diff options
Diffstat (limited to 'net')
37 files changed, 364 insertions, 350 deletions
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 10f7edfb176e..c2c986746d0b 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -69,7 +69,7 @@ int batadv_skb_head_push(struct sk_buff *skb, unsigned int len) int result; /* TODO: We must check if we can release all references to non-payload - * data using skb_header_release in our skbs to allow skb_cow_header to + * data using __skb_header_release in our skbs to allow skb_cow_header to * work optimally. This means that those skbs are not allowed to read * or write any data which is before the current position of skb->data * after that call and thus allow other skbs with the same data buffer diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 7970f8540cbb..66cd98772051 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -102,6 +102,9 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd) else ret = br_del_if(br, dev); + if (!ret) + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_MASTER, GFP_KERNEL); + return ret; } diff --git a/net/core/dev.c b/net/core/dev.c index 588b473194a8..97abddd9039a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7994,7 +7994,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned int txqs, unsigned int rxqs) { struct net_device *dev; - size_t alloc_size; + unsigned int alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); diff --git a/net/dsa/Makefile b/net/dsa/Makefile index fcce25da937c..2e7ac8bab19d 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,6 +1,6 @@ # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o dsa2.o legacy.o port.o slave.o switch.o +dsa_core-y += dsa.o dsa2.o legacy.o master.o port.o slave.o switch.o # tagging formats dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 03c58b0eb082..81c852e32821 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -112,34 +112,6 @@ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) return ops; } -int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp) -{ - struct dsa_switch *ds = cpu_dp->ds; - struct net_device *master; - struct ethtool_ops *cpu_ops; - - master = cpu_dp->netdev; - - cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); - if (!cpu_ops) - return -ENOMEM; - - memcpy(&cpu_dp->ethtool_ops, master->ethtool_ops, - sizeof(struct ethtool_ops)); - cpu_dp->orig_ethtool_ops = master->ethtool_ops; - memcpy(cpu_ops, &cpu_dp->ethtool_ops, - sizeof(struct ethtool_ops)); - dsa_cpu_port_ethtool_init(cpu_ops); - master->ethtool_ops = cpu_ops; - - return 0; -} - -void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp) -{ - cpu_dp->netdev->ethtool_ops = cpu_dp->orig_ethtool_ops; -} - void dsa_cpu_dsa_destroy(struct dsa_port *port) { struct device_node *port_dn = port->dn; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 873af0108e24..dcccaebde708 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -433,18 +433,17 @@ static int dsa_dst_apply(struct dsa_switch_tree *dst) return err; } - if (dst->cpu_dp) { - err = dsa_cpu_port_ethtool_setup(dst->cpu_dp); - if (err) - return err; - } - /* If we use a tagging format that doesn't have an ethertype * field, make sure that all packets from this point on get * sent to the tag format's receive function. */ wmb(); dst->cpu_dp->netdev->dsa_ptr = dst; + + err = dsa_master_ethtool_setup(dst->cpu_dp->netdev); + if (err) + return err; + dst->applied = true; return 0; @@ -458,6 +457,8 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) if (!dst->applied) return; + dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype @@ -474,10 +475,7 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst) dsa_ds_unapply(dst, ds); } - if (dst->cpu_dp) { - dsa_cpu_port_ethtool_restore(dst->cpu_dp); - dst->cpu_dp = NULL; - } + dst->cpu_dp = NULL; pr_info("DSA: tree %d unapplied\n", dst->tree); dst->applied = false; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 9c3eeb72462d..9803952a5b40 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -97,8 +97,6 @@ struct dsa_slave_priv { int dsa_cpu_dsa_setup(struct dsa_port *port); void dsa_cpu_dsa_destroy(struct dsa_port *dport); const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); -int dsa_cpu_port_ethtool_setup(struct dsa_port *cpu_dp); -void dsa_cpu_port_ethtool_restore(struct dsa_port *cpu_dp); bool dsa_schedule_work(struct work_struct *work); /* legacy.c */ @@ -112,6 +110,10 @@ int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); +/* master.c */ +int dsa_master_ethtool_setup(struct net_device *dev); +void dsa_master_ethtool_restore(struct net_device *dev); + /* port.c */ int dsa_port_set_state(struct dsa_port *dp, u8 state, struct switchdev_trans *trans); @@ -126,6 +128,7 @@ int dsa_port_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid); int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid); +int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data); int dsa_port_mdb_add(struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans); @@ -139,7 +142,6 @@ int dsa_port_vlan_del(struct dsa_port *dp, /* slave.c */ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); -void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops); int dsa_slave_create(struct dsa_port *port, const char *name); void dsa_slave_destroy(struct net_device *slave_dev); int dsa_slave_suspend(struct net_device *slave_dev); diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 91e6f7981d39..ae505d8e4417 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -206,10 +206,6 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, netdev_err(master, "[%d] : can't configure CPU and DSA ports\n", index); - ret = dsa_cpu_port_ethtool_setup(ds->dst->cpu_dp); - if (ret) - return ret; - return 0; } @@ -606,7 +602,7 @@ static int dsa_setup_dst(struct dsa_switch_tree *dst, struct net_device *dev, wmb(); dev->dsa_ptr = dst; - return 0; + return dsa_master_ethtool_setup(dst->cpu_dp->netdev); } static int dsa_probe(struct platform_device *pdev) @@ -671,6 +667,8 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) { int i; + dsa_master_ethtool_restore(dst->cpu_dp->netdev); + dst->cpu_dp->netdev->dsa_ptr = NULL; /* If we used a tagging format that doesn't have an ethertype @@ -686,8 +684,6 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } - dsa_cpu_port_ethtool_restore(dst->cpu_dp); - dev_put(dst->cpu_dp->netdev); } diff --git a/net/dsa/master.c b/net/dsa/master.c new file mode 100644 index 000000000000..5e5147ec5a44 --- /dev/null +++ b/net/dsa/master.c @@ -0,0 +1,120 @@ +/* + * Handling of a master device, switching frames via its switch fabric CPU port + * + * Copyright (c) 2017 Savoir-faire Linux Inc. + * Vivien Didelot <vivien.didelot@savoirfairelinux.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "dsa_priv.h" + +static void dsa_master_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *port = dst->cpu_dp; + struct dsa_switch *ds = port->ds; + const struct ethtool_ops *ops = port->orig_ethtool_ops; + int count = 0; + + if (ops && ops->get_sset_count && ops->get_ethtool_stats) { + count = ops->get_sset_count(dev, ETH_SS_STATS); + ops->get_ethtool_stats(dev, stats, data); + } + + if (ds->ops->get_ethtool_stats) + ds->ops->get_ethtool_stats(ds, port->index, data + count); +} + +static int dsa_master_get_sset_count(struct net_device *dev, int sset) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *port = dst->cpu_dp; + struct dsa_switch *ds = port->ds; + const struct ethtool_ops *ops = port->orig_ethtool_ops; + int count = 0; + + if (ops && ops->get_sset_count) + count += ops->get_sset_count(dev, sset); + + if (sset == ETH_SS_STATS && ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds); + + return count; +} + +static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, + uint8_t *data) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *port = dst->cpu_dp; + struct dsa_switch *ds = port->ds; + const struct ethtool_ops *ops = port->orig_ethtool_ops; + int len = ETH_GSTRING_LEN; + int mcount = 0, count; + unsigned int i; + uint8_t pfx[4]; + uint8_t *ndata; + + snprintf(pfx, sizeof(pfx), "p%.2d", port->index); + /* We do not want to be NULL-terminated, since this is a prefix */ + pfx[sizeof(pfx) - 1] = '_'; + + if (ops && ops->get_sset_count && ops->get_strings) { + mcount = ops->get_sset_count(dev, ETH_SS_STATS); + ops->get_strings(dev, stringset, data); + } + + if (stringset == ETH_SS_STATS && ds->ops->get_strings) { + ndata = data + mcount * len; + /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle + * the output after to prepend our CPU port prefix we + * constructed earlier + */ + ds->ops->get_strings(ds, port->index, ndata); + count = ds->ops->get_sset_count(ds); + for (i = 0; i < count; i++) { + memmove(ndata + (i * len + sizeof(pfx)), + ndata + i * len, len - sizeof(pfx)); + memcpy(ndata + i * len, pfx, sizeof(pfx)); + } + } +} + +int dsa_master_ethtool_setup(struct net_device *dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *port = dst->cpu_dp; + struct dsa_switch *ds = port->ds; + struct ethtool_ops *ops; + + ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + port->orig_ethtool_ops = dev->ethtool_ops; + if (port->orig_ethtool_ops) + memcpy(ops, port->orig_ethtool_ops, sizeof(*ops)); + + ops->get_sset_count = dsa_master_get_sset_count; + ops->get_ethtool_stats = dsa_master_get_ethtool_stats; + ops->get_strings = dsa_master_get_strings; + + dev->ethtool_ops = ops; + + return 0; +} + +void dsa_master_ethtool_restore(struct net_device *dev) +{ + struct dsa_switch_tree *dst = dev->dsa_ptr; + struct dsa_port *port = dst->cpu_dp; + + dev->ethtool_ops = port->orig_ethtool_ops; + port->orig_ethtool_ops = NULL; +} diff --git a/net/dsa/port.c b/net/dsa/port.c index 659676ba3f8b..76d43a82d397 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -173,6 +173,17 @@ int dsa_port_fdb_del(struct dsa_port *dp, const unsigned char *addr, return dsa_port_notify(dp, DSA_NOTIFIER_FDB_DEL, &info); } +int dsa_port_fdb_dump(struct dsa_port *dp, dsa_fdb_dump_cb_t *cb, void *data) +{ + struct dsa_switch *ds = dp->ds; + int port = dp->index; + + if (!ds->ops->port_fdb_dump) + return -EOPNOTSUPP; + + return ds->ops->port_fdb_dump(ds, port, cb, data); +} + int dsa_port_mdb_add(struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 2afa99506f8b..02ace7d462c4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -263,16 +263,11 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, }; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_port *dp = p->dp; - struct dsa_switch *ds = dp->ds; int err; - if (!ds->ops->port_fdb_dump) - return -EOPNOTSUPP; - - err = ds->ops->port_fdb_dump(ds, dp->index, - dsa_slave_port_fdb_do_dump, - &dump); + err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); *idx = dump.idx; + return err; } @@ -385,10 +380,12 @@ static int dsa_slave_port_attr_get(struct net_device *dev, return 0; } -static inline netdev_tx_t dsa_netpoll_send_skb(struct dsa_slave_priv *p, - struct sk_buff *skb) +static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER + struct dsa_slave_priv *p = netdev_priv(dev); + if (p->netpoll) netpoll_send_skb(p->netpoll, skb); #else @@ -422,7 +419,7 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) - return dsa_netpoll_send_skb(p, nskb); + return dsa_slave_netpoll_send_skb(dev, nskb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType @@ -567,79 +564,6 @@ static void dsa_slave_get_strings(struct net_device *dev, } } -static void dsa_cpu_port_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - s8 