diff options
| author | Mark Brown <broonie@kernel.org> | 2026-07-03 15:44:28 +0100 |
|---|---|---|
| committer | Mark Brown <broonie@kernel.org> | 2026-07-03 15:44:28 +0100 |
| commit | 5f9618618bce70008bcfb142e5502f111ddeb72c (patch) | |
| tree | 93fae2a33bc02a4fdb59209ce6af56edeaf3ceb6 | |
| parent | a7d435fd4c2f7e42117f5f31c3c40010b12d855a (diff) | |
| parent | 6fb33632323a396c9dc2bb9bea483e013e547d57 (diff) | |
| download | linux-next-5f9618618bce70008bcfb142e5502f111ddeb72c.tar.gz linux-next-5f9618618bce70008bcfb142e5502f111ddeb72c.zip | |
Merge branch 'main' of https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
# Conflicts:
# MAINTAINERS
95 files changed, 2200 insertions, 7979 deletions
diff --git a/Documentation/netlink/specs/rt-addr.yaml b/Documentation/netlink/specs/rt-addr.yaml index 163a106c41bb..0ecbd24c890c 100644 --- a/Documentation/netlink/specs/rt-addr.yaml +++ b/Documentation/netlink/specs/rt-addr.yaml @@ -123,6 +123,9 @@ attribute-sets: - name: proto type: u8 + - + name: mc-users + type: u32 operations: @@ -176,6 +179,7 @@ operations: value: 58 attributes: &mcaddr-attrs - multicast + - mc-users - cacheinfo dump: request: diff --git a/MAINTAINERS b/MAINTAINERS index 3635163e31ce..8e2551fd5cba 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9495,11 +9495,6 @@ L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/fbdev/efifb.c -EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER -L: netdev@vger.kernel.org -S: Orphan -F: drivers/net/ethernet/ibm/ehea/ - ELM327 CAN NETWORK DRIVER M: Max Staudt <max@enpas.org> L: linux-can@vger.kernel.org diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index f795b74602ec..1eb8e3457e8b 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -210,7 +210,6 @@ CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m CONFIG_BE2NET=m CONFIG_IBMVETH=m -CONFIG_EHEA=m CONFIG_IBMVNIC=m CONFIG_E100=y CONFIG_E1000=y diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 4c1afab91996..b617b69452cd 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -371,12 +371,6 @@ int devmem_is_allowed(unsigned long pfn) } #endif /* CONFIG_STRICT_DEVMEM */ -/* - * This is defined in kernel/resource.c but only powerpc needs to export it, for - * the EHEA driver. Drop this when drivers/net/ethernet/ibm/ehea is removed. - */ -EXPORT_SYMBOL_GPL(walk_system_ram_range); - #ifdef CONFIG_EXECMEM static struct execmem_info execmem_info __ro_after_init; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index acbba08dbdfa..b8e4b4d68dd6 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -760,14 +760,14 @@ static int __agg_usable_ports(struct aggregator *agg) return valid; } -static int __agg_active_ports(struct aggregator *agg) +static int __agg_active_ports(const struct aggregator *agg) { - struct port *port; + const struct port *port; int active = 0; for (port = agg->lag_ports; port; port = port->next_port_in_aggregator) { - if (port->is_enabled) + if (READ_ONCE(port->is_enabled)) active++; } @@ -2801,11 +2801,11 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) * some of he adaptors(ce1000.lan) report. */ if (link == BOND_LINK_UP) { - port->is_enabled = true; + WRITE_ONCE(port->is_enabled, true); ad_update_actor_keys(port, false); } else { /* link has failed */ - port->is_enabled = false; + WRITE_ONCE(port->is_enabled, false); ad_update_actor_keys(port, true); } agg = __get_first_agg(port); @@ -2878,16 +2878,20 @@ out: * Returns: 0 on success * < 0 on error */ -int __bond_3ad_get_active_agg_info(struct bonding *bond, +int __bond_3ad_get_active_agg_info(const struct bonding *bond, struct ad_info *ad_info) { - struct aggregator *aggregator = NULL, *tmp; + const struct aggregator *aggregator = NULL, *tmp; + struct ad_slave_info *ad_slave_info; + const struct port *port; struct list_head *iter; struct slave *slave; - struct port *port; bond_for_each_slave_rcu(bond, slave, iter) { - port = &(SLAVE_AD_INFO(slave)->port); + ad_slave_info = SLAVE_AD_INFO(slave); + if (!ad_slave_info) + continue; + port = &ad_slave_info->port; tmp = rcu_dereference(port->aggregator); if (tmp && tmp->is_active) { aggregator = tmp; @@ -2907,7 +2911,7 @@ int __bond_3ad_get_active_agg_info(struct bonding *bond, return 0; } -int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info) +int bond_3ad_get_active_agg_info(const struct bonding *bond, struct ad_info *ad_info) { int ret; diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 4a11572f663d..55d2f8a539d4 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -686,53 +686,58 @@ static size_t bond_get_size(const struct net_device *bond_dev) 0; } -static int bond_option_active_slave_get_ifindex(struct bonding *bond) +static int bond_option_active_slave_get_ifindex_rcu(const struct bonding *bond) { - const struct net_device *slave; - int ifindex; + const struct net_device *dev = NULL; + const struct slave *slave; - rcu_read_lock(); - slave = bond_option_active_slave_get_rcu(bond); - ifindex = slave ? slave->ifindex : 0; - rcu_read_unlock(); - return ifindex; + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + dev = slave->dev; + return dev ? dev->ifindex : 0; } static int bond_fill_info(struct sk_buff *skb, const struct net_device *bond_dev) { - struct bonding *bond = netdev_priv(bond_dev); - unsigned int packets_per_slave; - int ifindex, i, targets_added; + const struct bonding *bond = netdev_priv(bond_dev); + int i, targets_added, miimon, mode; + const struct slave *primary; struct nlattr *targets; - struct slave *primary; - if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond))) + rcu_read_lock(); + mode = READ_ONCE(bond->params.mode); + if (nla_put_u8(skb, IFLA_BOND_MODE, mode)) goto nla_put_failure; - ifindex = bond_option_active_slave_get_ifindex(bond); - if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex)) - goto nla_put_failure; + if (bond_mode_uses_primary(mode)) { + int ifindex = bond_option_active_slave_get_ifindex_rcu(bond); + + if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex)) + goto nla_put_failure; + } - if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon)) + miimon = READ_ONCE(bond->params.miimon); + if (nla_put_u32(skb, IFLA_BOND_MIIMON, miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_UPDELAY, - bond->params.updelay * bond->params.miimon)) + READ_ONCE(bond->params.updelay) * miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, - bond->params.downdelay * bond->params.miimon)) + READ_ONCE(bond->params.downdelay) * miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_PEER_NOTIF_DELAY, - bond->params.peer_notif_delay * bond->params.miimon)) + READ_ONCE(bond->params.peer_notif_delay) * miimon)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, 1)) goto nla_put_failure; - if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) + if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, + READ_ONCE(bond->params.arp_interval))) goto nla_put_failure; targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET); @@ -741,8 +746,10 @@ static int bond_fill_info(struct sk_buff *skb, targets_added = 0; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { - if (bond->params.arp_targets[i]) { - if (nla_put_be32(skb, i, bond->params.arp_targets[i])) + __be32 t = READ_ONCE(bond->params.arp_targets[i]); + + if (t) { + if (nla_put_be32(skb, i, t)) goto nla_put_failure; targets_added = 1; } @@ -753,11 +760,12 @@ static int bond_fill_info(struct sk_buff *skb, else nla_nest_cancel(skb, targets); - if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate)) + if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, + READ_ONCE(bond->params.arp_validate))) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS, - bond->params.arp_all_targets)) + READ_ONCE(bond->params.arp_all_targets))) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) @@ -767,6 +775,9 @@ static int bond_fill_info(struct sk_buff *skb, targets_added = 0; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + /* Note: IPv6 addresses can not be read in an atomic READ_ONCE() yet. + * We accept this minor race for the moment. + */ if (!ipv6_addr_any(&bond->params.ns_targets[i])) { if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i])) goto nla_put_failure; @@ -780,97 +791,97 @@ static int bond_fill_info(struct sk_buff *skb, nla_nest_cancel(skb, targets); #endif - primary = rtnl_dereference(bond->primary_slave); + primary = rcu_dereference(bond->primary_slave); if (primary && nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT, - bond->params.primary_reselect)) + READ_ONCE(bond->params.primary_reselect))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC, - bond->params.fail_over_mac)) + READ_ONCE(bond->params.fail_over_mac))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY, - bond->params.xmit_policy)) + READ_ONCE(bond->params.xmit_policy))) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP, - bond->params.resend_igmp)) + READ_ONCE(bond->params.resend_igmp))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF, - bond->params.num_peer_notif)) + READ_ONCE(bond->params.num_peer_notif))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE, - bond->params.all_slaves_active)) + READ_ONCE(bond->params.all_slaves_active))) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS, - bond->params.min_links)) + READ_ONCE(bond->params.min_links))) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL, - bond->params.lp_interval)) + READ_ONCE(bond->params.lp_interval))) goto nla_put_failure; - packets_per_slave = bond->params.packets_per_slave; if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE, - packets_per_slave)) + READ_ONCE(bond->params.packets_per_slave))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE, - bond->params.lacp_active)) + READ_ONCE(bond->params.lacp_active))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE, - bond->params.lacp_fast)) + READ_ONCE(bond->params.lacp_fast))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_SELECT, - bond->params.ad_select)) + READ_ONCE(bond->params.ad_select))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_TLB_DYNAMIC_LB, - bond->params.tlb_dynamic_lb)) + READ_ONCE(bond->params.tlb_dynamic_lb))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX, - bond->params.missed_max)) + READ_ONCE(bond->params.missed_max))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL, - bond->params.coupled_control)) + READ_ONCE(bond->params.coupled_control))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH, - bond->params.broadcast_neighbor)) + READ_ONCE(bond->params.broadcast_neighbor))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_LACP_STRICT, - bond->params.lacp_strict)) + READ_ONCE(bond->params.lacp_strict))) goto nla_put_failure; - if (BOND_MODE(bond) == BOND_MODE_8023AD) { + if (mode == BOND_MODE_8023AD) { struct ad_info info; if (capable(CAP_NET_ADMIN)) { if (nla_put_u16(skb, IFLA_BOND_AD_ACTOR_SYS_PRIO, - bond->params.ad_actor_sys_prio)) + READ_ONCE(bond->params.ad_actor_sys_prio))) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_USER_PORT_KEY, - bond->params.ad_user_port_key)) + READ_ONCE(bond->params.ad_user_port_key))) goto nla_put_failure; + /* Small race here, this is a minor trade off. */ if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM, ETH_ALEN, &bond->params.ad_actor_system)) goto nla_put_failure; } - if (!bond_3ad_get_active_agg_info(bond, &info)) { + if (!__bond_3ad_get_active_agg_info(bond, &info)) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO); @@ -898,9 +909,11 @@ static int bond_fill_info(struct sk_buff *skb, } } + rcu_read_unlock(); return 0; nla_put_failure: + rcu_read_unlock(); return -EMSGSIZE; } diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index e590c8dee86e..36b8d89387ee 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -934,14 +934,14 @@ static int bond_option_mode_set(struct bonding *bond, /* don't cache arp_validate between modes */ WRITE_ONCE(bond->params.arp_validate, BOND_ARP_VALIDATE_NONE); - bond->params.mode = newval->value; + WRITE_ONCE(bond->params.mode, newval->value); /* When changing mode, the bond device is down, we may reduce * the bond_bcast_neigh_enabled in bond_close() if broadcast_neighbor * enabled in 8023ad mode. Therefore, only clear broadcast_neighbor * to 0. */ - bond->params.broadcast_neighbor = 0; + WRITE_ONCE(bond->params.broadcast_neighbor, 0); if (bond->dev->reg_state == NETREG_REGISTERED) { bool update = false; @@ -1706,7 +1706,7 @@ static int bond_option_lacp_strict_set(struct bonding *bond, { netdev_dbg(bond->dev, "Setting LACP fallback to %s (%llu)\n", newval->string, newval->value); - bond->params.lacp_strict = newval->value; + WRITE_ONCE(bond->params.lacp_strict, newval->value); bond_3ad_set_carrier(bond); return 0; @@ -1927,7 +1927,7 @@ static int bond_option_broadcast_neigh_set(struct bonding *bond, if (bond->params.broadcast_neighbor == newval->value) return 0; - bond->params.broadcast_neighbor = newval->value; + WRITE_ONCE(bond->params.broadcast_neighbor, newval->value); if (bond->dev->flags & IFF_UP) { if (bond->params.broadcast_neighbor) static_branch_inc(&bond_bcast_neigh_enabled); diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index cd27a7344e89..29cca7945df7 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -23,6 +23,7 @@ #include <linux/mutex.h> #include <linux/phylink.h> #include <linux/etherdevice.h> +#include <linux/gpio/consumer.h> #include <net/dsa.h> #include "b53_regs.h" @@ -467,7 +468,7 @@ static inline void b53_arl_search_read(struct b53_device *dev, u8 idx, #ifdef CONFIG_BCM47XX #include <linux/bcm47xx_nvram.h> -#include <linux/gpio.h> +#include <linux/gpio/legacy.h> #include <bcm47xx_board.h> static inline struct gpio_desc *b53_switch_get_reset_gpio(struct b53_device *dev) { diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c index 138f2ab0774e..586916570a84 100644 --- a/drivers/net/dsa/microchip/ksz8.c +++ b/drivers/net/dsa/microchip/ksz8.c @@ -18,7 +18,7 @@ #include <linux/delay.h> #include <linux/dsa/ksz_common.h> #include <linux/export.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/if_vlan.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c index ef496e345a4e..0ada28377f46 100644 --- a/drivers/net/dsa/qca/qca8k-leds.c +++ b/drivers/net/dsa/qca/qca8k-leds.c @@ -457,6 +457,9 @@ qca8k_setup_led_ctrl(struct qca8k_priv *priv) int ret; ports = device_get_named_child_node(priv->dev, "ports"); + if (!ports) + ports = device_get_named_child_node(priv->dev, "ethernet-ports"); + if (!ports) { dev_info(priv->dev, "No ports node specified in device tree!"); return 0; diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c index 103039fe3086..d2fa8ff6a5d0 100644 --- a/drivers/net/dsa/realtek/rtl8366rb.c +++ b/drivers/net/dsa/realtek/rtl8366rb.c @@ -791,11 +791,87 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv) return ret; } +static int rtl8366rb_port_set_isolation(struct realtek_priv *priv, int port, + u32 mask) +{ + /* Bit 0 enables isolation so set this if we enable isolation + * any of the ports an clear it if we disable on all of them. + */ + if (mask) + mask = RTL8366RB_PORT_ISO_PORTS(mask) | RTL8366RB_PORT_ISO_EN; + + return regmap_write(priv->map, RTL8366RB_PORT_ISO(port), + mask); +} + +static int rtl8366rb_port_add_isolation(struct realtek_priv *priv, int port, + u32 mask) +{ + /* We assume isolation bit is on */ + return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), + RTL8366RB_PORT_ISO_PORTS(mask), + RTL8366RB_PORT_ISO_PORTS(mask)); +} + +static int rtl8366rb_port_remove_isolation(struct realtek_priv *priv, int port, + u32 mask) +{ + return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), + RTL8366RB_PORT_ISO_PORTS(mask), 0); +} + +static void +rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) +{ + struct realtek_priv *priv = ds->priv; + u32 val; + int i; + + switch (state) { + case BR_STATE_DISABLED: + val = RTL8366RB_STP_STATE_DISABLED; + break; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + val = RTL8366RB_STP_STATE_BLOCKING; + break; + case BR_STATE_LEARNING: + val = RTL8366RB_STP_STATE_LEARNING; + break; + case BR_STATE_FORWARDING: + val = RTL8366RB_STP_STATE_FORWARDING; + break; + default: + dev_err(priv->dev, "unknown bridge state requested\n"); + return; + } + + /* Set the same status for the port on all the FIDs */ + for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { + regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i, + RTL8366RB_STP_STATE_MASK(port), + RTL8366RB_STP_STATE(port, val)); + } +} + +static int rtl8366rb_port_set_learning(struct realtek_priv *priv, int port, + bool enable) +{ + /* Notice inverted semantics in this register: setting a bit disables + * learning instead of enabling it. + */ + return regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, + BIT(port), enable ? 0 : BIT(port)); +} + static int rtl8366rb_setup(struct dsa_switch *ds) { struct realtek_priv *priv = ds->priv; const struct rtl8366rb_jam_tbl_entry *jam_table; + u32 downports_mask = 0; struct rtl8366rb *rb; + u32 upports_mask = 0; + struct dsa_port *dp; u32 chip_ver = 0; u32 chip_id = 0; int jam_size; @@ -866,20 +942,58 @@ static int rtl8366rb_setup(struct dsa_switch *ds) if (ret) return ret; - /* Isolate all user ports so they can only send packets to itself and the CPU port */ - for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { - ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(i), - RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) | - RTL8366RB_PORT_ISO_EN); + /* Start with all ports blocked, including unused ports */ + dsa_switch_for_each_port(dp, ds) { + /* Set the initial STP state of all ports to DISABLED, otherwise + * ports will still forward frames to the CPU despite being + * administratively down by default. + */ + rtl8366rb_port_stp_state_set(ds, dp->index, BR_STATE_DISABLED); + + /* Start with all ports completely isolated */ + ret = rtl8366rb_port_set_isolation(priv, dp->index, 0); + if (ret) + return ret; + + /* Disable learning */ + ret = rtl8366rb_port_set_learning(priv, dp->index, false); + if (ret) + return ret; + + /* Collect CPU ports. If we support cascade switches, it should + * also include the upstream DSA ports. + */ + if (!dsa_port_is_cpu(dp)) + continue; + + upports_mask |= BIT(dp->index); + } + + /* Configure user ports */ + dsa_switch_for_each_port(dp, ds) { + if (!dsa_port_is_user(dp)) + continue; + + /* Forward only to the CPU */ + ret = rtl8366rb_port_set_isolation(priv, dp->index, upports_mask); + if (ret) + return ret; + + /* If we support cascade switches, it should also include the + * downstream DSA ports. + */ + downports_mask |= BIT(dp->index); + } + + /* Configure CPU ports. If we support cascade switches, this will also + * include DSA ports. + */ + dsa_switch_for_each_cpu_port(dp, ds) { + /* Forward to all user ports */ + ret = rtl8366rb_port_set_isolation(priv, dp->index, downports_mask); if (ret) return ret; } - /* CPU port can send packets to all ports */ - ret = regmap_write(priv->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), - RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) | - RTL8366RB_PORT_ISO_EN); - if (ret) - return ret; /* Set up the "green ethernet" feature */ ret = rtl8366rb_jam_table(rtl8366rb_green_jam, @@ -938,12 +1052,6 @@ static int rtl8366rb_setup(struct dsa_switch *ds) rb->max_mtu[i] = ETH_DATA_LEN; } - /* Disable learning for all ports */ - ret = regmap_write(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, - RTL8366RB_PORT_ALL); - if (ret) - return ret; - /* Enable auto ageing for all ports */ ret = regmap_write(priv->map, RTL8366RB_SECURITY_CTRL, 0); if (ret) @@ -1184,70 +1292,6 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) return; } -static int -rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, - struct dsa_bridge bridge, - bool *tx_fwd_offload, - struct netlink_ext_ack *extack) -{ - struct realtek_priv *priv = ds->priv; - unsigned int port_bitmap = 0; - int ret, i; - - /* Loop over all other ports than the current one */ - for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { - /* Current port handled last */ - if (i == port) - continue; - /* Not on this bridge */ - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Join this port to each other port on the bridge */ - ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), - RTL8366RB_PORT_ISO_PORTS(BIT(port)), - RTL8366RB_PORT_ISO_PORTS(BIT(port))); - if (ret) - dev_err(priv->dev, "failed to join port %d\n", port); - - port_bitmap |= BIT(i); - } - - /* Set the bits for the ports we can access */ - return regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), - RTL8366RB_PORT_ISO_PORTS(port_bitmap), - RTL8366RB_PORT_ISO_PORTS(port_bitmap)); -} - -static void -rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_bridge bridge) -{ - struct realtek_priv *priv = ds->priv; - unsigned int port_bitmap = 0; - int ret, i; - - /* Loop over all other ports than this one */ - for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { - /* Current port handled last */ - if (i == port) - continue; - /* Not on this bridge */ - if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) - continue; - /* Remove this port from any other port on the bridge */ - ret = regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(i), - RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0); - if (ret) - dev_err(priv->dev, "failed to leave port %d\n", port); - - port_bitmap |= BIT(i); - } - - /* Clear the bits for the ports we can not access, leave ourselves */ - regmap_update_bits(priv->map, RTL8366RB_PORT_ISO(port), - RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0); -} - /** * rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames * @priv: SMI state container @@ -1306,59 +1350,6 @@ rtl8366rb_port_pre_bridge_flags(struct dsa_switch *ds, int port, return 0; } -static int -rtl8366rb_port_bridge_flags(struct dsa_switch *ds, int port, - struct switchdev_brport_flags flags, - struct netlink_ext_ack *extack) -{ - struct realtek_priv *priv = ds->priv; - int ret; - - if (flags.mask & BR_LEARNING) { - ret = regmap_update_bits(priv->map, RTL8366RB_PORT_LEARNDIS_CTRL, - BIT(port), - (flags.val & BR_LEARNING) ? 0 : BIT(port)); - if (ret) - return ret; - } - - return 0; -} - -static void -rtl8366rb_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) -{ - struct realtek_priv *priv = ds->priv; - u32 val; - int i; - - switch (state) { - case BR_STATE_DISABLED: - val = RTL8366RB_STP_STATE_DISABLED; - break; - case BR_STATE_BLOCKING: - case BR_STATE_LISTENING: - val = RTL8366RB_STP_STATE_BLOCKING; - break; - case BR_STATE_LEARNING: - val = RTL8366RB_STP_STATE_LEARNING; - break; - case BR_STATE_FORWARDING: - val = RTL8366RB_STP_STATE_FORWARDING; - break; - default: - dev_err(priv->dev, "unknown bridge state requested\n"); - return; - } - - /* Set the same status for the port on all the FIDs */ - for (i = 0; i < RTL8366RB_NUM_FIDS; i++) { - regmap_update_bits(priv->map, RTL8366RB_STP_STATE_BASE + i, - RTL8366RB_STP_STATE_MASK(port), - RTL8366RB_STP_STATE(port, val)); - } -} - static void rtl8366rb_port_fast_age(struct dsa_switch *ds, int port) { @@ -1801,15 +1792,15 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = { .get_strings = rtl8366_get_strings, .get_ethtool_stats = rtl8366_get_ethtool_stats, .get_sset_count = rtl8366_get_sset_count, - .port_bridge_join = rtl8366rb_port_bridge_join, - .port_bridge_leave = rtl8366rb_port_bridge_leave, + .port_bridge_join = rtl83xx_port_bridge_join, + .port_bridge_leave = rtl83xx_port_bridge_leave, .port_vlan_filtering = rtl8366rb_vlan_filtering, .port_vlan_add = rtl8366_vlan_add, .port_vlan_del = rtl8366_vlan_del, .port_enable = rtl8366rb_port_enable, .port_disable = rtl8366rb_port_disable, .port_pre_bridge_flags = rtl8366rb_port_pre_bridge_flags, - .port_bridge_flags = rtl8366rb_port_bridge_flags, + .port_bridge_flags = rtl83xx_port_bridge_flags, .port_stp_state_set = rtl8366rb_port_stp_state_set, .port_fast_age = rtl8366rb_port_fast_age, .port_change_mtu = rtl8366rb_change_mtu, @@ -1830,6 +1821,9 @@ static const struct realtek_ops rtl8366rb_ops = { .is_vlan_valid = rtl8366rb_is_vlan_valid, .enable_vlan = rtl8366rb_enable_vlan, .enable_vlan4k = rtl8366rb_enable_vlan4k, + .port_add_isolation = rtl8366rb_port_add_isolation, + .port_remove_isolation = rtl8366rb_port_remove_isolation, + .port_set_learning = rtl8366rb_port_set_learning, .phy_read = rtl8366rb_phy_read, .phy_write = rtl8366rb_phy_write, }; diff --git a/drivers/net/dsa/realtek/rtl83xx.c b/drivers/net/dsa/realtek/rtl83xx.c index 71124ecca92f..90843d52c5a8 100644 --- a/drivers/net/dsa/realtek/rtl83xx.c +++ b/drivers/net/dsa/realtek/rtl83xx.c @@ -356,9 +356,6 @@ int rtl83xx_port_bridge_join(struct dsa_switch *ds, int port, if (!priv->ops->port_add_isolation) return -EOPNOTSUPP; - if (!priv->ops->port_set_learning) - return -EOPNOTSUPP; - dev_dbg(priv->dev, "bridge %d join port %d\n", bridge.num, port); /* Add this port to the isolation group of every other port @@ -396,9 +393,11 @@ int rtl83xx_port_bridge_join(struct dsa_switch *ds, int port, goto undo_self_isolation; } - ret = priv->ops->port_set_learning(priv, port, true); - if (ret) - goto undo_efid; + if (priv->ops->port_set_learning) { + ret = priv->ops->port_set_learning(priv, port, true); + if (ret) + goto undo_efid; + } return 0; @@ -443,9 +442,6 @@ void rtl83xx_port_bridge_leave(struct dsa_switch *ds, int port, if (!priv->ops->port_remove_isolation) return; - if (!priv->ops->port_set_learning) - return; - dev_dbg(priv->dev, "bridge %d leave port %d\n", bridge.num, port); /* Remove this port from the isolation group of every other @@ -474,11 +470,13 @@ void rtl83xx_port_bridge_leave(struct dsa_switch *ds, int port, * downstream DSA ports from the isolation group. */ - ret = priv->ops->port_set_learning(priv, port, false); - if (ret) - dev_err(priv->dev, - "failed to disable learning on port %d: %pe\n", - port, ERR_PTR(ret)); + if (priv->ops->port_set_learning) { + ret = priv->ops->port_set_learning(priv, port, false); + if (ret) + dev_err(priv->dev, + "failed to disable learning on port %d: %pe\n", + port, ERR_PTR(ret)); + } /* Remove those ports from the isolation group of this port */ ret = priv->ops->port_remove_isolation(priv, port, mask); diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index fc7341a5cbb7..42174249ef61 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -15,7 +15,7 @@ #include <linux/clk.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/mii.h> diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 3b2951030a38..507db46daf2b 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -7,7 +7,7 @@ * Keyur Chudgar <kchudgar@apm.com> */ -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include "xgene_enet_main.h" #include "xgene_enet_hw.h" #include "xgene_enet_sgmac.h" diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 858ba844ac51..8320b26c3f72 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -25,6 +25,9 @@ #define DEFAULT_VLAN_ID 1 +static struct notifier_block dpaa2_switch_port_switchdev_nb; +static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb; + static u16 dpaa2_switch_port_get_fdb_id(struct ethsw_port_priv *port_priv) { return port_priv->fdb->fdb_id; @@ -51,6 +54,17 @@ dpaa2_switch_filter_block_get_unused(struct ethsw_core *ethsw) return NULL; } +static struct dpaa2_switch_lag * +dpaa2_switch_lag_get_unused(struct ethsw_core *ethsw) +{ + int i; + + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) + if (!ethsw->lags[i].in_use) + return ðsw->lags[i]; + return NULL; +} + static bool dpaa2_switch_fdb_in_use_by_others(struct ethsw_core *ethsw, struct dpaa2_switch_fdb *fdb, struct ethsw_port_priv *except) @@ -71,9 +85,9 @@ static struct dpaa2_switch_fdb * dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv, struct net_device *upper_dev) { - struct ethsw_port_priv *other_port_priv; - struct net_device *other_dev; - struct list_head *iter; + struct ethsw_port_priv *other_port_priv = NULL; + struct net_device *other_dev, *other_dev2; + struct list_head *iter, *iter2; /* The below call to netdev_for_each_lower_dev() demands the RTNL lock * being held. Assert on it so that it's easier to catch new code @@ -82,17 +96,32 @@ dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv, ASSERT_RTNL(); /* If part of a bridge, use the FDB of the first dpaa2 switch interface - * to be present in that bridge + * to be present in that bridge. The search descends one level through + * a bridged bond's lowers as well. */ netdev_for_each_lower_dev(upper_dev, other_dev, iter) { - if (!dpaa2_switch_port_dev_check(other_dev)) - continue; + if (netif_is_lag_master(other_dev)) { + netdev_for_each_lower_dev(other_dev, other_dev2, iter2) { + if (!dpaa2_switch_port_dev_check(other_dev2)) + continue; - if (other_dev == port_priv->netdev) - continue; + if (other_dev2 == port_priv->netdev) + continue; - other_port_priv = netdev_priv(other_dev); - return other_port_priv->fdb; + other_port_priv = netdev_priv(other_dev2); + break; + } + } else { + if (!dpaa2_switch_port_dev_check(other_dev)) + continue; + + if (other_dev == port_priv->netdev) + continue; + + other_port_priv = netdev_priv(other_dev); + } + if (other_port_priv) + return other_port_priv->fdb; } return port_priv->fdb; @@ -537,6 +566,103 @@ static int dpaa2_switch_port_fdb_del_mc(struct ethsw_port_priv *port_priv, return err; } +static int dpaa2_switch_port_fdb_add(struct ethsw_port_priv *port_priv, + const unsigned char *addr) +{ + int err; + + if (is_unicast_ether_addr(addr)) + err = dpaa2_switch_port_fdb_add_uc(port_priv, addr); + else + err = dpaa2_switch_port_fdb_add_mc(port_priv, addr); + + return err; +} + +static int dpaa2_switch_port_fdb_del(struct ethsw_port_priv *port_priv, + const unsigned char *addr) +{ + if (is_unicast_ether_addr(addr)) + return dpaa2_switch_port_fdb_del_uc(port_priv, addr); + else + return dpaa2_switch_port_fdb_del_mc(port_priv, addr); +} + +static struct dpaa2_mac_addr * +dpaa2_switch_mac_addr_find(struct list_head *addr_list, + const unsigned char *addr, u16 vid) +{ + struct dpaa2_mac_addr *a; + + list_for_each_entry(a, addr_list, list) + if (ether_addr_equal(a->addr, addr) && a->vid == vid) + return a; + + return NULL; +} + +static int dpaa2_switch_lag_fdb_add(struct dpaa2_switch_lag *lag, + const unsigned char *addr, u16 vid) +{ + struct ethsw_port_priv *port_priv = lag->primary; + struct dpaa2_mac_addr *a; + int err = 0; + + mutex_lock(&lag->fdb_lock); + + a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid); + if (a) { + refcount_inc(&a->refcount); + goto out; + } + + a = kzalloc(sizeof(*a), GFP_KERNEL); + if (!a) { + err = -ENOMEM; + goto out; + } + + err = dpaa2_switch_port_fdb_add(port_priv, addr); + if (err) { + kfree(a); + goto out; + } + + ether_addr_copy(a->addr, addr); + a->vid = vid; + refcount_set(&a->refcount, 1); + list_add_tail(&a->list, &lag->fdbs); + +out: + mutex_unlock(&lag->fdb_lock); + + return err; +} + +static void dpaa2_switch_lag_fdb_del(struct dpaa2_switch_lag *lag, + const unsigned char *addr, u16 vid) +{ + struct ethsw_port_priv *port_priv = lag->primary; + struct dpaa2_mac_addr *a; + + mutex_lock(&lag->fdb_lock); + + a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid); + if (!a) + goto out; + + if (!refcount_dec_and_test(&a->refcount)) + goto out; + + list_del(&a->list); + kfree(a); + + dpaa2_switch_port_fdb_del(port_priv, addr); + +out: + mutex_unlock(&lag->fdb_lock); +} + static void dpaa2_switch_port_get_stats(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -1485,6 +1611,33 @@ bool dpaa2_switch_port_dev_check(const struct net_device *netdev) return netdev->netdev_ops == &dpaa2_switch_port_ops; } +static bool dpaa2_switch_foreign_dev_check(const struct net_device *dev, + const struct net_device *foreign_dev) +{ + struct ethsw_port_priv *port_priv = netdev_priv(dev); + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct ethsw_port_priv *other_port; + int i; + + if (netif_is_bridge_master(foreign_dev)) + if (port_priv->fdb->bridge_dev == foreign_dev) + return false; + + if (netif_is_bridge_port(foreign_dev)) { + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { + other_port = ethsw->ports[i]; + + if (!other_port) + continue; + if (dpaa2_switch_port_offloads_bridge_port(other_port, + foreign_dev)) + return false; + } + } + + return true; +} + static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv) { struct fsl_mc_device *dpsw_port_dev, *dpmac_dev; @@ -1860,51 +2013,32 @@ int dpaa2_switch_port_vlans_add(struct net_device *netdev, vlan->changed); } -static int dpaa2_switch_port_lookup_address(struct net_device *netdev, int is_uc, - const unsigned char *addr) -{ - struct netdev_hw_addr_list *list = (is_uc) ? &netdev->uc : &netdev->mc; - struct netdev_hw_addr *ha; - - netif_addr_lock_bh(netdev); - list_for_each_entry(ha, &list->list, list) { - if (ether_addr_equal(ha->addr, addr)) { - netif_addr_unlock_bh(netdev); - return 1; - } - } - netif_addr_unlock_bh(netdev); - return 0; -} - static int dpaa2_switch_port_mdb_add(struct net_device *netdev, const struct switchdev_obj_port_mdb *mdb) { struct ethsw_port_priv *port_priv = netdev_priv(netdev); - int err; + struct dpaa2_switch_lag *lag; - /* Check if address is already set on this port */ - if (dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr)) - return -EEXIST; - - err = dpaa2_switch_port_fdb_add_mc(port_priv, mdb->addr); - if (err) - return err; - - err = dev_mc_add(netdev, mdb->addr); - if (err) { - netdev_err(netdev, "dev_mc_add err %d\n", err); - dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr); - } - - return err; + lag = rtnl_dereference(port_priv->lag); + if (lag) + return dpaa2_switch_lag_fdb_add(lag, mdb->addr, mdb->vid); + else + return dpaa2_switch_port_fdb_add(port_priv, mdb->addr); } -static int dpaa2_switch_port_obj_add(struct net_device *netdev, - const struct switchdev_obj *obj) +static int dpaa2_switch_port_obj_add(struct net_device *netdev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { + struct ethsw_port_priv *port_priv = netdev_priv(netdev); int err; + if (ctx && ctx != port_priv) + return 0; + + if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev)) + return -EOPNOTSUPP; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dpaa2_switch_port_vlans_add(netdev, @@ -2000,29 +2134,29 @@ static int dpaa2_switch_port_mdb_del(struct net_device *netdev, const struct switchdev_obj_port_mdb *mdb) { struct ethsw_port_priv *port_priv = netdev_priv(netdev); - int err; - - if (!dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr)) - return -ENOENT; - - err = dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr); - if (err) - return err; + struct dpaa2_switch_lag *lag; - err = dev_mc_del(netdev, mdb->addr); - if (err) { - netdev_err(netdev, "dev_mc_del err %d\n", err); - return err; - } + lag = rtnl_dereference(port_priv->lag); + if (lag) + dpaa2_switch_lag_fdb_del(lag, mdb->addr, mdb->vid); + else + dpaa2_switch_port_fdb_del(port_priv, mdb->addr); - return err; + return 0; } -static int dpaa2_switch_port_obj_del(struct net_device *netdev, +static int dpaa2_switch_port_obj_del(struct net_device *netdev, const void *ctx, const struct switchdev_obj *obj) { + struct ethsw_port_priv *port_priv = netdev_priv(netdev); int err; + if (ctx && ctx != port_priv) + return 0; + + if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev)) + return -EOPNOTSUPP; + switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dpaa2_switch_port_vlans_del(netdev, SWITCHDEV_OBJ_PORT_VLAN(obj)); @@ -2048,6 +2182,21 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev, return notifier_from_errno(err); } +static struct net_device * +dpaa2_switch_port_to_bridge_port(struct ethsw_port_priv *port_priv) +{ + struct dpaa2_switch_lag *lag; + + if (!port_priv->fdb->bridge_dev) + return NULL; + + lag = rtnl_dereference(port_priv->lag); + if (lag) + return lag->bond_dev; + + return port_priv->netdev; +} + static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) @@ -2055,6 +2204,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, struct ethsw_port_priv *port_priv = netdev_priv(netdev); struct dpaa2_switch_fdb *old_fdb = port_priv->fdb; struct ethsw_core *ethsw = port_priv->ethsw_data; + struct net_device *brport_dev; bool learn_ena; int err; @@ -2066,7 +2216,8 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, dpaa2_switch_port_set_fdb(port_priv, upper_dev, true); /* Inherit the initial bridge port learning state */ - learn_ena = br_port_flag_is_set(netdev, BR_LEARNING); + brport_dev = dpaa2_switch_port_to_bridge_port(port_priv); + learn_ena = br_port_flag_is_set(brport_dev, BR_LEARNING); err = dpaa2_switch_port_set_learning(port_priv, learn_ena); port_priv->learn_ena = learn_ena; @@ -2080,8 +2231,11 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev, if (err) goto err_egress_flood; - err = switchdev_bridge_port_offload(netdev, netdev, NULL, - NULL, NULL, false, extack); + brport_dev = dpaa2_switch_port_to_bridge_port(port_priv); + err = switchdev_bridge_port_offload(brport_dev, netdev, port_priv, + &dpaa2_switch_port_switchdev_nb, + &dpaa2_switch_port_switchdev_blocking_nb, + false, extack); if (err) goto err_switchdev_offload; @@ -2115,7 +2269,22 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev) { - switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL); + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct net_device *brport_dev; + + brport_dev = dpaa2_switch_port_to_bridge_port(port_priv); + if (!brport_dev) + return; + + switchdev_bridge_port_unoffload(brport_dev, port_priv, + &dpaa2_switch_port_switchdev_nb, + &dpaa2_switch_port_switchdev_blocking_nb); + + /* Make sure that any FDB add/del operations are completed before the + * bridge layout changes + */ + flush_workqueue(ethsw->workqueue); } static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) @@ -2177,30 +2346,53 @@ static int dpaa2_switch_port_bridge_leave(struct net_device *netdev) false); } +static int +dpaa2_switch_have_vlan_upper(struct net_device *upper_dev, + __always_unused struct netdev_nested_priv *priv) +{ + return is_vlan_dev(upper_dev); +} + static int dpaa2_switch_prevent_bridging_with_8021q_upper(struct net_device *netdev) { - struct net_device *upper_dev; - struct list_head *iter; + struct netdev_nested_priv priv = {}; /* RCU read lock not necessary because we have write-side protection - * (rtnl_mutex), however a non-rcu iterator does not exist. + * (rtnl_mutex), however a non-rcu iterator does not exist. Walk the + * entire upper chain so that a VLAN device stacked on a intermediate + * bond is caught too. */ - netdev_for_each_upper_dev_rcu(netdev, upper_dev, iter) - if (is_vlan_dev(upper_dev)) - return -EOPNOTSUPP; + if (netdev_walk_all_upper_dev_rcu(netdev, dpaa2_switch_have_vlan_upper, + &priv)) + return -EOPNOTSUPP; return 0; } +static int dpaa2_switch_check_dpsw_instance(struct net_device *dev, + struct netdev_nested_priv *priv) +{ + struct ethsw_port_priv *port_priv = (struct ethsw_port_priv *)priv->data; + struct ethsw_port_priv *other_priv = netdev_priv(dev); + + if (!dpaa2_switch_port_dev_check(dev)) + return 0; + + if (other_priv->ethsw_data == port_priv->ethsw_data) + return 0; + + return 1; +} + static int dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct ethsw_port_priv *port_priv = netdev_priv(netdev); - struct ethsw_port_priv *other_port_priv; - struct net_device *other_dev; - struct list_head *iter; + struct netdev_nested_priv data = { + .data = (void *)port_priv, + }; int err; if (!br_vlan_enabled(upper_dev)) { @@ -2215,6 +2407,70 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev, return err; } + err = netdev_walk_all_lower_dev(upper_dev, + dpaa2_switch_check_dpsw_instance, + &data); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Interface from a different DPSW is in the bridge already"); + return -EINVAL; + } + + return 0; +} + +static int dpaa2_switch_pre_lag_join(struct net_device *netdev, + struct net_device *upper_dev, + struct netdev_lag_upper_info *info, + struct netlink_ext_ack *extack) +{ + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct ethsw_port_priv *other_port_priv; + struct dpaa2_switch_lag *lag = NULL; + struct dpsw_lag_cfg cfg = {0}; + struct net_device *other_dev; + int i, num_ifs = 0, err; + struct list_head *iter; + + if (!