_SET_ERR_MSG_MOD(extack, "Hardware does not support MST"); + return -EINVAL; + } + + 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(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; + int err; - if (switchdev_trans_ph_prepare(trans)) - return 0; + if (!ds->ops->port_bridge_flags) + return -EOPNOTSUPP; - if (ds->ops->port_egress_floods) - err = ds->ops->port_egress_floods(ds, port, flags & BR_FLOOD, - flags & BR_MCAST_FLOOD); + err = ds->ops->port_bridge_flags(ds, dp->index, flags, extack); + if (err) + return err; - return err; + if (flags.mask & BR_LEARNING) { + bool learning = flags.val & BR_LEARNING; + + if (learning == dp->learning) + return 0; + + if ((dp->learning && !learning) && + (dp->stp_state == BR_STATE_LEARNING || + dp->stp_state == BR_STATE_FORWARDING)) + dsa_port_fast_age(dp); + + dp->learning = learning; + } + + return 0; } -int dsa_port_mrouter(struct dsa_port *dp, bool mrouter, - struct switchdev_trans *trans) +void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc) { 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_host_flood) + ds->ops->port_set_host_flood(ds, dp->index, uc, mc); +} - return ds->ops->port_egress_floods(ds, port, true, mrouter); +int dsa_port_vlan_msti(struct dsa_port *dp, + const struct switchdev_vlan_msti *msti) +{ + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->vlan_msti_set) + return -EOPNOTSUPP; + + return ds->ops->vlan_msti_set(ds, *dp->bridge, msti); } -int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu, - bool propagate_upstream) +int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu) { struct dsa_notifier_mtu_info info = { - .sw_index = dp->ds->index, - .propagate_upstream = propagate_upstream, - .port = dp->index, + .dp = dp, .mtu = new_mtu, }; @@ -347,12 +977,22 @@ int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid) { struct dsa_notifier_fdb_info info = { - .sw_index = dp->ds->index, - .port = dp->index, + .dp = dp, .addr = addr, .vid = vid, + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, }; + /* Refcounting takes bridge.num as a key, and should be global for all + * bridges in the absence of FDB isolation, and per bridge otherwise. + * Force the bridge.num to zero here in the absence of FDB isolation. + */ + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + return dsa_port_notify(dp, DSA_NOTIFIER_FDB_ADD, &info); } @@ -360,16 +1000,157 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid) { struct dsa_notifier_fdb_info info = { - .sw_index = dp->ds->index, - .port = dp->index, + .dp = dp, .addr = addr, .vid = vid, - + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, }; + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } +static int dsa_port_host_fdb_add(struct dsa_port *dp, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct dsa_notifier_fdb_info info = { + .dp = dp, + .addr = addr, + .vid = vid, + .db = db, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_ADD, &info); +} + +int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, + const unsigned char *addr, u16 vid) +{ + struct dsa_db db = { + .type = DSA_DB_PORT, + .dp = dp, + }; + + return dsa_port_host_fdb_add(dp, addr, vid, db); +} + +int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, + const unsigned char *addr, u16 vid) +{ + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_db db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }; + int err; + + if (!dp->ds->fdb_isolation) + db.bridge.num = 0; + + /* Avoid a call to __dev_set_promiscuity() on the conduit, which + * requires rtnl_lock(), since we can't guarantee that is held here, + * and we can't take it either. + */ + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_add(conduit, addr); + if (err) + return err; + } + + return dsa_port_host_fdb_add(dp, addr, vid, db); +} + +static int dsa_port_host_fdb_del(struct dsa_port *dp, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct dsa_notifier_fdb_info info = { + .dp = dp, + .addr = addr, + .vid = vid, + .db = db, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_DEL, &info); +} + +int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, + const unsigned char *addr, u16 vid) +{ + struct dsa_db db = { + .type = DSA_DB_PORT, + .dp = dp, + }; + + return dsa_port_host_fdb_del(dp, addr, vid, db); +} + +int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, + const unsigned char *addr, u16 vid) +{ + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_db db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }; + int err; + + if (!dp->ds->fdb_isolation) + db.bridge.num = 0; + + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_del(conduit, addr); + if (err) + return err; + } + + return dsa_port_host_fdb_del(dp, addr, vid, db); +} + +int dsa_port_lag_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_lag_fdb_info info = { + .lag = dp->lag, + .addr = addr, + .vid = vid, + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, + }; + + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + + return dsa_port_notify(dp, DSA_NOTIFIER_LAG_FDB_ADD, &info); +} + +int dsa_port_lag_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid) +{ + struct dsa_notifier_lag_fdb_info info = { + .lag = dp->lag, + .addr = addr, + .vid = vid, + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, + }; + + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + + return dsa_port_notify(dp, DSA_NOTIFIER_LAG_FDB_DEL, &info); +} + int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) { struct dsa_switch *ds = dp->ds; @@ -382,16 +1163,20 @@ 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, + .dp = dp, .mdb = mdb, + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, }; + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + return dsa_port_notify(dp, DSA_NOTIFIER_MDB_ADD, &info); } @@ -399,23 +1184,116 @@ int dsa_port_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { struct dsa_notifier_mdb_info info = { - .sw_index = dp->ds->index, - .port = dp->index, + .dp = dp, .mdb = mdb, + .db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }, }; + if (!dp->ds->fdb_isolation) + info.db.bridge.num = 0; + return dsa_port_notify(dp, DSA_NOTIFIER_MDB_DEL, &info); } +static int dsa_port_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct dsa_notifier_mdb_info info = { + .dp = dp, + .mdb = mdb, + .db = db, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_ADD, &info); +} + +int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_db db = { + .type = DSA_DB_PORT, + .dp = dp, + }; + + return dsa_port_host_mdb_add(dp, mdb, db); +} + +int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_db db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }; + int err; + + if (!dp->ds->fdb_isolation) + db.bridge.num = 0; + + err = dev_mc_add(conduit, mdb->addr); + if (err) + return err; + + return dsa_port_host_mdb_add(dp, mdb, db); +} + +static int dsa_port_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct dsa_notifier_mdb_info info = { + .dp = dp, + .mdb = mdb, + .db = db, + }; + + return dsa_port_notify(dp, DSA_NOTIFIER_HOST_MDB_DEL, &info); +} + +int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct dsa_db db = { + .type = DSA_DB_PORT, + .dp = dp, + }; + + return dsa_port_host_mdb_del(dp, mdb, db); +} + +int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb) +{ + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_db db = { + .type = DSA_DB_BRIDGE, + .bridge = *dp->bridge, + }; + int err; + + if (!dp->ds->fdb_isolation) + db.bridge.num = 0; + + err = dev_mc_del(conduit, mdb->addr); + if (err) + return err; + + return dsa_port_host_mdb_del(dp, mdb, db); +} + 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, + .dp = dp, .vlan = vlan, + .extack = extack, }; return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_ADD, &info); @@ -425,266 +1303,377 @@ int dsa_port_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan) { struct dsa_notifier_vlan_info info = { - .sw_index = dp->ds->index, - .port = dp->index, + .dp = dp, .vlan = vlan, }; 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_host_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) { - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .flags = flags, - .vid_begin = vid, - .vid_end = vid, + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_notifier_vlan_info info = { + .dp = dp, + .vlan = vlan, + .extack = extack, }; - struct switchdev_trans trans; int err; - trans.ph_prepare = true; - err = dsa_port_vlan_add(dp, &vlan, &trans); - if (err) + err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_ADD, &info); + if (err && err != -EOPNOTSUPP) return err; - trans.ph_prepare = false; - return dsa_port_vlan_add(dp, &vlan, &trans); + vlan_vid_add(conduit, htons(ETH_P_8021Q), vlan->vid); + + return err; } -EXPORT_SYMBOL(dsa_port_vid_add); -int dsa_port_vid_del(struct dsa_port *dp, u16 vid) +int dsa_port_host_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan) { - struct switchdev_obj_port_vlan vlan = { - .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, - .vid_begin = vid, - .vid_end = vid, + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_notifier_vlan_info info = { + .dp = dp, + .vlan = vlan, }; + int err; + + err = dsa_port_notify(dp, DSA_NOTIFIER_HOST_VLAN_DEL, &info); + if (err && err != -EOPNOTSUPP) + return err; + + vlan_vid_del(conduit, htons(ETH_P_8021Q), vlan->vid); - return dsa_port_vlan_del(dp, &vlan); + return err; } -EXPORT_SYMBOL(dsa_port_vid_del); -static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) +int dsa_port_mrp_add(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) { - struct device_node *phy_dn; - struct phy_device *phydev; - - phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0); - if (!phy_dn) - return NULL; + struct dsa_switch *ds = dp->ds; - phydev = of_phy_find_device(phy_dn); - if (!phydev) { - of_node_put(phy_dn); - return ERR_PTR(-EPROBE_DEFER); - } + if (!ds->ops->port_mrp_add) + return -EOPNOTSUPP; - of_node_put(phy_dn); - return phydev; + return ds->ops->port_mrp_add(ds, dp->index, mrp); } -static void dsa_port_phylink_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state) +int dsa_port_mrp_del(const struct dsa_port *dp, + const struct switchdev_obj_mrp *mrp) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; - if (!ds->ops->phylink_validate) - return; + if (!ds->ops->port_mrp_del) + return -EOPNOTSUPP; - ds->ops->phylink_validate(ds, dp->index, supported, state); + return ds->ops->port_mrp_del(ds, dp->index, mrp); } -static void dsa_port_phylink_mac_pcs_get_state(struct phylink_config *config, - struct phylink_link_state *state) +int dsa_port_mrp_add_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; - int err; - /* Only called for inband modes */ - if (!ds->ops->phylink_mac_link_state) { - state->link = 0; - return; - } + if (!ds->ops->port_mrp_add_ring_role) + return -EOPNOTSUPP; - err = ds->ops->phylink_mac_link_state(ds, dp->index, state); - if (err < 0) { - dev_err(ds->dev, "p%d: phylink_mac_link_state() failed: %d\n", - dp->index, err); - state->link = 0; - } + return ds->ops->port_mrp_add_ring_role(ds, dp->index, mrp); } -static void dsa_port_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state) +int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, + const struct switchdev_obj_ring_role_mrp *mrp) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; - if (!ds->ops->phylink_mac_config) - return; + if (!ds->ops->port_mrp_del_ring_role) + return -EOPNOTSUPP; - ds->ops->phylink_mac_config(ds, dp->index, mode, state); + return ds->ops->port_mrp_del_ring_role(ds, dp->index, mrp); } -static void dsa_port_phylink_mac_an_restart(struct phylink_config *config) +static int dsa_port_assign_conduit(struct dsa_port *dp, + struct net_device *conduit, + struct netlink_ext_ack *extack, + bool fail_on_err) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; + int port = dp->index, err; - if (!ds->ops->phylink_mac_an_restart) - return; + err = ds->ops->port_change_conduit(ds, port, conduit, extack); + if (err && !fail_on_err) + dev_err(ds->dev, "port %d failed to assign conduit %s: %pe\n", + port, conduit->name, ERR_PTR(err)); + + if (err && fail_on_err) + return err; - ds->ops->phylink_mac_an_restart(ds, dp->index); + dp->cpu_dp = conduit->dsa_ptr; + dp->cpu_port_in_lag = netif_is_lag_master(conduit); + + return 0; } -static void dsa_port_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) +/* Change the dp->cpu_dp affinity for a user port. Note that both cross-chip + * notifiers and drivers have implicit assumptions about user-to-CPU-port + * mappings, so we unfortunately cannot delay the deletion of the objects + * (switchdev, standalone addresses, standalone VLANs) on the old CPU port + * until the new CPU port has been set up. So we need to completely tear down + * the old CPU port before changing it, and restore it on errors during the + * bringup of the new one. + */ +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct phy_device *phydev = NULL; + struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); + struct net_device *old_conduit = dsa_port_to_conduit(dp); + struct net_device *dev = dp->user; struct dsa_switch *ds = dp->ds; + bool vlan_filtering; + int err, tmp; - if (dsa_is_user_port(ds, dp->index)) - phydev = dp->slave->phydev; + /* Bridges may hold host FDB, MDB and VLAN objects. These need to be + * migrated, so dynamically unoffload and later reoffload the bridge + * port. + */ + if (bridge_dev) { + dsa_port_pre_bridge_leave(dp, bridge_dev); + dsa_port_bridge_leave(dp, bridge_dev); + } - if (!ds->ops->phylink_mac_link_down) { - if (ds->ops->adjust_link && phydev) - ds->ops->adjust_link(ds, dp->index, phydev); - return; + /* The port might still be VLAN filtering even if it's no longer + * under a bridge, either due to ds->vlan_filtering_is_global or + * ds->needs_standalone_vlan_filtering. In turn this means VLANs + * on the CPU port. + */ + vlan_filtering = dsa_port_is_vlan_filtering(dp); + if (vlan_filtering) { + err = dsa_user_manage_vlan_filtering(dev, false); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to remove standalone VLANs"); + goto rewind_old_bridge; + } } - ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); -} + /* Standalone addresses, and addresses of upper interfaces like + * VLAN, LAG, HSR need to be migrated. + */ + dsa_user_unsync_ha(dev); -static void dsa_port_phylink_mac_link_up(struct phylink_config *config, - struct phy_device *phydev, - unsigned int mode, - phy_interface_t interface, - int speed, int duplex, - bool tx_pause, bool rx_pause) -{ - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; + /* If live-changing, we also need to uninstall the user device address + * from the port FDB and the conduit interface. + */ + if (dev->flags & IFF_UP) + dsa_user_host_uc_uninstall(dev); - if (!ds->ops->phylink_mac_link_up) { - if (ds->ops->adjust_link && phydev) - ds->ops->adjust_link(ds, dp->index, phydev); - return; + err = dsa_port_assign_conduit(dp, conduit, extack, true); + if (err) + goto rewind_old_addrs; + + /* If the port doesn't have its own MAC address and relies on the DSA + * conduit's one, inherit it again from the new DSA conduit. + */ + if (is_zero_ether_addr(dp->mac)) + eth_hw_addr_inherit(dev, conduit); + + /* If live-changing, we need to install the user device address to the + * port FDB and the conduit interface. + */ + if (dev->flags & IFF_UP) { + err = dsa_user_host_uc_install(dev, dev->dev_addr); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to install host UC address"); + goto rewind_addr_inherit; + } } - ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev, - speed, duplex, tx_pause, rx_pause); -} + dsa_user_sync_ha(dev); -const struct phylink_mac_ops dsa_port_phylink_mac_ops = { - .validate = dsa_port_phylink_validate, - .mac_pcs_get_state = dsa_port_phylink_mac_pcs_get_state, - .mac_config = dsa_port_phylink_mac_config, - .mac_an_restart = dsa_port_phylink_mac_an_restart, - .mac_link_down = dsa_port_phylink_mac_link_down, - .mac_link_up = dsa_port_phylink_mac_link_up, -}; + if (vlan_filtering) { + err = dsa_user_manage_vlan_filtering(dev, true); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to restore standalone VLANs"); + goto rewind_new_addrs; + } + } -static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) -{ - struct dsa_switch *ds = dp->ds; - struct phy_device *phydev; - int port = dp->index; - int err = 0; + if (bridge_dev) { + err = dsa_port_bridge_join(dp, bridge_dev, extack); + if (err && err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to reoffload bridge"); + goto rewind_new_vlan; + } + } - phydev = dsa_port_get_phy_device(dp); - if (!phydev) - return 0; + return 0; - if (IS_ERR(phydev)) - return PTR_ERR(phydev); +rewind_new_vlan: + if (vlan_filtering) + dsa_user_manage_vlan_filtering(dev, false); - if (enable) { - err = genphy_resume(phydev); - if (err < 0) - goto err_put_dev; +rewind_new_addrs: + dsa_user_unsync_ha(dev); - err = genphy_read_status(phydev); - if (err < 0) - goto err_put_dev; - } else { - err = genphy_suspend(phydev); - if (err < 0) - goto err_put_dev; + if (dev->flags & IFF_UP) + dsa_user_host_uc_uninstall(dev); + +rewind_addr_inherit: + if (is_zero_ether_addr(dp->mac)) + eth_hw_addr_inherit(dev, old_conduit); + + dsa_port_assign_conduit(dp, old_conduit, NULL, false); + +/* Restore the objects on the old CPU port */ +rewind_old_addrs: + if (dev->flags & IFF_UP) { + tmp = dsa_user_host_uc_install(dev, dev->dev_addr); + if (tmp) { + dev_err(ds->dev, + "port %d failed to restore host UC address: %pe\n", + dp->index, ERR_PTR(tmp)); + } } - if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port, phydev); + dsa_user_sync_ha(dev); + + if (vlan_filtering) { + tmp = dsa_user_manage_vlan_filtering(dev, true); + if (tmp) { + dev_err(ds->dev, + "port %d failed to restore standalone VLANs: %pe\n", + dp->index, ERR_PTR(tmp)); + } + } - dev_dbg(ds->dev, "enabled port's phy: %s", phydev_name(phydev)); +rewind_old_bridge: + if (bridge_dev) { + tmp = dsa_port_bridge_join(dp, bridge_dev, extack); + if (tmp) { + dev_err(ds->dev, + "port %d failed to rejoin bridge %s: %pe\n", + dp->index, bridge_dev->name, ERR_PTR(tmp)); + } + } -err_put_dev: - put_device(&phydev->mdio.dev); return err; } -static int dsa_port_fixed_link_register_of(struct dsa_port *dp) +void dsa_port_set_tag_protocol(struct dsa_port *cpu_dp, + const struct dsa_device_ops *tag_ops) { - struct device_node *dn = dp->dn; + cpu_dp->rcv = tag_ops->rcv; + cpu_dp->tag_ops = tag_ops; +} + +/* dsa_supports_eee - indicate that EEE is supported + * @ds: pointer to &struct dsa_switch + * @port: port index + * + * A default implementation for the .support_eee() DSA operations member, + * which drivers can use to indicate that they support EEE on all of their + * user ports. + * + * Returns: true + */ +bool dsa_supports_eee(struct dsa_switch *ds, int port) +{ + return true; +} +EXPORT_SYMBOL_GPL(dsa_supports_eee); + +static void dsa_port_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) +{ +} + +static void dsa_port_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ +} + +static void dsa_port_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, + unsigned int mode, + phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ +} + +static const struct phylink_mac_ops dsa_port_phylink_mac_ops = { + .mac_config = dsa_port_phylink_mac_config, + .mac_link_down = dsa_port_phylink_mac_link_down, + .mac_link_up = dsa_port_phylink_mac_link_up, +}; + +int dsa_port_phylink_create(struct dsa_port *dp) +{ + const struct phylink_mac_ops *mac_ops; struct dsa_switch *ds = dp->ds; - struct phy_device *phydev; - int port = dp->index; phy_interface_t mode; + struct phylink *pl; int err; - err = of_phy_register_fixed_link(dn); - if (err) { - dev_err(ds->dev, - "failed to register the fixed PHY of port %d\n", - port); - return err; - } - - phydev = of_phy_find_device(dn); - - err = of_get_phy_mode(dn, &mode); + err = of_get_phy_mode(dp->dn, &mode); if (err) mode = PHY_INTERFACE_MODE_NA; - phydev->interface = mode; - genphy_read_status(phydev); + if (ds->ops->phylink_get_caps) { + ds->ops->phylink_get_caps(ds, dp->index, &dp->pl_config); + } else { + /* For legacy drivers */ + if (mode != PHY_INTERFACE_MODE_NA) { + __set_bit(mode, dp->pl_config.supported_interfaces); + } else { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + dp->pl_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_GMII, + dp->pl_config.supported_interfaces); + } + } + + mac_ops = &dsa_port_phylink_mac_ops; + if (ds->phylink_mac_ops) + mac_ops = ds->phylink_mac_ops; - if (ds->ops->adjust_link) - ds->ops->adjust_link(ds, port, phydev); + pl = phylink_create(&dp->pl_config, of_fwnode_handle(dp->dn), mode, + mac_ops); + if (IS_ERR(pl)) { + pr_err("error creating PHYLINK: %ld\n", PTR_ERR(pl)); + return PTR_ERR(pl); + } - put_device(&phydev->mdio.dev); + dp->pl = pl; return 0; } -static int dsa_port_phylink_register(struct dsa_port *dp) +void dsa_port_phylink_destroy(struct dsa_port *dp) +{ + phylink_destroy(dp->pl); + dp->pl = NULL; +} + +static int dsa_shared_port_phylink_register(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; struct device_node *port_dn = dp->dn; - phy_interface_t mode; int err; - err = of_get_phy_mode(port_dn, &mode); - if (err) - mode = PHY_INTERFACE_MODE_NA; - dp->pl_config.dev = ds->dev; dp->pl_config.type = PHYLINK_DEV; - dp->pl_config.pcs_poll = ds->pcs_poll; - dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), - mode, &dsa_port_phylink_mac_ops); - if (IS_ERR(dp->pl)) { - pr_err("error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); - return PTR_ERR(dp->pl); - } + err = dsa_port_phylink_create(dp); + if (err) + return err; err = phylink_of_phy_connect(dp->pl, port_dn, 0); if (err && err != -ENODEV) { @@ -695,108 +1684,272 @@ static int dsa_port_phylink_register(struct dsa_port *dp) return 0; err_phy_connect: - phylink_destroy(dp->pl); + dsa_port_phylink_destroy(dp); return err; } -int dsa_port_link_register_of(struct dsa_port *dp) +/* During the initial DSA driver migration to OF, port nodes were sometimes + * added to device trees with no indication of how they should operate from a + * link management perspective (phy-handle, fixed-link, etc). Additionally, the + * phy-mode may be absent. The interpretation of these port OF nodes depends on + * their type. + * + * User ports with no phy-handle or fixed-link are expected to connect to an + * internal PHY located on the ds->user_mii_bus at an MDIO address equal to + * the port number. This description is still actively supported. + * + * Shared (CPU and DSA) ports with no phy-handle or fixed-link are expected to + * operate at the maximum speed that their phy-mode is capable of. If the + * phy-mode is absent, they are expected to operate using the phy-mode + * supported by the port that gives the highest link speed. It is unspecified + * if the port should use flow control or not, half duplex or full duplex, or + * if the phy-mode is a SERDES link, whether in-band autoneg is expected to be + * enabled or not. + * + * In the latter case of shared ports, omitting the link management description + * from the firmware node is deprecated and strongly discouraged. DSA uses + * phylink, which rejects the firmware nodes of these ports for lacking + * required properties. + * + * For switches in this table, DSA will skip enforcing validation and will + * later omit registering a phylink instance for the shared ports, if they lack + * a fixed-link, a phy-handle, or a managed = "in-band-status" property. + * It becomes the responsibility of the driver to ensure that these ports + * operate at the maximum speed (whatever this means) and will interoperate + * with the DSA conduit or other cascade port, since phylink methods will not be + * invoked for them. + * + * If you are considering expanding this table for newly introduced switches, + * think again. It is OK to remove switches from this table if there aren't DT + * blobs in circulation which rely on defaulting the shared ports. + */ +static const char * const dsa_switches_apply_workarounds[] = { +#if IS_ENABLED(CONFIG_NET_DSA_XRS700X) + "arrow,xrs7003e", + "arrow,xrs7003f", + "arrow,xrs7004e", + "arrow,xrs7004f", +#endif +#if IS_ENABLED(CONFIG_B53) + "brcm,bcm5325", + "brcm,bcm53115", + "brcm,bcm53125", + "brcm,bcm53128", + "brcm,bcm5365", + "brcm,bcm5389", + "brcm,bcm5395", + "brcm,bcm5397", + "brcm,bcm5398", + "brcm,bcm53010-srab", + "brcm,bcm53011-srab", + "brcm,bcm53012-srab", + "brcm,bcm53018-srab", + "brcm,bcm53019-srab", + "brcm,bcm5301x-srab", + "brcm,bcm11360-srab", + "brcm,bcm58522-srab", + "brcm,bcm58525-srab", + "brcm,bcm58535-srab", + "brcm,bcm58622-srab", + "brcm,bcm58623-srab", + "brcm,bcm58625-srab", + "brcm,bcm88312-srab", + "brcm,cygnus-srab", + "brcm,nsp-srab", + "brcm,omega-srab", + "brcm,bcm3384-switch", + "brcm,bcm6328-switch", + "brcm,bcm6368-switch", + "brcm,bcm63xx-switch", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_BCM_SF2) + "brcm,bcm7445-switch-v4.0", + "brcm,bcm7278-switch-v4.0", + "brcm,bcm7278-switch-v4.8", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_LANTIQ_GSWIP) + "lantiq,xrx200-gswip", + "lantiq,xrx300-gswip", + "lantiq,xrx330-gswip", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6060) + "marvell,mv88e6060", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6XXX) + "marvell,mv88e6085", + "marvell,mv88e6190", + "marvell,mv88e6250", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_MICROCHIP_KSZ_COMMON) + "microchip,ksz8765", + "microchip,ksz8794", + "microchip,ksz8795", + "microchip,ksz8863", + "microchip,ksz8873", + "microchip,ksz9477", + "microchip,ksz9897", + "microchip,ksz9893", + "microchip,ksz9563", + "microchip,ksz8563", + "microchip,ksz9567", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) + "smsc,lan9303-mdio", +#endif +#if IS_ENABLED(CONFIG_NET_DSA_SMSC_LAN9303_I2C) + "smsc,lan9303-i2c", +#endif + NULL, +}; + +static void dsa_shared_port_validate_of(struct dsa_port *dp, + bool *missing_phy_mode, + bool *missing_link_description) { + struct device_node *dn = dp->dn, *phy_np; struct dsa_switch *ds = dp->ds; - struct device_node *phy_np; - int port = dp->index; + phy_interface_t mode; - if (!ds->ops->adjust_link) { - phy_np = of_parse_phandle(dp->dn, "phy-handle", 0); - if (of_phy_is_fixed_link(dp->dn) || phy_np) { - if (ds->ops->phylink_mac_link_down) - ds->ops->phylink_mac_link_down(ds, port, - MLO_AN_FIXED, PHY_INTERFACE_MODE_NA); - return dsa_port_phylink_register(dp); - } - return 0; + *missing_phy_mode = false; + *missing_link_description = false; + + if (of_get_phy_mode(dn, &mode)) { + *missing_phy_mode = true; + dev_err(ds->dev, + "OF node %pOF of %s port %d lacks the required \"phy-mode\" property\n", + dn, dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); } - dev_warn(ds->dev, - "Using legacy PHYLIB callbacks. Please migrate to PHYLINK!\n"); + /* Note: of_phy_is_fixed_link() also returns true for + * managed = "in-band-status" + */ + if (of_phy_is_fixed_link(dn)) + return; - if (of_phy_is_fixed_link(dp->dn)) - return dsa_port_fixed_link_register_of(dp); - else - return dsa_port_setup_phy_of(dp, true); + phy_np = of_parse_phandle(dn, "phy-handle", 0); + if (phy_np) { + of_node_put(phy_np); + return; + } + + *missing_link_description = true; + + dev_err(ds->dev, + "OF node %pOF of %s port %d lacks the required \"phy-handle\", \"fixed-link\" or \"managed\" properties\n", + dn, dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); +} + +static void dsa_shared_port_link_down(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + + if (ds->phylink_mac_ops && ds->phylink_mac_ops->mac_link_down) + ds->phylink_mac_ops->mac_link_down(&dp->pl_config, MLO_AN_FIXED, + PHY_INTERFACE_MODE_NA); } -void dsa_port_link_unregister_of(struct dsa_port *dp) +int dsa_shared_port_link_register_of(struct dsa_port *dp) { struct dsa_switch *ds = dp->ds; + bool missing_link_description; + bool missing_phy_mode; + + dsa_shared_port_validate_of(dp, &missing_phy_mode, + &missing_link_description); + + if ((missing_phy_mode || missing_link_description) && + !of_device_compatible_match(ds->dev->of_node, + dsa_switches_apply_workarounds)) + return -EINVAL; + + if (missing_link_description) { + dev_warn(ds->dev, + "Skipping phylink registration for %s port %d\n", + dsa_port_is_cpu(dp) ? "CPU" : "DSA", dp->index); + } else { + dsa_shared_port_link_down(dp); + + return dsa_shared_port_phylink_register(dp); + } + + return 0; +} - if (!ds->ops->adjust_link && dp->pl) { +void dsa_shared_port_link_unregister_of(struct dsa_port *dp) +{ + if (dp->pl) { rtnl_lock(); phylink_disconnect_phy(dp->pl); rtnl_unlock(); - phylink_destroy(dp->pl); - dp->pl = NULL; + dsa_port_phylink_destroy(dp); return; } - - if (of_phy_is_fixed_link(dp->dn)) - of_phy_deregister_fixed_link(dp->dn); - else - dsa_port_setup_phy_of(dp, false); } -int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data) +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr, + struct netlink_ext_ack *extack) { - struct phy_device *phydev; - int ret = -EOPNOTSUPP; + struct dsa_switch *ds = dp->ds; + int err; - if (of_phy_is_fixed_link(dp->dn)) - return ret; + if (!ds->ops->port_hsr_join) + return -EOPNOTSUPP; - phydev = dsa_port_get_phy_device(dp); - if (IS_ERR_OR_NULL(phydev)) - return ret; + dp->hsr_dev = hsr; - ret = phy_ethtool_get_strings(phydev, data); - put_device(&phydev->mdio.dev); + err = ds->ops->port_hsr_join(ds, dp->index, hsr, extack); + if (err) + dp->hsr_dev = NULL; - return ret; + return err; } -EXPORT_SYMBOL_GPL(dsa_port_get_phy_strings); -int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data) +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr) { - struct phy_device *phydev; - int ret = -EOPNOTSUPP; - - if (of_phy_is_fixed_link(dp->dn)) - return ret; + struct dsa_switch *ds = dp->ds; + int err; - phydev = dsa_port_get_phy_device(dp); - if (IS_ERR_OR_NULL(phydev)) - return ret; + if (!dp->hsr_dev) + return; - ret = phy_ethtool_get_stats(phydev, NULL, data); - put_device(&phydev->mdio.dev); + dp->hsr_dev = NULL; - return ret; + if (ds->ops->port_hsr_leave) { + err = ds->ops->port_hsr_leave(ds, dp->index, hsr); + if (err) + dev_err(dp->ds->dev, + "port %d failed to leave HSR %s: %pe\n", + dp->index, hsr->name, ERR_PTR(err)); + } } -EXPORT_SYMBOL_GPL(dsa_port_get_ethtool_phy_stats); -int dsa_port_get_phy_sset_count(struct dsa_port *dp) +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast) { - struct phy_device *phydev; - int ret = -EOPNOTSUPP; + struct dsa_notifier_tag_8021q_vlan_info info = { + .dp = dp, + .vid = vid, + }; - if (of_phy_is_fixed_link(dp->dn)) - return ret; + if (broadcast) + return dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, &info); - phydev = dsa_port_get_phy_device(dp); - if (IS_ERR_OR_NULL(phydev)) - return ret; + return dsa_port_notify(dp, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, &info); +} - ret = phy_ethtool_get_sset_count(phydev); - put_device(&phydev->mdio.dev); +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast) +{ + struct dsa_notifier_tag_8021q_vlan_info info = { + .dp = dp, + .vid = vid, + }; + int err; - return ret; + if (broadcast) + err = dsa_broadcast(DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, &info); + else + err = dsa_port_notify(dp, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, &info); + if (err) + dev_err(dp->ds->dev, + "port %d failed to notify tag_8021q VLAN %d deletion: %pe\n", + dp->index, vid, ERR_PTR(err)); } -EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count); diff --git a/net/dsa/port.h b/net/dsa/port.h new file mode 100644 index 000000000000..6bc3291573c0 --- /dev/null +++ b/net/dsa/port.h @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_PORT_H +#define __DSA_PORT_H + +#include <linux/types.h> +#include <net/dsa.h> + +struct ifreq; +struct netdev_lag_lower_state_info; +struct netdev_lag_upper_info; +struct netlink_ext_ack; +struct switchdev_mst_state; +struct switchdev_obj_port_mdb; +struct switchdev_vlan_msti; +struct phy_device; + +bool dsa_port_supports_hwtstamp(struct dsa_port *dp); +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, bool do_fast_age); +int dsa_port_set_mst_state(struct dsa_port *dp, + const struct switchdev_mst_state *state, + struct netlink_ext_ack *extack); +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, + struct netlink_ext_ack *extack); +void dsa_port_pre_bridge_leave(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, + struct netlink_ext_ack *extack); +void dsa_port_pre_lag_leave(struct dsa_port *dp, struct net_device *lag_dev); +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 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); +int dsa_port_mst_enable(struct dsa_port *dp, bool on, + struct netlink_ext_ack *extack); +int dsa_port_vlan_msti(struct dsa_port *dp, + const struct switchdev_vlan_msti *msti); +int dsa_port_mtu_change(struct dsa_port *dp, int new_mtu); +int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, + const unsigned char *addr, u16 vid); +int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, + const unsigned char *addr, u16 vid); +int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_lag_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid); +int dsa_port_lag_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); +int dsa_port_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb); +int dsa_port_bridge_host_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, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_bridge_flags(struct dsa_port *dp, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack); +int dsa_port_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); +int dsa_port_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); +int dsa_port_host_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack); +int dsa_port_host_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan); +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_phylink_create(struct dsa_port *dp); +void dsa_port_phylink_destroy(struct dsa_port *dp); +int dsa_shared_port_link_register_of(struct dsa_port *dp); +void dsa_shared_port_link_unregister_of(struct dsa_port *dp); +int dsa_port_hsr_join(struct dsa_port *dp, struct net_device *hsr, + struct netlink_ext_ack *extack); +void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); +int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); +void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); +void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc); +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack); + +#endif diff --git a/net/dsa/slave.c b/net/dsa/slave.c deleted file mode 100644 index 4c7f086a047b..000000000000 --- a/net/dsa/slave.c +++ /dev/null @@ -1,2116 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/dsa/slave.c - Slave device handling - * Copyright (c) 2008-2009 Marvell Semiconductor - */ - -#include <linux/list.h> -#include <linux/etherdevice.h> -#include <linux/netdevice.h> -#include <linux/phy.h> -#include <linux/phy_fixed.h> -#include <linux/phylink.h> -#include <linux/of_net.h> -#include <linux/of_mdio.h> -#include <linux/mdio.h> -#include <net/rtnetlink.h> -#include <net/pkt_cls.h> -#include <net/tc_act/tc_mirred.h> -#include <linux/if_bridge.h> -#include <linux/netpoll.h> -#include <linux/ptp_classify.h> - -#include "dsa_priv.h" - -/* slave mii_bus handling ***************************************************/ -static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) -{ - struct dsa_switch *ds = bus->priv; - - if (ds->phys_mii_mask & (1 << addr)) - return ds->ops->phy_read(ds, addr, reg); - - return 0xffff; -} - -static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) -{ - struct dsa_switch *ds = bus->priv; - - if (ds->phys_mii_mask & (1 << addr)) - return ds->ops->phy_write(ds, addr, reg, val); - - return 0; -} - -void dsa_slave_mii_bus_init(struct dsa_switch *ds) -{ - ds->slave_mii_bus->priv = (void *)ds; - ds->slave_mii_bus->name = "dsa slave smi"; - ds->slave_mii_bus->read = dsa_slave_phy_read; - ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", - ds->dst->index, ds->index); - ds->slave_mii_bus->parent = ds->dev; - ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; -} - - -/* slave device handling ****************************************************/ -static int dsa_slave_get_iflink(const struct net_device *dev) -{ - return dsa_slave_to_master(dev)->ifindex; -} - -static int dsa_slave_open(struct net_device *dev) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); - int err; - - if (!(master->flags & IFF_UP)) - return -ENETDOWN; - - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { - err = dev_uc_add(master, dev->dev_addr); - if (err < 0) - goto out; - } - - if (dev->flags & IFF_ALLMULTI) { - err = dev_set_allmulti(master, 1); - if (err < 0) - goto del_unicast; - } - if (dev->flags & IFF_PROMISC) { - err = dev_set_promiscuity(master, 1); - if (err < 0) - goto clear_allmulti; - } - - err = dsa_port_enable_rt(dp, dev->phydev); - if (err) - goto clear_promisc; - - return 0; - -clear_promisc: - if (dev->flags & IFF_PROMISC) - dev_set_promiscuity(master, -1); -clear_allmulti: - if (dev->flags & IFF_ALLMULTI) - dev_set_allmulti(master, -1); -del_unicast: - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); -out: - return err; -} - -static int dsa_slave_close(struct net_device *dev) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); - - dsa_port_disable_rt(dp); - - dev_mc_unsync(master, dev); - dev_uc_unsync(master, dev); - if (dev->flags & IFF_ALLMULTI) - dev_set_allmulti(master, -1); - if (dev->flags & IFF_PROMISC) - dev_set_promiscuity(master, -1); - - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); - - return 0; -} - -static void dsa_slave_change_rx_flags(struct net_device *dev, int change) -{ - struct net_device *master = dsa_slave_to_master(dev); - if (dev->flags & IFF_UP) { - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, - dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, - dev->flags & IFF_PROMISC ? 1 : -1); - } -} - -static void dsa_slave_set_rx_mode(struct net_device *dev) -{ - struct net_device *master = dsa_slave_to_master(dev); - - dev_mc_sync(master, dev); - dev_uc_sync(master, dev); -} - -static int dsa_slave_set_mac_address(struct net_device *dev, void *a) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct sockaddr *addr = a; - int err; - - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - - if (!