cpu_port = cpu_dp->index; - int count = 0; - - if (cpu_dp->ethtool_ops.get_sset_count) { - count = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - cpu_dp->ethtool_ops.get_ethtool_stats(dev, stats, data); - } - - if (ds->ops->get_ethtool_stats) - ds->ops->get_ethtool_stats(ds, cpu_port, data + count); -} - -static int dsa_cpu_port_get_sset_count(struct net_device *dev, int sset) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - int count = 0; - - if (cpu_dp->ethtool_ops.get_sset_count) - count += cpu_dp->ethtool_ops.get_sset_count(dev, sset); - - if (sset == ETH_SS_STATS && ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds); - - return count; -} - -static void dsa_cpu_port_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) -{ - struct dsa_switch_tree *dst = dev->dsa_ptr; - struct dsa_port *cpu_dp = dsa_get_cpu_port(dst); - struct dsa_switch *ds = cpu_dp->ds; - s8 cpu_port = cpu_dp->index; - int len = ETH_GSTRING_LEN; - int mcount = 0, count; - unsigned int i; - uint8_t pfx[4]; - uint8_t *ndata; - - snprintf(pfx, sizeof(pfx), "p%.2d", cpu_port); - /* We do not want to be NULL-terminated, since this is a prefix */ - pfx[sizeof(pfx) - 1] = '_'; - - if (cpu_dp->ethtool_ops.get_sset_count) { - mcount = cpu_dp->ethtool_ops.get_sset_count(dev, ETH_SS_STATS); - cpu_dp->ethtool_ops.get_strings(dev, stringset, data); - } - - if (stringset == ETH_SS_STATS && ds->ops->get_strings) { - ndata = data + mcount * len; - /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle - * the output after to prepend our CPU port prefix we - * constructed earlier - */ - ds->ops->get_strings(ds, cpu_port, ndata); - count = ds->ops->get_sset_count(ds); - for (i = 0; i < count; i++) { - memmove(ndata + (i * len + sizeof(pfx)), - ndata + i * len, len - sizeof(pfx)); - memcpy(ndata + i * len, pfx, sizeof(pfx)); - } - } -} - static void dsa_slave_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, uint64_t *data) @@ -809,9 +733,9 @@ static int dsa_slave_get_phys_port_name(struct net_device *dev, } static struct dsa_mall_tc_entry * -dsa_slave_mall_tc_entry_find(struct dsa_slave_priv *p, - unsigned long cookie) +dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { + struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) @@ -893,7 +817,7 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, if (!ds->ops->port_mirror_del) return; - mall_tc_entry = dsa_slave_mall_tc_entry_find(p, cls->cookie); + mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; @@ -976,13 +900,6 @@ static void dsa_slave_get_stats64(struct net_device *dev, } } -void dsa_cpu_port_ethtool_init(struct ethtool_ops *ops) -{ - ops->get_sset_count = dsa_cpu_port_get_sset_count; - ops->get_ethtool_stats = dsa_cpu_port_get_ethtool_stats; - ops->get_strings = dsa_cpu_port_get_strings; -} - static int dsa_slave_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *nfc, u32 *rule_locs) { @@ -1107,10 +1024,9 @@ static int dsa_slave_fixed_link_update(struct net_device *dev, } /* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct dsa_slave_priv *p, - struct net_device *slave_dev, - int addr) +static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { + struct dsa_slave_priv *p = netdev_priv(slave_dev); struct dsa_switch *ds = p->dp->ds; p->phy = mdiobus_get_phy(ds->slave_mii_bus, addr); @@ -1126,9 +1042,9 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p, p->phy_interface); } -static int dsa_slave_phy_setup(struct dsa_slave_priv *p, - struct net_device *slave_dev) +static int dsa_slave_phy_setup(struct net_device *slave_dev) { + struct dsa_slave_priv *p = netdev_priv(slave_dev); struct dsa_switch *ds = p->dp->ds; struct device_node *phy_dn, *port_dn; bool phy_is_fixed = false; @@ -1168,7 +1084,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, */ if (!phy_is_fixed && phy_id >= 0 && (ds->phys_mii_mask & (1 << phy_id))) { - ret = dsa_slave_phy_connect(p, slave_dev, phy_id); + ret = dsa_slave_phy_connect(slave_dev, phy_id); if (ret) { netdev_err(slave_dev, "failed to connect to phy%d: %d\n", phy_id, ret); of_node_put(phy_dn); @@ -1191,7 +1107,7 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, * MDIO bus instead */ if (!p->phy) { - ret = dsa_slave_phy_connect(p, slave_dev, p->dp->index); + ret = dsa_slave_phy_connect(slave_dev, p->dp->index); if (ret) { netdev_err(slave_dev, "failed to connect to port %d: %d\n", p->dp->index, ret); @@ -1313,7 +1229,7 @@ int dsa_slave_create(struct dsa_port *port, const char *name) netif_carrier_off(slave_dev); - ret = dsa_slave_phy_setup(p, slave_dev); + ret = dsa_slave_phy_setup(slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); unregister_netdev(slave_dev); @@ -1374,7 +1290,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); - if (dev->netdev_ops != &dsa_slave_netdev_ops) + if (!dsa_slave_dev_check(dev)) return NOTIFY_DONE; if (event == NETDEV_CHANGEUPPER) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index d7adc0616599..7ce22a2c07ce 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa) */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); - hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { - if (ifa->ifa_local == addr) { - struct net_device *dev = ifa->ifa_dev->dev; - - if (!net_eq(dev_net(dev), net)) - continue; - result = dev; - break; - } - } - if (!result) { + ifa = inet_lookup_ifaddr_rcu(net, addr); + if (!ifa) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; @@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); + } else { + result = ifa->ifa_dev->dev; } if (result && devref) dev_hold(result); @@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) } EXPORT_SYMBOL(__ip_dev_find); +/* called under RCU lock */ +struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr) +{ + u32 hash = inet_addr_hash(net, addr); + struct in_ifaddr *ifa; + + hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) + if (ifa->ifa_local == addr && + net_eq(dev_net(ifa->ifa_dev->dev), net)) + return ifa; + + return NULL; +} + static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 37819ab4cc74..f02819134ba2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -345,9 +345,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (res.type != RTN_UNICAST && (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev))) goto e_inval; - if (!rpf && !fib_num_tclassid_users(net) && - (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) - goto last_resort; fib_combine_itag(itag, &res); dev_match = false; @@ -402,13 +399,26 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); + struct net *net = dev_net(dev); - if (!r && !fib_num_tclassid_users(dev_net(dev)) && - IN_DEV_ACCEPT_LOCAL(idev) && + if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { + if (IN_DEV_ACCEPT_LOCAL(idev)) + goto ok; + /* if no local routes are added from user space we can check + * for local addresses looking-up the ifaddr table + */ + if (net->ipv4.fib_has_custom_local_routes) + goto full_check; + if (inet_lookup_ifaddr_rcu(net, src)) + return -EINVAL; + +ok: *itag = 0; return 0; } + +full_check: return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag); } @@ -759,6 +769,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, } err = fib_table_insert(net, tb, &cfg, extack); + if (!err && cfg.fc_type == RTN_LOCAL) + net->ipv4.fib_has_custom_local_routes = true; errout: return err; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c039c937ba90..8a91ebbf0c01 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -39,11 +39,11 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg); * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, * and 0.0.0.0 equals to 0.0.0.0 only */ -static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, - const struct in6_addr *sk2_rcv_saddr6, - __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk1_ipv6only, bool sk2_ipv6only, - bool match_wildcard) +static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, + const struct in6_addr *sk2_rcv_saddr6, + __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, + bool sk1_ipv6only, bool sk2_ipv6only, + bool match_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -52,29 +52,29 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) - return 1; + return true; if (!sk1_rcv_saddr || !sk2_rcv_saddr) return match_wildcard; } - return 0; + return false; } if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) - return 1; + return true; if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) - return 1; + return true; if (addr_type == IPV6_ADDR_ANY && match_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) - return 1; + return true; if (sk2_rcv_saddr6 && ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6)) - return 1; + return true; - return 0; + return false; } #endif @@ -82,20 +82,20 @@ static int ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, * match_wildcard == false: addresses must be exactly the same, i.e. * 0.0.0.0 only equals to 0.0.0.0 */ -static int ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk2_ipv6only, bool match_wildcard) +static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, + bool sk2_ipv6only, bool match_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) - return 1; + return true; if (!sk1_rcv_saddr || !sk2_rcv_saddr) return match_wildcard; } - return 0; + return false; } -int inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, - bool match_wildcard) +bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard) { #if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == AF_INET6) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0162fb955b33..9cee986ac6b8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1013,15 +1013,14 @@ static int __net_init ipgre_init_net(struct net *net) return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } -static void __net_exit ipgre_exit_net(struct net *net) +static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id); - ip_tunnel_delete_net(itn, &ipgre_link_ops); + ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, - .exit = ipgre_exit_net, + .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1540,15 +1539,14 @@ static int __net_init ipgre_tap_init_net(struct net *net) return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } -static void __net_exit ipgre_tap_exit_net(struct net *net) +static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id); - ip_tunnel_delete_net(itn, &ipgre_tap_ops); + ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, - .exit = ipgre_tap_exit_net, + .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; @@ -1559,16 +1557,14 @@ static int __net_init erspan_init_net(struct net *net) &erspan_link_ops, "erspan0"); } -static void __net_exit erspan_exit_net(struct net *net) +static void __net_exit erspan_exit_batch_net(struct list_head *net_list) { - struct ip_tunnel_net *itn = net_generic(net, erspan_net_id); - - ip_tunnel_delete_net(itn, &erspan_link_ops); + ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, - .exit = erspan_exit_net, + .