(ethsw->features & ETHSW_FEATURE_LAG_OFFLOAD)) { + NL_SET_ERR_MSG_MOD(extack, + "LAG offload is supported only for DPSW >= v8.13"); + return -EOPNOTSUPP; + } + + if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) { + NL_SET_ERR_MSG_MOD(extack, + "Can only offload LAG using hash TX type"); + return -EOPNOTSUPP; + } + + if (info->hash_type != NETDEV_LAG_HASH_L23) { + NL_SET_ERR_MSG_MOD(extack, "Can only offload L2+L3 Tx hash"); + return -EOPNOTSUPP; + } + + if (!dpaa2_switch_port_has_mac(port_priv)) { + NL_SET_ERR_MSG_MOD(extack, + "Only switch interfaces connected to MACs can be under a LAG"); + return -EINVAL; + } + + if (vlan_uses_dev(upper_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot join a LAG upper that has a VLAN"); + return -EOPNOTSUPP; + } + + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { + if (!ethsw->lags[i].in_use) + continue; + if (ethsw->lags[i].bond_dev != upper_dev) + continue; + lag = ðsw->lags[i]; + break; + } + netdev_for_each_lower_dev(upper_dev, other_dev, iter) { if (!dpaa2_switch_port_dev_check(other_dev)) continue; @@ -2222,9 +2478,248 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev, other_port_priv = netdev_priv(other_dev); if (other_port_priv->ethsw_data != port_priv->ethsw_data) { NL_SET_ERR_MSG_MOD(extack, - "Interface from a different DPSW is in the bridge already"); + "Interface from a different DPSW is in the bond already"); return -EINVAL; } + + cfg.if_id[num_ifs++] = other_port_priv->idx; + + if (num_ifs >= DPSW_MAX_LAG_IFS) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot add more than 8 DPAA2 switch ports under the same bond"); + return -EINVAL; + } + } + + if (lag) { + cfg.group_id = lag->id; + cfg.if_id[num_ifs++] = port_priv->idx; + cfg.num_ifs = num_ifs; + cfg.phase = DPSW_LAG_SET_PHASE_CHECK; + + err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot offload LAG configuration"); + return -EOPNOTSUPP; + } + } + + return 0; +} + +static void dpaa2_switch_port_set_lag_group(struct ethsw_port_priv *port_priv, + struct net_device *bond_dev) +{ + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct ethsw_port_priv *other_port_priv = NULL; + struct dpaa2_switch_lag *lag = NULL; + struct dpaa2_switch_lag *other_lag; + struct net_device *other_dev; + struct list_head *iter; + + netdev_for_each_lower_dev(bond_dev, other_dev, iter) { + if (!dpaa2_switch_port_dev_check(other_dev)) + continue; + + other_port_priv = netdev_priv(other_dev); + other_lag = rtnl_dereference(other_port_priv->lag); + if (!other_lag) + continue; + + if (other_lag->bond_dev == bond_dev) { + rcu_assign_pointer(port_priv->lag, other_lag); + return; + } + } + + /* This is the first interface to be added under a bond device. Find an + * unused LAG group. No need to check for NULL since there are the same + * amount of DPSW ports as LAG groups, meaning that each port can have + * its own LAG group. + */ + lag = dpaa2_switch_lag_get_unused(ethsw); + lag->in_use = true; + lag->bond_dev = bond_dev; + lag->primary = port_priv; + rcu_assign_pointer(port_priv->lag, lag); +} + +static bool dpaa2_switch_port_in_lag(struct ethsw_port_priv *port_priv, + struct net_device *bond_dev) +{ + struct dpaa2_switch_lag *lag; + + if (!port_priv) + return false; + + lag = rtnl_dereference(port_priv->lag); + return lag && lag->bond_dev == bond_dev; +} + +static int dpaa2_switch_set_lag_cfg(struct net_device *bond_dev, u8 lag_id, + struct ethsw_core *ethsw) +{ + struct dpaa2_switch_lag *lag = ðsw->lags[lag_id - 1]; + struct ethsw_port_priv *primary, *port_priv; + struct ethsw_port_priv *new_primary = NULL; + struct dpsw_lag_cfg cfg = {0}; + struct dpaa2_mac_addr *a; + u8 num_ifs = 0; + int err, i; + + cfg.group_id = lag_id; + + /* Determine the primary port. The caller clears ->lag on the port that + * is leaving, so a NULL ->lag on the current primary means it is the + * one leaving: elect the first remaining member as the new primary. + * Otherwise keep the current primary. + */ + if (rtnl_dereference(lag->primary->lag)) { + primary = lag->primary; + } else { + primary = NULL; + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { + if (dpaa2_switch_port_in_lag(ethsw->ports[i], bond_dev)) { + new_primary = ethsw->ports[i]; + primary = new_primary; + break; + } + } + } + + /* Build the interface list, always placing the primary first */ + if (primary) + cfg.if_id[num_ifs++] = primary->idx; + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { + port_priv = ethsw->ports[i]; + if (port_priv == primary) + continue; + if (!dpaa2_switch_port_in_lag(port_priv, bond_dev)) + continue; + + cfg.if_id[num_ifs++] = port_priv->idx; + } + cfg.num_ifs = num_ifs; + + /* No more interfaces under this LAG group, mark it as not in use. Wait + * for a grace period so that any readers of the lag structure finished. + */ + if (!num_ifs) { + synchronize_net(); + + lag->bond_dev = NULL; + lag->primary = NULL; + lag->in_use = false; + } + + /* When the primary changes, migrate the FDB entries from the old + * primary to the new one: remove them before reconfiguring the LAG in + * hardware and re-add them on the new primary afterwards. We do not + * touch any refcounting since the intention is to change the HW entry, + * not the parallel software tracking. + */ + if (new_primary) { + mutex_lock(&lag->fdb_lock); + list_for_each_entry(a, &lag->fdbs, list) + dpaa2_switch_port_fdb_del(lag->primary, a->addr); + mutex_unlock(&lag->fdb_lock); + } + + err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg); + if (err) + return err; + + if (new_primary) { + mutex_lock(&lag->fdb_lock); + list_for_each_entry(a, &lag->fdbs, list) { + err = dpaa2_switch_port_fdb_add(new_primary, a->addr); + if (err) + netdev_err(new_primary->netdev, "Unable to migrate FDB\n"); + } + mutex_unlock(&lag->fdb_lock); + + synchronize_net(); + lag->primary = new_primary; + } + + return 0; +} + +static int dpaa2_switch_port_bond_join(struct net_device *netdev, + struct net_device *bond_dev, + struct netdev_lag_upper_info *info, + struct netlink_ext_ack *extack) +{ + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct net_device *bridge_dev; + struct dpaa2_switch_lag *lag; + int err = 0; + u8 lag_id; + + /* Setup the port_priv->lag pointer for this switch port */ + dpaa2_switch_port_set_lag_group(port_priv, bond_dev); + + /* Create the LAG configuration and apply it in MC */ + lag = rtnl_dereference(port_priv->lag); + lag_id = lag->id; + err = dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw); + if (err) + goto err_lag_cfg; + + /* If the bond device is a switch port, join the bridge as well */ + bridge_dev = netdev_master_upper_dev_get(bond_dev); + if (!bridge_dev || !netif_is_bridge_master(bridge_dev)) + return 0; + + err = dpaa2_switch_port_bridge_join(netdev, bridge_dev, extack); + if (err) + goto err_lag_cfg; + + return err; + +err_lag_cfg: + rcu_assign_pointer(port_priv->lag, NULL); + dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw); + + return err; +} + +static int dpaa2_switch_port_bond_leave(struct net_device *netdev, + struct net_device *bond_dev) +{ + struct net_device *bridge_dev = netdev_master_upper_dev_get(bond_dev); + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct dpaa2_switch_lag *lag = rtnl_dereference(port_priv->lag); + struct ethsw_core *ethsw = port_priv->ethsw_data; + struct net_device *brpdev; + bool learn_ena; + int err; + + if (!lag) + return 0; + + /* Recreate the LAG configuration for the LAG group that we left. */ + rcu_assign_pointer(port_priv->lag, NULL); + dpaa2_switch_set_lag_cfg(bond_dev, lag->id, ethsw); + + if (bridge_dev && netif_is_bridge_master(bridge_dev)) { + /* Make sure that the new primary inherits the learning state */ + if (lag->primary) { + brpdev = dpaa2_switch_port_to_bridge_port(lag->primary); + learn_ena = br_port_flag_is_set(brpdev, BR_LEARNING); + err = dpaa2_switch_port_set_learning(lag->primary, + learn_ena); + if (err) + return err; + lag->primary->learn_ena = learn_ena; + } + + /* In case the bond is a bridge port, leave the upper bridge as + * well. + */ + return dpaa2_switch_port_bridge_leave(netdev); } return 0; @@ -2234,8 +2729,8 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev, struct netdev_notifier_changeupper_info *info) { struct ethsw_port_priv *port_priv; + struct net_device *upper_dev, *br; struct netlink_ext_ack *extack; - struct net_device *upper_dev; int err; if (!dpaa2_switch_port_dev_check(netdev)) @@ -2252,6 +2747,24 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev, if (!info->linking) dpaa2_switch_port_pre_bridge_leave(netdev); + } else if (netif_is_lag_master(upper_dev)) { + if (!info->linking) { + if (netif_is_bridge_port(upper_dev)) + dpaa2_switch_port_pre_bridge_leave(netdev); + return 0; + } + + if (netif_is_bridge_port(upper_dev)) { + br = netdev_master_upper_dev_get(upper_dev); + err = dpaa2_switch_prechangeupper_sanity_checks(netdev, + br, + extack); + if (err) + return err; + } + + return dpaa2_switch_pre_lag_join(netdev, upper_dev, + info->upper_info, extack); } else if (is_vlan_dev(upper_dev)) { port_priv = netdev_priv(netdev); if (port_priv->fdb->bridge_dev) { @@ -2283,6 +2796,80 @@ static int dpaa2_switch_port_changeupper(struct net_device *netdev, extack); else return dpaa2_switch_port_bridge_leave(netdev); + } else if (netif_is_lag_master(upper_dev)) { + if (info->linking) + return dpaa2_switch_port_bond_join(netdev, upper_dev, + info->upper_info, + extack); + else + return dpaa2_switch_port_bond_leave(netdev, upper_dev); + } + + return 0; +} + +static int +dpaa2_switch_lag_prechangeupper(struct net_device *netdev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = 0; + + if (!netif_is_lag_master(netdev)) + return 0; + + netdev_for_each_lower_dev(netdev, lower, iter) { + if (!dpaa2_switch_port_dev_check(lower)) + continue; + + err = dpaa2_switch_port_prechangeupper(lower, info); + if (err) + return err; + } + + return err; +} + +static int +dpaa2_switch_lag_changeupper(struct net_device *netdev, + struct netdev_notifier_changeupper_info *info) +{ + struct net_device *lower; + struct list_head *iter; + int err = 0; + + if (!netif_is_lag_master(netdev)) + return 0; + + netdev_for_each_lower_dev(netdev, lower, iter) { + if (!dpaa2_switch_port_dev_check(lower)) + continue; + + err = dpaa2_switch_port_changeupper(lower, info); + if (err) + return err; + } + + return 0; +} + +static int +dpaa2_switch_port_changelowerstate(struct net_device *netdev, + struct netdev_lag_lower_state_info *linfo) +{ + struct ethsw_port_priv *port_priv = netdev_priv(netdev); + struct ethsw_core *ethsw = port_priv->ethsw_data; + int err; + + if (!rtnl_dereference(port_priv->lag)) + return 0; + + err = dpsw_if_set_lag_state(ethsw->mc_io, 0, ethsw->dpsw_handle, + port_priv->idx, linfo->tx_enabled ? 1 : 0); + if (err) { + netdev_err(netdev, "dpsw_if_set_lag_state() = %d\n", err); + return err; } return 0; @@ -2292,6 +2879,7 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changelowerstate_info *info; int err = 0; switch (event) { @@ -2300,13 +2888,29 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb, if (err) return notifier_from_errno(err); + err = dpaa2_switch_lag_prechangeupper(netdev, ptr); + if (err) + return notifier_from_errno(err); + break; case NETDEV_CHANGEUPPER: err = dpaa2_switch_port_changeupper(netdev, ptr); if (err) return notifier_from_errno(err); + err = dpaa2_switch_lag_changeupper(netdev, ptr); + if (err) + return notifier_from_errno(err); + break; + case NETDEV_CHANGELOWERSTATE: + info = ptr; + if (!dpaa2_switch_port_dev_check(netdev)) + break; + + err = dpaa2_switch_port_changelowerstate(netdev, + info->lower_state_info); + return notifier_from_errno(err); } return NOTIFY_DONE; @@ -2316,80 +2920,97 @@ struct ethsw_switchdev_event_work { struct work_struct work; struct switchdev_notifier_fdb_info fdb_info; struct net_device *dev; + struct net_device *orig_dev; unsigned long event; + u16 vid; }; static void dpaa2_switch_event_work(struct work_struct *work) { struct ethsw_switchdev_event_work *switchdev_work = container_of(work, struct ethsw_switchdev_event_work, work); + struct net_device *orig_dev = switchdev_work->orig_dev; struct net_device *dev = switchdev_work->dev; + struct ethsw_port_priv *port_priv = netdev_priv(dev); struct switchdev_notifier_fdb_info *fdb_info; + struct dpaa2_switch_lag *lag; int err; - rtnl_lock(); fdb_info = &switchdev_work->fdb_info; + /* The lag structures are freed only from dpaa2_switch_remove(), which + * first flushes this workqueue, so the pointer stays valid for the + * lifetime of the work item. Only the dereference needs the RCU + * read-side lock; the FDB helpers below can sleep and must run outside + * of it. + */ + rcu_read_lock(); + lag = rcu_dereference(port_priv->lag); + rcu_read_unlock(); + switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: - if (!fdb_info->added_by_user || fdb_info->is_local) - break; - if (is_unicast_ether_addr(fdb_info->addr)) - err = dpaa2_switch_port_fdb_add_uc(netdev_priv(dev), - fdb_info->addr); + if (lag) + err = dpaa2_switch_lag_fdb_add(lag, fdb_info->addr, + switchdev_work->vid); else - err = dpaa2_switch_port_fdb_add_mc(netdev_priv(dev), - fdb_info->addr); + err = dpaa2_switch_port_fdb_add(port_priv, + fdb_info->addr); if (err) break; fdb_info->offloaded = true; - call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, orig_dev, &fdb_info->info, NULL); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (!fdb_info->added_by_user || fdb_info->is_local) - break; - if (is_unicast_ether_addr(fdb_info->addr)) - dpaa2_switch_port_fdb_del_uc(netdev_priv(dev), fdb_info->addr); + if (lag) + dpaa2_switch_lag_fdb_del(lag, fdb_info->addr, + switchdev_work->vid); else - dpaa2_switch_port_fdb_del_mc(netdev_priv(dev), fdb_info->addr); + dpaa2_switch_port_fdb_del(port_priv, fdb_info->addr); break; } - rtnl_unlock(); kfree(switchdev_work->fdb_info.addr); kfree(switchdev_work); dev_put(dev); + dev_put(orig_dev); } -/* Called under rcu_read_lock() */ -static int dpaa2_switch_port_event(struct notifier_block *nb, - unsigned long event, void *ptr) +static int +dpaa2_switch_port_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 net_device *dev = switchdev_notifier_info_to_dev(ptr); struct ethsw_port_priv *port_priv = netdev_priv(dev); struct ethsw_switchdev_event_work *switchdev_work; - struct switchdev_notifier_fdb_info *fdb_info = ptr; struct ethsw_core *ethsw = port_priv->ethsw_data; - if (event == SWITCHDEV_PORT_ATTR_SET) - return dpaa2_switch_port_attr_set_event(dev, ptr); + if (ctx && ctx != port_priv) + return 0; - if (!dpaa2_switch_port_dev_check(dev)) - return NOTIFY_DONE; + /* For the moment, do nothing with entries towards foreign devices */ + if (dpaa2_switch_foreign_dev_check(dev, orig_dev)) + return 0; + + if (!fdb_info->added_by_user || fdb_info->is_local) + return 0; switchdev_work = kzalloc_obj(*switchdev_work, GFP_ATOMIC); if (!switchdev_work) - return NOTIFY_BAD; + return -ENOMEM; INIT_WORK(&switchdev_work->work, dpaa2_switch_event_work); switchdev_work->dev = dev; switchdev_work->event = event; + switchdev_work->orig_dev = orig_dev; + switchdev_work->vid = fdb_info->vid; switch (event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: - memcpy(&switchdev_work->fdb_info, ptr, + 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) @@ -2400,52 +3021,61 @@ static int dpaa2_switch_port_event(struct notifier_block *nb, /* Take a reference on the device to avoid being freed. */ dev_hold(dev); + dev_hold(orig_dev); break; default: kfree(switchdev_work); - return NOTIFY_DONE; + return 0; } queue_work(ethsw->workqueue, &switchdev_work->work); - return NOTIFY_DONE; + return 0; err_addr_alloc: kfree(switchdev_work); - return NOTIFY_BAD; + return -ENOMEM; } -static int dpaa2_switch_port_obj_event(unsigned long event, - struct net_device *netdev, - struct switchdev_notifier_port_obj_info *port_obj_info) +/* Called under rcu_read_lock() */ +static int dpaa2_switch_port_event(struct notifier_block *nb, + unsigned long event, void *ptr) { - int err = -EOPNOTSUPP; - - if (!dpaa2_switch_port_dev_check(netdev)) - return NOTIFY_DONE; + struct net_device *dev = switchdev_notifier_info_to_dev(ptr); + int err; switch (event) { - case SWITCHDEV_PORT_OBJ_ADD: - err = dpaa2_switch_port_obj_add(netdev, port_obj_info->obj); - break; - case SWITCHDEV_PORT_OBJ_DEL: - err = dpaa2_switch_port_obj_del(netdev, port_obj_info->obj); - break; + case SWITCHDEV_PORT_ATTR_SET: + return dpaa2_switch_port_attr_set_event(dev, ptr); + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + err = switchdev_handle_fdb_event_to_device(dev, event, ptr, + dpaa2_switch_port_dev_check, + dpaa2_switch_foreign_dev_check, + dpaa2_switch_port_fdb_event); + return notifier_from_errno(err); + default: + return NOTIFY_DONE; } - - port_obj_info->handled = true; - return notifier_from_errno(err); } static int dpaa2_switch_port_blocking_event(struct notifier_block *nb, 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, + dpaa2_switch_port_dev_check, + dpaa2_switch_port_obj_add); + return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: - return dpaa2_switch_port_obj_event(event, dev, ptr); + err = switchdev_handle_port_obj_del(dev, ptr, + dpaa2_switch_port_dev_check, + dpaa2_switch_port_obj_del); + return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: return dpaa2_switch_port_attr_set_event(dev, ptr); } @@ -2490,19 +3120,22 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq, dma_addr_t addr = dpaa2_fd_get_addr(fd); struct ethsw_core *ethsw = fq->ethsw; struct ethsw_port_priv *port_priv; + struct dpaa2_switch_lag *lag; struct net_device *netdev; struct vlan_ethhdr *hdr; struct sk_buff *skb; u16 vlan_tci, vid; int if_id, err; void *vaddr; + u64 flc; vaddr = dpaa2_iova_to_virt(ethsw->iommu_domain, addr); dma_unmap_page(ethsw->dev, addr, DPAA2_SWITCH_RX_BUF_SIZE, DMA_FROM_DEVICE); /* get switch ingress interface ID */ - if_id = upper_32_bits(dpaa2_fd_get_flc(fd)) & 0x0000FFFF; + flc = dpaa2_fd_get_flc(fd); + if_id = DPAA2_ETHSW_FLC_IF_ID(flc); if (if_id >= ethsw->sw_attr.num_ifs) { dev_err(ethsw->dev, "Frame received from unknown interface!\n"); goto err_free_fd; @@ -2541,12 +3174,20 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq, } } - skb->dev = netdev; + rcu_read_lock(); + + lag = rcu_dereference(port_priv->lag); + if (DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc) && lag) + skb->dev = lag->bond_dev; + else + skb->dev = netdev; skb->protocol = eth_type_trans(skb, skb->dev); /* Setup the offload_fwd_mark only if the port is under a bridge */ skb->offload_fwd_mark = !!(port_priv->fdb->bridge_dev); + rcu_read_unlock(); + netif_receive_skb(skb); return; @@ -2561,6 +3202,9 @@ static void dpaa2_switch_detect_features(struct ethsw_core *ethsw) if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 6)) ethsw->features |= ETHSW_FEATURE_MAC_ADDR; + + if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 13)) + ethsw->features |= ETHSW_FEATURE_LAG_OFFLOAD; } static int dpaa2_switch_setup_fqs(struct ethsw_core *ethsw) @@ -3195,17 +3839,15 @@ err_close: return err; } -/* Add an ACL to redirect frames with specific destination MAC address to - * control interface - */ +/* Add an ACL to redirect frames to control interface based on the dst MAC */ static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv, - const char *mac) + const u8 *mac, const u8 *mask) { struct dpaa2_switch_acl_entry acl_entry = {0}; /* Match on the destination MAC address */ ether_addr_copy(acl_entry.key.match.l2_dest_mac, mac); - eth_broadcast_addr(acl_entry.key.mask.l2_dest_mac); + ether_addr_copy(acl_entry.key.mask.l2_dest_mac, mask); /* Trap to CPU */ acl_entry.cfg.precedence = 0; @@ -3216,7 +3858,8 @@ static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv, static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port) { - const char stpa[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00}; + const u8 ll_mac[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00}; + const u8 ll_mask[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xf0}; struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = DEFAULT_VLAN_ID, @@ -3291,7 +3934,7 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port) if (err) return err; - err = dpaa2_switch_port_trap_mac_addr(port_priv, stpa); + err = dpaa2_switch_port_trap_mac_addr(port_priv, ll_mac, ll_mask); if (err) return err; @@ -3331,6 +3974,9 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev) dev = &sw_dev->dev; ethsw = dev_get_drvdata(dev); + /* Make sure that all events were handled before we kfree anything */ + flush_workqueue(ethsw->workqueue); + dpaa2_switch_teardown_irqs(sw_dev); dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle); @@ -3344,12 +3990,15 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev) for (i = 0; i < DPAA2_SWITCH_RX_NUM_FQS; i++) netif_napi_del(ðsw->fq[i].napi); - for (i = 0; i < ethsw->sw_attr.num_ifs; i++) + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { dpaa2_switch_remove_port(ethsw, i); + mutex_destroy(ðsw->lags[i].fdb_lock); + } kfree(ethsw->fdbs); kfree(ethsw->filter_blocks); kfree(ethsw->ports); + kfree(ethsw->lags); dpaa2_switch_teardown(sw_dev); @@ -3377,6 +4026,7 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw, port_priv = netdev_priv(port_netdev); port_priv->netdev = port_netdev; port_priv->ethsw_data = ethsw; + rcu_assign_pointer(port_priv->lag, NULL); mutex_init(&port_priv->mac_lock); @@ -3484,6 +4134,21 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev) goto err_free_fdbs; } + ethsw->lags = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->lags), + GFP_KERNEL); + if (!ethsw->lags) { + err = -ENOMEM; + goto err_free_filter; + } + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { + ethsw->lags[i].bond_dev = NULL; + ethsw->lags[i].ethsw = ethsw; + ethsw->lags[i].id = i + 1; + ethsw->lags[i].in_use = 0; + mutex_init(ðsw->lags[i].fdb_lock); + INIT_LIST_HEAD(ðsw->lags[i].fdbs); + } + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) { err = dpaa2_switch_probe_port(ethsw, i); if (err) @@ -3530,6 +4195,10 @@ err_stop: err_free_netdev: for (i--; i >= 0; i--) dpaa2_switch_remove_port(ethsw, i); + for (i = 0; i < ethsw->sw_attr.num_ifs; i++) + mutex_destroy(ðsw->lags[i].fdb_lock); + kfree(ethsw->lags); +err_free_filter: kfree(ethsw->filter_blocks); err_free_fdbs: kfree(ethsw->fdbs); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h index 42b3ca73f55d..63b702b0000c 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h @@ -41,7 +41,8 @@ #define ETHSW_MAX_FRAME_LENGTH (DPAA2_MFL - VLAN_ETH_HLEN - ETH_FCS_LEN) #define ETHSW_L2_MAX_FRM(mtu) ((mtu) + VLAN_ETH_HLEN + ETH_FCS_LEN) -#define ETHSW_FEATURE_MAC_ADDR BIT(0) +#define ETHSW_FEATURE_MAC_ADDR BIT(0) +#define ETHSW_FEATURE_LAG_OFFLOAD BIT(1) /* Number of receive queues (one RX and one TX_CONF) */ #define DPAA2_SWITCH_RX_NUM_FQS 2 @@ -86,6 +87,9 @@ #define DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE 256 +#define DPAA2_ETHSW_FLC_IF_ID(flc) (((flc) >> 32) & GENMASK(15, 0)) +#define DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc) ((flc) & BIT_ULL(63)) + extern const struct ethtool_ops dpaa2_switch_port_ethtool_ops; struct ethsw_core; @@ -99,12 +103,30 @@ struct dpaa2_switch_fq { u32 fqid; }; +struct dpaa2_mac_addr { + unsigned char addr[ETH_ALEN]; + u16 vid; + refcount_t refcount; + struct list_head list; +}; + struct dpaa2_switch_fdb { struct net_device *bridge_dev; u16 fdb_id; bool in_use; }; +struct dpaa2_switch_lag { + struct ethsw_core *ethsw; + struct net_device *bond_dev; + bool in_use; + u8 id; + struct ethsw_port_priv *primary; + /* Protects the list of fdbs installed on this LAG */ + struct mutex fdb_lock; + struct list_head fdbs; +}; + struct dpaa2_switch_acl_entry { struct list_head list; u16 prio; @@ -163,6 +185,8 @@ struct ethsw_port_priv { struct dpaa2_mac *mac; /* Protects against changes to port_priv->mac */ struct mutex mac_lock; + + struct dpaa2_switch_lag __rcu *lag; }; /* Switch data */ @@ -190,6 +214,8 @@ struct ethsw_core { struct dpaa2_switch_fdb *fdbs; struct dpaa2_switch_filter_block *filter_blocks; u16 mirror_port; + + struct dpaa2_switch_lag *lags; }; static inline int dpaa2_switch_get_index(struct ethsw_core *ethsw, @@ -274,4 +300,18 @@ int dpaa2_switch_block_offload_mirror(struct dpaa2_switch_filter_block *block, int dpaa2_switch_block_unoffload_mirror(struct dpaa2_switch_filter_block *block, struct ethsw_port_priv *port_priv); + +static inline bool +dpaa2_switch_port_offloads_bridge_port(struct ethsw_port_priv *port_priv, + const struct net_device *dev) +{ + struct dpaa2_switch_lag *lag = rcu_dereference_rtnl(port_priv->lag); + + if (lag && lag->bond_dev == dev) + return true; + if (port_priv->netdev == dev) + return true; + return false; +} + #endif /* __ETHSW_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h index 397d55f2bd99..9a2055c64983 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h @@ -12,7 +12,7 @@ /* DPSW Version */ #define DPSW_VER_MAJOR 8 -#define DPSW_VER_MINOR 9 +#define DPSW_VER_MINOR 13 #define DPSW_CMD_BASE_VERSION 1 #define DPSW_CMD_VERSION_2 2 @@ -92,11 +92,14 @@ #define DPSW_CMDID_CTRL_IF_SET_POOLS DPSW_CMD_ID(0x0A1) #define DPSW_CMDID_CTRL_IF_ENABLE DPSW_CMD_ID(0x0A2) #define DPSW_CMDID_CTRL_IF_DISABLE DPSW_CMD_ID(0x0A3) +#define DPSW_CMDID_SET_LAG DPSW_CMD_V2(0x0A4) #define DPSW_CMDID_CTRL_IF_SET_QUEUE DPSW_CMD_ID(0x0A6) #define DPSW_CMDID_SET_EGRESS_FLOOD DPSW_CMD_ID(0x0AC) #define DPSW_CMDID_IF_SET_LEARNING_MODE DPSW_CMD_ID(0x0AD) +#define DPSW_CMDID_IF_SET_LAG_STATE DPSW_CMD_ID(0x0B0) + /* Macros for accessing command fields smaller than 1byte */ #define DPSW_MASK(field) \ GENMASK(DPSW_##field##_SHIFT + DPSW_##field##_SIZE - 1, \ @@ -552,5 +555,18 @@ struct dpsw_cmd_if_reflection { /* only 2 bits from the LSB */ u8 filter; }; + +struct dpsw_cmd_lag { + u8 group_id; + u8 num_ifs; + u8 pad[6]; + u8 if_id[DPSW_MAX_LAG_IFS]; + u8 phase; +}; + +struct dpsw_cmd_if_set_lag_state { + __le16 if_id; + u8 tx_enabled; +}; #pragma pack(pop) #endif /* __FSL_DPSW_CMD_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.c b/drivers/net/ethernet/freescale/dpaa2/dpsw.c index ab921d75deb2..f75cbdce42ba 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpsw.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.c @@ -1659,3 +1659,63 @@ int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, return mc_send_command(mc_io, &cmd); } + +/** + * dpsw_lag_set() - Set LAG configuration + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPSW object + * @cfg: pointer to LAG configuration + * + * Return: '0' on Success; Error code otherwise. + */ +int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, + const struct dpsw_lag_cfg *cfg) +{ + struct fsl_mc_command cmd = { 0 }; + struct dpsw_cmd_lag *cmd_params; + int i = 0; + + cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_LAG, cmd_flags, token); + + if (cfg->num_ifs > DPSW_MAX_LAG_IFS) + return -EOPNOTSUPP; + + cmd_params = (struct dpsw_cmd_lag *)cmd.params; + cmd_params->group_id = cfg->group_id; + cmd_params->num_ifs = cfg->num_ifs; + cmd_params->phase = cfg->phase; + + for (i = 0; i < cfg->num_ifs; i++) + cmd_params->if_id[i] = cfg->if_id[i]; + + return mc_send_command(mc_io, &cmd); +} + +/** + * dpsw_if_set_lag_state() - Change per port LAG state + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPSW object + * @if_id: ID of the switch interface + * @tx_enabled: Value of the per port LAG state + * - 0 if the interface will not be active as part of the LAG group + * - 1 if the interface will be active in the LAG group + * + * Return: '0' on Success; Error code otherwise. + */ +int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, + u16 if_id, u8 tx_enabled) +{ + struct dpsw_cmd_if_set_lag_state *cmd_params; + struct fsl_mc_command cmd = { 0 }; + + cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_LAG_STATE, + cmd_flags, token); + + cmd_params = (struct dpsw_cmd_if_set_lag_state *)cmd.params; + cmd_params->if_id = cpu_to_le16(if_id); + cmd_params->tx_enabled = tx_enabled; + + return mc_send_command(mc_io, &cmd); +} diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.h b/drivers/net/ethernet/freescale/dpaa2/dpsw.h index b90bd363f47a..89f0267de8e9 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpsw.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.h @@ -20,6 +20,8 @@ struct fsl_mc_io; #define DPSW_MAX_IF 64 +#define DPSW_MAX_LAG_IFS 8 + int dpsw_open(struct fsl_mc_io *mc_io, u32 cmd_flags, int dpsw_id, u16 *token); int dpsw_close(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token); @@ -788,4 +790,32 @@ int dpsw_if_add_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, u16 if_id, const struct dpsw_reflection_cfg *cfg); + +/* Link Aggregation Group configuration */ + +#define DPSW_LAG_SET_PHASE_APPLY 0 +#define DPSW_LAG_SET_PHASE_CHECK 1 + +/** + * struct dpsw_lag_cfg - Configuration structure for a LAG group + * @group_id: Link aggregation group ID. Valid values are in the + * [1, DPSW_MAX_LAG_IFS] range. + * @num_ifs: Number of interfaces in this LAG group, valid range is + * [0, DPSW_MAX_LAG_IFS]. + * @if_id: Array containing the interface IDs of the ports part of a LAG group + * @phase: Use DPSW_LAG_SET_PHASE_APPLY for LAG configuration processing or + * DPSW_LAG_SET_PHASE_CHECK for LAG configuration validation. + */ +struct dpsw_lag_cfg { + u8 group_id; + u8 num_ifs; + u8 if_id[DPSW_MAX_LAG_IFS]; + u8 phase; +}; + +int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, + const struct dpsw_lag_cfg *cfg); + +int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token, + u16 if_id, u8 tx_enabled); #endif /* __FSL_DPSW_H */ diff --git a/drivers/net/ethernet/ibm/Kconfig b/drivers/net/ethernet/ibm/Kconfig index 4f4b23465c47..8e55faac2035 100644 --- a/drivers/net/ethernet/ibm/Kconfig +++ b/drivers/net/ethernet/ibm/Kconfig @@ -42,15 +42,6 @@ config IBMVETH_KUNIT_TEST source "drivers/net/ethernet/ibm/emac/Kconfig" -config EHEA - tristate "eHEA Ethernet support" - depends on IBMEBUS && SPARSEMEM - help - This driver supports the IBM pSeries eHEA ethernet adapter. - - To compile the driver as a module, choose M here. The module - will be called ehea. - config IBMVNIC tristate "IBM Virtual NIC support" depends on PPC_PSERIES diff --git a/drivers/net/ethernet/ibm/Makefile b/drivers/net/ethernet/ibm/Makefile index 1d17d0c33d4d..c7e5d891c946 100644 --- a/drivers/net/ethernet/ibm/Makefile +++ b/drivers/net/ethernet/ibm/Makefile @@ -6,4 +6,3 @@ obj-$(CONFIG_IBMVETH) += ibmveth.o obj-$(CONFIG_IBMVNIC) += ibmvnic.o obj-$(CONFIG_IBM_EMAC) += emac/ -obj-$(CONFIG_EHEA) += ehea/ diff --git a/drivers/net/ethernet/ibm/ehea/Makefile b/drivers/net/ethernet/ibm/ehea/Makefile deleted file mode 100644 index 9e1e5c7aafe2..000000000000 --- a/drivers/net/ethernet/ibm/ehea/Makefile +++ /dev/null @@ -1,7 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for the eHEA ethernet device driver for IBM eServer System p -# -ehea-y = ehea_main.o ehea_phyp.o ehea_qmr.o ehea_ethtool.o -obj-$(CONFIG_EHEA) += ehea.o - diff --git a/drivers/net/ethernet/ibm/ehea/ehea.h b/drivers/net/ethernet/ibm/ehea/ehea.h deleted file mode 100644 index 208c440a602b..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea.h +++ /dev/null @@ -1,477 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea.h - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#ifndef __EHEA_H__ -#define __EHEA_H__ - -#include <linux/module.h> -#include <linux/ethtool.h> -#include <linux/vmalloc.h> -#include <linux/if_vlan.h> -#include <linux/platform_device.h> - -#include <asm/ibmebus.h> -#include <asm/io.h> - -#define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0107" - -/* eHEA capability flags */ -#define DLPAR_PORT_ADD_REM 1 -#define DLPAR_MEM_ADD 2 -#define DLPAR_MEM_REM 4 -#define EHEA_CAPABILITIES (DLPAR_PORT_ADD_REM | DLPAR_MEM_ADD | DLPAR_MEM_REM) - -#define EHEA_MSG_DEFAULT (NETIF_MSG_LINK | NETIF_MSG_TIMER \ - | NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR) - -#define EHEA_MAX_ENTRIES_RQ1 32767 -#define EHEA_MAX_ENTRIES_RQ2 16383 -#define EHEA_MAX_ENTRIES_RQ3 16383 -#define EHEA_MAX_ENTRIES_SQ 32767 -#define EHEA_MIN_ENTRIES_QP 127 - -#define EHEA_SMALL_QUEUES - -#ifdef EHEA_SMALL_QUEUES -#define EHEA_MAX_CQE_COUNT 1023 -#define EHEA_DEF_ENTRIES_SQ 1023 -#define EHEA_DEF_ENTRIES_RQ1 1023 -#define EHEA_DEF_ENTRIES_RQ2 1023 -#define EHEA_DEF_ENTRIES_RQ3 511 -#else -#define EHEA_MAX_CQE_COUNT 4080 -#define EHEA_DEF_ENTRIES_SQ 4080 -#define EHEA_DEF_ENTRIES_RQ1 8160 -#define EHEA_DEF_ENTRIES_RQ2 2040 -#define EHEA_DEF_ENTRIES_RQ3 2040 -#endif - -#define EHEA_MAX_ENTRIES_EQ 20 - -#define EHEA_SG_SQ 2 -#define EHEA_SG_RQ1 1 -#define EHEA_SG_RQ2 0 -#define EHEA_SG_RQ3 0 - -#define EHEA_MAX_PACKET_SIZE 9022 /* for jumbo frames */ -#define EHEA_RQ2_PKT_SIZE 2048 -#define EHEA_L_PKT_SIZE 256 /* low latency */ - -/* Send completion signaling */ - -/* Protection Domain Identifier */ -#define EHEA_PD_ID 0xaabcdeff - -#define EHEA_RQ2_THRESHOLD 1 -#define EHEA_RQ3_THRESHOLD 4 /* use RQ3 threshold of 2048 bytes */ - -#define EHEA_SPEED_10G 10000 -#define EHEA_SPEED_1G 1000 -#define EHEA_SPEED_100M 100 -#define EHEA_SPEED_10M 10 -#define EHEA_SPEED_AUTONEG 0 - -/* Broadcast/Multicast registration types */ -#define EHEA_BCMC_SCOPE_ALL 0x08 -#define EHEA_BCMC_SCOPE_SINGLE 0x00 -#define EHEA_BCMC_MULTICAST 0x04 -#define EHEA_BCMC_BROADCAST 0x00 -#define EHEA_BCMC_UNTAGGED 0x02 -#define EHEA_BCMC_TAGGED 0x00 -#define EHEA_BCMC_VLANID_ALL 0x01 -#define EHEA_BCMC_VLANID_SINGLE 0x00 - -#define EHEA_CACHE_LINE 128 - -/* Memory Regions */ -#define EHEA_MR_ACC_CTRL 0x00800000 - -#define EHEA_BUSMAP_START 0x8000000000000000ULL -#define EHEA_INVAL_ADDR 0xFFFFFFFFFFFFFFFFULL -#define EHEA_DIR_INDEX_SHIFT 13 /* 8k Entries in 64k block */ -#define EHEA_TOP_INDEX_SHIFT (EHEA_DIR_INDEX_SHIFT * 2) -#define EHEA_MAP_ENTRIES (1 << EHEA_DIR_INDEX_SHIFT) -#define EHEA_MAP_SIZE (0x10000) /* currently fixed map size */ -#define EHEA_INDEX_MASK (EHEA_MAP_ENTRIES - 1) - - -#define EHEA_WATCH_DOG_TIMEOUT 10*HZ - -/* utility functions */ - -void ehea_dump(void *adr, int len, char *msg); - -#define EHEA_BMASK(pos, length) (((pos) << 16) + (length)) - -#define EHEA_BMASK_IBM(from, to) (((63 - to) << 16) + ((to) - (from) + 1)) - -#define EHEA_BMASK_SHIFTPOS(mask) (((mask) >> 16) & 0xffff) - -#define EHEA_BMASK_MASK(mask) \ - (0xffffffffffffffffULL >> ((64 - (mask)) & 0xffff)) - -#define EHEA_BMASK_SET(mask, value) \ - ((EHEA_BMASK_MASK(mask) & ((u64)(value))) << EHEA_BMASK_SHIFTPOS(mask)) - -#define EHEA_BMASK_GET(mask, value) \ - (EHEA_BMASK_MASK(mask) & (((u64)(value)) >> EHEA_BMASK_SHIFTPOS(mask))) - -/* - * Generic ehea page - */ -struct ehea_page { - u8 entries[PAGE_SIZE]; -}; - -/* - * Generic queue in linux kernel virtual memory - */ -struct hw_queue { - u64 current_q_offset; /* current queue entry */ - struct ehea_page **queue_pages; /* array of pages belonging to queue */ - u32 qe_size; /* queue entry size */ - u32 queue_length; /* queue length allocated in bytes */ - u32 pagesize; - u32 toggle_state; /* toggle flag - per page */ - u32 reserved; /* 64 bit alignment */ -}; - -/* - * For pSeries this is a 64bit memory address where - * I/O memory is mapped into CPU address space - */ -struct h_epa { - void __iomem *addr; -}; - -struct h_epa_user { - u64 addr; -}; - -struct h_epas { - struct h_epa kernel; /* kernel space accessible resource, - set to 0 if unused */ - struct h_epa_user user; /* user space accessible resource - set to 0 if unused */ -}; - -/* - * Memory map data structures - */ -struct ehea_dir_bmap -{ - u64 ent[EHEA_MAP_ENTRIES]; -}; -struct ehea_top_bmap -{ - struct ehea_dir_bmap *dir[EHEA_MAP_ENTRIES]; -}; -struct ehea_bmap -{ - struct ehea_top_bmap *top[EHEA_MAP_ENTRIES]; -}; - -struct ehea_qp; -struct ehea_cq; -struct ehea_eq; -struct ehea_port; -struct ehea_av; - -/* - * Queue attributes passed to ehea_create_qp() - */ -struct ehea_qp_init_attr { - /* input parameter */ - u32 qp_token; /* queue token */ - u8 low_lat_rq1; - u8 signalingtype; /* cqe generation flag */ - u8 rq_count; /* num of receive queues */ - u8 eqe_gen; /* eqe generation flag */ - u16 max_nr_send_wqes; /* max number of send wqes */ - u16 max_nr_rwqes_rq1; /* max number of receive wqes */ - u16 max_nr_rwqes_rq2; - u16 max_nr_rwqes_rq3; - u8 wqe_size_enc_sq; - u8 wqe_size_enc_rq1; - u8 wqe_size_enc_rq2; - u8 wqe_size_enc_rq3; - u8 swqe_imm_data_len; /* immediate data length for swqes */ - u16 port_nr; - u16 rq2_threshold; - u16 rq3_threshold; - u64 send_cq_handle; - u64 recv_cq_handle; - u64 aff_eq_handle; - - /* output parameter */ - u32 qp_nr; - u16 act_nr_send_wqes; - u16 act_nr_rwqes_rq1; - u16 act_nr_rwqes_rq2; - u16 act_nr_rwqes_rq3; - u8 act_wqe_size_enc_sq; - u8 act_wqe_size_enc_rq1; - u8 act_wqe_size_enc_rq2; - u8 act_wqe_size_enc_rq3; - u32 nr_sq_pages; - u32 nr_rq1_pages; - u32 nr_rq2_pages; - u32 nr_rq3_pages; - u32 liobn_sq; - u32 liobn_rq1; - u32 liobn_rq2; - u32 liobn_rq3; -}; - -/* - * Event Queue attributes, passed as parameter - */ -struct ehea_eq_attr { - u32 type; - u32 max_nr_of_eqes; - u8 eqe_gen; /* generate eqe flag */ - u64 eq_handle; - u32 act_nr_of_eqes; - u32 nr_pages; - u32 ist1; /* Interrupt service token */ - u32 ist2; - u32 ist3; - u32 ist4; -}; - - -/* - * Event Queue - */ -struct ehea_eq { - struct ehea_adapter *adapter; - struct hw_queue hw_queue; - u64 fw_handle; - struct h_epas epas; - spinlock_t spinlock; - struct ehea_eq_attr attr; -}; - -/* - * HEA Queues - */ -struct ehea_qp { - struct ehea_adapter *adapter; - u64 fw_handle; /* QP handle for firmware calls */ - struct hw_queue hw_squeue; - struct hw_queue hw_rqueue1; - struct hw_queue hw_rqueue2; - struct hw_queue hw_rqueue3; - struct h_epas epas; - struct ehea_qp_init_attr init_attr; -}; - -/* - * Completion Queue attributes - */ -struct ehea_cq_attr { - /* input parameter */ - u32 max_nr_of_cqes; - u32 cq_token; - u64 eq_handle; - - /* output parameter */ - u32 act_nr_of_cqes; - u32 nr_pages; -}; - -/* - * Completion Queue - */ -struct ehea_cq { - struct ehea_adapter *adapter; - u64 fw_handle; - struct hw_queue hw_queue; - struct h_epas epas; - struct ehea_cq_attr attr; -}; - -/* - * Memory Region - */ -struct ehea_mr { - struct ehea_adapter *adapter; - u64 handle; - u64 vaddr; - u32 lkey; -}; - -/* - * Port state information - */ -struct port_stats { - int poll_receive_errors; - int queue_stopped; - int err_tcp_cksum; - int err_ip_cksum; - int err_frame_crc; -}; - -#define EHEA_IRQ_NAME_SIZE 20 - -/* - * Queue SKB Array - */ -struct ehea_q_skb_arr { - struct sk_buff **arr; /* skb array for queue */ - int len; /* array length */ - int index; /* array index */ - int os_skbs; /* rq2/rq3 only: outstanding skbs */ -}; - -/* - * Port resources - */ -struct ehea_port_res { - struct napi_struct napi; - struct port_stats p_stats; - struct ehea_mr send_mr; /* send memory region */ - struct ehea_mr recv_mr; /* receive memory region */ - struct ehea_port *port; - char int_recv_name[EHEA_IRQ_NAME_SIZE]; - char int_send_name[EHEA_IRQ_NAME_SIZE]; - struct ehea_qp *qp; - struct ehea_cq *send_cq; - struct ehea_cq *recv_cq; - struct ehea_eq *eq; - struct ehea_q_skb_arr rq1_skba; - struct ehea_q_skb_arr rq2_skba; - struct ehea_q_skb_arr rq3_skba; - struct ehea_q_skb_arr sq_skba; - int sq_skba_size; - int swqe_refill_th; - atomic_t swqe_avail; - int swqe_ll_count; - u32 swqe_id_counter; - u64 tx_packets; - u64 tx_bytes; - u64 rx_packets; - u64 rx_bytes; - int sq_restart_flag; -}; - - -#define EHEA_MAX_PORTS 16 - -#define EHEA_NUM_PORTRES_FW_HANDLES 6 /* QP handle, SendCQ handle, - RecvCQ handle, EQ handle, - SendMR handle, RecvMR handle */ -#define EHEA_NUM_PORT_FW_HANDLES 1 /* EQ handle */ -#define EHEA_NUM_ADAPTER_FW_HANDLES 2 /* MR handle, NEQ handle */ - -struct ehea_adapter { - u64 handle; - struct platform_device *ofdev; - struct ehea_port *port[EHEA_MAX_PORTS]; - struct ehea_eq *neq; /* notification event queue */ - struct tasklet_struct neq_tasklet; - struct ehea_mr mr; - u32 pd; /* protection domain */ - u64 max_mc_mac; /* max number of multicast mac addresses */ - int active_ports; - struct list_head list; -}; - - -struct ehea_mc_list { - struct list_head list; - u64 macaddr; -}; - -/* kdump support */ -struct ehea_fw_handle_entry { - u64 adh; /* Adapter Handle */ - u64 fwh; /* Firmware Handle */ -}; - -struct ehea_fw_handle_array { - struct ehea_fw_handle_entry *arr; - int num_entries; - struct mutex lock; -}; - -struct ehea_bcmc_reg_entry { - u64 adh; /* Adapter Handle */ - u32 port_id; /* Logical Port Id */ - u8 reg_type; /* Registration Type */ - u64 macaddr; -}; - -struct ehea_bcmc_reg_array { - struct ehea_bcmc_reg_entry *arr; - int num_entries; - spinlock_t lock; -}; - -#define EHEA_PORT_UP 1 -#define EHEA_PORT_DOWN 0 -#define EHEA_PHY_LINK_UP 1 -#define EHEA_PHY_LINK_DOWN 0 -#define EHEA_MAX_PORT_RES 16 -struct ehea_port { - struct ehea_adapter *adapter; /* adapter that owns this port */ - struct net_device *netdev; - struct rtnl_link_stats64 stats; - struct ehea_port_res port_res[EHEA_MAX_PORT_RES]; - struct platform_device ofdev; /* Open Firmware Device */ - struct ehea_mc_list *mc_list; /* Multicast MAC addresses */ - struct ehea_eq *qp_eq; - struct work_struct reset_task; - struct delayed_work stats_work; - struct mutex port_lock; - char int_aff_name[EHEA_IRQ_NAME_SIZE]; - int allmulti; /* Indicates IFF_ALLMULTI state */ - int promisc; /* Indicates IFF_PROMISC state */ - int num_mcs; - int resets; - unsigned long flags; - u64 mac_addr; - u32 logical_port_id; - u32 port_speed; - u32 msg_enable; - u32 sig_comp_iv; - u32 state; - u8 phy_link; - u8 full_duplex; - u8 autoneg; - u8 num_def_qps; - wait_queue_head_t swqe_avail_wq; - wait_queue_head_t restart_wq; -}; - -struct port_res_cfg { - int max_entries_rcq; - int max_entries_scq; - int max_entries_sq; - int max_entries_rq1; - int max_entries_rq2; - int max_entries_rq3; -}; - -enum ehea_flag_bits { - __EHEA_STOP_XFER, - __EHEA_DISABLE_PORT_RESET -}; - -void ehea_set_ethtool_ops(struct net_device *netdev); -int ehea_sense_port_attr(struct ehea_port *port); -int ehea_set_portspeed(struct ehea_port *port, u32 port_speed); - -#endif /* __EHEA_H__ */ diff --git a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c b/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c deleted file mode 100644 index 1db5b6790a41..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c +++ /dev/null @@ -1,277 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_ethtool.c - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include "ehea.h" -#include "ehea_phyp.h" - -static int ehea_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) -{ - struct ehea_port *port = netdev_priv(dev); - u32 supported, advertising; - u32 speed; - int ret; - - ret = ehea_sense_port_attr(port); - - if (ret) - return ret; - - if (netif_carrier_ok(dev)) { - switch (port->port_speed) { - case EHEA_SPEED_10M: - speed = SPEED_10; - break; - case EHEA_SPEED_100M: - speed = SPEED_100; - break; - case EHEA_SPEED_1G: - speed = SPEED_1000; - break; - case EHEA_SPEED_10G: - speed = SPEED_10000; - break; - default: - speed = -1; - break; /* BUG */ - } - cmd->base.duplex = port->full_duplex == 1 ? - DUPLEX_FULL : DUPLEX_HALF; - } else { - speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; - } - cmd->base.speed = speed; - - if (cmd->base.speed == SPEED_10000) { - supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE); - advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE); - cmd->base.port = PORT_FIBRE; - } else { - supported = (SUPPORTED_1000baseT_Full | SUPPORTED_100baseT_Full - | SUPPORTED_100baseT_Half | SUPPORTED_10baseT_Full - | SUPPORTED_10baseT_Half | SUPPORTED_Autoneg - | SUPPORTED_TP); - advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg - | ADVERTISED_TP); - cmd->base.port = PORT_TP; - } - - cmd->base.autoneg = port->autoneg == 1 ? - AUTONEG_ENABLE : AUTONEG_DISABLE; - - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising, - advertising); - - return 0; -} - -static int ehea_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) -{ - struct ehea_port *port = netdev_priv(dev); - int ret = 0; - u32 sp; - - if (cmd->base.autoneg == AUTONEG_ENABLE) { - sp = EHEA_SPEED_AUTONEG; - goto doit; - } - - switch (cmd->base.speed) { - case SPEED_10: - if (cmd->base.duplex == DUPLEX_FULL) - sp = H_SPEED_10M_F; - else - sp = H_SPEED_10M_H; - break; - - case SPEED_100: - if (cmd->base.duplex == DUPLEX_FULL) - sp = H_SPEED_100M_F; - else - sp = H_SPEED_100M_H; - break; - - case SPEED_1000: - if (cmd->base.duplex == DUPLEX_FULL) - sp = H_SPEED_1G_F; - else - ret = -EINVAL; - break; - - case SPEED_10000: - if (cmd->base.duplex == DUPLEX_FULL) - sp = H_SPEED_10G_F; - else - ret = -EINVAL; - break; - - default: - ret = -EINVAL; - break; - } - - if (ret) - goto out; -doit: - ret = ehea_set_portspeed(port, sp); - - if (!ret) - netdev_info(dev, - "Port speed successfully set: %dMbps %s Duplex\n", - port->port_speed, - port->full_duplex == 1 ? "Full" : "Half"); -out: - return ret; -} - -static int ehea_nway_reset(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - int ret; - - ret = ehea_set_portspeed(port, EHEA_SPEED_AUTONEG); - - if (!ret) - netdev_info(port->netdev, - "Port speed successfully set: %dMbps %s Duplex\n", - port->port_speed, - port->full_duplex == 1 ? "Full" : "Half"); - return ret; -} - -static void ehea_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) -{ - strscpy(info->driver, DRV_NAME, sizeof(info->driver)); - strscpy(info->version, DRV_VERSION, sizeof(info->version)); -} - -static u32 ehea_get_msglevel(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - return port->msg_enable; -} - -static void ehea_set_msglevel(struct net_device *dev, u32 value) -{ - struct ehea_port *port = netdev_priv(dev); - port->msg_enable = value; -} - -static const char ehea_ethtool_stats_keys[][ETH_GSTRING_LEN] = { - {"sig_comp_iv"}, - {"swqe_refill_th"}, - {"port resets"}, - {"Receive errors"}, - {"TCP cksum errors"}, - {"IP cksum errors"}, - {"Frame cksum errors"}, - {"num SQ stopped"}, - {"PR0 free_swqes"}, - {"PR1 free_swqes"}, - {"PR2 free_swqes"}, - {"PR3 free_swqes"}, - {"PR4 free_swqes"}, - {"PR5 free_swqes"}, - {"PR6 free_swqes"}, - {"PR7 free_swqes"}, - {"PR8 free_swqes"}, - {"PR9 free_swqes"}, - {"PR10 free_swqes"}, - {"PR11 free_swqes"}, - {"PR12 free_swqes"}, - {"PR13 free_swqes"}, - {"PR14 free_swqes"}, - {"PR15 free_swqes"}, -}; - -static void ehea_get_strings(struct net_device *dev, u32 stringset, u8 *data) -{ - if (stringset == ETH_SS_STATS) { - memcpy(data, &ehea_ethtool_stats_keys, - sizeof(ehea_ethtool_stats_keys)); - } -} - -static int ehea_get_sset_count(struct net_device *dev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return ARRAY_SIZE(ehea_ethtool_stats_keys); - default: - return -EOPNOTSUPP; - } -} - -static void ehea_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - int i, k, tmp; - struct ehea_port *port = netdev_priv(dev); - - for (i = 0; i < ehea_get_sset_count(dev, ETH_SS_STATS); i++) - data[i] = 0; - i = 0; - - data[i++] = port->sig_comp_iv; - data[i++] = port->port_res[0].swqe_refill_th; - data[i++] = port->resets; - - for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++) - tmp += port->port_res[k].p_stats.poll_receive_errors; - data[i++] = tmp; - - for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++) - tmp += port->port_res[k].p_stats.err_tcp_cksum; - data[i++] = tmp; - - for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++) - tmp += port->port_res[k].p_stats.err_ip_cksum; - data[i++] = tmp; - - for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++) - tmp += port->port_res[k].p_stats.err_frame_crc; - data[i++] = tmp; - - for (k = 0, tmp = 0; k < EHEA_MAX_PORT_RES; k++) - tmp += port->port_res[k].p_stats.queue_stopped; - data[i++] = tmp; - - for (k = 0; k < 16; k++) - data[i++] = atomic_read(&port->port_res[k].swqe_avail); -} - -static const struct ethtool_ops ehea_ethtool_ops = { - .get_drvinfo = ehea_get_drvinfo, - .get_msglevel = ehea_get_msglevel, - .set_msglevel = ehea_set_msglevel, - .get_link = ethtool_op_get_link, - .get_strings = ehea_get_strings, - .get_sset_count = ehea_get_sset_count, - .get_ethtool_stats = ehea_get_ethtool_stats, - .nway_reset = ehea_nway_reset, /* Restart autonegotiation */ - .get_link_ksettings = ehea_get_link_ksettings, - .set_link_ksettings = ehea_set_link_ksettings, -}; - -void ehea_set_ethtool_ops(struct net_device *netdev) -{ - netdev->ethtool_ops = &ehea_ethtool_ops; -} diff --git a/drivers/net/ethernet/ibm/ehea/ehea_hw.h b/drivers/net/ethernet/ibm/ehea/ehea_hw.h deleted file mode 100644 index 590933a45d65..