(dev->flags & IFF_UP)) - goto out; - - if (!ether_addr_equal(addr->sa_data, master->dev_addr)) { - err = dev_uc_add(master, addr->sa_data); - if (err < 0) - return err; - } - - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); - -out: - ether_addr_copy(dev->dev_addr, addr->sa_data); - - return 0; -} - -struct dsa_slave_dump_ctx { - struct net_device *dev; - struct sk_buff *skb; - struct netlink_callback *cb; - int idx; -}; - -static int -dsa_slave_port_fdb_do_dump(const unsigned char *addr, u16 vid, - bool is_static, void *data) -{ - struct dsa_slave_dump_ctx *dump = data; - u32 portid = NETLINK_CB(dump->cb->skb).portid; - u32 seq = dump->cb->nlh->nlmsg_seq; - struct nlmsghdr *nlh; - struct ndmsg *ndm; - - if (dump->idx < dump->cb->args[2]) - goto skip; - - nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, - sizeof(*ndm), NLM_F_MULTI); - if (!nlh) - return -EMSGSIZE; - - ndm = nlmsg_data(nlh); - ndm->ndm_family = AF_BRIDGE; - ndm->ndm_pad1 = 0; - ndm->ndm_pad2 = 0; - ndm->ndm_flags = NTF_SELF; - ndm->ndm_type = 0; - ndm->ndm_ifindex = dump->dev->ifindex; - ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - - if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) - goto nla_put_failure; - - if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) - goto nla_put_failure; - - nlmsg_end(dump->skb, nlh); - -skip: - dump->idx++; - return 0; - -nla_put_failure: - nlmsg_cancel(dump->skb, nlh); - return -EMSGSIZE; -} - -static int -dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, struct net_device *filter_dev, - int *idx) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_dump_ctx dump = { - .dev = dev, - .skb = skb, - .cb = cb, - .idx = *idx, - }; - int err; - - err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); - *idx = dump.idx; - - return err; -} - -static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - int port = p->dp->index; - - /* Pass through to switch driver if it supports timestamping */ - switch (cmd) { - case SIOCGHWTSTAMP: - if (ds->ops->port_hwtstamp_get) - return ds->ops->port_hwtstamp_get(ds, port, ifr); - break; - case SIOCSHWTSTAMP: - if (ds->ops->port_hwtstamp_set) - return ds->ops->port_hwtstamp_set(ds, port, ifr); - break; - } - - return phylink_mii_ioctl(p->dp->pl, ifr, cmd); -} - -static int dsa_slave_port_attr_set(struct net_device *dev, - const struct switchdev_attr *attr, - struct switchdev_trans *trans) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - int ret; - - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_STP_STATE: - ret = dsa_port_set_state(dp, attr->u.stp_state, trans); - break; - case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: - ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, - trans); - break; - case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: - ret = dsa_port_ageing_time(dp, attr->u.ageing_time, trans); - break; - case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: - ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, - trans); - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, trans); - break; - case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER: - ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, trans); - break; - default: - ret = -EOPNOTSUPP; - break; - } - - return ret; -} - -static int dsa_slave_vlan_add(struct net_device *dev, - const struct switchdev_obj *obj, - struct switchdev_trans *trans) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct switchdev_obj_port_vlan vlan; - int err; - - if (obj->orig_dev != dev) - return -EOPNOTSUPP; - - if (dsa_port_skip_vlan_configuration(dp)) - return 0; - - vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj); - - err = dsa_port_vlan_add(dp, &vlan, trans); - if (err) - return err; - - /* We need the dedicated CPU port to be a member of the VLAN as well. - * Even though drivers often handle CPU membership in special ways, - * it doesn't make sense to program a PVID, so clear this flag. - */ - vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; - - err = dsa_port_vlan_add(dp->cpu_dp, &vlan, trans); - if (err) - return err; - - return 0; -} - -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) - return -EOPNOTSUPP; - err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj), trans); - 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); - break; - case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_vlan_add(dev, obj, trans); - break; - default: - err = -EOPNOTSUPP; - break; - } - - return err; -} - -static int dsa_slave_vlan_del(struct net_device *dev, - const struct switchdev_obj *obj) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - if (obj->orig_dev != dev) - return -EOPNOTSUPP; - - if (dsa_port_skip_vlan_configuration(dp)) - return 0; - - /* 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)); -} - -static int dsa_slave_port_obj_del(struct net_device *dev, - const struct switchdev_obj *obj) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - int err; - - switch (obj->id) { - case SWITCHDEV_OBJ_ID_PORT_MDB: - if (obj->orig_dev != dev) - return -EOPNOTSUPP; - err = dsa_port_mdb_del(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_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj)); - break; - case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = dsa_slave_vlan_del(dev, obj); - break; - default: - err = -EOPNOTSUPP; - break; - } - - return err; -} - -static int dsa_slave_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - struct dsa_switch_tree *dst = ds->dst; - - /* For non-legacy ports, devlink is used and it takes - * care of the name generation. This ndo implementation - * should be removed with legacy support. - */ - if (dp->ds->devlink) - return -EOPNOTSUPP; - - ppid->id_len = sizeof(dst->index); - memcpy(&ppid->id, &dst->index, ppid->id_len); - - return 0; -} - -static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, - struct sk_buff *skb) -{ -#ifdef CONFIG_NET_POLL_CONTROLLER - struct dsa_slave_priv *p = netdev_priv(dev); - - return netpoll_send_skb(p->netpoll, skb); -#else - BUG(); - return NETDEV_TX_OK; -#endif -} - -static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, - struct sk_buff *skb) -{ - struct dsa_switch *ds = p->dp->ds; - struct sk_buff *clone; - unsigned int type; - - type = ptp_classify_raw(skb); - if (type == PTP_CLASS_NONE) - return; - - if (!ds->ops->port_txtstamp) - return; - - clone = skb_clone_sk(skb); - if (!clone) - return; - - DSA_SKB_CB(skb)->clone = clone; - - if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) - return; - - kfree_skb(clone); -} - -netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) -{ - /* SKB for netpoll still need to be mangled with the protocol-specific - * tag to be successfully transmitted - */ - if (unlikely(netpoll_tx_running(dev))) - return dsa_slave_netpoll_send_skb(dev, skb); - - /* Queue the SKB for transmission on the parent interface, but - * do not modify its EtherType - */ - skb->dev = dsa_slave_to_master(dev); - dev_queue_xmit(skb); - - return NETDEV_TX_OK; -} -EXPORT_SYMBOL_GPL(dsa_enqueue_skb); - -static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - 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); - - DSA_SKB_CB(skb)->clone = NULL; - - /* Identify PTP protocol packets, clone them, and pass them to the - * switch driver - */ - dsa_skb_tx_timestamp(p, skb); - - /* Transmit function may have to reallocate the original SKB, - * in which case it must have freed it. Only free it here on error. - */ - nskb = p->xmit(skb, dev); - if (!nskb) { - kfree_skb(skb); - return NETDEV_TX_OK; - } - - return dsa_enqueue_skb(nskb, dev); -} - -/* ethtool operations *******************************************************/ - -static void dsa_slave_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *drvinfo) -{ - strlcpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); - strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); - strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); -} - -static int dsa_slave_get_regs_len(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (ds->ops->get_regs_len) - return ds->ops->get_regs_len(ds, dp->index); - - return -EOPNOTSUPP; -} - -static void -dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (ds->ops->get_regs) - ds->ops->get_regs(ds, dp->index, regs, _p); -} - -static int dsa_slave_nway_reset(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return phylink_ethtool_nway_reset(dp->pl); -} - -static int dsa_slave_get_eeprom_len(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (ds->cd && ds->cd->eeprom_len) - return ds->cd->eeprom_len; - - if (ds->ops->get_eeprom_len) - return ds->ops->get_eeprom_len(ds); - - return 0; -} - -static int dsa_slave_get_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (ds->ops->get_eeprom) - return ds->ops->get_eeprom(ds, eeprom, data); - - return -EOPNOTSUPP; -} - -static int dsa_slave_set_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (ds->ops->set_eeprom) - return ds->ops->set_eeprom(ds, eeprom, data); - - return -EOPNOTSUPP; -} - -static void dsa_slave_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (stringset == ETH_SS_STATS) { - int len = ETH_GSTRING_LEN; - - strncpy(data, "tx_packets", len); - strncpy(data + len, "tx_bytes", len); - strncpy(data + 2 * len, "rx_packets", len); - strncpy(data + 3 * len, "rx_bytes", len); - if (ds->ops->get_strings) - ds->ops->get_strings(ds, dp->index, stringset, - data + 4 * len); - } -} - -static void dsa_slave_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - 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; - int i; - - 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)); - data[0] += tx_packets; - data[1] += tx_bytes; - data[2] += rx_packets; - data[3] += rx_bytes; - } - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, dp->index, data + 4); -} - -static int dsa_slave_get_sset_count(struct net_device *dev, int sset) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (sset == ETH_SS_STATS) { - int count; - - count = 4; - if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index, sset); - - return count; - } - - return -EOPNOTSUPP; -} - -static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - phylink_ethtool_get_wol(dp->pl, w); - - if (ds->ops->get_wol) - ds->ops->get_wol(ds, dp->index, w); -} - -static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int ret = -EOPNOTSUPP; - - phylink_ethtool_set_wol(dp->pl, w); - - if (ds->ops->set_wol) - ret = ds->ops->set_wol(ds, dp->index, w); - - return ret; -} - -static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int ret; - - /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev || !dp->pl) - return -ENODEV; - - if (!ds->ops->set_mac_eee) - return -EOPNOTSUPP; - - ret = ds->ops->set_mac_eee(ds, dp->index, e); - if (ret) - return ret; - - return phylink_ethtool_set_eee(dp->pl, e); -} - -static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int ret; - - /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev || !dp->pl) - return -ENODEV; - - if (!ds->ops->get_mac_eee) - return -EOPNOTSUPP; - - ret = ds->ops->get_mac_eee(ds, dp->index, e); - if (ret) - return ret; - - return phylink_ethtool_get_eee(dp->pl, e); -} - -static int dsa_slave_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return phylink_ethtool_ksettings_get(dp->pl, cmd); -} - -static int dsa_slave_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return phylink_ethtool_ksettings_set(dp->pl, cmd); -} - -static void dsa_slave_get_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - phylink_ethtool_get_pauseparam(dp->pl, pause); -} - -static int dsa_slave_set_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return phylink_ethtool_set_pauseparam(dp->pl, pause); -} - -#ifdef CONFIG_NET_POLL_CONTROLLER -static int dsa_slave_netpoll_setup(struct net_device *dev, - struct netpoll_info *ni) -{ - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_slave_priv *p = netdev_priv(dev); - struct netpoll *netpoll; - int err = 0; - - netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); - if (!netpoll) - return -ENOMEM; - - err = __netpoll_setup(netpoll, master); - if (err) { - kfree(netpoll); - goto out; - } - - p->netpoll = netpoll; -out: - return err; -} - -static void dsa_slave_netpoll_cleanup(struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct netpoll *netpoll = p->netpoll; - - if (!netpoll) - return; - - p->netpoll = NULL; - - __netpoll_free(netpoll); -} - -static void dsa_slave_poll_controller(struct net_device *dev) -{ -} -#endif - -static int dsa_slave_get_phys_port_name(struct net_device *dev, - char *name, size_t len) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - /* For non-legacy ports, devlink is used and it takes - * care of the name generation. This ndo implementation - * should be removed with legacy support. - */ - if (dp->ds->devlink) - return -EOPNOTSUPP; - - if (snprintf(name, len, "p%d", dp->index) >= len) - return -EINVAL; - - return 0; -} - -static struct dsa_mall_tc_entry * -dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_mall_tc_entry *mall_tc_entry; - - list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) - if (mall_tc_entry->cookie == cookie) - return mall_tc_entry; - - return NULL; -} - -static int -dsa_slave_add_cls_matchall_mirred(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_mall_mirror_tc_entry *mirror; - struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = dp->ds; - struct flow_action_entry *act; - struct dsa_port *to_dp; - int err; - - if (!ds->ops->port_mirror_add) - return -EOPNOTSUPP; - - if (!flow_action_basic_hw_stats_check(&cls->rule->action, - cls->common.extack)) - return -EOPNOTSUPP; - - act = &cls->rule->action.entries[0]; - - if (!act->dev) - return -EINVAL; - - if (!dsa_slave_dev_check(act->dev)) - return -EOPNOTSUPP; - - mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); - if (!mall_tc_entry) - return -ENOMEM; - - mall_tc_entry->cookie = cls->cookie; - mall_tc_entry->type = DSA_PORT_MALL_MIRROR; - mirror = &mall_tc_entry->mirror; - - to_dp = dsa_slave_to_port(act->dev); - - mirror->to_local_port = to_dp->index; - mirror->ingress = ingress; - - err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress); - if (err) { - kfree(mall_tc_entry); - return err; - } - - list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); - - return err; -} - -static int -dsa_slave_add_cls_matchall_police(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) -{ - struct netlink_ext_ack *extack = cls->common.extack; - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_mall_policer_tc_entry *policer; - struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = dp->ds; - struct flow_action_entry *act; - int err; - - if (!ds->ops->port_policer_add) { - NL_SET_ERR_MSG_MOD(extack, - "Policing offload not implemented"); - return -EOPNOTSUPP; - } - - if (!ingress) { - NL_SET_ERR_MSG_MOD(extack, - "Only supported on ingress qdisc"); - return -EOPNOTSUPP; - } - - if (!flow_action_basic_hw_stats_check(&cls->rule->action, - cls->common.extack)) - return -EOPNOTSUPP; - - list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { - if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { - NL_SET_ERR_MSG_MOD(extack, - "Only one port policer allowed"); - return -EEXIST; - } - } - - act = &cls->rule->action.entries[0]; - - mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); - if (!mall_tc_entry) - return -ENOMEM; - - mall_tc_entry->cookie = cls->cookie; - mall_tc_entry->type = DSA_PORT_MALL_POLICER; - policer = &mall_tc_entry->policer; - policer->rate_bytes_per_sec = act->police.rate_bytes_ps; - policer->burst = act->police.burst; - - err = ds->ops->port_policer_add(ds, dp->index, policer); - if (err) { - kfree(mall_tc_entry); - return err; - } - - list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); - - return err; -} - -static int dsa_slave_add_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) -{ - int err = -EOPNOTSUPP; - - if (cls->common.protocol == htons(ETH_P_ALL) && - flow_offload_has_one_action(&cls->rule->action) && - cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) - err = dsa_slave_add_cls_matchall_mirred(dev, cls, ingress); - else if (flow_offload_has_one_action(&cls->rule->action) && - cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) - err = dsa_slave_add_cls_matchall_police(dev, cls, ingress); - - return err; -} - -static void dsa_slave_del_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_mall_tc_entry *mall_tc_entry; - struct dsa_switch *ds = dp->ds; - - mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie); - if (!mall_tc_entry) - return; - - list_del(&mall_tc_entry->list); - - switch (mall_tc_entry->type) { - case DSA_PORT_MALL_MIRROR: - if (ds->ops->port_mirror_del) - ds->ops->port_mirror_del(ds, dp->index, - &mall_tc_entry->mirror); - break; - case DSA_PORT_MALL_POLICER: - if (ds->ops->port_policer_del) - ds->ops->port_policer_del(ds, dp->index); - break; - default: - WARN_ON(1); - } - - kfree(mall_tc_entry); -} - -static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) -{ - if (cls->common.chain_index) - return -EOPNOTSUPP; - - switch (cls->command) { - case TC_CLSMATCHALL_REPLACE: - return dsa_slave_add_cls_matchall(dev, cls, ingress); - case TC_CLSMATCHALL_DESTROY: - dsa_slave_del_cls_matchall(dev, cls); - return 0; - default: - return -EOPNOTSUPP; - } -} - -static int dsa_slave_add_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int port = dp->index; - - if (!ds->ops->cls_flower_add) - return -EOPNOTSUPP; - - return ds->ops->cls_flower_add(ds, port, cls, ingress); -} - -static int dsa_slave_del_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int port = dp->index; - - if (!ds->ops->cls_flower_del) - return -EOPNOTSUPP; - - return ds->ops->cls_flower_del(ds, port, cls, ingress); -} - -static int dsa_slave_stats_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - int port = dp->index; - - if (!ds->ops->cls_flower_stats) - return -EOPNOTSUPP; - - return ds->ops->cls_flower_stats(ds, port, cls, ingress); -} - -static int dsa_slave_setup_tc_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) -{ - switch (cls->command) { - case FLOW_CLS_REPLACE: - return dsa_slave_add_cls_flower(dev, cls, ingress); - case FLOW_CLS_DESTROY: - return dsa_slave_del_cls_flower(dev, cls, ingress); - case FLOW_CLS_STATS: - return dsa_slave_stats_cls_flower(dev, cls, ingress); - default: - return -EOPNOTSUPP; - } -} - -static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv, bool ingress) -{ - struct net_device *dev = cb_priv; - - if (!tc_can_offload(dev)) - return -EOPNOTSUPP; - - switch (type) { - case TC_SETUP_CLSMATCHALL: - return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress); - case TC_SETUP_CLSFLOWER: - return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress); - default: - return -EOPNOTSUPP; - } -} - -static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type, - void *type_data, void *cb_priv) -{ - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true); -} - -static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type, - void *type_data, void *cb_priv) -{ - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false); -} - -static LIST_HEAD(dsa_slave_block_cb_list); - -static int dsa_slave_setup_tc_block(struct net_device *dev, - struct flow_block_offload *f) -{ - struct flow_block_cb *block_cb; - flow_setup_cb_t *cb; - - if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) - cb = dsa_slave_setup_tc_block_cb_ig; - else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) - cb = dsa_slave_setup_tc_block_cb_eg; - else - return -EOPNOTSUPP; - - f->driver_block_list = &dsa_slave_block_cb_list; - - switch (f->command) { - case FLOW_BLOCK_BIND: - if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) - return -EBUSY; - - block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); - if (IS_ERR(block_cb)) - return PTR_ERR(block_cb); - - flow_block_cb_add(block_cb, f); - list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); - return 0; - case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f->block, cb, dev); - if (!block_cb) - return -ENOENT; - - flow_block_cb_remove(block_cb, f); - list_del(&block_cb->driver_list); - return 0; - default: - return -EOPNOTSUPP; - } -} - -static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (type == TC_SETUP_BLOCK) - return dsa_slave_setup_tc_block(dev, type_data); - - if (!ds->ops->port_setup_tc) - return -EOPNOTSUPP; - - 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) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->get_rxnfc) - return -EOPNOTSUPP; - - return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); -} - -static int dsa_slave_set_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *nfc) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_switch *ds = dp->ds; - - if (!ds->ops->set_rxnfc) - return -EOPNOTSUPP; - - return ds->ops->set_rxnfc(ds, dp->index, nfc); -} - -static int dsa_slave_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *ts) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - - if (!ds->ops->get_ts_info) - return -EOPNOTSUPP; - - return ds->ops->get_ts_info(ds, p->dp->index, ts); -} - -static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, - u16 vid) -{ - 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; - } - - ret = dsa_port_vid_add(dp, vid, 0); - if (ret) - return ret; - - ret = dsa_port_vid_add(dp->cpu_dp, vid, 0); - if (ret) - return ret; - - return 0; -} - -static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, - u16 vid) -{ - 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; - } - - /* 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); -} - -struct dsa_hw_port { - struct list_head list; - struct net_device *dev; - int old_mtu; -}; - -static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) -{ - const struct dsa_hw_port *p; - int err; - - list_for_each_entry(p, hw_port_list, list) { - if (p->dev->mtu == mtu) - continue; - - err = dev_set_mtu(p->dev, mtu); - if (err) - goto rollback; - } - - return 0; - -rollback: - list_for_each_entry_continue_reverse(p, hw_port_list, list) { - if (p->dev->mtu == p->old_mtu) - continue; - - if (dev_set_mtu(p->dev, p->old_mtu)) - netdev_err(p->dev, "Failed to restore MTU\n"); - } - - return err; -} - -static void dsa_hw_port_list_free(struct list_head *hw_port_list) -{ - struct dsa_hw_port *p, *n; - - list_for_each_entry_safe(p, n, hw_port_list, list) - kfree(p); -} - -/* Make the hardware datapath to/from @dev limited to a common MTU */ -static void dsa_bridge_mtu_normalization(struct dsa_port *dp) -{ - struct list_head hw_port_list; - struct dsa_switch_tree *dst; - int min_mtu = ETH_MAX_MTU; - struct dsa_port *other_dp; - int err; - - if (!dp->ds->mtu_enforcement_ingress) - return; - - if (!dp->bridge_dev) - return; - - INIT_LIST_HEAD(&hw_port_list); - - /* Populate the list of ports that are part of the same bridge - * as the newly added/modified port - */ - list_for_each_entry(dst, &dsa_tree_list, list) { - list_for_each_entry(other_dp, &dst->ports, list) { - struct dsa_hw_port *hw_port; - struct net_device *slave; - - if (other_dp->type != DSA_PORT_TYPE_USER) - continue; - - if (other_dp->bridge_dev != dp->bridge_dev) - continue; - - if (!other_dp->ds->mtu_enforcement_ingress) - continue; - - slave = other_dp->slave; - - if (min_mtu > slave->mtu) - min_mtu = slave->mtu; - - hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); - if (!hw_port) - goto out; - - hw_port->dev = slave; - hw_port->old_mtu = slave->mtu; - - list_add(&hw_port->list, &hw_port_list); - } - } - - /* Attempt to configure the entire hardware bridge to the newly added - * interface's MTU first, regardless of whether the intention of the - * user was to raise or lower it. - */ - err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->slave->mtu); - if (!err) - goto out; - - /* Clearly that didn't work out so well, so just set the minimum MTU on - * all hardware bridge ports now. If this fails too, then all ports will - * still have their old MTU rolled back anyway. - */ - dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); - -out: - dsa_hw_port_list_free(&hw_port_list); -} - -static 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); - struct dsa_slave_priv *p = netdev_priv(dev); - struct dsa_switch *ds = p->dp->ds; - struct dsa_port *cpu_dp; - int port = p->dp->index; - int largest_mtu = 0; - int new_master_mtu; - int old_master_mtu; - int mtu_limit; - int cpu_mtu; - int err, i; - - if (!ds->ops->port_change_mtu) - return -EOPNOTSUPP; - - for (i = 0; i < ds->num_ports; i++) { - int slave_mtu; - - if (!dsa_is_user_port(ds, i)) - continue; - - /* During probe, this function will be called for each slave - * device, while not all of them have been allocated. That's - * ok, it doesn't change what the maximum is, so ignore it. - */ - if (!dsa_to_port(ds, i)->slave) - continue; - - /* Pretend that we already applied the setting, which we - * actually haven't (still haven't done all integrity checks) - */ - if (i == port) - slave_mtu = new_mtu; - else - slave_mtu = dsa_to_port(ds, i)->slave->mtu; - - if (largest_mtu < slave_mtu) - largest_mtu = slave_mtu; - } - - cpu_dp = dsa_to_port(ds, port)->cpu_dp; - - mtu_limit = min_t(int, master->max_mtu, dev->max_mtu); - old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead; - if (new_master_mtu > mtu_limit) - return -ERANGE; - - /* If the master MTU isn't over limit, there's no need to check the CPU - * MTU, since that surely isn't either. - */ - cpu_mtu = largest_mtu; - - /* Start applying stuff */ - if (new_master_mtu != old_master_mtu) { - err = dev_set_mtu(master, new_master_mtu); - if (err < 0) - goto out_master_failed; - - /* We only need to propagate the MTU of the CPU port to - * upstream switches. - */ - err = dsa_port_mtu_change(cpu_dp, cpu_mtu, true); - if (err) - goto out_cpu_failed; - } - - err = dsa_port_mtu_change(dp, new_mtu, false); - if (err) - goto out_port_failed; - - dev->mtu = new_mtu; - - dsa_bridge_mtu_normalization(dp); - - return 0; - -out_port_failed: - if (new_master_mtu != old_master_mtu) - dsa_port_mtu_change(cpu_dp, old_master_mtu - - cpu_dp->tag_ops->overhead, - true); -out_cpu_failed: - if (new_master_mtu != old_master_mtu) - dev_set_mtu(master, old_master_mtu); -out_master_failed: - return err; -} - -static const struct ethtool_ops dsa_slave_ethtool_ops = { - .get_drvinfo = dsa_slave_get_drvinfo, - .get_regs_len = dsa_slave_get_regs_len, - .get_regs = dsa_slave_get_regs, - .nway_reset = dsa_slave_nway_reset, - .get_link = ethtool_op_get_link, - .get_eeprom_len = dsa_slave_get_eeprom_len, - .get_eeprom = dsa_slave_get_eeprom, - .set_eeprom = dsa_slave_set_eeprom, - .get_strings = dsa_slave_get_strings, - .get_ethtool_stats = dsa_slave_get_ethtool_stats, - .get_sset_count = dsa_slave_get_sset_count, - .set_wol = dsa_slave_set_wol, - .get_wol = dsa_slave_get_wol, - .set_eee = dsa_slave_set_eee, - .get_eee = dsa_slave_get_eee, - .get_link_ksettings = dsa_slave_get_link_ksettings, - .set_link_ksettings = dsa_slave_set_link_ksettings, - .get_pauseparam = dsa_slave_get_pauseparam, - .set_pauseparam = dsa_slave_set_pauseparam, - .get_rxnfc = dsa_slave_get_rxnfc, - .set_rxnfc = dsa_slave_set_rxnfc, - .get_ts_info = dsa_slave_get_ts_info, -}; - -/* 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) -{ - 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) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_fdb_del(dp, addr, vid); -} - -static struct devlink_port *dsa_slave_get_devlink_port(struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dp->ds->devlink ? &dp->devlink_port : NULL; -} - -static const struct net_device_ops dsa_slave_netdev_ops = { - .ndo_open = dsa_slave_open, - .ndo_stop = dsa_slave_close, - .ndo_start_xmit = dsa_slave_xmit, - .ndo_change_rx_flags = dsa_slave_change_rx_flags, - .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_add = dsa_legacy_fdb_add, - .ndo_fdb_del = dsa_legacy_fdb_del, - .ndo_fdb_dump = dsa_slave_fdb_dump, - .ndo_do_ioctl = dsa_slave_ioctl, - .ndo_get_iflink = dsa_slave_get_iflink, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_netpoll_setup = dsa_slave_netpoll_setup, - .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, - .ndo_poll_controller = dsa_slave_poll_controller, -#endif - .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, - .ndo_setup_tc = dsa_slave_setup_tc, - .ndo_get_stats64 = dsa_slave_get_stats64, - .ndo_get_port_parent_id = dsa_slave_get_port_parent_id, - .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_get_devlink_port = dsa_slave_get_devlink_port, - .ndo_change_mtu = dsa_slave_change_mtu, -}; - -static struct device_type dsa_type = { - .name = "dsa", -}; - -void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) -{ - const struct dsa_port *dp = dsa_to_port(ds, port); - - if (dp->pl) - phylink_mac_change(dp->pl, up); -} -EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); - -static void dsa_slave_phylink_fixed_state(struct phylink_config *config, - struct phylink_link_state *state) -{ - struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); - struct dsa_switch *ds = dp->ds; - - /* No need to check that this operation is valid, the callback would - * not be called if it was not. - */ - ds->ops->phylink_fixed_state(ds, dp->index, state); -} - -/* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) -{ - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_switch *ds = dp->ds; - - slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); - if (!slave_dev->phydev) { - netdev_err(slave_dev, "no phy at %d\n", addr); - return -ENODEV; - } - - return phylink_connect_phy(dp->pl, slave_dev->phydev); -} - -static int dsa_slave_phy_setup(struct net_device *slave_dev) -{ - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct device_node *port_dn = dp->dn; - struct dsa_switch *ds = dp->ds; - phy_interface_t mode; - u32 phy_flags = 0; - int ret; - - ret = of_get_phy_mode(port_dn, &mode); - if (ret) - mode = PHY_INTERFACE_MODE_NA; - - dp->pl_config.dev = &slave_dev->dev; - dp->pl_config.type = PHYLINK_NETDEV; - - /* The get_fixed_state callback takes precedence over polling the - * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set - * this if the switch provides such a callback. - */ - if (ds->ops->phylink_fixed_state) { - dp->pl_config.get_fixed_state = dsa_slave_phylink_fixed_state; - dp->pl_config.poll_fixed_state = true; - } - - dp->pl = phylink_create(&dp->pl_config, of_fwnode_handle(port_dn), mode, - &dsa_port_phylink_mac_ops); - if (IS_ERR(dp->pl)) { - netdev_err(slave_dev, - "error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); - return PTR_ERR(dp->pl); - } - - if (ds->ops->get_phy_flags) - phy_flags = ds->ops->get_phy_flags(ds, dp->index); - - ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); - if (ret == -ENODEV && ds->slave_mii_bus) { - /* We could not connect to a designated PHY or SFP, so try to - * use the switch internal MDIO bus instead - */ - ret = dsa_slave_phy_connect(slave_dev, dp->index); - if (ret) { - netdev_err(slave_dev, - "failed to connect to port %d: %d\n", - dp->index, ret); - phylink_destroy(dp->pl); - return ret; - } - } - - return ret; -} - -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, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &dsa_slave_netdev_xmit_lock_key); -} - -int dsa_slave_suspend(struct net_device *slave_dev) -{ - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - - if (!netif_running(slave_dev)) - return 0; - - netif_device_detach(slave_dev); - - rtnl_lock(); - phylink_stop(dp->pl); - rtnl_unlock(); - - return 0; -} - -int dsa_slave_resume(struct net_device *slave_dev) -{ - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - - if (!netif_running(slave_dev)) - return 0; - - netif_device_attach(slave_dev); - - rtnl_lock(); - phylink_start(dp->pl); - rtnl_unlock(); - - 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; - struct net_device *master = cpu_dp->master; - struct dsa_switch *ds = port->ds; - const char *name = port->name; - struct net_device *slave_dev; - struct dsa_slave_priv *p; - int ret; - - if (!ds->num_tx_queues) - ds->num_tx_queues = 1; - - slave_dev = alloc_netdev_mqs(sizeof(struct dsa_slave_priv), name, - NET_NAME_UNKNOWN, ether_setup, - ds->num_tx_queues, 1); - if (slave_dev == NULL) - return -ENOMEM; - - slave_dev->features = master->vlan_features | NETIF_F_HW_TC; - if (ds->ops->port_vlan_add && ds->ops->port_vlan_del) - slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - slave_dev->hw_features |= NETIF_F_HW_TC; - slave_dev->features |= NETIF_F_LLTX; - slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; - if (!IS_ERR_OR_NULL(port->mac)) - ether_addr_copy(slave_dev->dev_addr, port->mac); - else - eth_hw_addr_inherit(slave_dev, master); - slave_dev->priv_flags |= IFF_NO_QUEUE; - slave_dev->netdev_ops = &dsa_slave_netdev_ops; - slave_dev->min_mtu = 0; - if (ds->ops->port_max_mtu) - slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); - else - slave_dev->max_mtu = ETH_MAX_MTU; - SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - - netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, - NULL); - - SET_NETDEV_DEV(slave_dev, port->ds->dev); - slave_dev->dev.of_node = port->dn; - 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) { - free_netdev(slave_dev); - return -ENOMEM; - } - - ret = gro_cells_init(&p->gcells, slave_dev); - if (ret) - goto out_free; - - p->dp = port; - INIT_LIST_HEAD(&p->mall_tc_list); - p->xmit = cpu_dp->tag_ops->xmit; - port->slave = 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); - - netif_carrier_off(slave_dev); - - ret = dsa_slave_phy_setup(slave_dev); - if (ret) { - netdev_err(master, "error %d setting up slave phy\n", ret); - goto out_gcells; - } - - dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); - - ret = register_netdev(slave_dev); - if (ret) { - netdev_err(master, "error %d registering interface %s\n", - ret, slave_dev->name); - goto out_phy; - } - - return 0; - -out_phy: - rtnl_lock(); - phylink_disconnect_phy(p->dp->pl); - rtnl_unlock(); - phylink_destroy(p->dp->pl); -out_gcells: - gro_cells_destroy(&p->gcells); -out_free: - free_percpu(p->stats64); - free_netdev(slave_dev); - port->slave = NULL; - return ret; -} - -void dsa_slave_destroy(struct net_device *slave_dev) -{ - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); - - netif_carrier_off(slave_dev); - rtnl_lock(); - phylink_disconnect_phy(dp->pl); - rtnl_unlock(); - - dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); - unregister_netdev(slave_dev); - phylink_destroy(dp->pl); - gro_cells_destroy(&p->gcells); - free_percpu(p->stats64); - free_netdev(slave_dev); -} - -bool dsa_slave_dev_check(const struct net_device *dev) -{ - return dev->netdev_ops == &dsa_slave_netdev_ops; -} - -static int dsa_slave_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - int err = NOTIFY_DONE; - - if (netif_is_bridge_master(info->upper_dev)) { - if (info->linking) { - err = dsa_port_bridge_join(dp, info->upper_dev); - if (!err) - dsa_bridge_mtu_normalization(dp); - err = notifier_from_errno(err); - } else { - dsa_port_bridge_leave(dp, info->upper_dev); - err = NOTIFY_OK; - } - } - - return err; -} - -static int dsa_slave_upper_vlan_check(struct net_device *dev, - struct netdev_notifier_changeupper_info * - info) -{ - struct netlink_ext_ack *ext_ack; - struct net_device *slave; - struct dsa_port *dp; - - ext_ack = netdev_notifier_info_to_extack(&info->info); - - if (!is_vlan_dev(dev)) - return NOTIFY_DONE; - - slave = vlan_dev_real_dev(dev); - if (!dsa_slave_dev_check(slave)) - return NOTIFY_DONE; - - dp = dsa_slave_to_port(slave); - if (!dp->bridge_dev) - return NOTIFY_DONE; - - /* Deny enslaving a VLAN device into a VLAN-aware bridge */ - if (br_vlan_enabled(dp->bridge_dev) && - netif_is_bridge_master(info->upper_dev) && info->linking) { - NL_SET_ERR_MSG_MOD(ext_ack, - "Cannot enslave VLAN device into VLAN aware bridge"); - return notifier_from_errno(-EINVAL); - } - - 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) { - if (!dsa_slave_dev_check(dev)) - return dsa_slave_upper_vlan_check(dev, ptr); - - return dsa_slave_changeupper(dev, ptr); - } - - 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_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); - int err; - - 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); - if (err) { - netdev_dbg(dev, "fdb add failed err=%d\n", err); - break; - } - fdb_info->offloaded = true; - call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, - &fdb_info->info, NULL); - 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); - if (err) { - netdev_dbg(dev, "fdb del failed err=%d\n", err); - dev_close(dev); - } - break; - } - rtnl_unlock(); - - kfree(switchdev_work->fdb_info.addr); - kfree(switchdev_work); - dev_put(dev); -} - -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); - return 0; -} - -/* 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); - struct dsa_switchdev_event_work *switchdev_work; - int err; - - if (event == 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); - } - - if (!dsa_slave_dev_check(dev)) - return NOTIFY_DONE; - - switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); - if (!switchdev_work) - return NOTIFY_BAD; - - INIT_WORK(&switchdev_work->work, - dsa_slave_switchdev_event_work); - switchdev_work->dev = dev; - switchdev_work->event = event; - - switch (event) { - case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ - case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) - goto err_fdb_work_init; - dev_hold(dev); - 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, - unsigned long event, void *ptr) -{ - struct net_device *dev = switchdev_notifier_info_to_dev(ptr); - int err; - - switch (event) { - case SWITCHDEV_PORT_OBJ_ADD: - err = switchdev_handle_port_obj_add(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_obj_add); - return notifier_from_errno(err); - case SWITCHDEV_PORT_OBJ_DEL: - err = switchdev_handle_port_obj_del(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_obj_del); - return notifier_from_errno(err); - 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); - } - - return NOTIFY_DONE; -} - -static struct notifier_block dsa_slave_nb __read_mostly = { - .notifier_call = dsa_slave_netdevice_event, -}; - -static struct notifier_block dsa_slave_switchdev_notifier = { - .notifier_call = dsa_slave_switchdev_event, -}; - -static struct notifier_block dsa_slave_switchdev_blocking_notifier = { - .notifier_call = dsa_slave_switchdev_blocking_event, -}; - -int dsa_slave_register_notifier(void) -{ - struct notifier_block *nb; - int err; - - err = register_netdevice_notifier(&dsa_slave_nb); - if (err) - return err; - - err = register_switchdev_notifier(&dsa_slave_switchdev_notifier); - if (err) - goto err_switchdev_nb; - - nb = &dsa_slave_switchdev_blocking_notifier; - err = register_switchdev_blocking_notifier(nb); - if (err) - goto err_switchdev_blocking_nb; - - return 0; - -err_switchdev_blocking_nb: - unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); -err_switchdev_nb: - unregister_netdevice_notifier(&dsa_slave_nb); - return err; -} - -void dsa_slave_unregister_notifier(void) -{ - struct notifier_block *nb; - int err; - - nb = &dsa_slave_switchdev_blocking_notifier; - err = unregister_switchdev_blocking_notifier(nb); - if (err) - pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); - - err = unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); - if (err) - pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); - - err = unregister_netdevice_notifier(&dsa_slave_nb); - if (err) - pr_err("DSA: failed to unregister slave notifier (%d)\n", err); -} diff --git a/net/dsa/stubs.c b/net/dsa/stubs.c new file mode 100644 index 000000000000..2ed8a6c85fbf --- /dev/null +++ b/net/dsa/stubs.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Stubs for DSA functionality called by the core network stack. + * These are necessary because CONFIG_NET_DSA can be a module, and built-in + * code cannot directly call symbols exported by modules. + */ +#include <net/dsa_stubs.h> + +const struct dsa_stubs *dsa_stubs; +EXPORT_SYMBOL_GPL(dsa_stubs); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 86c8dc5c32a0..3d2feeea897b 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -12,19 +12,22 @@ #include <linux/if_vlan.h> #include <net/switchdev.h> -#include "dsa_priv.h" +#include "dsa.h" +#include "netlink.h" +#include "port.h" +#include "switch.h" +#include "tag_8021q.h" +#include "trace.h" +#include "user.h" static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) { - int i; - - for (i = 0; i < ds->num_ports; ++i) { - struct dsa_port *dp = dsa_to_port(ds, i); + struct dsa_port *dp; + dsa_switch_for_each_port(dp, ds) if (dp->ageing_time && dp->ageing_time < ageing_time) ageing_time = dp->ageing_time; - } return ageing_time; } @@ -33,15 +36,12 @@ 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); @@ -52,32 +52,25 @@ static int dsa_switch_ageing_time(struct dsa_switch *ds, return 0; } -static bool dsa_switch_mtu_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mtu_info *info) +static bool dsa_port_mtu_match(struct dsa_port *dp, + struct dsa_notifier_mtu_info *info) { - if (ds->index == info->sw_index) - return (port == info->port) || dsa_is_dsa_port(ds, port); - - if (!info->propagate_upstream) - return false; - - if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) - return true; - - return false; + return dp == info->dp || dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp); } static int dsa_switch_mtu(struct dsa_switch *ds, struct dsa_notifier_mtu_info *info) { - int port, ret; + struct dsa_port *dp; + int ret; if (!ds->ops->port_change_mtu) return -EOPNOTSUPP; - for (port = 0; port < ds->num_ports; port++) { - if (dsa_switch_mtu_match(ds, port, info)) { - ret = ds->ops->port_change_mtu(ds, port, info->mtu); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_mtu_match(dp, info)) { + ret = ds->ops->port_change_mtu(ds, dp->index, + info->mtu); if (ret) return ret; } @@ -89,17 +82,30 @@ static int dsa_switch_mtu(struct dsa_switch *ds, static int dsa_switch_bridge_join(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { - struct dsa_switch_tree *dst = ds->dst; + int err; - if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) - return ds->ops->port_bridge_join(ds, info->port, info->br); + if (info->dp->ds == ds) { + if (!ds->ops->port_bridge_join) + return -EOPNOTSUPP; - if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) - return ds->ops->crosschip_bridge_join(ds, info->tree_index, - info->sw_index, - info->port, info->br); + err = ds->ops->port_bridge_join(ds, info->dp->index, + info->bridge, + &info->tx_fwd_offload, + info->extack); + if (err) + return err; + } + + if (info->dp->ds != ds && ds->ops->crosschip_bridge_join) { + err = ds->ops->crosschip_bridge_join(ds, + info->dp->ds->dst->index, + info->dp->ds->index, + info->dp->index, + info->bridge, + info->extack); + if (err) + return err; + } return 0; } @@ -107,195 +113,714 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, static int dsa_switch_bridge_leave(struct dsa_switch *ds, struct dsa_notifier_bridge_info *info) { - bool unset_vlan_filtering = br_vlan_enabled(info->br); - struct dsa_switch_tree *dst = ds->dst; - int err, i; - - if (dst->index == info->tree_index && ds->index == info->sw_index && - ds->ops->port_bridge_join) - ds->ops->port_bridge_leave(ds, info->port, info->br); - - if ((dst->index != info->tree_index || ds->index != info->sw_index) && - ds->ops->crosschip_bridge_join) - ds->ops->crosschip_bridge_leave(ds, info->tree_index, - info->sw_index, info->port, - info->br); - - /* If the bridge was vlan_filtering, the bridge core doesn't trigger an - * event for changing vlan_filtering setting upon slave ports leaving - * it. That is a good thing, because that lets us handle it and also - * handle the case where the switch's vlan_filtering setting is global - * (not per port). When that happens, the correct moment to trigger the - * vlan_filtering callback is only when the last port left this bridge. - */ - if (unset_vlan_filtering && ds->vlan_filtering_is_global) { - for (i = 0; i < ds->num_ports; i++) { - if (i == info->port) - continue; - if (dsa_to_port(ds, i)->bridge_dev == info->br) { - unset_vlan_filtering = false; - break; + if (info->dp->ds == ds && ds->ops->port_bridge_leave) + ds->ops->port_bridge_leave(ds, info->dp->index, info->bridge); + + if (info->dp->ds != ds && ds->ops->crosschip_bridge_leave) + ds->ops->crosschip_bridge_leave(ds, info->dp->ds->dst->index, + info->dp->ds->index, + info->dp->index, + info->bridge); + + return 0; +} + +/* Matches for all upstream-facing ports (the CPU port and all upstream-facing + * DSA links) that sit between the targeted port on which the notifier was + * emitted and its dedicated CPU port. + */ +static bool dsa_port_host_address_match(struct dsa_port *dp, + const struct dsa_port *targeted_dp) +{ + struct dsa_port *cpu_dp = targeted_dp->cpu_dp; + + if (dsa_switch_is_upstream_of(dp->ds, targeted_dp->ds)) + return dp->index == dsa_towards_port(dp->ds, cpu_dp->ds->index, + cpu_dp->index); + + return false; +} + +static struct dsa_mac_addr *dsa_mac_addr_find(struct list_head *addr_list, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct dsa_mac_addr *a; + + list_for_each_entry(a, addr_list, list) + if (ether_addr_equal(a->addr, addr) && a->vid == vid && + dsa_db_equal(&a->db, &db)) + return a; + + return NULL; +} + +static int dsa_port_do_mdb_add(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_mac_addr *a; + int port = dp->index; + int err = 0; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_mdb_add(ds, port, mdb, db); + trace_dsa_mdb_add_hw(dp, mdb->addr, mdb->vid, &db, err); + + return err; + } + + mutex_lock(&dp->addr_lists_lock); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid, db); + if (a) { + refcount_inc(&a->refcount); + trace_dsa_mdb_add_bump(dp, mdb->addr, mdb->vid, &db, + &a->refcount); + goto out; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) { + err = -ENOMEM; + goto out; + } + + err = ds->ops->port_mdb_add(ds, port, mdb, db); + trace_dsa_mdb_add_hw(dp, mdb->addr, mdb->vid, &db, err); + if (err) { + kfree(a); + goto out; + } + + ether_addr_copy(a->addr, mdb->addr); + a->vid = mdb->vid; + a->db = db; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->mdbs); + +out: + mutex_unlock(&dp->addr_lists_lock); + + return err; +} + +static int dsa_port_do_mdb_del(struct dsa_port *dp, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_mac_addr *a; + int port = dp->index; + int err = 0; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_mdb_del(ds, port, mdb, db); + trace_dsa_mdb_del_hw(dp, mdb->addr, mdb->vid, &db, err); + + return err; + } + + mutex_lock(&dp->addr_lists_lock); + + a = dsa_mac_addr_find(&dp->mdbs, mdb->addr, mdb->vid, db); + if (!a) { + trace_dsa_mdb_del_not_found(dp, mdb->addr, mdb->vid, &db); + err = -ENOENT; + goto out; + } + + if (!refcount_dec_and_test(&a->refcount)) { + trace_dsa_mdb_del_drop(dp, mdb->addr, mdb->vid, &db, + &a->refcount); + goto out; + } + + err = ds->ops->port_mdb_del(ds, port, mdb, db); + trace_dsa_mdb_del_hw(dp, mdb->addr, mdb->vid, &db, err); + if (err) { + refcount_set(&a->refcount, 1); + goto out; + } + + list_del(&a->list); + kfree(a); + +out: + mutex_unlock(&dp->addr_lists_lock); + + return err; +} + +static int dsa_port_do_fdb_add(struct dsa_port *dp, const unsigned char *addr, + u16 vid, struct dsa_db db) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_mac_addr *a; + int port = dp->index; + int err = 0; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_fdb_add(ds, port, addr, vid, db); + trace_dsa_fdb_add_hw(dp, addr, vid, &db, err); + + return err; + } + + mutex_lock(&dp->addr_lists_lock); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid, db); + if (a) { + refcount_inc(&a->refcount); + trace_dsa_fdb_add_bump(dp, addr, vid, &db, &a->refcount); + goto out; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) { + err = -ENOMEM; + goto out; + } + + err = ds->ops->port_fdb_add(ds, port, addr, vid, db); + trace_dsa_fdb_add_hw(dp, addr, vid, &db, err); + if (err) { + kfree(a); + goto out; + } + + ether_addr_copy(a->addr, addr); + a->vid = vid; + a->db = db; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &dp->fdbs); + +out: + mutex_unlock(&dp->addr_lists_lock); + + return err; +} + +static int dsa_port_do_fdb_del(struct dsa_port *dp, const unsigned char *addr, + u16 vid, struct dsa_db db) +{ + struct dsa_switch *ds = dp->ds; + struct dsa_mac_addr *a; + int port = dp->index; + int err = 0; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_fdb_del(ds, port, addr, vid, db); + trace_dsa_fdb_del_hw(dp, addr, vid, &db, err); + + return err; + } + + mutex_lock(&dp->addr_lists_lock); + + a = dsa_mac_addr_find(&dp->fdbs, addr, vid, db); + if (!a) { + trace_dsa_fdb_del_not_found(dp, addr, vid, &db); + err = -ENOENT; + goto out; + } + + if (!refcount_dec_and_test(&a->refcount)) { + trace_dsa_fdb_del_drop(dp, addr, vid, &db, &a->refcount); + goto out; + } + + err = ds->ops->port_fdb_del(ds, port, addr, vid, db); + trace_dsa_fdb_del_hw(dp, addr, vid, &db, err); + if (err) { + refcount_set(&a->refcount, 1); + goto out; + } + + list_del(&a->list); + kfree(a); + +out: + mutex_unlock(&dp->addr_lists_lock); + + return err; +} + +static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct dsa_mac_addr *a; + int err = 0; + + mutex_lock(&lag->fdb_lock); + + a = dsa_mac_addr_find(&lag->fdbs, addr, vid, db); + if (a) { + refcount_inc(&a->refcount); + trace_dsa_lag_fdb_add_bump(lag->dev, addr, vid, &db, + &a->refcount); + goto out; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) { + err = -ENOMEM; + goto out; + } + + err = ds->ops->lag_fdb_add(ds, *lag, addr, vid, db); + trace_dsa_lag_fdb_add_hw(lag->dev, addr, vid, &db, err); + if (err) { + kfree(a); + goto out; + } + + ether_addr_copy(a->addr, addr); + a->vid = vid; + a->db = db; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &lag->fdbs); + +out: + mutex_unlock(&lag->fdb_lock); + + return err; +} + +static int dsa_switch_do_lag_fdb_del(struct dsa_switch *ds, struct dsa_lag *lag, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + struct dsa_mac_addr *a; + int err = 0; + + mutex_lock(&lag->fdb_lock); + + a = dsa_mac_addr_find(&lag->fdbs, addr, vid, db); + if (!a) { + trace_dsa_lag_fdb_del_not_found(lag->dev, addr, vid, &db); + err = -ENOENT; + goto out; + } + + if (!refcount_dec_and_test(&a->refcount)) { + trace_dsa_lag_fdb_del_drop(lag->dev, addr, vid, &db, + &a->refcount); + goto out; + } + + err = ds->ops->lag_fdb_del(ds, *lag, addr, vid, db); + trace_dsa_lag_fdb_del_hw(lag->dev, addr, vid, &db, err); + if (err) { + refcount_set(&a->refcount, 1); + goto out; + } + + list_del(&a->list); + kfree(a); + +out: + mutex_unlock(&lag->fdb_lock); + + return err; +} + +static int dsa_switch_host_fdb_add(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + struct dsa_port *dp; + int err = 0; + + if (!ds->ops->port_fdb_add) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->dp)) { + if (dsa_port_is_cpu(dp) && info->dp->cpu_port_in_lag) { + err = dsa_switch_do_lag_fdb_add(ds, dp->lag, + info->addr, + info->vid, + info->db); + } else { + err = dsa_port_do_fdb_add(dp, info->addr, + info->vid, info->db); } + if (err) + break; } } - if (unset_vlan_filtering) { - struct switchdev_trans trans = {0}; - err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port), - false, &trans); - if (err && err != EOPNOTSUPP) - return err; + return err; +} + +static int dsa_switch_host_fdb_del(struct dsa_switch *ds, + struct dsa_notifier_fdb_info *info) +{ + struct dsa_port *dp; + int err = 0; + + if (!ds->ops->port_fdb_del) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->dp)) { + if (dsa_port_is_cpu(dp) && info->dp->cpu_port_in_lag) { + err = dsa_switch_do_lag_fdb_del(ds, dp->lag, + info->addr, + info->vid, + info->db); + } else { + err = dsa_port_do_fdb_del(dp, info->addr, + info->vid, info->db); + } + if (err) + break; + } } - return 0; + + return err; } static int dsa_switch_fdb_add(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { - int port = dsa_towards_port(ds, info->sw_index, info->port); + int port = dsa_towards_port(ds, info->dp->ds->index, info->dp->index); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_fdb_add) return -EOPNOTSUPP; - return ds->ops->port_fdb_add(ds, port, info->addr, info->vid); + return dsa_port_do_fdb_add(dp, info->addr, info->vid, info->db); } static int dsa_switch_fdb_del(struct dsa_switch *ds, struct dsa_notifier_fdb_info *info) { - int port = dsa_towards_port(ds, info->sw_index, info->port); + int port = dsa_towards_port(ds, info->dp->ds->index, info->dp->index); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_fdb_del) return -EOPNOTSUPP; - return ds->ops->port_fdb_del(ds, port, info->addr, info->vid); + return dsa_port_do_fdb_del(dp, info->addr, info->vid, info->db); } -static bool dsa_switch_mdb_match(struct dsa_switch *ds, int port, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_lag_fdb_add(struct dsa_switch *ds, + struct dsa_notifier_lag_fdb_info *info) { - if (ds->index == info->sw_index && port == info->port) - return true; + struct dsa_port *dp; - if (dsa_is_dsa_port(ds, port)) - return true; + if (!ds->ops->lag_fdb_add) + return -EOPNOTSUPP; - return false; + /* Notify switch only if it has a port in this LAG */ + dsa_switch_for_each_port(dp, ds) + if (dsa_port_offloads_lag(dp, info->lag)) + return dsa_switch_do_lag_fdb_add(ds, info->lag, + info->addr, info->vid, + info->db); + + return 0; } -static int dsa_switch_mdb_prepare(struct dsa_switch *ds, - struct dsa_notifier_mdb_info *info) +static int dsa_switch_lag_fdb_del(struct dsa_switch *ds, + struct dsa_notifier_lag_fdb_info *info) { - int port, err; + struct dsa_port *dp; - if (!ds->ops->port_mdb_prepare || !ds->ops->port_mdb_add) + if (!ds->ops->lag_fdb_del) 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); - if (err) - return err; - } - } + /* Notify switch only if it has a port in this LAG */ + dsa_switch_for_each_port(dp, ds) + if (dsa_port_offloads_lag(dp, info->lag)) + return dsa_switch_do_lag_fdb_del(ds, info->lag, + info->addr, info->vid, + info->db); + + return 0; +} + +static int dsa_switch_lag_change(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (info->dp->ds == ds && ds->ops->port_lag_change) + return ds->ops->port_lag_change(ds, info->dp->index); + + if (info->dp->ds != ds && ds->ops->crosschip_lag_change) + return ds->ops->crosschip_lag_change(ds, info->dp->ds->index, + info->dp->index); return 0; } +static int dsa_switch_lag_join(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (info->dp->ds == ds && ds->ops->port_lag_join) + return ds->ops->port_lag_join(ds, info->dp->index, info->lag, + info->info, info->extack); + + if (info->dp->ds != ds && ds->ops->crosschip_lag_join) + return ds->ops->crosschip_lag_join(ds, info->dp->ds->index, + info->dp->index, info->lag, + info->info, info->extack); + + return -EOPNOTSUPP; +} + +static int dsa_switch_lag_leave(struct dsa_switch *ds, + struct dsa_notifier_lag_info *info) +{ + if (info->dp->ds == ds && ds->ops->port_lag_leave) + return ds->ops->port_lag_leave(ds, info->dp->index, info->lag); + + if (info->dp->ds != ds && ds->ops->crosschip_lag_leave) + return ds->ops->crosschip_lag_leave(ds, info->dp->ds->index, + info->dp->index, info->lag); + + return -EOPNOTSUPP; +} + static int dsa_switch_mdb_add(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { - int port; - - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_mdb_prepare(ds, info); + int port = dsa_towards_port(ds, info->dp->ds->index, info->dp->index); + struct dsa_port *dp = dsa_to_port(ds, port); if (!ds->ops->port_mdb_add) - 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); + return -EOPNOTSUPP; - return 0; + return dsa_port_do_mdb_add(dp, info->mdb, info->db); } static int dsa_switch_mdb_del(struct dsa_switch *ds, struct dsa_notifier_mdb_info *info) { + int port = dsa_towards_port(ds, info->dp->ds->index, info->dp->index); + struct dsa_port *dp = dsa_to_port(ds, port); + if (!ds->ops->port_mdb_del) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_mdb_del(ds, info->port, info->mdb); + return dsa_port_do_mdb_del(dp, info->mdb, info->db); +} - return 0; +static int dsa_switch_host_mdb_add(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) +{ + struct dsa_port *dp; + int err = 0; + + if (!ds->ops->port_mdb_add) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->dp)) { + err = dsa_port_do_mdb_add(dp, info->mdb, info->db); + if (err) + break; + } + } + + return err; } -static int dsa_port_vlan_device_check(struct net_device *vlan_dev, - int vlan_dev_vid, - void *arg) +static int dsa_switch_host_mdb_del(struct dsa_switch *ds, + struct dsa_notifier_mdb_info *info) { - struct switchdev_obj_port_vlan *vlan = arg; - u16 vid; + struct dsa_port *dp; + int err = 0; - for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { - if (vid == vlan_dev_vid) - return -EBUSY; + if (!ds->ops->port_mdb_del) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_address_match(dp, info->dp)) { + err = dsa_port_do_mdb_del(dp, info->mdb, info->db); + if (err) + break; + } } - return 0; + return err; +} + +/* Port VLANs match on the targeted port and on all DSA ports */ +static bool dsa_port_vlan_match(struct dsa_port *dp, + struct dsa_notifier_vlan_info *info) +{ + return dsa_port_is_dsa(dp) || dp == info->dp; +} + +/* Host VLANs match on the targeted port's CPU port, and on all DSA ports + * (upstream and downstream) of that switch and its upstream switches. + */ +static bool dsa_port_host_vlan_match(struct dsa_port *dp, + const struct dsa_port *targeted_dp) +{ + struct dsa_port *cpu_dp = targeted_dp->cpu_dp; + + if (dsa_switch_is_upstream_of(dp->ds, targeted_dp->ds)) + return dsa_port_is_dsa(dp) || dp == cpu_dp; + + return false; } -static int dsa_port_vlan_check(struct dsa_switch *ds, int port, +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, const struct switchdev_obj_port_vlan *vlan) { - const struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_vlan *v; + + list_for_each_entry(v, vlan_list, list) + if (v->vid == vlan->vid) + return v; + + return NULL; +} + +static int dsa_port_do_vlan_add(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + struct dsa_vlan *v; int err = 0; - /* Device is not bridged, let it proceed with the VLAN device - * creation. - */ - if (!dp->bridge_dev) + /* No need to bother with refcounting for user ports. */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_vlan_add(ds, port, vlan, extack); + trace_dsa_vlan_add_hw(dp, vlan, err); + 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. + /* No need to propagate on shared ports the existing VLANs that were + * re-notified after just the flags have changed. This would cause a + * refcount bump which we need to avoid, since it unbalances the + * additions with the deletions. */ - return vlan_for_each(dp->slave, dsa_port_vlan_device_check, - (void *)vlan); + if (vlan->changed) + return 0; + + mutex_lock(&dp->vlans_lock); + + v = dsa_vlan_find(&dp->vlans, vlan); + if (v) { + refcount_inc(&v->refcount); + trace_dsa_vlan_add_bump(dp, vlan, &v->refcount); + goto out; + } + + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) { + err = -ENOMEM; + goto out; + } + + err = ds->ops->port_vlan_add(ds, port, vlan, extack); + trace_dsa_vlan_add_hw(dp, vlan, err); + if (err) { + kfree(v); + goto out; + } + + v->vid = vlan->vid; + refcount_set(&v->refcount, 1); + list_add_tail(&v->list, &dp->vlans); + +out: + mutex_unlock(&dp->vlans_lock); + + return err; } -static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port, - struct dsa_notifier_vlan_info *info) +static int dsa_port_do_vlan_del(struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan) { - if (ds->index == info->sw_index && port == info->port) - return true; + struct dsa_switch *ds = dp->ds; + int port = dp->index; + struct dsa_vlan *v; + int err = 0; - if (dsa_is_dsa_port(ds, port)) - return true; + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) { + err = ds->ops->port_vlan_del(ds, port, vlan); + trace_dsa_vlan_del_hw(dp, vlan, err); - return false; + return err; + } + + mutex_lock(&dp->vlans_lock); + + v = dsa_vlan_find(&dp->vlans, vlan); + if (!v) { + trace_dsa_vlan_del_not_found(dp, vlan); + err = -ENOENT; + goto out; + } + + if (!refcount_dec_and_test(&v->refcount)) { + trace_dsa_vlan_del_drop(dp, vlan, &v->refcount); + goto out; + } + + err = ds->ops->port_vlan_del(ds, port, vlan); + trace_dsa_vlan_del_hw(dp, vlan, err); + if (err) { + refcount_set(&v->refcount, 1); + goto out; + } + + list_del(&v->list); + kfree(v); + +out: + mutex_unlock(&dp->vlans_lock); + + return err; } -static int dsa_switch_vlan_prepare(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int dsa_switch_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { - int port, err; + struct dsa_port *dp; + int err; - if (!ds->ops->port_vlan_prepare || !ds->ops->port_vlan_add) + if (!ds->ops->port_vlan_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); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_vlan_match(dp, info)) { + err = dsa_port_do_vlan_add(dp, info->vlan, + info->extack); if (err) return err; + } + } + + return 0; +} + +static int dsa_switch_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) +{ + struct dsa_port *dp; + int err; - err = ds->ops->port_vlan_prepare(ds, port, info->vlan); + if (!ds->ops->port_vlan_del) + return -EOPNOTSUPP; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_vlan_match(dp, info)) { + err = dsa_port_do_vlan_del(dp, info->vlan); if (err) return err; } @@ -304,39 +829,148 @@ static int dsa_switch_vlan_prepare(struct dsa_switch *ds, return 0; } -static int dsa_switch_vlan_add(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int dsa_switch_host_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { - int port; - - if (switchdev_trans_ph_prepare(info->trans)) - return dsa_switch_vlan_prepare(ds, info); + struct dsa_port *dp; + int err; if (!ds->ops->port_vlan_add) - return 0; + return -EOPNOTSUPP; - 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); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_vlan_match(dp, info->dp)) { + err = dsa_port_do_vlan_add(dp, info->vlan, + info->extack); + if (err) + return err; + } + } return 0; } -static int dsa_switch_vlan_del(struct dsa_switch *ds, - struct dsa_notifier_vlan_info *info) +static int dsa_switch_host_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_vlan_info *info) { + struct dsa_port *dp; + int err; + if (!ds->ops->port_vlan_del) return -EOPNOTSUPP; - if (ds->index == info->sw_index) - return ds->ops->port_vlan_del(ds, info->port, info->vlan); + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_host_vlan_match(dp, info->dp)) { + err = dsa_port_do_vlan_del(dp, info->vlan); + if (err) + return err; + } + } + + return 0; +} + +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; + struct dsa_port *dp, *cpu_dp; + int err; + + if (!ds->ops->change_tag_protocol) + return -EOPNOTSUPP; + + ASSERT_RTNL(); + + err = ds->ops->change_tag_protocol(ds, tag_ops->proto); + if (err) + return err; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) + dsa_port_set_tag_protocol(cpu_dp, 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. + */ + dsa_switch_for_each_user_port(dp, ds) { + struct net_device *user = dp->user; + + dsa_user_setup_tagger(user); + + /* rtnl_mutex is held in dsa_tree_change_tag_proto */ + dsa_user_change_mtu(user, user->mtu); + } + + return 0; +} + +/* We use the same cross-chip notifiers to inform both the tagger side, as well + * as the switch side, of connection and disconnection events. + * Since ds->tagger_data is owned by the tagger, it isn't a hard error if the + * switch side doesn't support connecting to this tagger, and therefore, the + * fact that we don't disconnect the tagger side doesn't constitute a memory + * leak: the tagger will still operate with persistent per-switch memory, just + * with the switch side unconnected to it. What does constitute a hard error is + * when the switch side supports connecting but fails. + */ +static int +dsa_switch_connect_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + int err; + + /* Notify the new tagger about the connection to this switch */ + if (tag_ops->connect) { + err = tag_ops->connect(ds); + if (err) + return err; + } + + if (!ds->ops->connect_tag_protocol) + return -EOPNOTSUPP; + + /* Notify the switch about the connection to the new tagger */ + err = ds->ops->connect_tag_protocol(ds, tag_ops->proto); + if (err) { + /* Revert the new tagger's connection to this tree */ + if (tag_ops->disconnect) + tag_ops->disconnect(ds); + return err; + } + + return 0; +} + +static int +dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, + struct dsa_notifier_tag_proto_info *info) +{ + const struct dsa_device_ops *tag_ops = info->tag_ops; + + /* Notify the tagger about the disconnection from this switch */ + if (tag_ops->disconnect && ds->tagger_data) + tag_ops->disconnect(ds); - /* Do not deprogram the DSA links as they may be used as conduit - * for other VLAN members in the fabric. + /* No need to notify the switch, since it shouldn't have any + * resources to tear down */ return 0; } +static int +dsa_switch_conduit_state_change(struct dsa_switch *ds, + struct dsa_notifier_conduit_state_info *info) +{ + if (!ds->ops->conduit_state_change) + return 0; + + ds->ops->conduit_state_change(ds, info->conduit, info->operational); + + return 0; +} + static int dsa_switch_event(struct notifier_block *nb, unsigned long event, void *info) { @@ -359,30 +993,77 @@ 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_HOST_FDB_ADD: + err = dsa_switch_host_fdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_FDB_DEL: + err = dsa_switch_host_fdb_del(ds, info); + break; + case DSA_NOTIFIER_LAG_FDB_ADD: + err = dsa_switch_lag_fdb_add(ds, info); + break; + case DSA_NOTIFIER_LAG_FDB_DEL: + err = dsa_switch_lag_fdb_del(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; case DSA_NOTIFIER_MDB_DEL: err = dsa_switch_mdb_del(ds, info); break; + case DSA_NOTIFIER_HOST_MDB_ADD: + err = dsa_switch_host_mdb_add(ds, info); + break; + case DSA_NOTIFIER_HOST_MDB_DEL: + err = dsa_switch_host_mdb_del(ds, info); + break; case DSA_NOTIFIER_VLAN_ADD: err = dsa_switch_vlan_add(ds, info); break; case DSA_NOTIFIER_VLAN_DEL: err = dsa_switch_vlan_del(ds, info); break; + case DSA_NOTIFIER_HOST_VLAN_ADD: + err = dsa_switch_host_vlan_add(ds, info); + break; + case DSA_NOTIFIER_HOST_VLAN_DEL: + err = dsa_switch_host_vlan_del(ds, info); + break; 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_TAG_PROTO_CONNECT: + err = dsa_switch_connect_tag_proto(ds, info); + break; + case DSA_NOTIFIER_TAG_PROTO_DISCONNECT: + err = dsa_switch_disconnect_tag_proto(ds, info); + break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_ADD: + err = dsa_switch_tag_8021q_vlan_add(ds, info); + break; + case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: + err = dsa_switch_tag_8021q_vlan_del(ds, info); + break; + case DSA_NOTIFIER_CONDUIT_STATE_CHANGE: + err = dsa_switch_conduit_state_change(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); @@ -390,6 +1071,52 @@ static int dsa_switch_event(struct notifier_block *nb, return notifier_from_errno(err); } +/** + * 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). + * + * WARNING: this function is not reliable during probe time, because probing + * between trees is asynchronous and not all DSA trees might have probed. + */ +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; +} + int dsa_switch_register_notifier(struct dsa_switch *ds) { ds->nb.notifier_call = dsa_switch_event; diff --git a/net/dsa/switch.h b/net/dsa/switch.h new file mode 100644 index 000000000000..be0a2749cd97 --- /dev/null +++ b/net/dsa/switch.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_SWITCH_H +#define __DSA_SWITCH_H + +#include <net/dsa.h> + +struct netlink_ext_ack; + +enum { + DSA_NOTIFIER_AGEING_TIME, + DSA_NOTIFIER_BRIDGE_JOIN, + DSA_NOTIFIER_BRIDGE_LEAVE, + DSA_NOTIFIER_FDB_ADD, + DSA_NOTIFIER_FDB_DEL, + DSA_NOTIFIER_HOST_FDB_ADD, + DSA_NOTIFIER_HOST_FDB_DEL, + DSA_NOTIFIER_LAG_FDB_ADD, + DSA_NOTIFIER_LAG_FDB_DEL, + DSA_NOTIFIER_LAG_CHANGE, + DSA_NOTIFIER_LAG_JOIN, + DSA_NOTIFIER_LAG_LEAVE, + DSA_NOTIFIER_MDB_ADD, + DSA_NOTIFIER_MDB_DEL, + DSA_NOTIFIER_HOST_MDB_ADD, + DSA_NOTIFIER_HOST_MDB_DEL, + DSA_NOTIFIER_VLAN_ADD, + DSA_NOTIFIER_VLAN_DEL, + DSA_NOTIFIER_HOST_VLAN_ADD, + DSA_NOTIFIER_HOST_VLAN_DEL, + DSA_NOTIFIER_MTU, + DSA_NOTIFIER_TAG_PROTO, + DSA_NOTIFIER_TAG_PROTO_CONNECT, + DSA_NOTIFIER_TAG_PROTO_DISCONNECT, + DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, + DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, + DSA_NOTIFIER_CONDUIT_STATE_CHANGE, +}; + +/* DSA_NOTIFIER_AGEING_TIME */ +struct dsa_notifier_ageing_time_info { + unsigned int ageing_time; +}; + +/* DSA_NOTIFIER_BRIDGE_* */ +struct dsa_notifier_bridge_info { + const struct dsa_port *dp; + struct dsa_bridge bridge; + bool tx_fwd_offload; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_FDB_* */ +struct dsa_notifier_fdb_info { + const struct dsa_port *dp; + const unsigned char *addr; + u16 vid; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_LAG_FDB_* */ +struct dsa_notifier_lag_fdb_info { + struct dsa_lag *lag; + const unsigned char *addr; + u16 vid; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_MDB_* */ +struct dsa_notifier_mdb_info { + const struct dsa_port *dp; + const struct switchdev_obj_port_mdb *mdb; + struct dsa_db db; +}; + +/* DSA_NOTIFIER_LAG_* */ +struct dsa_notifier_lag_info { + const struct dsa_port *dp; + struct dsa_lag lag; + struct netdev_lag_upper_info *info; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_VLAN_* */ +struct dsa_notifier_vlan_info { + const struct dsa_port *dp; + const struct switchdev_obj_port_vlan *vlan; + struct netlink_ext_ack *extack; +}; + +/* DSA_NOTIFIER_MTU */ +struct dsa_notifier_mtu_info { + const struct dsa_port *dp; + int mtu; +}; + +/* DSA_NOTIFIER_TAG_PROTO_* */ +struct dsa_notifier_tag_proto_info { + const struct dsa_device_ops *tag_ops; +}; + +/* DSA_NOTIFIER_TAG_8021Q_VLAN_* */ +struct dsa_notifier_tag_8021q_vlan_info { + const struct dsa_port *dp; + u16 vid; +}; + +/* DSA_NOTIFIER_CONDUIT_STATE_CHANGE */ +struct dsa_notifier_conduit_state_info { + const struct net_device *conduit; + bool operational; +}; + +struct dsa_vlan *dsa_vlan_find(struct list_head *vlan_list, + const struct switchdev_obj_port_vlan *vlan); + +int dsa_tree_notify(struct dsa_switch_tree *dst, unsigned long e, void *v); +int dsa_broadcast(unsigned long e, void *v); + +int dsa_switch_register_notifier(struct dsa_switch *ds); +void dsa_switch_unregister_notifier(struct dsa_switch *ds); + +#endif diff --git a/net/dsa/tag.c b/net/dsa/tag.c new file mode 100644 index 000000000000..79ad105902d9 --- /dev/null +++ b/net/dsa/tag.c @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * DSA tagging protocol handling + * + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> + */ + +#include <linux/netdevice.h> +#include <linux/ptp_classify.h> +#include <linux/skbuff.h> +#include <net/dsa.h> +#include <net/dst_metadata.h> + +#include "tag.h" +#include "user.h" + +static LIST_HEAD(dsa_tag_drivers_list); +static DEFINE_MUTEX(dsa_tag_drivers_lock); + +/* Determine if we should defer delivery of skb until we have a rx timestamp. + * + * Called from dsa_switch_rcv. For now, this will only work if tagging is + * enabled on the switch. Normally the MAC driver would retrieve the hardware + * timestamp when it reads the packet out of the hardware. However in a DSA + * switch, the DSA driver owning the interface to which the packet is + * delivered is never notified unless we do so here. + */ +static bool dsa_skb_defer_rx_timestamp(struct dsa_user_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + unsigned int type; + + if (!ds->ops->port_rxtstamp) + return false; + + if (skb_headroom(skb) < ETH_HLEN) + return false; + + __skb_push(skb, ETH_HLEN); + + type = ptp_classify_raw(skb); + + __skb_pull(skb, ETH_HLEN); + + if (type == PTP_CLASS_NONE) + return false; + + return ds->ops->port_rxtstamp(ds, p->dp->index, skb, type); +} + +static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *unused) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct sk_buff *nskb = NULL; + struct dsa_user_priv *p; + + if (unlikely(!cpu_dp)) { + kfree_skb(skb); + return 0; + } + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + return 0; + + if (md_dst && md_dst->type == METADATA_HW_PORT_MUX) { + unsigned int port = md_dst->u.port_info.port_id; + + skb_dst_drop(skb); + if (!skb_has_extensions(skb)) + skb->slow_gro = 0; + + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (likely(skb->dev)) { + dsa_default_offload_fwd_mark(skb); + nskb = skb; + } + } else { + nskb = cpu_dp->rcv(skb, dev); + } + + if (!nskb) { + kfree_skb(skb); + return 0; + } + + skb = nskb; + skb_push(skb, ETH_HLEN); + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, skb->dev); + + if (unlikely(!dsa_user_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 || + cpu_dp->ds->untag_vlan_aware_bridge_pvid)) { + nskb = dsa_software_vlan_untag(skb); + if (!nskb) { + kfree_skb(skb); + return 0; + } + skb = nskb; + } + + dev_sw_netstats_rx_add(skb->dev, skb->len + ETH_HLEN); + + if (dsa_skb_defer_rx_timestamp(p, skb)) + return 0; + + gro_cells_receive(&p->gcells, skb); + + return 0; +} + +struct packet_type dsa_pack_type __read_mostly = { + .type = cpu_to_be16(ETH_P_XDSA), + .func = dsa_switch_rcv, +}; + +static void dsa_tag_driver_register(struct dsa_tag_driver *dsa_tag_driver, + struct module *owner) +{ + dsa_tag_driver->owner = owner; + + mutex_lock(&dsa_tag_drivers_lock); + list_add_tail(&dsa_tag_driver->list, &dsa_tag_drivers_list); + mutex_unlock(&dsa_tag_drivers_lock); +} + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, struct module *owner) +{ + unsigned int i; + + for (i = 0; i < count; i++) + dsa_tag_driver_register(dsa_tag_driver_array[i], owner); +} + +static void dsa_tag_driver_unregister(struct dsa_tag_driver *dsa_tag_driver) +{ + mutex_lock(&dsa_tag_drivers_lock); + list_del(&dsa_tag_driver->list); + mutex_unlock(&dsa_tag_drivers_lock); +} +EXPORT_SYMBOL_GPL(dsa_tag_drivers_register); + +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count) +{ + unsigned int i; + + for (i = 0; i < count; i++) + dsa_tag_driver_unregister(dsa_tag_driver_array[i]); +} +EXPORT_SYMBOL_GPL(dsa_tag_drivers_unregister); + +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_tag_driver_get_by_name(const char *name) +{ + const struct dsa_device_ops *ops = ERR_PTR(-ENOPROTOOPT); + struct dsa_tag_driver *dsa_tag_driver; + + request_module("%s%s", DSA_TAG_DRIVER_ALIAS, name); + + 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 (strcmp(name, 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_by_id(int tag_protocol) +{ + struct dsa_tag_driver *dsa_tag_driver; + const struct dsa_device_ops *ops; + bool found = false; + + request_module("%sid-%d", DSA_TAG_DRIVER_ALIAS, tag_protocol); + + mutex_lock(&dsa_tag_drivers_lock); + list_for_each_entry(dsa_tag_driver, &dsa_tag_drivers_list, list) { + ops = dsa_tag_driver->ops; + if (ops->proto == tag_protocol) { + found = true; + break; + } + } + + if (found) { + if (!try_module_get(dsa_tag_driver->owner)) + ops = ERR_PTR(-ENOPROTOOPT); + } else { + ops = ERR_PTR(-ENOPROTOOPT); + } + + mutex_unlock(&dsa_tag_drivers_lock); + + return ops; +} + +void dsa_tag_driver_put(const struct dsa_device_ops *ops) +{ + 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) { + if (dsa_tag_driver->ops == ops) { + module_put(dsa_tag_driver->owner); + break; + } + } + mutex_unlock(&dsa_tag_drivers_lock); +} diff --git a/net/dsa/tag.h b/net/dsa/tag.h new file mode 100644 index 000000000000..cf52283fe9df --- /dev/null +++ b/net/dsa/tag.h @@ -0,0 +1,409 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_TAG_H +#define __DSA_TAG_H + +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/types.h> +#include <net/dsa.h> + +#include "port.h" +#include "user.h" + +struct dsa_tag_driver { + const struct dsa_device_ops *ops; + struct list_head list; + struct module *owner; +}; + +extern struct packet_type dsa_pack_type; + +const struct dsa_device_ops *dsa_tag_driver_get_by_id(int tag_protocol); +const struct dsa_device_ops *dsa_tag_driver_get_by_name(const char *name); +void dsa_tag_driver_put(const struct dsa_device_ops *ops); +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); + +static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) +{ + return ops->needed_headroom + ops->needed_tailroom; +} + +static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, + int device, int port) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dp->ds->index == device && dp->index == port && + dp->type == DSA_PORT_TYPE_USER) + return dp->user; + + return NULL; +} + +/** + * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge can process tagged packets. Software like STP/PTP may not. The + * bridge can also process untagged packets, to the same effect as if they were + * tagged with the PVID of the ingress port. So packets tagged with the PVID of + * the bridge port must be software-untagged, to support both use cases. + */ +static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + u16 pvid, proto; + int err; + + err = br_vlan_get_proto(br, &proto); + if (err) + return; + + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid == pvid && skb->vlan_proto == htons(proto)) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge + * @skb: Pointer to received socket buffer (packet) + * @br: Pointer to bridge upper interface of ingress port + * @vid: Parsed VID from packet + * + * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run + * on the plain port, or on a VLAN upper interface). Maybe packets are coming + * to software as tagged with a driver-defined VID which is NOT equal to the + * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration + * should NOT be committed to hardware). DSA needs a method for this private + * VID to be communicated by software to it, and if packets are tagged with it, + * software-untag them. Note: the private VID may be different per bridge, to + * support the FDB isolation use case. + * + * FIXME: this is currently implemented based on the broken assumption that + * the "private VID" used by the driver in VLAN-unaware mode is equal to the + * bridge PVID. It should not be, except for a coincidence; the bridge PVID is + * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that + * this function removes is wrong. + * + * All users of ds->untag_bridge_pvid should fix their drivers, if necessary, + * to make the two independent. Only then, if there still remains a need to + * strip the private VID from packets, then a new ds->ops->get_private_vid() + * API shall be introduced to communicate to DSA what this VID is, which needs + * to be stripped here. + */ +static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb, + struct net_device *br, + u16 vid) +{ + struct net_device *upper_dev; + u16 pvid, proto; + int err; + + err = br_vlan_get_proto(br, &proto); + if (err) + return; + + err = br_vlan_get_pvid_rcu(skb->dev, &pvid); + if (err) + return; + + if (vid != pvid || skb->vlan_proto != htons(proto)) + return; + + /* 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) + __vlan_hwaccel_clear_tag(skb); +} + +/** + * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path + * @skb: Pointer to socket buffer (packet) + * + * Receive path method for switches which send some packets as VLAN-tagged + * towards the CPU port (generally from VLAN-aware bridge ports) even when the + * packet was not tagged on the wire. Called when ds->untag_bridge_pvid + * (legacy) or ds->untag_vlan_aware_bridge_pvid is set to true. + * + * As a side effect of this method, any VLAN tag from the skb head is moved + * to hwaccel. + */ +static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 vid, proto; + int err; + + /* software untagging for standalone ports not yet necessary */ + if (!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); + + if (br_vlan_enabled(br)) { + if (dp->ds->untag_vlan_aware_bridge_pvid) + dsa_software_untag_vlan_aware_bridge(skb, br, vid); + } else { + if (dp->ds->untag_bridge_pvid) + dsa_software_untag_vlan_unaware_bridge(skb, br, vid); + } + + return skb; +} + +/* For switches without hardware support for DSA tagging to be able + * to support termination through the bridge. + */ +static inline struct net_device * +dsa_find_designated_bridge_port_by_vid(struct net_device *conduit, u16 vid) +{ + struct dsa_port *cpu_dp = conduit->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct bridge_vlan_info vinfo; + struct net_device *user; + struct dsa_port *dp; + int err; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->type != DSA_PORT_TYPE_USER) + continue; + + if (!dp->bridge) + continue; + + if (dp->stp_state != BR_STATE_LEARNING && + dp->stp_state != BR_STATE_FORWARDING) + continue; + + /* Since the bridge might learn this packet, keep the CPU port + * affinity with the port that will be used for the reply on + * xmit. + */ + if (dp->cpu_dp != cpu_dp) + continue; + + user = dp->user; + + err = br_vlan_get_info_rcu(user, vid, &vinfo); + if (err) + continue; + + return user; + } + + return NULL; +} + +/* If the ingress port offloads the bridge, we mark the frame as autonomously + * forwarded by hardware, so the software bridge doesn't forward in twice, back + * to us, because we already did. However, if we're in fallback mode and we do + * software bridging, we are not offloading it, therefore the dp->bridge + * pointer is not populated, and flooding needs to be done by software (we are + * effectively operating in standalone ports mode). + */ +static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) +{ + struct dsa_port *dp = dsa_user_to_port(skb->dev); + + skb->offload_fwd_mark = !!(dp->bridge); +} + +/* Helper for removing DSA header tags from packets in the RX path. + * Must not be called before skb_pull(len). + * skb->data + * | + * v + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * | | + * <----- len -----> <----- len -----> + * | + * >>>>>>> v + * >>>>>>> | | | | | | | | | | | | | | | + * >>>>>>> +-----------------------+-----------------------+-------+ + * >>>>>>> | Destination MAC | Source MAC | EType | + * +-----------------------+-----------------------+-------+ + * ^ + * | + * skb->data + */ +static inline void dsa_strip_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - len, 2 * ETH_ALEN); +} + +/* Helper for creating space for DSA header tags in TX path packets. + * Must not be called before skb_push(len). + * + * Before: + * + * <<<<<<< | | | | | | | | | | | | | | | + * ^ <<<<<<< +-----------------------+-----------------------+-------+ + * | <<<<<<< | Destination MAC | Source MAC | EType | + * | +-----------------------+-----------------------+-------+ + * <----- len -----> + * | + * | + * skb->data + * + * After: + * + * | | | | | | | | | | | | | | | | | | | + * +-----------------------+-----------------------+---------------+-------+ + * | Destination MAC | Source MAC | DSA header | EType | + * +-----------------------+-----------------------+---------------+-------+ + * ^ | | + * | <----- len -----> + * skb->data + */ +static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) +{ + memmove(skb->data, skb->data + len, 2 * ETH_ALEN); +} + +/* On RX, eth_type_trans() on the DSA conduit pulls ETH_HLEN bytes starting from + * skb_mac_header(skb), which leaves skb->data pointing at the first byte after + * what the DSA conduit perceives as the EtherType (the beginning of the L3 + * protocol). Since DSA EtherType header taggers treat the EtherType as part of + * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header + * is located 2 bytes behind skb->data. Note that EtherType in this context + * means the first 2 bytes of the DSA header, not the encapsulated EtherType + * that will become visible after the DSA header is stripped. + */ +static inline void *dsa_etype_header_pos_rx(struct sk_buff *skb) +{ + return skb->data - 2; +} + +/* On TX, skb->data points to the MAC header, which means that EtherType + * header taggers start exactly where the EtherType is (the EtherType is + * treated as part of the DSA header). + */ +static inline void *dsa_etype_header_pos_tx(struct sk_buff *skb) +{ + return skb->data + 2 * ETH_ALEN; +} + +static inline unsigned long dsa_xmit_port_mask(const struct sk_buff *skb, + const struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + unsigned long mask = BIT(dp->index); + + if (IS_ENABLED(CONFIG_HSR) && + unlikely(dev->features & NETIF_F_HW_HSR_DUP)) { + struct net_device *hsr_dev = dp->hsr_dev; + struct dsa_port *other_dp; + + dsa_hsr_foreach_port(other_dp, dp->ds, hsr_dev) + mask |= BIT(other_dp->index); + } + + return mask; +} + +/* Create 2 modaliases per tagging protocol, one to auto-load the module + * given the ID reported by get_tag_protocol(), and the other by name. + */ +#define DSA_TAG_DRIVER_ALIAS "dsa_tag:" +#define MODULE_ALIAS_DSA_TAG_DRIVER(__proto, __name) \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS __name); \ + MODULE_ALIAS(DSA_TAG_DRIVER_ALIAS "id-" \ + __stringify(__proto##_VALUE)) + +void dsa_tag_drivers_register(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count, + struct module *owner); +void dsa_tag_drivers_unregister(struct dsa_tag_driver *dsa_tag_driver_array[], + unsigned int count); + +#define dsa_tag_driver_module_drivers(__dsa_tag_drivers_array, __count) \ +static int __init dsa_tag_driver_module_init(void) \ +{ \ + dsa_tag_drivers_register(__dsa_tag_drivers_array, __count, \ + THIS_MODULE); \ + return 0; \ +} \ +module_init(dsa_tag_driver_module_init); \ + \ +static void __exit dsa_tag_driver_module_exit(void) \ +{ \ + dsa_tag_drivers_unregister(__dsa_tag_drivers_array, __count); \ +} \ +module_exit(dsa_tag_driver_module_exit) + +/** + * module_dsa_tag_drivers() - Helper macro for registering DSA tag + * drivers + * @__ops_array: Array of tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_drivers(__ops_array) \ +dsa_tag_driver_module_drivers(__ops_array, ARRAY_SIZE(__ops_array)) + +#define DSA_TAG_DRIVER_NAME(__ops) dsa_tag_driver ## _ ## __ops + +/* Create a static structure we can build a linked list of dsa_tag + * drivers + */ +#define DSA_TAG_DRIVER(__ops) \ +static struct dsa_tag_driver DSA_TAG_DRIVER_NAME(__ops) = { \ + .ops = &__ops, \ +} + +/** + * module_dsa_tag_driver() - Helper macro for registering a single DSA tag + * driver + * @__ops: Single tag driver structures + * + * Helper macro for DSA tag drivers which do not do anything special + * in module init/exit. Each module may only use this macro once, and + * calling it replaces module_init() and module_exit(). + */ +#define module_dsa_tag_driver(__ops) \ +DSA_TAG_DRIVER(__ops); \ + \ +static struct dsa_tag_driver *dsa_tag_driver_array[] = { \ + &DSA_TAG_DRIVER_NAME(__ops) \ +}; \ +module_dsa_tag_drivers(dsa_tag_driver_array) + +#endif diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 780b2a15ac9b..53e03fd8071b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -2,108 +2,99 @@ /* Copyright (c) 2019, Vladimir Oltean <olteanv@gmail.com> * * This module is not a complete tagger implementation. It only provides - * primitives for taggers that rely on 802.1Q VLAN tags to use. The - * dsa_8021q_netdev_ops is registered for API compliance and not used - * directly by callers. + * primitives for taggers that rely on 802.1Q VLAN tags to use. */ -#include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/dsa/8021q.h> -#include "dsa_priv.h" +#include "port.h" +#include "switch.h" +#include "tag.h" +#include "tag_8021q.h" /* Binary structure of the fake 12-bit VID field (when the TPID is * ETH_P_DSA_8021Q): * * | 11 | 10 | 9 | 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 | * +-----------+-----+-----------------+-----------+-----------------------+ - * | DIR | SVL | SWITCH_ID | SUBVLAN | PORT | + * | RSV | VBID| SWITCH_ID | VBID | PORT | * +-----------+-----+-----------------+-----------+-----------------------+ * - * DIR - VID[11:10]: - * Direction flags. - * * 1 (0b01) for RX VLAN, - * * 2 (0b10) for TX VLAN. - * These values make the special VIDs of 0, 1 and 4095 to be left - * unused by this coding scheme. - * - * SVL/SUBVLAN - { VID[9], VID[5:4] }: - * Sub-VLAN encoding. Valid only when DIR indicates an RX VLAN. - * * 0 (0b000): Field does not encode a sub-VLAN, either because - * received traffic is untagged, PVID-tagged or because a second - * VLAN tag is present after this tag and not inside of it. - * * 1 (0b001): Received traffic is tagged with a VID value private - * to the host. This field encodes the index in the host's lookup - * table through which the value of the ingress VLAN ID can be - * recovered. - * * 2 (0b010): Field encodes a sub-VLAN. - * ... - * * 7 (0b111): Field encodes a sub-VLAN. - * When DIR indicates a TX VLAN, SUBVLAN must be transmitted as zero - * (by the host) and ignored on receive (by the switch). + * RSV - VID[11:10]: + * Reserved. Must be set to 3 (0b11). * * SWITCH_ID - VID[8:6]: * Index of switch within DSA tree. Must be between 0 and 7. * + * VBID - { VID[9], VID[5:4] }: + * Virtual bridge ID. If between 1 and 7, packet targets the broadcast + * domain of a bridge. If transmitted as zero, packet targets a single + * port. + * * PORT - VID[3:0]: * Index of switch port. Must be between 0 and 15. */ -#define DSA_8021Q_DIR_SHIFT 10 -#define DSA_8021Q_DIR_MASK GENMASK(11, 10) -#define DSA_8021Q_DIR(x) (((x) << DSA_8021Q_DIR_SHIFT) & \ - DSA_8021Q_DIR_MASK) -#define DSA_8021Q_DIR_RX DSA_8021Q_DIR(1) -#define DSA_8021Q_DIR_TX DSA_8021Q_DIR(2) +#define DSA_8021Q_RSV_VAL 3 +#define DSA_8021Q_RSV_SHIFT 10 +#define DSA_8021Q_RSV_MASK GENMASK(11, 10) +#define DSA_8021Q_RSV ((DSA_8021Q_RSV_VAL << DSA_8021Q_RSV_SHIFT) & \ + DSA_8021Q_RSV_MASK) #define DSA_8021Q_SWITCH_ID_SHIFT 6 #define DSA_8021Q_SWITCH_ID_MASK GENMASK(8, 6) #define DSA_8021Q_SWITCH_ID(x) (((x) << DSA_8021Q_SWITCH_ID_SHIFT) & \ DSA_8021Q_SWITCH_ID_MASK) -#define DSA_8021Q_SUBVLAN_HI_SHIFT 9 -#define DSA_8021Q_SUBVLAN_HI_MASK GENMASK(9, 9) -#define DSA_8021Q_SUBVLAN_LO_SHIFT 4 -#define DSA_8021Q_SUBVLAN_LO_MASK GENMASK(4, 3) -#define DSA_8021Q_SUBVLAN_HI(x) (((x) & GENMASK(2, 2)) >> 2) -#define DSA_8021Q_SUBVLAN_LO(x) ((x) & GENMASK(1, 0)) -#define DSA_8021Q_SUBVLAN(x) \ - (((DSA_8021Q_SUBVLAN_LO(x) << DSA_8021Q_SUBVLAN_LO_SHIFT) & \ - DSA_8021Q_SUBVLAN_LO_MASK) | \ - ((DSA_8021Q_SUBVLAN_HI(x) << DSA_8021Q_SUBVLAN_HI_SHIFT) & \ - DSA_8021Q_SUBVLAN_HI_MASK)) +#define DSA_8021Q_VBID_HI_SHIFT 9 +#define DSA_8021Q_VBID_HI_MASK GENMASK(9, 9) +#define DSA_8021Q_VBID_LO_SHIFT 4 +#define DSA_8021Q_VBID_LO_MASK GENMASK(5, 4) +#define DSA_8021Q_VBID_HI(x) (((x) & GENMASK(2, 2)) >> 2) +#define DSA_8021Q_VBID_LO(x) ((x) & GENMASK(1, 0)) +#define DSA_8021Q_VBID(x) \ + (((DSA_8021Q_VBID_LO(x) << DSA_8021Q_VBID_LO_SHIFT) & \ + DSA_8021Q_VBID_LO_MASK) | \ + ((DSA_8021Q_VBID_HI(x) << DSA_8021Q_VBID_HI_SHIFT) & \ + DSA_8021Q_VBID_HI_MASK)) #define DSA_8021Q_PORT_SHIFT 0 #define DSA_8021Q_PORT_MASK GENMASK(3, 0) #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) -/* Returns the VID to be inserted into the frame from xmit for switch steering - * instructions on egress. Encodes switch ID and port ID. - */ -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +struct dsa_tag_8021q_vlan { + struct list_head list; + int port; + u16 vid; + refcount_t refcount; +}; + +struct dsa_8021q_context { + struct dsa_switch *ds; + struct list_head vlans; + /* EtherType of RX VID, used for filtering on conduit interface */ + __be16 proto; +}; + +u16 dsa_tag_8021q_bridge_vid(unsigned int bridge_num) { - return DSA_8021Q_DIR_TX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); + /* The VBID value of 0 is reserved for precise TX, but it is also + * reserved/invalid for the bridge_num, so all is well. + */ + return DSA_8021Q_RSV | DSA_8021Q_VBID(bridge_num); } -EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_vid); /* Returns the VID that will be installed as pvid for this switch port, sent as * tagged egress towards the CPU port and decoded by the rcv function. */ -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); -} -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) +u16 dsa_tag_8021q_standalone_vid(const struct dsa_port *dp) { - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port) | DSA_8021Q_SUBVLAN(subvlan); + return DSA_8021Q_RSV | DSA_8021Q_SWITCH_ID(dp->ds->index) | + DSA_8021Q_PORT(dp->index); } -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid_subvlan); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_standalone_vid); /* Returns the decoded switch ID from the RX VID. */ int dsa_8021q_rx_switch_id(u16 vid) @@ -119,311 +110,479 @@ int dsa_8021q_rx_source_port(u16 vid) } EXPORT_SYMBOL_GPL(dsa_8021q_rx_source_port); -/* Returns the decoded subvlan from the RX VID. */ -u16 dsa_8021q_rx_subvlan(u16 vid) +/* Returns the decoded VBID from the RX VID. */ +static int dsa_tag_8021q_rx_vbid(u16 vid) { - u16 svl_hi, svl_lo; - - svl_hi = (vid & DSA_8021Q_SUBVLAN_HI_MASK) >> - DSA_8021Q_SUBVLAN_HI_SHIFT; - svl_lo = (vid & DSA_8021Q_SUBVLAN_LO_MASK) >> - DSA_8021Q_SUBVLAN_LO_SHIFT; + u16 vbid_hi = (vid & DSA_8021Q_VBID_HI_MASK) >> DSA_8021Q_VBID_HI_SHIFT; + u16 vbid_lo = (vid & DSA_8021Q_VBID_LO_MASK) >> DSA_8021Q_VBID_LO_SHIFT; - return (svl_hi << 2) | svl_lo; + return (vbid_hi << 2) | vbid_lo; } -EXPORT_SYMBOL_GPL(dsa_8021q_rx_subvlan); 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); + u16 rsv = (vid & DSA_8021Q_RSV_MASK) >> DSA_8021Q_RSV_SHIFT; + + return rsv == DSA_8021Q_RSV_VAL; } EXPORT_SYMBOL_GPL(vid_is_dsa_8021q); -/* If @enabled is true, installs @vid with @flags into the switch port's HW - * filter. - * If @enabled is false, deletes @vid (ignores @flags) from the port. Had the - * 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, - u16 flags, bool enabled) +static struct dsa_tag_8021q_vlan * +dsa_tag_8021q_vlan_find(struct dsa_8021q_context *ctx, int port, u16 vid) { - struct dsa_port *dp = dsa_to_port(ds, port); + struct dsa_tag_8021q_vlan *v; - if (enabled) - return dsa_port_vid_add(dp, vid, flags); + list_for_each_entry(v, &ctx->vlans, list) + if (v->vid == vid && v->port == port) + return v; - return dsa_port_vid_del(dp, vid); + return NULL; } -/* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single - * front-panel switch port (here swp0). - * - * Port identification through VLAN (802.1Q) tags has different requirements - * for it to work effectively: - * - On RX (ingress from network): each front-panel port must have a pvid - * that uniquely identifies it, and the egress of this pvid must be tagged - * towards the CPU port, so that software can recover the source port based - * on the VID in the frame. But this would only work for standalone ports; - * if bridged, this VLAN setup would break autonomous forwarding and would - * force all switched traffic to pass through the CPU. So we must also make - * the other front-panel ports members of this VID we're adding, albeit - * we're not making it their PVID (they'll still have their own). - * By the way - just because we're installing the same VID in multiple - * switch ports doesn't mean that they'll start to talk to one another, even - * while not bridged: the final forwarding decision is still an AND between - * the L2 forwarding information (which is limiting forwarding in this case) - * and the VLAN-based restrictions (of which there are none in this case, - * since all ports are members). - * - On TX (ingress from CPU and towards network) we are faced with a problem. - * If we were to tag traffic (from within DSA) with the port's pvid, all - * would be well, assuming the switch ports were standalone. Frames would - * have no choice but to be directed towards the correct front-panel port. - * But because we also want the RX VLAN to not break bridging, then - * inevitably that means that we have to give them a choice (of what - * front-panel port to go out on), and therefore we cannot steer traffic - * based on the RX VID. So what we do is simply install one more VID on the - * front-panel and CPU ports, and profit off of the fact that steering will - * work just by virtue of the fact that there is only one other port that's - * a member of the VID we're tagging the traffic with - the desired one. - * - * So at the end, each front-panel port will have one RX VID (also the PVID), - * the RX VID of all other front-panel ports, and one TX VID. Whereas the CPU - * port will have the RX and TX VIDs of all front-panel ports, and on top of - * that, is also tagged-input and tagged-output (VLAN trunk). - * - * CPU port CPU port - * +-------------+-----+-------------+ +-------------+-----+-------------+ - * | RX VID | | | | TX VID | | | - * | of swp0 | | | | of swp0 | | | - * | +-----+ | | +-----+ | - * | ^ T | | | Tagged | - * | | | | | ingress | - * | +-------+---+---+-------+ | | +-----------+ | - * | | | | | | | | Untagged | - * | | U v U v U v | | v egress | - * | +-----+ +-----+ +-----+ +-----+ | | +-----+ +-----+ +-----+ +-----+ | - * | | | | | | | | | | | | | | | | | | | | - * | |PVID | | | | | | | | | | | | | | | | | | - * +-+-----+-+-----+-+-----+-+-----+-+ +-+-----+-+-----+-+-----+-+-----+-+ - * swp0 swp1 swp2 swp3 swp0 swp1 swp2 swp3 - */ -int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled) +static int dsa_port_do_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, + u16 flags) { - 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; + struct dsa_8021q_context *ctx = dp->ds->tag_8021q_ctx; + struct dsa_switch *ds = dp->ds; + struct dsa_tag_8021q_vlan *v; + int port = dp->index; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (v) { + refcount_inc(&v->refcount); + return 0; + } - /* The CPU port is implicitly configured by - * configuring the front-panel ports - */ - if (!dsa_is_user_port(ds, port)) + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) + return -ENOMEM; + + err = ds->ops->tag_8021q_vlan_add(ds, port, vid, flags); + if (err) { + kfree(v); + return err; + } + + v->vid = vid; + v->port = port; + refcount_set(&v->refcount, 1); + list_add_tail(&v->list, &ctx->vlans); + + return 0; +} + +static int dsa_port_do_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid) +{ + struct dsa_8021q_context *ctx = dp->ds->tag_8021q_ctx; + struct dsa_switch *ds = dp->ds; + struct dsa_tag_8021q_vlan *v; + int port = dp->index; + int err; + + /* No need to bother with refcounting for user ports */ + if (!