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index e9805ad664ac..fe6fee728ce4 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -1061,16 +1061,22 @@ static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, } } -void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops) +void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, + struct rtnl_link_ops *ops) { + struct ip_tunnel_net *itn; + struct net *net; LIST_HEAD(list); rtnl_lock(); - ip_tunnel_destroy(itn, &list, ops); + list_for_each_entry(net, net_list, exit_list) { + itn = net_generic(net, id); + ip_tunnel_destroy(itn, &list, ops); + } unregister_netdevice_many(&list); rtnl_unlock(); } -EXPORT_SYMBOL_GPL(ip_tunnel_delete_net); +EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets); int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_parm *p, __u32 fwmark) diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 5ed63d250950..02d70ca99db1 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -452,15 +452,14 @@ static int __net_init vti_init_net(struct net *net) return 0; } -static void __net_exit vti_exit_net(struct net *net) +static void __net_exit vti_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, vti_net_id); - ip_tunnel_delete_net(itn, &vti_link_ops); + ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, - .exit = vti_exit_net, + .exit_batch = vti_exit_batch_net, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index fb1ad22b5e29..1e47818e38c7 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -634,15 +634,14 @@ static int __net_init ipip_init_net(struct net *net) return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } -static void __net_exit ipip_exit_net(struct net *net) +static void __net_exit ipip_exit_batch_net(struct list_head *list_net) { - struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); - ip_tunnel_delete_net(itn, &ipip_link_ops); + ip_tunnel_delete_nets(list_net, ipip_net_id, &ipip_link_ops); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, - .exit = ipip_exit_net, + .exit_batch = ipip_exit_batch_net, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c5d7656beeee..db9bb46b5776 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2333,9 +2333,9 @@ static bool tcp_any_retrans_done(const struct sock *sk) return false; } -#if FASTRETRANS_DEBUG > 1 static void DBGUNDO(struct sock *sk, const char *msg) { +#if FASTRETRANS_DEBUG > 1 struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -2357,10 +2357,8 @@ static void DBGUNDO(struct sock *sk, const char *msg) tp->packets_out); } #endif -} -#else -#define DBGUNDO(x...) do { } while (0) #endif +} static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss) { @@ -4268,11 +4266,6 @@ static void tcp_sack_remove(struct tcp_sock *tp) tp->rx_opt.num_sacks = num_sacks; } -enum tcp_queue { - OOO_QUEUE, - RCV_QUEUE, -}; - /** * tcp_try_coalesce - try to merge skb to prior one * @sk: socket @@ -4288,7 +4281,6 @@ enum tcp_queue { * Returns true if caller should free @from instead of queueing it */ static bool tcp_try_coalesce(struct sock *sk, - enum tcp_queue dest, struct sk_buff *to, struct sk_buff *from, bool *fragstolen) @@ -4313,10 +4305,7 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->has_rxtstamp) { TCP_SKB_CB(to)->has_rxtstamp = true; - if (dest == OOO_QUEUE) - TCP_SKB_CB(to)->swtstamp = TCP_SKB_CB(from)->swtstamp; - else - to->tstamp = from->tstamp; + to->tstamp = from->tstamp; } return true; @@ -4353,9 +4342,6 @@ static void tcp_ofo_queue(struct sock *sk) } p = rb_next(p); rb_erase(&skb->rbnode, &tp->out_of_order_queue); - /* Replace tstamp which was stomped by rbnode */ - if (TCP_SKB_CB(skb)->has_rxtstamp) - skb->tstamp = TCP_SKB_CB(skb)->swtstamp; if (unlikely(!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))) { SOCK_DEBUG(sk, "ofo packet was already received\n"); @@ -4367,8 +4353,7 @@ static void tcp_ofo_queue(struct sock *sk) TCP_SKB_CB(skb)->end_seq); tail = skb_peek_tail(&sk->sk_receive_queue); - eaten = tail && tcp_try_coalesce(sk, RCV_QUEUE, - tail, skb, &fragstolen); + eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) @@ -4422,10 +4407,6 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) return; } - /* Stash tstamp to avoid being stomped on by rbnode */ - if (TCP_SKB_CB(skb)->has_rxtstamp) - TCP_SKB_CB(skb)->swtstamp = skb->tstamp; - /* Disable header prediction. */ tp->pred_flags = 0; inet_csk_schedule_ack(sk); @@ -4453,7 +4434,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, OOO_QUEUE, tp->ooo_last_skb, + if (tcp_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); @@ -4504,7 +4485,7 @@ coalesce_done: __kfree_skb(skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, OOO_QUEUE, skb1, + } else if (tcp_try_coalesce(sk, skb1, skb, &fragstolen)) { goto coalesce_done; } @@ -4556,7 +4537,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int __skb_pull(skb, hdrlen); eaten = (tail && - tcp_try_coalesce(sk, RCV_QUEUE, tail, + tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 102b2c90bb80..0ab78abc811b 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -892,10 +892,14 @@ static void tcp_metrics_flush_all(struct net *net) for (row = 0; row < max_rows; row++, hb++) { struct tcp_metrics_block __rcu **pp; + bool match; + spin_lock_bh(&tcp_metrics_lock); pp = &hb->chain; for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) { - if (net_eq(tm_net(tm), net)) { + match = net ? net_eq(tm_net(tm), net) : + !atomic_read(&tm_net(tm)->count); + if (match) { *pp = tm->tcpm_next; kfree_rcu(tm, rcu_head); } else { @@ -1018,14 +1022,14 @@ static int __net_init tcp_net_metrics_init(struct net *net) return 0; } -static void __net_exit tcp_net_metrics_exit(struct net *net) +static void __net_exit tcp_net_metrics_exit_batch(struct list_head *net_exit_list) { - tcp_metrics_flush_all(net); + tcp_metrics_flush_all(NULL); } static __net_initdata struct pernet_operations tcp_net_metrics_ops = { - .init = tcp_net_metrics_init, - .exit = tcp_net_metrics_exit, + .init = tcp_net_metrics_init, + .exit_batch = tcp_net_metrics_exit_batch, }; void __init tcp_metrics_init(void) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ef29df8648e4..784ced0b9150 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1212,8 +1212,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2) && - !skb_queue_empty(&up->reader_queue)) + if (size < (sk->sk_rcvbuf >> 2)) return; } else { size += up->forward_deficit; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index b055bc79f56d..c6311d7108f6 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -30,7 +30,6 @@ * Policy Table */ struct ip6addrlbl_entry { - possible_net_t lbl_net; struct in6_addr prefix; int prefixlen; int ifindex; @@ -41,19 +40,6 @@ struct ip6addrlbl_entry { struct rcu_head rcu; }; -static struct ip6addrlbl_table -{ - struct hlist_head head; - spinlock_t lock; - u32 seq; -} ip6addrlbl_table; - -static inline -struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl) -{ - return read_pnet(&lbl->lbl_net); -} - /* * Default policy table (RFC6724 + extensions) * @@ -148,13 +134,10 @@ static inline void ip6addrlbl_put(struct ip6addrlbl_entry *p) } /* Find label */ -static bool __ip6addrlbl_match(struct net *net, - const struct ip6addrlbl_entry *p, +static bool __ip6addrlbl_match(const struct ip6addrlbl_entry *p, const struct in6_addr *addr, int addrtype, int ifindex) { - if (!net_eq(ip6addrlbl_net(p), net)) - return false; if (p->ifindex && p->ifindex != ifindex) return false; if (p->addrtype && p->addrtype != addrtype) @@ -169,8 +152,9 @@ static struct ip6addrlbl_entry *__ipv6_addr_label(struct net *net, int type, int ifindex) { struct ip6addrlbl_entry *p; - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (__ip6addrlbl_match(net, p, addr, type, ifindex)) + + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (__ip6addrlbl_match(p, addr, type, ifindex)) return p; } return NULL; @@ -196,8 +180,7 @@ u32 ipv6_addr_label(struct net *net, } /* allocate one entry */ -static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, - const struct in6_addr *prefix, +static struct ip6addrlbl_entry *ip6addrlbl_alloc(const struct in6_addr *prefix, int prefixlen, int ifindex, u32 label) { @@ -236,24 +219,23 @@ static struct ip6addrlbl_entry *ip6addrlbl_alloc(struct net *net, newp->addrtype = addrtype; newp->label = label; INIT_HLIST_NODE(&newp->list); - write_pnet(&newp->lbl_net, net); refcount_set(&newp->refcnt, 1); return newp; } /* add a label */ -static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) +static int __ip6addrlbl_add(struct net *net, struct ip6addrlbl_entry *newp, + int replace) { - struct hlist_node *n; struct ip6addrlbl_entry *last = NULL, *p = NULL; + struct hlist_node *n; int ret = 0; ADDRLABEL(KERN_DEBUG "%s(newp=%p, replace=%d)\n", __func__, newp, replace); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == newp->prefixlen && - net_eq(ip6addrlbl_net(p), ip6addrlbl_net(newp)) && p->ifindex == newp->ifindex && ipv6_addr_equal(&p->prefix, &newp->prefix)) { if (!replace) { @@ -273,10 +255,10 @@ static int __ip6addrlbl_add(struct ip6addrlbl_entry *newp, int replace) if (last) hlist_add_behind_rcu(&newp->list, &last->list); else - hlist_add_head_rcu(&newp->list, &ip6addrlbl_table.head); + hlist_add_head_rcu(&newp->list, &net->ipv6.ip6addrlbl_table.head); out: if (!ret) - ip6addrlbl_table.seq++; + net->ipv6.ip6addrlbl_table.seq++; return ret; } @@ -292,12 +274,12 @@ static int ip6addrlbl_add(struct net *net, __func__, prefix, prefixlen, ifindex, (unsigned int)label, replace); - newp = ip6addrlbl_alloc(net, prefix, prefixlen, ifindex, label); + newp = ip6addrlbl_alloc(prefix, prefixlen, ifindex, label); if (IS_ERR(newp)) return PTR_ERR(newp); - spin_lock(&ip6addrlbl_table.lock); - ret = __ip6addrlbl_add(newp, replace); - spin_unlock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + ret = __ip6addrlbl_add(net, newp, replace); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); if (ret) ip6addrlbl_free(newp); return ret; @@ -315,9 +297,8 @@ static int __ip6addrlbl_del(struct net *net, ADDRLABEL(KERN_DEBUG "%s(prefix=%pI6, prefixlen=%d, ifindex=%d)\n", __func__, prefix, prefixlen, ifindex); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { if (p->prefixlen == prefixlen && - net_eq(ip6addrlbl_net(p), net) && p->ifindex == ifindex && ipv6_addr_equal(&p->prefix, prefix)) { hlist_del_rcu(&p->list); @@ -340,9 +321,9 @@ static int ip6addrlbl_del(struct net *net, __func__, prefix, prefixlen, ifindex); ipv6_addr_prefix(&prefix_buf, prefix, prefixlen); - spin_lock(&ip6addrlbl_table.lock); + spin_lock(&net->ipv6.ip6addrlbl_table.lock); ret = __ip6addrlbl_del(net, &prefix_buf, prefixlen, ifindex); - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); return ret; } @@ -354,6 +335,9 @@ static int __net_init ip6addrlbl_net_init(struct net *net) ADDRLABEL(KERN_DEBUG "%s\n", __func__); + spin_lock_init(&net->ipv6.ip6addrlbl_table.lock); + INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head); + for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) { int ret = ip6addrlbl_add(net, ip6addrlbl_init_table[i].prefix, @@ -373,14 +357,12 @@ static void __net_exit ip6addrlbl_net_exit(struct net *net) struct hlist_node *n; /* Remove all labels belonging to the exiting net */ - spin_lock(&ip6addrlbl_table.lock); - hlist_for_each_entry_safe(p, n, &ip6addrlbl_table.head, list) { - if (net_eq(ip6addrlbl_net(p), net)) { - hlist_del_rcu(&p->list); - ip6addrlbl_put(p); - } + spin_lock(&net->ipv6.ip6addrlbl_table.lock); + hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) { + hlist_del_rcu(&p->list); + ip6addrlbl_put(p); } - spin_unlock(&ip6addrlbl_table.lock); + spin_unlock(&net->ipv6.ip6addrlbl_table.lock); } static struct pernet_operations ipv6_addr_label_ops = { @@ -390,8 +372,6 @@ static struct pernet_operations ipv6_addr_label_ops = { int __init ipv6_addr_label_init(void) { - spin_lock_init(&ip6addrlbl_table.lock); - return register_pernet_subsys(&ipv6_addr_label_ops); } @@ -510,11 +490,10 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) int err; rcu_read_lock(); - hlist_for_each_entry_rcu(p, &ip6addrlbl_table.head, list) { - if (idx >= s_idx && - net_eq(ip6addrlbl_net(p), net)) { + hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) { + if (idx >= s_idx) { err = ip6addrlbl_fill(skb, p, - ip6addrlbl_table.seq, + net->ipv6.ip6addrlbl_table.seq, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, @@ -571,7 +550,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); if (p && !ip6addrlbl_hold(p)) p = NULL; - lseq = ip6addrlbl_table.seq; + lseq = net->ipv6.ip6addrlbl_table.seq; rcu_read_unlock(); if (!p) { diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 305e2ed730bf..115d60919f72 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -99,7 +99,7 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, break; hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) - hdrlen = (hp->hdrlen+2)<<2; + hdrlen = ipv6_authlen(hp); else hdrlen = ipv6_optlen(hp); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 20f66f4c9460..4b58f964da20 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1156,19 +1156,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6gre_exit_net(struct net *net) +static void __net_exit ip6gre_exit_batch_net(struct list_head *net_list) { + struct net *net; LIST_HEAD(list); rtnl_lock(); - ip6gre_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + ip6gre_destroy_tunnels(net, &list); unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6gre_net_ops = { .init = ip6gre_init_net, - .exit = ip6gre_exit_net, + .exit_batch = ip6gre_exit_batch_net, .id = &ip6gre_net_id, .size = sizeof(struct ip6gre_net), }; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f2f21c24915f..e0f9bc0421e0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2167,17 +2167,16 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .priority = 1, }; -static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) +static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; - LIST_HEAD(list); for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) - unregister_netdevice_queue(dev, &list); + unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); @@ -2186,12 +2185,10 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net) * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } - - unregister_netdevice_many(&list); } static int __net_init ip6_tnl_init_net(struct net *net) @@ -2235,16 +2232,21 @@ err_alloc_dev: return err; } -static void __net_exit ip6_tnl_exit_net(struct net *net) +static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list) { + struct net *net; + LIST_HEAD(list); + rtnl_lock(); - ip6_tnl_destroy_tunnels(net); + list_for_each_entry(net, net_list, exit_list) + ip6_tnl_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, - .exit = ip6_tnl_exit_net, + .exit_batch = ip6_tnl_exit_batch_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 79444a4bfd6d..714914d1bb98 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -1052,23 +1052,22 @@ static struct rtnl_link_ops vti6_link_ops __read_mostly = { .get_link_net = ip6_tnl_get_link_net, }; -static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n) +static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, + struct list_head *list) { int h; struct ip6_tnl *t; - LIST_HEAD(list); for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { - unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, &list); - unregister_netdevice_many(&list); + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) @@ -1108,18 +1107,24 @@ err_alloc_dev: return err; } -static void __net_exit vti6_exit_net(struct net *net) +static void __net_exit vti6_exit_batch_net(struct list_head *net_list) { - struct vti6_net *ip6n = net_generic(net, vti6_net_id); + struct vti6_net *ip6n; + struct net *net; + LIST_HEAD(list); rtnl_lock(); - vti6_destroy_tunnels(ip6n); + list_for_each_entry(net, net_list, exit_list) { + ip6n = net_generic(net, vti6_net_id); + vti6_destroy_tunnels(ip6n, &list); + } + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, - .exit = vti6_exit_net, + .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index ac912bb21747..a799f5258614 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1848,19 +1848,22 @@ err_alloc_dev: return err; } -static void __net_exit sit_exit_net(struct net *net) +static void __net_exit sit_exit_batch_net(struct list_head *net_list) { LIST_HEAD(list); + struct net *net; rtnl_lock(); - sit_destroy_tunnels(net, &list); + list_for_each_entry(net, net_list, exit_list) + sit_destroy_tunnels(net, &list); + unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, - .exit = sit_exit_net, + .exit_batch = sit_exit_batch_net, .id = &sit_net_id, .size = sizeof(struct sit_net), }; diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 1e1c9b20bab7..2fb703d70803 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -623,13 +623,18 @@ llsec_do_encrypt_unauth(struct sk_buff *skb, const struct mac802154_llsec *sec, u8 iv[16]; struct scatterlist src; SKCIPHER_REQUEST_ON_STACK(req, key->tfm0); - int err; + int err, datalen; + unsigned char *data; llsec_geniv(iv, sec->params.hwaddr, &hdr->sec); - sg_init_one(&src, skb->data, skb->len); + /* Compute data payload offset and data length */ + data = skb_mac_header(skb) + skb->mac_len; + datalen = skb_tail_pointer(skb) - data; + sg_init_one(&src, data, datalen); + skcipher_request_set_tfm(req, key->tfm0); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &src, &src, skb->len, iv); + skcipher_request_set_crypt(req, &src, &src, datalen, iv); err = crypto_skcipher_encrypt(req); skcipher_request_zero(req); return err; @@ -713,7 +718,8 @@ int mac802154_llsec_encrypt(struct mac802154_llsec *sec, struct sk_buff *skb) if (hlen < 0 || hdr.fc.type != IEEE802154_FC_TYPE_DATA) return -EINVAL; - if (!hdr.fc.security_enabled || hdr.sec.level == 0) { + if (!hdr.fc.security_enabled || + (hdr.sec.level == IEEE802154_SCF_SECLEVEL_NONE)) { skb_push(skb, hlen); return 0; } diff --git a/net/nfc/core.c b/net/nfc/core.c index 5cf33df888c3..e5e23c2cbe74 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -1094,9 +1094,8 @@ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, dev->targets_generation = 1; if (ops->check_presence) { - init_timer(&dev->check_pres_timer); - dev->check_pres_timer.data = (unsigned long)dev; - dev->check_pres_timer.function = nfc_check_pres_timeout; + setup_timer(&dev->check_pres_timer, nfc_check_pres_timeout, + (unsigned long)dev); INIT_WORK(&dev->check_pres_work, nfc_check_pres_work); } diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c6deb74e3d2f..aa82116ed10c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1500,7 +1500,6 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; - struct tcmsg *tcm = nlmsg_data(nlh); struct nlattr *tca[TCA_MAX + 1]; int err; @@ -1510,7 +1509,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; ASSERT_RTNL(); - err = nlmsg_parse(nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL); + err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX, NULL, NULL); if (err < 0) return err; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index bf8c81e07c70..a0a198768aad 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -689,10 +689,8 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_rcu_free(struct rcu_head *head) +static void qdisc_free(struct Qdisc *qdisc) { - struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); @@ -725,11 +723,7 @@ void qdisc_destroy(struct Qdisc *qdisc) kfree_skb_list(qdisc->gso_skb); kfree_skb(qdisc->skb_bad_txq); - /* - * gen_estimator est_timer() might access qdisc->q.lock, - * wait a RCU grace period before freeing qdisc. - */ - call_rcu(&qdisc->rcu_head, qdisc_rcu_free); + qdisc_free(qdisc); } EXPORT_SYMBOL(qdisc_destroy); diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7e148376ba52..c6d7ae81b41f 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -142,6 +142,7 @@ struct htb_class { struct rb_node node[TC_HTB_NUMPRIO]; /* node for self or feed tree */ unsigned int drops ____cacheline_aligned_in_smp; + unsigned int overlimits; }; struct htb_level { @@ -533,6 +534,9 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) if (new_mode == cl->cmode) return; + if (new_mode == HTB_CANT_SEND) + cl->overlimits++; + if (cl->prio_activity) { /* not necessary: speed optimization */ if (cl->cmode != HTB_CANT_SEND) htb_deactivate_prios(q, cl); @@ -1143,6 +1147,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) struct htb_class *cl = (struct htb_class *)arg; struct gnet_stats_queue qs = { .drops = cl->drops, + .overlimits = cl->overlimits, }; __u32 qlen = 0; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index b1266e75ca43..063a4bdb9ee6 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -146,7 +146,6 @@ struct netem_sched_data { */ struct netem_skb_cb { psched_time_t time_to_send; - ktime_t tstamp_save; }; @@ -561,7 +560,6 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, } cb->time_to_send = now + delay; - cb->tstamp_save = skb->tstamp; ++q->counter; tfifo_enqueue(skb, sch); } else { @@ -629,7 +627,10 @@ deliver: qdisc_qstats_backlog_dec(sch, skb); skb->next = NULL; skb->prev = NULL; - skb->tstamp = netem_skb_cb(skb)->tstamp_save; + /* skb->dev shares skb->rbnode area, + * we need to restore its value. + */ + skb->dev = qdisc_dev(sch); #ifdef CONFIG_NET_CLS_ACT /* diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7294edbc221..5ef97e5a5f78 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -62,10 +62,12 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, bh_unlock_sock(&smc->sk); } -int smc_cdc_get_free_slot(struct smc_link *link, +int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, struct smc_cdc_tx_pend **pend) { + struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; + return smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, (struct smc_wr_tx_pend_priv **)pend); } @@ -118,8 +120,7 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf, - &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc) return rc; diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 8e1d76f26007..56f883d1159c 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -206,7 +206,8 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_cdc_tx_pend; -int smc_cdc_get_free_slot(struct smc_link *link, struct smc_wr_buf **wr_buf, +int smc_cdc_get_free_slot(struct smc_connection *conn, + struct smc_wr_buf **wr_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 3866573288dd..ec49bc3c3283 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -396,8 +396,7 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) int rc; spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], &wr_buf, - &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = @@ -466,8 +465,7 @@ void smc_tx_consumer_update(struct smc_connection *conn) ((to_confirm > conn->rmbe_update_limit) && ((to_confirm > (conn->rmbe_size / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { - rc = smc_cdc_get_free_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], - &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); if (!rc) rc = smc_cdc_msg_send(conn, wr_buf, pend); if (rc < 0) { diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 10ae7823a19d..0206155bff53 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -21,7 +21,6 @@ #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/list.h> -#include <linux/miscdevice.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/net.h> |