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_hw.h +++ /dev/null @@ -1,253 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_hw.h - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#ifndef __EHEA_HW_H__ -#define __EHEA_HW_H__ - -#define QPX_SQA_VALUE EHEA_BMASK_IBM(48, 63) -#define QPX_RQ1A_VALUE EHEA_BMASK_IBM(48, 63) -#define QPX_RQ2A_VALUE EHEA_BMASK_IBM(48, 63) -#define QPX_RQ3A_VALUE EHEA_BMASK_IBM(48, 63) - -#define QPTEMM_OFFSET(x) offsetof(struct ehea_qptemm, x) - -struct ehea_qptemm { - u64 qpx_hcr; - u64 qpx_c; - u64 qpx_herr; - u64 qpx_aer; - u64 qpx_sqa; - u64 qpx_sqc; - u64 qpx_rq1a; - u64 qpx_rq1c; - u64 qpx_st; - u64 qpx_aerr; - u64 qpx_tenure; - u64 qpx_reserved1[(0x098 - 0x058) / 8]; - u64 qpx_portp; - u64 qpx_reserved2[(0x100 - 0x0A0) / 8]; - u64 qpx_t; - u64 qpx_sqhp; - u64 qpx_sqptp; - u64 qpx_reserved3[(0x140 - 0x118) / 8]; - u64 qpx_sqwsize; - u64 qpx_reserved4[(0x170 - 0x148) / 8]; - u64 qpx_sqsize; - u64 qpx_reserved5[(0x1B0 - 0x178) / 8]; - u64 qpx_sigt; - u64 qpx_wqecnt; - u64 qpx_rq1hp; - u64 qpx_rq1ptp; - u64 qpx_rq1size; - u64 qpx_reserved6[(0x220 - 0x1D8) / 8]; - u64 qpx_rq1wsize; - u64 qpx_reserved7[(0x240 - 0x228) / 8]; - u64 qpx_pd; - u64 qpx_scqn; - u64 qpx_rcqn; - u64 qpx_aeqn; - u64 reserved49; - u64 qpx_ram; - u64 qpx_reserved8[(0x300 - 0x270) / 8]; - u64 qpx_rq2a; - u64 qpx_rq2c; - u64 qpx_rq2hp; - u64 qpx_rq2ptp; - u64 qpx_rq2size; - u64 qpx_rq2wsize; - u64 qpx_rq2th; - u64 qpx_rq3a; - u64 qpx_rq3c; - u64 qpx_rq3hp; - u64 qpx_rq3ptp; - u64 qpx_rq3size; - u64 qpx_rq3wsize; - u64 qpx_rq3th; - u64 qpx_lpn; - u64 qpx_reserved9[(0x400 - 0x378) / 8]; - u64 reserved_ext[(0x500 - 0x400) / 8]; - u64 reserved2[(0x1000 - 0x500) / 8]; -}; - -#define MRx_HCR_LPARID_VALID EHEA_BMASK_IBM(0, 0) - -#define MRMWMM_OFFSET(x) offsetof(struct ehea_mrmwmm, x) - -struct ehea_mrmwmm { - u64 mrx_hcr; - u64 mrx_c; - u64 mrx_herr; - u64 mrx_aer; - u64 mrx_pp; - u64 reserved1; - u64 reserved2; - u64 reserved3; - u64 reserved4[(0x200 - 0x40) / 8]; - u64 mrx_ctl[64]; -}; - -#define QPEDMM_OFFSET(x) offsetof(struct ehea_qpedmm, x) - -struct ehea_qpedmm { - - u64 reserved0[(0x400) / 8]; - u64 qpedx_phh; - u64 qpedx_ppsgp; - u64 qpedx_ppsgu; - u64 qpedx_ppdgp; - u64 qpedx_ppdgu; - u64 qpedx_aph; - u64 qpedx_apsgp; - u64 qpedx_apsgu; - u64 qpedx_apdgp; - u64 qpedx_apdgu; - u64 qpedx_apav; - u64 qpedx_apsav; - u64 qpedx_hcr; - u64 reserved1[4]; - u64 qpedx_rrl0; - u64 qpedx_rrrkey0; - u64 qpedx_rrva0; - u64 reserved2; - u64 qpedx_rrl1; - u64 qpedx_rrrkey1; - u64 qpedx_rrva1; - u64 reserved3; - u64 qpedx_rrl2; - u64 qpedx_rrrkey2; - u64 qpedx_rrva2; - u64 reserved4; - u64 qpedx_rrl3; - u64 qpedx_rrrkey3; - u64 qpedx_rrva3; -}; - -#define CQX_FECADDER EHEA_BMASK_IBM(32, 63) -#define CQX_FEC_CQE_CNT EHEA_BMASK_IBM(32, 63) -#define CQX_N1_GENERATE_COMP_EVENT EHEA_BMASK_IBM(0, 0) -#define CQX_EP_EVENT_PENDING EHEA_BMASK_IBM(0, 0) - -#define CQTEMM_OFFSET(x) offsetof(struct ehea_cqtemm, x) - -struct ehea_cqtemm { - u64 cqx_hcr; - u64 cqx_c; - u64 cqx_herr; - u64 cqx_aer; - u64 cqx_ptp; - u64 cqx_tp; - u64 cqx_fec; - u64 cqx_feca; - u64 cqx_ep; - u64 cqx_eq; - u64 reserved1; - u64 cqx_n0; - u64 cqx_n1; - u64 reserved2[(0x1000 - 0x60) / 8]; -}; - -#define EQTEMM_OFFSET(x) offsetof(struct ehea_eqtemm, x) - -struct ehea_eqtemm { - u64 eqx_hcr; - u64 eqx_c; - u64 eqx_herr; - u64 eqx_aer; - u64 eqx_ptp; - u64 eqx_tp; - u64 eqx_ssba; - u64 eqx_psba; - u64 eqx_cec; - u64 eqx_meql; - u64 eqx_xisbi; - u64 eqx_xisc; - u64 eqx_it; -}; - -/* - * These access functions will be changed when the dissuccsion about - * the new access methods for POWER has settled. - */ - -static inline u64 epa_load(struct h_epa epa, u32 offset) -{ - return __raw_readq((void __iomem *)(epa.addr + offset)); -} - -static inline void epa_store(struct h_epa epa, u32 offset, u64 value) -{ - __raw_writeq(value, (void __iomem *)(epa.addr + offset)); - epa_load(epa, offset); /* synchronize explicitly to eHEA */ -} - -static inline void epa_store_acc(struct h_epa epa, u32 offset, u64 value) -{ - __raw_writeq(value, (void __iomem *)(epa.addr + offset)); -} - -#define epa_store_cq(epa, offset, value)\ - epa_store(epa, CQTEMM_OFFSET(offset), value) -#define epa_load_cq(epa, offset)\ - epa_load(epa, CQTEMM_OFFSET(offset)) - -static inline void ehea_update_sqa(struct ehea_qp *qp, u16 nr_wqes) -{ - struct h_epa epa = qp->epas.kernel; - epa_store_acc(epa, QPTEMM_OFFSET(qpx_sqa), - EHEA_BMASK_SET(QPX_SQA_VALUE, nr_wqes)); -} - -static inline void ehea_update_rq3a(struct ehea_qp *qp, u16 nr_wqes) -{ - struct h_epa epa = qp->epas.kernel; - epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq3a), - EHEA_BMASK_SET(QPX_RQ1A_VALUE, nr_wqes)); -} - -static inline void ehea_update_rq2a(struct ehea_qp *qp, u16 nr_wqes) -{ - struct h_epa epa = qp->epas.kernel; - epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq2a), - EHEA_BMASK_SET(QPX_RQ2A_VALUE, nr_wqes)); -} - -static inline void ehea_update_rq1a(struct ehea_qp *qp, u16 nr_wqes) -{ - struct h_epa epa = qp->epas.kernel; - epa_store_acc(epa, QPTEMM_OFFSET(qpx_rq1a), - EHEA_BMASK_SET(QPX_RQ3A_VALUE, nr_wqes)); -} - -static inline void ehea_update_feca(struct ehea_cq *cq, u32 nr_cqes) -{ - struct h_epa epa = cq->epas.kernel; - epa_store_acc(epa, CQTEMM_OFFSET(cqx_feca), - EHEA_BMASK_SET(CQX_FECADDER, nr_cqes)); -} - -static inline void ehea_reset_cq_n1(struct ehea_cq *cq) -{ - struct h_epa epa = cq->epas.kernel; - epa_store_cq(epa, cqx_n1, - EHEA_BMASK_SET(CQX_N1_GENERATE_COMP_EVENT, 1)); -} - -static inline void ehea_reset_cq_ep(struct ehea_cq *my_cq) -{ - struct h_epa epa = my_cq->epas.kernel; - epa_store_acc(epa, CQTEMM_OFFSET(cqx_ep), - EHEA_BMASK_SET(CQX_EP_EVENT_PENDING, 0)); -} - -#endif /* __EHEA_HW_H__ */ diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c deleted file mode 100644 index bfc8699a05b9..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ /dev/null @@ -1,3581 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_main.c - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/device.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/if.h> -#include <linux/list.h> -#include <linux/slab.h> -#include <linux/if_ether.h> -#include <linux/notifier.h> -#include <linux/reboot.h> -#include <linux/memory.h> -#include <asm/kexec.h> -#include <linux/mutex.h> -#include <linux/prefetch.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/platform_device.h> - -#include <net/ip.h> - -#include "ehea.h" -#include "ehea_qmr.h" -#include "ehea_phyp.h" - - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christoph Raisch <raisch@de.ibm.com>"); -MODULE_DESCRIPTION("IBM eServer HEA Driver"); -MODULE_VERSION(DRV_VERSION); - - -static int msg_level = -1; -static int rq1_entries = EHEA_DEF_ENTRIES_RQ1; -static int rq2_entries = EHEA_DEF_ENTRIES_RQ2; -static int rq3_entries = EHEA_DEF_ENTRIES_RQ3; -static int sq_entries = EHEA_DEF_ENTRIES_SQ; -static int use_mcs = 1; -static int prop_carrier_state; - -module_param(msg_level, int, 0); -module_param(rq1_entries, int, 0); -module_param(rq2_entries, int, 0); -module_param(rq3_entries, int, 0); -module_param(sq_entries, int, 0); -module_param(prop_carrier_state, int, 0); -module_param(use_mcs, int, 0); - -MODULE_PARM_DESC(msg_level, "msg_level"); -MODULE_PARM_DESC(prop_carrier_state, "Propagate carrier state of physical " - "port to stack. 1:yes, 0:no. Default = 0 "); -MODULE_PARM_DESC(rq3_entries, "Number of entries for Receive Queue 3 " - "[2^x - 1], x = [7..14]. Default = " - __MODULE_STRING(EHEA_DEF_ENTRIES_RQ3) ")"); -MODULE_PARM_DESC(rq2_entries, "Number of entries for Receive Queue 2 " - "[2^x - 1], x = [7..14]. Default = " - __MODULE_STRING(EHEA_DEF_ENTRIES_RQ2) ")"); -MODULE_PARM_DESC(rq1_entries, "Number of entries for Receive Queue 1 " - "[2^x - 1], x = [7..14]. Default = " - __MODULE_STRING(EHEA_DEF_ENTRIES_RQ1) ")"); -MODULE_PARM_DESC(sq_entries, " Number of entries for the Send Queue " - "[2^x - 1], x = [7..14]. Default = " - __MODULE_STRING(EHEA_DEF_ENTRIES_SQ) ")"); -MODULE_PARM_DESC(use_mcs, " Multiple receive queues, 1: enable, 0: disable, " - "Default = 1"); - -static int port_name_cnt; -static LIST_HEAD(adapter_list); -static unsigned long ehea_driver_flags; -static DEFINE_MUTEX(dlpar_mem_lock); -static struct ehea_fw_handle_array ehea_fw_handles; -static struct ehea_bcmc_reg_array ehea_bcmc_regs; - - -static int ehea_probe_adapter(struct platform_device *dev); - -static void ehea_remove(struct platform_device *dev); - -static const struct of_device_id ehea_module_device_table[] = { - { - .name = "lhea", - .compatible = "IBM,lhea", - }, - { - .type = "network", - .compatible = "IBM,lhea-ethernet", - }, - {}, -}; -MODULE_DEVICE_TABLE(of, ehea_module_device_table); - -static const struct of_device_id ehea_device_table[] = { - { - .name = "lhea", - .compatible = "IBM,lhea", - }, - {}, -}; -MODULE_DEVICE_TABLE(of, ehea_device_table); - -static struct platform_driver ehea_driver = { - .driver = { - .name = "ehea", - .owner = THIS_MODULE, - .of_match_table = ehea_device_table, - }, - .probe = ehea_probe_adapter, - .remove = ehea_remove, -}; - -void ehea_dump(void *adr, int len, char *msg) -{ - int x; - unsigned char *deb = adr; - for (x = 0; x < len; x += 16) { - pr_info("%s adr=%p ofs=%04x %016llx %016llx\n", - msg, deb, x, *((u64 *)&deb[0]), *((u64 *)&deb[8])); - deb += 16; - } -} - -static void ehea_schedule_port_reset(struct ehea_port *port) -{ - if (!test_bit(__EHEA_DISABLE_PORT_RESET, &port->flags)) - schedule_work(&port->reset_task); -} - -static void ehea_update_firmware_handles(void) -{ - struct ehea_fw_handle_entry *arr = NULL; - struct ehea_adapter *adapter; - int num_adapters = 0; - int num_ports = 0; - int num_portres = 0; - int i = 0; - int num_fw_handles, k, l; - - /* Determine number of handles */ - mutex_lock(&ehea_fw_handles.lock); - - list_for_each_entry(adapter, &adapter_list, list) { - num_adapters++; - - for (k = 0; k < EHEA_MAX_PORTS; k++) { - struct ehea_port *port = adapter->port[k]; - - if (!port || (port->state != EHEA_PORT_UP)) - continue; - - num_ports++; - num_portres += port->num_def_qps; - } - } - - num_fw_handles = num_adapters * EHEA_NUM_ADAPTER_FW_HANDLES + - num_ports * EHEA_NUM_PORT_FW_HANDLES + - num_portres * EHEA_NUM_PORTRES_FW_HANDLES; - - if (num_fw_handles) { - arr = kzalloc_objs(*arr, num_fw_handles); - if (!arr) - goto out; /* Keep the existing array */ - } else - goto out_update; - - list_for_each_entry(adapter, &adapter_list, list) { - if (num_adapters == 0) - break; - - for (k = 0; k < EHEA_MAX_PORTS; k++) { - struct ehea_port *port = adapter->port[k]; - - if (!port || (port->state != EHEA_PORT_UP) || - (num_ports == 0)) - continue; - - for (l = 0; l < port->num_def_qps; l++) { - struct ehea_port_res *pr = &port->port_res[l]; - - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->qp->fw_handle; - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->send_cq->fw_handle; - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->recv_cq->fw_handle; - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->eq->fw_handle; - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->send_mr.handle; - arr[i].adh = adapter->handle; - arr[i++].fwh = pr->recv_mr.handle; - } - arr[i].adh = adapter->handle; - arr[i++].fwh = port->qp_eq->fw_handle; - num_ports--; - } - - arr[i].adh = adapter->handle; - arr[i++].fwh = adapter->neq->fw_handle; - - if (adapter->mr.handle) { - arr[i].adh = adapter->handle; - arr[i++].fwh = adapter->mr.handle; - } - num_adapters--; - } - -out_update: - kfree(ehea_fw_handles.arr); - ehea_fw_handles.arr = arr; - ehea_fw_handles.num_entries = i; -out: - mutex_unlock(&ehea_fw_handles.lock); -} - -static void ehea_update_bcmc_registrations(void) -{ - unsigned long flags; - struct ehea_bcmc_reg_entry *arr = NULL; - struct ehea_adapter *adapter; - struct ehea_mc_list *mc_entry; - int num_registrations = 0; - int i = 0; - int k; - - spin_lock_irqsave(&ehea_bcmc_regs.lock, flags); - - /* Determine number of registrations */ - list_for_each_entry(adapter, &adapter_list, list) - for (k = 0; k < EHEA_MAX_PORTS; k++) { - struct ehea_port *port = adapter->port[k]; - - if (!port || (port->state != EHEA_PORT_UP)) - continue; - - num_registrations += 2; /* Broadcast registrations */ - - list_for_each_entry(mc_entry, &port->mc_list->list,list) - num_registrations += 2; - } - - if (num_registrations) { - arr = kzalloc_objs(*arr, num_registrations, GFP_ATOMIC); - if (!arr) - goto out; /* Keep the existing array */ - } else - goto out_update; - - list_for_each_entry(adapter, &adapter_list, list) { - for (k = 0; k < EHEA_MAX_PORTS; k++) { - struct ehea_port *port = adapter->port[k]; - - if (!port || (port->state != EHEA_PORT_UP)) - continue; - - if (num_registrations == 0) - goto out_update; - - arr[i].adh = adapter->handle; - arr[i].port_id = port->logical_port_id; - arr[i].reg_type = EHEA_BCMC_BROADCAST | - EHEA_BCMC_UNTAGGED; - arr[i++].macaddr = port->mac_addr; - - arr[i].adh = adapter->handle; - arr[i].port_id = port->logical_port_id; - arr[i].reg_type = EHEA_BCMC_BROADCAST | - EHEA_BCMC_VLANID_ALL; - arr[i++].macaddr = port->mac_addr; - num_registrations -= 2; - - list_for_each_entry(mc_entry, - &port->mc_list->list, list) { - if (num_registrations == 0) - goto out_update; - - arr[i].adh = adapter->handle; - arr[i].port_id = port->logical_port_id; - arr[i].reg_type = EHEA_BCMC_MULTICAST | - EHEA_BCMC_UNTAGGED; - if (mc_entry->macaddr == 0) - arr[i].reg_type |= EHEA_BCMC_SCOPE_ALL; - arr[i++].macaddr = mc_entry->macaddr; - - arr[i].adh = adapter->handle; - arr[i].port_id = port->logical_port_id; - arr[i].reg_type = EHEA_BCMC_MULTICAST | - EHEA_BCMC_VLANID_ALL; - if (mc_entry->macaddr == 0) - arr[i].reg_type |= EHEA_BCMC_SCOPE_ALL; - arr[i++].macaddr = mc_entry->macaddr; - num_registrations -= 2; - } - } - } - -out_update: - kfree(ehea_bcmc_regs.arr); - ehea_bcmc_regs.arr = arr; - ehea_bcmc_regs.num_entries = i; -out: - spin_unlock_irqrestore(&ehea_bcmc_regs.lock, flags); -} - -static void ehea_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - struct ehea_port *port = netdev_priv(dev); - u64 rx_packets = 0, tx_packets = 0, rx_bytes = 0, tx_bytes = 0; - int i; - - for (i = 0; i < port->num_def_qps; i++) { - rx_packets += port->port_res[i].rx_packets; - rx_bytes += port->port_res[i].rx_bytes; - } - - for (i = 0; i < port->num_def_qps; i++) { - tx_packets += port->port_res[i].tx_packets; - tx_bytes += port->port_res[i].tx_bytes; - } - - stats->tx_packets = tx_packets; - stats->rx_bytes = rx_bytes; - stats->tx_bytes = tx_bytes; - stats->rx_packets = rx_packets; - - stats->multicast = port->stats.multicast; - stats->rx_errors = port->stats.rx_errors; -} - -static void ehea_update_stats(struct work_struct *work) -{ - struct ehea_port *port = - container_of(work, struct ehea_port, stats_work.work); - struct net_device *dev = port->netdev; - struct rtnl_link_stats64 *stats = &port->stats; - struct hcp_ehea_port_cb2 *cb2; - u64 hret; - - cb2 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb2) { - netdev_err(dev, "No mem for cb2. Some interface statistics were not updated\n"); - goto resched; - } - - hret = ehea_h_query_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB2, H_PORT_CB2_ALL, cb2); - if (hret != H_SUCCESS) { - netdev_err(dev, "query_ehea_port failed\n"); - goto out_herr; - } - - if (netif_msg_hw(port)) - ehea_dump(cb2, sizeof(*cb2), "net_device_stats"); - - stats->multicast = cb2->rxmcp; - stats->rx_errors = cb2->rxuerr; - -out_herr: - free_page((unsigned long)cb2); -resched: - schedule_delayed_work(&port->stats_work, - round_jiffies_relative(msecs_to_jiffies(1000))); -} - -static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes) -{ - struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr; - struct net_device *dev = pr->port->netdev; - int max_index_mask = pr->rq1_skba.len - 1; - int fill_wqes = pr->rq1_skba.os_skbs + nr_of_wqes; - int adder = 0; - int i; - - pr->rq1_skba.os_skbs = 0; - - if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) { - if (nr_of_wqes > 0) - pr->rq1_skba.index = index; - pr->rq1_skba.os_skbs = fill_wqes; - return; - } - - for (i = 0; i < fill_wqes; i++) { - if (!skb_arr_rq1[index]) { - skb_arr_rq1[index] = netdev_alloc_skb(dev, - EHEA_L_PKT_SIZE); - if (!skb_arr_rq1[index]) { - pr->rq1_skba.os_skbs = fill_wqes - i; - break; - } - } - index--; - index &= max_index_mask; - adder++; - } - - if (adder == 0) - return; - - /* Ring doorbell */ - ehea_update_rq1a(pr->qp, adder); -} - -static void ehea_init_fill_rq1(struct ehea_port_res *pr, int nr_rq1a) -{ - struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr; - struct net_device *dev = pr->port->netdev; - int i; - - if (nr_rq1a > pr->rq1_skba.len) { - netdev_err(dev, "NR_RQ1A bigger than skb array len\n"); - return; - } - - for (i = 0; i < nr_rq1a; i++) { - skb_arr_rq1[i] = netdev_alloc_skb(dev, EHEA_L_PKT_SIZE); - if (!skb_arr_rq1[i]) - break; - } - /* Ring doorbell */ - ehea_update_rq1a(pr->qp, i - 1); -} - -static int ehea_refill_rq_def(struct ehea_port_res *pr, - struct ehea_q_skb_arr *q_skba, int rq_nr, - int num_wqes, int wqe_type, int packet_size) -{ - struct net_device *dev = pr->port->netdev; - struct ehea_qp *qp = pr->qp; - struct sk_buff **skb_arr = q_skba->arr; - struct ehea_rwqe *rwqe; - int i, index, max_index_mask, fill_wqes; - int adder = 0; - int ret = 0; - - fill_wqes = q_skba->os_skbs + num_wqes; - q_skba->os_skbs = 0; - - if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) { - q_skba->os_skbs = fill_wqes; - return ret; - } - - index = q_skba->index; - max_index_mask = q_skba->len - 1; - for (i = 0; i < fill_wqes; i++) { - u64 tmp_addr; - struct sk_buff *skb; - - skb = netdev_alloc_skb_ip_align(dev, packet_size); - if (!skb) { - q_skba->os_skbs = fill_wqes - i; - if (q_skba->os_skbs == q_skba->len - 2) { - netdev_info(pr->port->netdev, - "rq%i ran dry - no mem for skb\n", - rq_nr); - ret = -ENOMEM; - } - break; - } - - skb_arr[index] = skb; - tmp_addr = ehea_map_vaddr(skb->data); - if (tmp_addr == -1) { - dev_consume_skb_any(skb); - q_skba->os_skbs = fill_wqes - i; - ret = 0; - break; - } - - rwqe = ehea_get_next_rwqe(qp, rq_nr); - rwqe->wr_id = EHEA_BMASK_SET(EHEA_WR_ID_TYPE, wqe_type) - | EHEA_BMASK_SET(EHEA_WR_ID_INDEX, index); - rwqe->sg_list[0].l_key = pr->recv_mr.lkey; - rwqe->sg_list[0].vaddr = tmp_addr; - rwqe->sg_list[0].len = packet_size; - rwqe->data_segments = 1; - - index++; - index &= max_index_mask; - adder++; - } - - q_skba->index = index; - if (adder == 0) - goto out; - - /* Ring doorbell */ - iosync(); - if (rq_nr == 2) - ehea_update_rq2a(pr->qp, adder); - else - ehea_update_rq3a(pr->qp, adder); -out: - return ret; -} - - -static int ehea_refill_rq2(struct ehea_port_res *pr, int nr_of_wqes) -{ - return ehea_refill_rq_def(pr, &pr->rq2_skba, 2, - nr_of_wqes, EHEA_RWQE2_TYPE, - EHEA_RQ2_PKT_SIZE); -} - - -static int ehea_refill_rq3(struct ehea_port_res *pr, int nr_of_wqes) -{ - return ehea_refill_rq_def(pr, &pr->rq3_skba, 3, - nr_of_wqes, EHEA_RWQE3_TYPE, - EHEA_MAX_PACKET_SIZE); -} - -static inline int ehea_check_cqe(struct ehea_cqe *cqe, int *rq_num) -{ - *rq_num = (cqe->type & EHEA_CQE_TYPE_RQ) >> 5; - if ((cqe->status & EHEA_CQE_STAT_ERR_MASK) == 0) - return 0; - if (((cqe->status & EHEA_CQE_STAT_ERR_TCP) != 0) && - (cqe->header_length == 0)) - return 0; - return -EINVAL; -} - -static inline void ehea_fill_skb(struct net_device *dev, - struct sk_buff *skb, struct ehea_cqe *cqe, - struct ehea_port_res *pr) -{ - int length = cqe->num_bytes_transfered - 4; /*remove CRC */ - - skb_put(skb, length); - skb->protocol = eth_type_trans(skb, dev); - - /* The packet was not an IPV4 packet so a complemented checksum was - calculated. The value is found in the Internet Checksum field. */ - if (cqe->status & EHEA_CQE_BLIND_CKSUM) { - skb->ip_summed = CHECKSUM_COMPLETE; - skb->csum = csum_unfold(~cqe->inet_checksum_value); - } else - skb->ip_summed = CHECKSUM_UNNECESSARY; - - skb_record_rx_queue(skb, pr - &pr->port->port_res[0]); -} - -static inline struct sk_buff *get_skb_by_index(struct sk_buff **skb_array, - int arr_len, - struct ehea_cqe *cqe) -{ - int skb_index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, cqe->wr_id); - struct sk_buff *skb; - void *pref; - int x; - - x = skb_index + 1; - x &= (arr_len - 1); - - pref = skb_array[x]; - if (pref) { - prefetchw(pref); - prefetchw(pref + EHEA_CACHE_LINE); - - pref = (skb_array[x]->data); - prefetch(pref); - prefetch(pref + EHEA_CACHE_LINE); - prefetch(pref + EHEA_CACHE_LINE * 2); - prefetch(pref + EHEA_CACHE_LINE * 3); - } - - skb = skb_array[skb_index]; - skb_array[skb_index] = NULL; - return skb; -} - -static inline struct sk_buff *get_skb_by_index_ll(struct sk_buff **skb_array, - int arr_len, int wqe_index) -{ - struct sk_buff *skb; - void *pref; - int x; - - x = wqe_index + 1; - x &= (arr_len - 1); - - pref = skb_array[x]; - if (pref) { - prefetchw(pref); - prefetchw(pref + EHEA_CACHE_LINE); - - pref = (skb_array[x]->data); - prefetchw(pref); - prefetchw(pref + EHEA_CACHE_LINE); - } - - skb = skb_array[wqe_index]; - skb_array[wqe_index] = NULL; - return skb; -} - -static int ehea_treat_poll_error(struct ehea_port_res *pr, int rq, - struct ehea_cqe *cqe, int *processed_rq2, - int *processed_rq3) -{ - struct sk_buff *skb; - - if (cqe->status & EHEA_CQE_STAT_ERR_TCP) - pr->p_stats.err_tcp_cksum++; - if (cqe->status & EHEA_CQE_STAT_ERR_IP) - pr->p_stats.err_ip_cksum++; - if (cqe->status & EHEA_CQE_STAT_ERR_CRC) - pr->p_stats.err_frame_crc++; - - if (rq == 2) { - *processed_rq2 += 1; - skb = get_skb_by_index(pr->rq2_skba.arr, pr->rq2_skba.len, cqe); - dev_kfree_skb(skb); - } else if (rq == 3) { - *processed_rq3 += 1; - skb = get_skb_by_index(pr->rq3_skba.arr, pr->rq3_skba.len, cqe); - dev_kfree_skb(skb); - } - - if (cqe->status & EHEA_CQE_STAT_FAT_ERR_MASK) { - if (netif_msg_rx_err(pr->port)) { - pr_err("Critical receive error for QP %d. Resetting port.\n", - pr->qp->init_attr.qp_nr); - ehea_dump(cqe, sizeof(*cqe), "CQE"); - } - ehea_schedule_port_reset(pr->port); - return 1; - } - - return 0; -} - -static int ehea_proc_rwqes(struct net_device *dev, - struct ehea_port_res *pr, - int budget) -{ - struct ehea_port *port = pr->port; - struct ehea_qp *qp = pr->qp; - struct ehea_cqe *cqe; - struct sk_buff *skb; - struct sk_buff **skb_arr_rq1 = pr->rq1_skba.arr; - struct sk_buff **skb_arr_rq2 = pr->rq2_skba.arr; - struct sk_buff **skb_arr_rq3 = pr->rq3_skba.arr; - int skb_arr_rq1_len = pr->rq1_skba.len; - int skb_arr_rq2_len = pr->rq2_skba.len; - int skb_arr_rq3_len = pr->rq3_skba.len; - int processed, processed_rq1, processed_rq2, processed_rq3; - u64 processed_bytes = 0; - int wqe_index, last_wqe_index, rq, port_reset; - - processed = processed_rq1 = processed_rq2 = processed_rq3 = 0; - last_wqe_index = 0; - - cqe = ehea_poll_rq1(qp, &wqe_index); - while ((processed < budget) && cqe) { - ehea_inc_rq1(qp); - processed_rq1++; - processed++; - if (netif_msg_rx_status(port)) - ehea_dump(cqe, sizeof(*cqe), "CQE"); - - last_wqe_index = wqe_index; - rmb(); - if (!ehea_check_cqe(cqe, &rq)) { - if (rq == 1) { - /* LL RQ1 */ - skb = get_skb_by_index_ll(skb_arr_rq1, - skb_arr_rq1_len, - wqe_index); - if (unlikely(!skb)) { - netif_info(port, rx_err, dev, - "LL rq1: skb=NULL\n"); - - skb = netdev_alloc_skb(dev, - EHEA_L_PKT_SIZE); - if (!skb) - break; - } - skb_copy_to_linear_data(skb, ((char *)cqe) + 64, - cqe->num_bytes_transfered - 4); - ehea_fill_skb(dev, skb, cqe, pr); - } else if (rq == 2) { - /* RQ2 */ - skb = get_skb_by_index(skb_arr_rq2, - skb_arr_rq2_len, cqe); - if (unlikely(!skb)) { - netif_err(port, rx_err, dev, - "rq2: skb=NULL\n"); - break; - } - ehea_fill_skb(dev, skb, cqe, pr); - processed_rq2++; - } else { - /* RQ3 */ - skb = get_skb_by_index(skb_arr_rq3, - skb_arr_rq3_len, cqe); - if (unlikely(!skb)) { - netif_err(port, rx_err, dev, - "rq3: skb=NULL\n"); - break; - } - ehea_fill_skb(dev, skb, cqe, pr); - processed_rq3++; - } - - processed_bytes += skb->len; - - if (cqe->status & EHEA_CQE_VLAN_TAG_XTRACT) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), - cqe->vlan_tag); - - napi_gro_receive(&pr->napi, skb); - } else { - pr->p_stats.poll_receive_errors++; - port_reset = ehea_treat_poll_error(pr, rq, cqe, - &processed_rq2, - &processed_rq3); - if (port_reset) - break; - } - cqe = ehea_poll_rq1(qp, &wqe_index); - } - - pr->rx_packets += processed; - pr->rx_bytes += processed_bytes; - - ehea_refill_rq1(pr, last_wqe_index, processed_rq1); - ehea_refill_rq2(pr, processed_rq2); - ehea_refill_rq3(pr, processed_rq3); - - return processed; -} - -#define SWQE_RESTART_CHECK 0xdeadbeaff00d0000ull - -static void reset_sq_restart_flag(struct ehea_port *port) -{ - int i; - - for (i = 0; i < port->num_def_qps; i++) { - struct ehea_port_res *pr = &port->port_res[i]; - pr->sq_restart_flag = 0; - } - wake_up(&port->restart_wq); -} - -static void check_sqs(struct ehea_port *port) -{ - struct ehea_swqe *swqe; - int swqe_index; - int i; - - for (i = 0; i < port->num_def_qps; i++) { - struct ehea_port_res *pr = &port->port_res[i]; - int ret; - swqe = ehea_get_swqe(pr->qp, &swqe_index); - memset(swqe, 0, SWQE_HEADER_SIZE); - atomic_dec(&pr->swqe_avail); - - swqe->tx_control |= EHEA_SWQE_PURGE; - swqe->wr_id = SWQE_RESTART_CHECK; - swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION; - swqe->tx_control |= EHEA_SWQE_IMM_DATA_PRESENT; - swqe->immediate_data_length = 80; - - ehea_post_swqe(pr->qp, swqe); - - ret = wait_event_timeout(port->restart_wq, - pr->sq_restart_flag == 0, - msecs_to_jiffies(100)); - - if (!ret) { - pr_err("HW/SW queues out of sync\n"); - ehea_schedule_port_reset(pr->port); - return; - } - } -} - - -static struct ehea_cqe *ehea_proc_cqes(struct ehea_port_res *pr, int my_quota) -{ - struct sk_buff *skb; - struct ehea_cq *send_cq = pr->send_cq; - struct ehea_cqe *cqe; - int quota = my_quota; - int cqe_counter = 0; - int swqe_av = 0; - int index; - struct netdev_queue *txq = netdev_get_tx_queue(pr->port->netdev, - pr - &pr->port->port_res[0]); - - cqe = ehea_poll_cq(send_cq); - while (cqe && (quota > 0)) { - ehea_inc_cq(send_cq); - - cqe_counter++; - rmb(); - - if (cqe->wr_id == SWQE_RESTART_CHECK) { - pr->sq_restart_flag = 1; - swqe_av++; - break; - } - - if (cqe->status & EHEA_CQE_STAT_ERR_MASK) { - pr_err("Bad send completion status=0x%04X\n", - cqe->status); - - if (netif_msg_tx_err(pr->port)) - ehea_dump(cqe, sizeof(*cqe), "Send CQE"); - - if (cqe->status & EHEA_CQE_STAT_RESET_MASK) { - pr_err("Resetting port\n"); - ehea_schedule_port_reset(pr->port); - break; - } - } - - if (netif_msg_tx_done(pr->port)) - ehea_dump(cqe, sizeof(*cqe), "CQE"); - - if (likely(EHEA_BMASK_GET(EHEA_WR_ID_TYPE, cqe->wr_id) - == EHEA_SWQE2_TYPE)) { - - index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, cqe->wr_id); - skb = pr->sq_skba.arr[index]; - dev_consume_skb_any(skb); - pr->sq_skba.arr[index] = NULL; - } - - swqe_av += EHEA_BMASK_GET(EHEA_WR_ID_REFILL, cqe->wr_id); - quota--; - - cqe = ehea_poll_cq(send_cq); - } - - ehea_update_feca(send_cq, cqe_counter); - atomic_add(swqe_av, &pr->swqe_avail); - - if (unlikely(netif_tx_queue_stopped(txq) && - (atomic_read(&pr->swqe_avail) >= pr->swqe_refill_th))) { - __netif_tx_lock(txq, smp_processor_id()); - if (netif_tx_queue_stopped(txq) && - (atomic_read(&pr->swqe_avail) >= pr->swqe_refill_th)) - netif_tx_wake_queue(txq); - __netif_tx_unlock(txq); - } - - wake_up(&pr->port->swqe_avail_wq); - - return cqe; -} - -#define EHEA_POLL_MAX_CQES 65535 - -static int ehea_poll(struct napi_struct *napi, int budget) -{ - struct ehea_port_res *pr = container_of(napi, struct ehea_port_res, - napi); - struct net_device *dev = pr->port->netdev; - struct ehea_cqe *cqe; - struct ehea_cqe *cqe_skb = NULL; - int wqe_index; - int rx = 0; - - cqe_skb = ehea_proc_cqes(pr, EHEA_POLL_MAX_CQES); - rx += ehea_proc_rwqes(dev, pr, budget - rx); - - while (rx != budget) { - napi_complete(napi); - ehea_reset_cq_ep(pr->recv_cq); - ehea_reset_cq_ep(pr->send_cq); - ehea_reset_cq_n1(pr->recv_cq); - ehea_reset_cq_n1(pr->send_cq); - rmb(); - cqe = ehea_poll_rq1(pr->qp, &wqe_index); - cqe_skb = ehea_poll_cq(pr->send_cq); - - if (!cqe && !cqe_skb) - return rx; - - if (!napi_schedule(napi)) - return rx; - - cqe_skb = ehea_proc_cqes(pr, EHEA_POLL_MAX_CQES); - rx += ehea_proc_rwqes(dev, pr, budget - rx); - } - - return rx; -} - -static irqreturn_t ehea_recv_irq_handler(int irq, void *param) -{ - struct ehea_port_res *pr = param; - - napi_schedule(&pr->napi); - - return IRQ_HANDLED; -} - -static irqreturn_t ehea_qp_aff_irq_handler(int irq, void *param) -{ - struct ehea_port *port = param; - struct ehea_eqe *eqe; - struct ehea_qp *qp; - u32 qp_token; - u64 resource_type, aer, aerr; - int reset_port = 0; - - eqe = ehea_poll_eq(port->qp_eq); - - while (eqe) { - qp_token = EHEA_BMASK_GET(EHEA_EQE_QP_TOKEN, eqe->entry); - pr_err("QP aff_err: entry=0x%llx, token=0x%x\n", - eqe->entry, qp_token); - - qp = port->port_res[qp_token].qp; - - resource_type = ehea_error_data(port->adapter, qp->fw_handle, - &aer, &aerr); - - if (resource_type == EHEA_AER_RESTYPE_QP) { - if ((aer & EHEA_AER_RESET_MASK) || - (aerr & EHEA_AERR_RESET_MASK)) - reset_port = 1; - } else - reset_port = 1; /* Reset in case of CQ or EQ error */ - - eqe = ehea_poll_eq(port->qp_eq); - } - - if (reset_port) { - pr_err("Resetting port\n"); - ehea_schedule_port_reset(port); - } - - return IRQ_HANDLED; -} - -static struct ehea_port *ehea_get_port(struct ehea_adapter *adapter, - int logical_port) -{ - int i; - - for (i = 0; i < EHEA_MAX_PORTS; i++) - if (adapter->port[i]) - if (adapter->port[i]->logical_port_id == logical_port) - return adapter->port[i]; - return NULL; -} - -int ehea_sense_port_attr(struct ehea_port *port) -{ - int ret; - u64 hret; - struct hcp_ehea_port_cb0 *cb0; - - /* may be called via ehea_neq_tasklet() */ - cb0 = (void *)get_zeroed_page(GFP_ATOMIC); - if (!cb0) { - pr_err("no mem for cb0\n"); - ret = -ENOMEM; - goto out; - } - - hret = ehea_h_query_ehea_port(port->adapter->handle, - port->logical_port_id, H_PORT_CB0, - EHEA_BMASK_SET(H_PORT_CB0_ALL, 0xFFFF), - cb0); - if (hret != H_SUCCESS) { - ret = -EIO; - goto out_free; - } - - /* MAC address */ - port->mac_addr = cb0->port_mac_addr << 16; - - if (!is_valid_ether_addr((u8 *)&port->mac_addr)) { - ret = -EADDRNOTAVAIL; - goto out_free; - } - - /* Port speed */ - switch (cb0->port_speed) { - case H_SPEED_10M_H: - port->port_speed = EHEA_SPEED_10M; - port->full_duplex = 0; - break; - case H_SPEED_10M_F: - port->port_speed = EHEA_SPEED_10M; - port->full_duplex = 1; - break; - case H_SPEED_100M_H: - port->port_speed = EHEA_SPEED_100M; - port->full_duplex = 0; - break; - case H_SPEED_100M_F: - port->port_speed = EHEA_SPEED_100M; - port->full_duplex = 1; - break; - case H_SPEED_1G_F: - port->port_speed = EHEA_SPEED_1G; - port->full_duplex = 1; - break; - case H_SPEED_10G_F: - port->port_speed = EHEA_SPEED_10G; - port->full_duplex = 1; - break; - default: - port->port_speed = 0; - port->full_duplex = 0; - break; - } - - port->autoneg = 1; - port->num_mcs = cb0->num_default_qps; - - /* Number of default QPs */ - if (use_mcs) - port->num_def_qps = cb0->num_default_qps; - else - port->num_def_qps = 1; - - if (!port->num_def_qps) { - ret = -EINVAL; - goto out_free; - } - - ret = 0; -out_free: - if (ret || netif_msg_probe(port)) - ehea_dump(cb0, sizeof(*cb0), "ehea_sense_port_attr"); - free_page((unsigned long)cb0); -out: - return ret; -} - -int ehea_set_portspeed(struct ehea_port *port, u32 port_speed) -{ - struct hcp_ehea_port_cb4 *cb4; - u64 hret; - int ret = 0; - - cb4 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb4) { - pr_err("no mem for cb4\n"); - ret = -ENOMEM; - goto out; - } - - cb4->port_speed = port_speed; - - netif_carrier_off(port->netdev); - - hret = ehea_h_modify_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB4, H_PORT_CB4_SPEED, cb4); - if (hret == H_SUCCESS) { - port->autoneg = port_speed == EHEA_SPEED_AUTONEG ? 1 : 0; - - hret = ehea_h_query_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB4, H_PORT_CB4_SPEED, - cb4); - if (hret == H_SUCCESS) { - switch (cb4->port_speed) { - case H_SPEED_10M_H: - port->port_speed = EHEA_SPEED_10M; - port->full_duplex = 0; - break; - case H_SPEED_10M_F: - port->port_speed = EHEA_SPEED_10M; - port->full_duplex = 1; - break; - case H_SPEED_100M_H: - port->port_speed = EHEA_SPEED_100M; - port->full_duplex = 0; - break; - case H_SPEED_100M_F: - port->port_speed = EHEA_SPEED_100M; - port->full_duplex = 1; - break; - case H_SPEED_1G_F: - port->port_speed = EHEA_SPEED_1G; - port->full_duplex = 1; - break; - case H_SPEED_10G_F: - port->port_speed = EHEA_SPEED_10G; - port->full_duplex = 1; - break; - default: - port->port_speed = 0; - port->full_duplex = 0; - break; - } - } else { - pr_err("Failed sensing port speed\n"); - ret = -EIO; - } - } else { - if (hret == H_AUTHORITY) { - pr_info("Hypervisor denied setting port speed\n"); - ret = -EPERM; - } else { - ret = -EIO; - pr_err("Failed setting port speed\n"); - } - } - if (!prop_carrier_state || (port->phy_link == EHEA_PHY_LINK_UP)) - netif_carrier_on(port->netdev); - - free_page((unsigned long)cb4); -out: - return ret; -} - -static void ehea_parse_eqe(struct ehea_adapter *adapter, u64 eqe) -{ - int ret; - u8 ec; - u8 portnum; - struct ehea_port *port; - struct net_device *dev; - - ec = EHEA_BMASK_GET(NEQE_EVENT_CODE, eqe); - portnum = EHEA_BMASK_GET(NEQE_PORTNUM, eqe); - port = ehea_get_port(adapter, portnum); - if (!port) { - netdev_err(NULL, "unknown portnum %x\n", portnum); - return; - } - dev = port->netdev; - - switch (ec) { - case EHEA_EC_PORTSTATE_CHG: /* port state change */ - - if (EHEA_BMASK_GET(NEQE_PORT_UP, eqe)) { - if (!netif_carrier_ok(dev)) { - ret = ehea_sense_port_attr(port); - if (ret) { - netdev_err(dev, "failed resensing port attributes\n"); - break; - } - - netif_info(port, link, dev, - "Logical port up: %dMbps %s Duplex\n", - port->port_speed, - port->full_duplex == 1 ? - "Full" : "Half"); - - netif_carrier_on(dev); - netif_wake_queue(dev); - } - } else - if (netif_carrier_ok(dev)) { - netif_info(port, link, dev, - "Logical port down\n"); - netif_carrier_off(dev); - netif_tx_disable(dev); - } - - if (EHEA_BMASK_GET(NEQE_EXTSWITCH_PORT_UP, eqe)) { - port->phy_link = EHEA_PHY_LINK_UP; - netif_info(port, link, dev, - "Physical port up\n"); - if (prop_carrier_state) - netif_carrier_on(dev); - } else { - port->phy_link = EHEA_PHY_LINK_DOWN; - netif_info(port, link, dev, - "Physical port down\n"); - if (prop_carrier_state) - netif_carrier_off(dev); - } - - if (EHEA_BMASK_GET(NEQE_EXTSWITCH_PRIMARY, eqe)) - netdev_info(dev, - "External switch port is primary port\n"); - else - netdev_info(dev, - "External switch port is backup port\n"); - - break; - case EHEA_EC_ADAPTER_MALFUNC: - netdev_err(dev, "Adapter malfunction\n"); - break; - case EHEA_EC_PORT_MALFUNC: - netdev_info(dev, "Port malfunction\n"); - netif_carrier_off(dev); - netif_tx_disable(dev); - break; - default: - netdev_err(dev, "unknown event code %x, eqe=0x%llX\n", ec, eqe); - break; - } -} - -static void ehea_neq_tasklet(struct tasklet_struct *t) -{ - struct ehea_adapter *adapter = from_tasklet(adapter, t, neq_tasklet); - struct ehea_eqe *eqe; - u64 event_mask; - - eqe = ehea_poll_eq(adapter->neq); - pr_debug("eqe=%p\n", eqe); - - while (eqe) { - pr_debug("*eqe=%lx\n", (unsigned long) eqe->entry); - ehea_parse_eqe(adapter, eqe->entry); - eqe = ehea_poll_eq(adapter->neq); - pr_debug("next eqe=%p\n", eqe); - } - - event_mask = EHEA_BMASK_SET(NELR_PORTSTATE_CHG, 1) - | EHEA_BMASK_SET(NELR_ADAPTER_MALFUNC, 1) - | EHEA_BMASK_SET(NELR_PORT_MALFUNC, 1); - - ehea_h_reset_events(adapter->handle, - adapter->neq->fw_handle, event_mask); -} - -static irqreturn_t ehea_interrupt_neq(int irq, void *param) -{ - struct ehea_adapter *adapter = param; - tasklet_hi_schedule(&adapter->neq_tasklet); - return IRQ_HANDLED; -} - - -static int ehea_fill_port_res(struct ehea_port_res *pr) -{ - int ret; - struct ehea_qp_init_attr *init_attr = &pr->qp->init_attr; - - ehea_init_fill_rq1(pr, pr->rq1_skba.len); - - ret = ehea_refill_rq2(pr, init_attr->act_nr_rwqes_rq2 - 1); - - ret |= ehea_refill_rq3(pr, init_attr->act_nr_rwqes_rq3 - 1); - - return ret; -} - -static int ehea_reg_interrupts(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_port_res *pr; - int i, ret; - - - snprintf(port->int_aff_name, EHEA_IRQ_NAME_SIZE - 1, "%s-aff", - dev->name); - - ret = ibmebus_request_irq(port->qp_eq->attr.ist1, - ehea_qp_aff_irq_handler, - 0, port->int_aff_name, port); - if (ret) { - netdev_err(dev, "failed registering irq for qp_aff_irq_handler:ist=%X\n", - port->qp_eq->attr.ist1); - goto out_free_qpeq; - } - - netif_info(port, ifup, dev, - "irq_handle 0x%X for function qp_aff_irq_handler registered\n", - port->qp_eq->attr.ist1); - - - for (i = 0; i < port->num_def_qps; i++) { - pr = &port->port_res[i]; - snprintf(pr->int_send_name, EHEA_IRQ_NAME_SIZE - 1, - "%s-queue%d", dev->name, i); - ret = ibmebus_request_irq(pr->eq->attr.ist1, - ehea_recv_irq_handler, - 0, pr->int_send_name, pr); - if (ret) { - netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n", - i, pr->eq->attr.ist1); - goto out_free_req; - } - netif_info(port, ifup, dev, - "irq_handle 0x%X for function ehea_queue_int %d registered\n", - pr->eq->attr.ist1, i); - } -out: - return ret; - - -out_free_req: - while (--i >= 0) { - u32 ist = port->port_res[i].eq->attr.ist1; - ibmebus_free_irq(ist, &port->port_res[i]); - } - -out_free_qpeq: - ibmebus_free_irq(port->qp_eq->attr.ist1, port); - i = port->num_def_qps; - - goto out; - -} - -static void ehea_free_interrupts(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_port_res *pr; - int i; - - /* send */ - - for (i = 0; i < port->num_def_qps; i++) { - pr = &port->port_res[i]; - ibmebus_free_irq(pr->eq->attr.ist1, pr); - netif_info(port, intr, dev, - "free send irq for res %d with handle 0x%X\n", - i, pr->eq->attr.ist1); - } - - /* associated events */ - ibmebus_free_irq(port->qp_eq->attr.ist1, port); - netif_info(port, intr, dev, - "associated event interrupt for handle 0x%X freed\n", - port->qp_eq->attr.ist1); -} - -static int ehea_configure_port(struct ehea_port *port) -{ - int ret, i; - u64 hret, mask; - struct hcp_ehea_port_cb0 *cb0; - - ret = -ENOMEM; - cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) - goto out; - - cb0->port_rc = EHEA_BMASK_SET(PXLY_RC_VALID, 1) - | EHEA_BMASK_SET(PXLY_RC_IP_CHKSUM, 1) - | EHEA_BMASK_SET(PXLY_RC_TCP_UDP_CHKSUM, 1) - | EHEA_BMASK_SET(PXLY_RC_VLAN_XTRACT, 1) - | EHEA_BMASK_SET(PXLY_RC_VLAN_TAG_FILTER, - PXLY_RC_VLAN_FILTER) - | EHEA_BMASK_SET(PXLY_RC_JUMBO_FRAME, 1); - - for (i = 0; i < port->num_mcs; i++) - if (use_mcs) - cb0->default_qpn_arr[i] = - port->port_res[i].qp->init_attr.qp_nr; - else - cb0->default_qpn_arr[i] = - port->port_res[0].qp->init_attr.qp_nr; - - if (netif_msg_ifup(port)) - ehea_dump(cb0, sizeof(*cb0), "ehea_configure_port"); - - mask = EHEA_BMASK_SET(H_PORT_CB0_PRC, 1) - | EHEA_BMASK_SET(H_PORT_CB0_DEFQPNARRAY, 1); - - hret = ehea_h_modify_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB0, mask, cb0); - ret = -EIO; - if (hret != H_SUCCESS) - goto out_free; - - ret = 0; - -out_free: - free_page((unsigned long)cb0); -out: - return ret; -} - -static int ehea_gen_smrs(struct ehea_port_res *pr) -{ - int ret; - struct ehea_adapter *adapter = pr->port->adapter; - - ret = ehea_gen_smr(adapter, &adapter->mr, &pr->send_mr); - if (ret) - goto out; - - ret = ehea_gen_smr(adapter, &adapter->mr, &pr->recv_mr); - if (ret) - goto out_free; - - return 0; - -out_free: - ehea_rem_mr(&pr->send_mr); -out: - pr_err("Generating SMRS failed\n"); - return -EIO; -} - -static int ehea_rem_smrs(struct ehea_port_res *pr) -{ - if ((ehea_rem_mr(&pr->send_mr)) || - (ehea_rem_mr(&pr->recv_mr))) - return -EIO; - else - return 