(dsa_port_is_cpu(dp) || dsa_port_is_dsa(dp))) + return ds->ops->tag_8021q_vlan_del(ds, port, vid); + + v = dsa_tag_8021q_vlan_find(ctx, port, vid); + if (!v) + return -ENOENT; + + if (!refcount_dec_and_test(&v->refcount)) return 0; - /* Add this user port's RX VID to the membership list of all others - * (including itself). This is so that bridging will not be hindered. - * L2 forwarding rules still take precedence when there are no VLAN - * restrictions, so there are no concerns about leaking traffic. + err = ds->ops->tag_8021q_vlan_del(ds, port, vid); + if (err) { + refcount_set(&v->refcount, 1); + return err; + } + + list_del(&v->list); + kfree(v); + + return 0; +} + +static bool +dsa_port_tag_8021q_vlan_match(struct dsa_port *dp, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + return dsa_port_is_dsa(dp) || dsa_port_is_cpu(dp) || dp == info->dp; +} + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + struct dsa_port *dp; + int err; + + /* Since we use dsa_broadcast(), there might be other switches in other + * trees which don't support tag_8021q, so don't return an error. + * Or they might even support tag_8021q but have not registered yet to + * use it (maybe they use another tagger currently). */ - for (i = 0; i < ds->num_ports; i++) { - u16 flags; + if (!ds->ops->tag_8021q_vlan_add || !ds->tag_8021q_ctx) + return 0; - if (i == upstream) - continue; - else if (i == port) - /* The RX VID is pvid on this port */ - flags = BRIDGE_VLAN_INFO_UNTAGGED | - BRIDGE_VLAN_INFO_PVID; - else - /* The RX VID is a regular VLAN on all others */ - flags = BRIDGE_VLAN_INFO_UNTAGGED; - - err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled); - if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", - rx_vid, port, err); - return err; + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_tag_8021q_vlan_match(dp, info)) { + u16 flags = 0; + + if (dsa_port_is_user(dp)) + flags |= BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_PVID; + + err = dsa_port_do_tag_8021q_vlan_add(dp, info->vid, + flags); + if (err) + return err; } } - /* CPU port needs to see this port's RX VID - * as tagged egress. + return 0; +} + +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info) +{ + struct dsa_port *dp; + int err; + + if (!ds->ops->tag_8021q_vlan_del || !ds->tag_8021q_ctx) + return 0; + + dsa_switch_for_each_port(dp, ds) { + if (dsa_port_tag_8021q_vlan_match(dp, info)) { + err = dsa_port_do_tag_8021q_vlan_del(dp, info->vid); + if (err) + return err; + } + } + + return 0; +} + +/* There are 2 ways of offloading tag_8021q VLANs. + * + * One is to use a hardware TCAM to push the port's standalone VLAN into the + * frame when forwarding it to the CPU, as an egress modification rule on the + * CPU port. This is preferable because it has no side effects for the + * autonomous forwarding path, and accomplishes tag_8021q's primary goal of + * identifying the source port of each packet based on VLAN ID. + * + * The other is to commit the tag_8021q VLAN as a PVID to the VLAN table, and + * to configure the port as VLAN-unaware. This is less preferable because + * unique source port identification can only be done for standalone ports; + * under a VLAN-unaware bridge, all ports share the same tag_8021q VLAN as + * PVID, and under a VLAN-aware bridge, packets received by software will not + * have tag_8021q VLANs appended, just bridge VLANs. + * + * For tag_8021q implementations of the second type, this method is used to + * replace the standalone tag_8021q VLAN of a port with the tag_8021q VLAN to + * be used for VLAN-unaware bridging. + */ +int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge, bool *tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + u16 standalone_vid, bridge_vid; + int err; + + /* Delete the standalone VLAN of the port and replace it with a + * bridging VLAN */ - err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled); - if (err) { - dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n", - rx_vid, port, err); + standalone_vid = dsa_tag_8021q_standalone_vid(dp); + bridge_vid = dsa_tag_8021q_bridge_vid(bridge.num); + + err = dsa_port_tag_8021q_vlan_add(dp, bridge_vid, true); + if (err) return err; - } - /* 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, - enabled); + dsa_port_tag_8021q_vlan_del(dp, standalone_vid, false); + + *tx_fwd_offload = true; + + return 0; +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_join); + +void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + u16 standalone_vid, bridge_vid; + int err; + + /* Delete the bridging VLAN of the port and replace it with a + * standalone VLAN + */ + standalone_vid = dsa_tag_8021q_standalone_vid(dp); + bridge_vid = dsa_tag_8021q_bridge_vid(bridge.num); + + err = dsa_port_tag_8021q_vlan_add(dp, standalone_vid, false); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", - tx_vid, port, err); - return err; + dev_err(ds->dev, + "Failed to delete tag_8021q standalone VLAN %d from port %d: %pe\n", + standalone_vid, port, ERR_PTR(err)); } - err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled); + + dsa_port_tag_8021q_vlan_del(dp, bridge_vid, true); +} +EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_leave); + +/* Set up a port's standalone tag_8021q VLAN */ +static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) +{ + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + u16 vid = dsa_tag_8021q_standalone_vid(dp); + struct net_device *conduit; + int err; + + /* The CPU port is implicitly configured by + * configuring the front-panel ports + */ + if (!dsa_port_is_user(dp)) + return 0; + + conduit = dsa_port_to_conduit(dp); + + err = dsa_port_tag_8021q_vlan_add(dp, vid, false); if (err) { - dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n", - tx_vid, upstream, err); + dev_err(ds->dev, + "Failed to apply standalone VID %d to port %d: %pe\n", + vid, port, ERR_PTR(err)); return err; } + /* Add the VLAN to the conduit's RX filter. */ + vlan_vid_add(conduit, ctx->proto, vid); + 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 other_port, bool enabled) +static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) { - u16 rx_vid = dsa_8021q_rx_vid(ds, port); + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_port *dp = dsa_to_port(ds, port); + u16 vid = dsa_tag_8021q_standalone_vid(dp); + struct net_device *conduit; - /* @rx_vid of local @ds port @port goes to @other_port of - * @other_ds + /* The CPU port is implicitly configured by + * configuring the front-panel ports */ - return dsa_8021q_vid_apply(other_ds, other_port, rx_vid, - BRIDGE_VLAN_INFO_UNTAGGED, enabled); + if (!dsa_port_is_user(dp)) + return; + + conduit = dsa_port_to_conduit(dp); + + dsa_port_tag_8021q_vlan_del(dp, vid, false); + + vlan_vid_del(conduit, ctx->proto, vid); } -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_tag_8021q_setup(struct dsa_switch *ds) { - struct dsa_8021q_crosschip_link *c; + int err, port; + + ASSERT_RTNL(); - list_for_each_entry(c, crosschip_links, list) { - if (c->port == port && c->other_ds == other_ds && - c->other_port == other_port) { - refcount_inc(&c->refcount); - return 0; + for (port = 0; port < ds->num_ports; port++) { + err = dsa_tag_8021q_port_setup(ds, port); + if (err < 0) { + dev_err(ds->dev, + "Failed to setup VLAN tagging for port %d: %pe\n", + port, ERR_PTR(err)); + return err; } } - dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n", - port, dev_name(other_ds->dev), other_port); + return 0; +} + +static void dsa_tag_8021q_teardown(struct dsa_switch *ds) +{ + int port; + + ASSERT_RTNL(); + + for (port = 0; port < ds->num_ports; port++) + dsa_tag_8021q_port_teardown(ds, port); +} + +int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto) +{ + struct dsa_8021q_context *ctx; + int err; - c = kzalloc(sizeof(*c), GFP_KERNEL); - if (!c) + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) return -ENOMEM; - c->port = port; - c->other_ds = other_ds; - c->other_port = other_port; - refcount_set(&c->refcount, 1); + ctx->proto = proto; + ctx->ds = ds; + + INIT_LIST_HEAD(&ctx->vlans); + + ds->tag_8021q_ctx = ctx; - list_add(&c->list, crosschip_links); + err = dsa_tag_8021q_setup(ds); + if (err) + goto err_free; return 0; + +err_free: + kfree(ctx); + return err; } +EXPORT_SYMBOL_GPL(dsa_tag_8021q_register); -static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds, - struct dsa_8021q_crosschip_link *c, - struct list_head *crosschip_links, - bool *keep) +void dsa_tag_8021q_unregister(struct dsa_switch *ds) { - *keep = !refcount_dec_and_test(&c->refcount); + struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; + struct dsa_tag_8021q_vlan *v, *n; - if (*keep) - return; + dsa_tag_8021q_teardown(ds); + + list_for_each_entry_safe(v, n, &ctx->vlans, list) { + list_del(&v->list); + kfree(v); + } - dev_dbg(ds->dev, - "deleting crosschip link from port %d to %s port %d\n", - c->port, dev_name(c->other_ds->dev), c->other_port); + ds->tag_8021q_ctx = NULL; - list_del(&c->list); - kfree(c); + kfree(ctx); } +EXPORT_SYMBOL_GPL(dsa_tag_8021q_unregister); -/* Make traffic from local port @port be received by remote port @other_port. - * This means that our @rx_vid needs to be installed on @other_ds's upstream - * and user ports. The user ports should be egress-untagged so that they can - * pop the dsa_8021q VLAN. But the @other_upstream can be either egress-tagged - * 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) +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci) { - /* @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. + /* skb->data points at the MAC header, which is fine + * for vlan_insert_tag(). */ - int other_upstream = dsa_upstream_port(other_ds, other_port); - int rc; - - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_port, crosschip_links); - if (rc) - return rc; - - rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds, - other_port, true); - if (rc) - return rc; - - rc = dsa_8021q_crosschip_link_add(ds, port, other_ds, - other_upstream, - crosschip_links); - if (rc) - return rc; - - return dsa_8021q_crosschip_link_apply(ds, port, other_ds, - other_upstream, true); + return vlan_insert_tag(skb, htons(tpid), tci); } -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join); +EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -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) +static struct net_device * +dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid) { - int other_upstream = dsa_upstream_port(other_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 && - (c->other_port == other_port || - c->other_port == other_upstream)) { - struct dsa_switch *other_ds = c->other_ds; - int other_port = c->other_port; - bool keep; - int rc; - - dsa_8021q_crosschip_link_del(ds, c, crosschip_links, - &keep); - if (keep) - continue; - - rc = dsa_8021q_crosschip_link_apply(ds, port, - other_ds, - other_port, - false); - if (rc) - return rc; - } + struct dsa_port *cpu_dp = conduit->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_port *dp; + + if (WARN_ON(!vbid)) + return NULL; + + dsa_tree_for_each_user_port(dp, dst) { + if (!dp->bridge) + continue; + + if (dp->stp_state != BR_STATE_LEARNING && + dp->stp_state != BR_STATE_FORWARDING) + continue; + + if (dp->cpu_dp != cpu_dp) + continue; + + if (dsa_port_bridge_num_get(dp) == vbid) + return dp->user; } - return 0; + return NULL; } -EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_leave); -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) +struct net_device *dsa_tag_8021q_find_user(struct net_device *conduit, + int source_port, int switch_id, + int vid, int vbid) { - /* skb->data points at skb_mac_header, which - * is fine for vlan_insert_tag. - */ - return vlan_insert_tag(skb, htons(tpid), tci); + /* Always prefer precise source port information, if available */ + if (source_port != -1 && switch_id != -1) + return dsa_conduit_find_user(conduit, switch_id, source_port); + else if (vbid >= 1) + return dsa_tag_8021q_find_port_by_vbid(conduit, vbid); + + return dsa_find_designated_bridge_port_by_vid(conduit, vid); } -EXPORT_SYMBOL_GPL(dsa_8021q_xmit); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_find_user); + +/** + * dsa_8021q_rcv - Decode source information from tag_8021q header + * @skb: RX socket buffer + * @source_port: pointer to storage for precise source port information. + * If this is known already from outside tag_8021q, the pre-initialized + * value is preserved. If not known, pass -1. + * @switch_id: similar to source_port. + * @vbid: pointer to storage for imprecise bridge ID. Must be pre-initialized + * with -1. If a positive value is returned, the source_port and switch_id + * are invalid. + * @vid: pointer to storage for original VID, in case tag_8021q decoding failed. + * + * If the packet has a tag_8021q header, decode it and set @source_port, + * @switch_id and @vbid, and strip the header. Otherwise set @vid and keep the + * header in the hwaccel area of the packet. + */ +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid, int *vid) +{ + int tmp_source_port, tmp_switch_id, tmp_vbid; + __be16 vlan_proto; + u16 tmp_vid, tci; + + if (skb_vlan_tag_present(skb)) { + vlan_proto = skb->vlan_proto; + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); + + vlan_proto = hdr->h_vlan_proto; + skb_push_rcsum(skb, ETH_HLEN); + __skb_vlan_pop(skb, &tci); + skb_pull_rcsum(skb, ETH_HLEN); + } -MODULE_LICENSE("GPL v2"); + tmp_vid = tci & VLAN_VID_MASK; + if (!vid_is_dsa_8021q(tmp_vid)) { + /* Not a tag_8021q frame, so return the VID to the + * caller for further processing, and put the tag back + */ + if (vid) + *vid = tmp_vid; + + __vlan_hwaccel_put_tag(skb, vlan_proto, tci); + + return; + } + + tmp_source_port = dsa_8021q_rx_source_port(tmp_vid); + tmp_switch_id = dsa_8021q_rx_switch_id(tmp_vid); + tmp_vbid = dsa_tag_8021q_rx_vbid(tmp_vid); + + /* Precise source port information is unknown when receiving from a + * VLAN-unaware bridging domain, and tmp_source_port and tmp_switch_id + * are zeroes in this case. + * + * Preserve the source information from hardware-specific mechanisms, + * if available. This allows us to not overwrite a valid source port + * and switch ID with less precise values. + */ + if (tmp_vbid == 0 && *source_port == -1) + *source_port = tmp_source_port; + if (tmp_vbid == 0 && *switch_id == -1) + *switch_id = tmp_switch_id; + + if (vbid) + *vbid = tmp_vbid; + + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + return; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h new file mode 100644 index 000000000000..27b8906f99ec --- /dev/null +++ b/net/dsa/tag_8021q.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_TAG_8021Q_H +#define __DSA_TAG_8021Q_H + +#include <net/dsa.h> + +#include "switch.h" + +struct sk_buff; +struct net_device; + +struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, + u16 tpid, u16 tci); + +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *vbid, int *vid); + +struct net_device *dsa_tag_8021q_find_user(struct net_device *conduit, + int source_port, int switch_id, + int vid, int vbid); + +int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); +int dsa_switch_tag_8021q_vlan_del(struct dsa_switch *ds, + struct dsa_notifier_tag_8021q_vlan_info *info); + +#endif diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 55b00694cdba..cbb588ca73aa 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -7,7 +7,9 @@ #include <linux/bitfield.h> #include <linux/etherdevice.h> -#include "dsa_priv.h" +#include "tag.h" + +#define AR9331_NAME "ar9331" #define AR9331_HDR_LEN 2 #define AR9331_HDR_VERSION 1 @@ -27,13 +29,10 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __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); @@ -47,8 +46,7 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, } static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, - struct net_device *ndev, - struct packet_type *pt) + struct net_device *ndev) { u8 ver, port; u16 hdr; @@ -76,7 +74,7 @@ static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = FIELD_GET(AR9331_HDR_PORT_NUM_MASK, hdr); - skb->dev = dsa_master_find_slave(ndev, 0, port); + skb->dev = dsa_conduit_find_user(ndev, 0, port); if (!skb->dev) return NULL; @@ -84,13 +82,14 @@ static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops ar9331_netdev_ops = { - .name = "ar9331", + .name = AR9331_NAME, .proto = DSA_TAG_PROTO_AR9331, .xmit = ar9331_tag_xmit, .rcv = ar9331_tag_rcv, - .overhead = AR9331_HDR_LEN, + .needed_headroom = AR9331_HDR_LEN, }; +MODULE_DESCRIPTION("DSA tag driver for Atheros AR9331 SoC with built-in switch"); MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_AR9331, AR9331_NAME); module_dsa_tag_driver(ar9331_netdev_ops); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cc8512b5f9e2..cf9420439054 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -5,18 +5,46 @@ * Copyright (C) 2014 Broadcom Corporation */ +#include <linux/dsa/brcm.h> #include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" -/* This tag length is 4 bytes, older ones were 6 bytes, we do not - * handle them - */ +#define BRCM_NAME "brcm" +#define BRCM_LEGACY_NAME "brcm-legacy" +#define BRCM_LEGACY_FCS_NAME "brcm-legacy-fcs" +#define BRCM_PREPEND_NAME "brcm-prepend" + +/* Legacy Broadcom tag (6 bytes) */ +#define BRCM_LEG_TAG_LEN 6 + +/* Type fields */ +/* 1st byte in the tag */ +#define BRCM_LEG_TYPE_HI 0x88 +/* 2nd byte in the tag */ +#define BRCM_LEG_TYPE_LO 0x74 + +/* Tag fields */ +/* 3rd byte in the tag */ +#define BRCM_LEG_UNICAST (0 << 5) +#define BRCM_LEG_MULTICAST (1 << 5) +#define BRCM_LEG_EGRESS (2 << 5) +#define BRCM_LEG_INGRESS (3 << 5) +#define BRCM_LEG_LEN_HI(x) (((x) >> 8) & 0x7) + +/* 4th byte in the tag */ +#define BRCM_LEG_LEN_LO(x) ((x) & 0xff) + +/* 6th byte in the tag */ +#define BRCM_LEG_PORT_ID (0xf) + +/* Newer Broadcom tag (4 bytes) */ #define BRCM_TAG_LEN 4 -/* Tag is constructed and desconstructed using byte by byte access +/* Tag is constructed and deconstructed using byte by byte access * because the tag is placed after the MAC Source Address, which does * not make it 4-bytes aligned, so this might cause unaligned accesses * on most systems where this is used. @@ -62,13 +90,11 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, struct net_device *dev, unsigned int offset) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u16 queue = skb_get_queue_mapping(skb); + u16 port_mask; 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 @@ -76,7 +102,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, * (including FCS and tag) because the length verification is done after * the Broadcom tag is stripped off the ingress packet. * - * Let dsa_slave_xmit() free the SKB + * Let dsa_user_xmit() free the SKB */ if (__skb_put_padto(skb, ETH_ZLEN + BRCM_TAG_LEN, false)) return NULL; @@ -84,22 +110,21 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, skb_push(skb, BRCM_TAG_LEN); if (offset) - memmove(skb->data, skb->data + BRCM_TAG_LEN, offset); + dsa_alloc_etype_header(skb, BRCM_TAG_LEN); brcm_tag = skb->data + offset; - /* Set the ingress opcode, traffic class, tag enforcment is + /* Set the ingress opcode, traffic class, tag enforcement is * deprecated */ brcm_tag[0] = (1 << BRCM_OPCODE_SHIFT) | ((queue & BRCM_IG_TC_MASK) << BRCM_IG_TC_SHIFT); brcm_tag[1] = 0; - brcm_tag[2] = 0; - if (dp->index == 8) - brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; - brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; + port_mask = dsa_xmit_port_mask(skb, dev); + brcm_tag[2] = (port_mask >> 8) & BRCM_IG_DSTMAP2_MASK; + brcm_tag[3] = port_mask & BRCM_IG_DSTMAP1_MASK; - /* Now tell the master network device about the desired output queue + /* Now tell the conduit network device about the desired output queue * as well */ skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); @@ -107,9 +132,20 @@ 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, unsigned int offset) { int source_port; @@ -133,38 +169,18 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); - skb->offload_fwd_mark = 1; + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(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) @@ -176,37 +192,184 @@ static struct sk_buff *brcm_tag_xmit(struct sk_buff *skb, } -static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev) { struct sk_buff *nskb; /* skb->data points to the EtherType, the tag is right before it */ - nskb = brcm_tag_rcv_ll(skb, dev, pt, 2); + nskb = brcm_tag_rcv_ll(skb, dev, 2); if (!nskb) return nskb; - /* Move the Ethernet DA and SA */ - memmove(nskb->data - ETH_HLEN, - nskb->data - ETH_HLEN - BRCM_TAG_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, BRCM_TAG_LEN); return nskb; } static const struct dsa_device_ops brcm_netdev_ops = { - .name = "brcm", + .name = BRCM_NAME, .proto = DSA_TAG_PROTO_BRCM, .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, - .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM, BRCM_NAME); #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) || \ + IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) +static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + int len = BRCM_LEG_TAG_LEN; + int source_port; + __be16 *proto; + u8 *brcm_tag; + + if (unlikely(!pskb_may_pull(skb, BRCM_LEG_TAG_LEN + VLAN_HLEN))) + return NULL; + + brcm_tag = dsa_etype_header_pos_rx(skb); + proto = (__be16 *)(brcm_tag + BRCM_LEG_TAG_LEN); + + source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; + + skb->dev = dsa_conduit_find_user(dev, 0, source_port); + if (!skb->dev) + return NULL; + + /* The internal switch in BCM63XX SoCs always tags on egress on the CPU + * port. We use VID 0 internally for untagged traffic, so strip the tag + * if the TCI field is all 0, and keep it otherwise to also retain + * e.g. 802.1p tagged packets. + */ + if (proto[0] == htons(ETH_P_8021Q) && proto[1] == 0) + len += VLAN_HLEN; + + /* Remove Broadcom tag and update checksum */ + skb_pull_rcsum(skb, len); + + if (likely(!is_link_local_ether_addr(eth_hdr(skb)->h_dest))) + dsa_default_offload_fwd_mark(skb); + + dsa_strip_etype_header(skb, len); + + return skb; +} +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY || CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS */ + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) +static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + u8 *brcm_tag; + + /* 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 + * need to make sure that packets are at least 70 bytes + * (including FCS and tag) because the length verification is done after + * the Broadcom tag is stripped off the ingress packet. + * + * Let dsa_user_xmit() free the SKB + */ + if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) + return NULL; + + skb_push(skb, BRCM_LEG_TAG_LEN); + + dsa_alloc_etype_header(skb, BRCM_LEG_TAG_LEN); + + brcm_tag = skb->data + 2 * ETH_ALEN; + + /* Broadcom tag type */ + brcm_tag[0] = BRCM_LEG_TYPE_HI; + brcm_tag[1] = BRCM_LEG_TYPE_LO; + + /* Broadcom tag value */ + brcm_tag[2] = BRCM_LEG_EGRESS; + brcm_tag[3] = 0; + brcm_tag[4] = 0; + brcm_tag[5] = dp->index & BRCM_LEG_PORT_ID; + + return skb; +} + +static const struct dsa_device_ops brcm_legacy_netdev_ops = { + .name = BRCM_LEGACY_NAME, + .proto = DSA_TAG_PROTO_BRCM_LEGACY, + .xmit = brcm_leg_tag_xmit, + .rcv = brcm_leg_tag_rcv, + .needed_headroom = BRCM_LEG_TAG_LEN, +}; + +DSA_TAG_DRIVER(brcm_legacy_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY, BRCM_LEGACY_NAME); +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY */ + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) +static struct sk_buff *brcm_leg_fcs_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + unsigned int fcs_len; + __le32 fcs_val; + u8 *brcm_tag; + + /* 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 + * need to make sure that packets are at least 70 bytes (including FCS + * and tag) because the length verification is done after the Broadcom + * tag is stripped off the ingress packet. + * + * Let dsa_user_xmit() free the SKB. + */ + if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) + return NULL; + + fcs_len = skb->len; + fcs_val = cpu_to_le32(crc32_le(~0, skb->data, fcs_len) ^ ~0); + + skb_push(skb, BRCM_LEG_TAG_LEN); + + dsa_alloc_etype_header(skb, BRCM_LEG_TAG_LEN); + + brcm_tag = skb->data + 2 * ETH_ALEN; + + /* Broadcom tag type */ + brcm_tag[0] = BRCM_LEG_TYPE_HI; + brcm_tag[1] = BRCM_LEG_TYPE_LO; + + /* Broadcom tag value */ + brcm_tag[2] = BRCM_LEG_EGRESS | BRCM_LEG_LEN_HI(fcs_len); + brcm_tag[3] = BRCM_LEG_LEN_LO(fcs_len); + brcm_tag[4] = 0; + brcm_tag[5] = dp->index & BRCM_LEG_PORT_ID; + + /* Original FCS value */ + if (__skb_pad(skb, ETH_FCS_LEN, false)) + return NULL; + skb_put_data(skb, &fcs_val, ETH_FCS_LEN); + + return skb; +} + +static const struct dsa_device_ops brcm_legacy_fcs_netdev_ops = { + .name = BRCM_LEGACY_FCS_NAME, + .proto = DSA_TAG_PROTO_BRCM_LEGACY_FCS, + .xmit = brcm_leg_fcs_tag_xmit, + .rcv = brcm_leg_tag_rcv, + .needed_headroom = BRCM_LEG_TAG_LEN, +}; + +DSA_TAG_DRIVER(brcm_legacy_fcs_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_LEGACY_FCS, BRCM_LEGACY_FCS_NAME); +#endif /* CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS */ + #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, struct net_device *dev) @@ -216,30 +379,34 @@ static struct sk_buff *brcm_tag_xmit_prepend(struct sk_buff *skb, } static struct sk_buff *brcm_tag_rcv_prepend(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { /* tag is prepended to the packet */ - return brcm_tag_rcv_ll(skb, dev, pt, ETH_HLEN); + return brcm_tag_rcv_ll(skb, dev, ETH_HLEN); } static const struct dsa_device_ops brcm_prepend_netdev_ops = { - .name = "brcm-prepend", + .name = BRCM_PREPEND_NAME, .proto = DSA_TAG_PROTO_BRCM_PREPEND, .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, - .overhead = BRCM_TAG_LEN, - .flow_dissect = brcm_tag_flow_dissect, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM_PREPEND, BRCM_PREPEND_NAME); #endif static struct dsa_tag_driver *dsa_tag_driver_array[] = { #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM) &DSA_TAG_DRIVER_NAME(brcm_netdev_ops), #endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY) + &DSA_TAG_DRIVER_NAME(brcm_legacy_netdev_ops), +#endif +#if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_LEGACY_FCS) + &DSA_TAG_DRIVER_NAME(brcm_legacy_fcs_netdev_ops), +#endif #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM_PREPEND) &DSA_TAG_DRIVER_NAME(brcm_prepend_netdev_ops), #endif @@ -247,4 +414,5 @@ static struct dsa_tag_driver *dsa_tag_driver_array[] = { module_dsa_tag_drivers(dsa_tag_driver_array); +MODULE_DESCRIPTION("DSA tag driver for Broadcom switches using in-frame headers"); MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7ddec9794477..2a2c4fb61a65 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -1,106 +1,297 @@ // 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/dsa/mv88e6xxx.h> #include <linux/etherdevice.h> #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" + +#define DSA_NAME "dsa" +#define EDSA_NAME "edsa" #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); + struct dsa_port *dp = dsa_user_to_port(dev); + struct net_device *br_dev; + u8 tag_dev, tag_port; + enum dsa_cmd cmd; 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 (skb->offload_fwd_mark) { + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + struct dsa_switch_tree *dst = dp->ds->dst; - /* - * Construct tagged FROM_CPU DSA tag from 802.1q tag. - */ - dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x60 | dp->ds->index; - dsa_header[1] = dp->index << 3; + cmd = DSA_CMD_FORWARD; - /* - * Move CFI field from byte 2 to byte 1. + /* When offloading forwarding for a bridge, inject FORWARD + * packets on behalf of a virtual switch device with an index + * past the physical switches. */ + tag_dev = dst->last_switch + bridge_num; + tag_port = 0; + } else { + cmd = DSA_CMD_FROM_CPU; + tag_dev = dp->ds->index; + tag_port = dp->index; + } + + br_dev = dsa_port_bridge_dev_get(dp); + + /* If frame is already 802.1Q tagged, we can convert it to a DSA + * tag (avoiding a memmove), but only if the port is standalone + * (in which case we always send FROM_CPU) or if the port's + * bridge has VLAN filtering enabled (in which case the CPU port + * will be a member of the VLAN). + */ + if (skb->protocol == htons(ETH_P_8021Q) && + (!br_dev || br_vlan_enabled(br_dev))) { + if (extra) { + skb_push(skb, extra); + dsa_alloc_etype_header(skb, extra); + } + + /* Construct tagged DSA tag from 802.1Q tag. */ + dsa_header = dsa_etype_header_pos_tx(skb) + extra; + dsa_header[0] = (cmd << 6) | 0x20 | tag_dev; + dsa_header[1] = tag_port << 3; + + /* 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); + u16 vid; - memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); + vid = br_dev ? MV88E6XXX_VID_BRIDGED : MV88E6XXX_VID_STANDALONE; - /* - * Construct untagged FROM_CPU DSA tag. - */ - dsa_header = skb->data + 2 * ETH_ALEN; - dsa_header[0] = 0x40 | dp->ds->index; - dsa_header[1] = dp->index << 3; - dsa_header[2] = 0x00; - dsa_header[3] = 0x00; + skb_push(skb, DSA_HLEN + extra); + dsa_alloc_etype_header(skb, DSA_HLEN + extra); + + /* Construct DSA header from untagged frame. */ + dsa_header = dsa_etype_header_pos_tx(skb) + extra; + + dsa_header[0] = (cmd << 6) | tag_dev; + dsa_header[1] = tag_port << 3; + dsa_header[2] = vid >> 8; + dsa_header[3] = vid & 0xff; } 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) { + bool trap = false, trunk = false; + int source_device, source_port; + 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. */ + dsa_header = dsa_etype_header_pos_rx(skb); - /* - * The ethertype field is part of the DSA header. - */ - dsa_header = skb->data - 2; + cmd = dsa_header[0] >> 6; + switch (cmd) { + case DSA_CMD_FORWARD: + trunk = !!(dsa_header[1] & 4); + break; - /* - * Check that frame type is either TO_CPU or FORWARD. - */ - if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0) + 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. + */ + 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. + */ + trap = true; + 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; + struct dsa_lag *lag; + + /* The exact source port is not available in the tag, + * so we inject the frame directly on the upper + * team/bond. + */ + lag = dsa_lag_by_id(cpu_dp->dst, source_port + 1); + skb->dev = lag ? lag->dev : NULL; + } else { + skb->dev = dsa_conduit_find_user(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. + /* When using LAG offload, skb->dev is not a DSA user interface, + * so we cannot call dsa_default_offload_fwd_mark and we need to + * special-case it. + */ + if (trunk) + skb->offload_fwd_mark = true; + else if (!trap) + dsa_default_offload_fwd_mark(skb); + + /* 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 +300,13 @@ 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 +315,96 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev, } memcpy(dsa_header, new_header, DSA_HLEN); + + if (extra) + dsa_strip_etype_header(skb, extra); } else { - /* - * Remove DSA tag and update checksum. - */ skb_pull_rcsum(skb, DSA_HLEN); - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - DSA_HLEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, DSA_HLEN + extra); } - 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) +{ + return dsa_xmit_ll(skb, dev, 0); +} + +static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev) { - *offset = 4; - *proto = ((__be16 *)skb->data)[1]; - return 0; + 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, - .overhead = DSA_HLEN, + .name = DSA_NAME, + .proto = DSA_TAG_PROTO_DSA, + .xmit = dsa_xmit, + .rcv = dsa_rcv, + .needed_headroom = DSA_HLEN, }; -MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA); +DSA_TAG_DRIVER(dsa_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA, DSA_NAME); +#endif /* CONFIG_NET_DSA_TAG_DSA */ + +#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA) -module_dsa_tag_driver(dsa_netdev_ops); +#define EDSA_HLEN 8 + +static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) +{ + u8 *edsa_header; + + skb = dsa_xmit_ll(skb, dev, EDSA_HLEN - DSA_HLEN); + if (!skb) + return NULL; + + edsa_header = dsa_etype_header_pos_tx(skb); + 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) +{ + 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_NAME, + .proto = DSA_TAG_PROTO_EDSA, + .xmit = edsa_xmit, + .rcv = edsa_rcv, + .needed_headroom = EDSA_HLEN, +}; + +DSA_TAG_DRIVER(edsa_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA, EDSA_NAME); +#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_DESCRIPTION("DSA tag driver for Marvell switches using DSA headers"); +MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c deleted file mode 100644 index e8eaa804ccb9..000000000000 --- a/net/dsa/tag_edsa.c +++ /dev/null @@ -1,184 +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 - -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 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. - */ - if ((edsa_header[0] & 0xc0) != 0x00 && (edsa_header[0] & 0xc0) != 0xc0) - 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); - } - - skb->offload_fwd_mark = 1; - - 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..5fa436121087 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -10,7 +10,9 @@ #include <linux/skbuff.h> #include <net/dsa.h> -#include "dsa_priv.h" +#include "tag.h" + +#define GSWIP_NAME "gswip" #define GSWIP_TX_HEADER_LEN 4 @@ -46,8 +48,7 @@ /* Byte 3 */ #define GSWIP_TX_DPID_EN BIT(0) -#define GSWIP_TX_PORT_MAP_SHIFT 1 -#define GSWIP_TX_PORT_MAP_MASK GENMASK(6, 1) +#define GSWIP_TX_PORT_MAP GENMASK(6, 1) #define GSWIP_RX_HEADER_LEN 8 @@ -59,29 +60,22 @@ 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; gswip_tag[0] = GSWIP_TX_SLPID_CPU; gswip_tag[1] = GSWIP_TX_DPID_ELAN; gswip_tag[2] = GSWIP_TX_PORT_MAP_EN | GSWIP_TX_PORT_MAP_SEL; - gswip_tag[3] = BIT(dp->index + GSWIP_TX_PORT_MAP_SHIFT) & GSWIP_TX_PORT_MAP_MASK; + gswip_tag[3] = FIELD_PREP(GSWIP_TX_PORT_MAP, dsa_xmit_port_mask(skb, dev)); gswip_tag[3] |= GSWIP_TX_DPID_EN; return skb; } static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, - struct net_device *dev, - struct packet_type *pt) + struct net_device *dev) { int port; u8 *gswip_tag; @@ -93,7 +87,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; @@ -104,14 +98,15 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops gswip_netdev_ops = { - .name = "gswip", + .name = GSWIP_NAME, .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, - .overhead = GSWIP_RX_HEADER_LEN, + .needed_headroom = GSWIP_RX_HEADER_LEN, }; +MODULE_DESCRIPTION("DSA tag driver for Lantiq / Intel GSWIP switches"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_GSWIP, GSWIP_NAME); module_dsa_tag_driver(gswip_netdev_ops); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c new file mode 100644 index 000000000000..544ab15685a2 --- /dev/null +++ b/net/dsa/tag_hellcreek.c @@ -0,0 +1,73 @@ +// 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 <kurt@linutronix.de> + * + * Based on tag_ksz.c. + */ + +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "tag.h" + +#define HELLCREEK_NAME "hellcreek" + +#define HELLCREEK_TAG_LEN 1 + +static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + u8 *tag; + + /* Calculate checksums (if required) before adding the trailer tag to + * avoid including it in calculations. That would lead to wrong + * checksums after the switch strips the tag. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + return NULL; + + /* Tag encoding */ + tag = skb_put(skb, HELLCREEK_TAG_LEN); + *tag = dsa_xmit_port_mask(skb, dev); + + return skb; +} + +static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + /* Tag decoding */ + u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; + unsigned int port = tag[0] & 0x03; + + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) { + netdev_warn_once(dev, "Failed to get source port: %d\n", port); + return NULL; + } + + if (pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN)) + return NULL; + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops hellcreek_netdev_ops = { + .name = HELLCREEK_NAME, + .proto = DSA_TAG_PROTO_HELLCREEK, + .xmit = hellcreek_xmit, + .rcv = hellcreek_rcv, + .needed_tailroom = HELLCREEK_TAG_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for Hirschmann Hellcreek TSN switches"); +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK, HELLCREEK_NAME); + +module_dsa_tag_driver(hellcreek_netdev_ops); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 90d055c4df9e..9170a0148cc4 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -4,67 +4,97 @@ * Copyright (c) 2017 Microchip Technology */ +#include <linux/dsa/ksz_common.h> #include <linux/etherdevice.h> #include <linux/list.h> -#include <linux/slab.h> +#include <linux/ptp_classify.h> #include <net/dsa.h> -#include "dsa_priv.h" + +#include "tag.h" + +#define KSZ8795_NAME "ksz8795" +#define KSZ9477_NAME "ksz9477" +#define KSZ9893_NAME "ksz9893" +#define LAN937X_NAME "lan937x" /* Typically only one byte is used for tail tag. */ +#define KSZ_PTP_TAG_LEN 4 #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) +#define KSZ_HWTS_EN 0 + +struct ksz_tagger_private { + struct ksz_tagger_data data; /* Must be first */ + unsigned long state; + struct kthread_worker *xmit_worker; +}; + +static struct ksz_tagger_private * +ksz_tagger_private(struct dsa_switch *ds) +{ + return ds->tagger_data; +} + +static void ksz_hwtstamp_set_state(struct dsa_switch *ds, bool on) +{ + struct ksz_tagger_private *priv = ksz_tagger_private(ds); + + if (on) + set_bit(KSZ_HWTS_EN, &priv->state); + else + clear_bit(KSZ_HWTS_EN, &priv->state); +} + +static void ksz_disconnect(struct dsa_switch *ds) { - 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); + struct ksz_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int ksz_connect(struct dsa_switch *ds) +{ + struct ksz_tagger_data *tagger_data; + struct kthread_worker *xmit_worker; + struct ksz_tagger_private *priv; + int ret; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit", + ds->dst->index, ds->index); + if (IS_ERR(xmit_worker)) { + ret = PTR_ERR(xmit_worker); + kfree(priv); + return ret; } - return nskb; + priv->xmit_worker = xmit_worker; + /* Export functions for switch driver use */ + tagger_data = &priv->data; + tagger_data->hwtstamp_set_state = ksz_hwtstamp_set_state; + ds->tagger_data = priv; + + return 0; } static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) { - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; - pskb_trim_rcsum(skb, skb->len - len); + if (pskb_trim_rcsum(skb, skb->len - len)) + return NULL; - skb->offload_fwd_mark = true; + dsa_default_offload_fwd_mark(skb); return skb; } @@ -81,172 +111,355 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- * tag0 : zero-based value represents port - * (eg, 0x00=port1, 0x02=port3, 0x06=port7) + * (eg, 0x0=port1, 0x2=port3, 0x3=port4) */ +#define KSZ8795_TAIL_TAG_EG_PORT_M GENMASK(1, 0) #define KSZ8795_TAIL_TAG_OVERRIDE BIT(6) #define KSZ8795_TAIL_TAG_LOOKUP BIT(7) 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; + struct ethhdr *hdr; u8 *tag; - u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) 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); + hdr = skb_eth_hdr(skb); - *tag = 1 << dp->index; - if (is_link_local_ether_addr(addr)) + *tag = dsa_xmit_port_mask(skb, dev); + if (is_link_local_ether_addr(hdr->h_dest)) *tag |= KSZ8795_TAIL_TAG_OVERRIDE; - return nskb; + return skb; } -static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; - return ksz_common_rcv(skb, dev, tag[0] & 7, KSZ_EGRESS_TAG_LEN); + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + + return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, + KSZ_EGRESS_TAG_LEN); } static const struct dsa_device_ops ksz8795_netdev_ops = { - .name = "ksz8795", + .name = KSZ8795_NAME, .