0; -} - -static int ehea_init_q_skba(struct ehea_q_skb_arr *q_skba, int max_q_entries) -{ - int arr_size = sizeof(void *) * max_q_entries; - - q_skba->arr = vzalloc(arr_size); - if (!q_skba->arr) - return -ENOMEM; - - q_skba->len = max_q_entries; - q_skba->index = 0; - q_skba->os_skbs = 0; - - return 0; -} - -static int ehea_init_port_res(struct ehea_port *port, struct ehea_port_res *pr, - struct port_res_cfg *pr_cfg, int queue_token) -{ - struct ehea_adapter *adapter = port->adapter; - enum ehea_eq_type eq_type = EHEA_EQ; - struct ehea_qp_init_attr *init_attr = NULL; - int ret = -EIO; - u64 tx_bytes, rx_bytes, tx_packets, rx_packets; - - tx_bytes = pr->tx_bytes; - tx_packets = pr->tx_packets; - rx_bytes = pr->rx_bytes; - rx_packets = pr->rx_packets; - - memset(pr, 0, sizeof(struct ehea_port_res)); - - pr->tx_bytes = tx_bytes; - pr->tx_packets = tx_packets; - pr->rx_bytes = rx_bytes; - pr->rx_packets = rx_packets; - - pr->port = port; - - pr->eq = ehea_create_eq(adapter, eq_type, EHEA_MAX_ENTRIES_EQ, 0); - if (!pr->eq) { - pr_err("create_eq failed (eq)\n"); - goto out_free; - } - - pr->recv_cq = ehea_create_cq(adapter, pr_cfg->max_entries_rcq, - pr->eq->fw_handle, - port->logical_port_id); - if (!pr->recv_cq) { - pr_err("create_cq failed (cq_recv)\n"); - goto out_free; - } - - pr->send_cq = ehea_create_cq(adapter, pr_cfg->max_entries_scq, - pr->eq->fw_handle, - port->logical_port_id); - if (!pr->send_cq) { - pr_err("create_cq failed (cq_send)\n"); - goto out_free; - } - - if (netif_msg_ifup(port)) - pr_info("Send CQ: act_nr_cqes=%d, Recv CQ: act_nr_cqes=%d\n", - pr->send_cq->attr.act_nr_of_cqes, - pr->recv_cq->attr.act_nr_of_cqes); - - init_attr = kzalloc_obj(*init_attr); - if (!init_attr) { - ret = -ENOMEM; - pr_err("no mem for ehea_qp_init_attr\n"); - goto out_free; - } - - init_attr->low_lat_rq1 = 1; - init_attr->signalingtype = 1; /* generate CQE if specified in WQE */ - init_attr->rq_count = 3; - init_attr->qp_token = queue_token; - init_attr->max_nr_send_wqes = pr_cfg->max_entries_sq; - init_attr->max_nr_rwqes_rq1 = pr_cfg->max_entries_rq1; - init_attr->max_nr_rwqes_rq2 = pr_cfg->max_entries_rq2; - init_attr->max_nr_rwqes_rq3 = pr_cfg->max_entries_rq3; - init_attr->wqe_size_enc_sq = EHEA_SG_SQ; - init_attr->wqe_size_enc_rq1 = EHEA_SG_RQ1; - init_attr->wqe_size_enc_rq2 = EHEA_SG_RQ2; - init_attr->wqe_size_enc_rq3 = EHEA_SG_RQ3; - init_attr->rq2_threshold = EHEA_RQ2_THRESHOLD; - init_attr->rq3_threshold = EHEA_RQ3_THRESHOLD; - init_attr->port_nr = port->logical_port_id; - init_attr->send_cq_handle = pr->send_cq->fw_handle; - init_attr->recv_cq_handle = pr->recv_cq->fw_handle; - init_attr->aff_eq_handle = port->qp_eq->fw_handle; - - pr->qp = ehea_create_qp(adapter, adapter->pd, init_attr); - if (!pr->qp) { - pr_err("create_qp failed\n"); - ret = -EIO; - goto out_free; - } - - if (netif_msg_ifup(port)) - pr_info("QP: qp_nr=%d\n act_nr_snd_wqe=%d\n nr_rwqe_rq1=%d\n nr_rwqe_rq2=%d\n nr_rwqe_rq3=%d\n", - init_attr->qp_nr, - init_attr->act_nr_send_wqes, - init_attr->act_nr_rwqes_rq1, - init_attr->act_nr_rwqes_rq2, - init_attr->act_nr_rwqes_rq3); - - pr->sq_skba_size = init_attr->act_nr_send_wqes + 1; - - ret = ehea_init_q_skba(&pr->sq_skba, pr->sq_skba_size); - ret |= ehea_init_q_skba(&pr->rq1_skba, init_attr->act_nr_rwqes_rq1 + 1); - ret |= ehea_init_q_skba(&pr->rq2_skba, init_attr->act_nr_rwqes_rq2 + 1); - ret |= ehea_init_q_skba(&pr->rq3_skba, init_attr->act_nr_rwqes_rq3 + 1); - if (ret) - goto out_free; - - pr->swqe_refill_th = init_attr->act_nr_send_wqes / 10; - if (ehea_gen_smrs(pr) != 0) { - ret = -EIO; - goto out_free; - } - - atomic_set(&pr->swqe_avail, init_attr->act_nr_send_wqes - 1); - - kfree(init_attr); - - netif_napi_add(pr->port->netdev, &pr->napi, ehea_poll); - - ret = 0; - goto out; - -out_free: - kfree(init_attr); - vfree(pr->sq_skba.arr); - vfree(pr->rq1_skba.arr); - vfree(pr->rq2_skba.arr); - vfree(pr->rq3_skba.arr); - ehea_destroy_qp(pr->qp); - ehea_destroy_cq(pr->send_cq); - ehea_destroy_cq(pr->recv_cq); - ehea_destroy_eq(pr->eq); -out: - return ret; -} - -static int ehea_clean_portres(struct ehea_port *port, struct ehea_port_res *pr) -{ - int ret, i; - - if (pr->qp) - netif_napi_del(&pr->napi); - - ret = ehea_destroy_qp(pr->qp); - - if (!ret) { - ehea_destroy_cq(pr->send_cq); - ehea_destroy_cq(pr->recv_cq); - ehea_destroy_eq(pr->eq); - - for (i = 0; i < pr->rq1_skba.len; i++) - dev_kfree_skb(pr->rq1_skba.arr[i]); - - for (i = 0; i < pr->rq2_skba.len; i++) - dev_kfree_skb(pr->rq2_skba.arr[i]); - - for (i = 0; i < pr->rq3_skba.len; i++) - dev_kfree_skb(pr->rq3_skba.arr[i]); - - for (i = 0; i < pr->sq_skba.len; i++) - dev_kfree_skb(pr->sq_skba.arr[i]); - - vfree(pr->rq1_skba.arr); - vfree(pr->rq2_skba.arr); - vfree(pr->rq3_skba.arr); - vfree(pr->sq_skba.arr); - ret = ehea_rem_smrs(pr); - } - return ret; -} - -static void write_swqe2_immediate(struct sk_buff *skb, struct ehea_swqe *swqe, - u32 lkey) -{ - int skb_data_size = skb_headlen(skb); - u8 *imm_data = &swqe->u.immdata_desc.immediate_data[0]; - struct ehea_vsgentry *sg1entry = &swqe->u.immdata_desc.sg_entry; - unsigned int immediate_len = SWQE2_MAX_IMM; - - swqe->descriptors = 0; - - if (skb_is_gso(skb)) { - swqe->tx_control |= EHEA_SWQE_TSO; - swqe->mss = skb_shinfo(skb)->gso_size; - /* - * For TSO packets we only copy the headers into the - * immediate area. - */ - immediate_len = skb_tcp_all_headers(skb); - } - - if (skb_is_gso(skb) || skb_data_size >= SWQE2_MAX_IMM) { - skb_copy_from_linear_data(skb, imm_data, immediate_len); - swqe->immediate_data_length = immediate_len; - - if (skb_data_size > immediate_len) { - sg1entry->l_key = lkey; - sg1entry->len = skb_data_size - immediate_len; - sg1entry->vaddr = - ehea_map_vaddr(skb->data + immediate_len); - swqe->descriptors++; - } - } else { - skb_copy_from_linear_data(skb, imm_data, skb_data_size); - swqe->immediate_data_length = skb_data_size; - } -} - -static inline void write_swqe2_data(struct sk_buff *skb, struct net_device *dev, - struct ehea_swqe *swqe, u32 lkey) -{ - struct ehea_vsgentry *sg_list, *sg1entry, *sgentry; - skb_frag_t *frag; - int nfrags, sg1entry_contains_frag_data, i; - - nfrags = skb_shinfo(skb)->nr_frags; - sg1entry = &swqe->u.immdata_desc.sg_entry; - sg_list = (struct ehea_vsgentry *)&swqe->u.immdata_desc.sg_list; - sg1entry_contains_frag_data = 0; - - write_swqe2_immediate(skb, swqe, lkey); - - /* write descriptors */ - if (nfrags > 0) { - if (swqe->descriptors == 0) { - /* sg1entry not yet used */ - frag = &skb_shinfo(skb)->frags[0]; - - /* copy sg1entry data */ - sg1entry->l_key = lkey; - sg1entry->len = skb_frag_size(frag); - sg1entry->vaddr = - ehea_map_vaddr(skb_frag_address(frag)); - swqe->descriptors++; - sg1entry_contains_frag_data = 1; - } - - for (i = sg1entry_contains_frag_data; i < nfrags; i++) { - - frag = &skb_shinfo(skb)->frags[i]; - sgentry = &sg_list[i - sg1entry_contains_frag_data]; - - sgentry->l_key = lkey; - sgentry->len = skb_frag_size(frag); - sgentry->vaddr = ehea_map_vaddr(skb_frag_address(frag)); - swqe->descriptors++; - } - } -} - -static int ehea_broadcast_reg_helper(struct ehea_port *port, u32 hcallid) -{ - int ret = 0; - u64 hret; - u8 reg_type; - - /* De/Register untagged packets */ - reg_type = EHEA_BCMC_BROADCAST | EHEA_BCMC_UNTAGGED; - hret = ehea_h_reg_dereg_bcmc(port->adapter->handle, - port->logical_port_id, - reg_type, port->mac_addr, 0, hcallid); - if (hret != H_SUCCESS) { - pr_err("%sregistering bc address failed (tagged)\n", - hcallid == H_REG_BCMC ? "" : "de"); - ret = -EIO; - goto out_herr; - } - - /* De/Register VLAN packets */ - reg_type = EHEA_BCMC_BROADCAST | EHEA_BCMC_VLANID_ALL; - hret = ehea_h_reg_dereg_bcmc(port->adapter->handle, - port->logical_port_id, - reg_type, port->mac_addr, 0, hcallid); - if (hret != H_SUCCESS) { - pr_err("%sregistering bc address failed (vlan)\n", - hcallid == H_REG_BCMC ? "" : "de"); - ret = -EIO; - } -out_herr: - return ret; -} - -static int ehea_set_mac_addr(struct net_device *dev, void *sa) -{ - struct ehea_port *port = netdev_priv(dev); - struct sockaddr *mac_addr = sa; - struct hcp_ehea_port_cb0 *cb0; - int ret; - u64 hret; - - if (!is_valid_ether_addr(mac_addr->sa_data)) { - ret = -EADDRNOTAVAIL; - goto out; - } - - cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) { - pr_err("no mem for cb0\n"); - ret = -ENOMEM; - goto out; - } - - memcpy(&(cb0->port_mac_addr), &(mac_addr->sa_data[0]), ETH_ALEN); - - cb0->port_mac_addr = cb0->port_mac_addr >> 16; - - hret = ehea_h_modify_ehea_port(port->adapter->handle, - port->logical_port_id, H_PORT_CB0, - EHEA_BMASK_SET(H_PORT_CB0_MAC, 1), cb0); - if (hret != H_SUCCESS) { - ret = -EIO; - goto out_free; - } - - eth_hw_addr_set(dev, mac_addr->sa_data); - - /* Deregister old MAC in pHYP */ - if (port->state == EHEA_PORT_UP) { - ret = ehea_broadcast_reg_helper(port, H_DEREG_BCMC); - if (ret) - goto out_upregs; - } - - port->mac_addr = cb0->port_mac_addr << 16; - - /* Register new MAC in pHYP */ - if (port->state == EHEA_PORT_UP) { - ret = ehea_broadcast_reg_helper(port, H_REG_BCMC); - if (ret) - goto out_upregs; - } - - ret = 0; - -out_upregs: - ehea_update_bcmc_registrations(); -out_free: - free_page((unsigned long)cb0); -out: - return ret; -} - -static void ehea_promiscuous_error(u64 hret, int enable) -{ - if (hret == H_AUTHORITY) - pr_info("Hypervisor denied %sabling promiscuous mode\n", - enable == 1 ? "en" : "dis"); - else - pr_err("failed %sabling promiscuous mode\n", - enable == 1 ? "en" : "dis"); -} - -static void ehea_promiscuous(struct net_device *dev, int enable) -{ - struct ehea_port *port = netdev_priv(dev); - struct hcp_ehea_port_cb7 *cb7; - u64 hret; - - if (enable == port->promisc) - return; - - cb7 = (void *)get_zeroed_page(GFP_ATOMIC); - if (!cb7) { - pr_err("no mem for cb7\n"); - goto out; - } - - /* Modify Pxs_DUCQPN in CB7 */ - cb7->def_uc_qpn = enable == 1 ? port->port_res[0].qp->fw_handle : 0; - - hret = ehea_h_modify_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB7, H_PORT_CB7_DUCQPN, cb7); - if (hret) { - ehea_promiscuous_error(hret, enable); - goto out; - } - - port->promisc = enable; -out: - free_page((unsigned long)cb7); -} - -static u64 ehea_multicast_reg_helper(struct ehea_port *port, u64 mc_mac_addr, - u32 hcallid) -{ - u64 hret; - u8 reg_type; - - reg_type = EHEA_BCMC_MULTICAST | EHEA_BCMC_UNTAGGED; - if (mc_mac_addr == 0) - reg_type |= EHEA_BCMC_SCOPE_ALL; - - hret = ehea_h_reg_dereg_bcmc(port->adapter->handle, - port->logical_port_id, - reg_type, mc_mac_addr, 0, hcallid); - if (hret) - goto out; - - reg_type = EHEA_BCMC_MULTICAST | EHEA_BCMC_VLANID_ALL; - if (mc_mac_addr == 0) - reg_type |= EHEA_BCMC_SCOPE_ALL; - - hret = ehea_h_reg_dereg_bcmc(port->adapter->handle, - port->logical_port_id, - reg_type, mc_mac_addr, 0, hcallid); -out: - return hret; -} - -static int ehea_drop_multicast_list(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_mc_list *mc_entry = port->mc_list; - struct list_head *pos; - struct list_head *temp; - int ret = 0; - u64 hret; - - list_for_each_safe(pos, temp, &(port->mc_list->list)) { - mc_entry = list_entry(pos, struct ehea_mc_list, list); - - hret = ehea_multicast_reg_helper(port, mc_entry->macaddr, - H_DEREG_BCMC); - if (hret) { - pr_err("failed deregistering mcast MAC\n"); - ret = -EIO; - } - - list_del(pos); - kfree(mc_entry); - } - return ret; -} - -static void ehea_allmulti(struct net_device *dev, int enable) -{ - struct ehea_port *port = netdev_priv(dev); - u64 hret; - - if (!port->allmulti) { - if (enable) { - /* Enable ALLMULTI */ - ehea_drop_multicast_list(dev); - hret = ehea_multicast_reg_helper(port, 0, H_REG_BCMC); - if (!hret) - port->allmulti = 1; - else - netdev_err(dev, - "failed enabling IFF_ALLMULTI\n"); - } - } else { - if (!enable) { - /* Disable ALLMULTI */ - hret = ehea_multicast_reg_helper(port, 0, H_DEREG_BCMC); - if (!hret) - port->allmulti = 0; - else - netdev_err(dev, - "failed disabling IFF_ALLMULTI\n"); - } - } -} - -static void ehea_add_multicast_entry(struct ehea_port *port, u8 *mc_mac_addr) -{ - struct ehea_mc_list *ehea_mcl_entry; - u64 hret; - - ehea_mcl_entry = kzalloc_obj(*ehea_mcl_entry, GFP_ATOMIC); - if (!ehea_mcl_entry) - return; - - INIT_LIST_HEAD(&ehea_mcl_entry->list); - - memcpy(&ehea_mcl_entry->macaddr, mc_mac_addr, ETH_ALEN); - - hret = ehea_multicast_reg_helper(port, ehea_mcl_entry->macaddr, - H_REG_BCMC); - if (!hret) - list_add(&ehea_mcl_entry->list, &port->mc_list->list); - else { - pr_err("failed registering mcast MAC\n"); - kfree(ehea_mcl_entry); - } -} - -static void ehea_set_multicast_list(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct netdev_hw_addr *ha; - int ret; - - ehea_promiscuous(dev, !!(dev->flags & IFF_PROMISC)); - - if (dev->flags & IFF_ALLMULTI) { - ehea_allmulti(dev, 1); - goto out; - } - ehea_allmulti(dev, 0); - - if (!netdev_mc_empty(dev)) { - ret = ehea_drop_multicast_list(dev); - if (ret) { - /* Dropping the current multicast list failed. - * Enabling ALL_MULTI is the best we can do. - */ - ehea_allmulti(dev, 1); - } - - if (netdev_mc_count(dev) > port->adapter->max_mc_mac) { - pr_info("Mcast registration limit reached (0x%llx). Use ALLMULTI!\n", - port->adapter->max_mc_mac); - goto out; - } - - netdev_for_each_mc_addr(ha, dev) - ehea_add_multicast_entry(port, ha->addr); - - } -out: - ehea_update_bcmc_registrations(); -} - -static void xmit_common(struct sk_buff *skb, struct ehea_swqe *swqe) -{ - swqe->tx_control |= EHEA_SWQE_IMM_DATA_PRESENT | EHEA_SWQE_CRC; - - if (vlan_get_protocol(skb) != htons(ETH_P_IP)) - return; - - if (skb->ip_summed == CHECKSUM_PARTIAL) - swqe->tx_control |= EHEA_SWQE_IP_CHECKSUM; - - swqe->ip_start = skb_network_offset(skb); - swqe->ip_end = swqe->ip_start + ip_hdrlen(skb) - 1; - - switch (ip_hdr(skb)->protocol) { - case IPPROTO_UDP: - if (skb->ip_summed == CHECKSUM_PARTIAL) - swqe->tx_control |= EHEA_SWQE_TCP_CHECKSUM; - - swqe->tcp_offset = swqe->ip_end + 1 + - offsetof(struct udphdr, check); - break; - - case IPPROTO_TCP: - if (skb->ip_summed == CHECKSUM_PARTIAL) - swqe->tx_control |= EHEA_SWQE_TCP_CHECKSUM; - - swqe->tcp_offset = swqe->ip_end + 1 + - offsetof(struct tcphdr, check); - break; - } -} - -static void ehea_xmit2(struct sk_buff *skb, struct net_device *dev, - struct ehea_swqe *swqe, u32 lkey) -{ - swqe->tx_control |= EHEA_SWQE_DESCRIPTORS_PRESENT; - - xmit_common(skb, swqe); - - write_swqe2_data(skb, dev, swqe, lkey); -} - -static void ehea_xmit3(struct sk_buff *skb, struct net_device *dev, - struct ehea_swqe *swqe) -{ - u8 *imm_data = &swqe->u.immdata_nodesc.immediate_data[0]; - - xmit_common(skb, swqe); - - if (!skb->data_len) - skb_copy_from_linear_data(skb, imm_data, skb->len); - else - skb_copy_bits(skb, 0, imm_data, skb->len); - - swqe->immediate_data_length = skb->len; - dev_consume_skb_any(skb); -} - -static netdev_tx_t ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_swqe *swqe; - u32 lkey; - int swqe_index; - struct ehea_port_res *pr; - struct netdev_queue *txq; - - pr = &port->port_res[skb_get_queue_mapping(skb)]; - txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); - - swqe = ehea_get_swqe(pr->qp, &swqe_index); - memset(swqe, 0, SWQE_HEADER_SIZE); - atomic_dec(&pr->swqe_avail); - - if (skb_vlan_tag_present(skb)) { - swqe->tx_control |= EHEA_SWQE_VLAN_INSERT; - swqe->vlan_tag = skb_vlan_tag_get(skb); - } - - pr->tx_packets++; - pr->tx_bytes += skb->len; - - if (skb->len <= SWQE3_MAX_IMM) { - u32 sig_iv = port->sig_comp_iv; - u32 swqe_num = pr->swqe_id_counter; - ehea_xmit3(skb, dev, swqe); - swqe->wr_id = EHEA_BMASK_SET(EHEA_WR_ID_TYPE, EHEA_SWQE3_TYPE) - | EHEA_BMASK_SET(EHEA_WR_ID_COUNT, swqe_num); - if (pr->swqe_ll_count >= (sig_iv - 1)) { - swqe->wr_id |= EHEA_BMASK_SET(EHEA_WR_ID_REFILL, - sig_iv); - swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION; - pr->swqe_ll_count = 0; - } else - pr->swqe_ll_count += 1; - } else { - swqe->wr_id = - EHEA_BMASK_SET(EHEA_WR_ID_TYPE, EHEA_SWQE2_TYPE) - | EHEA_BMASK_SET(EHEA_WR_ID_COUNT, pr->swqe_id_counter) - | EHEA_BMASK_SET(EHEA_WR_ID_REFILL, 1) - | EHEA_BMASK_SET(EHEA_WR_ID_INDEX, pr->sq_skba.index); - pr->sq_skba.arr[pr->sq_skba.index] = skb; - - pr->sq_skba.index++; - pr->sq_skba.index &= (pr->sq_skba.len - 1); - - lkey = pr->send_mr.lkey; - ehea_xmit2(skb, dev, swqe, lkey); - swqe->tx_control |= EHEA_SWQE_SIGNALLED_COMPLETION; - } - pr->swqe_id_counter += 1; - - netif_info(port, tx_queued, dev, - "post swqe on QP %d\n", pr->qp->init_attr.qp_nr); - if (netif_msg_tx_queued(port)) - ehea_dump(swqe, 512, "swqe"); - - if (unlikely(test_bit(__EHEA_STOP_XFER, &ehea_driver_flags))) { - netif_tx_stop_queue(txq); - swqe->tx_control |= EHEA_SWQE_PURGE; - } - - ehea_post_swqe(pr->qp, swqe); - - if (unlikely(atomic_read(&pr->swqe_avail) <= 1)) { - pr->p_stats.queue_stopped++; - netif_tx_stop_queue(txq); - } - - return NETDEV_TX_OK; -} - -static int ehea_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_adapter *adapter = port->adapter; - struct hcp_ehea_port_cb1 *cb1; - int index; - u64 hret; - int err = 0; - - cb1 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb1) { - pr_err("no mem for cb1\n"); - err = -ENOMEM; - goto out; - } - - hret = ehea_h_query_ehea_port(adapter->handle, port->logical_port_id, - H_PORT_CB1, H_PORT_CB1_ALL, cb1); - if (hret != H_SUCCESS) { - pr_err("query_ehea_port failed\n"); - err = -EINVAL; - goto out; - } - - index = (vid / 64); - cb1->vlan_filter[index] |= ((u64)(0x8000000000000000 >> (vid & 0x3F))); - - hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id, - H_PORT_CB1, H_PORT_CB1_ALL, cb1); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_port failed\n"); - err = -EINVAL; - } -out: - free_page((unsigned long)cb1); - return err; -} - -static int ehea_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_adapter *adapter = port->adapter; - struct hcp_ehea_port_cb1 *cb1; - int index; - u64 hret; - int err = 0; - - cb1 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb1) { - pr_err("no mem for cb1\n"); - err = -ENOMEM; - goto out; - } - - hret = ehea_h_query_ehea_port(adapter->handle, port->logical_port_id, - H_PORT_CB1, H_PORT_CB1_ALL, cb1); - if (hret != H_SUCCESS) { - pr_err("query_ehea_port failed\n"); - err = -EINVAL; - goto out; - } - - index = (vid / 64); - cb1->vlan_filter[index] &= ~((u64)(0x8000000000000000 >> (vid & 0x3F))); - - hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id, - H_PORT_CB1, H_PORT_CB1_ALL, cb1); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_port failed\n"); - err = -EINVAL; - } -out: - free_page((unsigned long)cb1); - return err; -} - -static int ehea_activate_qp(struct ehea_adapter *adapter, struct ehea_qp *qp) -{ - int ret = -EIO; - u64 hret; - u16 dummy16 = 0; - u64 dummy64 = 0; - struct hcp_modify_qp_cb0 *cb0; - - cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) { - ret = -ENOMEM; - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (1)\n"); - goto out; - } - - cb0->qp_ctl_reg = H_QP_CR_STATE_INITIALIZED; - hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0, - &dummy64, &dummy64, &dummy16, &dummy16); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_qp failed (1)\n"); - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (2)\n"); - goto out; - } - - cb0->qp_ctl_reg = H_QP_CR_ENABLED | H_QP_CR_STATE_INITIALIZED; - hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0, - &dummy64, &dummy64, &dummy16, &dummy16); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_qp failed (2)\n"); - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (3)\n"); - goto out; - } - - cb0->qp_ctl_reg = H_QP_CR_ENABLED | H_QP_CR_STATE_RDY2SND; - hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, 1), cb0, - &dummy64, &dummy64, &dummy16, &dummy16); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_qp failed (3)\n"); - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (4)\n"); - goto out; - } - - ret = 0; -out: - free_page((unsigned long)cb0); - return ret; -} - -static int ehea_port_res_setup(struct ehea_port *port, int def_qps) -{ - int ret, i; - struct port_res_cfg pr_cfg, pr_cfg_small_rx; - enum ehea_eq_type eq_type = EHEA_EQ; - - port->qp_eq = ehea_create_eq(port->adapter, eq_type, - EHEA_MAX_ENTRIES_EQ, 1); - if (!port->qp_eq) { - ret = -EINVAL; - pr_err("ehea_create_eq failed (qp_eq)\n"); - goto out_kill_eq; - } - - pr_cfg.max_entries_rcq = rq1_entries + rq2_entries + rq3_entries; - pr_cfg.max_entries_scq = sq_entries * 2; - pr_cfg.max_entries_sq = sq_entries; - pr_cfg.max_entries_rq1 = rq1_entries; - pr_cfg.max_entries_rq2 = rq2_entries; - pr_cfg.max_entries_rq3 = rq3_entries; - - pr_cfg_small_rx.max_entries_rcq = 1; - pr_cfg_small_rx.max_entries_scq = sq_entries; - pr_cfg_small_rx.max_entries_sq = sq_entries; - pr_cfg_small_rx.max_entries_rq1 = 1; - pr_cfg_small_rx.max_entries_rq2 = 1; - pr_cfg_small_rx.max_entries_rq3 = 1; - - for (i = 0; i < def_qps; i++) { - ret = ehea_init_port_res(port, &port->port_res[i], &pr_cfg, i); - if (ret) - goto out_clean_pr; - } - for (i = def_qps; i < def_qps; i++) { - ret = ehea_init_port_res(port, &port->port_res[i], - &pr_cfg_small_rx, i); - if (ret) - goto out_clean_pr; - } - - return 0; - -out_clean_pr: - while (--i >= 0) - ehea_clean_portres(port, &port->port_res[i]); - -out_kill_eq: - ehea_destroy_eq(port->qp_eq); - return ret; -} - -static int ehea_clean_all_portres(struct ehea_port *port) -{ - int ret = 0; - int i; - - for (i = 0; i < port->num_def_qps; i++) - ret |= ehea_clean_portres(port, &port->port_res[i]); - - ret |= ehea_destroy_eq(port->qp_eq); - - return ret; -} - -static void ehea_remove_adapter_mr(struct ehea_adapter *adapter) -{ - if (adapter->active_ports) - return; - - ehea_rem_mr(&adapter->mr); -} - -static int ehea_add_adapter_mr(struct ehea_adapter *adapter) -{ - if (adapter->active_ports) - return 0; - - return ehea_reg_kernel_mr(adapter, &adapter->mr); -} - -static int ehea_up(struct net_device *dev) -{ - int ret, i; - struct ehea_port *port = netdev_priv(dev); - - if (port->state == EHEA_PORT_UP) - return 0; - - ret = ehea_port_res_setup(port, port->num_def_qps); - if (ret) { - netdev_err(dev, "port_res_failed\n"); - goto out; - } - - /* Set default QP for this port */ - ret = ehea_configure_port(port); - if (ret) { - netdev_err(dev, "ehea_configure_port failed. ret:%d\n", ret); - goto out_clean_pr; - } - - ret = ehea_reg_interrupts(dev); - if (ret) { - netdev_err(dev, "reg_interrupts failed. ret:%d\n", ret); - goto out_clean_pr; - } - - for (i = 0; i < port->num_def_qps; i++) { - ret = ehea_activate_qp(port->adapter, port->port_res[i].qp); - if (ret) { - netdev_err(dev, "activate_qp failed\n"); - goto out_free_irqs; - } - } - - for (i = 0; i < port->num_def_qps; i++) { - ret = ehea_fill_port_res(&port->port_res[i]); - if (ret) { - netdev_err(dev, "out_free_irqs\n"); - goto out_free_irqs; - } - } - - ret = ehea_broadcast_reg_helper(port, H_REG_BCMC); - if (ret) { - ret = -EIO; - goto out_free_irqs; - } - - port->state = EHEA_PORT_UP; - - ret = 0; - goto out; - -out_free_irqs: - ehea_free_interrupts(dev); - -out_clean_pr: - ehea_clean_all_portres(port); -out: - if (ret) - netdev_info(dev, "Failed starting. ret=%i\n", ret); - - ehea_update_bcmc_registrations(); - ehea_update_firmware_handles(); - - return ret; -} - -static void port_napi_disable(struct ehea_port *port) -{ - int i; - - for (i = 0; i < port->num_def_qps; i++) - napi_disable(&port->port_res[i].napi); -} - -static void port_napi_enable(struct ehea_port *port) -{ - int i; - - for (i = 0; i < port->num_def_qps; i++) - napi_enable(&port->port_res[i].napi); -} - -static int ehea_open(struct net_device *dev) -{ - int ret; - struct ehea_port *port = netdev_priv(dev); - - mutex_lock(&port->port_lock); - - netif_info(port, ifup, dev, "enabling port\n"); - - netif_carrier_off(dev); - - ret = ehea_up(dev); - if (!ret) { - port_napi_enable(port); - netif_tx_start_all_queues(dev); - } - - mutex_unlock(&port->port_lock); - schedule_delayed_work(&port->stats_work, - round_jiffies_relative(msecs_to_jiffies(1000))); - - return ret; -} - -static int ehea_down(struct net_device *dev) -{ - int ret; - struct ehea_port *port = netdev_priv(dev); - - if (port->state == EHEA_PORT_DOWN) - return 0; - - ehea_drop_multicast_list(dev); - ehea_allmulti(dev, 0); - ehea_broadcast_reg_helper(port, H_DEREG_BCMC); - - ehea_free_interrupts(dev); - - port->state = EHEA_PORT_DOWN; - - ehea_update_bcmc_registrations(); - - ret = ehea_clean_all_portres(port); - if (ret) - netdev_info(dev, "Failed freeing resources. ret=%i\n", ret); - - ehea_update_firmware_handles(); - - return ret; -} - -static int ehea_stop(struct net_device *dev) -{ - int ret; - struct ehea_port *port = netdev_priv(dev); - - netif_info(port, ifdown, dev, "disabling port\n"); - - set_bit(__EHEA_DISABLE_PORT_RESET, &port->flags); - cancel_work_sync(&port->reset_task); - cancel_delayed_work_sync(&port->stats_work); - mutex_lock(&port->port_lock); - netif_tx_stop_all_queues(dev); - port_napi_disable(port); - ret = ehea_down(dev); - mutex_unlock(&port->port_lock); - clear_bit(__EHEA_DISABLE_PORT_RESET, &port->flags); - return ret; -} - -static void ehea_purge_sq(struct ehea_qp *orig_qp) -{ - struct ehea_qp qp = *orig_qp; - struct ehea_qp_init_attr *init_attr = &qp.init_attr; - struct ehea_swqe *swqe; - int wqe_index; - int i; - - for (i = 0; i < init_attr->act_nr_send_wqes; i++) { - swqe = ehea_get_swqe(&qp, &wqe_index); - swqe->tx_control |= EHEA_SWQE_PURGE; - } -} - -static void ehea_flush_sq(struct ehea_port *port) -{ - int i; - - for (i = 0; i < port->num_def_qps; i++) { - struct ehea_port_res *pr = &port->port_res[i]; - int swqe_max = pr->sq_skba_size - 2 - pr->swqe_ll_count; - int ret; - - ret = wait_event_timeout(port->swqe_avail_wq, - atomic_read(&pr->swqe_avail) >= swqe_max, - msecs_to_jiffies(100)); - - if (!ret) { - pr_err("WARNING: sq not flushed completely\n"); - break; - } - } -} - -static int ehea_stop_qps(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_adapter *adapter = port->adapter; - struct hcp_modify_qp_cb0 *cb0; - int ret = -EIO; - int dret; - int i; - u64 hret; - u64 dummy64 = 0; - u16 dummy16 = 0; - - cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) { - ret = -ENOMEM; - goto out; - } - - for (i = 0; i < (port->num_def_qps); i++) { - struct ehea_port_res *pr = &port->port_res[i]; - struct ehea_qp *qp = pr->qp; - - /* Purge send queue */ - ehea_purge_sq(qp); - - /* Disable queue pair */ - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), - cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (1)\n"); - goto out; - } - - cb0->qp_ctl_reg = (cb0->qp_ctl_reg & H_QP_CR_RES_STATE) << 8; - cb0->qp_ctl_reg &= ~H_QP_CR_ENABLED; - - hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, - 1), cb0, &dummy64, - &dummy64, &dummy16, &dummy16); - if (hret != H_SUCCESS) { - pr_err("modify_ehea_qp failed (1)\n"); - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), - cb0); - if (hret != H_SUCCESS) { - pr_err("query_ehea_qp failed (2)\n"); - goto out; - } - - /* deregister shared memory regions */ - dret = ehea_rem_smrs(pr); - if (dret) { - pr_err("unreg shared memory region failed\n"); - goto out; - } - } - - ret = 0; -out: - free_page((unsigned long)cb0); - - return ret; -} - -static void ehea_update_rqs(struct ehea_qp *orig_qp, struct ehea_port_res *pr) -{ - struct ehea_qp qp = *orig_qp; - struct ehea_qp_init_attr *init_attr = &qp.init_attr; - struct ehea_rwqe *rwqe; - struct sk_buff **skba_rq2 = pr->rq2_skba.arr; - struct sk_buff **skba_rq3 = pr->rq3_skba.arr; - struct sk_buff *skb; - u32 lkey = pr->recv_mr.lkey; - - - int i; - int index; - - for (i = 0; i < init_attr->act_nr_rwqes_rq2 + 1; i++) { - rwqe = ehea_get_next_rwqe(&qp, 2); - rwqe->sg_list[0].l_key = lkey; - index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, rwqe->wr_id); - skb = skba_rq2[index]; - if (skb) - rwqe->sg_list[0].vaddr = ehea_map_vaddr(skb->data); - } - - for (i = 0; i < init_attr->act_nr_rwqes_rq3 + 1; i++) { - rwqe = ehea_get_next_rwqe(&qp, 3); - rwqe->sg_list[0].l_key = lkey; - index = EHEA_BMASK_GET(EHEA_WR_ID_INDEX, rwqe->wr_id); - skb = skba_rq3[index]; - if (skb) - rwqe->sg_list[0].vaddr = ehea_map_vaddr(skb->data); - } -} - -static int ehea_restart_qps(struct net_device *dev) -{ - struct ehea_port *port = netdev_priv(dev); - struct ehea_adapter *adapter = port->adapter; - int ret = 0; - int i; - - struct hcp_modify_qp_cb0 *cb0; - u64 hret; - u64 dummy64 = 0; - u16 dummy16 = 0; - - cb0 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb0) - return -ENOMEM; - - for (i = 0; i < (port->num_def_qps); i++) { - struct ehea_port_res *pr = &port->port_res[i]; - struct ehea_qp *qp = pr->qp; - - ret = ehea_gen_smrs(pr); - if (ret) { - netdev_err(dev, "creation of shared memory regions failed\n"); - goto out; - } - - ehea_update_rqs(qp, pr); - - /* Enable queue pair */ - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), - cb0); - if (hret != H_SUCCESS) { - netdev_err(dev, "query_ehea_qp failed (1)\n"); - ret = -EFAULT; - goto out; - } - - cb0->qp_ctl_reg = (cb0->qp_ctl_reg & H_QP_CR_RES_STATE) << 8; - cb0->qp_ctl_reg |= H_QP_CR_ENABLED; - - hret = ehea_h_modify_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_QP_CTL_REG, - 1), cb0, &dummy64, - &dummy64, &dummy16, &dummy16); - if (hret != H_SUCCESS) { - netdev_err(dev, "modify_ehea_qp failed (1)\n"); - ret = -EFAULT; - goto out; - } - - hret = ehea_h_query_ehea_qp(adapter->handle, 0, qp->fw_handle, - EHEA_BMASK_SET(H_QPCB0_ALL, 0xFFFF), - cb0); - if (hret != H_SUCCESS) { - netdev_err(dev, "query_ehea_qp failed (2)\n"); - ret = -EFAULT; - goto out; - } - - /* refill entire queue */ - ehea_refill_rq1(pr, pr->rq1_skba.index, 0); - ehea_refill_rq2(pr, 0); - ehea_refill_rq3(pr, 0); - } -out: - free_page((unsigned long)cb0); - - return ret; -} - -static void ehea_reset_port(struct work_struct *work) -{ - int ret; - struct ehea_port *port = - container_of(work, struct ehea_port, reset_task); - struct net_device *dev = port->netdev; - - mutex_lock(&dlpar_mem_lock); - port->resets++; - mutex_lock(&port->port_lock); - netif_tx_disable(dev); - - port_napi_disable(port); - - ehea_down(dev); - - ret = ehea_up(dev); - if (ret) - goto out; - - ehea_set_multicast_list(dev); - - netif_info(port, timer, dev, "reset successful\n"); - - port_napi_enable(port); - - netif_tx_wake_all_queues(dev); -out: - mutex_unlock(&port->port_lock); - mutex_unlock(&dlpar_mem_lock); -} - -static void ehea_rereg_mrs(void) -{ - int ret, i; - struct ehea_adapter *adapter; - - pr_info("LPAR memory changed - re-initializing driver\n"); - - list_for_each_entry(adapter, &adapter_list, list) - if (adapter->active_ports) { - /* Shutdown all ports */ - for (i = 0; i < EHEA_MAX_PORTS; i++) { - struct ehea_port *port = adapter->port[i]; - struct net_device *dev; - - if (!port) - continue; - - dev = port->netdev; - - if (dev->flags & IFF_UP) { - mutex_lock(&port->port_lock); - netif_tx_disable(dev); - ehea_flush_sq(port); - ret = ehea_stop_qps(dev); - if (ret) { - mutex_unlock(&port->port_lock); - goto out; - } - port_napi_disable(port); - mutex_unlock(&port->port_lock); - } - reset_sq_restart_flag(port); - } - - /* Unregister old memory region */ - ret = ehea_rem_mr(&adapter->mr); - if (ret) { - pr_err("unregister MR failed - driver inoperable!\n"); - goto out; - } - } - - clear_bit(__EHEA_STOP_XFER, &ehea_driver_flags); - - list_for_each_entry(adapter, &adapter_list, list) - if (adapter->active_ports) { - /* Register new memory region */ - ret = ehea_reg_kernel_mr(adapter, &adapter->mr); - if (ret) { - pr_err("register MR failed - driver inoperable!\n"); - goto out; - } - - /* Restart all ports */ - for (i = 0; i < EHEA_MAX_PORTS; i++) { - struct ehea_port *port = adapter->port[i]; - - if (port) { - struct net_device *dev = port->netdev; - - if (dev->flags & IFF_UP) { - mutex_lock(&port->port_lock); - ret = ehea_restart_qps(dev); - if (!ret) { - check_sqs(port); - port_napi_enable(port); - netif_tx_wake_all_queues(dev); - } else { - netdev_err(dev, "Unable to restart QPS\n"); - } - mutex_unlock(&port->port_lock); - } - } - } - } - pr_info("re-initializing driver complete\n"); -out: - return; -} - -static void ehea_tx_watchdog(struct net_device *dev, unsigned int txqueue) -{ - struct ehea_port *port = netdev_priv(dev); - - if (netif_carrier_ok(dev) && - !test_bit(__EHEA_STOP_XFER, &ehea_driver_flags)) - ehea_schedule_port_reset(port); -} - -static int ehea_sense_adapter_attr(struct ehea_adapter *adapter) -{ - struct hcp_query_ehea *cb; - u64 hret; - int ret; - - cb = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb) { - ret = -ENOMEM; - goto out; - } - - hret = ehea_h_query_ehea(adapter->handle, cb); - - if (hret != H_SUCCESS) { - ret = -EIO; - goto out_herr; - } - - adapter->max_mc_mac = cb->max_mc_mac - 1; - ret = 0; - -out_herr: - free_page((unsigned long)cb); -out: - return ret; -} - -static int ehea_get_jumboframe_status(struct ehea_port *port, int *jumbo) -{ - struct hcp_ehea_port_cb4 *cb4; - u64 hret; - int ret = 0; - - *jumbo = 0; - - /* (Try to) enable *jumbo frames */ - cb4 = (void *)get_zeroed_page(GFP_KERNEL); - if (!cb4) { - pr_err("no mem for cb4\n"); - ret = -ENOMEM; - goto out; - } else { - hret = ehea_h_query_ehea_port(port->adapter->handle, - port->logical_port_id, - H_PORT_CB4, - H_PORT_CB4_JUMBO, cb4); - if (hret == H_SUCCESS) { - if (cb4->jumbo_frame) - *jumbo = 1; - else { - cb4->jumbo_frame = 1; - hret = ehea_h_modify_ehea_port(port->adapter-> - handle, - port-> - logical_port_id, - H_PORT_CB4, - H_PORT_CB4_JUMBO, - cb4); - if (hret == H_SUCCESS) - *jumbo = 1; - } - } else - ret = -EINVAL; - - free_page((unsigned long)cb4); - } -out: - return ret; -} - -static ssize_t log_port_id_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev); - return sprintf(buf, "%d", port->logical_port_id); -} - -static DEVICE_ATTR_RO(log_port_id); - -static void logical_port_release(struct device *dev) -{ - struct ehea_port *port = container_of(dev, struct ehea_port, ofdev.dev); - of_node_put(port->ofdev.dev.of_node); -} - -static struct device *ehea_register_port(struct ehea_port *port, - struct device_node *dn) -{ - int ret; - - port->ofdev.dev.of_node = of_node_get(dn); - port->ofdev.dev.parent = &port->adapter->ofdev->dev; - port->ofdev.dev.bus = &ibmebus_bus_type; - - dev_set_name(&port->ofdev.dev, "port%d", port_name_cnt++); - port->ofdev.dev.release = logical_port_release; - - ret = of_device_register(&port->ofdev); - if (ret) { - pr_err("failed to register device. ret=%d\n", ret); - put_device(&port->ofdev.dev); - goto out; - } - - ret = device_create_file(&port->ofdev.dev, &dev_attr_log_port_id); - if (ret) { - pr_err("failed to register attributes, ret=%d\n", ret); - goto out_unreg_of_dev; - } - - return &port->ofdev.dev; - -out_unreg_of_dev: - of_device_unregister(&port->ofdev); -out: - return NULL; -} - -static void ehea_unregister_port(struct ehea_port *port) -{ - device_remove_file(&port->ofdev.dev, &dev_attr_log_port_id); - of_device_unregister(&port->ofdev); -} - -static const struct net_device_ops ehea_netdev_ops = { - .ndo_open = ehea_open, - .ndo_stop = ehea_stop, - .ndo_start_xmit = ehea_start_xmit, - .ndo_get_stats64 = ehea_get_stats64, - .ndo_set_mac_address = ehea_set_mac_addr, - .ndo_validate_addr = eth_validate_addr, - .ndo_set_rx_mode = ehea_set_multicast_list, - .ndo_vlan_rx_add_vid = ehea_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = ehea_vlan_rx_kill_vid, - .ndo_tx_timeout = ehea_tx_watchdog, -}; - -static struct ehea_port *ehea_setup_single_port(struct ehea_adapter *adapter, - u32 logical_port_id, - struct device_node *dn) -{ - int ret; - struct net_device *dev; - struct ehea_port *port; - struct device *port_dev; - int jumbo; - - /* allocate memory for the port structures */ - dev = alloc_etherdev_mq(sizeof(struct ehea_port), EHEA_MAX_PORT_RES); - - if (!dev) { - ret = -ENOMEM; - goto out_err; - } - - port = netdev_priv(dev); - - mutex_init(&port->port_lock); - port->state = EHEA_PORT_DOWN; - port->sig_comp_iv = sq_entries / 10; - - port->adapter = adapter; - port->netdev = dev; - port->logical_port_id = logical_port_id; - - port->msg_enable = netif_msg_init(msg_level, EHEA_MSG_DEFAULT); - - port->mc_list = kzalloc_obj(struct ehea_mc_list); - if (!port->mc_list) { - ret = -ENOMEM; - goto out_free_ethdev; - } - - INIT_LIST_HEAD(&port->mc_list->list); - - ret = ehea_sense_port_attr(port); - if (ret) - goto out_free_mc_list; - - netif_set_real_num_rx_queues(dev, port->num_def_qps); - netif_set_real_num_tx_queues(dev, port->num_def_qps); - - port_dev = ehea_register_port(port, dn); - if (!port_dev) - goto out_free_mc_list; - - SET_NETDEV_DEV(dev, port_dev); - - /* initialize net_device structure */ - eth_hw_addr_set(dev, (u8 *)&port->mac_addr); - - dev->netdev_ops = &ehea_netdev_ops; - ehea_set_ethtool_ops(dev); - - dev->hw_features = NETIF_F_SG | NETIF_F_TSO | - NETIF_F_IP_CSUM | NETIF_F_HW_VLAN_CTAG_TX; - dev->features = NETIF_F_SG | NETIF_F_TSO | - NETIF_F_HIGHDMA | NETIF_F_IP_CSUM | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXCSUM; - dev->vlan_features = NETIF_F_SG | NETIF_F_TSO | NETIF_F_HIGHDMA | - NETIF_F_IP_CSUM; - dev->watchdog_timeo = EHEA_WATCH_DOG_TIMEOUT; - - /* MTU range: 68 - 9022 */ - dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = EHEA_MAX_PACKET_SIZE; - - INIT_WORK(&port->reset_task, ehea_reset_port); - INIT_DELAYED_WORK(&port->stats_work, ehea_update_stats); - - init_waitqueue_head(&port->swqe_avail_wq); - init_waitqueue_head(&port->restart_wq); - - ret = register_netdev(dev); - if (ret) { - pr_err("register_netdev failed. ret=%d\n", ret); - goto out_unreg_port; - } - - ret = ehea_get_jumboframe_status(port, &jumbo); - if (ret) - netdev_err(dev, "failed determining jumbo frame status\n"); - - netdev_info(dev, "Jumbo frames are %sabled\n", - jumbo == 1 ? "en" : "dis"); - - adapter->active_ports++; - - return port; - -out_unreg_port: - ehea_unregister_port(port); - -out_free_mc_list: - kfree(port->mc_list); - -out_free_ethdev: - free_netdev(dev); - -out_err: - pr_err("setting up logical port with id=%d failed, ret=%d\n", - logical_port_id, ret); - return NULL; -} - -static void ehea_shutdown_single_port(struct ehea_port *port) -{ - struct ehea_adapter *adapter = port->adapter; - - cancel_work_sync(&port->reset_task); - cancel_delayed_work_sync(&port->stats_work); - unregister_netdev(port->netdev); - ehea_unregister_port(port); - kfree(port->mc_list); - free_netdev(port->netdev); - adapter->active_ports--; -} - -static int ehea_setup_ports(struct ehea_adapter *adapter) -{ - struct device_node *lhea_dn; - struct device_node *eth_dn; - - const u32 *dn_log_port_id; - int i = 0; - - lhea_dn = adapter->ofdev->dev.of_node; - for_each_child_of_node(lhea_dn, eth_dn) { - dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", - NULL); - if (!dn_log_port_id) { - pr_err("bad device node: eth_dn name=%pOF\n", eth_dn); - continue; - } - - if (ehea_add_adapter_mr(adapter)) { - pr_err("creating MR failed\n"); - of_node_put(eth_dn); - return -EIO; - } - - adapter->port[i] = ehea_setup_single_port(adapter, - *dn_log_port_id, - eth_dn); - if (adapter->port[i]) - netdev_info(adapter->port[i]->netdev, - "logical port id #%d\n", *dn_log_port_id); - else - ehea_remove_adapter_mr(adapter); - - i++; - } - return 0; -} - -static struct device_node *ehea_get_eth_dn(struct ehea_adapter *adapter, - u32 logical_port_id) -{ - struct device_node *lhea_dn; - struct device_node *eth_dn; - const u32 *dn_log_port_id; - - lhea_dn = adapter->ofdev->dev.of_node; - for_each_child_of_node(lhea_dn, eth_dn) { - dn_log_port_id = of_get_property(eth_dn, "ibm,hea-port-no", - NULL); - if (dn_log_port_id) - if (*dn_log_port_id == logical_port_id) - return eth_dn; - } - - return NULL; -} - -static ssize_t probe_port_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct ehea_adapter *adapter = dev_get_drvdata(dev); - struct ehea_port *port; - struct device_node *eth_dn = NULL; - int i; - - u32 logical_port_id; - - sscanf(buf, "%d", &logical_port_id); - - port = ehea_get_port(adapter, logical_port_id); - - if (port) { - netdev_info(port->netdev, "adding port with logical port id=%d failed: port already configured\n", - logical_port_id); - return -EINVAL; - } - - eth_dn = ehea_get_eth_dn(adapter, logical_port_id); - - if (!eth_dn) { - pr_info("no logical port with id %d found\n", logical_port_id); - return -EINVAL; - } - - if (ehea_add_adapter_mr(adapter)) { - pr_err("creating MR failed\n"); - of_node_put(eth_dn); - return -EIO; - } - - port = ehea_setup_single_port(adapter, logical_port_id, eth_dn); - - of_node_put(eth_dn); - - if (port) { - for (i = 0; i < EHEA_MAX_PORTS; i++) - if (!adapter->port[i]) { - adapter->port[i] = port; - break; - } - - netdev_info(port->netdev, "added: (logical port id=%d)\n", - logical_port_id); - } else { - ehea_remove_adapter_mr(adapter); - return -EIO; - } - - return (ssize_t) count; -} - -static ssize_t remove_port_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - struct ehea_adapter *adapter = dev_get_drvdata(dev); - struct ehea_port *port; - int i; - u32 logical_port_id; - - sscanf(buf, "%d", &logical_port_id); - - port = ehea_get_port(adapter, logical_port_id); - - if (port) { - netdev_info(port->netdev, "removed: (logical port id=%d)\n", - logical_port_id); - - ehea_shutdown_single_port(port); - - for (i = 0; i < EHEA_MAX_PORTS; i++) - if (adapter->port[i] == port) { - adapter->port[i] = NULL; - break; - } - } else { - pr_err("removing port with logical port id=%d failed. port not configured.