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ8795, KSZ8795_NAME); /* - * For Ingress (Host -> KSZ9477), 2 bytes are added before FCS. + * For Ingress (Host -> KSZ9477), 2/6 bytes are added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|tag1(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)| + * FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if PTP is enabled in the Hardware) * tag0 : Prioritization (not used now) * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x10=port5) * - * For Egress (KSZ9477 -> Host), 1 byte is added before FCS. + * For Egress (KSZ9477 -> Host), 1/5 bytes is added before FCS. * --------------------------------------------------------------------------- - * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|tag0(1byte)|FCS(4bytes) + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes) * --------------------------------------------------------------------------- + * ts : time stamp (Present only if bit 7 of tag0 is set) * tag0 : zero-based value represents port * (eg, 0x00=port1, 0x02=port3, 0x06=port7) */ #define KSZ9477_INGRESS_TAG_LEN 2 #define KSZ9477_PTP_TAG_LEN 4 -#define KSZ9477_PTP_TAG_INDICATION 0x80 +#define KSZ9477_PTP_TAG_INDICATION BIT(7) +#define KSZ9477_TAIL_TAG_EG_PORT_M GENMASK(2, 0) +#define KSZ9477_TAIL_TAG_PRIO GENMASK(8, 7) #define KSZ9477_TAIL_TAG_OVERRIDE BIT(9) #define KSZ9477_TAIL_TAG_LOOKUP BIT(10) +static void ksz_rcv_timestamp(struct sk_buff *skb, u8 *tag) +{ + u8 *tstamp_raw = tag - KSZ_PTP_TAG_LEN; + ktime_t tstamp; + + tstamp = ksz_decode_tstamp(get_unaligned_be32(tstamp_raw)); + KSZ_SKB_CB(skb)->tstamp = tstamp; +} + +/* Time stamp tag *needs* to be inserted if PTP is enabled in hardware. + * Regardless of Whether it is a PTP frame or not. + */ +static void ksz_xmit_timestamp(struct dsa_port *dp, struct sk_buff *skb) +{ + struct ksz_tagger_private *priv; + struct ptp_header *ptp_hdr; + unsigned int ptp_type; + u32 tstamp_raw = 0; + s64 correction; + + priv = ksz_tagger_private(dp->ds); + + if (!test_bit(KSZ_HWTS_EN, &priv->state)) + return; + + if (!KSZ_SKB_CB(skb)->update_correction) + goto output_tag; + + ptp_type = KSZ_SKB_CB(skb)->ptp_type; + + ptp_hdr = ptp_parse_header(skb, ptp_type); + if (!ptp_hdr) + goto output_tag; + + correction = (s64)get_unaligned_be64(&ptp_hdr->correction); + + if (correction < 0) { + struct timespec64 ts; + + ts = ns_to_timespec64(-correction >> 16); + tstamp_raw = ((ts.tv_sec & 3) << 30) | ts.tv_nsec; + + /* Set correction field to 0 and update UDP checksum */ + ptp_header_update_correction(skb, ptp_type, ptp_hdr, 0); + } + +output_tag: + put_unaligned_be32(tstamp_raw, skb_put(skb, KSZ_PTP_TAG_LEN)); +} + +/* Defer transmit if waiting for egress time stamp is required. */ +static struct sk_buff *ksz_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) +{ + struct ksz_tagger_data *tagger_data = ksz_tagger_data(dp->ds); + struct ksz_tagger_private *priv = ksz_tagger_private(dp->ds); + void (*xmit_work_fn)(struct kthread_work *work); + struct sk_buff *clone = KSZ_SKB_CB(skb)->clone; + struct ksz_deferred_xmit_work *xmit_work; + struct kthread_worker *xmit_worker; + + if (!clone) + return skb; /* no deferred xmit for this packet */ + + xmit_work_fn = tagger_data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + kthread_init_work(&xmit_work->work, xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_user_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); + + return NULL; +} + 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; - u16 *tag; - u8 *addr; - - nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN); - if (!nskb) + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 prio = netdev_txq_to_tc(dev, queue_mapping); + struct dsa_port *dp = dsa_user_to_port(dev); + struct ethhdr *hdr; + __be16 *tag; + u16 val; + + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + ksz_xmit_timestamp(dp, skb); + + tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); + hdr = skb_eth_hdr(skb); - *tag = BIT(dp->index); + val = dsa_xmit_port_mask(skb, dev); + val |= FIELD_PREP(KSZ9477_TAIL_TAG_PRIO, prio); - if (is_link_local_ether_addr(addr)) - *tag |= KSZ9477_TAIL_TAG_OVERRIDE; + if (is_link_local_ether_addr(hdr->h_dest)) + val |= KSZ9477_TAIL_TAG_OVERRIDE; - *tag = cpu_to_be16(*tag); + *tag = cpu_to_be16(val); - return nskb; + return ksz_defer_xmit(dp, skb); } -static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { - /* Tag decoding */ - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; - unsigned int port = tag[0] & 7; unsigned int len = KSZ_EGRESS_TAG_LEN; + unsigned int port; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + /* Tag decoding */ + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; /* Extra 4-bytes PTP timestamp */ - if (tag[0] & KSZ9477_PTP_TAG_INDICATION) - len += KSZ9477_PTP_TAG_LEN; + if (tag[0] & KSZ9477_PTP_TAG_INDICATION) { + ksz_rcv_timestamp(skb, tag); + len += KSZ_PTP_TAG_LEN; + } return ksz_common_rcv(skb, dev, port, len); } static const struct dsa_device_ops ksz9477_netdev_ops = { - .name = "ksz9477", + .name = KSZ9477_NAME, .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ9477_INGRESS_TAG_LEN, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = KSZ9477_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9477, KSZ9477_NAME); +#define KSZ9893_TAIL_TAG_PRIO GENMASK(4, 3) #define KSZ9893_TAIL_TAG_OVERRIDE BIT(5) #define KSZ9893_TAIL_TAG_LOOKUP BIT(6) 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; + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 prio = netdev_txq_to_tc(dev, queue_mapping); + struct dsa_port *dp = dsa_user_to_port(dev); + struct ethhdr *hdr; u8 *tag; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) return NULL; /* Tag encoding */ - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + ksz_xmit_timestamp(dp, skb); + + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); + hdr = skb_eth_hdr(skb); - *tag = BIT(dp->index); + *tag = dsa_xmit_port_mask(skb, dev); + *tag |= FIELD_PREP(KSZ9893_TAIL_TAG_PRIO, prio); - if (is_link_local_ether_addr(addr)) + if (is_link_local_ether_addr(hdr->h_dest)) *tag |= KSZ9893_TAIL_TAG_OVERRIDE; - return nskb; + return ksz_defer_xmit(dp, skb); } static const struct dsa_device_ops ksz9893_netdev_ops = { - .name = "ksz9893", + .name = KSZ9893_NAME, .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = KSZ_INGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_KSZ9893, KSZ9893_NAME); + +/* For xmit, 2/6 bytes are added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|tag1(1byte)| + * FCS(4bytes) + * --------------------------------------------------------------------------- + * ts : time stamp (Present only if PTP is enabled in the Hardware) + * tag0 : represents tag override, lookup and valid + * tag1 : each bit represents port (eg, 0x01=port1, 0x02=port2, 0x80=port8) + * + * For rcv, 1/5 bytes is added before FCS. + * --------------------------------------------------------------------------- + * DA(6bytes)|SA(6bytes)|....|Data(nbytes)|ts(4bytes)|tag0(1byte)|FCS(4bytes) + * --------------------------------------------------------------------------- + * ts : time stamp (Present only if bit 7 of tag0 is set) + * tag0 : zero-based value represents port + * (eg, 0x00=port1, 0x02=port3, 0x07=port8) + */ +#define LAN937X_EGRESS_TAG_LEN 2 + +#define LAN937X_TAIL_TAG_BLOCKING_OVERRIDE BIT(11) +#define LAN937X_TAIL_TAG_LOOKUP BIT(12) +#define LAN937X_TAIL_TAG_VALID BIT(13) +#define LAN937X_TAIL_TAG_PRIO GENMASK(10, 8) +#define LAN937X_TAIL_TAG_PORT_MASK 7 + +static struct sk_buff *lan937x_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 prio = netdev_txq_to_tc(dev, queue_mapping); + struct dsa_port *dp = dsa_user_to_port(dev); + const struct ethhdr *hdr = eth_hdr(skb); + __be16 *tag; + u16 val; + + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + + ksz_xmit_timestamp(dp, skb); + + tag = skb_put(skb, LAN937X_EGRESS_TAG_LEN); + + val = dsa_xmit_port_mask(skb, dev); + val |= FIELD_PREP(LAN937X_TAIL_TAG_PRIO, prio); + + if (is_link_local_ether_addr(hdr->h_dest)) + val |= LAN937X_TAIL_TAG_BLOCKING_OVERRIDE; + + /* Tail tag valid bit - This bit should always be set by the CPU */ + val |= LAN937X_TAIL_TAG_VALID; + + put_unaligned_be16(val, tag); + + return ksz_defer_xmit(dp, skb); +} + +static const struct dsa_device_ops lan937x_netdev_ops = { + .name = LAN937X_NAME, + .proto = DSA_TAG_PROTO_LAN937X, + .xmit = lan937x_xmit, + .rcv = ksz9477_rcv, + .connect = ksz_connect, + .disconnect = ksz_disconnect, + .needed_tailroom = LAN937X_EGRESS_TAG_LEN + KSZ_PTP_TAG_LEN, +}; + +DSA_TAG_DRIVER(lan937x_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN937X, LAN937X_NAME); static struct dsa_tag_driver *dsa_tag_driver_array[] = { &DSA_TAG_DRIVER_NAME(ksz8795_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9477_netdev_ops), &DSA_TAG_DRIVER_NAME(ksz9893_netdev_ops), + &DSA_TAG_DRIVER_NAME(lan937x_netdev_ops), }; module_dsa_tag_drivers(dsa_tag_driver_array); +MODULE_DESCRIPTION("DSA tag driver for Microchip 8795/937x/9477/9893 families of switches"); MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index eb0e7a32e53d..258e5d7dc5ef 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -7,7 +7,7 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" /* To define the outgoing port and to discover the incoming port a regular * VLAN tag is used by the LAN9303. But its VID meaning is 'special': @@ -30,6 +30,8 @@ * Required when no forwarding between the external ports should happen. */ +#define LAN9303_NAME "lan9303" + #define LAN9303_TAG_LEN 4 # define LAN9303_TAG_TX_USE_ALR BIT(3) # define LAN9303_TAG_TX_STP_OVERRIDE BIT(4) @@ -54,38 +56,29 @@ static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr) static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); - u16 *lan9303_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; - } + struct dsa_port *dp = dsa_user_to_port(dev); + __be16 *lan9303_tag; + u16 tag; /* provide 'LAN9303_TAG_LEN' bytes additional space */ skb_push(skb, LAN9303_TAG_LEN); /* make room between MACs and Ether-Type */ - memmove(skb->data, skb->data + LAN9303_TAG_LEN, 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, LAN9303_TAG_LEN); - lan9303_tag = (u16 *)(skb->data + 2 * ETH_ALEN); + lan9303_tag = dsa_etype_header_pos_tx(skb); + + tag = lan9303_xmit_use_arl(dp, skb->data) ? + LAN9303_TAG_TX_USE_ALR : + dp->index | LAN9303_TAG_TX_STP_OVERRIDE; lan9303_tag[0] = htons(ETH_P_8021Q); - lan9303_tag[1] = lan9303_xmit_use_arl(dp, skb->data) ? - LAN9303_TAG_TX_USE_ALR : - dp->index | LAN9303_TAG_TX_STP_OVERRIDE; - lan9303_tag[1] = htons(lan9303_tag[1]); + lan9303_tag[1] = htons(tag); return skb; } -static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev) { - u16 *lan9303_tag; u16 lan9303_tag1; unsigned int source_port; @@ -95,48 +88,39 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev, return NULL; } - /* '->data' points into the middle of our special VLAN tag information: - * - * ~ MAC src | 0x81 | 0x00 | 0xyy | 0xzz | ether type - * ^ - * ->data - */ - lan9303_tag = (u16 *)(skb->data - 2); - - if (lan9303_tag[0] != htons(ETH_P_8021Q)) { - dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid VLAN marker\n"); - return NULL; + if (skb_vlan_tag_present(skb)) { + lan9303_tag1 = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + skb_push_rcsum(skb, ETH_HLEN); + __skb_vlan_pop(skb, &lan9303_tag1); + skb_pull_rcsum(skb, ETH_HLEN); } - lan9303_tag1 = ntohs(lan9303_tag[1]); source_port = lan9303_tag1 & 0x3; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; } - /* remove the special VLAN tag between the MAC addresses - * and the current ethertype field. - */ - skb_pull_rcsum(skb, 2 + 2); - memmove(skb->data - ETH_HLEN, skb->data - (ETH_HLEN + LAN9303_TAG_LEN), - 2 * ETH_ALEN); - skb->offload_fwd_mark = !(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU); + if (!(lan9303_tag1 & LAN9303_TAG_RX_TRAPPED_TO_CPU)) + dsa_default_offload_fwd_mark(skb); return skb; } static const struct dsa_device_ops lan9303_netdev_ops = { - .name = "lan9303", + .name = LAN9303_NAME, .proto = DSA_TAG_PROTO_LAN9303, .xmit = lan9303_xmit, .rcv = lan9303_rcv, - .overhead = LAN9303_TAG_LEN, + .needed_headroom = LAN9303_TAG_LEN, }; +MODULE_DESCRIPTION("DSA tag driver for SMSC/Microchip LAN9303 family of switches"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_LAN9303, LAN9303_NAME); module_dsa_tag_driver(lan9303_netdev_ops); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index d6619edd53e5..dea3eecaf093 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -8,11 +8,14 @@ #include <linux/etherdevice.h> #include <linux/if_vlan.h> -#include "dsa_priv.h" +#include "tag.h" + +#define MTK_NAME "mtk" #define MTK_HDR_LEN 4 #define MTK_HDR_XMIT_UNTAGGED 0 #define MTK_HDR_XMIT_TAGGED_TPID_8100 1 +#define MTK_HDR_XMIT_TAGGED_TPID_88A8 2 #define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) #define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0) #define MTK_HDR_XMIT_SA_DIS BIT(6) @@ -20,12 +23,11 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + u8 xmit_tpid; u8 *mtk_tag; - bool is_vlan_skb = true; - unsigned char *dest = eth_hdr(skb)->h_dest; - bool is_multicast_skb = is_multicast_ether_addr(dest) && - !is_broadcast_ether_addr(dest); + + skb_set_queue_mapping(skb, dp->index); /* Build the special tag after the MAC Source Address. If VLAN header * is present, it's required that VLAN header and special tag is @@ -33,30 +35,30 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * the both special and VLAN tag at the same time and then look up VLAN * table with VID. */ - if (!skb_vlan_tagged(skb)) { - if (skb_cow_head(skb, MTK_HDR_LEN) < 0) - return NULL; - + switch (skb->protocol) { + case htons(ETH_P_8021Q): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100; + break; + case htons(ETH_P_8021AD): + xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8; + break; + default: + xmit_tpid = MTK_HDR_XMIT_UNTAGGED; skb_push(skb, MTK_HDR_LEN); - memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); - is_vlan_skb = false; + dsa_alloc_etype_header(skb, MTK_HDR_LEN); } - mtk_tag = skb->data + 2 * ETH_ALEN; + mtk_tag = dsa_etype_header_pos_tx(skb); /* Mark tag attribute on special tag insertion to notify hardware * whether that's a combined special tag with 802.1Q header. */ - mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 : - MTK_HDR_XMIT_UNTAGGED; - mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; - - /* Disable SA learning for multicast frames */ - if (unlikely(is_multicast_skb)) - mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; + mtk_tag[0] = xmit_tpid; + mtk_tag[1] = FIELD_PREP(MTK_HDR_XMIT_DP_BIT_MASK, + dsa_xmit_port_mask(skb, dev)); /* Tag control information is kept for 802.1Q */ - if (!is_vlan_skb) { + if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) { mtk_tag[2] = 0; mtk_tag[3] = 0; } @@ -64,65 +66,45 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, return skb; } -static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev) { + u16 hdr; int port; - __be16 *phdr, hdr; - unsigned char *dest = eth_hdr(skb)->h_dest; - bool is_multicast_skb = is_multicast_ether_addr(dest) && - !is_broadcast_ether_addr(dest); + __be16 *phdr; if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) return NULL; - /* The MTK header is added by the switch between src addr - * and ethertype at this point, skb->data points to 2 bytes - * after src addr so header should be 2 bytes right before. - */ - phdr = (__be16 *)(skb->data - 2); + phdr = dsa_etype_header_pos_rx(skb); hdr = ntohs(*phdr); /* Remove MTK tag and recalculate checksum. */ skb_pull_rcsum(skb, MTK_HDR_LEN); - memmove(skb->data - ETH_HLEN, - skb->data - ETH_HLEN - MTK_HDR_LEN, - 2 * ETH_ALEN); + dsa_strip_etype_header(skb, MTK_HDR_LEN); /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; - /* Only unicast or broadcast frames are offloaded */ - if (likely(!is_multicast_skb)) - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); 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", + .name = MTK_NAME, .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .flow_dissect = mtk_tag_flow_dissect, - .overhead = MTK_HDR_LEN, + .needed_headroom = MTK_HDR_LEN, }; +MODULE_DESCRIPTION("DSA tag driver for Mediatek switches"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MTK, MTK_NAME); module_dsa_tag_driver(mtk_netdev_ops); diff --git a/net/dsa/tag_mxl-gsw1xx.c b/net/dsa/tag_mxl-gsw1xx.c new file mode 100644 index 000000000000..60f7c445e656 --- /dev/null +++ b/net/dsa/tag_mxl-gsw1xx.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DSA driver Special Tag support for MaxLinear GSW1xx switch chips + * + * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org> + * Copyright (C) 2023 - 2024 MaxLinear Inc. + */ + +#include <linux/bitops.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "tag.h" + +/* To define the outgoing port and to discover the incoming port a special + * tag is used by the GSW1xx. + * + * Dest MAC Src MAC special TAG EtherType + * ...| 1 2 3 4 5 6 | 1 2 3 4 5 6 | 1 2 3 4 5 6 7 8 | 1 2 |... + * |<--------------->| + */ + +#define GSW1XX_TAG_NAME "gsw1xx" + +/* special tag header length (RX and TX) */ +#define GSW1XX_HEADER_LEN 8 + +/* Word 0 = Ethertype -> 0x88C3 */ + +/* Word 1 */ +#define GSW1XX_TX_PORT_MAP GENMASK(7, 0) +#define GSW1XX_TX_PORT_MAP_EN BIT(15) +#define GSW1XX_TX_CLASS_EN BIT(14) +#define GSW1XX_TX_TIME_STAMP_EN BIT(13) +#define GSW1XX_TX_LRN_DIS BIT(12) +#define GSW1XX_TX_CLASS GENMASK(11, 8) + +/* special tag in RX path header */ +/* Word 2 */ +#define GSW1XX_RX_PORT_MAP GENMASK(15, 8) + +static struct sk_buff *gsw1xx_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + __be16 *gsw1xx_tag; + u16 tag; + + /* provide additional space 'GSW1XX_HEADER_LEN' bytes */ + skb_push(skb, GSW1XX_HEADER_LEN); + + /* add space between MAC address and Ethertype */ + dsa_alloc_etype_header(skb, GSW1XX_HEADER_LEN); + + /* special tag ingress */ + gsw1xx_tag = dsa_etype_header_pos_tx(skb); + gsw1xx_tag[0] = htons(ETH_P_MXLGSW); + + tag = FIELD_PREP(GSW1XX_TX_PORT_MAP, dsa_xmit_port_mask(skb, dev)) | + GSW1XX_TX_PORT_MAP_EN | GSW1XX_TX_LRN_DIS; + gsw1xx_tag[1] = htons(tag); + gsw1xx_tag[2] = 0; + gsw1xx_tag[3] = 0; + + return skb; +} + +static struct sk_buff *gsw1xx_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + int port; + __be16 *gsw1xx_tag; + + if (unlikely(!pskb_may_pull(skb, GSW1XX_HEADER_LEN))) { + dev_warn_ratelimited(&dev->dev, "Dropping packet, cannot pull SKB\n"); + return NULL; + } + + gsw1xx_tag = dsa_etype_header_pos_rx(skb); + + if (unlikely(ntohs(gsw1xx_tag[0]) != ETH_P_MXLGSW)) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid special tag\n"); + dev_warn_ratelimited(&dev->dev, "Tag: %8ph\n", gsw1xx_tag); + return NULL; + } + + /* Get source port information */ + port = FIELD_GET(GSW1XX_RX_PORT_MAP, ntohs(gsw1xx_tag[1])); + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); + dev_warn_ratelimited(&dev->dev, "Tag: %8ph\n", gsw1xx_tag); + return NULL; + } + + /* remove the GSW1xx special tag between MAC addresses and the current + * ethertype field. + */ + skb_pull_rcsum(skb, GSW1XX_HEADER_LEN); + dsa_strip_etype_header(skb, GSW1XX_HEADER_LEN); + + return skb; +} + +static const struct dsa_device_ops gsw1xx_netdev_ops = { + .name = GSW1XX_TAG_NAME, + .proto = DSA_TAG_PROTO_MXL_GSW1XX, + .xmit = gsw1xx_tag_xmit, + .rcv = gsw1xx_tag_rcv, + .needed_headroom = GSW1XX_HEADER_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for MaxLinear GSW1xx 8 byte protocol"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MXL_GSW1XX, GSW1XX_TAG_NAME); + +module_dsa_tag_driver(gsw1xx_netdev_ops); diff --git a/net/dsa/tag_none.c b/net/dsa/tag_none.c new file mode 100644 index 000000000000..e9c9670a9c44 --- /dev/null +++ b/net/dsa/tag_none.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/dsa/tag_none.c - Traffic handling for switches with no tag + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * + * WARNING: do not use this for new switches. In case of no hardware + * tagging support, look at tag_8021q.c instead. + */ + +#include "tag.h" + +#define NONE_NAME "none" + +static struct sk_buff *dsa_user_notag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Just return the original SKB */ + return skb; +} + +static const struct dsa_device_ops none_ops = { + .name = NONE_NAME, + .proto = DSA_TAG_PROTO_NONE, + .xmit = dsa_user_notag_xmit, +}; + +module_dsa_tag_driver(none_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_NONE, NONE_NAME); +MODULE_DESCRIPTION("DSA no-op tag driver"); +MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index b0c98ee4e13b..3405def79c2d 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,199 +1,90 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019 NXP Semiconductors - */ -#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 | - * +------+------+------+------+------+------+------+------+ +/* Copyright 2019 NXP */ +#include <linux/dsa/ocelot.h> -static struct sk_buff *ocelot_xmit(struct sk_buff *skb, - struct net_device *netdev) +#include "tag.h" + +#define OCELOT_NAME "ocelot" +#define SEVILLE_NAME "seville" + +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); - u64 bypass, dest, src, qos_class, rew_op; + struct dsa_port *dp = dsa_user_to_port(netdev); struct dsa_switch *ds = dp->ds; - int port = dp->index; - struct ocelot *ocelot = ds->priv; - struct ocelot_port *ocelot_port = ocelot->ports[port]; - u8 *injection; + u64 vlan_tci, tag_type; + void *injection; + __be32 *prefix; + u32 rew_op = 0; + u64 qos_class; - if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) { - netdev_err(netdev, "Cannot make room for tag.\n"); - return NULL; - } + ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci, + &tag_type); + + qos_class = netdev_get_num_tc(netdev) ? + netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority; injection = skb_push(skb, OCELOT_TAG_LEN); + prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN); + *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, qos_class); + ocelot_ifh_set_vlan_tci(injection, vlan_tci); + ocelot_ifh_set_tag_type(injection, tag_type); - /* Set the source port as the CPU port module and not the NPI port */ - src = ocelot->num_phys_ports; - dest = BIT(port); - bypass = true; - qos_class = skb->priority; - - packing(injection, &bypass, 127, 127, OCELOT_TAG_LEN, PACK, 0); - packing(injection, &dest, 68, 56, OCELOT_TAG_LEN, PACK, 0); - packing(injection, &src, 46, 43, OCELOT_TAG_LEN, PACK, 0); - packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); - - if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - rew_op = ocelot_port->ptp_cmd; - if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { - rew_op |= (ocelot_port->ts_id % 4) << 3; - ocelot_port->ts_id++; - } - - packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); - } + rew_op = ocelot_ptp_rew_op(skb); + if (rew_op) + ocelot_ifh_set_rew_op(injection, rew_op); + + *ifh = injection; +} + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + void *injection; + + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x8880000a), &injection); + ocelot_ifh_set_dest(injection, dsa_xmit_port_mask(skb, netdev)); + + return skb; +} + +static struct sk_buff *seville_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + void *injection; + + ocelot_xmit_common(skb, netdev, cpu_to_be32(0x88800005), &injection); + seville_ifh_set_dest(injection, dsa_xmit_port_mask(skb, netdev)); return skb; } static struct sk_buff *ocelot_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { u64 src_port, qos_class; + u64 vlan_tci, tag_type; u8 *start = skb->data; + struct dsa_port *dp; u8 *extraction; + u16 vlan_tpid; + u64 rew_val; - /* Revert skb->data by the amount consumed by the DSA master, + /* Revert skb->data by the amount consumed by the DSA conduit, * 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 - * into the DSA master's RX filter. Discard it now by moving it into + /* We don't care about the short prefix, it is just for easy entrance + * into the DSA conduit'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. */ @@ -207,36 +98,89 @@ 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_rew_val(extraction, &rew_val); - skb->dev = dsa_master_find_slave(netdev, 0, src_port); + skb->dev = dsa_conduit_find_user(netdev, 0, src_port); if (!skb->dev) /* The switch will reflect back some frames sent through - * sockets opened on the bare DSA master. These will come back + * sockets opened on the bare DSA conduit. These will come back * with src_port equal to the index of the CPU port, for which - * there is no slave registered. So don't print any error + * there is no user registered. So don't print any error * message here (ignore and drop those frames). */ return NULL; - skb->offload_fwd_mark = 1; + dsa_default_offload_fwd_mark(skb); skb->priority = qos_class; + OCELOT_SKB_CB(skb)->tstamp_lo = rew_val; + + /* 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_user_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; } static const struct dsa_device_ops ocelot_netdev_ops = { - .name = "ocelot", + .name = OCELOT_NAME, .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, + .promisc_on_conduit = true, }; -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT); +DSA_TAG_DRIVER(ocelot_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT, OCELOT_NAME); -module_dsa_tag_driver(ocelot_netdev_ops); +static const struct dsa_device_ops seville_netdev_ops = { + .name = SEVILLE_NAME, + .proto = DSA_TAG_PROTO_SEVILLE, + .xmit = seville_xmit, + .rcv = ocelot_rcv, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, + .promisc_on_conduit = true, +}; + +DSA_TAG_DRIVER(seville_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SEVILLE, SEVILLE_NAME); + +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_DESCRIPTION("DSA tag driver for Ocelot family of switches, using NPI port"); +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..3929584791e4 --- /dev/null +++ b/net/dsa/tag_ocelot_8021q.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2020-2021 NXP + * + * 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 <linux/dsa/ocelot.h> + +#include "tag.h" +#include "tag_8021q.h" + +#define OCELOT_8021Q_NAME "ocelot-8021q" + +struct ocelot_8021q_tagger_private { + struct ocelot_8021q_tagger_data data; /* Must be first */ + struct kthread_worker *xmit_worker; +}; + +static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, + struct sk_buff *skb) +{ + struct ocelot_8021q_tagger_private *priv = dp->ds->tagger_data; + struct ocelot_8021q_tagger_data *data = &priv->data; + void (*xmit_work_fn)(struct kthread_work *work); + struct felix_deferred_xmit_work *xmit_work; + struct kthread_worker *xmit_worker; + + xmit_work_fn = data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; + + /* PTP over IP packets need UDP checksumming. We may have inherited + * NETIF_F_HW_CSUM from the DSA conduit, but these packets are not sent + * through the DSA conduit, so calculate the checksum here. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + /* Calls felix_port_deferred_xmit in felix.c */ + kthread_init_work(&xmit_work->work, xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_user_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); + + return NULL; +} + +static struct sk_buff *ocelot_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct dsa_port *dp = dsa_user_to_port(netdev); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); + struct ethhdr *hdr = eth_hdr(skb); + + if (ocelot_ptp_rew_op(skb) || is_link_local_ether_addr(hdr->h_dest)) + return ocelot_defer_xmit(dp, skb); + + 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) +{ + int src_port = -1, switch_id = -1; + + dsa_8021q_rcv(skb, &src_port, &switch_id, NULL, NULL); + + skb->dev = dsa_conduit_find_user(netdev, switch_id, src_port); + if (!skb->dev) + return NULL; + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static void ocelot_disconnect(struct dsa_switch *ds) +{ + struct ocelot_8021q_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int ocelot_connect(struct dsa_switch *ds) +{ + struct ocelot_8021q_tagger_private *priv; + int err; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->xmit_worker = kthread_run_worker(0, "felix_xmit"); + if (IS_ERR(priv->xmit_worker)) { + err = PTR_ERR(priv->xmit_worker); + kfree(priv); + return err; + } + + ds->tagger_data = priv; + + return 0; +} + +static const struct dsa_device_ops ocelot_8021q_netdev_ops = { + .name = OCELOT_8021Q_NAME, + .proto = DSA_TAG_PROTO_OCELOT_8021Q, + .xmit = ocelot_xmit, + .rcv = ocelot_rcv, + .connect = ocelot_connect, + .disconnect = ocelot_disconnect, + .needed_headroom = VLAN_HLEN, + .promisc_on_conduit = true, +}; + +MODULE_DESCRIPTION("DSA tag driver for Ocelot family of switches, using VLAN"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_OCELOT_8021Q, OCELOT_8021Q_NAME); + +module_dsa_tag_driver(ocelot_8021q_netdev_ops); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 70db7c909f74..6d56a28c914c 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -4,108 +4,122 @@ */ #include <linux/etherdevice.h> +#include <linux/bitfield.h> +#include <net/dsa.h> +#include <linux/dsa/tag_qca.h> -#include "dsa_priv.h" - -#define QCA_HDR_LEN 2 -#define QCA_HDR_VERSION 0x2 - -#define QCA_HDR_RECV_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_RECV_VERSION_S 14 -#define QCA_HDR_RECV_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_RECV_PRIORITY_S 11 -#define QCA_HDR_RECV_TYPE_MASK GENMASK(10, 6) -#define QCA_HDR_RECV_TYPE_S 6 -#define QCA_HDR_RECV_FRAME_IS_TAGGED BIT(3) -#define QCA_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) - -#define QCA_HDR_XMIT_VERSION_MASK GENMASK(15, 14) -#define QCA_HDR_XMIT_VERSION_S 14 -#define QCA_HDR_XMIT_PRIORITY_MASK GENMASK(13, 11) -#define QCA_HDR_XMIT_PRIORITY_S 11 -#define QCA_HDR_XMIT_CONTROL_MASK GENMASK(10, 8) -#define QCA_HDR_XMIT_CONTROL_S 8 -#define QCA_HDR_XMIT_FROM_CPU BIT(7) -#define QCA_HDR_XMIT_DP_BIT_MASK GENMASK(6, 0) +#include "tag.h" + +#define QCA_NAME "qca" static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); - u16 *phdr, hdr; - - if (skb_cow_head(skb, QCA_HDR_LEN) < 0) - return NULL; + __be16 *phdr; + u16 hdr; skb_push(skb, QCA_HDR_LEN); - memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN); - phdr = (u16 *)(skb->data + 2 * ETH_ALEN); + dsa_alloc_etype_header(skb, QCA_HDR_LEN); + phdr = dsa_etype_header_pos_tx(skb); /* Set the version field, and set destination port information */ - hdr = QCA_HDR_VERSION << QCA_HDR_XMIT_VERSION_S | - QCA_HDR_XMIT_FROM_CPU | BIT(dp->index); + hdr = FIELD_PREP(QCA_HDR_XMIT_VERSION, QCA_HDR_VERSION); + hdr |= QCA_HDR_XMIT_FROM_CPU; + hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, dsa_xmit_port_mask(skb, dev)); *phdr = htons(hdr); return skb; } -static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 ver; + struct qca_tagger_data *tagger_data; + struct dsa_port *dp = dev->dsa_ptr; + struct dsa_switch *ds = dp->ds; + u8 ver, pk_type; + __be16 *phdr; int port; - __be16 *phdr, hdr; + u16 hdr; + + BUILD_BUG_ON(sizeof(struct qca_mgmt_ethhdr) != QCA_HDR_MGMT_HEADER_LEN + QCA_HDR_LEN); + + tagger_data = ds->tagger_data; if (unlikely(!pskb_may_pull(skb, QCA_HDR_LEN))) return NULL; - /* The QCA header is added by the switch between src addr and Ethertype - * At this point, skb->data points to ethertype so header should be - * right before - */ - phdr = (__be16 *)(skb->data - 2); + phdr = dsa_etype_header_pos_rx(skb); hdr = ntohs(*phdr); /* Make sure the version is correct */ - ver = (hdr & QCA_HDR_RECV_VERSION_MASK) >> QCA_HDR_RECV_VERSION_S; + ver = FIELD_GET(QCA_HDR_RECV_VERSION, hdr); if (unlikely(ver != QCA_HDR_VERSION)) return NULL; - /* Remove QCA tag and recalculate checksum */ - skb_pull_rcsum(skb, QCA_HDR_LEN); - memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - QCA_HDR_LEN, - ETH_HLEN - QCA_HDR_LEN); + /* Get pk type */ + pk_type = FIELD_GET(QCA_HDR_RECV_TYPE, hdr); + + /* Ethernet mgmt read/write packet */ + if (pk_type == QCA_HDR_RECV_TYPE_RW_REG_ACK) { + if (likely(tagger_data->rw_reg_ack_handler)) + tagger_data->rw_reg_ack_handler(ds, skb); + return NULL; + } + + /* Ethernet MIB counter packet */ + if (pk_type == QCA_HDR_RECV_TYPE_MIB) { + if (likely(tagger_data->mib_autocast_handler)) + tagger_data->mib_autocast_handler(ds, skb); + return NULL; + } /* Get source port information */ - port = (hdr & QCA_HDR_RECV_SOURCE_PORT_MASK); + port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; + /* Remove QCA tag and recalculate checksum */ + skb_pull_rcsum(skb, QCA_HDR_LEN); + dsa_strip_etype_header(skb, QCA_HDR_LEN); + return skb; } -static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto, - int *offset) +static int qca_tag_connect(struct dsa_switch *ds) { - *offset = QCA_HDR_LEN; - *proto = ((__be16 *)skb->data)[0]; + struct qca_tagger_data *tagger_data; + + tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL); + if (!tagger_data) + return -ENOMEM; + + ds->tagger_data = tagger_data; return 0; } +static void qca_tag_disconnect(struct dsa_switch *ds) +{ + kfree(ds->tagger_data); + ds->tagger_data = NULL; +} + static const struct dsa_device_ops qca_netdev_ops = { - .name = "qca", + .name = QCA_NAME, .proto = DSA_TAG_PROTO_QCA, + .connect = qca_tag_connect, + .disconnect = qca_tag_disconnect, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .flow_dissect = qca_tag_flow_dissect, - .overhead = QCA_HDR_LEN, + .needed_headroom = QCA_HDR_LEN, + .promisc_on_conduit = true, }; +MODULE_DESCRIPTION("DSA tag driver for Qualcomm Atheros QCA8K switches"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_QCA, QCA_NAME); module_dsa_tag_driver(qca_netdev_ops); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c new file mode 100644 index 000000000000..3cc63eacfa03 --- /dev/null +++ b/net/dsa/tag_rtl4_a.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handler for Realtek 4 byte DSA switch tags + * Currently only supports protocol "A" found in RTL8366RB + * Copyright (c) 2020 Linus Walleij <linus.walleij@linaro.org> + * + * This "proprietary tag" header looks like so: + * + * ------------------------------------------------- + * | MAC DA | MAC SA | 0x8899 | 2 bytes tag | Type | + * ------------------------------------------------- + * + * The 2 bytes tag form a 16 bit big endian word. The exact + * meaning has been guessed from packet dumps from ingress + * frames. + */ + +#include <linux/etherdevice.h> +#include <linux/bits.h> + +#include "tag.h" + +#define RTL4_A_NAME "rtl4a" + +#define RTL4_A_HDR_LEN 4 +#define RTL4_A_PROTOCOL_SHIFT 12 +/* + * 0x1 = Realtek Remote Control protocol (RRCP) + * 0x2/0x3 seems to be used for loopback testing + * 0x9 = RTL8306 DSA protocol + * 0xa = RTL8366RB DSA protocol + */ +#define RTL4_A_PROTOCOL_RTL8366RB 0xa + +static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + __be16 *p; + u8 *tag; + u16 out; + + /* Pad out to at least 60 bytes */ + if (unlikely(__skb_put_padto(skb, ETH_ZLEN, false))) + return NULL; + + netdev_dbg(dev, "add realtek tag to package to port %d\n", + dp->index); + skb_push(skb, RTL4_A_HDR_LEN); + + dsa_alloc_etype_header(skb, RTL4_A_HDR_LEN); + tag = dsa_etype_header_pos_tx(skb); + + /* Set Ethertype */ + p = (__be16 *)tag; + *p = htons(ETH_P_REALTEK); + + out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT); + /* The lower bits indicate the port number */ + out |= dsa_xmit_port_mask(skb, dev); + + p = (__be16 *)(tag + 2); + *p = htons(out); + + return skb; +} + +static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + u16 protport; + __be16 *p; + u16 etype; + u8 *tag; + u8 prot; + u8 port; + + if (unlikely(!pskb_may_pull(skb, RTL4_A_HDR_LEN))) + return NULL; + + tag = dsa_etype_header_pos_rx(skb); + p = (__be16 *)tag; + etype = ntohs(*p); + if (etype != ETH_P_REALTEK) { + /* Not custom, just pass through */ + netdev_dbg(dev, "non-realtek ethertype 0x%04x\n", etype); + return skb; + } + p = (__be16 *)(tag + 2); + protport = ntohs(*p); + /* The 4 upper bits are the protocol */ + prot = (protport >> RTL4_A_PROTOCOL_SHIFT) & 0x0f; + if (prot != RTL4_A_PROTOCOL_RTL8366RB) { + netdev_err(dev, "unknown realtek protocol 0x%01x\n", prot); + return NULL; + } + port = protport & 0xff; + + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) { + netdev_dbg(dev, "could not find user for port %d\n", port); + return NULL; + } + + /* Remove RTL4 tag and recalculate checksum */ + skb_pull_rcsum(skb, RTL4_A_HDR_LEN); + + dsa_strip_etype_header(skb, RTL4_A_HDR_LEN); + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops rtl4a_netdev_ops = { + .name = RTL4_A_NAME, + .proto = DSA_TAG_PROTO_RTL4_A, + .xmit = rtl4a_tag_xmit, + .rcv = rtl4a_tag_rcv, + .needed_headroom = RTL4_A_HDR_LEN, +}; +module_dsa_tag_driver(rtl4a_netdev_ops); + +MODULE_DESCRIPTION("DSA tag driver for Realtek 4 byte protocol A tags"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL4_A, RTL4_A_NAME); diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c new file mode 100644 index 000000000000..2464545da4d2 --- /dev/null +++ b/net/dsa/tag_rtl8_4.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Handler for Realtek 8 byte switch tags + * + * Copyright (C) 2021 Alvin Å ipraga <alsi@bang-olufsen.dk> + * + * NOTE: Currently only supports protocol "4" found in the RTL8365MB, hence + * named tag_rtl8_4. + * + * This tag has the following format: + * + * 0 7|8 15 + * |-----------------------------------+-----------------------------------|--- + * | (16-bit) | ^ + * | Realtek EtherType [0x8899] | | + * |-----------------------------------+-----------------------------------| 8 + * | (8-bit) | (8-bit) | + * | Protocol [0x04] | REASON | b + * |-----------------------------------+-----------------------------------| y + * | (1) | (1) | (2) | (1) | (3) | (1) | (1) | (1) | (5) | t + * | FID_EN | X | FID | PRI_EN | PRI | KEEP | X | LEARN_DIS | X | e + * |-----------------------------------+-----------------------------------| s + * | (1) | (15-bit) | | + * | ALLOW | TX/RX | v + * |-----------------------------------+-----------------------------------|--- + * + * With the following field descriptions: + * + * field | description + * ------------+------------- + * Realtek | 0x8899: indicates that this is a proprietary Realtek tag; + * EtherType | note that Realtek uses the same EtherType for + * | other incompatible tag formats (e.g. tag_rtl4_a.c) + * Protocol | 0x04: indicates that this tag conforms to this format + * X | reserved + * ------------+------------- + * REASON | reason for forwarding packet to CPU + * | 0: packet was forwarded or flooded to CPU + * | 80: packet was trapped to CPU + * FID_EN | 1: packet has an FID + * | 0: no FID + * FID | FID of packet (if FID_EN=1) + * PRI_EN | 1: force priority of packet + * | 0: don't force priority + * PRI | priority of packet (if PRI_EN=1) + * KEEP | preserve packet VLAN tag format + * LEARN_DIS | don't learn the source MAC address of the packet + * ALLOW | 1: treat TX/RX field as an allowance port mask, meaning the + * | packet may only be forwarded to ports specified in the + * | mask + * | 0: no allowance port mask, TX/RX field is the forwarding + * | port mask + * TX/RX | TX (switch->CPU): port number the packet was received on + * | RX (CPU->switch): forwarding port mask (if ALLOW=0) + * | allowance port mask (if ALLOW=1) + * + * The tag can be positioned before Ethertype, using tag "rtl8_4": + * + * +--------+--------+------------+------+----- + * | MAC DA | MAC SA | 8 byte tag | Type | ... + * +--------+--------+------------+------+----- + * + * The tag can also appear between the end of the payload and before the CRC, + * using tag "rtl8_4t": + * + * +--------+--------+------+-----+---------+------------+-----+ + * | MAC DA | MAC SA | TYPE | ... | payload | 8-byte tag | CRC | + * +--------+--------+------+-----+---------+------------+-----+ + * + * The added bytes after the payload will break most checksums, either in + * software or hardware. To avoid this issue, if the checksum is still pending, + * this tagger checksums the packet in software before adding the tag. + * + */ + +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/etherdevice.h> + +#include "tag.h" + +/* Protocols supported: + * + * 0x04 = RTL8365MB DSA protocol + */ + +#define RTL8_4_NAME "rtl8_4" +#define RTL8_4T_NAME "rtl8_4t" + +#define RTL8_4_TAG_LEN 8 + +#define RTL8_4_PROTOCOL GENMASK(15, 8) +#define RTL8_4_PROTOCOL_RTL8365MB 0x04 +#define RTL8_4_REASON GENMASK(7, 0) +#define RTL8_4_REASON_FORWARD 0 +#define RTL8_4_REASON_TRAP 80 + +#define RTL8_4_LEARN_DIS BIT(5) + +#define RTL8_4_TX GENMASK(3, 0) +#define RTL8_4_RX GENMASK(10, 0) + +static void rtl8_4_write_tag(struct sk_buff *skb, struct net_device *dev, + void *tag) +{ + __be16 tag16[RTL8_4_TAG_LEN / 2]; + + /* Set Realtek EtherType */ + tag16[0] = htons(ETH_P_REALTEK); + + /* Set Protocol; zero REASON */ + tag16[1] = htons(FIELD_PREP(RTL8_4_PROTOCOL, RTL8_4_PROTOCOL_RTL8365MB)); + + /* Zero FID_EN, FID, PRI_EN, PRI, KEEP; set LEARN_DIS */ + tag16[2] = htons(FIELD_PREP(RTL8_4_LEARN_DIS, 1)); + + /* Zero ALLOW; set RX (CPU->switch) forwarding port mask */ + tag16[3] = htons(FIELD_PREP(RTL8_4_RX, dsa_xmit_port_mask(skb, dev))); + + memcpy(tag, tag16, RTL8_4_TAG_LEN); +} + +static struct sk_buff *rtl8_4_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + skb_push(skb, RTL8_4_TAG_LEN); + + dsa_alloc_etype_header(skb, RTL8_4_TAG_LEN); + + rtl8_4_write_tag(skb, dev, dsa_etype_header_pos_tx(skb)); + + return skb; +} + +static struct sk_buff *rtl8_4t_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Calculate the checksum here if not done yet as trailing tags will + * break either software or hardware based checksum + */ + if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) + return NULL; + + rtl8_4_write_tag(skb, dev, skb_put(skb, RTL8_4_TAG_LEN)); + + return skb; +} + +static int rtl8_4_read_tag(struct sk_buff *skb, struct net_device *dev, + void *tag) +{ + __be16 tag16[RTL8_4_TAG_LEN / 2]; + u16 etype; + u8 reason; + u8 proto; + u8 port; + + memcpy(tag16, tag, RTL8_4_TAG_LEN); + + /* Parse Realtek EtherType */ + etype = ntohs(tag16[0]); + if (unlikely(etype != ETH_P_REALTEK)) { + dev_warn_ratelimited(&dev->dev, + "non-realtek ethertype 0x%04x\n", etype); + return -EPROTO; + } + + /* Parse Protocol */ + proto = FIELD_GET(RTL8_4_PROTOCOL, ntohs(tag16[1])); + if (unlikely(proto != RTL8_4_PROTOCOL_RTL8365MB)) { + dev_warn_ratelimited(&dev->dev, + "unknown realtek protocol 0x%02x\n", + proto); + return -EPROTO; + } + + /* Parse REASON */ + reason = FIELD_GET(RTL8_4_REASON, ntohs(tag16[1])); + + /* Parse TX (switch->CPU) */ + port = FIELD_GET(RTL8_4_TX, ntohs(tag16[3])); + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) { + dev_warn_ratelimited(&dev->dev, + "could not find user for port %d\n", + port); + return -ENOENT; + } + + if (reason != RTL8_4_REASON_TRAP) + dsa_default_offload_fwd_mark(skb); + + return 0; +} + +static struct sk_buff *rtl8_4_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + if (unlikely(!pskb_may_pull(skb, RTL8_4_TAG_LEN))) + return NULL; + + if (unlikely(rtl8_4_read_tag(skb, dev, dsa_etype_header_pos_rx(skb)))) + return NULL; + + /* Remove tag and recalculate checksum */ + skb_pull_rcsum(skb, RTL8_4_TAG_LEN); + + dsa_strip_etype_header(skb, RTL8_4_TAG_LEN); + + return skb; +} + +static struct sk_buff *rtl8_4t_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + if (skb_linearize(skb)) + return NULL; + + if (unlikely(rtl8_4_read_tag(skb, dev, skb_tail_pointer(skb) - RTL8_4_TAG_LEN))) + return NULL; + + if (pskb_trim_rcsum(skb, skb->len - RTL8_4_TAG_LEN)) + return NULL; + + return skb; +} + +/* Ethertype version */ +static const struct dsa_device_ops rtl8_4_netdev_ops = { + .name = "rtl8_4", + .proto = DSA_TAG_PROTO_RTL8_4, + .xmit = rtl8_4_tag_xmit, + .rcv = rtl8_4_tag_rcv, + .needed_headroom = RTL8_4_TAG_LEN, +}; + +DSA_TAG_DRIVER(rtl8_4_netdev_ops); + +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4, RTL8_4_NAME); + +/* Tail version */ +static const struct dsa_device_ops rtl8_4t_netdev_ops = { + .name = "rtl8_4t", + .proto = DSA_TAG_PROTO_RTL8_4T, + .xmit = rtl8_4t_tag_xmit, + .rcv = rtl8_4t_tag_rcv, + .needed_tailroom = RTL8_4_TAG_LEN, +}; + +DSA_TAG_DRIVER(rtl8_4t_netdev_ops); + +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4T, RTL8_4T_NAME); + +static struct dsa_tag_driver *dsa_tag_drivers[] = { + &DSA_TAG_DRIVER_NAME(rtl8_4_netdev_ops), + &DSA_TAG_DRIVER_NAME(rtl8_4t_netdev_ops), +}; +module_dsa_tag_drivers(dsa_tag_drivers); + +MODULE_DESCRIPTION("DSA tag driver for Realtek 8 byte protocol 4 tags"); +MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c new file mode 100644 index 000000000000..10994b3470f6 --- /dev/null +++ b/net/dsa/tag_rzn1_a5psw.c @@ -0,0 +1,115 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 Schneider Electric + * + * Clément Léger <clement.leger@bootlin.com> + */ + +#include <linux/bitfield.h> +#include <linux/etherdevice.h> +#include <linux/if_ether.h> +#include <net/dsa.h> + +#include "tag.h" + +/* To define the outgoing port and to discover the incoming port a TAG is + * inserted after Src MAC : + * + * Dest MAC Src MAC TAG Type + * ...| 1 2 3 4 5 6 | 1 2 3 4 5 6 | 1 2 3 4 5 6 7 8 | 1 2 |... + * |<--------------->| + * + * See struct a5psw_tag for layout + */ + +#define A5PSW_NAME "a5psw" + +#define ETH_P_DSA_A5PSW 0xE001 +#define A5PSW_TAG_LEN 8 +#define A5PSW_CTRL_DATA_FORCE_FORWARD BIT(0) +/* This is both used for xmit tag and rcv tagging */ +#define A5PSW_CTRL_DATA_PORT GENMASK(3, 0) + +struct a5psw_tag { + __be16 ctrl_tag; + __be16 ctrl_data; + __be16 ctrl_data2_hi; + __be16 ctrl_data2_lo; +}; + +static struct sk_buff *a5psw_tag_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct a5psw_tag *ptag; + u32 data2_val; + + BUILD_BUG_ON(sizeof(*ptag) != A5PSW_TAG_LEN); + + /* The Ethernet switch we are interfaced with needs packets to be at + * least 60 bytes otherwise they will be discarded when they enter the + * switch port logic. + */ + if (__skb_put_padto(skb, ETH_ZLEN, false)) + return NULL; + + /* provide 'A5PSW_TAG_LEN' bytes additional space */ + skb_push(skb, A5PSW_TAG_LEN); + + /* make room between MACs and Ether-Type to insert tag */ + dsa_alloc_etype_header(skb, A5PSW_TAG_LEN); + + ptag = dsa_etype_header_pos_tx(skb); + + data2_val = FIELD_PREP(A5PSW_CTRL_DATA_PORT, dsa_xmit_port_mask(skb, dev)); + ptag->ctrl_tag = htons(ETH_P_DSA_A5PSW); + ptag->ctrl_data = htons(A5PSW_CTRL_DATA_FORCE_FORWARD); + ptag->ctrl_data2_lo = htons(data2_val); + ptag->ctrl_data2_hi = 0; + + return skb; +} + +static struct sk_buff *a5psw_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + struct a5psw_tag *tag; + int port; + + if (unlikely(!pskb_may_pull(skb, A5PSW_TAG_LEN))) { + dev_warn_ratelimited(&dev->dev, + "Dropping packet, cannot pull\n"); + return NULL; + } + + tag = dsa_etype_header_pos_rx(skb); + + if (tag->ctrl_tag != htons(ETH_P_DSA_A5PSW)) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid TAG marker\n"); + return NULL; + } + + port = FIELD_GET(A5PSW_CTRL_DATA_PORT, ntohs(tag->ctrl_data)); + + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) + return NULL; + + skb_pull_rcsum(skb, A5PSW_TAG_LEN); + dsa_strip_etype_header(skb, A5PSW_TAG_LEN); + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops a5psw_netdev_ops = { + .name = A5PSW_NAME, + .proto = DSA_TAG_PROTO_RZN1_A5PSW, + .xmit = a5psw_tag_xmit, + .rcv = a5psw_tag_rcv, + .needed_headroom = A5PSW_TAG_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for Renesas RZ/N1 A5PSW switch"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_A5PSW, A5PSW_NAME); +module_dsa_tag_driver(a5psw_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 9b4a4d719291..02adec693811 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -5,10 +5,77 @@ #include <linux/dsa/sja1105.h> #include <linux/dsa/8021q.h> #include <linux/packing.h> -#include "dsa_priv.h" + +#include "tag.h" +#include "tag_8021q.h" + +#define SJA1105_NAME "sja1105" +#define SJA1110_NAME "sja1110" + +/* Is this a TX or an RX header? */ +#define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) + +/* RX header */ +#define SJA1110_RX_HEADER_IS_METADATA BIT(14) +#define SJA1110_RX_HEADER_HOST_ONLY BIT(13) +#define SJA1110_RX_HEADER_HAS_TRAILER BIT(12) + +/* Trap-to-host format (no trailer present) */ +#define SJA1110_RX_HEADER_SRC_PORT(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_HEADER_SWITCH_ID(x) ((x) & GENMASK(3, 0)) + +/* Timestamp format (trailer present) */ +#define SJA1110_RX_HEADER_TRAILER_POS(x) ((x) & GENMASK(11, 0)) + +#define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) + +/* Meta frame format (for 2-step TX timestamps) */ +#define SJA1110_RX_HEADER_N_TS(x) (((x) & GENMASK(8, 4)) >> 4) + +/* TX header */ +#define SJA1110_TX_HEADER_UPDATE_TC BIT(14) +#define SJA1110_TX_HEADER_TAKE_TS BIT(13) +#define SJA1110_TX_HEADER_TAKE_TS_CASC BIT(12) +#define SJA1110_TX_HEADER_HAS_TRAILER BIT(11) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */ +#define SJA1110_TX_HEADER_PRIO(x) (((x) << 7) & GENMASK(10, 7)) +#define SJA1110_TX_HEADER_TSTAMP_ID(x) ((x) & GENMASK(7, 0)) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */ +#define SJA1110_TX_HEADER_TRAILER_POS(x) ((x) & GENMASK(10, 0)) + +#define SJA1110_TX_TRAILER_TSTAMP_ID(x) (((x) << 24) & GENMASK(31, 24)) +#define SJA1110_TX_TRAILER_PRIO(x) (((x) << 21) & GENMASK(23, 21)) +#define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) +#define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) + +#define SJA1110_META_TSTAMP_SIZE 10 + +#define SJA1110_HEADER_LEN 4 +#define SJA1110_RX_TRAILER_LEN 13 +#define SJA1110_TX_TRAILER_LEN 4 +#define SJA1110_MAX_PADDING_LEN 15 + +struct sja1105_tagger_private { + struct sja1105_tagger_data data; /* Must be first */ + /* Protects concurrent access to the meta state machine + * from taggers running on multiple ports on SMP systems + */ + spinlock_t meta_lock; + struct sk_buff *stampable_skb; + struct kthread_worker *xmit_worker; +}; + +static struct sja1105_tagger_private * +sja1105_tagger_private(struct dsa_switch *ds) +{ + return ds->tagger_data; +} /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ -static inline bool sja1105_is_link_local(const struct sk_buff *skb) +static bool sja1105_is_link_local(const struct sk_buff *skb) { const struct ethhdr *hdr = eth_hdr(skb); u64 dmac = ether_addr_to_u64(hdr->h_dest); @@ -48,13 +115,13 @@ static void sja1105_meta_unpack(const struct sk_buff *skb, * a unified unpacking command for both device series. */ packing(buf, &meta->tstamp, 31, 0, 4, UNPACK, 0); - packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); - packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 4, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 5, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0); packing(buf + 7, &meta->switch_id, 7, 0, 1, UNPACK, 0); } -static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) +static bool sja1105_is_meta_frame(const struct sk_buff *skb) { const struct ethhdr *hdr = eth_hdr(skb); u64 smac = ether_addr_to_u64(hdr->h_source); @@ -69,70 +136,213 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) return true; } -static bool sja1105_can_use_vlan_as_tags(const struct sk_buff *skb) +/* Calls sja1105_port_deferred_xmit in sja1105_main.c */ +static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, + struct sk_buff *skb) { - struct vlan_ethhdr *hdr = vlan_eth_hdr(skb); + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(dp->ds); + struct sja1105_tagger_private *priv = sja1105_tagger_private(dp->ds); + void (*xmit_work_fn)(struct kthread_work *work); + struct sja1105_deferred_xmit_work *xmit_work; + struct kthread_worker *xmit_worker; - if (hdr->h_vlan_proto == htons(ETH_P_SJA1105)) - return true; + xmit_work_fn = tagger_data->xmit_work_fn; + xmit_worker = priv->xmit_worker; - if (hdr->h_vlan_proto != htons(ETH_P_8021Q)) - return false; + if (!xmit_work_fn || !xmit_worker) + return NULL; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + kthread_init_work(&xmit_work->work, xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_user_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); - return vid_is_dsa_8021q(ntohs(hdr->h_vlan_TCI) & VLAN_VID_MASK); + return NULL; } -/* This is the first time the tagger sees the frame on RX. - * Figure out if we can decode it. +/* Send VLAN tags with a TPID that blends in with whatever VLAN protocol a + * bridge spanning ports of this switch might have. */ -static bool sja1105_filter(const struct sk_buff *skb, struct net_device *dev) +static u16 sja1105_xmit_tpid(struct dsa_port *dp) { - if (sja1105_can_use_vlan_as_tags(skb)) - return true; - if (sja1105_is_link_local(skb)) - return true; - if (sja1105_is_meta_frame(skb)) - return true; - return false; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + u16 proto; + + /* Since VLAN awareness is global, then if this port is VLAN-unaware, + * all ports are. Use the VLAN-unaware TPID used for tag_8021q. + */ + if (!dsa_port_is_vlan_filtering(dp)) + return ETH_P_SJA1105; + + /* Port is VLAN-aware, so there is a bridge somewhere (a single one, + * we're sure about that). It may not be on this port though, so we + * need to find it. + */ + dsa_switch_for_each_port(other_dp, ds) { + struct net_device *br = dsa_port_bridge_dev_get(other_dp); + + if (!br) + continue; + + /* Error is returned only if CONFIG_BRIDGE_VLAN_FILTERING, + * which seems pointless to handle, as our port cannot become + * VLAN-aware in that case. + */ + br_vlan_get_proto(br, &proto); + + return proto; + } + + WARN_ONCE(1, "Port is VLAN-aware but cannot find associated bridge!\n"); + + return ETH_P_SJA1105; } -/* Calls sja1105_port_deferred_xmit in sja1105_main.c */ -static struct sk_buff *sja1105_defer_xmit(struct sja1105_port *sp, - struct sk_buff *skb) +static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, + struct net_device *netdev) { - /* Increase refcount so the kfree_skb in dsa_slave_xmit - * won't really free the packet. + struct dsa_port *dp = dsa_user_to_port(netdev); + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u16 tx_vid; + + /* If the port is under a VLAN-aware bridge, just slide the + * VLAN-tagged packet into the FDB and hope for the best. + * This works because we support a single VLAN-aware bridge + * across the entire dst, and its VLANs cannot be shared with + * any standalone port. */ - skb_queue_tail(&sp->xmit_queue, skb_get(skb)); - kthread_queue_work(sp->xmit_worker, &sp->xmit_work); + if (br_vlan_enabled(br)) + return skb; - return NULL; + /* If the port is under a VLAN-unaware bridge, use an imprecise + * TX VLAN that targets the bridge's entire broadcast domain, + * instead of just the specific port. + */ + tx_vid = dsa_tag_8021q_bridge_vid(bridge_num); + + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), tx_vid); } -static u16 sja1105_xmit_tpid(struct sja1105_port *sp) +/* Transform untagged control packets into pvid-tagged control packets so that + * all packets sent by this tagger are VLAN-tagged and we can configure the + * switch to drop untagged packets coming from the DSA conduit. + */ +static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, + struct sk_buff *skb, u8 pcp) { - return sp->xmit_tpid; + __be16 xmit_tpid = htons(sja1105_xmit_tpid(dp)); + struct vlan_ethhdr *hdr; + + /* If VLAN tag is in hwaccel area, move it to the payload + * to deal with both cases uniformly and to ensure that + * the VLANs are added in the right order. + */ + if (unlikely(skb_vlan_tag_present(skb))) { + skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + return NULL; + } + + hdr = skb_vlan_eth_hdr(skb); + + /* If skb is already VLAN-tagged, leave that VLAN ID in place */ + if (hdr->h_vlan_proto == xmit_tpid) + return skb; + + return vlan_insert_tag(skb, xmit_tpid, (pcp << VLAN_PRIO_SHIFT) | + SJA1105_DEFAULT_VLAN); } static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); + + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); /* Transmitting management traffic does not rely upon switch tagging, * but instead SPI-installed management routes. Part 2 of this * is the .port_deferred_xmit driver callback. */ - if (unlikely(sja1105_is_link_local(skb))) - return sja1105_defer_xmit(dp->priv, skb); + if (unlikely(sja1105_is_link_local(skb))) { + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; - return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + return sja1105_defer_xmit(dp, skb); + } + + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } +static struct sk_buff *sja1110_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct dsa_port *dp = dsa_user_to_port(netdev); + u16 queue_mapping = skb_get_queue_mapping(skb); + u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); + __be32 *tx_trailer; + __be16 *tx_header; + int trailer_pos; + + if (skb->offload_fwd_mark) + return sja1105_imprecise_xmit(skb, netdev); + + /* Transmitting control packets is done using in-band control + * extensions, while data packets are transmitted using + * tag_8021q TX VLANs. + */ + if (likely(!sja1105_is_link_local(skb))) + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp), + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + + skb = sja1105_pvid_tag_control_pkt(dp, skb, pcp); + if (!skb) + return NULL; + + skb_push(skb, SJA1110_HEADER_LEN); + + dsa_alloc_etype_header(skb, SJA1110_HEADER_LEN); + + trailer_pos = skb->len; + + tx_header = dsa_etype_header_pos_tx(skb); + tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); + + tx_header[0] = htons(ETH_P_SJA1110); + tx_header[1] = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | + SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | + SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + if (clone) { + u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; + + tx_header[1] |= htons(SJA1110_TX_HEADER_TAKE_TS); + *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); + } + + return skb; +} + static void sja1105_transfer_meta(struct sk_buff *skb, const struct sja1105_meta *meta) { @@ -140,7 +350,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb, hdr->h_dest[3] = meta->dmac_byte_3; hdr->h_dest[4] = meta->dmac_byte_4; - SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp; + SJA1105_SKB_CB(skb)->tstamp = meta->tstamp; } /* This is a simple state machine which follows the hardware mechanism of @@ -169,37 +379,33 @@ static struct sk_buff bool is_link_local, bool is_meta) { - struct sja1105_port *sp; - struct dsa_port *dp; - - dp = dsa_slave_to_port(skb->dev); - sp = dp->priv; - /* Step 1: A timestampable frame was received. * Buffer it until we get its meta frame. */ if (is_link_local) { - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) - /* Do normal processing. */ - return skb; + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct sja1105_tagger_private *priv; + struct dsa_switch *ds = dp->ds; + + priv = sja1105_tagger_private(ds); - spin_lock(&sp->data->meta_lock); + spin_lock(&priv->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? */ - if (sp->data->stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + if (priv->stampable_skb) { + dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " - "in the DSA master multicast filter?\n", + "in the DSA conduit multicast filter?\n", SJA1105_META_DMAC); - kfree_skb(sp->data->stampable_skb); + kfree_skb(priv->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv * from freeing the skb. */ - sp->data->stampable_skb = skb_get(skb); - spin_unlock(&sp->data->meta_lock); + priv->stampable_skb = skb_get(skb); + spin_unlock(&priv->meta_lock); /* Tell DSA we got nothing */ return NULL; @@ -211,33 +417,32 @@ static struct sk_buff * frame, which serves no further purpose). */ } else if (is_meta) { + struct dsa_port *dp = dsa_user_to_port(skb->dev); + struct sja1105_tagger_private *priv; + struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; - /* Drop the meta frame if we're not in the right state - * to process it. - */ - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) - return NULL; + priv = sja1105_tagger_private(ds); - spin_lock(&sp->data->meta_lock); + spin_lock(&priv->meta_lock); - stampable_skb = sp->data->stampable_skb; - sp->data->stampable_skb = NULL; + stampable_skb = priv->stampable_skb; + priv->stampable_skb = NULL; /* Was this a meta frame instead of the link-local * that we were expecting? */ if (!stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Unexpected meta frame\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } if (stampable_skb->dev != skb->dev) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Meta frame on wrong port\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } @@ -248,101 +453,310 @@ static struct sk_buff skb = stampable_skb; sja1105_transfer_meta(skb, meta); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&priv->meta_lock); } return skb; } -static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) +static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; - u16 vid = sp->subvlan_map[subvlan]; - u16 vlan_tci; + u16 tpid = ntohs(eth_hdr(skb)->h_proto); - if (vid == VLAN_N_VID) - return; + return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb); +} - vlan_tci = (skb->priority << VLAN_PRIO_SHIFT) | vid; - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); +static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) +{ + return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; } static struct sk_buff *sja1105_rcv(struct sk_buff *skb, - struct net_device *netdev, - struct packet_type *pt) + struct net_device *netdev) { + int source_port = -1, switch_id = -1, vbid = -1, vid = -1; struct sja1105_meta meta = {0}; - int source_port, switch_id; struct ethhdr *hdr; - u16 tpid, vid, tci; bool is_link_local; - u16 subvlan = 0; - bool is_tagged; bool is_meta; hdr = eth_hdr(skb); - tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); - skb->offload_fwd_mark = 1; - - if (is_tagged) { - /* Normal traffic path. */ - skb_push_rcsum(skb, ETH_HLEN); - __skb_vlan_pop(skb, &tci); - skb_pull_rcsum(skb, ETH_HLEN); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - - vid = tci & VLAN_VID_MASK; - source_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - subvlan = dsa_8021q_rx_subvlan(vid); - } else if (is_link_local) { + if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of * the incl_srcpt options. */ source_port = hdr->h_dest[3]; switch_id = hdr->h_dest[4]; - /* Clear the DMAC bytes that were mangled by the switch */ - hdr->h_dest[3] = 0; - hdr->h_dest[4] = 0; } else if (is_meta) { sja1105_meta_unpack(skb, &meta); source_port = meta.source_port; switch_id = meta.switch_id; - } else { - return NULL; } - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + /* Normal data plane traffic and link-local frames are tagged with + * a tag_8021q VLAN which we have to strip + */ + if (sja1105_skb_has_tag_8021q(skb)) + dsa_8021q_rcv(skb, &source_port, &switch_id, &vbid, &vid); + else if (source_port == -1 && switch_id == -1) + /* Packets with no source information have no chance of + * getting accepted, drop them straight away. + */ + return NULL; + + skb->dev = dsa_tag_8021q_find_user(netdev, source_port, switch_id, + vid, vbid); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; } - if (subvlan) - sja1105_decode_subvlan(skb, subvlan); + if (!is_link_local) + dsa_default_offload_fwd_mark(skb); return sja1105_rcv_meta_state_machine(skb, &meta, is_link_local, is_meta); } +static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) +{ + u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; + int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct sja1105_tagger_data *tagger_data; + struct net_device *conduit = skb->dev; + struct dsa_port *cpu_dp; + struct dsa_switch *ds; + int i; + + cpu_dp = conduit->dsa_ptr; + ds = dsa_switch_find(cpu_dp->dst->index, switch_id); + if (!ds) { + net_err_ratelimited("%s: cannot find switch id %d\n", + conduit->name, switch_id); + return NULL; + } + + tagger_data = sja1105_tagger_data(ds); + if (!tagger_data->meta_tstamp_handler) + return NULL; + + for (i = 0; i <= n_ts; i++) { + u8 ts_id, source_port, dir; + u64 tstamp; + + ts_id = buf[0]; + source_port = (buf[1] & GENMASK(7, 4)) >> 4; + dir = (buf[1] & BIT(3)) >> 3; + tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); + + tagger_data->meta_tstamp_handler(ds, source_port, ts_id, dir, + tstamp); + + buf += SJA1110_META_TSTAMP_SIZE; + } + + /* Discard the meta frame, we've consumed the timestamps it contained */ + return NULL; +} + +static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, + int *source_port, + int *switch_id, + bool *host_only) +{ + u16 rx_header; + + if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN))) + return NULL; + + /* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly + * what we need because the caller has checked the EtherType (which is + * located 2 bytes back) and we just need a pointer to the header that + * comes afterwards. + */ + rx_header = ntohs(*(__be16 *)skb->data); + + if (rx_header & SJA1110_RX_HEADER_HOST_ONLY) + *host_only = true; + + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) + return sja1110_rcv_meta(skb, rx_header); + + /* Timestamp frame, we have a trailer */ + if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { + int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); + u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN; + u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp; + u8 last_byte = rx_trailer[12]; + + /* The timestamp is unaligned, so we need to use packing() + * to get it + */ + packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0); + + *source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte); + *switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte); + + /* skb->len counts from skb->data, while start_of_padding + * counts from the destination MAC address. Right now skb->data + * is still as set by the DSA conduit, so to trim away the + * padding and trailer we need to account for the fact that + * skb->data points to skb_mac_header(skb) + ETH_HLEN. + */ + if (pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN)) + return NULL; + /* Trap-to-host frame, no timestamp trailer */ + } else { + *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); + *switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + } + + /* Advance skb->data past the DSA header */ + skb_pull_rcsum(skb, SJA1110_HEADER_LEN); + + dsa_strip_etype_header(skb, SJA1110_HEADER_LEN); + + /* With skb->data in its final place, update the MAC header + * so that eth_hdr() continues to works properly. + */ + skb_set_mac_header(skb, -ETH_HLEN); + + return skb; +} + +static struct sk_buff *sja1110_rcv(struct sk_buff *skb, + struct net_device *netdev) +{ + int source_port = -1, switch_id = -1, vbid = -1, vid = -1; + bool host_only = false; + + if (sja1110_skb_has_inband_control_extension(skb)) { + skb = sja1110_rcv_inband_control_extension(skb, &source_port, + &switch_id, + &host_only); + if (!skb) + return NULL; + } + + /* Packets with in-band control extensions might still have RX VLANs */ + if (likely(sja1105_skb_has_tag_8021q(skb))) + dsa_8021q_rcv(skb, &source_port, &switch_id, &vbid, &vid); + + skb->dev = dsa_tag_8021q_find_user(netdev, source_port, switch_id, + vid, vbid); + + if (!skb->dev) { + netdev_warn(netdev, "Couldn't decode source port\n"); + return NULL; + } + + if (!host_only) + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +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 void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* Management frames have 2 DSA tags on RX, so the needed_headroom we + * declared is fine for the generic dissector adjustment procedure. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_tag_generic_flow_dissect(skb, proto, offset); + + /* For the rest, there is a single DSA tag, the tag_8021q one */ + *offset = VLAN_HLEN; + *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; +} + +static void sja1105_disconnect(struct dsa_switch *ds) +{ + struct sja1105_tagger_private *priv = ds->tagger_data; + + kthread_destroy_worker(priv->xmit_worker); + kfree(priv); + ds->tagger_data = NULL; +} + +static int sja1105_connect(struct dsa_switch *ds) +{ + struct sja1105_tagger_private *priv; + struct kthread_worker *xmit_worker; + int err; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + spin_lock_init(&priv->meta_lock); + + xmit_worker = kthread_run_worker(0, "dsa%d:%d_xmit", + ds->dst->index, ds->index); + if (IS_ERR(xmit_worker)) { + err = PTR_ERR(xmit_worker); + kfree(priv); + return err; + } + + priv->xmit_worker = xmit_worker; + ds->tagger_data = priv; + + return 0; +} + static const struct dsa_device_ops sja1105_netdev_ops = { - .name = "sja1105", + .name = SJA1105_NAME, .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, - .filter = sja1105_filter, - .overhead = VLAN_HLEN, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, + .needed_headroom = VLAN_HLEN, + .flow_dissect = sja1105_flow_dissect, + .promisc_on_conduit = true, }; -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); +DSA_TAG_DRIVER(sja1105_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105, SJA1105_NAME); + +static const struct dsa_device_ops sja1110_netdev_ops = { + .name = SJA1110_NAME, + .proto = DSA_TAG_PROTO_SJA1110, + .xmit = sja1110_xmit, + .rcv = sja1110_rcv, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, + .flow_dissect = sja1110_flow_dissect, + .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, + .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, +}; -module_dsa_tag_driver(sja1105_netdev_ops); +DSA_TAG_DRIVER(sja1110_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110, SJA1110_NAME); + +static struct dsa_tag_driver *sja1105_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), + &DSA_TAG_DRIVER_NAME(sja1110_netdev_ops), +}; + +module_dsa_tag_drivers(sja1105_tag_driver_array); + +MODULE_DESCRIPTION("DSA tag driver for NXP SJA1105 switches"); +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 4f8ab62f0208..4dce24cfe6a7 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -8,51 +8,24 @@ #include <linux/list.h> #include <linux/slab.h> -#include "dsa_priv.h" +#include "tag.h" + +#define TRAILER_NAME "trailer" 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[1] = dsa_xmit_port_mask(skb, dev); trailer[2] = 0x10; trailer[3] = 0x00; - return nskb; + return skb; } -static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt) +static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev) { u8 *trailer; int source_port; @@ -67,7 +40,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, source_port = trailer[1] & 7; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; @@ -78,14 +51,15 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, } static const struct dsa_device_ops trailer_netdev_ops = { - .name = "trailer", + .name = TRAILER_NAME, .proto = DSA_TAG_PROTO_TRAILER, .xmit = trailer_xmit, .rcv = trailer_rcv, - .overhead = 4, + .needed_tailroom = 4, }; +MODULE_DESCRIPTION("DSA tag driver for switches using a trailer tag"); MODULE_LICENSE("GPL"); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_TRAILER, TRAILER_NAME); module_dsa_tag_driver(trailer_netdev_ops); diff --git a/net/dsa/tag_vsc73xx_8021q.c b/net/dsa/tag_vsc73xx_8021q.c new file mode 100644 index 000000000000..af121a9aff7f --- /dev/null +++ b/net/dsa/tag_vsc73xx_8021q.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* Copyright (C) 2024 Pawel Dembicki <paweldembicki@gmail.com> + */ +#include <linux/dsa/8021q.h> + +#include "tag.h" +#include "tag_8021q.h" + +#define VSC73XX_8021Q_NAME "vsc73xx-8021q" + +static struct sk_buff * +vsc73xx_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct dsa_port *dp = dsa_user_to_port(netdev); + u16 queue_mapping = skb_get_queue_mapping(skb); + u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); + u8 pcp; + + if (skb->offload_fwd_mark) { + unsigned int bridge_num = dsa_port_bridge_num_get(dp); + struct net_device *br = dsa_port_bridge_dev_get(dp); + + if (br_vlan_enabled(br)) + return skb; + + tx_vid = dsa_tag_8021q_bridge_vid(bridge_num); + } + + pcp = netdev_txq_to_tc(netdev, queue_mapping); + + return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); +} + +static struct sk_buff * +vsc73xx_rcv(struct sk_buff *skb, struct net_device *netdev) +{ + int src_port = -1, switch_id = -1, vbid = -1, vid = -1; + + dsa_8021q_rcv(skb, &src_port, &switch_id, &vbid, &vid); + + skb->dev = dsa_tag_8021q_find_user(netdev, src_port, switch_id, + vid, vbid); + if (!skb->dev) { + dev_warn_ratelimited(&netdev->dev, + "Couldn't decode source port\n"); + return NULL; + } + + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops vsc73xx_8021q_netdev_ops = { + .name = VSC73XX_8021Q_NAME, + .proto = DSA_TAG_PROTO_VSC73XX_8021Q, + .xmit = vsc73xx_xmit, + .rcv = vsc73xx_rcv, + .needed_headroom = VLAN_HLEN, + .promisc_on_conduit = true, +}; + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("DSA tag driver for VSC73XX family of switches, using VLAN"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_VSC73XX_8021Q, VSC73XX_8021Q_NAME); + +module_dsa_tag_driver(vsc73xx_8021q_netdev_ops); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c new file mode 100644 index 000000000000..a05219f702c6 --- /dev/null +++ b/net/dsa/tag_xrs700x.c @@ -0,0 +1,61 @@ +// 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 "tag.h" + +#define XRS700X_NAME "xrs700x" + +static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) +{ + u8 *trailer; + + trailer = skb_put(skb, 1); + trailer[0] = dsa_xmit_port_mask(skb, dev); + + return skb; +} + +static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev) +{ + 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_conduit_find_user(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. */ + dsa_default_offload_fwd_mark(skb); + + return skb; +} + +static const struct dsa_device_ops xrs700x_netdev_ops = { + .name = XRS700X_NAME, + .proto = DSA_TAG_PROTO_XRS700X, + .xmit = xrs700x_xmit, + .rcv = xrs700x_rcv, + .needed_tailroom = 1, +}; + +MODULE_DESCRIPTION("DSA tag driver for XRS700x switches"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_XRS700X, XRS700X_NAME); + +module_dsa_tag_driver(xrs700x_netdev_ops); diff --git a/net/dsa/tag_yt921x.c b/net/dsa/tag_yt921x.c new file mode 100644 index 000000000000..6bbfd42dc5df --- /dev/null +++ b/net/dsa/tag_yt921x.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Motorcomm YT921x Switch Extended CPU Port Tagging + * + * Copyright (c) 2025 David Yang <mmyangfl@gmail.com> + * + * +----+----+-------+-----+----+--------- + * | DA | SA | TagET | Tag | ET | Payload ... + * +----+----+-------+-----+----+--------- + * 6 6 2 6 2 N + * + * Tag Ethertype: CPU_TAG_TPID_TPID (default: ETH_P_YT921X = 0x9988) + * * Hardcoded for the moment, but still configurable. Discuss it if there + * are conflicts somewhere and/or you want to change it for some reason. + * Tag: + * 2: VLAN Tag + * 2: Rx Port + * 15b: Rx Port Valid + * 14b-11b: Rx Port + * 10b-0b: Cmd? + * 2: Tx Port(s) + * 15b: Tx Port(s) Valid + * 10b-0b: Tx Port(s) Mask + */ + +#include <linux/etherdevice.h> + +#include "tag.h" + +#define YT921X_TAG_NAME "yt921x" + +#define YT921X_TAG_LEN 8 + +#define YT921X_TAG_PORT_EN BIT(15) +#define YT921X_TAG_RX_PORT_M GENMASK(14, 11) +#define YT921X_TAG_RX_CMD_M GENMASK(10, 0) +#define YT921X_TAG_RX_CMD(x) FIELD_PREP(YT921X_TAG_RX_CMD_M, (x)) +#define YT921X_TAG_RX_CMD_FORWARDED 0x80 +#define YT921X_TAG_RX_CMD_UNK_UCAST 0xb2 +#define YT921X_TAG_RX_CMD_UNK_MCAST 0xb4 +#define YT921X_TAG_TX_PORTS GENMASK(10, 0) + +static struct sk_buff * +yt921x_tag_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + __be16 *tag; + u16 tx; + + skb_push(skb, YT921X_TAG_LEN); + dsa_alloc_etype_header(skb, YT921X_TAG_LEN); + + tag = dsa_etype_header_pos_tx(skb); + + tag[0] = htons(ETH_P_YT921X); + /* VLAN tag unrelated when TX */ + tag[1] = 0; + tag[2] = 0; + tx = FIELD_PREP(YT921X_TAG_TX_PORTS, dsa_xmit_port_mask(skb, netdev)) | + YT921X_TAG_PORT_EN; + tag[3] = htons(tx); + + return skb; +} + +static struct sk_buff * +yt921x_tag_rcv(struct sk_buff *skb, struct net_device *netdev) +{ + unsigned int port; + __be16 *tag; + u16 cmd; + u16 rx; + + if (unlikely(!pskb_may_pull(skb, YT921X_TAG_LEN))) + return NULL; + + tag = dsa_etype_header_pos_rx(skb); + + if (unlikely(tag[0] != htons(ETH_P_YT921X))) { + dev_warn_ratelimited(&netdev->dev, + "Unexpected EtherType 0x%04x\n", + ntohs(tag[0])); + return NULL; + } + + /* Locate which port this is coming from */ + rx = ntohs(tag[2]); + if (unlikely((rx & YT921X_TAG_PORT_EN) == 0)) { + dev_warn_ratelimited(&netdev->dev, + "Unexpected rx tag 0x%04x\n", rx); + return NULL; + } + + port = FIELD_GET(YT921X_TAG_RX_PORT_M, rx); + skb->dev = dsa_conduit_find_user(netdev, 0, port); + if (unlikely(!skb->dev)) { + dev_warn_ratelimited(&netdev->dev, + "Couldn't decode source port %u\n", port); + return NULL; + } + + cmd = FIELD_GET(YT921X_TAG_RX_CMD_M, rx); + switch (cmd) { + case YT921X_TAG_RX_CMD_FORWARDED: + /* Already forwarded by hardware */ + dsa_default_offload_fwd_mark(skb); + break; + case YT921X_TAG_RX_CMD_UNK_UCAST: + case YT921X_TAG_RX_CMD_UNK_MCAST: + /* NOTE: hardware doesn't distinguish between TRAP (copy to CPU + * only) and COPY (forward and copy to CPU). In order to perform + * a soft switch, NEVER use COPY action in the switch driver. + */ + break; + default: + dev_warn_ratelimited(&netdev->dev, + "Unexpected rx cmd 0x%02x\n", cmd); + break; + } + + /* Remove YT921x tag and update checksum */ + skb_pull_rcsum(skb, YT921X_TAG_LEN); + dsa_strip_etype_header(skb, YT921X_TAG_LEN); + + return skb; +} + +static const struct dsa_device_ops yt921x_netdev_ops = { + .name = YT921X_TAG_NAME, + .proto = DSA_TAG_PROTO_YT921X, + .xmit = yt921x_tag_xmit, + .rcv = yt921x_tag_rcv, + .needed_headroom = YT921X_TAG_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for Motorcomm YT921x switches"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_YT921X, YT921X_TAG_NAME); + +module_dsa_tag_driver(yt921x_netdev_ops); diff --git a/net/dsa/trace.c b/net/dsa/trace.c new file mode 100644 index 000000000000..1b107165d331 --- /dev/null +++ b/net/dsa/trace.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright 2022-2023 NXP + */ + +#define CREATE_TRACE_POINTS +#include "trace.h" + +void dsa_db_print(const struct dsa_db *db, char buf[DSA_DB_BUFSIZ]) +{ + switch (db->type) { + case DSA_DB_PORT: + sprintf(buf, "port %s", db->dp->name); + break; + case DSA_DB_LAG: + sprintf(buf, "lag %s id %d", db->lag.dev->name, db->lag.id); + break; + case DSA_DB_BRIDGE: + sprintf(buf, "bridge %s num %d", db->bridge.dev->name, + db->bridge.num); + break; + default: + sprintf(buf, "unknown"); + break; + } +} + +const char *dsa_port_kind(const struct dsa_port *dp) +{ + switch (dp->type) { + case DSA_PORT_TYPE_USER: + return "user"; + case DSA_PORT_TYPE_CPU: + return "cpu"; + case DSA_PORT_TYPE_DSA: + return "dsa"; + default: + return "unused"; + } +} diff --git a/net/dsa/trace.h b/net/dsa/trace.h new file mode 100644 index 000000000000..83f3e5f78491 --- /dev/null +++ b/net/dsa/trace.h @@ -0,0 +1,447 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright 2022-2023 NXP + */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM dsa + +#if !defined(_NET_DSA_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _NET_DSA_TRACE_H + +#include <net/dsa.h> +#include <net/switchdev.h> +#include <linux/etherdevice.h> +#include <linux/if_bridge.h> +#include <linux/refcount.h> +#include <linux/tracepoint.h> + +/* Enough to fit "bridge %s num %d" where num has 3 digits */ +#define DSA_DB_BUFSIZ (IFNAMSIZ + 16) + +void dsa_db_print(const struct dsa_db *db, char buf[DSA_DB_BUFSIZ]); +const char *dsa_port_kind(const struct dsa_port *dp); + +DECLARE_EVENT_CLASS(dsa_port_addr_op_hw, + + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, u16 vid, + const struct dsa_db *db, int err), + + TP_ARGS(dp, addr, vid, db, err), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(int, err) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->err = err; + ), + + TP_printk("%s %s port %d addr %pM vid %u db \"%s\" err %d", + __get_str(dev), __get_str(kind), __entry->port, __entry->addr, + __entry->vid, __entry->db_buf, __entry->err) +); + +/* Add unicast/multicast address to hardware, either on user ports + * (where no refcounting is kept), or on shared ports when the entry + * is first seen and its refcount is 1. + */ +DEFINE_EVENT(dsa_port_addr_op_hw, dsa_fdb_add_hw, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + TP_ARGS(dp, addr, vid, db, err)); + +DEFINE_EVENT(dsa_port_addr_op_hw, dsa_mdb_add_hw, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + TP_ARGS(dp, addr, vid, db, err)); + +/* Delete unicast/multicast address from hardware, either on user ports or + * when the refcount on shared ports reaches 0 + */ +DEFINE_EVENT(dsa_port_addr_op_hw, dsa_fdb_del_hw, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + TP_ARGS(dp, addr, vid, db, err)); + +DEFINE_EVENT(dsa_port_addr_op_hw, dsa_mdb_del_hw, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + TP_ARGS(dp, addr, vid, db, err)); + +DECLARE_EVENT_CLASS(dsa_port_addr_op_refcount, + + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, u16 vid, + const struct dsa_db *db, const refcount_t *refcount), + + TP_ARGS(dp, addr, vid, db, refcount), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->refcount = refcount_read(refcount); + ), + + TP_printk("%s %s port %d addr %pM vid %u db \"%s\" refcount %u", + __get_str(dev), __get_str(kind), __entry->port, __entry->addr, + __entry->vid, __entry->db_buf, __entry->refcount) +); + +/* Bump the refcount of an existing unicast/multicast address on shared ports */ +DEFINE_EVENT(dsa_port_addr_op_refcount, dsa_fdb_add_bump, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, + const refcount_t *refcount), + TP_ARGS(dp, addr, vid, db, refcount)); + +DEFINE_EVENT(dsa_port_addr_op_refcount, dsa_mdb_add_bump, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, + const refcount_t *refcount), + TP_ARGS(dp, addr, vid, db, refcount)); + +/* Drop the refcount of a multicast address that we still keep on + * shared ports + */ +DEFINE_EVENT(dsa_port_addr_op_refcount, dsa_fdb_del_drop, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, + const refcount_t *refcount), + TP_ARGS(dp, addr, vid, db, refcount)); + +DEFINE_EVENT(dsa_port_addr_op_refcount, dsa_mdb_del_drop, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db, + const refcount_t *refcount), + TP_ARGS(dp, addr, vid, db, refcount)); + +DECLARE_EVENT_CLASS(dsa_port_addr_del_not_found, + + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, u16 vid, + const struct dsa_db *db), + + TP_ARGS(dp, addr, vid, db), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + ), + + TP_printk("%s %s port %d addr %pM vid %u db \"%s\"", + __get_str(dev), __get_str(kind), __entry->port, + __entry->addr, __entry->vid, __entry->db_buf) +); + +/* Attempt to delete a unicast/multicast address on shared ports for which + * the delete operation was called more times than the addition + */ +DEFINE_EVENT(dsa_port_addr_del_not_found, dsa_fdb_del_not_found, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db), + TP_ARGS(dp, addr, vid, db)); + +DEFINE_EVENT(dsa_port_addr_del_not_found, dsa_mdb_del_not_found, + TP_PROTO(const struct dsa_port *dp, const unsigned char *addr, + u16 vid, const struct dsa_db *db), + TP_ARGS(dp, addr, vid, db)); + +TRACE_EVENT(dsa_lag_fdb_add_hw, + + TP_PROTO(const struct net_device *lag_dev, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + + TP_ARGS(lag_dev, addr, vid, db, err), + + TP_STRUCT__entry( + __string(dev, lag_dev->name) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(int, err) + ), + + TP_fast_assign( + __assign_str(dev); + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->err = err; + ), + + TP_printk("%s addr %pM vid %u db \"%s\" err %d", + __get_str(dev), __entry->addr, __entry->vid, + __entry->db_buf, __entry->err) +); + +TRACE_EVENT(dsa_lag_fdb_add_bump, + + TP_PROTO(const struct net_device *lag_dev, const unsigned char *addr, + u16 vid, const struct dsa_db *db, const refcount_t *refcount), + + TP_ARGS(lag_dev, addr, vid, db, refcount), + + TP_STRUCT__entry( + __string(dev, lag_dev->name) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __assign_str(dev); + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->refcount = refcount_read(refcount); + ), + + TP_printk("%s addr %pM vid %u db \"%s\" refcount %u", + __get_str(dev), __entry->addr, __entry->vid, + __entry->db_buf, __entry->refcount) +); + +TRACE_EVENT(dsa_lag_fdb_del_hw, + + TP_PROTO(const struct net_device *lag_dev, const unsigned char *addr, + u16 vid, const struct dsa_db *db, int err), + + TP_ARGS(lag_dev, addr, vid, db, err), + + TP_STRUCT__entry( + __string(dev, lag_dev->name) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(int, err) + ), + + TP_fast_assign( + __assign_str(dev); + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->err = err; + ), + + TP_printk("%s addr %pM vid %u db \"%s\" err %d", + __get_str(dev), __entry->addr, __entry->vid, + __entry->db_buf, __entry->err) +); + +TRACE_EVENT(dsa_lag_fdb_del_drop, + + TP_PROTO(const struct net_device *lag_dev, const unsigned char *addr, + u16 vid, const struct dsa_db *db, const refcount_t *refcount), + + TP_ARGS(lag_dev, addr, vid, db, refcount), + + TP_STRUCT__entry( + __string(dev, lag_dev->name) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __assign_str(dev); + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + __entry->refcount = refcount_read(refcount); + ), + + TP_printk("%s addr %pM vid %u db \"%s\" refcount %u", + __get_str(dev), __entry->addr, __entry->vid, + __entry->db_buf, __entry->refcount) +); + +TRACE_EVENT(dsa_lag_fdb_del_not_found, + + TP_PROTO(const struct net_device *lag_dev, const unsigned char *addr, + u16 vid, const struct dsa_db *db), + + TP_ARGS(lag_dev, addr, vid, db), + + TP_STRUCT__entry( + __string(dev, lag_dev->name) + __array(unsigned char, addr, ETH_ALEN) + __field(u16, vid) + __array(char, db_buf, DSA_DB_BUFSIZ) + ), + + TP_fast_assign( + __assign_str(dev); + ether_addr_copy(__entry->addr, addr); + __entry->vid = vid; + dsa_db_print(db, __entry->db_buf); + ), + + TP_printk("%s addr %pM vid %u db \"%s\"", + __get_str(dev), __entry->addr, __entry->vid, __entry->db_buf) +); + +DECLARE_EVENT_CLASS(dsa_vlan_op_hw, + + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, int err), + + TP_ARGS(dp, vlan, err), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __field(u16, vid) + __field(u16, flags) + __field(bool, changed) + __field(int, err) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + __entry->vid = vlan->vid; + __entry->flags = vlan->flags; + __entry->changed = vlan->changed; + __entry->err = err; + ), + + TP_printk("%s %s port %d vid %u%s%s%s", + __get_str(dev), __get_str(kind), __entry->port, __entry->vid, + __entry->flags & BRIDGE_VLAN_INFO_PVID ? " pvid" : "", + __entry->flags & BRIDGE_VLAN_INFO_UNTAGGED ? " untagged" : "", + __entry->changed ? " (changed)" : "") +); + +DEFINE_EVENT(dsa_vlan_op_hw, dsa_vlan_add_hw, + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, int err), + TP_ARGS(dp, vlan, err)); + +DEFINE_EVENT(dsa_vlan_op_hw, dsa_vlan_del_hw, + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, int err), + TP_ARGS(dp, vlan, err)); + +DECLARE_EVENT_CLASS(dsa_vlan_op_refcount, + + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + const refcount_t *refcount), + + TP_ARGS(dp, vlan, refcount), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __field(u16, vid) + __field(u16, flags) + __field(bool, changed) + __field(unsigned int, refcount) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + __entry->vid = vlan->vid; + __entry->flags = vlan->flags; + __entry->changed = vlan->changed; + __entry->refcount = refcount_read(refcount); + ), + + TP_printk("%s %s port %d vid %u%s%s%s refcount %u", + __get_str(dev), __get_str(kind), __entry->port, __entry->vid, + __entry->flags & BRIDGE_VLAN_INFO_PVID ? " pvid" : "", + __entry->flags & BRIDGE_VLAN_INFO_UNTAGGED ? " untagged" : "", + __entry->changed ? " (changed)" : "", __entry->refcount) +); + +DEFINE_EVENT(dsa_vlan_op_refcount, dsa_vlan_add_bump, + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + const refcount_t *refcount), + TP_ARGS(dp, vlan, refcount)); + +DEFINE_EVENT(dsa_vlan_op_refcount, dsa_vlan_del_drop, + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan, + const refcount_t *refcount), + TP_ARGS(dp, vlan, refcount)); + +TRACE_EVENT(dsa_vlan_del_not_found, + + TP_PROTO(const struct dsa_port *dp, + const struct switchdev_obj_port_vlan *vlan), + + TP_ARGS(dp, vlan), + + TP_STRUCT__entry( + __string(dev, dev_name(dp->ds->dev)) + __string(kind, dsa_port_kind(dp)) + __field(int, port) + __field(u16, vid) + ), + + TP_fast_assign( + __assign_str(dev); + __assign_str(kind); + __entry->port = dp->index; + __entry->vid = vlan->vid; + ), + + TP_printk("%s %s port %d vid %u", + __get_str(dev), __get_str(kind), __entry->port, __entry->vid) +); + +#endif /* _NET_DSA_TRACE_H */ + +/* We don't want to use include/trace/events */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/net/dsa/user.c b/net/dsa/user.c new file mode 100644 index 000000000000..f59d66f0975d --- /dev/null +++ b/net/dsa/user.c @@ -0,0 +1,3877 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * net/dsa/user.c - user device handling + * Copyright (c) 2008-2009 Marvell Semiconductor + */ + +#include <linux/list.h> +#include <linux/etherdevice.h> +#include <linux/netdevice.h> +#include <linux/phy.h> +#include <linux/phy_fixed.h> +#include <linux/phylink.h> +#include <linux/of_net.h> +#include <linux/of_mdio.h> +#include <linux/mdio.