\n", - logical_port_id); - return -EINVAL; - } - - ehea_remove_adapter_mr(adapter); - - return (ssize_t) count; -} - -static DEVICE_ATTR_WO(probe_port); -static DEVICE_ATTR_WO(remove_port); - -static int ehea_create_device_sysfs(struct platform_device *dev) -{ - int ret = device_create_file(&dev->dev, &dev_attr_probe_port); - if (ret) - goto out; - - ret = device_create_file(&dev->dev, &dev_attr_remove_port); - if (ret) - device_remove_file(&dev->dev, &dev_attr_probe_port); -out: - return ret; -} - -static void ehea_remove_device_sysfs(struct platform_device *dev) -{ - device_remove_file(&dev->dev, &dev_attr_probe_port); - device_remove_file(&dev->dev, &dev_attr_remove_port); -} - -static int ehea_reboot_notifier(struct notifier_block *nb, - unsigned long action, void *unused) -{ - if (action == SYS_RESTART) { - pr_info("Reboot: freeing all eHEA resources\n"); - ibmebus_unregister_driver(&ehea_driver); - } - return NOTIFY_DONE; -} - -static struct notifier_block ehea_reboot_nb = { - .notifier_call = ehea_reboot_notifier, -}; - -static int ehea_mem_notifier(struct notifier_block *nb, - unsigned long action, void *data) -{ - int ret = NOTIFY_BAD; - struct memory_notify *arg = data; - - mutex_lock(&dlpar_mem_lock); - - switch (action) { - case MEM_CANCEL_OFFLINE: - pr_info("memory offlining canceled"); - fallthrough; /* re-add canceled memory block */ - - case MEM_ONLINE: - pr_info("memory is going online"); - set_bit(__EHEA_STOP_XFER, &ehea_driver_flags); - if (ehea_add_sect_bmap(arg->start_pfn, arg->nr_pages)) - goto out_unlock; - ehea_rereg_mrs(); - break; - - case MEM_GOING_OFFLINE: - pr_info("memory is going offline"); - set_bit(__EHEA_STOP_XFER, &ehea_driver_flags); - if (ehea_rem_sect_bmap(arg->start_pfn, arg->nr_pages)) - goto out_unlock; - ehea_rereg_mrs(); - break; - - default: - break; - } - - ehea_update_firmware_handles(); - ret = NOTIFY_OK; - -out_unlock: - mutex_unlock(&dlpar_mem_lock); - return ret; -} - -static struct notifier_block ehea_mem_nb = { - .notifier_call = ehea_mem_notifier, -}; - -static void ehea_crash_handler(void) -{ - int i; - - if (ehea_fw_handles.arr) - for (i = 0; i < ehea_fw_handles.num_entries; i++) - ehea_h_free_resource(ehea_fw_handles.arr[i].adh, - ehea_fw_handles.arr[i].fwh, - FORCE_FREE); - - if (ehea_bcmc_regs.arr) - for (i = 0; i < ehea_bcmc_regs.num_entries; i++) - ehea_h_reg_dereg_bcmc(ehea_bcmc_regs.arr[i].adh, - ehea_bcmc_regs.arr[i].port_id, - ehea_bcmc_regs.arr[i].reg_type, - ehea_bcmc_regs.arr[i].macaddr, - 0, H_DEREG_BCMC); -} - -static atomic_t ehea_memory_hooks_registered; - -/* Register memory hooks on probe of first adapter */ -static int ehea_register_memory_hooks(void) -{ - int ret = 0; - - if (atomic_inc_return(&ehea_memory_hooks_registered) > 1) - return 0; - - ret = ehea_create_busmap(); - if (ret) { - pr_info("ehea_create_busmap failed\n"); - goto out; - } - - ret = register_reboot_notifier(&ehea_reboot_nb); - if (ret) { - pr_info("register_reboot_notifier failed\n"); - goto out; - } - - ret = register_memory_notifier(&ehea_mem_nb); - if (ret) { - pr_info("register_memory_notifier failed\n"); - goto out2; - } - - ret = crash_shutdown_register(ehea_crash_handler); - if (ret) { - pr_info("crash_shutdown_register failed\n"); - goto out3; - } - - return 0; - -out3: - unregister_memory_notifier(&ehea_mem_nb); -out2: - unregister_reboot_notifier(&ehea_reboot_nb); -out: - atomic_dec(&ehea_memory_hooks_registered); - return ret; -} - -static void ehea_unregister_memory_hooks(void) -{ - /* Only remove the hooks if we've registered them */ - if (atomic_read(&ehea_memory_hooks_registered) == 0) - return; - - unregister_reboot_notifier(&ehea_reboot_nb); - if (crash_shutdown_unregister(ehea_crash_handler)) - pr_info("failed unregistering crash handler\n"); - unregister_memory_notifier(&ehea_mem_nb); -} - -static int ehea_probe_adapter(struct platform_device *dev) -{ - struct ehea_adapter *adapter; - const u64 *adapter_handle; - int ret; - int i; - - ret = ehea_register_memory_hooks(); - if (ret) - return ret; - - if (!dev || !dev->dev.of_node) { - pr_err("Invalid ibmebus device probed\n"); - return -EINVAL; - } - - adapter = devm_kzalloc(&dev->dev, sizeof(*adapter), GFP_KERNEL); - if (!adapter) { - ret = -ENOMEM; - dev_err(&dev->dev, "no mem for ehea_adapter\n"); - goto out; - } - - list_add(&adapter->list, &adapter_list); - - adapter->ofdev = dev; - - adapter_handle = of_get_property(dev->dev.of_node, "ibm,hea-handle", - NULL); - if (adapter_handle) - adapter->handle = *adapter_handle; - - if (!adapter->handle) { - dev_err(&dev->dev, "failed getting handle for adapter" - " '%pOF'\n", dev->dev.of_node); - ret = -ENODEV; - goto out_free_ad; - } - - adapter->pd = EHEA_PD_ID; - - platform_set_drvdata(dev, adapter); - - - /* initialize adapter and ports */ - /* get adapter properties */ - ret = ehea_sense_adapter_attr(adapter); - if (ret) { - dev_err(&dev->dev, "sense_adapter_attr failed: %d\n", ret); - goto out_free_ad; - } - - adapter->neq = ehea_create_eq(adapter, - EHEA_NEQ, EHEA_MAX_ENTRIES_EQ, 1); - if (!adapter->neq) { - ret = -EIO; - dev_err(&dev->dev, "NEQ creation failed\n"); - goto out_free_ad; - } - - tasklet_setup(&adapter->neq_tasklet, ehea_neq_tasklet); - - ret = ehea_create_device_sysfs(dev); - if (ret) - goto out_kill_eq; - - ret = ehea_setup_ports(adapter); - if (ret) { - dev_err(&dev->dev, "setup_ports failed\n"); - goto out_rem_dev_sysfs; - } - - ret = ibmebus_request_irq(adapter->neq->attr.ist1, - ehea_interrupt_neq, 0, - "ehea_neq", adapter); - if (ret) { - dev_err(&dev->dev, "requesting NEQ IRQ failed\n"); - goto out_shutdown_ports; - } - - /* Handle any events that might be pending. */ - tasklet_hi_schedule(&adapter->neq_tasklet); - - ret = 0; - goto out; - -out_shutdown_ports: - for (i = 0; i < EHEA_MAX_PORTS; i++) - if (adapter->port[i]) { - ehea_shutdown_single_port(adapter->port[i]); - adapter->port[i] = NULL; - } - -out_rem_dev_sysfs: - ehea_remove_device_sysfs(dev); - -out_kill_eq: - ehea_destroy_eq(adapter->neq); - -out_free_ad: - list_del(&adapter->list); - -out: - ehea_update_firmware_handles(); - - return ret; -} - -static void ehea_remove(struct platform_device *dev) -{ - struct ehea_adapter *adapter = platform_get_drvdata(dev); - int i; - - for (i = 0; i < EHEA_MAX_PORTS; i++) - if (adapter->port[i]) { - ehea_shutdown_single_port(adapter->port[i]); - adapter->port[i] = NULL; - } - - ehea_remove_device_sysfs(dev); - - ibmebus_free_irq(adapter->neq->attr.ist1, adapter); - tasklet_kill(&adapter->neq_tasklet); - - ehea_destroy_eq(adapter->neq); - ehea_remove_adapter_mr(adapter); - list_del(&adapter->list); - - ehea_update_firmware_handles(); -} - -static int check_module_parm(void) -{ - int ret = 0; - - if ((rq1_entries < EHEA_MIN_ENTRIES_QP) || - (rq1_entries > EHEA_MAX_ENTRIES_RQ1)) { - pr_info("Bad parameter: rq1_entries\n"); - ret = -EINVAL; - } - if ((rq2_entries < EHEA_MIN_ENTRIES_QP) || - (rq2_entries > EHEA_MAX_ENTRIES_RQ2)) { - pr_info("Bad parameter: rq2_entries\n"); - ret = -EINVAL; - } - if ((rq3_entries < EHEA_MIN_ENTRIES_QP) || - (rq3_entries > EHEA_MAX_ENTRIES_RQ3)) { - pr_info("Bad parameter: rq3_entries\n"); - ret = -EINVAL; - } - if ((sq_entries < EHEA_MIN_ENTRIES_QP) || - (sq_entries > EHEA_MAX_ENTRIES_SQ)) { - pr_info("Bad parameter: sq_entries\n"); - ret = -EINVAL; - } - - return ret; -} - -static ssize_t capabilities_show(struct device_driver *drv, char *buf) -{ - return sprintf(buf, "%d", EHEA_CAPABILITIES); -} - -static DRIVER_ATTR_RO(capabilities); - -static int __init ehea_module_init(void) -{ - int ret; - - pr_info("IBM eHEA ethernet device driver (Release %s)\n", DRV_VERSION); - - memset(&ehea_fw_handles, 0, sizeof(ehea_fw_handles)); - memset(&ehea_bcmc_regs, 0, sizeof(ehea_bcmc_regs)); - - mutex_init(&ehea_fw_handles.lock); - spin_lock_init(&ehea_bcmc_regs.lock); - - ret = check_module_parm(); - if (ret) - goto out; - - ret = ibmebus_register_driver(&ehea_driver); - if (ret) { - pr_err("failed registering eHEA device driver on ebus\n"); - goto out; - } - - ret = driver_create_file(&ehea_driver.driver, - &driver_attr_capabilities); - if (ret) { - pr_err("failed to register capabilities attribute, ret=%d\n", - ret); - goto out2; - } - - return ret; - -out2: - ibmebus_unregister_driver(&ehea_driver); -out: - return ret; -} - -static void __exit ehea_module_exit(void) -{ - driver_remove_file(&ehea_driver.driver, &driver_attr_capabilities); - ibmebus_unregister_driver(&ehea_driver); - ehea_unregister_memory_hooks(); - kfree(ehea_fw_handles.arr); - kfree(ehea_bcmc_regs.arr); - ehea_destroy_busmap(); -} - -module_init(ehea_module_init); -module_exit(ehea_module_exit); diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c b/drivers/net/ethernet/ibm/ehea/ehea_phyp.c deleted file mode 100644 index e63716e139f5..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.c +++ /dev/null @@ -1,612 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.c - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include "ehea_phyp.h" - - -static inline u16 get_order_of_qentries(u16 queue_entries) -{ - u8 ld = 1; /* logarithmus dualis */ - while (((1U << ld) - 1) < queue_entries) - ld++; - return ld - 1; -} - -/* Defines for H_CALL H_ALLOC_RESOURCE */ -#define H_ALL_RES_TYPE_QP 1 -#define H_ALL_RES_TYPE_CQ 2 -#define H_ALL_RES_TYPE_EQ 3 -#define H_ALL_RES_TYPE_MR 5 -#define H_ALL_RES_TYPE_MW 6 - -static long ehea_plpar_hcall_norets(unsigned long opcode, - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4, - unsigned long arg5, - unsigned long arg6, - unsigned long arg7) -{ - long ret; - int i, sleep_msecs; - - for (i = 0; i < 5; i++) { - ret = plpar_hcall_norets(opcode, arg1, arg2, arg3, arg4, - arg5, arg6, arg7); - - if (H_IS_LONG_BUSY(ret)) { - sleep_msecs = get_longbusy_msecs(ret); - msleep_interruptible(sleep_msecs); - continue; - } - - if (ret < H_SUCCESS) - pr_err("opcode=%lx ret=%lx" - " arg1=%lx arg2=%lx arg3=%lx arg4=%lx" - " arg5=%lx arg6=%lx arg7=%lx\n", - opcode, ret, - arg1, arg2, arg3, arg4, arg5, arg6, arg7); - - return ret; - } - - return H_BUSY; -} - -static long ehea_plpar_hcall9(unsigned long opcode, - unsigned long *outs, /* array of 9 outputs */ - unsigned long arg1, - unsigned long arg2, - unsigned long arg3, - unsigned long arg4, - unsigned long arg5, - unsigned long arg6, - unsigned long arg7, - unsigned long arg8, - unsigned long arg9) -{ - long ret; - int i, sleep_msecs; - u8 cb_cat; - - for (i = 0; i < 5; i++) { - ret = plpar_hcall9(opcode, outs, - arg1, arg2, arg3, arg4, arg5, - arg6, arg7, arg8, arg9); - - if (H_IS_LONG_BUSY(ret)) { - sleep_msecs = get_longbusy_msecs(ret); - msleep_interruptible(sleep_msecs); - continue; - } - - cb_cat = EHEA_BMASK_GET(H_MEHEAPORT_CAT, arg2); - - if ((ret < H_SUCCESS) && !(((ret == H_AUTHORITY) - && (opcode == H_MODIFY_HEA_PORT)) - && (((cb_cat == H_PORT_CB4) && ((arg3 == H_PORT_CB4_JUMBO) - || (arg3 == H_PORT_CB4_SPEED))) || ((cb_cat == H_PORT_CB7) - && (arg3 == H_PORT_CB7_DUCQPN))))) - pr_err("opcode=%lx ret=%lx" - " arg1=%lx arg2=%lx arg3=%lx arg4=%lx" - " arg5=%lx arg6=%lx arg7=%lx arg8=%lx" - " arg9=%lx" - " out1=%lx out2=%lx out3=%lx out4=%lx" - " out5=%lx out6=%lx out7=%lx out8=%lx" - " out9=%lx\n", - opcode, ret, - arg1, arg2, arg3, arg4, arg5, - arg6, arg7, arg8, arg9, - outs[0], outs[1], outs[2], outs[3], outs[4], - outs[5], outs[6], outs[7], outs[8]); - return ret; - } - - return H_BUSY; -} - -u64 ehea_h_query_ehea_qp(const u64 adapter_handle, const u8 qp_category, - const u64 qp_handle, const u64 sel_mask, void *cb_addr) -{ - return ehea_plpar_hcall_norets(H_QUERY_HEA_QP, - adapter_handle, /* R4 */ - qp_category, /* R5 */ - qp_handle, /* R6 */ - sel_mask, /* R7 */ - __pa(cb_addr), /* R8 */ - 0, 0); -} - -/* input param R5 */ -#define H_ALL_RES_QP_EQPO EHEA_BMASK_IBM(9, 11) -#define H_ALL_RES_QP_QPP EHEA_BMASK_IBM(12, 12) -#define H_ALL_RES_QP_RQR EHEA_BMASK_IBM(13, 15) -#define H_ALL_RES_QP_EQEG EHEA_BMASK_IBM(16, 16) -#define H_ALL_RES_QP_LL_QP EHEA_BMASK_IBM(17, 17) -#define H_ALL_RES_QP_DMA128 EHEA_BMASK_IBM(19, 19) -#define H_ALL_RES_QP_HSM EHEA_BMASK_IBM(20, 21) -#define H_ALL_RES_QP_SIGT EHEA_BMASK_IBM(22, 23) -#define H_ALL_RES_QP_TENURE EHEA_BMASK_IBM(48, 55) -#define H_ALL_RES_QP_RES_TYP EHEA_BMASK_IBM(56, 63) - -/* input param R9 */ -#define H_ALL_RES_QP_TOKEN EHEA_BMASK_IBM(0, 31) -#define H_ALL_RES_QP_PD EHEA_BMASK_IBM(32, 63) - -/* input param R10 */ -#define H_ALL_RES_QP_MAX_SWQE EHEA_BMASK_IBM(4, 7) -#define H_ALL_RES_QP_MAX_R1WQE EHEA_BMASK_IBM(12, 15) -#define H_ALL_RES_QP_MAX_R2WQE EHEA_BMASK_IBM(20, 23) -#define H_ALL_RES_QP_MAX_R3WQE EHEA_BMASK_IBM(28, 31) -/* Max Send Scatter Gather Elements */ -#define H_ALL_RES_QP_MAX_SSGE EHEA_BMASK_IBM(37, 39) -#define H_ALL_RES_QP_MAX_R1SGE EHEA_BMASK_IBM(45, 47) -/* Max Receive SG Elements RQ1 */ -#define H_ALL_RES_QP_MAX_R2SGE EHEA_BMASK_IBM(53, 55) -#define H_ALL_RES_QP_MAX_R3SGE EHEA_BMASK_IBM(61, 63) - -/* input param R11 */ -#define H_ALL_RES_QP_SWQE_IDL EHEA_BMASK_IBM(0, 7) -/* max swqe immediate data length */ -#define H_ALL_RES_QP_PORT_NUM EHEA_BMASK_IBM(48, 63) - -/* input param R12 */ -#define H_ALL_RES_QP_TH_RQ2 EHEA_BMASK_IBM(0, 15) -/* Threshold RQ2 */ -#define H_ALL_RES_QP_TH_RQ3 EHEA_BMASK_IBM(16, 31) -/* Threshold RQ3 */ - -/* output param R6 */ -#define H_ALL_RES_QP_ACT_SWQE EHEA_BMASK_IBM(0, 15) -#define H_ALL_RES_QP_ACT_R1WQE EHEA_BMASK_IBM(16, 31) -#define H_ALL_RES_QP_ACT_R2WQE EHEA_BMASK_IBM(32, 47) -#define H_ALL_RES_QP_ACT_R3WQE EHEA_BMASK_IBM(48, 63) - -/* output param, R7 */ -#define H_ALL_RES_QP_ACT_SSGE EHEA_BMASK_IBM(0, 7) -#define H_ALL_RES_QP_ACT_R1SGE EHEA_BMASK_IBM(8, 15) -#define H_ALL_RES_QP_ACT_R2SGE EHEA_BMASK_IBM(16, 23) -#define H_ALL_RES_QP_ACT_R3SGE EHEA_BMASK_IBM(24, 31) -#define H_ALL_RES_QP_ACT_SWQE_IDL EHEA_BMASK_IBM(32, 39) - -/* output param R8,R9 */ -#define H_ALL_RES_QP_SIZE_SQ EHEA_BMASK_IBM(0, 31) -#define H_ALL_RES_QP_SIZE_RQ1 EHEA_BMASK_IBM(32, 63) -#define H_ALL_RES_QP_SIZE_RQ2 EHEA_BMASK_IBM(0, 31) -#define H_ALL_RES_QP_SIZE_RQ3 EHEA_BMASK_IBM(32, 63) - -/* output param R11,R12 */ -#define H_ALL_RES_QP_LIOBN_SQ EHEA_BMASK_IBM(0, 31) -#define H_ALL_RES_QP_LIOBN_RQ1 EHEA_BMASK_IBM(32, 63) -#define H_ALL_RES_QP_LIOBN_RQ2 EHEA_BMASK_IBM(0, 31) -#define H_ALL_RES_QP_LIOBN_RQ3 EHEA_BMASK_IBM(32, 63) - -u64 ehea_h_alloc_resource_qp(const u64 adapter_handle, - struct ehea_qp_init_attr *init_attr, const u32 pd, - u64 *qp_handle, struct h_epas *h_epas) -{ - u64 hret; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - u64 allocate_controls = - EHEA_BMASK_SET(H_ALL_RES_QP_EQPO, init_attr->low_lat_rq1 ? 1 : 0) - | EHEA_BMASK_SET(H_ALL_RES_QP_QPP, 0) - | EHEA_BMASK_SET(H_ALL_RES_QP_RQR, 6) /* rq1 & rq2 & rq3 */ - | EHEA_BMASK_SET(H_ALL_RES_QP_EQEG, 0) /* EQE gen. disabled */ - | EHEA_BMASK_SET(H_ALL_RES_QP_LL_QP, init_attr->low_lat_rq1) - | EHEA_BMASK_SET(H_ALL_RES_QP_DMA128, 0) - | EHEA_BMASK_SET(H_ALL_RES_QP_HSM, 0) - | EHEA_BMASK_SET(H_ALL_RES_QP_SIGT, init_attr->signalingtype) - | EHEA_BMASK_SET(H_ALL_RES_QP_RES_TYP, H_ALL_RES_TYPE_QP); - - u64 r9_reg = EHEA_BMASK_SET(H_ALL_RES_QP_PD, pd) - | EHEA_BMASK_SET(H_ALL_RES_QP_TOKEN, init_attr->qp_token); - - u64 max_r10_reg = - EHEA_BMASK_SET(H_ALL_RES_QP_MAX_SWQE, - get_order_of_qentries(init_attr->max_nr_send_wqes)) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R1WQE, - get_order_of_qentries(init_attr->max_nr_rwqes_rq1)) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R2WQE, - get_order_of_qentries(init_attr->max_nr_rwqes_rq2)) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R3WQE, - get_order_of_qentries(init_attr->max_nr_rwqes_rq3)) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_SSGE, init_attr->wqe_size_enc_sq) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R1SGE, - init_attr->wqe_size_enc_rq1) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R2SGE, - init_attr->wqe_size_enc_rq2) - | EHEA_BMASK_SET(H_ALL_RES_QP_MAX_R3SGE, - init_attr->wqe_size_enc_rq3); - - u64 r11_in = - EHEA_BMASK_SET(H_ALL_RES_QP_SWQE_IDL, init_attr->swqe_imm_data_len) - | EHEA_BMASK_SET(H_ALL_RES_QP_PORT_NUM, init_attr->port_nr); - u64 threshold = - EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ2, init_attr->rq2_threshold) - | EHEA_BMASK_SET(H_ALL_RES_QP_TH_RQ3, init_attr->rq3_threshold); - - hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, - outs, - adapter_handle, /* R4 */ - allocate_controls, /* R5 */ - init_attr->send_cq_handle, /* R6 */ - init_attr->recv_cq_handle, /* R7 */ - init_attr->aff_eq_handle, /* R8 */ - r9_reg, /* R9 */ - max_r10_reg, /* R10 */ - r11_in, /* R11 */ - threshold); /* R12 */ - - *qp_handle = outs[0]; - init_attr->qp_nr = (u32)outs[1]; - - init_attr->act_nr_send_wqes = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_SWQE, outs[2]); - init_attr->act_nr_rwqes_rq1 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R1WQE, outs[2]); - init_attr->act_nr_rwqes_rq2 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R2WQE, outs[2]); - init_attr->act_nr_rwqes_rq3 = - (u16)EHEA_BMASK_GET(H_ALL_RES_QP_ACT_R3WQE, outs[2]); - - init_attr->act_wqe_size_enc_sq = init_attr->wqe_size_enc_sq; - init_attr->act_wqe_size_enc_rq1 = init_attr->wqe_size_enc_rq1; - init_attr->act_wqe_size_enc_rq2 = init_attr->wqe_size_enc_rq2; - init_attr->act_wqe_size_enc_rq3 = init_attr->wqe_size_enc_rq3; - - init_attr->nr_sq_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_SQ, outs[4]); - init_attr->nr_rq1_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ1, outs[4]); - init_attr->nr_rq2_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ2, outs[5]); - init_attr->nr_rq3_pages = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_SIZE_RQ3, outs[5]); - - init_attr->liobn_sq = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_SQ, outs[7]); - init_attr->liobn_rq1 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ1, outs[7]); - init_attr->liobn_rq2 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ2, outs[8]); - init_attr->liobn_rq3 = - (u32)EHEA_BMASK_GET(H_ALL_RES_QP_LIOBN_RQ3, outs[8]); - - if (!hret) - hcp_epas_ctor(h_epas, outs[6], outs[6]); - - return hret; -} - -u64 ehea_h_alloc_resource_cq(const u64 adapter_handle, - struct ehea_cq_attr *cq_attr, - u64 *cq_handle, struct h_epas *epas) -{ - u64 hret; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, - outs, - adapter_handle, /* R4 */ - H_ALL_RES_TYPE_CQ, /* R5 */ - cq_attr->eq_handle, /* R6 */ - cq_attr->cq_token, /* R7 */ - cq_attr->max_nr_of_cqes, /* R8 */ - 0, 0, 0, 0); /* R9-R12 */ - - *cq_handle = outs[0]; - cq_attr->act_nr_of_cqes = outs[3]; - cq_attr->nr_pages = outs[4]; - - if (!hret) - hcp_epas_ctor(epas, outs[5], outs[6]); - - return hret; -} - -/* Defines for H_CALL H_ALLOC_RESOURCE */ -#define H_ALL_RES_TYPE_QP 1 -#define H_ALL_RES_TYPE_CQ 2 -#define H_ALL_RES_TYPE_EQ 3 -#define H_ALL_RES_TYPE_MR 5 -#define H_ALL_RES_TYPE_MW 6 - -/* input param R5 */ -#define H_ALL_RES_EQ_NEQ EHEA_BMASK_IBM(0, 0) -#define H_ALL_RES_EQ_NON_NEQ_ISN EHEA_BMASK_IBM(6, 7) -#define H_ALL_RES_EQ_INH_EQE_GEN EHEA_BMASK_IBM(16, 16) -#define H_ALL_RES_EQ_RES_TYPE EHEA_BMASK_IBM(56, 63) -/* input param R6 */ -#define H_ALL_RES_EQ_MAX_EQE EHEA_BMASK_IBM(32, 63) - -/* output param R6 */ -#define H_ALL_RES_EQ_LIOBN EHEA_BMASK_IBM(32, 63) - -/* output param R7 */ -#define H_ALL_RES_EQ_ACT_EQE EHEA_BMASK_IBM(32, 63) - -/* output param R8 */ -#define H_ALL_RES_EQ_ACT_PS EHEA_BMASK_IBM(32, 63) - -/* output param R9 */ -#define H_ALL_RES_EQ_ACT_EQ_IST_C EHEA_BMASK_IBM(30, 31) -#define H_ALL_RES_EQ_ACT_EQ_IST_1 EHEA_BMASK_IBM(40, 63) - -/* output param R10 */ -#define H_ALL_RES_EQ_ACT_EQ_IST_2 EHEA_BMASK_IBM(40, 63) - -/* output param R11 */ -#define H_ALL_RES_EQ_ACT_EQ_IST_3 EHEA_BMASK_IBM(40, 63) - -/* output param R12 */ -#define H_ALL_RES_EQ_ACT_EQ_IST_4 EHEA_BMASK_IBM(40, 63) - -u64 ehea_h_alloc_resource_eq(const u64 adapter_handle, - struct ehea_eq_attr *eq_attr, u64 *eq_handle) -{ - u64 hret, allocate_controls; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - /* resource type */ - allocate_controls = - EHEA_BMASK_SET(H_ALL_RES_EQ_RES_TYPE, H_ALL_RES_TYPE_EQ) - | EHEA_BMASK_SET(H_ALL_RES_EQ_NEQ, eq_attr->type ? 1 : 0) - | EHEA_BMASK_SET(H_ALL_RES_EQ_INH_EQE_GEN, !eq_attr->eqe_gen) - | EHEA_BMASK_SET(H_ALL_RES_EQ_NON_NEQ_ISN, 1); - - hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, - outs, - adapter_handle, /* R4 */ - allocate_controls, /* R5 */ - eq_attr->max_nr_of_eqes, /* R6 */ - 0, 0, 0, 0, 0, 0); /* R7-R10 */ - - *eq_handle = outs[0]; - eq_attr->act_nr_of_eqes = outs[3]; - eq_attr->nr_pages = outs[4]; - eq_attr->ist1 = outs[5]; - eq_attr->ist2 = outs[6]; - eq_attr->ist3 = outs[7]; - eq_attr->ist4 = outs[8]; - - return hret; -} - -u64 ehea_h_modify_ehea_qp(const u64 adapter_handle, const u8 cat, - const u64 qp_handle, const u64 sel_mask, - void *cb_addr, u64 *inv_attr_id, u64 *proc_mask, - u16 *out_swr, u16 *out_rwr) -{ - u64 hret; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - hret = ehea_plpar_hcall9(H_MODIFY_HEA_QP, - outs, - adapter_handle, /* R4 */ - (u64) cat, /* R5 */ - qp_handle, /* R6 */ - sel_mask, /* R7 */ - __pa(cb_addr), /* R8 */ - 0, 0, 0, 0); /* R9-R12 */ - - *inv_attr_id = outs[0]; - *out_swr = outs[3]; - *out_rwr = outs[4]; - *proc_mask = outs[5]; - - return hret; -} - -u64 ehea_h_register_rpage(const u64 adapter_handle, const u8 pagesize, - const u8 queue_type, const u64 resource_handle, - const u64 log_pageaddr, u64 count) -{ - u64 reg_control; - - reg_control = EHEA_BMASK_SET(H_REG_RPAGE_PAGE_SIZE, pagesize) - | EHEA_BMASK_SET(H_REG_RPAGE_QT, queue_type); - - return ehea_plpar_hcall_norets(H_REGISTER_HEA_RPAGES, - adapter_handle, /* R4 */ - reg_control, /* R5 */ - resource_handle, /* R6 */ - log_pageaddr, /* R7 */ - count, /* R8 */ - 0, 0); /* R9-R10 */ -} - -u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle, - const u64 vaddr_in, const u32 access_ctrl, const u32 pd, - struct ehea_mr *mr) -{ - u64 hret; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - hret = ehea_plpar_hcall9(H_REGISTER_SMR, - outs, - adapter_handle , /* R4 */ - orig_mr_handle, /* R5 */ - vaddr_in, /* R6 */ - (((u64)access_ctrl) << 32ULL), /* R7 */ - pd, /* R8 */ - 0, 0, 0, 0); /* R9-R12 */ - - mr->handle = outs[0]; - mr->lkey = (u32)outs[2]; - - return hret; -} - -u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle) -{ - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - return ehea_plpar_hcall9(H_DISABLE_AND_GET_HEA, - outs, - adapter_handle, /* R4 */ - H_DISABLE_GET_EHEA_WQE_P, /* R5 */ - qp_handle, /* R6 */ - 0, 0, 0, 0, 0, 0); /* R7-R12 */ -} - -u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle, - u64 force_bit) -{ - return ehea_plpar_hcall_norets(H_FREE_RESOURCE, - adapter_handle, /* R4 */ - res_handle, /* R5 */ - force_bit, - 0, 0, 0, 0); /* R7-R10 */ -} - -u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr, - const u64 length, const u32 access_ctrl, - const u32 pd, u64 *mr_handle, u32 *lkey) -{ - u64 hret; - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - - hret = ehea_plpar_hcall9(H_ALLOC_HEA_RESOURCE, - outs, - adapter_handle, /* R4 */ - 5, /* R5 */ - vaddr, /* R6 */ - length, /* R7 */ - (((u64) access_ctrl) << 32ULL), /* R8 */ - pd, /* R9 */ - 0, 0, 0); /* R10-R12 */ - - *mr_handle = outs[0]; - *lkey = (u32)outs[2]; - return hret; -} - -u64 ehea_h_register_rpage_mr(const u64 adapter_handle, const u64 mr_handle, - const u8 pagesize, const u8 queue_type, - const u64 log_pageaddr, const u64 count) -{ - if ((count > 1) && (log_pageaddr & ~PAGE_MASK)) { - pr_err("not on pageboundary\n"); - return H_PARAMETER; - } - - return ehea_h_register_rpage(adapter_handle, pagesize, - queue_type, mr_handle, - log_pageaddr, count); -} - -u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr) -{ - u64 hret, cb_logaddr; - - cb_logaddr = __pa(cb_addr); - - hret = ehea_plpar_hcall_norets(H_QUERY_HEA, - adapter_handle, /* R4 */ - cb_logaddr, /* R5 */ - 0, 0, 0, 0, 0); /* R6-R10 */ -#ifdef DEBUG - ehea_dump(cb_addr, sizeof(struct hcp_query_ehea), "hcp_query_ehea"); -#endif - return hret; -} - -u64 ehea_h_query_ehea_port(const u64 adapter_handle, const u16 port_num, - const u8 cb_cat, const u64 select_mask, - void *cb_addr) -{ - u64 port_info; - u64 cb_logaddr = __pa(cb_addr); - u64 arr_index = 0; - - port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat) - | EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num); - - return ehea_plpar_hcall_norets(H_QUERY_HEA_PORT, - adapter_handle, /* R4 */ - port_info, /* R5 */ - select_mask, /* R6 */ - arr_index, /* R7 */ - cb_logaddr, /* R8 */ - 0, 0); /* R9-R10 */ -} - -u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num, - const u8 cb_cat, const u64 select_mask, - void *cb_addr) -{ - unsigned long outs[PLPAR_HCALL9_BUFSIZE]; - u64 port_info; - u64 arr_index = 0; - u64 cb_logaddr = __pa(cb_addr); - - port_info = EHEA_BMASK_SET(H_MEHEAPORT_CAT, cb_cat) - | EHEA_BMASK_SET(H_MEHEAPORT_PN, port_num); -#ifdef DEBUG - ehea_dump(cb_addr, sizeof(struct hcp_ehea_port_cb0), "Before HCALL"); -#endif - return ehea_plpar_hcall9(H_MODIFY_HEA_PORT, - outs, - adapter_handle, /* R4 */ - port_info, /* R5 */ - select_mask, /* R6 */ - arr_index, /* R7 */ - cb_logaddr, /* R8 */ - 0, 0, 0, 0); /* R9-R12 */ -} - -u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num, - const u8 reg_type, const u64 mc_mac_addr, - const u16 vlan_id, const u32 hcall_id) -{ - u64 r5_port_num, r6_reg_type, r7_mc_mac_addr, r8_vlan_id; - u64 mac_addr = mc_mac_addr >> 16; - - r5_port_num = EHEA_BMASK_SET(H_REGBCMC_PN, port_num); - r6_reg_type = EHEA_BMASK_SET(H_REGBCMC_REGTYPE, reg_type); - r7_mc_mac_addr = EHEA_BMASK_SET(H_REGBCMC_MACADDR, mac_addr); - r8_vlan_id = EHEA_BMASK_SET(H_REGBCMC_VLANID, vlan_id); - - return ehea_plpar_hcall_norets(hcall_id, - adapter_handle, /* R4 */ - r5_port_num, /* R5 */ - r6_reg_type, /* R6 */ - r7_mc_mac_addr, /* R7 */ - r8_vlan_id, /* R8 */ - 0, 0); /* R9-R12 */ -} - -u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle, - const u64 event_mask) -{ - return ehea_plpar_hcall_norets(H_RESET_EVENTS, - adapter_handle, /* R4 */ - neq_handle, /* R5 */ - event_mask, /* R6 */ - 0, 0, 0, 0); /* R7-R12 */ -} - -u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle, - void *rblock) -{ - return ehea_plpar_hcall_norets(H_ERROR_DATA, - adapter_handle, /* R4 */ - ressource_handle, /* R5 */ - __pa(rblock), /* R6 */ - 0, 0, 0, 0); /* R7-R12 */ -} diff --git a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h b/drivers/net/ethernet/ibm/ehea/ehea_phyp.h deleted file mode 100644 index e8b56c103410..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_phyp.h +++ /dev/null @@ -1,433 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_phyp.h - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#ifndef __EHEA_PHYP_H__ -#define __EHEA_PHYP_H__ - -#include <linux/delay.h> -#include <asm/hvcall.h> -#include "ehea.h" -#include "ehea_hw.h" - -/* Some abbreviations used here: - * - * hcp_* - structures, variables and functions releated to Hypervisor Calls - */ - -/* Number of pages which can be registered at once by H_REGISTER_HEA_RPAGES */ -#define EHEA_MAX_RPAGE 512 - -/* Notification Event Queue (NEQ) Entry bit masks */ -#define NEQE_EVENT_CODE EHEA_BMASK_IBM(2, 7) -#define NEQE_PORTNUM EHEA_BMASK_IBM(32, 47) -#define NEQE_PORT_UP EHEA_BMASK_IBM(16, 16) -#define NEQE_EXTSWITCH_PORT_UP EHEA_BMASK_IBM(17, 17) -#define NEQE_EXTSWITCH_PRIMARY EHEA_BMASK_IBM(18, 18) -#define NEQE_PLID EHEA_BMASK_IBM(16, 47) - -/* Notification Event Codes */ -#define EHEA_EC_PORTSTATE_CHG 0x30 -#define EHEA_EC_ADAPTER_MALFUNC 0x32 -#define EHEA_EC_PORT_MALFUNC 0x33 - -/* Notification Event Log Register (NELR) bit masks */ -#define NELR_PORT_MALFUNC EHEA_BMASK_IBM(61, 61) -#define NELR_ADAPTER_MALFUNC EHEA_BMASK_IBM(62, 62) -#define NELR_PORTSTATE_CHG EHEA_BMASK_IBM(63, 63) - -static inline void hcp_epas_ctor(struct h_epas *epas, u64 paddr_kernel, - u64 paddr_user) -{ - /* To support 64k pages we must round to 64k page boundary */ - epas->kernel.addr = ioremap((paddr_kernel & PAGE_MASK), PAGE_SIZE) + - (paddr_kernel & ~PAGE_MASK); - epas->user.addr = paddr_user; -} - -static inline void hcp_epas_dtor(struct h_epas *epas) -{ - if (epas->kernel.addr) - iounmap((void __iomem *)((u64)epas->kernel.addr & PAGE_MASK)); - - epas->user.addr = 0; - epas->kernel.addr = 0; -} - -struct hcp_modify_qp_cb0 { - u64 qp_ctl_reg; /* 00 */ - u32 max_swqe; /* 02 */ - u32 max_rwqe; /* 03 */ - u32 port_nb; /* 04 */ - u32 reserved0; /* 05 */ - u64 qp_aer; /* 06 */ - u64 qp_tenure; /* 08 */ -}; - -/* Hcall Query/Modify Queue Pair Control Block 0 Selection Mask Bits */ -#define H_QPCB0_ALL EHEA_BMASK_IBM(0, 5) -#define H_QPCB0_QP_CTL_REG EHEA_BMASK_IBM(0, 0) -#define H_QPCB0_MAX_SWQE EHEA_BMASK_IBM(1, 1) -#define H_QPCB0_MAX_RWQE EHEA_BMASK_IBM(2, 2) -#define H_QPCB0_PORT_NB EHEA_BMASK_IBM(3, 3) -#define H_QPCB0_QP_AER EHEA_BMASK_IBM(4, 4) -#define H_QPCB0_QP_TENURE EHEA_BMASK_IBM(5, 5) - -/* Queue Pair Control Register Status Bits */ -#define H_QP_CR_ENABLED 0x8000000000000000ULL /* QP enabled */ - /* QP States: */ -#define H_QP_CR_STATE_RESET 0x0000010000000000ULL /* Reset */ -#define H_QP_CR_STATE_INITIALIZED 0x0000020000000000ULL /* Initialized */ -#define H_QP_CR_STATE_RDY2RCV 0x0000030000000000ULL /* Ready to recv */ -#define H_QP_CR_STATE_RDY2SND 0x0000050000000000ULL /* Ready to send */ -#define H_QP_CR_STATE_ERROR 0x0000800000000000ULL /* Error */ -#define H_QP_CR_RES_STATE 0x0000007F00000000ULL /* Resultant state */ - -struct hcp_modify_qp_cb1 { - u32 qpn; /* 00 */ - u32 qp_asyn_ev_eq_nb; /* 01 */ - u64 sq_cq_handle; /* 02 */ - u64 rq_cq_handle; /* 04 */ - /* sgel = scatter gather element */ - u32 sgel_nb_sq; /* 06 */ - u32 sgel_nb_rq1; /* 07 */ - u32 sgel_nb_rq2; /* 08 */ - u32 sgel_nb_rq3; /* 09 */ -}; - -/* Hcall Query/Modify Queue Pair Control Block 1 Selection Mask Bits */ -#define H_QPCB1_ALL EHEA_BMASK_IBM(0, 7) -#define H_QPCB1_QPN EHEA_BMASK_IBM(0, 0) -#define H_QPCB1_ASYN_EV_EQ_NB EHEA_BMASK_IBM(1, 1) -#define H_QPCB1_SQ_CQ_HANDLE EHEA_BMASK_IBM(2, 2) -#define H_QPCB1_RQ_CQ_HANDLE EHEA_BMASK_IBM(3, 3) -#define H_QPCB1_SGEL_NB_SQ EHEA_BMASK_IBM(4, 4) -#define H_QPCB1_SGEL_NB_RQ1 EHEA_BMASK_IBM(5, 5) -#define H_QPCB1_SGEL_NB_RQ2 EHEA_BMASK_IBM(6, 6) -#define H_QPCB1_SGEL_NB_RQ3 EHEA_BMASK_IBM(7, 7) - -struct hcp_query_ehea { - u32 cur_num_qps; /* 00 */ - u32 cur_num_cqs; /* 01 */ - u32 cur_num_eqs; /* 02 */ - u32 cur_num_mrs; /* 03 */ - u32 auth_level; /* 04 */ - u32 max_num_qps; /* 05 */ - u32 max_num_cqs; /* 06 */ - u32 max_num_eqs; /* 07 */ - u32 max_num_mrs; /* 08 */ - u32 reserved0; /* 09 */ - u32 int_clock_freq; /* 10 */ - u32 max_num_pds; /* 11 */ - u32 max_num_addr_handles; /* 12 */ - u32 max_num_cqes; /* 13 */ - u32 max_num_wqes; /* 14 */ - u32 max_num_sgel_rq1wqe; /* 15 */ - u32 max_num_sgel_rq2wqe; /* 16 */ - u32 max_num_sgel_rq3wqe; /* 17 */ - u32 mr_page_size; /* 18 */ - u32 reserved1; /* 19 */ - u64 max_mr_size; /* 20 */ - u64 reserved2; /* 22 */ - u32 num_ports; /* 24 */ - u32 reserved3; /* 25 */ - u32 reserved4; /* 26 */ - u32 reserved5; /* 27 */ - u64 max_mc_mac; /* 28 */ - u64 ehea_cap; /* 30 */ - u32 max_isn_per_eq; /* 32 */ - u32 max_num_neq; /* 33 */ - u64 max_num_vlan_ids; /* 34 */ - u32 max_num_port_group; /* 36 */ - u32 max_num_phys_port; /* 37 */ - -}; - -/* Hcall Query/Modify Port Control Block defines */ -#define H_PORT_CB0 0 -#define H_PORT_CB1 1 -#define H_PORT_CB2 2 -#define H_PORT_CB3 3 -#define H_PORT_CB4 4 -#define H_PORT_CB5 5 -#define H_PORT_CB6 6 -#define H_PORT_CB7 7 - -struct hcp_ehea_port_cb0 { - u64 port_mac_addr; - u64 port_rc; - u64 reserved0; - u32 port_op_state; - u32 port_speed; - u32 ext_swport_op_state; - u32 neg_tpf_prpf; - u32 num_default_qps; - u32 reserved1; - u64 default_qpn_arr[16]; -}; - -/* Hcall Query/Modify Port Control Block 0 Selection Mask Bits */ -#define H_PORT_CB0_ALL EHEA_BMASK_IBM(0, 7) /* Set all bits */ -#define H_PORT_CB0_MAC EHEA_BMASK_IBM(0, 0) /* MAC address */ -#define H_PORT_CB0_PRC EHEA_BMASK_IBM(1, 1) /* Port Recv Control */ -#define H_PORT_CB0_DEFQPNARRAY EHEA_BMASK_IBM(7, 7) /* Default QPN Array */ - -/* Hcall Query Port: Returned port speed values */ -#define H_SPEED_10M_H 1 /* 10 Mbps, Half Duplex */ -#define H_SPEED_10M_F 2 /* 10 Mbps, Full Duplex */ -#define H_SPEED_100M_H 3 /* 100 Mbps, Half Duplex */ -#define H_SPEED_100M_F 4 /* 100 Mbps, Full Duplex */ -#define H_SPEED_1G_F 6 /* 1 Gbps, Full Duplex */ -#define H_SPEED_10G_F 8 /* 10 Gbps, Full Duplex */ - -/* Port Receive Control Status Bits */ -#define PXLY_RC_VALID EHEA_BMASK_IBM(49, 49) -#define PXLY_RC_VLAN_XTRACT EHEA_BMASK_IBM(50, 50) -#define PXLY_RC_TCP_6_TUPLE EHEA_BMASK_IBM(51, 51) -#define PXLY_RC_UDP_6_TUPLE EHEA_BMASK_IBM(52, 52) -#define PXLY_RC_TCP_3_TUPLE EHEA_BMASK_IBM(53, 53) -#define PXLY_RC_TCP_2_TUPLE EHEA_BMASK_IBM(54, 54) -#define PXLY_RC_LLC_SNAP EHEA_BMASK_IBM(55, 55) -#define PXLY_RC_JUMBO_FRAME EHEA_BMASK_IBM(56, 56) -#define PXLY_RC_FRAG_IP_PKT EHEA_BMASK_IBM(57, 57) -#define PXLY_RC_TCP_UDP_CHKSUM EHEA_BMASK_IBM(58, 58) -#define PXLY_RC_IP_CHKSUM EHEA_BMASK_IBM(59, 59) -#define PXLY_RC_MAC_FILTER EHEA_BMASK_IBM(60, 60) -#define PXLY_RC_UNTAG_FILTER EHEA_BMASK_IBM(61, 61) -#define PXLY_RC_VLAN_TAG_FILTER EHEA_BMASK_IBM(62, 63) - -#define PXLY_RC_VLAN_FILTER 2 -#define PXLY_RC_VLAN_PERM 0 - - -#define H_PORT_CB1_ALL 0x8000000000000000ULL - -struct hcp_ehea_port_cb1 { - u64 vlan_filter[64]; -}; - -#define H_PORT_CB2_ALL 0xFFE0000000000000ULL - -struct hcp_ehea_port_cb2 { - u64 rxo; - u64 rxucp; - u64 rxufd; - u64 rxuerr; - u64 rxftl; - u64 rxmcp; - u64 rxbcp; - u64 txo; - u64 txucp; - u64 txmcp; - u64 txbcp; -}; - -struct hcp_ehea_port_cb3 { - u64 vlan_bc_filter[64]; - u64 vlan_mc_filter[64]; - u64 vlan_un_filter[64]; - u64 port_mac_hash_array[64]; -}; - -#define H_PORT_CB4_ALL 0xF000000000000000ULL -#define H_PORT_CB4_JUMBO 0x1000000000000000ULL -#define H_PORT_CB4_SPEED 0x8000000000000000ULL - -struct hcp_ehea_port_cb4 { - u32 port_speed; - u32 pause_frame; - u32 ens_port_op_state; - u32 jumbo_frame; - u32 ens_port_wrap; -}; - -/* Hcall Query/Modify Port Control Block 5 Selection Mask Bits */ -#define H_PORT_CB5_RCU 0x0001000000000000ULL -#define PXS_RCU EHEA_BMASK_IBM(61, 63) - -struct hcp_ehea_port_cb5 { - u64 prc; /* 00 */ - u64 uaa; /* 01 */ - u64 macvc; /* 02 */ - u64 xpcsc; /* 03 */ - u64 xpcsp; /* 04 */ - u64 pcsid; /* 05 */ - u64 xpcsst; /* 06 */ - u64 pthlb; /* 07 */ - u64 pthrb; /* 08 */ - u64 pqu; /* 09 */ - u64 pqd; /* 10 */ - u64 prt; /* 11 */ - u64 wsth; /* 12 */ - u64 rcb; /* 13 */ - u64 rcm; /* 14 */ - u64 rcu; /* 15 */ - u64 macc; /* 16 */ - u64 pc; /* 17 */ - u64 pst; /* 18 */ - u64 ducqpn; /* 19 */ - u64 mcqpn; /* 20 */ - u64 mma; /* 21 */ - u64 pmc0h; /* 22 */ - u64 pmc0l; /* 23 */ - u64 lbc; /* 24 */ -}; - -#define H_PORT_CB6_ALL 0xFFFFFE7FFFFF8000ULL - -struct hcp_ehea_port_cb6 { - u64 rxo; /* 00 */ - u64 rx64; /* 01 */ - u64 rx65; /* 02 */ - u64 rx128; /* 03 */ - u64 rx256; /* 04 */ - u64 rx512; /* 05 */ - u64 rx1024; /* 06 */ - u64 rxbfcs; /* 07 */ - u64 rxime; /* 08 */ - u64 rxrle; /* 09 */ - u64 rxorle; /* 10 */ - u64 rxftl; /* 11 */ - u64 rxjab; /* 12 */ - u64 rxse; /* 13 */ - u64 rxce; /* 14 */ - u64 rxrf; /* 15 */ - u64 rxfrag; /* 16 */ - u64 rxuoc; /* 17 */ - u64 rxcpf; /* 18 */ - u64 rxsb; /* 19 */ - u64 rxfd; /* 20 */ - u64 rxoerr; /* 21 */ - u64 rxaln; /* 22 */ - u64 ducqpn; /* 23 */ - u64 reserved0; /* 24 */ - u64 rxmcp; /* 25 */ - u64 rxbcp; /* 26 */ - u64 txmcp; /* 27 */ - u64 txbcp; /* 28 */ - u64 txo; /* 29 */ - u64 tx64; /* 30 */ - u64 tx65; /* 31 */ - u64 tx128; /* 32 */ - u64 tx256; /* 33 */ - u64 tx512; /* 34 */ - u64 tx1024; /* 35 */ - u64 txbfcs; /* 36 */ - u64 txcpf; /* 37 */ - u64 txlf; /* 38 */ - u64 txrf; /* 39 */ - u64 txime; /* 40 */ - u64 txsc; /* 41 */ - u64 txmc; /* 42 */ - u64 txsqe; /* 43 */ - u64 txdef; /* 44 */ - u64 txlcol; /* 45 */ - u64 txexcol; /* 46 */ - u64 txcse; /* 47 */ - u64 txbor; /* 48 */ -}; - -#define H_PORT_CB7_DUCQPN 0x8000000000000000ULL - -struct hcp_ehea_port_cb7 { - u64 def_uc_qpn; -}; - -u64 ehea_h_query_ehea_qp(const u64 adapter_handle, - const u8 qp_category, - const u64 qp_handle, const u64 sel_mask, - void *cb_addr); - -u64 ehea_h_modify_ehea_qp(const u64 adapter_handle, - const u8 cat, - const u64 qp_handle, - const u64 sel_mask, - void *cb_addr, - u64 *inv_attr_id, - u64 *proc_mask, u16 *out_swr, u16 *out_rwr); - -u64 ehea_h_alloc_resource_eq(const u64 adapter_handle, - struct ehea_eq_attr *eq_attr, u64 *eq_handle); - -u64 ehea_h_alloc_resource_cq(const u64 adapter_handle, - struct ehea_cq_attr *cq_attr, - u64 *cq_handle, struct h_epas *epas); - -u64 ehea_h_alloc_resource_qp(const u64 adapter_handle, - struct ehea_qp_init_attr *init_attr, - const u32 pd, - u64 *qp_handle, struct h_epas *h_epas); - -#define H_REG_RPAGE_PAGE_SIZE EHEA_BMASK_IBM(48, 55) -#define H_REG_RPAGE_QT EHEA_BMASK_IBM(62, 63) - -u64 ehea_h_register_rpage(const u64 adapter_handle, - const u8 pagesize, - const u8 queue_type, - const u64 resource_handle, - const u64 log_pageaddr, u64 count); - -#define H_DISABLE_GET_EHEA_WQE_P 1 -#define H_DISABLE_GET_SQ_WQE_P 2 -#define H_DISABLE_GET_RQC 3 - -u64 ehea_h_disable_and_get_hea(const u64 adapter_handle, const u64 qp_handle); - -#define FORCE_FREE 1 -#define NORMAL_FREE 0 - -u64 ehea_h_free_resource(const u64 adapter_handle, const u64 res_handle, - u64 force_bit); - -u64 ehea_h_alloc_resource_mr(const u64 adapter_handle, const u64 vaddr, - const u64 length, const u32 access_ctrl, - const u32 pd, u64 *mr_handle, u32 *lkey); - -u64 ehea_h_register_rpage_mr(const u64 adapter_handle, const u64 mr_handle, - const u8 pagesize, const u8 queue_type, - const u64 log_pageaddr, const u64 count); - -u64 ehea_h_register_smr(const u64 adapter_handle, const u64 orig_mr_handle, - const u64 vaddr_in, const u32 access_ctrl, const u32 pd, - struct ehea_mr *mr); - -u64 ehea_h_query_ehea(const u64 adapter_handle, void *cb_addr); - -/* output param R5 */ -#define H_MEHEAPORT_CAT EHEA_BMASK_IBM(40, 47) -#define H_MEHEAPORT_PN EHEA_BMASK_IBM(48, 63) - -u64 ehea_h_query_ehea_port(const u64 adapter_handle, const u16 port_num, - const u8 cb_cat, const u64 select_mask, - void *cb_addr); - -u64 ehea_h_modify_ehea_port(const u64 adapter_handle, const u16 port_num, - const u8 cb_cat, const u64 select_mask, - void *cb_addr); - -#define H_REGBCMC_PN EHEA_BMASK_IBM(48, 63) -#define H_REGBCMC_REGTYPE EHEA_BMASK_IBM(60, 63) -#define H_REGBCMC_MACADDR EHEA_BMASK_IBM(16, 63) -#define H_REGBCMC_VLANID EHEA_BMASK_IBM(52, 63) - -u64 ehea_h_reg_dereg_bcmc(const u64 adapter_handle, const u16 port_num, - const u8 reg_type, const u64 mc_mac_addr, - const u16 vlan_id, const u32 hcall_id); - -u64 ehea_h_reset_events(const u64 adapter_handle, const u64 neq_handle, - const u64 event_mask); - -u64 ehea_h_error_data(const u64 adapter_handle, const u64 ressource_handle, - void *rblock); - -#endif /* __EHEA_PHYP_H__ */ diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c b/drivers/net/ethernet/ibm/ehea/ehea_qmr.c deleted file mode 100644 index 60629a0032b2..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.c +++ /dev/null @@ -1,999 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.c - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/mm.h> -#include <linux/slab.h> -#include "ehea.h" -#include "ehea_phyp.h" -#include "ehea_qmr.h" - -static struct ehea_bmap *ehea_bmap; - -static void *hw_qpageit_get_inc(struct hw_queue *queue) -{ - void *retvalue = hw_qeit_get(queue); - - queue->current_q_offset += queue->pagesize; - if (queue->current_q_offset > queue->queue_length) { - queue->current_q_offset -= queue->pagesize; - retvalue = NULL; - } else if (((u64) retvalue) & (EHEA_PAGESIZE-1)) { - pr_err("not on pageboundary\n"); - retvalue = NULL; - } - return retvalue; -} - -static int hw_queue_ctor(struct hw_queue *queue, const u32 nr_of_pages, - const u32 pagesize, const u32 qe_size) -{ - int pages_per_kpage = PAGE_SIZE / pagesize; - int i, k; - - if ((pagesize > PAGE_SIZE) || (!pages_per_kpage)) { - pr_err("pagesize conflict! kernel pagesize=%d, ehea pagesize=%d\n", - (int)PAGE_SIZE, (int)pagesize); - return -EINVAL; - } - - queue->queue_length = nr_of_pages * pagesize; - queue->queue_pages = kmalloc_array(nr_of_pages, sizeof(void *), - GFP_KERNEL); - if (!queue->queue_pages) - return -ENOMEM; - - /* - * allocate pages for queue: - * outer loop allocates whole kernel pages (page aligned) and - * inner loop divides a kernel page into smaller hea queue pages - */ - i = 0; - while (i < nr_of_pages) { - u8 *kpage = (u8 *)get_zeroed_page(GFP_KERNEL); - if (!kpage) - goto out_nomem; - for (k = 0; k < pages_per_kpage && i < nr_of_pages; k++) { - (queue->queue_pages)[i] = (struct ehea_page *)kpage; - kpage += pagesize; - i++; - } - } - - queue->current_q_offset = 0; - queue->qe_size = qe_size; - queue->pagesize = pagesize; - queue->toggle_state = 1; - - return 0; -out_nomem: - for (i = 0; i < nr_of_pages; i += pages_per_kpage) { - if (!(queue->queue_pages)[i]) - break; - free_page((unsigned long)(queue->queue_pages)[i]); - } - return -ENOMEM; -} - -static void hw_queue_dtor(struct hw_queue *queue) -{ - int pages_per_kpage; - int i, nr_pages; - - if (!queue || !queue->queue_pages) - return; - - pages_per_kpage = PAGE_SIZE / queue->pagesize; - - nr_pages = queue->queue_length / queue->pagesize; - - for (i = 0; i < nr_pages; i += pages_per_kpage) - free_page((unsigned long)(queue->queue_pages)[i]); - - kfree(queue->queue_pages); -} - -struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter, - int nr_of_cqe, u64 eq_handle, u32 cq_token) -{ - struct ehea_cq *cq; - u64 hret, rpage; - u32 counter; - int ret; - void *vpage; - - cq = kzalloc_obj(*cq); - if (!cq) - goto out_nomem; - - cq->attr.max_nr_of_cqes = nr_of_cqe; - cq->attr.cq_token = cq_token; - cq->attr.eq_handle = eq_handle; - - cq->adapter = adapter; - - hret = ehea_h_alloc_resource_cq(adapter->handle, &cq->attr, - &cq->fw_handle, &cq->epas); - if (hret != H_SUCCESS) { - pr_err("alloc_resource_cq failed\n"); - goto out_freemem; - } - - ret = hw_queue_ctor(&cq->hw_queue, cq->attr.nr_pages, - EHEA_PAGESIZE, sizeof(struct ehea_cqe)); - if (ret) - goto out_freeres; - - for (counter = 0; counter < cq->attr.nr_pages; counter++) { - vpage = hw_qpageit_get_inc(&cq->hw_queue); - if (!vpage) { - pr_err("hw_qpageit_get_inc failed\n"); - goto out_kill_hwq; - } - - rpage = __pa(vpage); - hret = ehea_h_register_rpage(adapter->handle, - 0, EHEA_CQ_REGISTER_ORIG, - cq->fw_handle, rpage, 1); - if (hret < H_SUCCESS) { - pr_err("register_rpage_cq failed ehea_cq=%p hret=%llx counter=%i act_pages=%i\n", - cq, hret, counter, cq->attr.nr_pages); - goto out_kill_hwq; - } - - if (counter == (cq->attr.nr_pages - 1)) { - vpage = hw_qpageit_get_inc(&cq->hw_queue); - - if ((hret != H_SUCCESS) || (vpage)) { - pr_err("registration of pages not complete hret=%llx\n", - hret); - goto out_kill_hwq; - } - } else { - if (hret != H_PAGE_REGISTERED) { - pr_err("CQ: registration of page failed hret=%llx\n", - hret); - goto out_kill_hwq; - } - } - } - - hw_qeit_reset(&cq->hw_queue); - ehea_reset_cq_ep(cq); - ehea_reset_cq_n1(cq); - - return cq; - -out_kill_hwq: - hw_queue_dtor(&cq->hw_queue); - -out_freeres: - ehea_h_free_resource(adapter->handle, cq->fw_handle, FORCE_FREE); - -out_freemem: - kfree(cq); - -out_nomem: - return NULL; -} - -static u64 ehea_destroy_cq_res(struct ehea_cq *cq, u64 force) -{ - u64 hret; - u64 adapter_handle = cq->adapter->handle; - - /* deregister all previous registered pages */ - hret = ehea_h_free_resource(adapter_handle, cq->fw_handle, force); - if (hret != H_SUCCESS) - return hret; - - hw_queue_dtor(&cq->hw_queue); - kfree(cq); - - return hret; -} - -int ehea_destroy_cq(struct ehea_cq *cq) -{ - u64 hret, aer, aerr; - if (!cq) - return 0; - - hcp_epas_dtor(&cq->epas); - hret = ehea_destroy_cq_res(cq, NORMAL_FREE); - if (hret == H_R_STATE) { - ehea_error_data(cq->adapter, cq->fw_handle, &aer, &aerr); - hret = ehea_destroy_cq_res(cq, FORCE_FREE); - } - - if (hret != H_SUCCESS) { - pr_err("destroy CQ failed\n"); - return -EIO; - } - - return 0; -} - -struct ehea_eq *ehea_create_eq(struct ehea_adapter *adapter, - const enum ehea_eq_type type, - const u32 max_nr_of_eqes, const u8 eqe_gen) -{ - int ret, i; - u64 hret, rpage; - void *vpage; - struct ehea_eq *eq; - - eq = kzalloc_obj(*eq); - if (!eq) - return NULL; - - eq->adapter = adapter; - eq->attr.type = type; - eq->attr.max_nr_of_eqes = max_nr_of_eqes; - eq->attr.eqe_gen = eqe_gen; - spin_lock_init(&eq->spinlock); - - hret = ehea_h_alloc_resource_eq(adapter->handle, - &eq->attr, &eq->fw_handle); - if (hret != H_SUCCESS) { - pr_err("alloc_resource_eq failed\n"); - goto out_freemem; - } - - ret = hw_queue_ctor(&eq->hw_queue, eq->attr.nr_pages, - EHEA_PAGESIZE, sizeof(struct ehea_eqe)); - if (ret) { - pr_err("can't allocate eq pages\n"); - goto out_freeres; - } - - for (i = 0; i < eq->attr.nr_pages; i++) { - vpage = hw_qpageit_get_inc(&eq->hw_queue); - if (!vpage) { - pr_err("hw_qpageit_get_inc failed\n"); - hret = H_RESOURCE; - goto out_kill_hwq; - } - - rpage = __pa(vpage); - - hret = ehea_h_register_rpage(adapter->handle, 0, - EHEA_EQ_REGISTER_ORIG, - eq->fw_handle, rpage, 1); - - if (i == (eq->attr.nr_pages - 1)) { - /* last page */ - vpage = hw_qpageit_get_inc(&eq->hw_queue); - if ((hret != H_SUCCESS) || (vpage)) - goto out_kill_hwq; - - } else { - if (hret != H_PAGE_REGISTERED) - goto out_kill_hwq; - - } - } - - hw_qeit_reset(&eq->hw_queue); - return eq; - -out_kill_hwq: - hw_queue_dtor(&eq->hw_queue); - -out_freeres: - ehea_h_free_resource(adapter->handle, eq->fw_handle, FORCE_FREE); - -out_freemem: - kfree(eq); - return NULL; -} - -struct ehea_eqe *ehea_poll_eq(struct ehea_eq *eq) -{ - struct ehea_eqe *eqe; - unsigned long flags; - - spin_lock_irqsave(&eq->spinlock, flags); - eqe = hw_eqit_eq_get_inc_valid(&eq->hw_queue); - spin_unlock_irqrestore(&eq->spinlock, flags); - - return eqe; -} - -static u64 ehea_destroy_eq_res(struct ehea_eq *eq, u64 force) -{ - u64 hret; - unsigned long flags; - - spin_lock_irqsave(&eq->spinlock, flags); - - hret = ehea_h_free_resource(eq->adapter->handle, eq->fw_handle, force); - spin_unlock_irqrestore(&eq->spinlock, flags); - - if (hret != H_SUCCESS) - return hret; - - hw_queue_dtor(&eq->hw_queue); - kfree(eq); - - return hret; -} - -int ehea_destroy_eq(struct ehea_eq *eq) -{ - u64 hret, aer, aerr; - if (!eq) - return 0; - - hcp_epas_dtor(&eq->epas); - - hret = ehea_destroy_eq_res(eq, NORMAL_FREE); - if (hret == H_R_STATE) { - ehea_error_data(eq->adapter, eq->fw_handle, &aer, &aerr); - hret = ehea_destroy_eq_res(eq, FORCE_FREE); - } - - if (hret != H_SUCCESS) { - pr_err("destroy EQ failed\n"); - return -EIO; - } - - return 0; -} - -/* allocates memory for a queue and registers pages in phyp */ -static int ehea_qp_alloc_register(struct ehea_qp *qp, struct hw_queue *hw_queue, - int nr_pages, int wqe_size, int act_nr_sges, - struct ehea_adapter *adapter, int h_call_q_selector) -{ - u64 hret, rpage; - int ret, cnt; - void *vpage; - - ret = hw_queue_ctor(hw_queue, nr_pages, EHEA_PAGESIZE, wqe_size); - if (ret) - return ret; - - for (cnt = 0; cnt < nr_pages; cnt++) { - vpage = hw_qpageit_get_inc(hw_queue); - if (!vpage) { - pr_err("hw_qpageit_get_inc failed\n"); - goto out_kill_hwq; - } - rpage = __pa(vpage); - hret = ehea_h_register_rpage(adapter->handle, - 0, h_call_q_selector, - qp->fw_handle, rpage, 1); - if (hret < H_SUCCESS) { - pr_err("register_rpage_qp failed\n"); - goto out_kill_hwq; - } - } - hw_qeit_reset(hw_queue); - return 0; - -out_kill_hwq: - hw_queue_dtor(hw_queue); - return -EIO; -} - -static inline u32 map_wqe_size(u8 wqe_enc_size) -{ - return 128 << wqe_enc_size; -} - -struct ehea_qp *ehea_create_qp(struct ehea_adapter *adapter, - u32 pd, struct ehea_qp_init_attr *init_attr) -{ - int ret; - u64 hret; - struct ehea_qp *qp; - u32 wqe_size_in_bytes_sq, wqe_size_in_bytes_rq1; - u32 wqe_size_in_bytes_rq2, wqe_size_in_bytes_rq3; - - - qp = kzalloc_obj(*qp); - if (!qp) - return NULL; - - qp->adapter = adapter; - - hret = ehea_h_alloc_resource_qp(adapter->handle, init_attr, pd, - &qp->fw_handle, &qp->epas); - if (hret != H_SUCCESS) { - pr_err("ehea_h_alloc_resource_qp failed\n"); - goto out_freemem; - } - - wqe_size_in_bytes_sq = map_wqe_size(init_attr->act_wqe_size_enc_sq); - wqe_size_in_bytes_rq1 = map_wqe_size(init_attr->act_wqe_size_enc_rq1); - wqe_size_in_bytes_rq2 = map_wqe_size(init_attr->act_wqe_size_enc_rq2); - wqe_size_in_bytes_rq3 = map_wqe_size(init_attr->act_wqe_size_enc_rq3); - - ret = ehea_qp_alloc_register(qp, &qp->hw_squeue, init_attr->nr_sq_pages, - wqe_size_in_bytes_sq, - init_attr->act_wqe_size_enc_sq, adapter, - 0); - if (ret) { - pr_err("can't register for sq ret=%x\n", ret); - goto out_freeres; - } - - ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue1, - init_attr->nr_rq1_pages, - wqe_size_in_bytes_rq1, - init_attr->act_wqe_size_enc_rq1, - adapter, 1); - if (ret) { - pr_err("can't register for rq1 ret=%x\n", ret); - goto out_kill_hwsq; - } - - if (init_attr->rq_count > 1) { - ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue2, - init_attr->nr_rq2_pages, - wqe_size_in_bytes_rq2, - init_attr->act_wqe_size_enc_rq2, - adapter, 2); - if (ret) { - pr_err("can't register for rq2 ret=%x\n", ret); - goto out_kill_hwr1q; - } - } - - if (init_attr->rq_count > 2) { - ret = ehea_qp_alloc_register(qp, &qp->hw_rqueue3, - init_attr->nr_rq3_pages, - wqe_size_in_bytes_rq3, - init_attr->act_wqe_size_enc_rq3, - adapter, 3); - if (ret) { - pr_err("can't register for rq3 ret=%x\n", ret); - goto out_kill_hwr2q; - } - } - - qp->init_attr = *init_attr; - - return qp; - -out_kill_hwr2q: - hw_queue_dtor(&qp->hw_rqueue2); - -out_kill_hwr1q: - hw_queue_dtor(&qp->hw_rqueue1); - -out_kill_hwsq: - hw_queue_dtor(&qp->hw_squeue); - -out_freeres: - ehea_h_disable_and_get_hea(adapter->handle, qp->fw_handle); - ehea_h_free_resource(adapter->handle, qp->fw_handle, FORCE_FREE); - -out_freemem: - kfree(qp); - return NULL; -} - -static u64 ehea_destroy_qp_res(struct ehea_qp *qp, u64 force) -{ - u64 hret; - struct ehea_qp_init_attr *qp_attr = &qp->init_attr; - - - ehea_h_disable_and_get_hea(qp->adapter->handle, qp->fw_handle); - hret = ehea_h_free_resource(qp->adapter->handle, qp->fw_handle, force); - if (hret != H_SUCCESS) - return hret; - - hw_queue_dtor(&qp->hw_squeue); - hw_queue_dtor(&qp->hw_rqueue1); - - if (qp_attr->rq_count > 1) - hw_queue_dtor(&qp->hw_rqueue2); - if (qp_attr->rq_count > 2) - hw_queue_dtor(&qp->hw_rqueue3); - kfree(qp); - - return hret; -} - -int ehea_destroy_qp(struct ehea_qp *qp) -{ - u64 hret, aer, aerr; - if (!qp) - return 0; - - hcp_epas_dtor(&qp->epas); - - hret = ehea_destroy_qp_res(qp, NORMAL_FREE); - if (hret == H_R_STATE) { - ehea_error_data(qp->adapter, qp->fw_handle, &aer, &aerr); - hret = ehea_destroy_qp_res(qp, FORCE_FREE); - } - - if (hret != H_SUCCESS) { - pr_err("destroy QP failed\n"); - return -EIO; - } - - return 0; -} - -static inline int ehea_calc_index(unsigned long i, unsigned long s) -{ - return (i >> s) & EHEA_INDEX_MASK; -} - -static inline int ehea_init_top_bmap(struct ehea_top_bmap *ehea_top_bmap, - int dir) -{ - if (!ehea_top_bmap->dir[dir]) { - ehea_top_bmap->dir[dir] = - kzalloc_obj(struct ehea_dir_bmap); - if (!ehea_top_bmap->dir[dir]) - return -ENOMEM; - } - return 0; -} - -static inline int ehea_init_bmap(struct ehea_bmap *ehea_bmap, int top, int dir) -{ - if (!ehea_bmap->top[top]) { - ehea_bmap->top[top] = - kzalloc_obj(struct ehea_top_bmap); - if (!ehea_bmap->top[top]) - return -ENOMEM; - } - return ehea_init_top_bmap(ehea_bmap->top[top], dir); -} - -static DEFINE_MUTEX(ehea_busmap_mutex); -static unsigned long ehea_mr_len; - -#define EHEA_BUSMAP_ADD_SECT 1 -#define EHEA_BUSMAP_REM_SECT 0 - -static void ehea_rebuild_busmap(void) -{ - u64 vaddr = EHEA_BUSMAP_START; - int top, dir, idx; - - for (top = 0; top < EHEA_MAP_ENTRIES; top++) { - struct ehea_top_bmap *ehea_top; - int valid_dir_entries = 0; - - if (!ehea_bmap->top[top]) - continue; - ehea_top = ehea_bmap->top[top]; - for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) { - struct ehea_dir_bmap *ehea_dir; - int valid_entries = 0; - - if (!ehea_top->dir[dir]) - continue; - valid_dir_entries++; - ehea_dir = ehea_top->dir[dir]; - for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) { - if (!ehea_dir->ent[idx]) - continue; - valid_entries++; - ehea_dir->ent[idx] = vaddr; - vaddr += EHEA_SECTSIZE; - } - if (!valid_entries) { - ehea_top->dir[dir] = NULL; - kfree(ehea_dir); - } - } - if (!valid_dir_entries) { - ehea_bmap->top[top] = NULL; - kfree(ehea_top); - } - } -} - -static int ehea_update_busmap(unsigned long pfn, unsigned long nr_pages, int add) -{ - unsigned long i, start_section, end_section; - - if (!nr_pages) - return 0; - - if (!ehea_bmap) { - ehea_bmap = kzalloc_obj(struct ehea_bmap); - if (!ehea_bmap) - return -ENOMEM; - } - - start_section = (pfn * PAGE_SIZE) / EHEA_SECTSIZE; - end_section = start_section + ((nr_pages * PAGE_SIZE) / EHEA_SECTSIZE); - /* Mark entries as valid or invalid only; address is assigned later */ - for (i = start_section; i < end_section; i++) { - u64 flag; - int top = ehea_calc_index(i, EHEA_TOP_INDEX_SHIFT); - int dir = ehea_calc_index(i, EHEA_DIR_INDEX_SHIFT); - int idx = i & EHEA_INDEX_MASK; - - if (add) { - int ret = ehea_init_bmap(ehea_bmap, top, dir); - if (ret) - return ret; - flag = 1; /* valid */ - ehea_mr_len += EHEA_SECTSIZE; - } else { - if (!ehea_bmap->top[top]) - continue; - if (!ehea_bmap->top[top]->dir[dir]) - continue; - flag = 0; /* invalid */ - ehea_mr_len -= EHEA_SECTSIZE; - } - - ehea_bmap->top[top]->dir[dir]->ent[idx] = flag; - } - ehea_rebuild_busmap(); /* Assign contiguous addresses for mr */ - return 0; -} - -int ehea_add_sect_bmap(unsigned long pfn, unsigned long nr_pages) -{ - int ret; - - mutex_lock(&ehea_busmap_mutex); - ret = ehea_update_busmap(pfn, nr_pages, EHEA_BUSMAP_ADD_SECT); - mutex_unlock(&ehea_busmap_mutex); - return ret; -} - -int ehea_rem_sect_bmap(unsigned long pfn, unsigned long nr_pages) -{ - int ret; - - mutex_lock(&ehea_busmap_mutex); - ret = ehea_update_busmap(pfn, nr_pages, EHEA_BUSMAP_REM_SECT); - mutex_unlock(&ehea_busmap_mutex); - return ret; -} - -static int ehea_is_hugepage(unsigned long pfn) -{ - if (pfn & EHEA_HUGEPAGE_PFN_MASK) - return 0; - - if (page_shift(pfn_to_page(pfn)) != EHEA_HUGEPAGESHIFT) - return 0; - - return 1; -} - -static int ehea_create_busmap_callback(unsigned long initial_pfn, - unsigned long total_nr_pages, void *arg) -{ - int ret; - unsigned long pfn, start_pfn, end_pfn, nr_pages; - - if ((total_nr_pages * PAGE_SIZE) < EHEA_HUGEPAGE_SIZE) - return ehea_update_busmap(initial_pfn, total_nr_pages, - EHEA_BUSMAP_ADD_SECT); - - /* Given chunk is >= 16GB -> check for hugepages */ - start_pfn = initial_pfn; - end_pfn = initial_pfn + total_nr_pages; - pfn = start_pfn; - - while (pfn < end_pfn) { - if (ehea_is_hugepage(pfn)) { - /* Add mem found in front of the hugepage */ - nr_pages = pfn - start_pfn; - ret = ehea_update_busmap(start_pfn, nr_pages, - EHEA_BUSMAP_ADD_SECT); - if (ret) - return ret; - - /* Skip the hugepage */ - pfn += (EHEA_HUGEPAGE_SIZE / PAGE_SIZE); - start_pfn = pfn; - } else - pfn += (EHEA_SECTSIZE / PAGE_SIZE); - } - - /* Add mem found behind the hugepage(s) */ - nr_pages = pfn - start_pfn; - return ehea_update_busmap(start_pfn, nr_pages, EHEA_BUSMAP_ADD_SECT); -} - -int ehea_create_busmap(void) -{ - int ret; - - mutex_lock(&ehea_busmap_mutex); - ehea_mr_len = 0; - ret = walk_system_ram_range(0, 1ULL << MAX_PHYSMEM_BITS, NULL, - ehea_create_busmap_callback); - mutex_unlock(&ehea_busmap_mutex); - return ret; -} - -void ehea_destroy_busmap(void) -{ - int top, dir; - mutex_lock(&ehea_busmap_mutex); - if (!ehea_bmap) - goto out_destroy; - - for (top = 0; top < EHEA_MAP_ENTRIES; top++) { - if (!ehea_bmap->top[top]) - continue; - - for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) { - if (!ehea_bmap->top[top]->dir[dir]) - continue; - - kfree(ehea_bmap->top[top]->dir[dir]); - } - - kfree(ehea_bmap->top[top]); - } - - kfree(ehea_bmap); - ehea_bmap = NULL; -out_destroy: - mutex_unlock(&ehea_busmap_mutex); -} - -u64 ehea_map_vaddr(void *caddr) -{ - int top, dir, idx; - unsigned long index, offset; - - if (!ehea_bmap) - return EHEA_INVAL_ADDR; - - index = __pa(caddr) >> SECTION_SIZE_BITS; - top = (index >> EHEA_TOP_INDEX_SHIFT) & EHEA_INDEX_MASK; - if (!ehea_bmap->top[top]) - return EHEA_INVAL_ADDR; - - dir = (index >> EHEA_DIR_INDEX_SHIFT) & EHEA_INDEX_MASK; - if (!ehea_bmap->top[top]->dir[dir]) - return EHEA_INVAL_ADDR; - - idx = index & EHEA_INDEX_MASK; - if (!ehea_bmap->top[top]->dir[dir]->ent[idx]) - return EHEA_INVAL_ADDR; - - offset = (unsigned long)caddr & (EHEA_SECTSIZE - 1); - return ehea_bmap->top[top]->dir[dir]->ent[idx] | offset; -} - -static inline void *ehea_calc_sectbase(int top, int dir, int idx) -{ - unsigned long ret = idx; - ret |= dir << EHEA_DIR_INDEX_SHIFT; - ret |= top << EHEA_TOP_INDEX_SHIFT; - return __va(ret << SECTION_SIZE_BITS); -} - -static u64 ehea_reg_mr_section(int top, int dir, int idx, u64 *pt, - struct ehea_adapter *adapter, - struct ehea_mr *mr) -{ - void *pg; - u64 j, m, hret; - unsigned long k = 0; - u64 pt_abs = __pa(pt); - - void *sectbase = ehea_calc_sectbase(top, dir, idx); - - for (j = 0; j < (EHEA_PAGES_PER_SECTION / EHEA_MAX_RPAGE); j++) { - - for (m = 0; m < EHEA_MAX_RPAGE; m++) { - pg = sectbase + ((k++) * EHEA_PAGESIZE); - pt[m] = __pa(pg); - } - hret = ehea_h_register_rpage_mr(adapter->handle, mr->handle, 0, - 0, pt_abs, EHEA_MAX_RPAGE); - - if ((hret != H_SUCCESS) && - (hret != H_PAGE_REGISTERED)) { - ehea_h_free_resource(adapter->handle, mr->handle, - FORCE_FREE); - pr_err("register_rpage_mr failed\n"); - return hret; - } - } - return hret; -} - -static u64 ehea_reg_mr_sections(int top, int dir, u64 *pt, - struct ehea_adapter *adapter, - struct ehea_mr *mr) -{ - u64 hret = H_SUCCESS; - int idx; - - for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) { - if (!ehea_bmap->top[top]->dir[dir]->ent[idx]) - continue; - - hret = ehea_reg_mr_section(top, dir, idx, pt, adapter, mr); - if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED)) - return hret; - } - return hret; -} - -static u64 ehea_reg_mr_dir_sections(int top, u64 *pt, - struct ehea_adapter *adapter, - struct ehea_mr *mr) -{ - u64 hret = H_SUCCESS; - int dir; - - for (dir = 0; dir < EHEA_MAP_ENTRIES; dir++) { - if (!ehea_bmap->top[top]->dir[dir]) - continue; - - hret = ehea_reg_mr_sections(top, dir, pt, adapter, mr); - if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED)) - return hret; - } - return hret; -} - -int ehea_reg_kernel_mr(struct ehea_adapter *adapter, struct ehea_mr *mr) -{ - int ret; - u64 *pt; - u64 hret; - u32 acc_ctrl = EHEA_MR_ACC_CTRL; - - unsigned long top; - - pt = (void *)get_zeroed_page(GFP_KERNEL); - if (!pt) { - pr_err("no mem\n"); - ret = -ENOMEM; - goto out; - } - - hret = ehea_h_alloc_resource_mr(adapter->handle, EHEA_BUSMAP_START, - ehea_mr_len, acc_ctrl, adapter->pd, - &mr->handle, &mr->lkey); - - if (hret != H_SUCCESS) { - pr_err("alloc_resource_mr failed\n"); - ret = -EIO; - goto out; - } - - if (!ehea_bmap) { - ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE); - pr_err("no busmap available\n"); - ret = -EIO; - goto out; - } - - for (top = 0; top < EHEA_MAP_ENTRIES; top++) { - if (!ehea_bmap->top[top]) - continue; - - hret = ehea_reg_mr_dir_sections(top, pt, adapter, mr); - if((hret != H_PAGE_REGISTERED) && (hret != H_SUCCESS)) - break; - } - - if (hret != H_SUCCESS) { - ehea_h_free_resource(adapter->handle, mr->handle, FORCE_FREE); - pr_err("registering mr failed\n"); - ret = -EIO; - goto out; - } - - mr->vaddr = EHEA_BUSMAP_START; - mr->adapter = adapter; - ret = 0; -out: - free_page((unsigned long)pt); - return ret; -} - -int ehea_rem_mr(struct ehea_mr *mr) -{ - u64 hret; - - if (!mr || !mr->adapter) - return -EINVAL; - - hret = ehea_h_free_resource(mr->adapter->handle, mr->handle, - FORCE_FREE); - if (hret != H_SUCCESS) { - pr_err("destroy MR failed\n"); - return -EIO; - } - - return 0; -} - -int ehea_gen_smr(struct ehea_adapter *adapter, struct ehea_mr *old_mr, - struct ehea_mr *shared_mr) -{ - u64 hret; - - hret = ehea_h_register_smr(adapter->handle, old_mr->handle, - old_mr->vaddr, EHEA_MR_ACC_CTRL, - adapter->pd, shared_mr); - if (hret != H_SUCCESS) - return -EIO; - - shared_mr->adapter = adapter; - - return 0; -} - -static void print_error_data(u64 *data) -{ - int length; - u64 type = EHEA_BMASK_GET(ERROR_DATA_TYPE, data[2]); - u64 resource = data[1]; - - length = EHEA_BMASK_GET(ERROR_DATA_LENGTH, data[0]); - - if (length > EHEA_PAGESIZE) - length = EHEA_PAGESIZE; - - if (type == EHEA_AER_RESTYPE_QP) - pr_err("QP (resource=%llX) state: AER=0x%llX, AERR=0x%llX, port=%llX\n", - resource, data[6], data[12], data[22]); - else if (type == EHEA_AER_RESTYPE_CQ) - pr_err("CQ (resource=%llX) state: AER=0x%llX\n", - resource, data[6]); - else if (type == EHEA_AER_RESTYPE_EQ) - pr_err("EQ (resource=%llX) state: AER=0x%llX\n", - resource, data[6]); - - ehea_dump(data, length, "error data"); -} - -u64 ehea_error_data(struct ehea_adapter *adapter, u64 res_handle, - u64 *aer, u64 *aerr) -{ - unsigned long ret; - u64 *rblock; - u64 type = 0; - - rblock = (void *)get_zeroed_page(GFP_KERNEL); - if (!rblock) { - pr_err("Cannot allocate rblock memory\n"); - goto out; - } - - ret = ehea_h_error_data(adapter->handle, res_handle, rblock); - - if (ret == H_SUCCESS) { - type = EHEA_BMASK_GET(ERROR_DATA_TYPE, rblock[2]); - *aer = rblock[6]; - *aerr = rblock[12]; - print_error_data(rblock); - } else if (ret == H_R_STATE) { - pr_err("No error data available: %llX\n", res_handle); - } else - pr_err("Error data could not be fetched: %llX\n", res_handle); - - free_page((unsigned long)rblock); -out: - return type; -} diff --git a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h b/drivers/net/ethernet/ibm/ehea/ehea_qmr.h deleted file mode 100644 index 7c7cccd820f7..000000000000 --- a/drivers/net/ethernet/ibm/ehea/ehea_qmr.h +++ /dev/null @@ -1,390 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * linux/drivers/net/ethernet/ibm/ehea/ehea_qmr.h - * - * eHEA ethernet device driver for IBM eServer System p - * - * (C) Copyright IBM Corp. 2006 - * - * Authors: - * Christoph Raisch <raisch@de.ibm.com> - * Jan-Bernd Themann <themann@de.ibm.com> - * Thomas Klein <tklein@de.ibm.com> - */ - -#ifndef __EHEA_QMR_H__ -#define __EHEA_QMR_H__ - -#include <linux/prefetch.h> -#include "ehea.h" -#include "ehea_hw.h" - -/* - * page size of ehea hardware queues - */ - -#define EHEA_PAGESHIFT 12 -#define EHEA_PAGESIZE (1UL << EHEA_PAGESHIFT) -#define EHEA_SECTSIZE (1UL << 24) -#define EHEA_PAGES_PER_SECTION (EHEA_SECTSIZE >> EHEA_PAGESHIFT) -#define EHEA_HUGEPAGESHIFT 34 -#define EHEA_HUGEPAGE_SIZE (1UL << EHEA_HUGEPAGESHIFT) -#define EHEA_HUGEPAGE_PFN_MASK ((EHEA_HUGEPAGE_SIZE - 1) >> PAGE_SHIFT) - -#if ((1UL << SECTION_SIZE_BITS) < EHEA_SECTSIZE) -#error eHEA module cannot work if kernel sectionsize < ehea sectionsize -#endif - -/* Some abbreviations used here: - * - * WQE - Work Queue Entry - * SWQE - Send Work Queue Entry - * RWQE - Receive Work Queue Entry - * CQE - Completion Queue Entry - * EQE - Event Queue Entry - * MR - Memory Region - */ - -/* Use of WR_ID field for EHEA */ -#define EHEA_WR_ID_COUNT EHEA_BMASK_IBM(0, 19) -#define EHEA_WR_ID_TYPE EHEA_BMASK_IBM(20, 23) -#define EHEA_SWQE2_TYPE 0x1 -#define EHEA_SWQE3_TYPE 0x2 -#define EHEA_RWQE2_TYPE 0x3 -#define EHEA_RWQE3_TYPE 0x4 -#define EHEA_WR_ID_INDEX EHEA_BMASK_IBM(24, 47) -#define EHEA_WR_ID_REFILL EHEA_BMASK_IBM(48, 63) - -struct ehea_vsgentry { - u64 vaddr; - u32 l_key; - u32 len; -}; - -/* maximum number of sg entries allowed in a WQE */ -#define EHEA_MAX_WQE_SG_ENTRIES 252 -#define SWQE2_MAX_IMM (0xD0 - 0x30) -#define SWQE3_MAX_IMM 224 - -/* tx control flags for swqe */ -#define EHEA_SWQE_CRC 0x8000 -#define EHEA_SWQE_IP_CHECKSUM 0x4000 -#define EHEA_SWQE_TCP_CHECKSUM 0x2000 -#define EHEA_SWQE_TSO 0x1000 -#define EHEA_SWQE_SIGNALLED_COMPLETION 0x0800 -#define EHEA_SWQE_VLAN_INSERT 0x0400 -#define EHEA_SWQE_IMM_DATA_PRESENT 0x0200 -#define EHEA_SWQE_DESCRIPTORS_PRESENT 0x0100 -#define EHEA_SWQE_WRAP_CTL_REC 0x0080 -#define EHEA_SWQE_WRAP_CTL_FORCE 0x0040 -#define EHEA_SWQE_BIND 0x0020 -#define EHEA_SWQE_PURGE 0x0010 - -/* sizeof(struct ehea_swqe) less the union */ -#define SWQE_HEADER_SIZE 32 - -struct ehea_swqe { - u64 wr_id; - u16 tx_control; - u16 vlan_tag; - u8 reserved1; - u8 ip_start; - u8 ip_end; - u8 immediate_data_length; - u8 tcp_offset; - u8 reserved2; - u16 reserved2b; - u8 wrap_tag; - u8 descriptors; /* number of valid descriptors in WQE */ - u16 reserved3; - u16 reserved4; - u16 mss; - u32 reserved5; - union { - /* Send WQE Format 1 */ - struct { - struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES]; - } no_immediate_data; - - /* Send WQE Format 2 */ - struct { - struct ehea_vsgentry sg_entry; - /* 0x30 */ - u8 immediate_data[SWQE2_MAX_IMM]; - /* 0xd0 */ - struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES-1]; - } immdata_desc __packed; - - /* Send WQE Format 3 */ - struct { - u8 immediate_data[SWQE3_MAX_IMM]; - } immdata_nodesc; - } u; -}; - -struct ehea_rwqe { - u64 wr_id; /* work request ID */ - u8 reserved1[5]; - u8 data_segments; - u16 reserved2; - u64 reserved3; - u64 reserved4; - struct ehea_vsgentry sg_list[EHEA_MAX_WQE_SG_ENTRIES]; -}; - -#define EHEA_CQE_VLAN_TAG_XTRACT 0x0400 - -#define EHEA_CQE_TYPE_RQ 0x60 -#define EHEA_CQE_STAT_ERR_MASK 0x700F -#define EHEA_CQE_STAT_FAT_ERR_MASK 0xF -#define EHEA_CQE_BLIND_CKSUM 0x8000 -#define EHEA_CQE_STAT_ERR_TCP 0x4000 -#define EHEA_CQE_STAT_ERR_IP 0x2000 -#define EHEA_CQE_STAT_ERR_CRC 0x1000 - -/* Defines which bad send cqe stati lead to a port reset */ -#define EHEA_CQE_STAT_RESET_MASK 0x0002 - -struct ehea_cqe { - u64 wr_id; /* work request ID from WQE */ - u8 type; - u8 valid; - u16 status; - u16 reserved1; - u16 num_bytes_transfered; - u16 vlan_tag; - u16 inet_checksum_value; - u8 reserved2; - u8 header_length; - u16 reserved3; - u16 page_offset; - u16 wqe_count; - u32 qp_token; - u32 timestamp; - u32 reserved4; - u64 reserved5[3]; -}; - -#define EHEA_EQE_VALID EHEA_BMASK_IBM(0, 0) -#define EHEA_EQE_IS_CQE EHEA_BMASK_IBM(1, 1) -#define EHEA_EQE_IDENTIFIER EHEA_BMASK_IBM(2, 7) -#define EHEA_EQE_QP_CQ_NUMBER EHEA_BMASK_IBM(8, 31) -#define EHEA_EQE_QP_TOKEN EHEA_BMASK_IBM(32, 63) -#define EHEA_EQE_CQ_TOKEN EHEA_BMASK_IBM(32, 63) -#define EHEA_EQE_KEY EHEA_BMASK_IBM(32, 63) -#define EHEA_EQE_PORT_NUMBER EHEA_BMASK_IBM(56, 63) -#define EHEA_EQE_EQ_NUMBER EHEA_BMASK_IBM(48, 63) -#define EHEA_EQE_SM_ID EHEA_BMASK_IBM(48, 63) -#define EHEA_EQE_SM_MECH_NUMBER EHEA_BMASK_IBM(48, 55) -#define EHEA_EQE_SM_PORT_NUMBER EHEA_BMASK_IBM(56, 63) - -#define EHEA_AER_RESTYPE_QP 0x8 -#define EHEA_AER_RESTYPE_CQ 0x4 -#define EHEA_AER_RESTYPE_EQ 0x3 - -/* Defines which affiliated errors lead to a port reset */ -#define EHEA_AER_RESET_MASK 0xFFFFFFFFFEFFFFFFULL -#define EHEA_AERR_RESET_MASK 0xFFFFFFFFFFFFFFFFULL - -struct ehea_eqe { - u64 entry; -}; - -#define ERROR_DATA_LENGTH EHEA_BMASK_IBM(52, 63) -#define ERROR_DATA_TYPE EHEA_BMASK_IBM(0, 7) - -static inline void *hw_qeit_calc(struct hw_queue *queue, u64 q_offset) -{ - struct ehea_page *current_page; - - if (q_offset >= queue->queue_length) - q_offset -= queue->queue_length; - current_page = (queue->queue_pages)[q_offset >> EHEA_PAGESHIFT]; - return ¤t_page->entries[q_offset & (EHEA_PAGESIZE - 1)]; -} - -static inline void *hw_qeit_get(struct hw_queue *queue) -{ - return hw_qeit_calc(queue, queue->current_q_offset); -} - -static inline void hw_qeit_inc(struct hw_queue *queue) -{ - queue->current_q_offset += queue->qe_size; - if (queue->current_q_offset >= queue->queue_length) { - queue->current_q_offset = 0; - /* toggle the valid flag */ - queue->toggle_state = (~queue->toggle_state) & 1; - } -} - -static inline void *hw_qeit_get_inc(struct hw_queue *queue) -{ - void *retvalue = hw_qeit_get(queue); - hw_qeit_inc(queue); - return retvalue; -} - -static inline void *hw_qeit_get_inc_valid(struct hw_queue *queue) -{ - struct ehea_cqe *retvalue = hw_qeit_get(queue); - u8 valid = retvalue->valid; - void *pref; - - if ((valid >> 7) == (queue->toggle_state & 1)) { - /* this is a good one */ - hw_qeit_inc(queue); - pref = hw_qeit_calc(queue, queue->current_q_offset); - prefetch(pref); - prefetch(pref + 128); - } else - retvalue = NULL; - return retvalue; -} - -static inline void *hw_qeit_get_valid(struct hw_queue *queue) -{ - struct ehea_cqe *retvalue = hw_qeit_get(queue); - void *pref; - u8 valid; - - pref = hw_qeit_calc(queue, queue->current_q_offset); - prefetch(pref); - prefetch(pref + 128); - prefetch(pref + 256); - valid = retvalue->valid; - if (!((valid >> 7) == (queue->toggle_state & 1))) - retvalue = NULL; - return retvalue; -} - -static inline void *hw_qeit_reset(struct hw_queue *queue) -{ - queue->current_q_offset = 0; - return hw_qeit_get(queue); -} - -static inline void *hw_qeit_eq_get_inc(struct hw_queue *queue) -{ - u64 last_entry_in_q = queue->queue_length - queue->qe_size; - void *retvalue; - - retvalue = hw_qeit_get(queue); - queue->current_q_offset += queue->qe_size; - if (queue->current_q_offset > last_entry_in_q) { - queue->current_q_offset = 0; - queue->toggle_state = (~queue->toggle_state) & 1; - } - return retvalue; -} - -static inline void *hw_eqit_eq_get_inc_valid(struct hw_queue *queue) -{ - void *retvalue = hw_qeit_get(queue); - u32 qe = *(u8 *)retvalue; - if ((qe >> 7) == (queue->toggle_state & 1)) - hw_qeit_eq_get_inc(queue); - else - retvalue = NULL; - return retvalue; -} - -static inline struct ehea_rwqe *ehea_get_next_rwqe(struct ehea_qp *qp, - int rq_nr) -{ - struct hw_queue *queue; - - if (rq_nr == 1) - queue = &qp->hw_rqueue1; - else if (rq_nr == 2) - queue = &qp->hw_rqueue2; - else - queue = &qp->hw_rqueue3; - - return hw_qeit_get_inc(queue); -} - -static inline struct ehea_swqe *ehea_get_swqe(struct ehea_qp *my_qp, - int *wqe_index) -{ - struct hw_queue *queue = &my_qp->hw_squeue; - struct ehea_swqe *wqe_p; - - *wqe_index = (queue->current_q_offset) >> (7 + EHEA_SG_SQ); - wqe_p = hw_qeit_get_inc(&my_qp->hw_squeue); - - return wqe_p; -} - -static inline void ehea_post_swqe(struct ehea_qp *my_qp, struct ehea_swqe *swqe) -{ - iosync(); - ehea_update_sqa(my_qp, 1); -} - -static inline struct ehea_cqe *ehea_poll_rq1(struct ehea_qp *qp, int *wqe_index) -{ - struct hw_queue *queue = &qp->hw_rqueue1; - - *wqe_index = (queue->current_q_offset) >> (7 + EHEA_SG_RQ1); - return hw_qeit_get_valid(queue); -} - -static inline void ehea_inc_cq(struct ehea_cq *cq) -{ - hw_qeit_inc(&cq->hw_queue); -} - -static inline void ehea_inc_rq1(struct ehea_qp *qp) -{ - hw_qeit_inc(&qp->hw_rqueue1); -} - -static inline struct ehea_cqe *ehea_poll_cq(struct ehea_cq *my_cq) -{ - return hw_qeit_get_valid(&my_cq->hw_queue); -} - -#define EHEA_CQ_REGISTER_ORIG 0 -#define EHEA_EQ_REGISTER_ORIG 0 - -enum ehea_eq_type { - EHEA_EQ = 0, /* event queue */ - EHEA_NEQ /* notification event queue */ -}; - -struct ehea_eq *ehea_create_eq(struct ehea_adapter *adapter, - enum ehea_eq_type type, - const u32 length, const u8 eqe_gen); - -int ehea_destroy_eq(struct ehea_eq *eq); - -struct ehea_eqe *ehea_poll_eq(struct ehea_eq *eq); - -struct ehea_cq *ehea_create_cq(struct ehea_adapter *adapter, int cqe, - u64 eq_handle, u32 cq_token); - -int ehea_destroy_cq(struct ehea_cq *cq); - -struct ehea_qp *ehea_create_qp(struct ehea_adapter *adapter, u32 pd, - struct ehea_qp_init_attr *init_attr); - -int ehea_destroy_qp(struct ehea_qp *qp); - -int ehea_reg_kernel_mr(struct ehea_adapter *adapter, struct ehea_mr *mr); - -int ehea_gen_smr(struct ehea_adapter *adapter, struct ehea_mr *old_mr, - struct ehea_mr *shared_mr); - -int ehea_rem_mr(struct ehea_mr *mr); - -u64 ehea_error_data(struct ehea_adapter *adapter, u64 res_handle, - u64 *aer, u64 *aerr); - -int ehea_add_sect_bmap(unsigned long pfn, unsigned long nr_pages); -int ehea_rem_sect_bmap(unsigned long pfn, unsigned long nr_pages); -int ehea_create_busmap(void); -void ehea_destroy_busmap(void); -u64 ehea_map_vaddr(void *caddr); - -#endif /* __EHEA_QMR_H__ */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 744d6585a949..543e566425c1 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5678,6 +5678,24 @@ static int mvneta_probe(struct platform_device *pdev) "use SW buffer management\n"); mvneta_bm_put(pp->bm_priv); pp->bm_priv = NULL; + } else if (!device_link_add(&pdev->dev, + &pp->bm_priv->pdev->dev, + DL_FLAG_AUTOREMOVE_CONSUMER)) { + /* + * Link guarantees BM resumes before mvneta. + * Without it, BM may not be ready when + * mvneta_bm_port_init() runs on resume, + * causing stale buffer addresses and a crash. + * Fall back to SW management to be safe. + */ + dev_warn(&pdev->dev, + "failed to link to BM, use SW buffer management\n"); + mvneta_bm_pool_destroy(pp->bm_priv, + pp->pool_long, 1 << pp->id); + mvneta_bm_pool_destroy(pp->bm_priv, + pp->pool_short, 1 << pp->id); + mvneta_bm_put(pp->bm_priv); + pp->bm_priv = NULL; } } /* Set RX packet offset correction for platforms, whose diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c index 6bb380494919..e0c693c0a910 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.c +++ b/drivers/net/ethernet/marvell/mvneta_bm.c @@ -129,6 +129,7 @@ static int mvneta_bm_pool_create(struct mvneta_bm *priv, if (!IS_ALIGNED((u32)bm_pool->virt_addr, MVNETA_BM_POOL_PTR_ALIGN)) { dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr, bm_pool->phys_addr); + bm_pool->virt_addr = NULL; dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n", bm_pool->id, MVNETA_BM_POOL_PTR_ALIGN); return -ENOMEM; @@ -139,6 +140,7 @@ static int mvneta_bm_pool_create(struct mvneta_bm *priv, if (err < 0) { dma_free_coherent(&pdev->dev, size_bytes, bm_pool->virt_addr, bm_pool->phys_addr); + bm_pool->virt_addr = NULL; return err; } @@ -477,6 +479,75 @@ static void mvneta_bm_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk); } +static int mvneta_bm_suspend(struct device *dev) +{ + struct mvneta_bm *priv = dev_get_drvdata(dev); + int i; + + /* Drain buffers and free pool resources while BM is still clocked */ + for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) { + struct mvneta_bm_pool *bm_pool = &priv->bm_pools[i]; + int size_bytes; + + if (bm_pool->type == MVNETA_BM_FREE) + continue; + + mvneta_bm_bufs_free(priv, bm_pool, bm_pool->port_map); + if (bm_pool->hwbm_pool.buf_num) + dev_warn(&priv->pdev->dev, + "pool %d: %d buffers not freed\n", + bm_pool->id, bm_pool->hwbm_pool.buf_num); + + mvneta_bm_pool_disable(priv, bm_pool->id); + + if (bm_pool->virt_addr) { + size_bytes = sizeof(u32) * bm_pool->hwbm_pool.size; + dma_free_coherent(&priv->pdev->dev, size_bytes, + bm_pool->virt_addr, + bm_pool->phys_addr); + bm_pool->virt_addr = NULL; + } + /* + * Safe to destroy: device_link guarantees all mvneta ports + * have already suspended, so no hwbm_pool_add() can be in + * progress holding buf_lock. Pairs with mutex_init() in + * mvneta_bm_pool_use() on resume. + */ + mutex_destroy(&bm_pool->hwbm_pool.buf_lock); + bm_pool->type = MVNETA_BM_FREE; + } + + mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_STOP_MASK); + clk_disable_unprepare(priv->clk); + return 0; +} + +static int mvneta_bm_resume(struct device *dev) +{ + struct mvneta_bm *priv = dev_get_drvdata(dev); + int i, err; + + err = clk_prepare_enable(priv->clk); + if (err) + return err; + + /* Reinitialize BM hardware; pools are refilled by mvneta_resume() */ + mvneta_bm_default_set(priv); + + /* Restore pool registers lost during clock gating */ + for (i = 0; i < MVNETA_BM_POOLS_NUM; i++) { + mvneta_bm_write(priv, MVNETA_BM_POOL_READ_PTR_REG(i), 0); + mvneta_bm_write(priv, MVNETA_BM_POOL_WRITE_PTR_REG(i), 0); + mvneta_bm_write(priv, MVNETA_BM_POOL_SIZE_REG(i), + priv->bm_pools[i].hwbm_pool.size); + } + + mvneta_bm_write(priv, MVNETA_BM_COMMAND_REG, MVNETA_BM_START_MASK); + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(mvneta_bm_pm_ops, mvneta_bm_suspend, mvneta_bm_resume); + static const struct of_device_id mvneta_bm_match[] = { { .compatible = "marvell,armada-380-neta-bm" }, { } @@ -489,6 +560,7 @@ static struct platform_driver mvneta_bm_driver = { .driver = { .name = MVNETA_BM_DRIVER_NAME, .of_match_table = mvneta_bm_match, + .pm = pm_sleep_ptr(&mvneta_bm_pm_ops), }, }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 714e47f68d93..f87cdf1b971d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -803,6 +803,7 @@ struct npc_set_pkind { */ u8 var_len_off_mask; /* Mask for length with in offset */ u8 shift_dir; /* shift direction to get length of the header at var_len_off */ + u8 skip_size; /* l2 size to skip */ }; /* NPA mbox message formats */ @@ -1267,6 +1268,7 @@ struct nix_rss_flowkey_cfg { #define NIX_FLOW_KEY_TYPE_IPV4_PROTO BIT(21) #define NIX_FLOW_KEY_TYPE_AH BIT(22) #define NIX_FLOW_KEY_TYPE_ESP BIT(23) +#define NIX_FLOW_KEY_TYPE_ROCEV2 BIT(24) #define NIX_FLOW_KEY_TYPE_L4_DST_ONLY BIT(28) #define NIX_FLOW_KEY_TYPE_L4_SRC_ONLY BIT(29) #define NIX_FLOW_KEY_TYPE_L3_DST_ONLY BIT(30) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index eaed172f1606..719b3618eeb5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -161,10 +161,12 @@ enum npc_kpu_lh_ltype { * Software assigns pkind for each incoming port such as CGX * Ethernet interfaces, LBK interfaces, etc. */ -#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_CPT_HDR_PTP_PKIND +#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_SKIP_SIZE_PKIND enum npc_pkind_type { NPC_RX_LBK_PKIND = 0ULL, + NPC_RX_SKIP_SIZE_PKIND = 46ULL, + NPC_RX_CPT_SKIP_SIZE_PKIND = 50ULL, NPC_RX_CPT_HDR_PTP_PKIND = 54ULL, NPC_RX_CUSTOM_PRE_L2_PKIND = 55ULL, NPC_RX_VLAN_EXDSA_PKIND = 56ULL, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 7f3505ae6860..c5610f242687 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -1181,7 +1181,7 @@ void rvu_switch_enable_lbk_link(struct rvu *rvu, u16 pcifunc, bool ena); int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, u64 pkind, u8 var_len_off, u8 var_len_off_mask, - u8 shift_dir); + u8 shift_dir, u8 skip_size); int rvu_get_hwvf(struct rvu *rvu, int pcifunc); /* CN10K MCS */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 0297c7ab0614..8e3bb47eb3ba 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -4305,6 +4305,13 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg) keyoff_marker = false; } break; + case NIX_FLOW_KEY_TYPE_ROCEV2: + field->hdr_offset = 5; + field->bytesm1 = 2; /* Destination QP */ + field->ltype_mask = 0xF; + field->lid = NPC_LID_LE; + field->ltype_match = NPC_LT_LE_ROCEV2; + break; } field->ena = 1; @@ -5392,7 +5399,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) /* reset HW config done for Switch headers */ rvu_npc_set_parse_mode(rvu, pcifunc, OTX2_PRIV_FLAGS_DEFAULT, - (PKIND_TX | PKIND_RX), 0, 0, 0, 0); + (PKIND_TX | PKIND_RX), 0, 0, 0, 0, 0); /* Disabling CGX and NPC config done for PTP */ if (pfvf->hw_rx_tstamp_en) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index c7bc0b3a29b9..08b83de9beb4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -4194,10 +4194,40 @@ npc_set_var_len_offset_pkind(struct rvu *rvu, u16 pcifunc, u64 pkind, return 0; } +static int npc_set_skip_size_pkind(struct rvu *rvu, u16 pcifunc, u64 pkind, + u8 skip_size) +{ + struct npc_kpu_action0 *act0; + int blkaddr; + u64 val; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, pcifunc); + if (blkaddr < 0) { + dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__); + return -EINVAL; + } + + val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind)); + act0 = (struct npc_kpu_action0 *)&val; + act0->ptr_advance = skip_size; + rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind), val); + + /* Update CPT_HR new PKIND */ + val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind + 4)); + act0 = (struct npc_kpu_action0 *)&val; + act0->ptr_advance = (skip_size + 40); + act0->next_state = NPC_S_KPU1_CPT_HDR; + act0->var_len_offset = (skip_size + 6); + act0->var_len_mask = 0xe0; + act0->var_len_shift = 0x5; + act0->var_len_right = 0x1; + rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind + 4), val); + return 0; +} + int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, u64 pkind, u8 var_len_off, u8 var_len_off_mask, - u8 shift_dir) - + u8 shift_dir, u8 skip_size) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); int blkaddr, nixlf, rc, intf_mode; @@ -4218,6 +4248,12 @@ int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, shift_dir); if (rc) return rc; + } else if (pkind >= NPC_RX_SKIP_SIZE_PKIND && + pkind <= NPC_RX_SKIP_SIZE_PKIND + 3) { + rc = npc_set_skip_size_pkind(rvu, pcifunc, pkind, + skip_size); + if (rc) + return rc; } rxpkind = pkind; txpkind = pkind; @@ -4254,7 +4290,8 @@ int rvu_mbox_handler_npc_set_pkind(struct rvu *rvu, struct npc_set_pkind *req, { return rvu_npc_set_parse_mode(rvu, req->hdr.pcifunc, req->mode, req->dir, req->pkind, req->var_len_off, - req->var_len_off_mask, req->shift_dir); + req->var_len_off_mask, req->shift_dir, + req->skip_size); } int rvu_mbox_handler_npc_read_base_steer_rule(struct rvu *rvu, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c index dbf173196608..8e41431c7f9c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c @@ -656,6 +656,7 @@ static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, pp_params.nid = NUMA_NO_NODE; pp_params.dev = pfvf->dev; pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.netdev = pfvf->netdev; pool->page_pool = page_pool_create(&pp_params); if (IS_ERR(pool->page_pool)) { netdev_err(pfvf->netdev, "Creation of page pool failed\n"); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 3d253132a17f..ca73a94db794 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1035,7 +1035,6 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura) if (qidx > pfvf->hw.xdp_queues) otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues)); - chan_offset = qidx % pfvf->hw.tx_chan_cnt; err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura); if (err) { @@ -1517,6 +1516,7 @@ int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, pp_params.nid = NUMA_NO_NODE; pp_params.dev = pfvf->dev; pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.netdev = pfvf->netdev; pool->page_pool = page_pool_create(&pp_params); if (IS_ERR(pool->page_pool)) { netdev_err(pfvf->netdev, "Creation of page pool failed\n"); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index cbb272a96359..0d0cd093b3c6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1118,7 +1118,7 @@ u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta, } void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta, - const char *enc_key) + char *enc_key) { u16 start = delta->start; u8 mask = delta->mask; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 010204f73ea4..67cc7a5737dd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -245,7 +245,7 @@ u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta); u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta, const char *enc_key); void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta, - const char *enc_key); + char *enc_key); struct mlxsw_sp_acl_erp_mask; diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index 48b94ce77490..88c5c52e0e38 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -16,7 +16,7 @@ #include <linux/net_tstamp.h> #include <linux/ptp_classify.h> #include <linux/ptp_pch.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #define PCH_GBE_MAR_ENTRIES 16 #define PCH_GBE_SHORT_PKT 64 diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c index 528114877677..c999754afb5f 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -558,18 +558,15 @@ struct sync_item { void ionic_rx_filter_sync(struct ionic_lif *lif) { struct device *dev = lif->ionic->dev; - struct list_head sync_add_list; - struct list_head sync_del_list; struct sync_item *sync_item; struct ionic_rx_filter *f; + LIST_HEAD(sync_add_list); + LIST_HEAD(sync_del_list); struct hlist_head *head; struct hlist_node *tmp; struct sync_item *spos; unsigned int i; - INIT_LIST_HEAD(&sync_add_list); - INIT_LIST_HEAD(&sync_del_list); - clear_bit(IONIC_LIF_F_FILTER_SYNC_NEEDED, lif->state); /* Copy the filters to be added and deleted diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 39731069d99e..009f37105eaf 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -967,11 +967,12 @@ static void ioc3eth_remove(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct ioc3_private *ip = netdev_priv(dev); + unregister_netdev(dev); + timer_delete_sync(&ip->ioc3_timer); + dma_free_coherent(ip->dma_dev, RX_RING_SIZE, ip->rxr, ip->rxr_dma); dma_free_coherent(ip->dma_dev, TX_RING_SIZE + SZ_16K - 1, ip->tx_ring, ip->txr_dma); - unregister_netdev(dev); - timer_delete_sync(&ip->ioc3_timer); free_netdev(dev); } @@ -1061,9 +1062,9 @@ static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) d1 = dma_map_single(ip->dma_dev, skb->data, s1, DMA_TO_DEVICE); if (dma_mapping_error(ip->dma_dev, d1)) goto drop_packet; - d2 = dma_map_single(ip->dma_dev, (void *)b2, s1, DMA_TO_DEVICE); + d2 = dma_map_single(ip->dma_dev, (void *)b2, s2, DMA_TO_DEVICE); if (dma_mapping_error(ip->dma_dev, d2)) { - dma_unmap_single(ip->dma_dev, d1, len, DMA_TO_DEVICE); + dma_unmap_single(ip->dma_dev, d1, s1, DMA_TO_DEVICE); goto drop_packet; } desc->p1 = cpu_to_be64(ioc3_map(d1, PCI64_ATTR_PREF)); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 862001d09aa8..c1812a98365b 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -1737,7 +1737,7 @@ static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve) netpoll_zap_completion_queue(); repeat: - skb = alloc_skb(len, GFP_ATOMIC); + skb = alloc_skb(len, GFP_ATOMIC | __GFP_NOWARN); if (!skb) skb = netcons_skb_pop(np, len); diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 56080d3d2d25..a18263d5bb02 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -8,7 +8,7 @@ #include <linux/delay.h> #include <linux/errno.