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/selftests.h> +#include <net/tc_act/tc_mirred.h> +#include <linux/if_bridge.h> +#include <linux/if_hsr.h> +#include <net/dcbnl.h> +#include <linux/netpoll.h> +#include <linux/string.h> + +#include "conduit.h" +#include "dsa.h" +#include "netlink.h" +#include "port.h" +#include "switch.h" +#include "tag.h" +#include "user.h" + +struct dsa_switchdev_event_work { + struct net_device *dev; + struct net_device *orig_dev; + 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; + bool host_addr; +}; + +enum dsa_standalone_event { + DSA_UC_ADD, + DSA_UC_DEL, + DSA_MC_ADD, + DSA_MC_DEL, +}; + +struct dsa_standalone_event_work { + struct work_struct work; + struct net_device *dev; + enum dsa_standalone_event event; + unsigned char addr[ETH_ALEN]; + u16 vid; +}; + +struct dsa_host_vlan_rx_filtering_ctx { + struct net_device *dev; + const unsigned char *addr; + enum dsa_standalone_event event; +}; + +static bool dsa_switch_supports_uc_filtering(struct dsa_switch *ds) +{ + return ds->ops->port_fdb_add && ds->ops->port_fdb_del && + ds->fdb_isolation && !ds->vlan_filtering_is_global && + !ds->needs_standalone_vlan_filtering; +} + +static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) +{ + return ds->ops->port_mdb_add && ds->ops->port_mdb_del && + ds->fdb_isolation && !ds->vlan_filtering_is_global && + !ds->needs_standalone_vlan_filtering; +} + +static void dsa_user_standalone_event_work(struct work_struct *work) +{ + struct dsa_standalone_event_work *standalone_work = + container_of(work, struct dsa_standalone_event_work, work); + const unsigned char *addr = standalone_work->addr; + struct net_device *dev = standalone_work->dev; + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_mdb mdb; + struct dsa_switch *ds = dp->ds; + u16 vid = standalone_work->vid; + int err; + + switch (standalone_work->event) { + case DSA_UC_ADD: + err = dsa_port_standalone_host_fdb_add(dp, addr, vid); + if (err) { + dev_err(ds->dev, + "port %d failed to add %pM vid %d to fdb: %d\n", + dp->index, addr, vid, err); + break; + } + break; + + case DSA_UC_DEL: + err = dsa_port_standalone_host_fdb_del(dp, addr, vid); + if (err) { + dev_err(ds->dev, + "port %d failed to delete %pM vid %d from fdb: %d\n", + dp->index, addr, vid, err); + } + + break; + case DSA_MC_ADD: + ether_addr_copy(mdb.addr, addr); + mdb.vid = vid; + + err = dsa_port_standalone_host_mdb_add(dp, &mdb); + if (err) { + dev_err(ds->dev, + "port %d failed to add %pM vid %d to mdb: %d\n", + dp->index, addr, vid, err); + break; + } + break; + case DSA_MC_DEL: + ether_addr_copy(mdb.addr, addr); + mdb.vid = vid; + + err = dsa_port_standalone_host_mdb_del(dp, &mdb); + if (err) { + dev_err(ds->dev, + "port %d failed to delete %pM vid %d from mdb: %d\n", + dp->index, addr, vid, err); + } + + break; + } + + kfree(standalone_work); +} + +static int dsa_user_schedule_standalone_work(struct net_device *dev, + enum dsa_standalone_event event, + const unsigned char *addr, + u16 vid) +{ + struct dsa_standalone_event_work *standalone_work; + + standalone_work = kzalloc(sizeof(*standalone_work), GFP_ATOMIC); + if (!standalone_work) + return -ENOMEM; + + INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); + standalone_work->event = event; + standalone_work->dev = dev; + + ether_addr_copy(standalone_work->addr, addr); + standalone_work->vid = vid; + + dsa_schedule_work(&standalone_work->work); + + return 0; +} + +static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) +{ + struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; + + return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, + ctx->addr, vid); +} + +static int dsa_user_vlan_for_each(struct net_device *dev, + int (*cb)(void *arg, int vid), void *arg) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_vlan *v; + int err; + + lockdep_assert_held(&dev->addr_list_lock); + + err = cb(arg, 0); + if (err) + return err; + + list_for_each_entry(v, &dp->user_vlans, list) { + err = cb(arg, v->vid); + if (err) + return err; + } + + return 0; +} + +static int dsa_user_sync_uc(struct net_device *dev, + const unsigned char *addr) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_ADD, + }; + + dev_uc_add(conduit, addr); + + if (!dsa_switch_supports_uc_filtering(dp->ds)) + return 0; + + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, + &ctx); +} + +static int dsa_user_unsync_uc(struct net_device *dev, + const unsigned char *addr) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_UC_DEL, + }; + + dev_uc_del(conduit, addr); + + if (!dsa_switch_supports_uc_filtering(dp->ds)) + return 0; + + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, + &ctx); +} + +static int dsa_user_sync_mc(struct net_device *dev, + const unsigned char *addr) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_ADD, + }; + + dev_mc_add(conduit, addr); + + if (!dsa_switch_supports_mc_filtering(dp->ds)) + return 0; + + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, + &ctx); +} + +static int dsa_user_unsync_mc(struct net_device *dev, + const unsigned char *addr) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_host_vlan_rx_filtering_ctx ctx = { + .dev = dev, + .addr = addr, + .event = DSA_MC_DEL, + }; + + dev_mc_del(conduit, addr); + + if (!dsa_switch_supports_mc_filtering(dp->ds)) + return 0; + + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, + &ctx); +} + +void dsa_user_sync_ha(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; + + netif_addr_lock_bh(dev); + + netdev_for_each_synced_mc_addr(ha, dev) + dsa_user_sync_mc(dev, ha->addr); + + netdev_for_each_synced_uc_addr(ha, dev) + dsa_user_sync_uc(dev, ha->addr); + + netif_addr_unlock_bh(dev); + + if (dsa_switch_supports_uc_filtering(ds) || + dsa_switch_supports_mc_filtering(ds)) + dsa_flush_workqueue(); +} + +void dsa_user_unsync_ha(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; + + netif_addr_lock_bh(dev); + + netdev_for_each_synced_uc_addr(ha, dev) + dsa_user_unsync_uc(dev, ha->addr); + + netdev_for_each_synced_mc_addr(ha, dev) + dsa_user_unsync_mc(dev, ha->addr); + + netif_addr_unlock_bh(dev); + + if (dsa_switch_supports_uc_filtering(ds) || + dsa_switch_supports_mc_filtering(ds)) + dsa_flush_workqueue(); +} + +/* user mii_bus handling ***************************************************/ +static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) +{ + struct dsa_switch *ds = bus->priv; + + if (ds->phys_mii_mask & (1 << addr)) + return ds->ops->phy_read(ds, addr, reg); + + return 0xffff; +} + +static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) +{ + struct dsa_switch *ds = bus->priv; + + if (ds->phys_mii_mask & (1 << addr)) + return ds->ops->phy_write(ds, addr, reg, val); + + return 0; +} + +void dsa_user_mii_bus_init(struct dsa_switch *ds) +{ + ds->user_mii_bus->priv = (void *)ds; + ds->user_mii_bus->name = "dsa user smi"; + ds->user_mii_bus->read = dsa_user_phy_read; + ds->user_mii_bus->write = dsa_user_phy_write; + snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", + ds->dst->index, ds->index); + ds->user_mii_bus->parent = ds->dev; + ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; +} + + +/* user device handling ****************************************************/ +static int dsa_user_get_iflink(const struct net_device *dev) +{ + return READ_ONCE(dsa_user_to_conduit(dev)->ifindex); +} + +int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int err; + + if (dsa_switch_supports_uc_filtering(ds)) { + err = dsa_port_standalone_host_fdb_add(dp, addr, 0); + if (err) + goto out; + } + + if (!ether_addr_equal(addr, conduit->dev_addr)) { + err = dev_uc_add(conduit, addr); + if (err < 0) + goto del_host_addr; + } + + return 0; + +del_host_addr: + if (dsa_switch_supports_uc_filtering(ds)) + dsa_port_standalone_host_fdb_del(dp, addr, 0); +out: + return err; +} + +void dsa_user_host_uc_uninstall(struct net_device *dev) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); + + if (dsa_switch_supports_uc_filtering(ds)) + dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); +} + +static int dsa_user_open(struct net_device *dev) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + int err; + + err = dev_open(conduit, NULL); + if (err < 0) { + netdev_err(dev, "failed to open conduit %s\n", conduit->name); + goto out; + } + + err = dsa_user_host_uc_install(dev, dev->dev_addr); + if (err) + goto out; + + err = dsa_port_enable_rt(dp, dev->phydev); + if (err) + goto out_del_host_uc; + + return 0; + +out_del_host_uc: + dsa_user_host_uc_uninstall(dev); +out: + return err; +} + +static int dsa_user_close(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + dsa_port_disable_rt(dp); + + dsa_user_host_uc_uninstall(dev); + + return 0; +} + +static void dsa_user_manage_host_flood(struct net_device *dev) +{ + bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); + struct dsa_port *dp = dsa_user_to_port(dev); + bool uc = dev->flags & IFF_PROMISC; + + dsa_port_set_host_flood(dp, uc, mc); +} + +static void dsa_user_change_rx_flags(struct net_device *dev, int change) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (change & IFF_ALLMULTI) + dev_set_allmulti(conduit, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(conduit, + dev->flags & IFF_PROMISC ? 1 : -1); + + if (dsa_switch_supports_uc_filtering(ds) && + dsa_switch_supports_mc_filtering(ds)) + dsa_user_manage_host_flood(dev); +} + +static void dsa_user_set_rx_mode(struct net_device *dev) +{ + __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); + __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); +} + +static int dsa_user_set_mac_address(struct net_device *dev, void *a) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct sockaddr *addr = a; + int err; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (ds->ops->port_set_mac_address) { + err = ds->ops->port_set_mac_address(ds, dp->index, + addr->sa_data); + if (err) + return err; + } + + /* If the port is down, the address isn't synced yet to hardware or + * to the DSA conduit, so there is nothing to change. + */ + if (!(dev->flags & IFF_UP)) + goto out_change_dev_addr; + + err = dsa_user_host_uc_install(dev, addr->sa_data); + if (err) + return err; + + dsa_user_host_uc_uninstall(dev); + +out_change_dev_addr: + eth_hw_addr_set(dev, addr->sa_data); + + return 0; +} + +struct dsa_user_dump_ctx { + struct net_device *dev; + struct sk_buff *skb; + struct netlink_callback *cb; + int idx; +}; + +static int +dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, + bool is_static, void *data) +{ + struct dsa_user_dump_ctx *dump = data; + struct ndo_fdb_dump_context *ctx = (void *)dump->cb->ctx; + u32 portid = NETLINK_CB(dump->cb->skb).portid; + u32 seq = dump->cb->nlh->nlmsg_seq; + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + if (dump->idx < ctx->fdb_idx) + goto skip; + + nlh = nlmsg_put(dump->skb, portid, seq, RTM_NEWNEIGH, + sizeof(*ndm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = AF_BRIDGE; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = NTF_SELF; + ndm->ndm_type = 0; + ndm->ndm_ifindex = dump->dev->ifindex; + ndm->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + + if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, addr)) + goto nla_put_failure; + + if (vid && nla_put_u16(dump->skb, NDA_VLAN, vid)) + goto nla_put_failure; + + nlmsg_end(dump->skb, nlh); + +skip: + dump->idx++; + return 0; + +nla_put_failure: + nlmsg_cancel(dump->skb, nlh); + return -EMSGSIZE; +} + +static int +dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, struct net_device *filter_dev, + int *idx) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_dump_ctx dump = { + .dev = dev, + .skb = skb, + .cb = cb, + .idx = *idx, + }; + int err; + + err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); + *idx = dump.idx; + + return err; +} + +static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct dsa_user_priv *p = netdev_priv(dev); + + return phylink_mii_ioctl(p->dp->pl, ifr, cmd); +} + +static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + int ret; + + if (ctx && ctx != dp) + return 0; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_set_state(dp, attr->u.stp_state, true); + break; + case SWITCHDEV_ATTR_ID_PORT_MST_STATE: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_set_mst_state(dp, &attr->u.mst_state, extack); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING: + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering, + extack); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME: + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_ageing_time(dp, attr->u.ageing_time); + break; + case SWITCHDEV_ATTR_ID_BRIDGE_MST: + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_mst_enable(dp, attr->u.mst, extack); + break; + case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags, + extack); + break; + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: + if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack); + break; + case SWITCHDEV_ATTR_ID_VLAN_MSTI: + if (!dsa_port_offloads_bridge_dev(dp, attr->orig_dev)) + return -EOPNOTSUPP; + + ret = dsa_port_vlan_msti(dp, &attr->u.vlan_msti); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +/* Must be called under rcu_read_lock() */ +static int +dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, + const struct switchdev_obj_port_vlan *vlan) +{ + struct net_device *upper_dev; + struct list_head *iter; + + netdev_for_each_upper_dev_rcu(user, 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_user_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_vlan *vlan; + int err; + + 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); + + /* Deny adding a bridge VLAN when there is already an 802.1Q upper with + * the same VID. + */ + if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { + rcu_read_lock(); + err = dsa_user_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; + } + } + + return dsa_port_vlan_add(dp, vlan, extack); +} + +/* Offload a VLAN installed on the bridge or on a foreign interface by + * installing it as a VLAN towards the CPU port. + */ +static int dsa_user_host_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_vlan vlan; + + /* Do nothing if this is a software bridge */ + if (!dp->bridge) + return -EOPNOTSUPP; + + 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); + + /* Even though drivers often handle CPU membership in special ways, + * it doesn't make sense to program a PVID, so clear this flag. + */ + vlan.flags &= ~BRIDGE_VLAN_INFO_PVID; + + return dsa_port_host_vlan_add(dp, &vlan, extack); +} + +static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + int err; + + if (ctx && ctx != dp) + return 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_MDB: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + + err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; + case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + + err = dsa_port_bridge_host_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; + case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + err = dsa_user_vlan_add(dev, obj, extack); + else + err = dsa_user_host_vlan_add(dev, obj, extack); + break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_bridge_dev(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_bridge_dev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + + err = dsa_port_mrp_add_ring_role(dp, + SWITCHDEV_OBJ_RING_ROLE_MRP(obj)); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static int dsa_user_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_vlan *vlan; + + if (dsa_port_skip_vlan_configuration(dp)) + return 0; + + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + + return dsa_port_vlan_del(dp, vlan); +} + +static int dsa_user_host_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_vlan *vlan; + + /* Do nothing if this is a software bridge */ + if (!dp->bridge) + return -EOPNOTSUPP; + + if (dsa_port_skip_vlan_configuration(dp)) + return 0; + + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + + return dsa_port_host_vlan_del(dp, vlan); +} + +static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + int err; + + if (ctx && ctx != dp) + return 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_PORT_MDB: + if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + return -EOPNOTSUPP; + + err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; + case SWITCHDEV_OBJ_ID_HOST_MDB: + if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) + return -EOPNOTSUPP; + + err = dsa_port_bridge_host_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj)); + break; + case SWITCHDEV_OBJ_ID_PORT_VLAN: + if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) + err = dsa_user_vlan_del(dev, obj); + else + err = dsa_user_host_vlan_del(dev, obj); + break; + case SWITCHDEV_OBJ_ID_MRP: + if (!dsa_port_offloads_bridge_dev(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_bridge_dev(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; + } + + return err; +} + +static netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) +{ +#ifdef CONFIG_NET_POLL_CONTROLLER + struct dsa_user_priv *p = netdev_priv(dev); + + return netpoll_send_skb(p->netpoll, skb); +#else + BUG(); + return NETDEV_TX_OK; +#endif +} + +static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, + struct sk_buff *skb) +{ + struct dsa_switch *ds = p->dp->ds; + + if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NOBPF)) + return; + + if (!ds->ops->port_txtstamp) + return; + + ds->ops->port_txtstamp(ds, p->dp->index, skb); +} + +netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) +{ + /* SKB for netpoll still need to be mangled with the protocol-specific + * tag to be successfully transmitted + */ + if (unlikely(netpoll_tx_running(dev))) + return dsa_user_netpoll_send_skb(dev, skb); + + /* Queue the SKB for transmission on the parent interface, but + * do not modify its EtherType + */ + skb->dev = dsa_user_to_conduit(dev); + dev_queue_xmit(skb); + + return NETDEV_TX_OK; +} +EXPORT_SYMBOL_GPL(dsa_enqueue_skb); + +static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + struct sk_buff *nskb; + + dev_sw_netstats_tx_add(dev, 1, skb->len); + + memset(skb->cb, 0, sizeof(skb->cb)); + + /* Handle tx timestamp if any */ + dsa_skb_tx_timestamp(p, skb); + + if (skb_ensure_writable_head_tail(skb, dev)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* needed_tailroom should still be 'warm' in the cache line from + * skb_ensure_writable_head_tail(), 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. + */ + nskb = p->xmit(skb, dev); + if (!nskb) { + kfree_skb(skb); + return NETDEV_TX_OK; + } + + return dsa_enqueue_skb(nskb, dev); +} + +/* ethtool operations *******************************************************/ + +static void dsa_user_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) +{ + strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); + strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); + strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); +} + +static int dsa_user_get_regs_len(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_regs_len) + return ds->ops->get_regs_len(ds, dp->index); + + return -EOPNOTSUPP; +} + +static void +dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_regs) + ds->ops->get_regs(ds, dp->index, regs, _p); +} + +static int dsa_user_nway_reset(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return phylink_ethtool_nway_reset(dp->pl); +} + +static int dsa_user_get_eeprom_len(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->cd && ds->cd->eeprom_len) + return ds->cd->eeprom_len; + + if (ds->ops->get_eeprom_len) + return ds->ops->get_eeprom_len(ds); + + return 0; +} + +static int dsa_user_get_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eeprom) + return ds->ops->get_eeprom(ds, eeprom, data); + + return -EOPNOTSUPP; +} + +static int dsa_user_set_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->set_eeprom) + return ds->ops->set_eeprom(ds, eeprom, data); + + return -EOPNOTSUPP; +} + +static void dsa_user_get_strings(struct net_device *dev, + uint32_t stringset, uint8_t *data) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (stringset == ETH_SS_STATS) { + ethtool_puts(&data, "tx_packets"); + ethtool_puts(&data, "tx_bytes"); + ethtool_puts(&data, "rx_packets"); + ethtool_puts(&data, "rx_bytes"); + if (ds->ops->get_strings) + ds->ops->get_strings(ds, dp->index, stringset, data); + } else if (stringset == ETH_SS_TEST) { + net_selftest_get_strings(data); + } + +} + +static void dsa_user_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct pcpu_sw_netstats *s; + unsigned int start; + int i; + + for_each_possible_cpu(i) { + u64 tx_packets, tx_bytes, rx_packets, rx_bytes; + + s = per_cpu_ptr(dev->tstats, i); + do { + start = u64_stats_fetch_begin(&s->syncp); + tx_packets = u64_stats_read(&s->tx_packets); + tx_bytes = u64_stats_read(&s->tx_bytes); + rx_packets = u64_stats_read(&s->rx_packets); + rx_bytes = u64_stats_read(&s->rx_bytes); + } while (u64_stats_fetch_retry(&s->syncp, start)); + data[0] += tx_packets; + data[1] += tx_bytes; + data[2] += rx_packets; + data[3] += rx_bytes; + } + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, dp->index, data + 4); +} + +static int dsa_user_get_sset_count(struct net_device *dev, int sset) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (sset == ETH_SS_STATS) { + int count = 0; + + if (ds->ops->get_sset_count) { + count = ds->ops->get_sset_count(ds, dp->index, sset); + if (count < 0) + return count; + } + + return count + 4; + } else if (sset == ETH_SS_TEST) { + return net_selftest_get_count(); + } + + return -EOPNOTSUPP; +} + +static void dsa_user_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_phy_stats) + ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); +} + +static void dsa_user_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_mac_stats) + ds->ops->get_eth_mac_stats(ds, dp->index, mac_stats); +} + +static void +dsa_user_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_eth_ctrl_stats) + ds->ops->get_eth_ctrl_stats(ds, dp->index, ctrl_stats); +} + +static void +dsa_user_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_rmon_stats) + ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); +} + +static void dsa_user_get_ts_stats(struct net_device *dev, + struct ethtool_ts_stats *ts_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_ts_stats) + ds->ops->get_ts_stats(ds, dp->index, ts_stats); +} + +static void dsa_user_net_selftest(struct net_device *ndev, + struct ethtool_test *etest, u64 *buf) +{ + struct dsa_port *dp = dsa_user_to_port(ndev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->self_test) { + ds->ops->self_test(ds, dp->index, etest, buf); + return; + } + + net_selftest(ndev, etest, buf); +} + +static int dsa_user_get_mm(struct net_device *dev, + struct ethtool_mm_state *state) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->get_mm) + return -EOPNOTSUPP; + + return ds->ops->get_mm(ds, dp->index, state); +} + +static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->set_mm) + return -EOPNOTSUPP; + + return ds->ops->set_mm(ds, dp->index, cfg, extack); +} + +static void dsa_user_get_mm_stats(struct net_device *dev, + struct ethtool_mm_stats *stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_mm_stats) + ds->ops->get_mm_stats(ds, dp->index, stats); +} + +static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + phylink_ethtool_get_wol(dp->pl, w); + + if (ds->ops->get_wol) + ds->ops->get_wol(ds, dp->index, w); +} + +static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int ret = -EOPNOTSUPP; + + phylink_ethtool_set_wol(dp->pl, w); + + if (ds->ops->set_wol) + ret = ds->ops->set_wol(ds, dp->index, w); + + return ret; +} + +static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int ret; + + /* Check whether the switch supports EEE */ + if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) + return -EOPNOTSUPP; + + /* If the port is using phylink managed EEE, then an unimplemented + * set_mac_eee() is permissible. + */ + if (!phylink_mac_implements_lpi(ds->phylink_mac_ops)) { + /* Port's PHY and MAC both need to be EEE capable */ + if (!dev->phydev) + return -ENODEV; + + if (!ds->ops->set_mac_eee) + return -EOPNOTSUPP; + + ret = ds->ops->set_mac_eee(ds, dp->index, e); + if (ret) + return ret; + } else if (ds->ops->set_mac_eee) { + ret = ds->ops->set_mac_eee(ds, dp->index, e); + if (ret) + return ret; + } + + return phylink_ethtool_set_eee(dp->pl, e); +} + +static int dsa_user_get_eee(struct net_device *dev, struct ethtool_keee *e) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + /* Check whether the switch supports EEE */ + if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index)) + return -EOPNOTSUPP; + + /* Port's PHY and MAC both need to be EEE capable */ + if (!dev->phydev) + return -ENODEV; + + return phylink_ethtool_get_eee(dp->pl, e); +} + +static int dsa_user_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return phylink_ethtool_ksettings_get(dp->pl, cmd); +} + +static int dsa_user_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return phylink_ethtool_ksettings_set(dp->pl, cmd); +} + +static void dsa_user_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (ds->ops->get_pause_stats) + ds->ops->get_pause_stats(ds, dp->index, pause_stats); +} + +static void dsa_user_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + phylink_ethtool_get_pauseparam(dp->pl, pause); +} + +static int dsa_user_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return phylink_ethtool_set_pauseparam(dp->pl, pause); +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static int dsa_user_netpoll_setup(struct net_device *dev) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_user_priv *p = netdev_priv(dev); + struct netpoll *netpoll; + int err = 0; + + netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL); + if (!netpoll) + return -ENOMEM; + + err = __netpoll_setup(netpoll, conduit); + if (err) { + kfree(netpoll); + goto out; + } + + p->netpoll = netpoll; +out: + return err; +} + +static void dsa_user_netpoll_cleanup(struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + struct netpoll *netpoll = p->netpoll; + + if (!netpoll) + return; + + p->netpoll = NULL; + + __netpoll_free(netpoll); +} + +static void dsa_user_poll_controller(struct net_device *dev) +{ +} +#endif + +static struct dsa_mall_tc_entry * +dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) +{ + struct dsa_user_priv *p = netdev_priv(dev); + struct dsa_mall_tc_entry *mall_tc_entry; + + list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) + if (mall_tc_entry->cookie == cookie) + return mall_tc_entry; + + return NULL; +} + +static int +dsa_user_add_cls_matchall_mirred(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress, bool ingress_target) +{ + struct netlink_ext_ack *extack = cls->common.extack; + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); + struct dsa_mall_mirror_tc_entry *mirror; + struct dsa_mall_tc_entry *mall_tc_entry; + struct dsa_switch *ds = dp->ds; + struct flow_action_entry *act; + struct dsa_port *to_dp; + int err; + + if (cls->common.protocol != htons(ETH_P_ALL)) { + NL_SET_ERR_MSG_MOD(extack, + "Can only offload \"protocol all\" matchall filter"); + return -EOPNOTSUPP; + } + + if (!ds->ops->port_mirror_add) { + NL_SET_ERR_MSG_MOD(extack, + "Switch does not support mirroring operation"); + return -EOPNOTSUPP; + } + + if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) + return -EOPNOTSUPP; + + act = &cls->rule->action.entries[0]; + + if (!act->dev) + return -EINVAL; + + if (dsa_user_dev_check(act->dev)) { + if (ingress_target) { + /* We can only fulfill this using software assist */ + if (cls->common.skip_sw) { + NL_SET_ERR_MSG_MOD(extack, + "Can only mirred to ingress of DSA user port if filter also runs in software"); + return -EOPNOTSUPP; + } + to_dp = dp->cpu_dp; + } else { + to_dp = dsa_user_to_port(act->dev); + } + } else { + /* Handle mirroring to foreign target ports as a mirror towards + * the CPU. The software tc rule will take the packets from + * there. + */ + if (cls->common.skip_sw) { + NL_SET_ERR_MSG_MOD(extack, + "Can only mirred to CPU if filter also runs in software"); + return -EOPNOTSUPP; + } + to_dp = dp->cpu_dp; + } + + if (dp->ds != to_dp->ds) { + NL_SET_ERR_MSG_MOD(extack, + "Cross-chip mirroring not implemented"); + return -EOPNOTSUPP; + } + + mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); + if (!mall_tc_entry) + return -ENOMEM; + + mall_tc_entry->cookie = cls->cookie; + mall_tc_entry->type = DSA_PORT_MALL_MIRROR; + mirror = &mall_tc_entry->mirror; + mirror->to_local_port = to_dp->index; + mirror->ingress = ingress; + + err = ds->ops->port_mirror_add(ds, dp->index, mirror, ingress, extack); + if (err) { + kfree(mall_tc_entry); + return err; + } + + list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); + + return err; +} + +static int +dsa_user_add_cls_matchall_police(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) +{ + struct netlink_ext_ack *extack = cls->common.extack; + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); + struct dsa_mall_policer_tc_entry *policer; + struct dsa_mall_tc_entry *mall_tc_entry; + struct dsa_switch *ds = dp->ds; + struct flow_action_entry *act; + int err; + + if (!ds->ops->port_policer_add) { + NL_SET_ERR_MSG_MOD(extack, + "Policing offload not implemented"); + return -EOPNOTSUPP; + } + + if (!ingress) { + NL_SET_ERR_MSG_MOD(extack, + "Only supported on ingress qdisc"); + return -EOPNOTSUPP; + } + + if (!flow_action_basic_hw_stats_check(&cls->rule->action, extack)) + return -EOPNOTSUPP; + + list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) { + if (mall_tc_entry->type == DSA_PORT_MALL_POLICER) { + NL_SET_ERR_MSG_MOD(extack, + "Only one port policer allowed"); + return -EEXIST; + } + } + + act = &cls->rule->action.entries[0]; + + mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); + if (!mall_tc_entry) + return -ENOMEM; + + mall_tc_entry->cookie = cls->cookie; + mall_tc_entry->type = DSA_PORT_MALL_POLICER; + policer = &mall_tc_entry->policer; + policer->rate_bytes_per_sec = act->police.rate_bytes_ps; + policer->burst = act->police.burst; + + err = ds->ops->port_policer_add(ds, dp->index, policer); + if (err) { + kfree(mall_tc_entry); + return err; + } + + list_add_tail(&mall_tc_entry->list, &p->mall_tc_list); + + return err; +} + +static int dsa_user_add_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) +{ + const struct flow_action *action = &cls->rule->action; + struct netlink_ext_ack *extack = cls->common.extack; + + if (!flow_offload_has_one_action(action)) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload matchall filter with more than one action"); + return -EOPNOTSUPP; + } + + switch (action->entries[0].id) { + case FLOW_ACTION_MIRRED: + return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, + false); + case FLOW_ACTION_MIRRED_INGRESS: + return dsa_user_add_cls_matchall_mirred(dev, cls, ingress, + true); + case FLOW_ACTION_POLICE: + return dsa_user_add_cls_matchall_police(dev, cls, ingress); + default: + NL_SET_ERR_MSG_MOD(extack, "Unknown action"); + break; + } + + return -EOPNOTSUPP; +} + +static void dsa_user_del_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_mall_tc_entry *mall_tc_entry; + struct dsa_switch *ds = dp->ds; + + mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); + if (!mall_tc_entry) + return; + + list_del(&mall_tc_entry->list); + + switch (mall_tc_entry->type) { + case DSA_PORT_MALL_MIRROR: + if (ds->ops->port_mirror_del) + ds->ops->port_mirror_del(ds, dp->index, + &mall_tc_entry->mirror); + break; + case DSA_PORT_MALL_POLICER: + if (ds->ops->port_policer_del) + ds->ops->port_policer_del(ds, dp->index); + break; + default: + WARN_ON(1); + } + + kfree(mall_tc_entry); +} + +static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) +{ + if (cls->common.chain_index) + return -EOPNOTSUPP; + + switch (cls->command) { + case TC_CLSMATCHALL_REPLACE: + return dsa_user_add_cls_matchall(dev, cls, ingress); + case TC_CLSMATCHALL_DESTROY: + dsa_user_del_cls_matchall(dev, cls); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int dsa_user_add_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_add) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_add(ds, port, cls, ingress); +} + +static int dsa_user_del_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_del) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_del(ds, port, cls, ingress); +} + +static int dsa_user_stats_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->cls_flower_stats) + return -EOPNOTSUPP; + + return ds->ops->cls_flower_stats(ds, port, cls, ingress); +} + +static int dsa_user_setup_tc_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) +{ + switch (cls->command) { + case FLOW_CLS_REPLACE: + return dsa_user_add_cls_flower(dev, cls, ingress); + case FLOW_CLS_DESTROY: + return dsa_user_del_cls_flower(dev, cls, ingress); + case FLOW_CLS_STATS: + return dsa_user_stats_cls_flower(dev, cls, ingress); + default: + return -EOPNOTSUPP; + } +} + +static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv, bool ingress) +{ + struct net_device *dev = cb_priv; + + if (!tc_can_offload(dev)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSMATCHALL: + return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); + case TC_SETUP_CLSFLOWER: + return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); + default: + return -EOPNOTSUPP; + } +} + +static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); +} + +static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, + void *type_data, void *cb_priv) +{ + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); +} + +static LIST_HEAD(dsa_user_block_cb_list); + +static int dsa_user_setup_tc_block(struct net_device *dev, + struct flow_block_offload *f) +{ + struct flow_block_cb *block_cb; + flow_setup_cb_t *cb; + + if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + cb = dsa_user_setup_tc_block_cb_ig; + else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) + cb = dsa_user_setup_tc_block_cb_eg; + else + return -EOPNOTSUPP; + + f->driver_block_list = &dsa_user_block_cb_list; + + switch (f->command) { + case FLOW_BLOCK_BIND: + if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) + return -EBUSY; + + block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); + if (IS_ERR(block_cb)) + return PTR_ERR(block_cb); + + flow_block_cb_add(block_cb, f); + list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); + return 0; + case FLOW_BLOCK_UNBIND: + block_cb = flow_block_cb_lookup(f->block, cb, dev); + if (!block_cb) + return -ENOENT; + + flow_block_cb_remove(block_cb, f); + list_del(&block_cb->driver_list); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, + void *type_data) +{ + struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); + + if (!conduit->netdev_ops->ndo_setup_tc) + return -EOPNOTSUPP; + + return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); +} + +static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + switch (type) { + case TC_SETUP_BLOCK: + return dsa_user_setup_tc_block(dev, type_data); + case TC_SETUP_FT: + return dsa_user_setup_ft_block(ds, dp->index, type_data); + default: + break; + } + + if (!ds->ops->port_setup_tc) + return -EOPNOTSUPP; + + return ds->ops->port_setup_tc(ds, dp->index, type, type_data); +} + +static int dsa_user_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc, u32 *rule_locs) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->get_rxnfc) + return -EOPNOTSUPP; + + return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); +} + +static int dsa_user_set_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->set_rxnfc) + return -EOPNOTSUPP; + + return ds->ops->set_rxnfc(ds, dp->index, nfc); +} + +static int dsa_user_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *ts) +{ + struct dsa_user_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->dp->ds; + + if (!ds->ops->get_ts_info) + return -EOPNOTSUPP; + + return ds->ops->get_ts_info(ds, p->dp->index, ts); +} + +static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + 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}; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; + struct dsa_vlan *v; + int 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; + } + + /* And CPU port... */ + ret = dsa_port_host_vlan_add(dp, &vlan, &extack); + if (ret) { + if (extack._msg) + netdev_err(dev, "CPU port %d: %s\n", dp->cpu_dp->index, + extack._msg); + return ret; + } + + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + v = kzalloc(sizeof(*v), GFP_KERNEL); + if (!v) { + ret = -ENOMEM; + goto rollback; + } + + netif_addr_lock_bh(dev); + + v->vid = vid; + list_add_tail(&v->list, &dp->user_vlans); + + if (dsa_switch_supports_mc_filtering(ds)) { + netdev_for_each_synced_mc_addr(ha, dev) { + dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, + ha->addr, vid); + } + } + + if (dsa_switch_supports_uc_filtering(ds)) { + netdev_for_each_synced_uc_addr(ha, dev) { + dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, + ha->addr, vid); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + + return 0; + +rollback: + dsa_port_host_vlan_del(dp, &vlan); + dsa_port_vlan_del(dp, &vlan); + + return ret; +} + +static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, + u16 vid) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct switchdev_obj_port_vlan vlan = { + .vid = vid, + /* This API only allows programming tagged, non-PVID VIDs */ + .flags = 0, + }; + struct dsa_switch *ds = dp->ds; + struct netdev_hw_addr *ha; + struct dsa_vlan *v; + int err; + + err = dsa_port_vlan_del(dp, &vlan); + if (err) + return err; + + err = dsa_port_host_vlan_del(dp, &vlan); + if (err) + return err; + + if (!dsa_switch_supports_uc_filtering(ds) && + !dsa_switch_supports_mc_filtering(ds)) + return 0; + + netif_addr_lock_bh(dev); + + v = dsa_vlan_find(&dp->user_vlans, &vlan); + if (!v) { + netif_addr_unlock_bh(dev); + return -ENOENT; + } + + list_del(&v->list); + kfree(v); + + if (dsa_switch_supports_mc_filtering(ds)) { + netdev_for_each_synced_mc_addr(ha, dev) { + dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, + ha->addr, vid); + } + } + + if (dsa_switch_supports_uc_filtering(ds)) { + netdev_for_each_synced_uc_addr(ha, dev) { + dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, + ha->addr, vid); + } + } + + netif_addr_unlock_bh(dev); + + dsa_flush_workqueue(); + + return 0; +} + +static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) +{ + __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); + + return dsa_user_vlan_rx_add_vid(arg, proto, vid); +} + +static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) +{ + __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); + + return dsa_user_vlan_rx_kill_vid(arg, proto, vid); +} + +/* Keep the VLAN RX filtering list in sync with the hardware only if VLAN + * filtering is enabled. The baseline is that only ports that offload a + * VLAN-aware bridge are VLAN-aware, and standalone ports are VLAN-unaware, + * but there are exceptions for quirky hardware. + * + * If ds->vlan_filtering_is_global = true, then standalone ports which share + * the same switch with other ports that offload a VLAN-aware bridge are also + * inevitably VLAN-aware. + * + * To summarize, a DSA switch port offloads: + * + * - If standalone (this includes software bridge, software LAG): + * - if ds->needs_standalone_vlan_filtering = true, OR if + * (ds->vlan_filtering_is_global = true AND there are bridges spanning + * this switch chip which have vlan_filtering=1) + * - the 8021q upper VLANs + * - else (standalone VLAN filtering is not needed, VLAN filtering is not + * global, or it is, but no port is under a VLAN-aware bridge): + * - no VLAN (any 8021q upper is a software VLAN) + * + * - If under a vlan_filtering=0 bridge which it offload: + * - if ds->configure_vlan_while_not_filtering = true (default): + * - the bridge VLANs. These VLANs are committed to hardware but inactive. + * - else (deprecated): + * - no VLAN. The bridge VLANs are not restored when VLAN awareness is + * enabled, so this behavior is broken and discouraged. + * + * - If under a vlan_filtering=1 bridge which it offload: + * - the bridge VLANs + * - the 8021q upper VLANs + */ +int dsa_user_manage_vlan_filtering(struct net_device *user, + bool vlan_filtering) +{ + int err; + + if (vlan_filtering) { + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + err = vlan_for_each(user, dsa_user_restore_vlan, user); + if (err) { + vlan_for_each(user, dsa_user_clear_vlan, user); + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + return err; + } + } else { + err = vlan_for_each(user, dsa_user_clear_vlan, user); + if (err) + return err; + + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + } + + return 0; +} + +struct dsa_hw_port { + struct list_head list; + struct net_device *dev; + int old_mtu; +}; + +static int dsa_hw_port_list_set_mtu(struct list_head *hw_port_list, int mtu) +{ + const struct dsa_hw_port *p; + int err; + + list_for_each_entry(p, hw_port_list, list) { + if (p->dev->mtu == mtu) + continue; + + err = dev_set_mtu(p->dev, mtu); + if (err) + goto rollback; + } + + return 0; + +rollback: + list_for_each_entry_continue_reverse(p, hw_port_list, list) { + if (p->dev->mtu == p->old_mtu) + continue; + + if (dev_set_mtu(p->dev, p->old_mtu)) + netdev_err(p->dev, "Failed to restore MTU\n"); + } + + return err; +} + +static void dsa_hw_port_list_free(struct list_head *hw_port_list) +{ + struct dsa_hw_port *p, *n; + + list_for_each_entry_safe(p, n, hw_port_list, list) + kfree(p); +} + +/* Make the hardware datapath to/from @dev limited to a common MTU */ +static void dsa_bridge_mtu_normalization(struct dsa_port *dp) +{ + struct list_head hw_port_list; + struct dsa_switch_tree *dst; + int min_mtu = ETH_MAX_MTU; + struct dsa_port *other_dp; + int err; + + if (!dp->ds->mtu_enforcement_ingress) + return; + + if (!dp->bridge) + return; + + INIT_LIST_HEAD(&hw_port_list); + + /* Populate the list of ports that are part of the same bridge + * as the newly added/modified port + */ + list_for_each_entry(dst, &dsa_tree_list, list) { + list_for_each_entry(other_dp, &dst->ports, list) { + struct dsa_hw_port *hw_port; + struct net_device *user; + + if (other_dp->type != DSA_PORT_TYPE_USER) + continue; + + if (!dsa_port_bridge_same(dp, other_dp)) + continue; + + if (!other_dp->ds->mtu_enforcement_ingress) + continue; + + user = other_dp->user; + + if (min_mtu > user->mtu) + min_mtu = user->mtu; + + hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); + if (!hw_port) + goto out; + + hw_port->dev = user; + hw_port->old_mtu = user->mtu; + + list_add(&hw_port->list, &hw_port_list); + } + } + + /* Attempt to configure the entire hardware bridge to the newly added + * interface's MTU first, regardless of whether the intention of the + * user was to raise or lower it. + */ + err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); + if (!err) + goto out; + + /* Clearly that didn't work out so well, so just set the minimum MTU on + * all hardware bridge ports now. If this fails too, then all ports will + * still have their old MTU rolled back anyway. + */ + dsa_hw_port_list_set_mtu(&hw_port_list, min_mtu); + +out: + dsa_hw_port_list_free(&hw_port_list); +} + +int dsa_user_change_mtu(struct net_device *dev, int new_mtu) +{ + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_port *cpu_dp = dp->cpu_dp; + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + int largest_mtu = 0; + int new_conduit_mtu; + int old_conduit_mtu; + int mtu_limit; + int overhead; + int cpu_mtu; + int err; + + if (!ds->ops->port_change_mtu) + return -EOPNOTSUPP; + + dsa_tree_for_each_user_port(other_dp, ds->dst) { + int user_mtu; + + /* During probe, this function will be called for each user + * device, while not all of them have been allocated. That's + * ok, it doesn't change what the maximum is, so ignore it. + */ + if (!other_dp->user) + continue; + + /* Pretend that we already applied the setting, which we + * actually haven't (still haven't done all integrity checks) + */ + if (dp == other_dp) + user_mtu = new_mtu; + else + user_mtu = other_dp->user->mtu; + + if (largest_mtu < user_mtu) + largest_mtu = user_mtu; + } + + overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); + mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); + old_conduit_mtu = conduit->mtu; + new_conduit_mtu = largest_mtu + overhead; + if (new_conduit_mtu > mtu_limit) + return -ERANGE; + + /* If the conduit MTU isn't over limit, there's no need to check the CPU + * MTU, since that surely isn't either. + */ + cpu_mtu = largest_mtu; + + /* Start applying stuff */ + if (new_conduit_mtu != old_conduit_mtu) { + err = dev_set_mtu(conduit, new_conduit_mtu); + if (err < 0) + goto out_conduit_failed; + + /* We only need to propagate the MTU of the CPU port to + * upstream switches, so emit a notifier which updates them. + */ + err = dsa_port_mtu_change(cpu_dp, cpu_mtu); + if (err) + goto out_cpu_failed; + } + + err = ds->ops->port_change_mtu(ds, dp->index, new_mtu); + if (err) + goto out_port_failed; + + WRITE_ONCE(dev->mtu, new_mtu); + + dsa_bridge_mtu_normalization(dp); + + return 0; + +out_port_failed: + if (new_conduit_mtu != old_conduit_mtu) + dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); +out_cpu_failed: + if (new_conduit_mtu != old_conduit_mtu) + dev_set_mtu(conduit, old_conduit_mtu); +out_conduit_failed: + return err; +} + +static int __maybe_unused +dsa_user_dcbnl_set_apptrust(struct net_device *dev, u8 *sel, int nsel) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_set_apptrust) + return -EOPNOTSUPP; + + return ds->ops->port_set_apptrust(ds, port, sel, nsel); +} + +static int __maybe_unused +dsa_user_dcbnl_get_apptrust(struct net_device *dev, u8 *sel, int *nsel) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_get_apptrust) + return -EOPNOTSUPP; + + return ds->ops->port_get_apptrust(ds, port, sel, nsel); +} + +static int __maybe_unused +dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + unsigned long mask, new_prio; + int err, port = dp->index; + + if (!ds->ops->port_set_default_prio) + return -EOPNOTSUPP; + + err = dcb_ieee_setapp(dev, app); + if (err) + return err; + + mask = dcb_ieee_getapp_mask(dev, app); + new_prio = __fls(mask); + + err = ds->ops->port_set_default_prio(ds, port, new_prio); + if (err) { + dcb_ieee_delapp(dev, app); + return err; + } + + return 0; +} + +/* Update the DSCP prio entries on all user ports of the switch in case + * the switch supports global DSCP prio instead of per port DSCP prios. + */ +static int dsa_user_dcbnl_ieee_global_dscp_setdel(struct net_device *dev, + struct dcb_app *app, bool del) +{ + int (*setdel)(struct net_device *dev, struct dcb_app *app); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; + int err, restore_err; + + if (del) + setdel = dcb_ieee_delapp; + else + setdel = dcb_ieee_setapp; + + dsa_switch_for_each_user_port(other_dp, ds) { + struct net_device *user = other_dp->user; + + if (!user || user == dev) + continue; + + err = setdel(user, app); + if (err) + goto err_try_to_restore; + } + + return 0; + +err_try_to_restore: + + /* Revert logic to restore previous state of app entries */ + if (!del) + setdel = dcb_ieee_delapp; + else + setdel = dcb_ieee_setapp; + + dsa_switch_for_each_user_port_continue_reverse(other_dp, ds) { + struct net_device *user = other_dp->user; + + if (!user || user == dev) + continue; + + restore_err = setdel(user, app); + if (restore_err) + netdev_err(user, "Failed to restore DSCP prio entry configuration\n"); + } + + return err; +} + +static int __maybe_unused +dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + unsigned long mask, new_prio; + int err, port = dp->index; + u8 dscp = app->protocol; + + if (!ds->ops->port_add_dscp_prio) + return -EOPNOTSUPP; + + if (dscp >= 64) { + netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n", + dscp); + return -EINVAL; + } + + err = dcb_ieee_setapp(dev, app); + if (err) + return err; + + mask = dcb_ieee_getapp_mask(dev, app); + new_prio = __fls(mask); + + err = ds->ops->port_add_dscp_prio(ds, port, dscp, new_prio); + if (err) { + dcb_ieee_delapp(dev, app); + return err; + } + + if (!ds->dscp_prio_mapping_is_global) + return 0; + + err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, false); + if (err) { + if (ds->ops->port_del_dscp_prio) + ds->ops->port_del_dscp_prio(ds, port, dscp, new_prio); + dcb_ieee_delapp(dev, app); + return err; + } + + return 0; +} + +static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) +{ + switch (app->selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + switch (app->protocol) { + case 0: + return dsa_user_dcbnl_set_default_prio(dev, app); + default: + return -EOPNOTSUPP; + } + break; + case IEEE_8021QAZ_APP_SEL_DSCP: + return dsa_user_dcbnl_add_dscp_prio(dev, app); + default: + return -EOPNOTSUPP; + } +} + +static int __maybe_unused +dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + unsigned long mask, new_prio; + int err, port = dp->index; + + if (!ds->ops->port_set_default_prio) + return -EOPNOTSUPP; + + err = dcb_ieee_delapp(dev, app); + if (err) + return err; + + mask = dcb_ieee_getapp_mask(dev, app); + new_prio = mask ? __fls(mask) : 0; + + err = ds->ops->port_set_default_prio(ds, port, new_prio); + if (err) { + dcb_ieee_setapp(dev, app); + return err; + } + + return 0; +} + +static int __maybe_unused +dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int err, port = dp->index; + u8 dscp = app->protocol; + + if (!ds->ops->port_del_dscp_prio) + return -EOPNOTSUPP; + + err = dcb_ieee_delapp(dev, app); + if (err) + return err; + + err = ds->ops->port_del_dscp_prio(ds, port, dscp, app->priority); + if (err) { + dcb_ieee_setapp(dev, app); + return err; + } + + if (!ds->dscp_prio_mapping_is_global) + return 0; + + err = dsa_user_dcbnl_ieee_global_dscp_setdel(dev, app, true); + if (err) { + if (ds->ops->port_add_dscp_prio) + ds->ops->port_add_dscp_prio(ds, port, dscp, + app->priority); + dcb_ieee_setapp(dev, app); + return err; + } + + return 0; +} + +static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) +{ + switch (app->selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + switch (app->protocol) { + case 0: + return dsa_user_dcbnl_del_default_prio(dev, app); + default: + return -EOPNOTSUPP; + } + break; + case IEEE_8021QAZ_APP_SEL_DSCP: + return dsa_user_dcbnl_del_dscp_prio(dev, app); + default: + return -EOPNOTSUPP; + } +} + +/* Pre-populate the DCB application priority table with the priorities + * configured during switch setup, which we read from hardware here. + */ +static int dsa_user_dcbnl_init(struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + int port = dp->index; + int err; + + if (ds->ops->port_get_default_prio) { + int prio = ds->ops->port_get_default_prio(ds, port); + struct dcb_app app = { + .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, + .protocol = 0, + .priority = prio, + }; + + if (prio < 0) + return prio; + + err = dcb_ieee_setapp(dev, &app); + if (err) + return err; + } + + if (ds->ops->port_get_dscp_prio) { + int protocol; + + for (protocol = 0; protocol < 64; protocol++) { + struct dcb_app app = { + .selector = IEEE_8021QAZ_APP_SEL_DSCP, + .protocol = protocol, + }; + int prio; + + prio = ds->ops->port_get_dscp_prio(ds, port, protocol); + if (prio == -EOPNOTSUPP) + continue; + if (prio < 0) + return prio; + + app.priority = prio; + + err = dcb_ieee_setapp(dev, &app); + if (err) + return err; + } + } + + return 0; +} + +static const struct ethtool_ops dsa_user_ethtool_ops = { + .get_drvinfo = dsa_user_get_drvinfo, + .get_regs_len = dsa_user_get_regs_len, + .get_regs = dsa_user_get_regs, + .nway_reset = dsa_user_nway_reset, + .get_link = ethtool_op_get_link, + .get_eeprom_len = dsa_user_get_eeprom_len, + .get_eeprom = dsa_user_get_eeprom, + .set_eeprom = dsa_user_set_eeprom, + .get_strings = dsa_user_get_strings, + .get_ethtool_stats = dsa_user_get_ethtool_stats, + .get_sset_count = dsa_user_get_sset_count, + .get_eth_phy_stats = dsa_user_get_eth_phy_stats, + .get_eth_mac_stats = dsa_user_get_eth_mac_stats, + .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, + .get_rmon_stats = dsa_user_get_rmon_stats, + .get_ts_stats = dsa_user_get_ts_stats, + .set_wol = dsa_user_set_wol, + .get_wol = dsa_user_get_wol, + .set_eee = dsa_user_set_eee, + .get_eee = dsa_user_get_eee, + .get_link_ksettings = dsa_user_get_link_ksettings, + .set_link_ksettings = dsa_user_set_link_ksettings, + .get_pause_stats = dsa_user_get_pause_stats, + .get_pauseparam = dsa_user_get_pauseparam, + .set_pauseparam = dsa_user_set_pauseparam, + .get_rxnfc = dsa_user_get_rxnfc, + .set_rxnfc = dsa_user_set_rxnfc, + .get_ts_info = dsa_user_get_ts_info, + .self_test = dsa_user_net_selftest, + .get_mm = dsa_user_get_mm, + .set_mm = dsa_user_set_mm, + .get_mm_stats = dsa_user_get_mm_stats, +}; + +static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { + .ieee_setapp = dsa_user_dcbnl_ieee_setapp, + .ieee_delapp = dsa_user_dcbnl_ieee_delapp, + .dcbnl_setapptrust = dsa_user_dcbnl_set_apptrust, + .dcbnl_getapptrust = dsa_user_dcbnl_get_apptrust, +}; + +static void dsa_user_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) +{ + struct dsa_port *dp = dsa_user_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 int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) +{ + struct dsa_port *dp = dsa_user_to_port(ctx->dev); + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_port *cpu_dp = dp->cpu_dp; + + path->dev = ctx->dev; + path->type = DEV_PATH_DSA; + path->dsa.proto = cpu_dp->tag_ops->proto; + path->dsa.port = dp->index; + ctx->dev = conduit; + + return 0; +} + +static int dsa_user_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *cfg) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->port_hwtstamp_get) + return -EOPNOTSUPP; + + return ds->ops->port_hwtstamp_get(ds, dp->index, cfg); +} + +static int dsa_user_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->port_hwtstamp_set) + return -EOPNOTSUPP; + + return ds->ops->port_hwtstamp_set(ds, dp->index, cfg, extack); +} + +static const struct net_device_ops dsa_user_netdev_ops = { + .ndo_open = dsa_user_open, + .ndo_stop = dsa_user_close, + .ndo_start_xmit = dsa_user_xmit, + .ndo_change_rx_flags = dsa_user_change_rx_flags, + .ndo_set_rx_mode = dsa_user_set_rx_mode, + .ndo_set_mac_address = dsa_user_set_mac_address, + .ndo_fdb_dump = dsa_user_fdb_dump, + .ndo_eth_ioctl = dsa_user_ioctl, + .ndo_get_iflink = dsa_user_get_iflink, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_netpoll_setup = dsa_user_netpoll_setup, + .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, + .ndo_poll_controller = dsa_user_poll_controller, +#endif + .ndo_setup_tc = dsa_user_setup_tc, + .ndo_get_stats64 = dsa_user_get_stats64, + .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, + .ndo_change_mtu = dsa_user_change_mtu, + .ndo_fill_forward_path = dsa_user_fill_forward_path, + .ndo_hwtstamp_get = dsa_user_hwtstamp_get, + .ndo_hwtstamp_set = dsa_user_hwtstamp_set, +}; + +static const struct device_type dsa_type = { + .name = "dsa", +}; + +void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) +{ + const struct dsa_port *dp = dsa_to_port(ds, port); + + if (dp->pl) + phylink_mac_change(dp->pl, up); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); + +static void dsa_user_phylink_fixed_state(struct phylink_config *config, + struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct dsa_switch *ds = dp->ds; + + /* No need to check that this operation is valid, the callback would + * not be called if it was not. + */ + ds->ops->phylink_fixed_state(ds, dp->index, state); +} + +/* user device setup *******************************************************/ +static int dsa_user_phy_connect(struct net_device *user_dev, int addr, + u32 flags) +{ + struct dsa_port *dp = dsa_user_to_port(user_dev); + struct dsa_switch *ds = dp->ds; + + user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); + if (!user_dev->phydev) { + netdev_err(user_dev, "no phy at %d\n", addr); + return -ENODEV; + } + + user_dev->phydev->dev_flags |= flags; + + return phylink_connect_phy(dp->pl, user_dev->phydev); +} + +static int dsa_user_phy_setup(struct net_device *user_dev) +{ + struct dsa_port *dp = dsa_user_to_port(user_dev); + struct device_node *port_dn = dp->dn; + struct dsa_switch *ds = dp->ds; + u32 phy_flags = 0; + int ret; + + dp->pl_config.dev = &user_dev->dev; + dp->pl_config.type = PHYLINK_NETDEV; + + /* The get_fixed_state callback takes precedence over polling the + * link GPIO in PHYLINK (see phylink_get_fixed_state). Only set + * this if the switch provides such a callback. + */ + if (ds->ops->phylink_fixed_state) { + dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; + dp->pl_config.poll_fixed_state = true; + } + + ret = dsa_port_phylink_create(dp); + if (ret) + return ret; + + if (ds->ops->get_phy_flags) + phy_flags = ds->ops->get_phy_flags(ds, dp->index); + + ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); + if (ret == -ENODEV && ds->user_mii_bus) { + /* We could not connect to a designated PHY or SFP, so try to + * use the switch internal MDIO bus instead + */ + ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); + } + if (ret) { + netdev_err(user_dev, "failed to connect to PHY: %pe\n", + ERR_PTR(ret)); + dsa_port_phylink_destroy(dp); + } + + return ret; +} + +void dsa_user_setup_tagger(struct net_device *user) +{ + struct dsa_port *dp = dsa_user_to_port(user); + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_user_priv *p = netdev_priv(user); + const struct dsa_port *cpu_dp = dp->cpu_dp; + const struct dsa_switch *ds = dp->ds; + + user->needed_headroom = cpu_dp->tag_ops->needed_headroom; + user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; + /* Try to save one extra realloc later in the TX path (in the conduit) + * by also inheriting the conduit's needed headroom and tailroom. + * The 8021q driver also does this. + */ + user->needed_headroom += conduit->needed_headroom; + user->needed_tailroom += conduit->needed_tailroom; + + p->xmit = cpu_dp->tag_ops->xmit; + + user->features = conduit->vlan_features | NETIF_F_HW_TC; + user->hw_features |= NETIF_F_HW_TC; + if (user->needed_tailroom) + user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); + if (ds->needs_standalone_vlan_filtering) + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + + user->lltx = true; +} + +int dsa_user_suspend(struct net_device *user_dev) +{ + struct dsa_port *dp = dsa_user_to_port(user_dev); + + if (!netif_running(user_dev)) + return 0; + + netif_device_detach(user_dev); + + rtnl_lock(); + phylink_stop(dp->pl); + rtnl_unlock(); + + return 0; +} + +int dsa_user_resume(struct net_device *user_dev) +{ + struct dsa_port *dp = dsa_user_to_port(user_dev); + + if (!netif_running(user_dev)) + return 0; + + netif_device_attach(user_dev); + + rtnl_lock(); + phylink_start(dp->pl); + rtnl_unlock(); + + return 0; +} + +int dsa_user_create(struct dsa_port *port) +{ + struct net_device *conduit = dsa_port_to_conduit(port); + struct dsa_switch *ds = port->ds; + struct net_device *user_dev; + struct dsa_user_priv *p; + const char *name; + int assign_type; + int ret; + + if (!ds->num_tx_queues) + ds->num_tx_queues = 1; + + if (port->name) { + name = port->name; + assign_type = NET_NAME_PREDICTABLE; + } else { + name = "eth%d"; + assign_type = NET_NAME_ENUM; + } + + user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, + assign_type, ether_setup, + ds->num_tx_queues, 1); + if (user_dev == NULL) + return -ENOMEM; + + user_dev->rtnl_link_ops = &dsa_link_ops; + user_dev->ethtool_ops = &dsa_user_ethtool_ops; +#if IS_ENABLED(CONFIG_DCB) + user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; +#endif + if (!is_zero_ether_addr(port->mac)) + eth_hw_addr_set(user_dev, port->mac); + else + eth_hw_addr_inherit(user_dev, conduit); + user_dev->priv_flags |= IFF_NO_QUEUE; + if (dsa_switch_supports_uc_filtering(ds)) + user_dev->priv_flags |= IFF_UNICAST_FLT; + user_dev->netdev_ops = &dsa_user_netdev_ops; + if (ds->ops->port_max_mtu) + user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); + SET_NETDEV_DEVTYPE(user_dev, &dsa_type); + + SET_NETDEV_DEV(user_dev, port->ds->dev); + SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); + user_dev->dev.of_node = port->dn; + user_dev->vlan_features = conduit->vlan_features; + + p = netdev_priv(user_dev); + user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + + ret = gro_cells_init(&p->gcells, user_dev); + if (ret) + goto out_free; + + p->dp = port; + INIT_LIST_HEAD(&p->mall_tc_list); + port->user = user_dev; + dsa_user_setup_tagger(user_dev); + + netif_carrier_off(user_dev); + + ret = dsa_user_phy_setup(user_dev); + if (ret) { + netdev_err(user_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; + } + + rtnl_lock(); + + ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); + 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); + + ret = register_netdevice(user_dev); + if (ret) { + netdev_err(conduit, "error %d registering interface %s\n", + ret, user_dev->name); + rtnl_unlock(); + goto out_phy; + } + + if (IS_ENABLED(CONFIG_DCB)) { + ret = dsa_user_dcbnl_init(user_dev); + if (ret) { + netdev_err(user_dev, + "failed to initialize DCB: %pe\n", + ERR_PTR(ret)); + rtnl_unlock(); + goto out_unregister; + } + } + + ret = netdev_upper_dev_link(conduit, user_dev, NULL); + + rtnl_unlock(); + + if (ret) + goto out_unregister; + + return 0; + +out_unregister: + unregister_netdev(user_dev); +out_phy: + rtnl_lock(); + phylink_disconnect_phy(p->dp->pl); + rtnl_unlock(); + dsa_port_phylink_destroy(p->dp); +out_gcells: + gro_cells_destroy(&p->gcells); +out_free: + free_netdev(user_dev); + port->user = NULL; + return ret; +} + +void dsa_user_destroy(struct net_device *user_dev) +{ + struct net_device *conduit = dsa_user_to_conduit(user_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); + struct dsa_user_priv *p = netdev_priv(user_dev); + + netif_carrier_off(user_dev); + rtnl_lock(); + netdev_upper_dev_unlink(conduit, user_dev); + unregister_netdevice(user_dev); + phylink_disconnect_phy(dp->pl); + rtnl_unlock(); + + dsa_port_phylink_destroy(dp); + gro_cells_destroy(&p->gcells); + free_netdev(user_dev); +} + +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, + struct netlink_ext_ack *extack) +{ + struct net_device *old_conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch *ds = dp->ds; + struct net_device *upper; + struct list_head *iter; + int err; + + if (conduit == old_conduit) + return 0; + + if (!ds->ops->port_change_conduit) { + NL_SET_ERR_MSG_MOD(extack, + "Driver does not support changing DSA conduit"); + return -EOPNOTSUPP; + } + + if (!netdev_uses_dsa(conduit)) { + NL_SET_ERR_MSG_MOD(extack, + "Interface not eligible as DSA conduit"); + return -EOPNOTSUPP; + } + + netdev_for_each_upper_dev_rcu(conduit, upper, iter) { + if (dsa_user_dev_check(upper)) + continue; + if (netif_is_bridge_master(upper)) + continue; + NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); + return -EOPNOTSUPP; + } + + /* Since we allow live-changing the DSA conduit, plus we auto-open the + * DSA conduit when the user port opens => we need to ensure that the + * new DSA conduit is open too. + */ + if (dev->flags & IFF_UP) { + err = dev_open(conduit, extack); + if (err) + return err; + } + + netdev_upper_dev_unlink(old_conduit, dev); + + err = netdev_upper_dev_link(conduit, dev, extack); + if (err) + goto out_revert_old_conduit_unlink; + + err = dsa_port_change_conduit(dp, conduit, extack); + if (err) + goto out_revert_conduit_link; + + /* Update the MTU of the new CPU port through cross-chip notifiers */ + err = dsa_user_change_mtu(dev, dev->mtu); + if (err && err != -EOPNOTSUPP) { + netdev_warn(dev, + "nonfatal error updating MTU with new conduit: %pe\n", + ERR_PTR(err)); + } + + return 0; + +out_revert_conduit_link: + netdev_upper_dev_unlink(conduit, dev); +out_revert_old_conduit_unlink: + netdev_upper_dev_link(old_conduit, dev, NULL); + return err; +} + +bool dsa_user_dev_check(const struct net_device *dev) +{ + return dev->netdev_ops == &dsa_user_netdev_ops; +} +EXPORT_SYMBOL_GPL(dsa_user_dev_check); + +static int dsa_user_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct netlink_ext_ack *extack; + int err = NOTIFY_DONE; + struct dsa_port *dp; + + if (!dsa_user_dev_check(dev)) + return err; + + dp = dsa_user_to_port(dev); + extack = netdev_notifier_info_to_extack(&info->info); + + if (netif_is_bridge_master(info->upper_dev)) { + if (info->linking) { + err = dsa_port_bridge_join(dp, info->upper_dev, extack); + if (!err) + dsa_bridge_mtu_normalization(dp); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); + err = 0; + } + err = notifier_from_errno(err); + } else { + 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, extack); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_WEAK_MOD(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, extack); + if (err == -EOPNOTSUPP) { + NL_SET_ERR_MSG_WEAK_MOD(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_user_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp; + + if (!dsa_user_dev_check(dev)) + return NOTIFY_DONE; + + dp = dsa_user_to_port(dev); + + if (netif_is_bridge_master(info->upper_dev) && !info->linking) + dsa_port_pre_bridge_leave(dp, info->upper_dev); + else if (netif_is_lag_master(info->upper_dev) && !info->linking) + dsa_port_pre_lag_leave(dp, info->upper_dev); + /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot + * meaningfully placed under a bridge yet + */ + + return NOTIFY_DONE; +} + +static int +dsa_user_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; + + if (!netif_is_lag_master(dev)) + return err; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_user_dev_check(lower)) + continue; + + dp = dsa_user_to_port(lower); + if (!dp->lag) + /* Software LAG */ + continue; + + err = dsa_user_changeupper(lower, info); + if (notifier_to_errno(err)) + break; + } + + return err; +} + +/* Same as dsa_user_lag_changeupper() except that it calls + * dsa_user_prechangeupper() + */ +static int +dsa_user_lag_prechangeupper(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; + + if (!netif_is_lag_master(dev)) + return err; + + netdev_for_each_lower_dev(dev, lower, iter) { + if (!dsa_user_dev_check(lower)) + continue; + + dp = dsa_user_to_port(lower); + if (!dp->lag) + /* Software LAG */ + continue; + + err = dsa_user_prechangeupper(lower, info); + if (notifier_to_errno(err)) + break; + } + + return err; +} + +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 *user, *br; + struct dsa_port *dp; + + ext_ack = netdev_notifier_info_to_extack(&info->info); + + if (!is_vlan_dev(dev)) + return NOTIFY_DONE; + + user = vlan_dev_real_dev(dev); + if (!dsa_user_dev_check(user)) + return NOTIFY_DONE; + + dp = dsa_user_to_port(user); + br = dsa_port_bridge_dev_get(dp); + if (!br) + return NOTIFY_DONE; + + /* Deny enslaving a VLAN device into a VLAN-aware bridge */ + if (br_vlan_enabled(br) && + netif_is_bridge_master(info->upper_dev) && info->linking) { + NL_SET_ERR_MSG_MOD(ext_ack, + "Cannot make VLAN device join VLAN-aware bridge"); + return notifier_from_errno(-EINVAL); + } + + return NOTIFY_DONE; +} + +static int +dsa_user_check_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + struct net_device *br = dsa_port_bridge_dev_get(dp); + 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_user_prechangeupper_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct dsa_switch *ds; + struct dsa_port *dp; + int err; + + if (!dsa_user_dev_check(dev)) + return dsa_prevent_bridging_8021q_upper(dev, info); + + dp = dsa_user_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_user_check_8021q_upper(dev, info); + + return NOTIFY_DONE; +} + +/* To be eligible as a DSA conduit, a LAG must have all lower interfaces be + * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of + * switches in the same switch tree. + */ +static int dsa_lag_conduit_validate(struct net_device *lag_dev, + struct netlink_ext_ack *extack) +{ + struct net_device *lower1, *lower2; + struct list_head *iter1, *iter2; + + netdev_for_each_lower_dev(lag_dev, lower1, iter1) { + netdev_for_each_lower_dev(lag_dev, lower2, iter2) { + if (!netdev_uses_dsa(lower1) || + !netdev_uses_dsa(lower2)) { + NL_SET_ERR_MSG_MOD(extack, + "All LAG ports must be eligible as DSA conduits"); + return notifier_from_errno(-EINVAL); + } + + if (lower1 == lower2) + continue; + + if (!dsa_port_tree_same(lower1->dsa_ptr, + lower2->dsa_ptr)) { + NL_SET_ERR_MSG_MOD(extack, + "LAG contains DSA conduits of disjoint switch trees"); + return notifier_from_errno(-EINVAL); + } + } + } + + return NOTIFY_DONE; +} + +static int +dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, + struct netdev_notifier_changeupper_info *info) +{ + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); + + if (!netdev_uses_dsa(conduit)) + return NOTIFY_DONE; + + if (!info->linking) + return NOTIFY_DONE; + + /* Allow DSA switch uppers */ + if (dsa_user_dev_check(info->upper_dev)) + return NOTIFY_DONE; + + /* Allow bridge uppers of DSA conduits, subject to further + * restrictions in dsa_bridge_prechangelower_sanity_check() + */ + if (netif_is_bridge_master(info->upper_dev)) + return NOTIFY_DONE; + + /* Allow LAG uppers, subject to further restrictions in + * dsa_lag_conduit_prechangelower_sanity_check() + */ + if (netif_is_lag_master(info->upper_dev)) + return dsa_lag_conduit_validate(info->upper_dev, extack); + + NL_SET_ERR_MSG_MOD(extack, + "DSA conduit cannot join unknown upper interfaces"); + return notifier_from_errno(-EBUSY); +} + +static int +dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); + struct net_device *lag_dev = info->upper_dev; + struct net_device *lower; + struct list_head *iter; + + if (!netdev_uses_dsa(lag_dev) || !netif_is_lag_master(lag_dev)) + return NOTIFY_DONE; + + if (!info->linking) + return NOTIFY_DONE; + + if (!netdev_uses_dsa(dev)) { + NL_SET_ERR_MSG(extack, + "Only DSA conduits can join a LAG DSA conduit"); + return notifier_from_errno(-EINVAL); + } + + netdev_for_each_lower_dev(lag_dev, lower, iter) { + if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { + NL_SET_ERR_MSG(extack, + "Interface is DSA conduit for a different switch tree than this LAG"); + return notifier_from_errno(-EINVAL); + } + + break; + } + + return NOTIFY_DONE; +} + +/* Don't allow bridging of DSA conduits, since the bridge layer rx_handler + * prevents the DSA fake ethertype handler to be invoked, so we don't get the + * chance to strip off and parse the DSA switch tag protocol header (the bridge + * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these + * frames). + * The only case where that would not be an issue is when bridging can already + * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev + * port, and is bridged only with other ports from the same hardware device. + */ +static int +dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *br = info->upper_dev; + struct netlink_ext_ack *extack; + struct net_device *lower; + struct list_head *iter; + + if (!netif_is_bridge_master(br)) + return NOTIFY_DONE; + + if (!info->linking) + return NOTIFY_DONE; + + extack = netdev_notifier_info_to_extack(&info->info); + + netdev_for_each_lower_dev(br, lower, iter) { + if (!netdev_uses_dsa(new_lower) && !netdev_uses_dsa(lower)) + continue; + + if (!netdev_port_same_parent_id(lower, new_lower)) { + NL_SET_ERR_MSG(extack, + "Cannot do software bridging with a DSA conduit"); + return notifier_from_errno(-EINVAL); + } + } + + return NOTIFY_DONE; +} + +static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, + struct net_device *lag_dev) +{ + struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); + struct dsa_port *dp; + int err; + + dsa_tree_for_each_user_port(dp, dst) { + if (dsa_port_to_conduit(dp) != lag_dev) + continue; + + err = dsa_user_change_conduit(dp->user, new_conduit, NULL); + if (err) { + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + new_conduit->name, ERR_PTR(err)); + } + } +} + +static int dsa_conduit_lag_join(struct net_device *conduit, + struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) +{ + struct dsa_port *cpu_dp = conduit->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_port *dp; + int err; + + err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); + if (err) + return err; + + dsa_tree_for_each_user_port(dp, dst) { + if (dsa_port_to_conduit(dp) != conduit) + continue; + + err = dsa_user_change_conduit(dp->user, lag_dev, extack); + if (err) + goto restore; + } + + return 0; + +restore: + dsa_tree_for_each_user_port_continue_reverse(dp, dst) { + if (dsa_port_to_conduit(dp) != lag_dev) + continue; + + err = dsa_user_change_conduit(dp->user, conduit, NULL); + if (err) { + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + conduit->name, ERR_PTR(err)); + } + } + + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); + + return err; +} + +static void dsa_conduit_lag_leave(struct net_device *conduit, + struct net_device *lag_dev) +{ + struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->dst; + struct dsa_port *new_cpu_dp = NULL; + struct net_device *lower; + struct list_head *iter; + + netdev_for_each_lower_dev(lag_dev, lower, iter) { + if (netdev_uses_dsa(lower)) { + new_cpu_dp = lower->dsa_ptr; + break; + } + } + + if (new_cpu_dp) { + /* Update the CPU port of the user ports still under the LAG + * so that dsa_port_to_conduit() continues to work properly + */ + dsa_tree_for_each_user_port(dp, dst) + if (dsa_port_to_conduit(dp) == lag_dev) + dp->cpu_dp = new_cpu_dp; + + /* Update the index of the virtual CPU port to match the lowest + * physical CPU port + */ + lag_dev->dsa_ptr = new_cpu_dp; + wmb(); + } else { + /* If the LAG DSA conduit has no ports left, migrate back all + * user ports to the first physical CPU port + */ + dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); + } + + /* This DSA conduit has left its LAG in any case, so let + * the CPU port leave the hardware LAG as well + */ + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); +} + +static int dsa_conduit_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) +{ + struct netlink_ext_ack *extack; + int err = NOTIFY_DONE; + + if (!netdev_uses_dsa(dev)) + return err; + + extack = netdev_notifier_info_to_extack(&info->info); + + if (netif_is_lag_master(info->upper_dev)) { + if (info->linking) { + err = dsa_conduit_lag_join(dev, info->upper_dev, + info->upper_info, extack); + err = notifier_from_errno(err); + } else { + dsa_conduit_lag_leave(dev, info->upper_dev); + err = NOTIFY_OK; + } + } + + return err; +} + +static int dsa_user_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_PRECHANGEUPPER: { + struct netdev_notifier_changeupper_info *info = ptr; + int err; + + err = dsa_user_prechangeupper_sanity_check(dev, info); + if (notifier_to_errno(err)) + return err; + + err = dsa_conduit_prechangeupper_sanity_check(dev, info); + if (notifier_to_errno(err)) + return err; + + err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); + if (notifier_to_errno(err)) + return err; + + err = dsa_bridge_prechangelower_sanity_check(dev, info); + if (notifier_to_errno(err)) + return err; + + err = dsa_user_prechangeupper(dev, ptr); + if (notifier_to_errno(err)) + return err; + + err = dsa_user_lag_prechangeupper(dev, ptr); + if (notifier_to_errno(err)) + return err; + + break; + } + case NETDEV_CHANGEUPPER: { + int err; + + err = dsa_user_changeupper(dev, ptr); + if (notifier_to_errno(err)) + return err; + + err = dsa_user_lag_changeupper(dev, ptr); + if (notifier_to_errno(err)) + return err; + + err = dsa_conduit_changeupper(dev, ptr); + if (notifier_to_errno(err)) + return err; + + break; + } + case NETDEV_CHANGELOWERSTATE: { + struct netdev_notifier_changelowerstate_info *info = ptr; + struct dsa_port *dp; + int err = 0; + + if (dsa_user_dev_check(dev)) { + dp = dsa_user_to_port(dev); + + err = dsa_port_lag_change(dp, info->lower_state_info); + } + + /* Mirror LAG port events on DSA conduits that are in + * a LAG towards their respective switch CPU ports + */ + if (netdev_uses_dsa(dev)) { + dp = dev->dsa_ptr; + + err = dsa_port_lag_change(dp, info->lower_state_info); + } + + return notifier_from_errno(err); + } + case NETDEV_CHANGE: + case NETDEV_UP: { + /* Track state of conduit port. + * DSA driver may require the conduit port (and indirectly + * the tagger) to be available for some special operation. + */ + if (netdev_uses_dsa(dev)) { + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch_tree *dst = cpu_dp->ds->dst; + + /* Track when the conduit port is UP */ + dsa_tree_conduit_oper_state_change(dst, dev, + netif_oper_up(dev)); + + /* Track when the conduit port is ready and can accept + * packet. + * NETDEV_UP event is not enough to flag a port as ready. + * We also have to wait for linkwatch_do_dev to dev_activate + * and emit a NETDEV_CHANGE event. + * We check if a conduit port is ready by checking if the dev + * have a qdisc assigned and is not noop. + */ + dsa_tree_conduit_admin_state_change(dst, dev, + !qdisc_tx_is_noop(dev)); + + return NOTIFY_OK; + } + + return NOTIFY_DONE; + } + 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; + + dsa_tree_conduit_admin_state_change(dst, dev, false); + + list_for_each_entry(dp, &dst->ports, list) { + if (!dsa_port_is_user(dp)) + continue; + + if (dp->cpu_dp != cpu_dp) + continue; + + list_add(&dp->user->close_list, &close_list); + } + + netif_close_many(&close_list, true); + + return NOTIFY_OK; + } + default: + break; + } + + return NOTIFY_DONE; +} + +static void +dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) +{ + struct switchdev_notifier_fdb_info info = {}; + + info.addr = switchdev_work->addr; + info.vid = switchdev_work->vid; + info.offloaded = true; + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, + switchdev_work->orig_dev, &info.info, NULL); +} + +static void dsa_user_switchdev_event_work(struct work_struct *work) +{ + struct dsa_switchdev_event_work *switchdev_work = + container_of(work, struct dsa_switchdev_event_work, work); + const unsigned char *addr = switchdev_work->addr; + struct net_device *dev = switchdev_work->dev; + u16 vid = switchdev_work->vid; + struct dsa_switch *ds; + struct dsa_port *dp; + int err; + + dp = dsa_user_to_port(dev); + ds = dp->ds; + + switch (switchdev_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + if (switchdev_work->host_addr) + err = dsa_port_bridge_host_fdb_add(dp, addr, vid); + else if (dp->lag) + err = dsa_port_lag_fdb_add(dp, addr, vid); + else + err = dsa_port_fdb_add(dp, addr, vid); + if (err) { + dev_err(ds->dev, + "port %d failed to add %pM vid %d to fdb: %d\n", + dp->index, addr, vid, err); + break; + } + dsa_fdb_offload_notify(switchdev_work); + break; + + case SWITCHDEV_FDB_DEL_TO_DEVICE: + if (switchdev_work->host_addr) + err = dsa_port_bridge_host_fdb_del(dp, addr, vid); + else if (dp->lag) + err = dsa_port_lag_fdb_del(dp, addr, vid); + else + err = dsa_port_fdb_del(dp, addr, vid); + if (err) { + dev_err(ds->dev, + "port %d failed to delete %pM vid %d from fdb: %d\n", + dp->index, addr, vid, err); + } + + break; + } + + kfree(switchdev_work); +} + +static bool dsa_foreign_dev_check(const struct net_device *dev, + const struct net_device *foreign_dev) +{ + const struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_switch_tree *dst = dp->ds->dst; + + if (netif_is_bridge_master(foreign_dev)) + return !dsa_tree_offloads_bridge_dev(dst, foreign_dev); + + if (netif_is_bridge_port(foreign_dev)) + return !dsa_tree_offloads_bridge_port(dst, foreign_dev); + + /* Everything else is foreign */ + return true; +} + +static int dsa_user_fdb_event(struct net_device *dev, + struct net_device *orig_dev, + unsigned long event, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info) +{ + struct dsa_switchdev_event_work *switchdev_work; + struct dsa_port *dp = dsa_user_to_port(dev); + bool host_addr = fdb_info->is_local; + struct dsa_switch *ds = dp->ds; + + if (ctx && ctx != dp) + return 0; + + if (!dp->bridge) + return 0; + + if (switchdev_fdb_is_dynamically_learned(fdb_info)) { + if (dsa_port_offloads_bridge_port(dp, orig_dev)) + return 0; + + /* FDB entries learned by the software bridge or by foreign + * bridge ports should be installed as host addresses only if + * the driver requests assisted learning. + */ + if (!ds->assisted_learning_on_cpu_port) + return 0; + } + + /* Also treat FDB entries on foreign interfaces bridged with us as host + * addresses. + */ + if (dsa_foreign_dev_check(dev, orig_dev)) + host_addr = true; + + /* Check early that we're not doing work in vain. + * Host addresses on LAG ports still require regular FDB ops, + * since the CPU port isn't in a LAG. + */ + if (dp->lag && !host_addr) { + if (!ds->ops->lag_fdb_add || !ds->ops->lag_fdb_del) + return -EOPNOTSUPP; + } else { + if (!ds->ops->port_fdb_add || !ds->ops->port_fdb_del) + return -EOPNOTSUPP; + } + + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (!switchdev_work) + return -ENOMEM; + + netdev_dbg(dev, "%s FDB entry towards %s, addr %pM vid %d%s\n", + event == SWITCHDEV_FDB_ADD_TO_DEVICE ? "Adding" : "Deleting", + orig_dev->name, fdb_info->addr, fdb_info->vid, + host_addr ? " as host address" : ""); + + INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); + switchdev_work->event = event; + switchdev_work->dev = dev; + switchdev_work->orig_dev = orig_dev; + + ether_addr_copy(switchdev_work->addr, fdb_info->addr); + switchdev_work->vid = fdb_info->vid; + switchdev_work->host_addr = host_addr; + + dsa_schedule_work(&switchdev_work->work); + + return 0; +} + +/* Called under rcu_read_lock() */ +static int dsa_user_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + dsa_user_dev_check, + dsa_user_port_attr_set); + return notifier_from_errno(err); + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + err = switchdev_handle_fdb_event_to_device(dev, event, ptr, + dsa_user_dev_check, + dsa_foreign_dev_check, + dsa_user_fdb_event); + return notifier_from_errno(err); + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add_foreign(dev, ptr, + dsa_user_dev_check, + dsa_foreign_dev_check, + dsa_user_port_obj_add); + return notifier_from_errno(err); + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del_foreign(dev, ptr, + dsa_user_dev_check, + dsa_foreign_dev_check, + dsa_user_port_obj_del); + return notifier_from_errno(err); + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set(dev, ptr, + dsa_user_dev_check, + dsa_user_port_attr_set); + return notifier_from_errno(err); + } + + return NOTIFY_DONE; +} + +static struct notifier_block dsa_user_nb __read_mostly = { + .notifier_call = dsa_user_netdevice_event, +}; + +struct notifier_block dsa_user_switchdev_notifier = { + .notifier_call = dsa_user_switchdev_event, +}; + +struct notifier_block dsa_user_switchdev_blocking_notifier = { + .notifier_call = dsa_user_switchdev_blocking_event, +}; + +int dsa_user_register_notifier(void) +{ + struct notifier_block *nb; + int err; + + err = register_netdevice_notifier(&dsa_user_nb); + if (err) + return err; + + err = register_switchdev_notifier(&dsa_user_switchdev_notifier); + if (err) + goto err_switchdev_nb; + + nb = &dsa_user_switchdev_blocking_notifier; + err = register_switchdev_blocking_notifier(nb); + if (err) + goto err_switchdev_blocking_nb; + + return 0; + +err_switchdev_blocking_nb: + unregister_switchdev_notifier(&dsa_user_switchdev_notifier); +err_switchdev_nb: + unregister_netdevice_notifier(&dsa_user_nb); + return err; +} + +void dsa_user_unregister_notifier(void) +{ + struct notifier_block *nb; + int err; + + nb = &dsa_user_switchdev_blocking_notifier; + err = unregister_switchdev_blocking_notifier(nb); + if (err) + pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); + + err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); + if (err) + pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); + + err = unregister_netdevice_notifier(&dsa_user_nb); + if (err) + pr_err("DSA: failed to unregister user notifier (%d)\n", err); +} diff --git a/net/dsa/user.h b/net/dsa/user.h new file mode 100644 index 000000000000..016884bead3c --- /dev/null +++ b/net/dsa/user.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_USER_H +#define __DSA_USER_H + +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/netpoll.h> +#include <linux/types.h> +#include <net/dsa.h> +#include <net/gro_cells.h> + +struct net_device; +struct netlink_ext_ack; + +extern struct notifier_block dsa_user_switchdev_notifier; +extern struct notifier_block dsa_user_switchdev_blocking_notifier; + +struct dsa_user_priv { + /* Copy of CPU port xmit for faster access in user transmit hot path */ + struct sk_buff * (*xmit)(struct sk_buff *skb, + struct net_device *dev); + + struct gro_cells gcells; + + /* DSA port data, such as switch, port index, etc. */ + struct dsa_port *dp; + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif + + /* TC context */ + struct list_head mall_tc_list; +}; + +void dsa_user_mii_bus_init(struct dsa_switch *ds); +int dsa_user_create(struct dsa_port *dp); +void dsa_user_destroy(struct net_device *user_dev); +int dsa_user_suspend(struct net_device *user_dev); +int dsa_user_resume(struct net_device *user_dev); +int dsa_user_register_notifier(void); +void dsa_user_unregister_notifier(void); +int dsa_user_host_uc_install(struct net_device *dev, const u8 *addr); +void dsa_user_host_uc_uninstall(struct net_device *dev); +void dsa_user_sync_ha(struct net_device *dev); +void dsa_user_unsync_ha(struct net_device *dev); +void dsa_user_setup_tagger(struct net_device *user); +int dsa_user_change_mtu(struct net_device *dev, int new_mtu); +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, + struct netlink_ext_ack *extack); +int dsa_user_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); + +static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_user_to_conduit(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return dsa_port_to_conduit(dp); +} + +#endif |