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/gpio/consumer.h> #include <linux/init.h> #include <linux/interrupt.h> diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 087ac63f9193..59dfe35afa54 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -153,8 +153,7 @@ static DECLARE_PHY_INTERFACE_MASK(phylink_sfp_interfaces); * phylink_set_port_modes() - set the port type modes in the ethtool mask * @mask: ethtool link mode mask * - * Sets all the port type modes in the ethtool mask. MAC drivers should - * use this in their 'validate' callback. + * Sets all the port type modes in the ethtool mask. */ void phylink_set_port_modes(unsigned long *mask) { @@ -2095,9 +2094,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, /* * This is the new way of dealing with flow control for PHYs, * as described by Timur Tabi in commit 529ed1275263 ("net: phy: - * phy drivers should not set SUPPORTED_[Asym_]Pause") except - * using our validate call to the MAC, we rely upon the MAC - * clearing the bits from both supported and advertising fields. + * phy drivers should not set SUPPORTED_[Asym_]Pause"). MAC drivers + * set their support using the MAC_SYM_PAUSE and MAC_ASYM_PAUSE + * capabilities and must NOT change the phy's pause settings directly. */ phy_support_asym_pause(phy); @@ -3931,9 +3930,9 @@ static int phylink_sfp_connect_phy(void *upstream, struct phy_device *phy) /* * This is the new way of dealing with flow control for PHYs, * as described by Timur Tabi in commit 529ed1275263 ("net: phy: - * phy drivers should not set SUPPORTED_[Asym_]Pause") except - * using our validate call to the MAC, we rely upon the MAC - * clearing the bits from both supported and advertising fields. + * phy drivers should not set SUPPORTED_[Asym_]Pause"). MAC drivers + * set their support using the MAC_SYM_PAUSE and MAC_ASYM_PAUSE + * capabilities and must NOT change the phy's pause settings directly. */ phy_support_asym_pause(phy); diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index c880c95c41a5..d51e43170e03 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -732,7 +732,9 @@ static void set_carrier(struct net_device *netdev) rtl8150_t *dev = netdev_priv(netdev); short tmp; - get_registers(dev, CSCR, 2, &tmp); + if (get_registers(dev, CSCR, 2, &tmp)) + return; + if (tmp & CSCR_LINK_STATUS) netif_carrier_on(netdev); else diff --git a/include/linux/net.h b/include/linux/net.h index fdcf9956805c..3d82966e2243 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -47,6 +47,29 @@ typedef struct sockopt { int optlen; } sockopt_t; +/* + * Initialize a user-backed sockopt_t from the (optval, optlen) __user pair of + * a getsockopt() callback. Used by transitional __user getsockopt wrappers + * while the proto-layer callbacks are converted to take a sockopt_t; the + * caller writes opt->optlen back to the user optlen after the callback. + */ +static inline int sockopt_init_user(sockopt_t *opt, char __user *optval, + int __user *optlen) +{ + int len; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) + return -EINVAL; + + iov_iter_ubuf(&opt->iter_out, ITER_DEST, optval, len); + iov_iter_ubuf(&opt->iter_in, ITER_SOURCE, optval, len); + opt->optlen = len; + + return 0; +} + struct poll_table_struct; struct pipe_inode_info; struct inode; diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h index 05572c19e14b..ef667dff2972 100644 --- a/include/net/bond_3ad.h +++ b/include/net/bond_3ad.h @@ -302,8 +302,8 @@ void bond_3ad_state_machine_handler(struct work_struct *); void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); void bond_3ad_adapter_speed_duplex_changed(struct slave *slave); void bond_3ad_handle_link_change(struct slave *slave, char link); -int bond_3ad_get_active_agg_info(struct bonding *bond, struct ad_info *ad_info); -int __bond_3ad_get_active_agg_info(struct bonding *bond, +int bond_3ad_get_active_agg_info(const struct bonding *bond, struct ad_info *ad_info); +int __bond_3ad_get_active_agg_info(const struct bonding *bond, struct ad_info *ad_info); int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave); diff --git a/include/net/bonding.h b/include/net/bonding.h index 2c54a36a8477..598d56b1bc97 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -345,14 +345,14 @@ static inline bool bond_mode_uses_primary(int mode) mode == BOND_MODE_ALB; } -static inline bool bond_uses_primary(struct bonding *bond) +static inline bool bond_uses_primary(const struct bonding *bond) { return bond_mode_uses_primary(BOND_MODE(bond)); } -static inline struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond) +static inline struct net_device *bond_option_active_slave_get_rcu(const struct bonding *bond) { - struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); + const struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave); return bond_uses_primary(bond) && slave ? slave->dev : NULL; } @@ -703,7 +703,7 @@ void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); int bond_netlink_init(void); void bond_netlink_fini(void); -struct net_device *bond_option_active_slave_get_rcu(struct bonding *bond); +struct net_device *bond_option_active_slave_get_rcu(const struct bonding *bond); const char *bond_slave_link_status(s8 link); struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev, struct net_device *end_dev, diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 7dee0ae616e3..c6b94790fa81 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -82,7 +82,7 @@ struct fib_rules_ops { struct fib_rule_hdr *, struct nlattr **, struct netlink_ext_ack *); - int (*delete)(struct fib_rule *); + void (*delete)(struct fib_rule *); int (*compare)(struct fib_rule *, struct fib_rule_hdr *, struct nlattr **); @@ -93,11 +93,13 @@ struct fib_rules_ops { /* Called after modifications to the rules set, must flush * the route cache if one exists. */ void (*flush_cache)(struct fib_rules_ops *ops); + bool (*need_rtnl)(struct net *net); int nlgroup; struct list_head rules_list; struct module *owner; struct net *fro_net; + struct mutex lock; struct rcu_head rcu; }; diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c63a3c4967ae..0a35355fb0f3 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -302,7 +302,8 @@ static inline struct fib_table *fib_get_table(struct net *net, u32 id) &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; - tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); + /* Only fib4_rules_init() adds fib_table. */ + tb_hlist = rcu_dereference_protected(hlist_first_rcu(ptr), true); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6e27c56514df..59506320558a 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -127,6 +127,7 @@ struct netns_ipv4 { atomic_t fib_num_tclassid_users; #endif struct hlist_head *fib_table_hash; + spinlock_t fib_table_hash_lock; struct sock *fibnl; struct hlist_head *fib_info_hash; unsigned int fib_info_hash_bits; diff --git a/include/net/udp.h b/include/net/udp.h index 8262e2b215b4..1fee17274745 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -430,7 +430,7 @@ struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, netdev_features_t features, bool is_ipv6); int udp_lib_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); + sockopt_t *opt); int udp_lib_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)); diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index aa7958b4e41d..7fb630b7fe31 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -36,6 +36,7 @@ enum { IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ IFA_TARGET_NETNSID, IFA_PROTO, /* u8, address protocol */ + IFA_MC_USERS, /* u32, multicast group users */ __IFA_MAX, }; diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index bb2f012b454e..22622283f59b 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -404,23 +404,14 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet, /* send a batman ogm packet */ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) { - struct net_device *mesh_iface; - if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not specified\n"); return; } - mesh_iface = forw_packet->if_incoming->mesh_iface; - if (WARN_ON(!forw_packet->if_outgoing)) return; - if (forw_packet->if_outgoing->mesh_iface != mesh_iface) { - pr_warn("%s: mesh interface switch for queued OGM\n", __func__); - return; - } - if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; @@ -910,8 +901,7 @@ out: static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) { - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || - hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + if (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) return; mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 4841f0f1a9b1..262e40040007 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -90,12 +90,6 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, u32 throughput; int ret; - /* don't query throughput when no longer associated with any - * batman-adv interface - */ - if (!mesh_iface) - return false; - /* if the user specified a customised value for this interface, then * return it directly */ @@ -311,8 +305,7 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) goto out; /* we are in the process of shutting this interface down */ - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || - hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + if (hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) goto out; /* the interface was enabled but may not be ready yet */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 037921aad35d..e921d49f7ece 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -115,14 +115,14 @@ static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv) /** * batadv_v_ogm_send_to_if() - send a batman ogm using a given interface - * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to send * @hard_iface: the interface to use to send the OGM */ -static void batadv_v_ogm_send_to_if(struct batadv_priv *bat_priv, - struct sk_buff *skb, +static void batadv_v_ogm_send_to_if(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { + struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); + if (hard_iface->if_status != BATADV_IF_ACTIVE) { kfree_skb(skb); return; @@ -189,7 +189,6 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) /** * batadv_v_ogm_aggr_send() - flush & send aggregation queue - * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: the interface with the aggregation queue to flush * * Aggregates all OGMv2 packets currently in the aggregation queue into a @@ -199,8 +198,7 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. */ -static void batadv_v_ogm_aggr_send(struct batadv_priv *bat_priv, - struct batadv_hard_iface *hard_iface) +static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) { unsigned int aggr_len = hard_iface->bat_v.aggr_len; struct sk_buff *skb_aggr; @@ -230,26 +228,21 @@ static void batadv_v_ogm_aggr_send(struct batadv_priv *bat_priv, consume_skb(skb); } - batadv_v_ogm_send_to_if(bat_priv, skb_aggr, hard_iface); + batadv_v_ogm_send_to_if(skb_aggr, hard_iface); } /** * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface - * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to queue * @hard_iface: the interface to queue the OGM on */ -static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv, - struct sk_buff *skb, +static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { - if (hard_iface->mesh_iface != bat_priv->mesh_iface) { - kfree_skb(skb); - return; - } + struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); if (!READ_ONCE(bat_priv->aggregated_ogms)) { - batadv_v_ogm_send_to_if(bat_priv, skb, hard_iface); + batadv_v_ogm_send_to_if(skb, hard_iface); return; } @@ -260,7 +253,7 @@ static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv, } if (!batadv_v_ogm_queue_left(skb, hard_iface)) - batadv_v_ogm_aggr_send(bat_priv, hard_iface); + batadv_v_ogm_aggr_send(hard_iface); hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); @@ -357,7 +350,7 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) break; } - batadv_v_ogm_queue_on_if(bat_priv, skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -397,14 +390,12 @@ void batadv_v_ogm_aggr_work(struct work_struct *work) { struct batadv_hard_iface_bat_v *batv; struct batadv_hard_iface *hard_iface; - struct batadv_priv *bat_priv; batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); - bat_priv = netdev_priv(hard_iface->mesh_iface); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); - batadv_v_ogm_aggr_send(bat_priv, hard_iface); + batadv_v_ogm_aggr_send(hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_start_queue_timer(hard_iface); @@ -601,7 +592,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_queue_on_if(bat_priv, skb, if_outgoing); + batadv_v_ogm_queue_on_if(skb, if_outgoing); out: batadv_orig_ifinfo_put(orig_ifinfo); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5c73f6ba16cf..f9a1fadf8de9 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -344,7 +344,6 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, struct sk_buff *skb; struct ethhdr *ethhdr; struct batadv_hard_iface *primary_if; - struct net_device *mesh_iface; u8 *hw_src; struct batadv_bla_claim_dst local_claim_dest; __be32 zeroip = 0; @@ -357,14 +356,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, sizeof(local_claim_dest)); local_claim_dest.type = claimtype; - mesh_iface = READ_ONCE(primary_if->mesh_iface); - if (!mesh_iface) - goto out; - skb = arp_create(ARPOP_REPLY, ETH_P_ARP, /* IP DST: 0.0.0.0 */ zeroip, - mesh_iface, + primary_if->mesh_iface, /* IP SRC: 0.0.0.0 */ zeroip, /* Ethernet DST: Broadcast */ @@ -442,7 +437,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, } skb_reset_mac_header(skb); - skb->protocol = eth_type_trans(skb, mesh_iface); + skb->protocol = eth_type_trans(skb, primary_if->mesh_iface); batadv_inc_counter(bat_priv, BATADV_CNT_RX); batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES, skb->len + ETH_HLEN); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 03d01c20a954..b6867576bbaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -63,6 +63,7 @@ void batadv_hardif_release(struct kref *ref) struct batadv_hard_iface *hard_iface; hard_iface = container_of(ref, struct batadv_hard_iface, refcount); + netdev_put(hard_iface->mesh_iface, &hard_iface->meshif_dev_tracker); netdev_put(hard_iface->net_dev, &hard_iface->dev_tracker); kfree_rcu(hard_iface, rcu); @@ -75,21 +76,21 @@ void batadv_hardif_release(struct kref *ref) * Return: batadv_hard_iface of net_dev (with increased refcnt), NULL on errors */ struct batadv_hard_iface * -batadv_hardif_get_by_netdev(const struct net_device *net_dev) +batadv_hardif_get_by_netdev(struct net_device *net_dev) { struct batadv_hard_iface *hard_iface; + struct net_device *mesh_iface; - rcu_read_lock(); - list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) { - if (hard_iface->net_dev == net_dev && - kref_get_unless_zero(&hard_iface->refcount)) - goto out; - } + ASSERT_RTNL(); - hard_iface = NULL; + mesh_iface = netdev_master_upper_dev_get(net_dev); + if (!mesh_iface || !batadv_meshif_is_valid(mesh_iface)) + return NULL; + + hard_iface = netdev_lower_dev_get_private(mesh_iface, net_dev); + if (!kref_get_unless_zero(&hard_iface->refcount)) + return NULL; -out: - rcu_read_unlock(); return hard_iface; } @@ -245,7 +246,7 @@ struct net_device *__batadv_get_real_netdev(struct net_device *netdev) } hard_iface = batadv_hardif_get_by_netdev(netdev); - if (!hard_iface || !hard_iface->mesh_iface) + if (!hard_iface) goto out; net = dev_net(hard_iface->mesh_iface); @@ -539,16 +540,10 @@ static void batadv_check_known_mac_addr(const struct batadv_hard_iface *hard_ifa const struct batadv_hard_iface *tmp_hard_iface; struct list_head *iter; - if (!mesh_iface) - return; - netdev_for_each_lower_private(mesh_iface, tmp_hard_iface, iter) { if (tmp_hard_iface == hard_iface) continue; - if (tmp_hard_iface->if_status == BATADV_IF_NOT_IN_USE) - continue; - if (!batadv_compare_eth(tmp_hard_iface->net_dev->dev_addr, hard_iface->net_dev->dev_addr)) continue; @@ -574,9 +569,6 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *mesh_iface) rcu_read_lock(); netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter) { - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) - continue; - lower_header_len = max_t(unsigned short, lower_header_len, hard_iface->net_dev->hard_header_len); @@ -723,38 +715,63 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface) } /** - * batadv_hardif_enable_interface() - Enslave hard interface to mesh interface - * @hard_iface: hard interface to add to mesh interface + * batadv_hardif_enable_interface() - Enslave interface to mesh interface + * @net_dev: netdev struct of the interface to add to mesh interface * @mesh_iface: netdev struct of the mesh interface * * Return: 0 on success or negative error number in case of failure */ -int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, +int batadv_hardif_enable_interface(struct net_device *net_dev, struct net_device *mesh_iface) { struct batadv_priv *bat_priv; __be16 ethertype = htons(ETH_P_BATMAN); int max_header_len = batadv_max_header_len(); + struct batadv_hard_iface *hard_iface; unsigned int required_mtu; unsigned int hardif_mtu; bool fragmentation; int ret; - hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu); + ASSERT_RTNL(); + + if (!batadv_is_valid_iface(net_dev)) + return -EINVAL; + + hardif_mtu = READ_ONCE(net_dev->mtu); required_mtu = READ_ONCE(mesh_iface->mtu) + max_header_len; if (hardif_mtu < ETH_MIN_MTU + max_header_len) return -EINVAL; - if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) - goto out; + hard_iface = kzalloc_obj(*hard_iface, GFP_ATOMIC); + if (!hard_iface) + return -ENOMEM; - kref_get(&hard_iface->refcount); + netdev_hold(net_dev, &hard_iface->dev_tracker, GFP_ATOMIC); + hard_iface->net_dev = net_dev; + + hard_iface->if_status = BATADV_IF_INACTIVE; + + INIT_HLIST_HEAD(&hard_iface->neigh_list); + + mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); + spin_lock_init(&hard_iface->neigh_list_lock); + kref_init(&hard_iface->refcount); + + hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; + if (batadv_is_wifi_hardif(hard_iface)) + hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; + + WRITE_ONCE(hard_iface->hop_penalty, 0); + + batadv_v_hardif_init(hard_iface); netdev_hold(mesh_iface, &hard_iface->meshif_dev_tracker, GFP_ATOMIC); hard_iface->mesh_iface = mesh_iface; bat_priv = netdev_priv(hard_iface->mesh_iface); + bat_priv->hardif_generation++; ret = netdev_master_upper_dev_link(hard_iface->net_dev, mesh_iface, hard_iface, NULL, NULL); if (ret) @@ -764,9 +781,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, if (ret < 0) goto err_upper; - hard_iface->if_status = BATADV_IF_INACTIVE; - - kref_get(&hard_iface->refcount); hard_iface->batman_adv_ptype.type = ethertype; hard_iface->batman_adv_ptype.func = batadv_batman_skb_recv; hard_iface->batman_adv_ptype.dev = hard_iface->net_dev; @@ -802,14 +816,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, if (bat_priv->algo_ops->iface.enabled) bat_priv->algo_ops->iface.enabled(hard_iface); -out: return 0; err_upper: netdev_upper_dev_unlink(hard_iface->net_dev, mesh_iface); err_dev: - hard_iface->mesh_iface = NULL; - netdev_put(mesh_iface, &hard_iface->meshif_dev_tracker); batadv_hardif_put(hard_iface); return ret; } @@ -821,17 +832,18 @@ err_dev: void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); - struct batadv_hard_iface *primary_if = NULL; + struct batadv_hard_iface *primary_if; + + ASSERT_RTNL(); batadv_hardif_deactivate_interface(hard_iface); if (hard_iface->if_status != BATADV_IF_INACTIVE) - goto out; + return; batadv_info(hard_iface->mesh_iface, "Removing interface: %s\n", hard_iface->net_dev->name); dev_remove_pack(&hard_iface->batman_adv_ptype); - batadv_hardif_put(hard_iface); primary_if = batadv_primary_if_get_selected(bat_priv); if (hard_iface == primary_if) { @@ -842,15 +854,16 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) batadv_hardif_put(new_if); } + batadv_hardif_put(primary_if); bat_priv->algo_ops->iface.disable(hard_iface); - hard_iface->if_status = BATADV_IF_NOT_IN_USE; + hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; /* delete all references to this hard_iface */ batadv_purge_orig_ref(bat_priv); batadv_purge_outstanding_packets(bat_priv, hard_iface); - netdev_put(hard_iface->mesh_iface, &hard_iface->meshif_dev_tracker); + bat_priv->hardif_generation++; netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->mesh_iface); batadv_hardif_recalc_extra_skbroom(hard_iface->mesh_iface); @@ -858,67 +871,6 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface) if (list_empty(&hard_iface->mesh_iface->adj_list.lower)) batadv_gw_check_client_stop(bat_priv); - hard_iface->mesh_iface = NULL; - batadv_hardif_put(hard_iface); - -out: - batadv_hardif_put(primary_if); -} - -static struct batadv_hard_iface * -batadv_hardif_add_interface(struct net_device *net_dev) -{ - struct batadv_hard_iface *hard_iface; - - ASSERT_RTNL(); - - if (!batadv_is_valid_iface(net_dev)) - return NULL; - - hard_iface = kzalloc_obj(*hard_iface, GFP_ATOMIC); - if (!hard_iface) - return NULL; - - netdev_hold(net_dev, &hard_iface->dev_tracker, GFP_ATOMIC); - hard_iface->net_dev = net_dev; - - hard_iface->mesh_iface = NULL; - hard_iface->if_status = BATADV_IF_NOT_IN_USE; - - INIT_LIST_HEAD(&hard_iface->list); - INIT_HLIST_HEAD(&hard_iface->neigh_list); - - mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); - spin_lock_init(&hard_iface->neigh_list_lock); - kref_init(&hard_iface->refcount); - - hard_iface->num_bcasts = BATADV_NUM_BCASTS_DEFAULT; - if (batadv_is_wifi_hardif(hard_iface)) - hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; - - WRITE_ONCE(hard_iface->hop_penalty, 0); - - batadv_v_hardif_init(hard_iface); - - kref_get(&hard_iface->refcount); - list_add_tail_rcu(&hard_iface->list, &batadv_hardif_list); - batadv_hardif_generation++; - - return hard_iface; -} - -static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface) -{ - ASSERT_RTNL(); - - /* first deactivate interface */ - if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) - batadv_hardif_disable_interface(hard_iface); - - if (hard_iface->if_status != BATADV_IF_NOT_IN_USE) - return; - - hard_iface->if_status = BATADV_IF_TO_BE_REMOVED; batadv_hardif_put(hard_iface); } @@ -1082,10 +1034,6 @@ static int batadv_hard_if_event(struct notifier_block *this, batadv_wifi_net_device_event(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); - if (!hard_iface && (event == NETDEV_REGISTER || - event == NETDEV_POST_TYPE_CHANGE)) - hard_iface = batadv_hardif_add_interface(net_dev); - if (!hard_iface) goto out; @@ -1099,19 +1047,12 @@ static int batadv_hard_if_event(struct notifier_block *this, break; case NETDEV_UNREGISTER: case NETDEV_PRE_TYPE_CHANGE: - list_del_rcu(&hard_iface->list); - batadv_hardif_generation++; - - batadv_hardif_remove_interface(hard_iface); + batadv_hardif_disable_interface(hard_iface); break; case NETDEV_CHANGEMTU: - if (hard_iface->mesh_iface) - batadv_update_min_mtu(hard_iface->mesh_iface); + batadv_update_min_mtu(hard_iface->mesh_iface); break; case NETDEV_CHANGEADDR: - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE) - goto hardif_put; - batadv_check_known_mac_addr(hard_iface); bat_priv = netdev_priv(hard_iface->mesh_iface); diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index af31696c3978..935f47ca9a48 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -22,12 +22,6 @@ */ enum batadv_hard_if_state { /** - * @BATADV_IF_NOT_IN_USE: interface is not used as slave interface of a - * batman-adv mesh interface - */ - BATADV_IF_NOT_IN_USE, - - /** * @BATADV_IF_TO_BE_REMOVED: interface will be removed from mesh * interface */ @@ -74,8 +68,8 @@ u32 batadv_netdev_get_wifi_flags(struct net_device *net_dev); u32 batadv_hardif_get_wifi_flags(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); struct batadv_hard_iface* -batadv_hardif_get_by_netdev(const struct net_device *net_dev); -int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface, +batadv_hardif_get_by_netdev(struct net_device *net_dev); +int batadv_hardif_enable_interface(struct net_device *net_dev, struct net_device *mesh_iface); void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface); int batadv_hardif_min_mtu(struct net_device *mesh_iface); diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4d3807a645b7..fb2b0e35e349 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -59,11 +59,6 @@ #include "tp_meter.h" #include "translation-table.h" -/* List manipulations on hardif_list have to be rtnl_lock()'ed, - * list traversals just rcu-locked - */ -struct list_head batadv_hardif_list; -unsigned int batadv_hardif_generation; static int (*batadv_rx_handler[256])(struct sk_buff *skb, struct batadv_hard_iface *recv_if); @@ -95,7 +90,6 @@ static int __init batadv_init(void) if (ret < 0) return ret; - INIT_LIST_HEAD(&batadv_hardif_list); batadv_algo_init(); batadv_recv_handler_init(); @@ -450,9 +444,6 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev, if (unlikely(skb->mac_len != ETH_HLEN || !skb_mac_header(skb))) goto err_free; - if (!hard_iface->mesh_iface) - goto err_free; - bat_priv = netdev_priv(hard_iface->mesh_iface); if (READ_ONCE(bat_priv->mesh_state) != BATADV_MESH_ACTIVE) diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index f68fc8b7239c..e738758ee4a7 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -226,9 +226,6 @@ static inline int batadv_print_vid(unsigned short vid) return -1; } -extern struct list_head batadv_hardif_list; -extern unsigned int batadv_hardif_generation; - extern struct workqueue_struct *batadv_event_workqueue; int batadv_mesh_init(struct net_device *mesh_iface); diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c index 511f70e0706a..5cc72bbc4570 100644 --- a/net/batman-adv/mesh-interface.c +++ b/net/batman-adv/mesh-interface.c @@ -837,18 +837,7 @@ static int batadv_meshif_slave_add(struct net_device *dev, struct net_device *slave_dev, struct netlink_ext_ack *extack) { - struct batadv_hard_iface *hard_iface; - int ret = -EINVAL; - - hard_iface = batadv_hardif_get_by_netdev(slave_dev); - if (!hard_iface || hard_iface->mesh_iface) - goto out; - - ret = batadv_hardif_enable_interface(hard_iface, dev); - -out: - batadv_hardif_put(hard_iface); - return ret; + return batadv_hardif_enable_interface(slave_dev, dev); } /** diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 4cf9e3c54ad3..d2bc48c70714 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -968,7 +968,7 @@ batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) bat_priv = netdev_priv(mesh_iface); rtnl_lock(); - cb->seq = batadv_hardif_generation << 1 | 1; + cb->seq = bat_priv->hardif_generation << 1 | 1; netdev_for_each_lower_private(mesh_iface, hard_iface, iter) { if (i++ < skip) @@ -1211,7 +1211,9 @@ batadv_netlink_get_hardif_from_ifindex(struct batadv_priv *bat_priv, if (!hard_dev) return ERR_PTR(-ENODEV); + rtnl_lock(); hard_iface = batadv_hardif_get_by_netdev(hard_dev); + rtnl_unlock(); if (!hard_iface) goto err_put_harddev; diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 9b38bd9e8da7..48f837cf665a 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1033,7 +1033,6 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv, /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && - if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; @@ -1077,7 +1076,6 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv, /* don't purge if the interface is not (going) down */ if (if_outgoing->if_status != BATADV_IF_INACTIVE && - if_outgoing->if_status != BATADV_IF_NOT_IN_USE && if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED) continue; @@ -1127,10 +1125,8 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv, if (batadv_has_timed_out(last_seen, BATADV_PURGE_TIMEOUT) || if_incoming->if_status == BATADV_IF_INACTIVE || - if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) { if (if_incoming->if_status == BATADV_IF_INACTIVE || - if_incoming->if_status == BATADV_IF_NOT_IN_USE || if_incoming->if_status == BATADV_IF_TO_BE_REMOVED) batadv_dbg(BATADV_DBG_BATMAN, bat_priv, "neighbor purge: originator %pM, neighbor: %pM, iface: %s\n", diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index c2eea7dbc488..00467aa79de9 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -358,28 +358,16 @@ batadv_tp_list_find_sender_session(struct batadv_priv *bat_priv, const u8 *dst, } /** - * batadv_tp_vars_common_release() - release batadv_tp_vars_common from lists + * batadv_tp_sender_release() - release batadv_tp_sender * and queue for free after rcu grace period - * @ref: kref pointer of the batadv_tp_vars_common + * @ref: kref pointer of the batadv_tp_sender */ -static void batadv_tp_vars_common_release(struct kref *ref) +static void batadv_tp_sender_release(struct kref *ref) { - struct batadv_tp_vars_common *tp_vars; - struct batadv_tp_unacked *un, *safe; - - tp_vars = container_of(ref, struct batadv_tp_vars_common, refcount); - - /* lock should not be needed because this object is now out of any - * context! - */ - spin_lock_bh(&tp_vars->unacked_lock); - list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { - list_del(&un->list); - kfree(un); - } - spin_unlock_bh(&tp_vars->unacked_lock); + struct batadv_tp_sender *tp_vars; - kfree_rcu(tp_vars, rcu); + tp_vars = container_of(ref, struct batadv_tp_sender, common.refcount); + kfree_rcu(tp_vars, common.rcu); } /** @@ -392,7 +380,7 @@ static void batadv_tp_sender_put(struct batadv_tp_sender *tp_vars) if (!tp_vars) return; - kref_put(&tp_vars->common.refcount, batadv_tp_vars_common_release); + kref_put(&tp_vars->common.refcount, batadv_tp_sender_release); } /** @@ -1145,9 +1133,6 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, init_waitqueue_head(&tp_vars->more_bytes); init_completion(&tp_vars->finished); - spin_lock_init(&tp_vars->common.unacked_lock); - INIT_LIST_HEAD(&tp_vars->common.unacked_list); - spin_lock_init(&tp_vars->cc_lock); tp_vars->prerandom_offset = 0; @@ -1252,6 +1237,33 @@ batadv_tp_list_find_receiver_session(struct batadv_priv *bat_priv, const u8 *dst } /** + * batadv_tp_receiver_release() - release batadv_tp_receiver + * and queue for free after rcu grace period + * @ref: kref pointer of the batadv_tp_receiver + */ +static void batadv_tp_receiver_release(struct kref *ref) +{ + struct batadv_tp_receiver *tp_vars; + struct batadv_tp_unacked *safe; + struct batadv_tp_unacked *un; + + tp_vars = container_of(ref, struct batadv_tp_receiver, common.refcount); + + /* lock should not be needed because this object is now out of any + * context! + */ + spin_lock_bh(&tp_vars->ack_seqno_lock); + list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { + list_del(&un->list); + kfree(un); + tp_vars->unacked_count--; + } + spin_unlock_bh(&tp_vars->ack_seqno_lock); + + kfree_rcu(tp_vars, common.rcu); +} + +/** * batadv_tp_receiver_put() - decrement the batadv_tp_receiver * refcounter and possibly release it * @tp_vars: the private data of the current TP meter session to be free'd @@ -1261,7 +1273,7 @@ static void batadv_tp_receiver_put(struct batadv_tp_receiver *tp_vars) if (!tp_vars) return; - kref_put(&tp_vars->common.refcount, batadv_tp_vars_common_release); + kref_put(&tp_vars->common.refcount, batadv_tp_receiver_release); } /** @@ -1304,13 +1316,13 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) if (batadv_tp_list_detach(&tp_vars->common)) batadv_tp_receiver_put(tp_vars); - spin_lock_bh(&tp_vars->common.unacked_lock); - list_for_each_entry_safe(un, safe, &tp_vars->common.unacked_list, list) { + spin_lock_bh(&tp_vars->ack_seqno_lock); + list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { list_del(&un->list); kfree(un); - tp_vars->common.unacked_count--; + tp_vars->unacked_count--; } - spin_unlock_bh(&tp_vars->common.unacked_lock); + spin_unlock_bh(&tp_vars->ack_seqno_lock); /* drop reference of timer */ if (WARN_ON(atomic_xchg(&tp_vars->receiving, 0) != 1)) @@ -1403,69 +1415,106 @@ out: */ static bool batadv_tp_handle_out_of_order(struct batadv_tp_receiver *tp_vars, u32 seqno, u32 payload_len) - __must_hold(&tp_vars->common.unacked_lock) + __must_hold(&tp_vars->ack_seqno_lock) { - struct batadv_tp_unacked *un, *new; - bool added = false; - - new = kmalloc_obj(*new, GFP_ATOMIC); - if (unlikely(!new)) - return false; - - new->seqno = seqno; - new->len = payload_len; - - /* if the list is empty immediately attach this new object */ - if (list_empty(&tp_vars->common.unacked_list)) { - list_add(&new->list, &tp_vars->common.unacked_list); - tp_vars->common.unacked_count++; - return true; - } - - /* otherwise loop over the list and either drop the packet because this - * is a duplicate or store it at the right position. + struct list_head *pos = &tp_vars->unacked_list; + struct batadv_tp_unacked *new = NULL; + u32 end_seqno = seqno + payload_len; + struct batadv_tp_unacked *safe; + struct batadv_tp_unacked *un; + + /* loop over the list to find either an existing entry which the new + * seqno range can be merged with or the position at which a new entry + * has to be inserted. * * The iteration is done in the reverse way because it is likely that * the last received packet (the one being processed now) has a bigger * seqno than all the others already stored. */ - list_for_each_entry_reverse(un, &tp_vars->common.unacked_list, list) { - /* check for duplicates */ - if (new->seqno == un->seqno) { - if (new->len > un->len) - un->len = new->len; - kfree(new); - added = true; - break; - } - - /* look for the right position */ - if (batadv_seq_before(new->seqno, un->seqno)) + list_for_each_entry_reverse(un, &tp_vars->unacked_list, list) { + /* look for the right position - an un which is smaller */ + if (batadv_seq_before(seqno, un->seqno)) continue; - /* as soon as an entry having a bigger seqno is found, the new - * one is attached _after_ it. In this way the list is kept in - * ascending order + /* smaller/equal seqno was found but they might be directly + * after another or overlapping. keep only a single entry + * + * It is already known that: + * + * un->seqno <= seqno + * + * When establishing that: + * + * seqno <= un->seqno + un->len + * + * Then it is not necessary to add a new entry because the + * smaller/equal seqno of un might already contain the new + * received packet or we only add new data directly after + * the end of un. The latter can be identified using: + * + * un->seqno + un->len <= end_seqno */ - list_add(&new->list, &un->list); - added = true; - tp_vars->common.unacked_count++; + if (!batadv_seq_before(un->seqno + un->len, seqno)) { + /* new data directly after un? */ + if (!batadv_seq_before(end_seqno, un->seqno + un->len)) + un->len = end_seqno - un->seqno; + + /* un now represents both old un + new range and has to + * be used to check if the gap to the next seqno range + * was closed + */ + new = un; + } else { + /* as soon as an entry having a smaller seqno is found, + * the new one is attached _after_ it. In this way the + * list is kept in ascending order + */ + pos = &un->list; + } + break; } - /* received packet with smallest seqno out of order; add it to front */ - if (!added) { - list_add(&new->list, &tp_vars->common.unacked_list); - tp_vars->common.unacked_count++; + /* no entry to merge with was found; insert a new one after the entry + * with the next smaller seqno (or at the front of the list when the + * new seqno is the smallest or the list is empty) + */ + if (!new) { + new = kmalloc_obj(*new, GFP_ATOMIC); + if (unlikely(!new)) + return false; + + new->seqno = seqno; + new->len = payload_len; + + list_add(&new->list, pos); + tp_vars->unacked_count++; + } + + /* check if new filled the gap to the next list entries */ + un = new; + list_for_each_entry_safe_continue(un, safe, &tp_vars->unacked_list, list) { + if (batadv_seq_before(end_seqno, un->seqno)) + break; + + /* next entry is overlapping or adjacent - combine both */ + if (batadv_seq_before(end_seqno, un->seqno + un->len)) { + end_seqno = un->seqno + un->len; + new->len = end_seqno - new->seqno; + } + + list_del(&un->list); + kfree(un); + tp_vars->unacked_count--; } /* remove the last (biggest) unacked seqno when list is too large */ - if (tp_vars->common.unacked_count > BATADV_TP_MAX_UNACKED) { - un = list_last_entry(&tp_vars->common.unacked_list, + if (tp_vars->unacked_count > BATADV_TP_MAX_UNACKED) { + un = list_last_entry(&tp_vars->unacked_list, struct batadv_tp_unacked, list); list_del(&un->list); kfree(un); - tp_vars->common.unacked_count--; + tp_vars->unacked_count--; } return true; @@ -1477,7 +1526,7 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_receiver *tp_vars, * @tp_vars: the private data of the current TP meter session */ static void batadv_tp_ack_unordered(struct batadv_tp_receiver *tp_vars) - __must_hold(&tp_vars->common.unacked_lock) + __must_hold(&tp_vars->ack_seqno_lock) { struct batadv_tp_unacked *un, *safe; u32 to_ack; @@ -1485,7 +1534,7 @@ static void batadv_tp_ack_unordered(struct batadv_tp_receiver *tp_vars) /* go through the unacked packet list and possibly ACK them as * well */ - list_for_each_entry_safe(un, safe, &tp_vars->common.unacked_list, list) { + list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) { /* the list is ordered, therefore it is possible to stop as soon * there is a gap between the last acked seqno and the seqno of * the packet under inspection @@ -1493,14 +1542,14 @@ static void batadv_tp_ack_unordered(struct batadv_tp_receiver *tp_vars) if (batadv_seq_before(tp_vars->last_recv, un->seqno)) break; - to_ack = un->seqno + un->len - tp_vars->last_recv; + to_ack = un->seqno + un->len; - if (batadv_seq_before(tp_vars->last_recv, un->seqno + un->len)) - tp_vars->last_recv += to_ack; + if (batadv_seq_before(tp_vars->last_recv, to_ack)) + tp_vars->last_recv = to_ack; list_del(&un->list); kfree(un); - tp_vars->common.unacked_count--; + tp_vars->unacked_count--; } } @@ -1547,9 +1596,9 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, tp_vars->common.bat_priv = bat_priv; kref_init(&tp_vars->common.refcount); - spin_lock_init(&tp_vars->common.unacked_lock); - INIT_LIST_HEAD(&tp_vars->common.unacked_list); - tp_vars->common.unacked_count = 0; + spin_lock_init(&tp_vars->ack_seqno_lock); + INIT_LIST_HEAD(&tp_vars->unacked_list); + tp_vars->unacked_count = 0; kref_get(&tp_vars->common.refcount); timer_setup(&tp_vars->common.timer, batadv_tp_receiver_shutdown, 0); @@ -1609,7 +1658,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, WRITE_ONCE(tp_vars->last_recv_time, jiffies); } - spin_lock_bh(&tp_vars->common.unacked_lock); + spin_lock_bh(&tp_vars->ack_seqno_lock); /* if the packet is a duplicate, it may be the case that an ACK has been * lost. Resend the ACK @@ -1625,7 +1674,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, * not been enqueued correctly */ if (!batadv_tp_handle_out_of_order(tp_vars, seqno, payload_len)) { - spin_unlock_bh(&tp_vars->common.unacked_lock); + spin_unlock_bh(&tp_vars->ack_seqno_lock); goto out; } @@ -1641,7 +1690,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, send_ack: to_ack = tp_vars->last_recv; - spin_unlock_bh(&tp_vars->common.unacked_lock); + spin_unlock_bh(&tp_vars->ack_seqno_lock); /* send the ACK. If the received packet was out of order, the ACK that * is going to be sent is a duplicate (the sender will count them and diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 1c9fb21985f6..49bf2ed9ecdc 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -443,6 +443,54 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, } /** + * batadv_tvlv_hdr_next() - move a tvlv buffer cursor to the next container + * @tvlv_value: cursor into the tvlv buffer, advanced past the returned + * container's content on success + * @tvlv_value_len: remaining length of the tvlv buffer, reduced by the returned + * container's size on success + * + * Parses a single container header at the current cursor position and, if a + * complete container is available, advances the cursor and remaining length + * past it. The returned header stays valid; its content is located at + * (returned header + 1) and is ntohs(hdr->len) bytes long. + * + * Return: pointer to the next tvlv container header, or NULL if no further + * complete container is present in the buffer. + */ +static struct batadv_tvlv_hdr *batadv_tvlv_hdr_next(void **tvlv_value, u16 *tvlv_value_len) +{ + struct batadv_tvlv_hdr *tvlv_hdr; + u16 tvlv_value_cont_len; + void *tvlv_value_cont; + u16 tvlv_len; + + tvlv_value_cont = *tvlv_value; + tvlv_len = *tvlv_value_len; + + if (tvlv_len < sizeof(*tvlv_hdr)) + return NULL; + + tvlv_hdr = tvlv_value_cont; + tvlv_value_cont_len = ntohs(tvlv_hdr->len); + tvlv_value_cont = tvlv_hdr + 1; + tvlv_len -= sizeof(*tvlv_hdr); + + if (tvlv_value_cont_len > tvlv_len) + return NULL; + + /* the next tvlv header is accessed assuming (at least) 2-byte + * alignment, so it must start at an even offset. + */ + if (tvlv_value_cont_len & 1) + return NULL; + + *tvlv_value = (u8 *)tvlv_value_cont + tvlv_value_cont_len; + *tvlv_value_len = tvlv_len - tvlv_value_cont_len; + + return tvlv_hdr; +} + +/** * batadv_tvlv_containers_contain() - check if a tvlv buffer holds a container * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length @@ -457,28 +505,10 @@ static bool batadv_tvlv_containers_contain(void *tvlv_value, u8 version) { struct batadv_tvlv_hdr *tvlv_hdr; - u16 tvlv_value_cont_len; - - while (tvlv_value_len >= sizeof(*tvlv_hdr)) { - tvlv_hdr = tvlv_value; - tvlv_value_cont_len = ntohs(tvlv_hdr->len); - tvlv_value = tvlv_hdr + 1; - tvlv_value_len -= sizeof(*tvlv_hdr); - - if (tvlv_value_cont_len > tvlv_value_len) - break; - - /* the next tvlv header is accessed assuming (at least) 2-byte - * alignment, so it must start at an even offset. - */ - if (tvlv_value_cont_len & 1) - break; + while ((tvlv_hdr = batadv_tvlv_hdr_next(&tvlv_value, &tvlv_value_len))) { if (tvlv_hdr->type == type && tvlv_hdr->version == version) return true; - - tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; - tvlv_value_len -= tvlv_value_cont_len; } return false; @@ -511,20 +541,8 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND; int ret = NET_RX_SUCCESS; - while (tvlv_value_len >= sizeof(*tvlv_hdr)) { - tvlv_hdr = tvlv_value; + while ((tvlv_hdr = batadv_tvlv_hdr_next(&tvlv_value, &tvlv_value_len))) { tvlv_value_cont_len = ntohs(tvlv_hdr->len); - tvlv_value = tvlv_hdr + 1; - tvlv_value_len -= sizeof(*tvlv_hdr); - - if (tvlv_value_cont_len > tvlv_value_len) - break; - - /* the next tvlv header is accessed assuming (at least) 2-byte - * alignment, so it must start at an even offset. - */ - if (tvlv_value_cont_len & 1) - break; tvlv_handler = batadv_tvlv_handler_get(bat_priv, tvlv_hdr->type, @@ -532,11 +550,9 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler, packet_type, orig_node, skb, - tvlv_value, + tvlv_hdr + 1, tvlv_value_cont_len); batadv_tvlv_handler_put(tvlv_handler); - tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; - tvlv_value_len -= tvlv_value_cont_len; } if (packet_type != BATADV_IV_OGM && diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index b1f9f8964c3f..cd12755d21f3 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -214,9 +214,6 @@ struct batadv_wifi_net_device_state { * struct batadv_hard_iface - network device known to batman-adv */ struct batadv_hard_iface { - /** @list: list node for batadv_hardif_list */ - struct list_head list; - /** @if_status: status of the interface for batman-adv */ char if_status; @@ -1335,9 +1332,9 @@ struct batadv_tp_unacked { u32 seqno; /** @len: length of the packet */ - u16 len; + u32 len; - /** @list: list node for &batadv_tp_vars_common.unacked_list */ + /** @list: list node for &batadv_tp_receiver.unacked_list */ struct list_head list; }; @@ -1360,15 +1357,6 @@ struct batadv_tp_vars_common { /** @session: TP session identifier */ u8 session[2]; - /** @unacked_list: list of unacked packets (meta-info only) */ - struct list_head unacked_list; - - /** @unacked_lock: protect unacked_list + &batadv_tp_receiver.last_recv */ - spinlock_t unacked_lock; - - /** @unacked_count: number of unacked entries */ - size_t unacked_count; - /** @refcount: number of context where the object is used */ struct kref refcount; @@ -1482,6 +1470,15 @@ struct batadv_tp_receiver { /** @last_recv_time: time (jiffies) a msg was received */ unsigned long last_recv_time; + + /** @unacked_list: list of unacked packets (meta-info only) */ + struct list_head unacked_list; + + /** @ack_seqno_lock: protect unacked_list + &batadv_tp_receiver.last_recv */ + spinlock_t ack_seqno_lock; + + /** @unacked_count: number of unacked entries */ + size_t unacked_count; }; /** @@ -1679,6 +1676,9 @@ struct batadv_priv { /** @tp_num: number of currently active tp sessions */ atomic_t tp_num; + /** @hardif_generation: generation counter added to netlink hardif dumps */ + unsigned int hardif_generation; + /** @orig_work: work queue callback item for orig node purging */ struct delayed_work orig_work; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index cf374c208732..22e5e5e1a9c4 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -51,7 +51,6 @@ bool fib_rule_matchall(const struct fib_rule *rule) return false; return true; } -EXPORT_SYMBOL_GPL(fib_rule_matchall); int fib_default_rule_add(struct fib_rules_ops *ops, u32 pref, u32 table) @@ -78,7 +77,6 @@ int fib_default_rule_add(struct fib_rules_ops *ops, list_add_tail(&r->list, &ops->rules_list); return 0; } -EXPORT_SYMBOL(fib_default_rule_add); static u32 fib_default_rule_pref(struct fib_rules_ops *ops) { @@ -172,6 +170,7 @@ fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&ops->rules_list); + mutex_init(&ops->lock); ops->fro_net = net; err = __fib_rules_register(ops); @@ -182,7 +181,6 @@ fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) return ops; } -EXPORT_SYMBOL_GPL(fib_rules_register); static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { @@ -207,7 +205,6 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); kfree_rcu(ops, rcu); } -EXPORT_SYMBOL_GPL(fib_rules_unregister); static int uid_range_set(struct fib_kuid_range *range) { @@ -363,7 +360,6 @@ out: return err; } -EXPORT_SYMBOL_GPL(fib_rules_lookup); static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, @@ -391,7 +387,7 @@ static int call_fib_rule_notifiers(struct net *net, .rule = rule, }; - ASSERT_RTNL_NET(net); + lockdep_assert_held(&ops->lock); /* Paired with READ_ONCE() in fib_rules_seq() */ WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1); @@ -423,7 +419,6 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, return err; } -EXPORT_SYMBOL_GPL(fib_rules_dump); unsigned int fib_rules_seq_read(const struct net *net, int family) { @@ -439,7 +434,6 @@ unsigned int fib_rules_seq_read(const struct net *net, int family) return fib_rules_seq; } -EXPORT_SYMBOL_GPL(fib_rules_seq_read); static struct fib_rule *rule_find(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, @@ -740,10 +734,10 @@ errout: return err; } -static int fib_nl2rule_rtnl(struct fib_rule *nlrule, - struct fib_rules_ops *ops, - struct nlattr *tb[], - struct netlink_ext_ack *extack) +static int fib_nl2rule_locked(struct fib_rule *nlrule, + struct fib_rules_ops *ops, + struct nlattr *tb[], + struct netlink_ext_ack *extack) { if (!tb[FRA_PRIORITY]) nlrule->pref = fib_default_rule_pref(ops); @@ -754,12 +748,14 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule, return -EINVAL; } + rcu_read_lock(); + if (tb[FRA_IIFNAME]) { struct net_device *dev; - dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname); + dev = dev_get_by_name_rcu(nlrule->fr_net, nlrule->iifname); if (dev) { - nlrule->iifindex = dev->ifindex; + nlrule->iifindex = READ_ONCE(dev->ifindex); nlrule->iif_is_l3_master = netif_is_l3_master(dev); } } @@ -767,13 +763,15 @@ static int fib_nl2rule_rtnl(struct fib_rule *nlrule, if (tb[FRA_OIFNAME]) { struct net_device *dev; - dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname); + dev = dev_get_by_name_rcu(nlrule->fr_net, nlrule->oifname); if (dev) { - nlrule->oifindex = dev->ifindex; + nlrule->oifindex = READ_ONCE(dev->ifindex); nlrule->oif_is_l3_master = netif_is_l3_master(dev); } } + rcu_read_unlock(); + return 0; } @@ -883,6 +881,7 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *tb[FRA_MAX + 1]; bool user_priority = false; struct fib_rule_hdr *frh; + bool unlock_rtnl = false; frh = nlmsg_payload(nlh, sizeof(*frh)); if (!frh) { @@ -908,10 +907,13 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto errout; - if (!rtnl_held) + if (!rtnl_held && ops->need_rtnl && ops->need_rtnl(net)) { + unlock_rtnl = true; rtnl_net_lock(net); + } + mutex_lock(&ops->lock); - err = fib_nl2rule_rtnl(rule, ops, tb, extack); + err = fib_nl2rule_locked(rule, ops, tb, extack); if (err) goto errout_free; @@ -959,7 +961,7 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref && - rtnl_dereference(r->ctarget) == NULL) { + !rcu_access_pointer(r->ctarget)) { rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; @@ -978,7 +980,8 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, fib_rule_get(rule); - if (!rtnl_held) + mutex_unlock(&ops->lock); + if (unlock_rtnl) rtnl_net_unlock(net); notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); @@ -988,7 +991,8 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, return 0; errout_free: - if (!rtnl_held) + mutex_unlock(&ops->lock); + if (unlock_rtnl) rtnl_net_unlock(net); kfree(rule); errout: @@ -1037,10 +1041,9 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto errout; - if (!rtnl_held) - rtnl_net_lock(net); + mutex_lock(&ops->lock); - err = fib_nl2rule_rtnl(nlrule, ops, tb, extack); + err = fib_nl2rule_locked(nlrule, ops, tb, extack); if (err) goto errout_free; @@ -1055,11 +1058,8 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_free; } - if (ops->delete) { - err = ops->delete(rule); - if (err) - goto errout_free; - } + if (ops->delete) + ops->delete(rule); if (rule->tun_id) ip_tunnel_unneed_metadata(); @@ -1068,7 +1068,7 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, if (rule->action == FR_ACT_GOTO) { ops->nr_goto_rules--; - if (rtnl_dereference(rule->ctarget) == NULL) + if (!rcu_access_pointer(rule->ctarget)) ops->unresolved_rules--; } @@ -1086,7 +1086,7 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, if (&n->list == &ops->rules_list || n->pref != rule->pref) n = NULL; list_for_each_entry(r, &ops->rules_list, list) { - if (rtnl_dereference(r->ctarget) != rule) + if (rcu_access_pointer(r->ctarget) != rule) continue; rcu_assign_pointer(r->ctarget, n); if (!n) @@ -1096,8 +1096,7 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL); - if (!rtnl_held) - rtnl_net_unlock(net); + mutex_unlock(&ops->lock); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid); fib_rule_put(rule); @@ -1107,8 +1106,7 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh, return 0; errout_free: - if (!rtnl_held) - rtnl_net_unlock(net); + mutex_unlock(&ops->lock); kfree(nlrule); errout: rules_ops_put(ops); @@ -1402,24 +1400,30 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct net *net = dev_net(dev); struct fib_rules_ops *ops; - ASSERT_RTNL(); - switch (event) { case NETDEV_REGISTER: - list_for_each_entry(ops, &net->rules_ops, list) + list_for_each_entry(ops, &net->rules_ops, list) { + mutex_lock(&ops->lock); attach_rules(&ops->rules_list, dev); + mutex_unlock(&ops->lock); + } break; case NETDEV_CHANGENAME: list_for_each_entry(ops, &net->rules_ops, list) { + mutex_lock(&ops->lock); detach_rules(&ops->rules_list, dev); attach_rules(&ops->rules_list, dev); + mutex_unlock(&ops->lock); } break; case NETDEV_UNREGISTER: - list_for_each_entry(ops, &net->rules_ops, list) + list_for_each_entry(ops, &net->rules_ops, list) { + mutex_lock(&ops->lock); detach_rules(&ops->rules_list, dev); + mutex_unlock(&ops->lock); + } break; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 96d5945e6a30..aed415d3cd74 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -221,7 +221,7 @@ static void refill_skbs(struct netpoll *np) skb_pool = &np->skb_pool; while (READ_ONCE(skb_pool->qlen) < MAX_SKBS) { - skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC); + skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC | __GFP_NOWARN); if (!skb) break; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 42212970d735..a5e739d32d59 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -76,7 +76,7 @@ fail: struct fib_table *fib_new_table(struct net *net, u32 id) { - struct fib_table *tb, *alias = NULL; + struct fib_table *tb, *new_tb, *alias = NULL; unsigned int h; if (id == 0) @@ -85,14 +85,27 @@ struct fib_table *fib_new_table(struct net *net, u32 id) if (tb) return tb; + if (!check_net(net)) + return NULL; + if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); - if (check_net(net)) - tb = fib_trie_table(id, alias); - if (!tb) + new_tb = fib_trie_table(id, alias); + if (!new_tb) return NULL; + spin_lock(&net->ipv4.fib_table_hash_lock); + + tb = fib_get_table(net, id); + if (tb) { + spin_unlock(&net->ipv4.fib_table_hash_lock); + fib_free_table(new_tb); + return tb; + } + + tb = new_tb; + switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); @@ -106,28 +119,35 @@ struct fib_table *fib_new_table(struct net *net, u32 id) h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); + + spin_unlock(&net->ipv4.fib_table_hash_lock); + return tb; } EXPORT_SYMBOL_GPL(fib_new_table); -/* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { - struct fib_table *tb; + struct fib_table *tb = NULL; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); - head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, head, tb_hlist, - lockdep_rtnl_is_held()) { + + /* fib_table is not destroyed until ip_fib_net_exit() + * except for the merged main/local table. + * fib_unmerge() is called under RTNL, so other readers + * under RTNL (e.g. fib_flush(), fib_info_notify_update()) + * can safely traverse the list with rcu_dereference_raw(). + */ + hlist_for_each_entry_rcu(tb, head, tb_hlist, true) if (tb->tb_id == id) - return tb; - } - return NULL; + break; + + return tb; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ @@ -190,10 +210,9 @@ void fib_flush(struct net *net) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; - struct hlist_node *tmp; struct fib_table *tb; - hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) + hlist_for_each_entry_rcu(tb, head, tb_hlist, true) flushed += fib_table_flush(net, tb, false); } @@ -1019,10 +1038,11 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) .dump_routes = true, .dump_exceptions = true, }; - unsigned int e = 0, s_e, h, s_h; struct hlist_head *head; int dumped = 0, err = 0; struct fib_table *tb; + unsigned int h, s_h; + u32 s_id; rcu_read_lock(); if (cb->strict_check) { @@ -1054,29 +1074,28 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) } s_h = cb->args[0]; - s_e = cb->args[1]; + s_id = cb->args[1]; err = 0; - for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { - e = 0; + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_id = 0) { head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { - if (e < s_e) - goto next; + if (s_id && tb->tb_id != s_id) + continue; + + s_id = 0; if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); + cb->args[1] = tb->tb_id; err = fib_table_dump(tb, skb, cb, &filter); if (err < 0) goto out; dumped = 1; -next: - e++; } } out: - cb->args[1] = e; cb->args[0] = h; unlock: @@ -1565,6 +1584,7 @@ static int __net_init ip_fib_net_init(struct net *net) net->ipv4.sysctl_fib_multipath_hash_fields = FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK; #endif + spin_lock_init(&net->ipv4.fib_table_hash_lock); /* Avoid false sharing : Use at least a full cache line */ size = max_t(size_t, size, L1_CACHE_BYTES); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index e068a5bace73..4edb0dca7be8 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -301,10 +301,12 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0) goto errout; - /* split local/main if they are not already split */ - err = fib_unmerge(net); - if (err) - goto errout; + if (!net->ipv4.fib_has_custom_rules) { + /* split local/main if they are not already split */ + err = fib_unmerge(net); + if (err) + goto errout; + } if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) { if (rule->action == FR_ACT_TO_TBL) { @@ -349,7 +351,7 @@ errout: return err; } -static int fib4_rule_delete(struct fib_rule *rule) +static void fib4_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; @@ -361,8 +363,6 @@ static int fib4_rule_delete(struct fib_rule *rule) if (net->ipv4.fib_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv4.fib_rules_require_fldissect--; - - return 0; } static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, @@ -460,6 +460,11 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) rt_cache_flush(ops->fro_net); } +static bool fib4_rule_need_rtnl(struct net *net) +{ + return !net->ipv4.fib_has_custom_rules; +} + static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .family = AF_INET, .rule_size = sizeof(struct fib4_rule), @@ -473,6 +478,7 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .fill = fib4_rule_fill, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, + .need_rtnl = fib4_rule_need_rtnl, .nlgroup = RTNLGRP_IPV4_RULE, .owner = THIS_MODULE, }; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e11dc86ceda0..d1d342d7148e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2137,8 +2137,7 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist, - lockdep_rtnl_is_held()) + hlist_for_each_entry_rcu(tb, head, tb_hlist, true) __fib_info_notify_update(net, tb, info); } } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b6337a47c141..116ce7cec80e 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1473,6 +1473,7 @@ int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, ci.ifa_valid = INFINITY_LIFE_TIME; if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || + nla_put_u32(skb, IFA_MC_USERS, READ_ONCE(im->users)) < 0 || nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -1494,6 +1495,7 @@ static void inet_ifmcaddr_notify(struct net_device *dev, skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(__be32)) + + nla_total_size(sizeof(u32)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index e9fbab6ad914..2aebaf8297e0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -809,23 +809,18 @@ static int raw_seticmpfilter(struct sock *sk, sockptr_t optval, int optlen) return 0; } -static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen) +static int raw_geticmpfilter(struct sock *sk, sockopt_t *opt) { - int len, ret = -EFAULT; + int len = opt->optlen; - if (get_user(len, optlen)) - goto out; - ret = -EINVAL; if (len < 0) - goto out; + return -EINVAL; if (len > sizeof(struct icmp_filter)) len = sizeof(struct icmp_filter); - ret = -EFAULT; - if (put_user(len, optlen) || - copy_to_user(optval, &raw_sk(sk)->filter, len)) - goto out; - ret = 0; -out: return ret; + opt->optlen = len; + if (copy_to_iter(&raw_sk(sk)->filter, len, &opt->iter_out) != len) + return -EFAULT; + return 0; } static int do_raw_setsockopt(struct sock *sk, int optname, @@ -848,14 +843,13 @@ static int raw_setsockopt(struct sock *sk, int level, int optname, return do_raw_setsockopt(sk, optname, optval, optlen); } -static int do_raw_getsockopt(struct sock *sk, int optname, - char __user *optval, int __user *optlen) +static int do_raw_getsockopt(struct sock *sk, int optname, sockopt_t *opt) { if (optname == ICMP_FILTER) { if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else - return raw_geticmpfilter(sk, optval, optlen); + return raw_geticmpfilter(sk, opt); } return -ENOPROTOOPT; } @@ -863,9 +857,24 @@ static int do_raw_getsockopt(struct sock *sk, int optname, static int raw_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { + sockopt_t opt; + int err; + if (level != SOL_RAW) return ip_getsockopt(sk, level, optname, optval, optlen); - return do_raw_getsockopt(sk, optname, optval, optlen); + + err = sockopt_init_user(&opt, optval, optlen); + if (err) + return err; + + err = do_raw_getsockopt(sk, optname, &opt); + if (err) + return err; + + if (put_user(opt.optlen, optlen)) + return -EFAULT; + + return 0; } static int raw_ioctl(struct sock *sk, int cmd, int *karg) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 70f6cbd4ef73..59248a59358c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -76,6 +76,7 @@ #include <linux/bpf-cgroup.h> #include <linux/uaccess.h> +#include <linux/uio.h> #include <asm/ioctls.h> #include <linux/memblock.h> #include <linux/highmem.h> @@ -2995,14 +2996,13 @@ static int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t opt } int udp_lib_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + sockopt_t *opt) { struct udp_sock *up = udp_sk(sk); int val, len; - if (get_user(len, optlen)) - return -EFAULT; - + len = opt->optlen; + /* keep the check so direct sockopt_t callers stay covered. */ if (len < 0) return -EINVAL; @@ -3037,9 +3037,8 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; } - if (put_user(len, optlen)) - return -EFAULT; - if (copy_to_user(optval, &val, len)) + opt->optlen = len; + if (copy_to_iter(&val, len, &opt->iter_out) != len) return -EFAULT; return 0; } @@ -3047,9 +3046,29 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, static int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { - if (level == SOL_UDP) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return ip_getsockopt(sk, level, optname, optval, optlen); + sockopt_t opt; + int err; + + /* + * keep the old __user pointers, until ip_getsockopt() moves + * to sockopt_t + */ + if (level != SOL_UDP) + return ip_getsockopt(sk, level, optname, optval, optlen); + + err = sockopt_init_user(&opt, optval, optlen); + if (err) + return err; + + err = udp_lib_getsockopt(sk, level, optname, &opt); + if (err) + return err; + + /* optval was written by copy_to_iter() in udp_lib_getsockopt() */ + if (put_user(opt.optlen, optlen)) + return -EFAULT; + + return 0; } /** diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cbe681de3818..f1fe9ede1edb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5264,6 +5264,7 @@ int inet6_fill_ifmcaddr(struct sk_buff *skb, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || + nla_put_u32(skb, IFA_MC_USERS, READ_ONCE(ifmca->mca_users)) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index e1b2b4fa6e18..04dab9329d0c 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -480,15 +480,13 @@ errout: return err; } -static int fib6_rule_delete(struct fib_rule *rule) +static void fib6_rule_delete(struct fib_rule *rule) { struct net *net = rule->fr_net; if (net->ipv6.fib6_rules_require_fldissect && fib_rule_requires_fldissect(rule)) net->ipv6.fib6_rules_require_fldissect--; - - return 0; } static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, @@ -637,21 +635,14 @@ out_fib6_rules_ops: goto out; } -static void __net_exit fib6_rules_net_exit_batch(struct list_head *net_list) +static void __net_exit fib6_rules_net_exit(struct net *net) { - struct net *net; - - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { - fib_rules_unregister(net->ipv6.fib6_rules_ops); - cond_resched(); - } - rtnl_unlock(); + fib_rules_unregister(net->ipv6.fib6_rules_ops); } static struct pernet_operations fib6_rules_net_ops = { .init = fib6_rules_net_init, - .exit_batch = fib6_rules_net_exit_batch, + .exit = fib6_rules_net_exit, }; int __init fib6_rules_init(void) diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 04b811b3be97..774f4c72a6fa 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -908,6 +908,7 @@ static void inet6_ifmcaddr_notify(struct net_device *dev, skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(struct in6_addr)) + + nla_total_size(sizeof(u32)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 15e032194ecc..392e18b97045 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1826,9 +1826,22 @@ static int udpv6_setsockopt(struct sock *sk, int level, int optname, static int udpv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { - if (level == SOL_UDP) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return ipv6_getsockopt(sk, level, optname, optval, optlen); + sockopt_t opt; + int err; + + if (level != SOL_UDP) + return ipv6_getsockopt(sk, level, optname, optval, optlen); + + err = sockopt_init_user(&opt, optval, optlen); + if (err) + return err; + + err = udp_lib_getsockopt(sk, level, optname, &opt); + if (err) + return err; + if (put_user(opt.optlen, optlen)) + return -EFAULT; + return 0; } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 09475007165b..41c2a0b82a8e 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -328,38 +328,35 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW) return pkt_len; - if (info->msg) { - /* If zerocopy is not enabled by 'setsockopt()', we behave as - * there is no MSG_ZEROCOPY flag set. + if (info->msg && (info->msg->msg_flags & MSG_ZEROCOPY)) { + /* If 'info->msg' is not NULL, this is only VIRTIO_VSOCK_OP_RW. + * 'MSG_ZEROCOPY' flag handling here is based on the same flag + * handling from 'tcp_sendmsg_locked()'. */ - if (!sock_flag(sk_vsock(vsk), SOCK_ZEROCOPY)) - info->msg->msg_flags &= ~MSG_ZEROCOPY; + if (info->msg->msg_ubuf) { + uarg = info->msg->msg_ubuf; + can_zcopy = virtio_transport_can_zcopy(t_ops, info, pkt_len); + } else if (sock_flag(sk_vsock(vsk), SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk_vsock(vsk), pkt_len, + NULL, false); + if (!uarg) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } - if (info->msg->msg_flags & MSG_ZEROCOPY) can_zcopy = virtio_transport_can_zcopy(t_ops, info, pkt_len); + if (!can_zcopy) + uarg_to_msgzc(uarg)->zerocopy = 0; + have_uref = true; + } + + /* 'can_zcopy' means that this transmission will be + * in zerocopy way (e.g. using 'frags' array). + */ if (can_zcopy) max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, (MAX_SKB_FRAGS * PAGE_SIZE)); - - if (info->msg->msg_flags & MSG_ZEROCOPY && - info->op == VIRTIO_VSOCK_OP_RW) { - uarg = info->msg->msg_ubuf; - - if (!uarg) { - uarg = msg_zerocopy_realloc(sk_vsock(vsk), - pkt_len, NULL, false); - if (!uarg) { - virtio_transport_put_credit(vvs, pkt_len); - return -ENOMEM; - } - - if (!can_zcopy) - uarg_to_msgzc(uarg)->zerocopy = 0; - - have_uref = true; - } - } } rest_len = pkt_len; diff --git a/tools/net/ynl/pyynl/__init__.py b/tools/net/ynl/pyynl/__init__.py index e69de29bb2d1..d8f59c132ab7 100644 --- a/tools/net/ynl/pyynl/__init__.py +++ b/tools/net/ynl/pyynl/__init__.py @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +""" Python YNL (YAML Netlink) library. """ + +# Re-export the public library API so it can be imported straight from the +# package, e.g. `from pyynl import YnlFamily`. +# pylint: disable=wildcard-import,unused-wildcard-import +from .lib import * +from .lib import __all__ diff --git a/tools/net/ynl/pyynl/cli.py b/tools/net/ynl/pyynl/cli.py index 8275a806cf73..b6a6ce12b4a7 100755 --- a/tools/net/ynl/pyynl/cli.py +++ b/tools/net/ynl/pyynl/cli.py @@ -17,9 +17,7 @@ import textwrap # pylint: disable=no-name-in-module,wrong-import-position sys.path.append(pathlib.Path(__file__).resolve().parent.as_posix()) from lib import YnlFamily, Netlink, NlError, SpecFamily, SpecException, YnlException - -SYS_SCHEMA_DIR='/usr/share/ynl' -RELATIVE_SCHEMA_DIR='../../../../Documentation/netlink' +from lib import list_families # pylint: disable=too-few-public-methods,too-many-locals class Colors: @@ -48,30 +46,6 @@ def term_width(): """ Get terminal width in columns (80 if stdout is not a terminal) """ return shutil.get_terminal_size().columns -def schema_dir(): - """ - Return the effective schema directory, preferring in-tree before - system schema directory. - """ - script_dir = os.path.dirname(os.path.abspath(__file__)) - schema_dir_ = os.path.abspath(f"{script_dir}/{RELATIVE_SCHEMA_DIR}") - if not os.path.isdir(schema_dir_): - schema_dir_ = SYS_SCHEMA_DIR - if not os.path.isdir(schema_dir_): - raise YnlException(f"Schema directory {schema_dir_} does not exist") - return schema_dir_ - -def spec_dir(): - """ - Return the effective spec directory, relative to the effective - schema directory. - """ - spec_dir_ = schema_dir() + '/specs' - if not os.path.isdir(spec_dir_): - raise YnlException(f"Spec directory {spec_dir_} does not exist") - return spec_dir_ - - class YnlEncoder(json.JSONEncoder): """A custom encoder for emitting JSON with ynl-specific instance types""" def default(self, o): @@ -272,9 +246,8 @@ def main(): pprint.pprint(msg, width=term_width(), compact=True) if args.list_families: - for filename in sorted(os.listdir(spec_dir())): - if filename.endswith('.yaml'): - print(filename.removesuffix('.yaml')) + for family in list_families(): + print(family) return if args.no_schema: @@ -284,28 +257,23 @@ def main(): if args.json_text: attrs = json.loads(args.json_text) - if args.family: - spec = f"{spec_dir()}/{args.family}.yaml" - else: - spec = args.spec - if not os.path.isfile(spec): - raise YnlException(f"Spec file {spec} does not exist") + if args.spec and not os.path.isfile(args.spec): + raise YnlException(f"Spec file {args.spec} does not exist") + # Spec/YnlFamily will raise if both or neither spec and family are given if args.validate: + # Force validation even for installed specs (schema=True), unless the + # user explicitly picked a schema or opted out with --no-schema. + schema = True if args.schema is None else args.schema try: - SpecFamily(spec, args.schema) + SpecFamily(args.spec, schema_path=schema, family=args.family) except SpecException as error: print(error) sys.exit(1) return - if args.family: # set behaviour when using installed specs - if args.schema is None and spec.startswith(SYS_SCHEMA_DIR): - args.schema = '' # disable schema validation when installed - if args.process_unknown is None: - args.process_unknown = True - - ynl = YnlFamily(spec, args.schema, args.process_unknown, + ynl = YnlFamily(args.spec, schema=args.schema, family=args.family, + process_unknown=args.process_unknown, recv_size=args.dbg_small_recv) if args.dbg_small_recv: ynl.set_recv_dbg(True) diff --git a/tools/net/ynl/pyynl/lib/__init__.py b/tools/net/ynl/pyynl/lib/__init__.py index be741985ae4e..aa4263c8cba9 100644 --- a/tools/net/ynl/pyynl/lib/__init__.py +++ b/tools/net/ynl/pyynl/lib/__init__.py @@ -5,12 +5,13 @@ from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \ SpecFamily, SpecOperation, SpecSubMessage, SpecSubMessageFormat, \ SpecException +from .specdir import list_families from .ynl import YnlFamily, Netlink, NlError, NlPolicy, YnlException from .doc_generator import YnlDocGenerator __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet", "SpecFamily", "SpecOperation", "SpecSubMessage", "SpecSubMessageFormat", - "SpecException", + "SpecException", "list_families", "YnlFamily", "Netlink", "NlError", "NlPolicy", "YnlException", "YnlDocGenerator"] diff --git a/tools/net/ynl/pyynl/lib/nlspec.py b/tools/net/ynl/pyynl/lib/nlspec.py index 0469a0e270d0..b4ec59814ab1 100644 --- a/tools/net/ynl/pyynl/lib/nlspec.py +++ b/tools/net/ynl/pyynl/lib/nlspec.py @@ -12,6 +12,8 @@ import importlib import os import yaml as pyyaml +from .specdir import find_spec, SYS_SCHEMA_DIR + class SpecException(Exception): """Netlink spec exception. @@ -444,7 +446,23 @@ class SpecFamily(SpecElement): except AttributeError: _yaml_loader = pyyaml.SafeLoader - def __init__(self, spec_path, schema_path=None, exclude_ops=None): + def __init__(self, spec_path=None, schema_path=None, exclude_ops=None, + family=None): + # schema_path selects how the spec is validated: + # None -- no preference: validate against the default schema, + # but trust (skip) installed specs selected by family= + # True -- always validate against the default schema + # path -- validate against this schema + # '' -- do not validate + if (spec_path is None) == (family is None): + raise ValueError("Specify exactly one of spec path or family name") + if family is not None: + spec_path = find_spec(family) + # Installed specs are assumed correct, so skip schema validation + # to save cycles unless the caller asked to validate. + if schema_path is None and spec_path.startswith(SYS_SCHEMA_DIR): + schema_path = '' + with open(spec_path, "r", encoding='utf-8') as stream: prefix = '# SPDX-License-Identifier: ' first = stream.readline().strip() @@ -465,7 +483,7 @@ class SpecFamily(SpecElement): self.proto = self.yaml.get('protocol', 'genetlink') self.msg_id_model = self.yaml['operations'].get('enum-model', 'unified') - if schema_path is None: + if schema_path is None or schema_path is True: schema_path = os.path.dirname(os.path.dirname(spec_path)) + f'/{self.proto}.yaml' if schema_path: with open(schema_path, "r", encoding='utf-8') as stream: diff --git a/tools/net/ynl/pyynl/lib/specdir.py b/tools/net/ynl/pyynl/lib/specdir.py new file mode 100644 index 000000000000..fcea9b9fb7b0 --- /dev/null +++ b/tools/net/ynl/pyynl/lib/specdir.py @@ -0,0 +1,51 @@ +# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause + +""" +Locating YNL spec and schema files on disk. + +Resolves the directory holding the YAML specs (preferring an in-tree copy +over the installed system path) and maps family names to spec files. +""" + +import os + +SYS_SCHEMA_DIR='/usr/share/ynl' +RELATIVE_SCHEMA_DIR='../../../../../Documentation/netlink' + + +def schema_dir(): + """ + Return the effective schema directory, preferring in-tree before + system schema directory. + """ + script_dir = os.path.dirname(os.path.abspath(__file__)) + schema_dir_ = os.path.abspath(f"{script_dir}/{RELATIVE_SCHEMA_DIR}") + if not os.path.isdir(schema_dir_): + schema_dir_ = SYS_SCHEMA_DIR + if not os.path.isdir(schema_dir_): + raise FileNotFoundError(f"Schema directory {schema_dir_} does not exist") + return schema_dir_ + +def spec_dir(): + """ + Return the effective spec directory, relative to the effective + schema directory. + """ + spec_dir_ = schema_dir() + '/specs' + if not os.path.isdir(spec_dir_): + raise FileNotFoundError(f"Spec directory {spec_dir_} does not exist") + return spec_dir_ + + +def find_spec(family): + """ Return the path to the YAML spec file for a family by name. """ + spec = f"{spec_dir()}/{family}.yaml" + if not os.path.isfile(spec): + raise FileNotFoundError(f"Spec for family '{family}' not found at {spec}") + return spec + + +def list_families(): + """ Return the sorted names of all families with an installed spec. """ + return sorted(f.removesuffix('.yaml') + for f in os.listdir(spec_dir()) if f.endswith('.yaml')) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 092d132edec1..8682bf588e1f 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -661,6 +661,14 @@ class YnlFamily(SpecFamily): """ YNL family -- a Netlink interface built from a YAML spec. + The spec can be selected either by file path (def_path=) or, when it + ships in a well-known location, by family name (family="xyz"); exactly + one of the two must be given. For example: + + from pyynl import YnlFamily + + ynl = YnlFamily(family="netdev") + Primary use of the class is to execute Netlink commands: ynl.<op_name>(attrs, ...) @@ -691,11 +699,16 @@ class YnlFamily(SpecFamily): ynl.get_policy(op_name, mode) -- query kernel policy for an op """ - def __init__(self, def_path, schema=None, process_unknown=False, - recv_size=0): - super().__init__(def_path, schema) + def __init__(self, def_path=None, schema=None, process_unknown=None, + recv_size=0, family=None): + super().__init__(def_path, schema, family=family) self.include_raw = False + # Specs from /usr (selected by family=) have a higher chance of being + # stale, default to ignoring unknown attrs. In-tree users, and users + # who bundle the spec need to make a conscious decision. + if process_unknown is None: + process_unknown = family is not None self.process_unknown = process_unknown try: diff --git a/tools/net/ynl/tests/ethtool.py b/tools/net/ynl/tests/ethtool.py index db3b62c652e7..0ee0c8e87686 100755 --- a/tools/net/ynl/tests/ethtool.py +++ b/tools/net/ynl/tests/ethtool.py @@ -11,12 +11,10 @@ import pathlib import pprint import sys import re -import os # pylint: disable=no-name-in-module,wrong-import-position sys.path.append(pathlib.Path(__file__).resolve().parent.parent.joinpath('pyynl').as_posix()) # pylint: disable=import-error -from cli import schema_dir, spec_dir from lib import YnlFamily @@ -173,10 +171,7 @@ def main(): args = parser.parse_args() - spec = os.path.join(spec_dir(), 'ethtool.yaml') - schema = os.path.join(schema_dir(), 'genetlink-legacy.yaml') - - ynl = YnlFamily(spec, schema, recv_size=args.dbg_small_recv) + ynl = YnlFamily(family='ethtool', recv_size=args.dbg_small_recv) if args.dbg_small_recv: ynl.set_recv_dbg(True) diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c index 6eb9096d084c..477aedbb01ba 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -1164,8 +1164,8 @@ static int __send_pkts(struct ifobject *ifobject, struct xsk_socket_info *xsk, bool test_timeout) { u32 i, idx = 0, valid_pkts = 0, valid_frags = 0, buffer_len; + struct xsk_umem_info *umem = ifobject->xsk_arr[0].umem_real; struct pkt_stream *pkt_stream = xsk->pkt_stream; - struct xsk_umem_info *umem = xsk->umem; bool use_poll = ifobject->use_poll; struct pollfd fds = { }; int ret; @@ -1514,7 +1514,7 @@ static int thread_common_ops_tx(struct test_spec *test, struct ifobject *ifobjec umem_tx->base_addr = 0; umem_tx->next_buffer = 0; - ret = xsk_configure(test, ifobject, umem_tx, true); + ret = xsk_configure(test, ifobject, umem_rx, true); if (ret) return ret; ifobject->xsk = &ifobject->xsk_arr[0]; diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index cd7e080e6f84..571732198b93 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -21,6 +21,8 @@ from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx ETH_RSS_HASH_TOP = 1 # Must match RPS_MAX_CPUS in toeplitz.c RPS_MAX_CPUS = 16 +# Cap Rx queues so IRQ pinning leaves free CPUs in the RPS_MAX_CPUS range +QUEUE_CAP = 8 def _check_rps_and_rfs_not_configured(cfg): @@ -48,6 +50,25 @@ def _get_cpu_for_irq(irq): return int(data) +def _cap_queue_count(cfg): + ehdr = {"header": {"dev-index": cfg.ifindex}} + chans = cfg.ethnl.channels_get(ehdr) + + config = {} + restore = {} + for key in ("combined-count", "rx-count"): + cur = chans.get(key, 0) + if cur > QUEUE_CAP: + config[key] = QUEUE_CAP + restore[key] = cur + + if not config: + return + + cfg.ethnl.channels_set(ehdr | config) + defer(cfg.ethnl.channels_set, ehdr | restore) + + def _get_irq_cpus(cfg): """ Read the list of IRQs for the device Rx queues. @@ -177,6 +198,7 @@ def test(cfg, proto_flag, ipver, grp): ] if grp: + _cap_queue_count(cfg) _check_rps_and_rfs_not_configured(cfg) if grp == "rss": irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)]) diff --git a/tools/testing/selftests/net/getsockopt_iter.c b/tools/testing/selftests/net/getsockopt_iter.c index 209569354d0e..fe5a5268bc34 100644 --- a/tools/testing/selftests/net/getsockopt_iter.c +++ b/tools/testing/selftests/net/getsockopt_iter.c @@ -11,6 +11,8 @@ * that always reports the required buffer length back via optlen, * even when the user buffer is too small to receive any group bits. * - vsock: SO_VM_SOCKETS_BUFFER_SIZE covers the u64 path. + * - raw: ICMP_FILTER covers a fixed-size struct payload that clamps + * the length down on a short buffer instead of failing. * * Author: Breno Leitao <leitao@debian.org> */ @@ -24,12 +26,20 @@ #include <linux/rtnetlink.h> #include <linux/time_types.h> #include <linux/vm_sockets.h> +#include <linux/icmp.h> +#include <netinet/in.h> #include <sys/socket.h> #include "kselftest_harness.h" #ifndef AF_VSOCK #define AF_VSOCK 40 #endif +#ifndef SOL_RAW +#define SOL_RAW 255 +#endif +#ifndef ICMP_FILTER +#define ICMP_FILTER 1 +#endif /* ---------- netlink ---------- */ @@ -297,4 +307,91 @@ TEST_F(vsock, connect_timeout_old_exact) ASSERT_EQ(sizeof(tv), optlen); } +/* ---------- raw (ipv4) ---------- */ + +FIXTURE(raw) +{ + int fd; +}; + +FIXTURE_SETUP(raw) +{ + struct icmp_filter filt = { .data = 0xdeadbeef }; + + self->fd = socket(AF_INET, SOCK_RAW, IPPROTO_ICMP); + if (self->fd < 0) + SKIP(return, "SOCK_RAW/ICMP socket: %s", strerror(errno)); + + if (setsockopt(self->fd, SOL_RAW, ICMP_FILTER, &filt, sizeof(filt)) < 0) + SKIP(return, "set ICMP_FILTER: %s", strerror(errno)); +} + +FIXTURE_TEARDOWN(raw) +{ + if (self->fd >= 0) + close(self->fd); +} + +TEST_F(raw, icmpfilter_exact) +{ + struct icmp_filter filt = {}; + socklen_t optlen = sizeof(filt); + + ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER, + &filt, &optlen)); + ASSERT_EQ(sizeof(filt), optlen); + ASSERT_EQ(0xdeadbeef, filt.data); +} + +TEST_F(raw, icmpfilter_oversize_clamped) +{ + char buf[16] = {}; + socklen_t optlen = sizeof(buf); + + ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER, + buf, &optlen)); + ASSERT_EQ(sizeof(struct icmp_filter), optlen); +} + +/* Unlike the int/u64 options above, ICMP_FILTER clamps the length down + * to the user buffer instead of returning EINVAL: a short buffer + * succeeds and reports the truncated length back via optlen. + */ +TEST_F(raw, icmpfilter_undersize_clamped) +{ + char buf[2] = {}; + socklen_t optlen = sizeof(buf); + + ASSERT_EQ(0, getsockopt(self->fd, SOL_RAW, ICMP_FILTER, + buf, &optlen)); + ASSERT_EQ(sizeof(buf), optlen); +} + +TEST_F(raw, icmpfilter_wrong_proto) +{ + struct icmp_filter filt; + socklen_t optlen = sizeof(filt); + int fd; + + fd = socket(AF_INET, SOCK_RAW, IPPROTO_UDP); + if (fd < 0) + SKIP(return, "SOCK_RAW/UDP socket: %s", strerror(errno)); + + ASSERT_EQ(-1, getsockopt(fd, SOL_RAW, ICMP_FILTER, &filt, &optlen)); + ASSERT_EQ(EOPNOTSUPP, errno); + close(fd); +} + +TEST_F(raw, bad_optname) +{ + socklen_t optlen; + int val; + + optlen = sizeof(val); + + ASSERT_EQ(-1, getsockopt(self->fd, SOL_RAW, 0x7fff, &val, &optlen)); + ASSERT_EQ(ENOPROTOOPT, errno); + ASSERT_EQ(sizeof(val), optlen); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index b3827b43782b..d389a965d8f1 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -70,12 +70,27 @@ ksft_exit_status_merge() $ksft_xfail $ksft_pass $ksft_skip $ksft_fail } +timestamp_ms() +{ + local now=$(date -u +%s:%N) + local seconds=${now%:*} + local nanoseconds=${now#*:} + + if [[ $nanoseconds =~ ^[0-9]+$ ]]; then + nanoseconds=${nanoseconds:0:9} + else + nanoseconds=0 + fi + + echo $((seconds * 1000 + 10#$nanoseconds / 1000000)) +} + loopy_wait() { local sleep_cmd=$1; shift local timeout_ms=$1; shift - local start_time="$(date -u +%s%3N)" + local start_time=$(timestamp_ms) while true do local out @@ -84,7 +99,7 @@ loopy_wait() return 0 fi - local current_time="$(date -u +%s%3N)" + local current_time=$(timestamp_ms) if ((current_time - start_time > timeout_ms)); then echo -n "$out" return 1 diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py index 3622413d793d..0c67c7c00d84 100755 --- a/tools/testing/selftests/net/rtnetlink.py +++ b/tools/testing/selftests/net/rtnetlink.py @@ -2,27 +2,106 @@ # SPDX-License-Identifier: GPL-2.0 import socket +import struct import time -from lib.py import bkg, ip, ksft_exit, ksft_run, ksft_ge, ksft_true, KsftSkipEx +from lib.py import bkg, ip, ksft_exit, ksft_run, ksft_eq, ksft_ge, ksft_true, KsftSkipEx from lib.py import CmdExitFailure, NetNS, NetNSEnter, RtnlAddrFamily IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01' +IPV4_TEST_MULTICAST = b'\xef\x01\x01\x01' +IPV6_TEST_MULTICAST = bytes.fromhex('ff020000000000000000000000000123') + + +def _users_for(rtnl: RtnlAddrFamily, family: int, grp: bytes, ifindex: int): + """Return mc-users for grp on ifindex, or 0 if absent.""" + + addrs = rtnl.getmulticast({"ifa-family": family}, dump=True) + matches = [addr for addr in addrs + if addr['multicast'] == grp and addr['ifa-index'] == ifindex] + if not matches: + return 0 + if 'mc-users' not in matches[0]: + return None + + return matches[0]['mc-users'] + def dump_mcaddr_check() -> None: """ - Verify that at least one interface has the IPv4 all-hosts multicast address. - At least the loopback interface should have this address. + Verify IPv4 multicast addresses and their user counts in RTM_GETMULTICAST. + """ + + with NetNS() as ns: + with NetNSEnter(str(ns)): + ip("link set lo up") + rtnl = RtnlAddrFamily() + lo_idx = socket.if_nametoindex('lo') + addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True) + + all_host_multicasts = [ + addr for addr in addresses + if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST + ] + + ksft_ge(len(all_host_multicasts), 1, + "No interface found with the IPv4 all-hosts multicast address") + + mreq = IPV4_TEST_MULTICAST + socket.inet_aton('127.0.0.1') + before = _users_for(rtnl, socket.AF_INET, IPV4_TEST_MULTICAST, lo_idx) + if before is None: + raise KsftSkipEx("kernel does not expose IFA_MC_USERS") + + s1 = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + s2 = socket.socket(socket.AF_INET, socket.SOCK_DGRAM) + try: + s1.setsockopt(socket.IPPROTO_IP, socket.IP_ADD_MEMBERSHIP, mreq) + s2.setsockopt(socket.IPPROTO_IP, socket.IP_ADD_MEMBERSHIP, mreq) + + after_join = _users_for(rtnl, socket.AF_INET, + IPV4_TEST_MULTICAST, lo_idx) + if after_join is None: + raise KsftSkipEx("kernel does not expose IFA_MC_USERS") + ksft_eq(after_join - before, 2, + f"users delta != 2 after two joins " + f"(before={before}, after={after_join})") + finally: + s1.close() + s2.close() + + +def dump_mcaddr6_check() -> None: + """ + Verify IPv6 multicast addresses and their user counts in RTM_GETMULTICAST. """ - rtnl = RtnlAddrFamily() - addresses = rtnl.getmulticast({"ifa-family": socket.AF_INET}, dump=True) + with NetNS() as ns: + with NetNSEnter(str(ns)): + ip("link set lo up") + rtnl = RtnlAddrFamily() + lo_idx = socket.if_nametoindex('lo') + before = _users_for(rtnl, socket.AF_INET6, + IPV6_TEST_MULTICAST, lo_idx) + if before is None: + raise KsftSkipEx("kernel does not expose IFA_MC_USERS for IPv6") + + mreq = IPV6_TEST_MULTICAST + struct.pack('=I', lo_idx) + s1 = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) + s2 = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) + try: + s1.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_JOIN_GROUP, mreq) + s2.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_JOIN_GROUP, mreq) - all_host_multicasts = [ - addr for addr in addresses if addr['multicast'] == IPV4_ALL_HOSTS_MULTICAST - ] + after_join = _users_for(rtnl, socket.AF_INET6, + IPV6_TEST_MULTICAST, lo_idx) + if after_join is None: + raise KsftSkipEx("kernel does not expose IFA_MC_USERS for IPv6") + ksft_eq(after_join - before, 2, + f"IPv6 users delta != 2 after two joins " + f"(before={before}, after={after_join})") + finally: + s1.close() + s2.close() - ksft_ge(len(all_host_multicasts), 1, - "No interface found with the IPv4 all-hosts multicast address") def ipv4_devconf_notify() -> None: """ @@ -56,7 +135,7 @@ def ipv4_devconf_notify() -> None: f"No 'forwarding on' notificiation found for interface {ifname}") def main() -> None: - ksft_run([dump_mcaddr_check, ipv4_devconf_notify]) + ksft_run([dump_mcaddr_check, dump_mcaddr6_check, ipv4_devconf_notify]) ksft_exit() if __name__ == "__main__": |
