diff options
Diffstat (limited to 'net')
102 files changed, 2120 insertions, 1561 deletions
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 780089d75915..d020299baba4 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -627,20 +627,9 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) return err < 0 ? NET_XMIT_DROP : err; } -static struct lock_class_key bt_tx_busylock; -static struct lock_class_key bt_netdev_xmit_lock_key; - -static void bt_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &bt_netdev_xmit_lock_key); -} - static int bt_dev_init(struct net_device *dev) { - netdev_for_each_tx_queue(dev, bt_set_lockdep_class_one, NULL); - dev->qdisc_tx_busylock = &bt_tx_busylock; + netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 904ff431d570..c43c9d2a88cf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -139,6 +139,7 @@ #include <linux/hrtimer.h> #include <linux/netfilter_ingress.h> #include <linux/sctp.h> +#include <linux/crash_dump.h> #include "net-sysfs.h" @@ -2249,11 +2250,12 @@ EXPORT_SYMBOL(netif_set_real_num_rx_queues); */ int netif_get_num_default_rss_queues(void) { - return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); + return is_kdump_kernel() ? + 1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); } EXPORT_SYMBOL(netif_get_num_default_rss_queues); -static inline void __netif_reschedule(struct Qdisc *q) +static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; @@ -3075,7 +3077,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. - * This permits __QDISC___STATE_RUNNING owner to get the lock more + * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. */ contended = qdisc_is_running(q); @@ -3898,22 +3900,14 @@ static void net_tx_action(struct softirq_action *h) head = head->next_sched; root_lock = qdisc_lock(q); - if (spin_trylock(root_lock)) { - smp_mb__before_atomic(); - clear_bit(__QDISC_STATE_SCHED, - &q->state); - qdisc_run(q); - spin_unlock(root_lock); - } else { - if (!test_bit(__QDISC_STATE_DEACTIVATED, - &q->state)) { - __netif_reschedule(q); - } else { - smp_mb__before_atomic(); - clear_bit(__QDISC_STATE_SCHED, - &q->state); - } - } + spin_lock(root_lock); + /* We need to make sure head->next_sched is read + * before clearing __QDISC_STATE_SCHED + */ + smp_mb__before_atomic(); + clear_bit(__QDISC_STATE_SCHED, &q->state); + qdisc_run(q); + spin_unlock(root_lock); } } } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f4034817d255..977489820eb9 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -89,6 +89,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", + [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 840acebbb80c..98298b11f534 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -173,7 +173,8 @@ void fib_rules_unregister(struct fib_rules_ops *ops) EXPORT_SYMBOL_GPL(fib_rules_unregister); static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, - struct flowi *fl, int flags) + struct flowi *fl, int flags, + struct fib_lookup_arg *arg) { int ret = 0; @@ -189,6 +190,9 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, if (rule->tun_id && (rule->tun_id != fl->flowi_tun_key.tun_id)) goto out; + if (rule->l3mdev && !l3mdev_fib_rule_match(rule->fr_net, fl, arg)) + goto out; + ret = ops->match(rule, fl, flags); out: return (rule->flags & FIB_RULE_INVERT) ? !ret : ret; @@ -204,7 +208,7 @@ int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, list_for_each_entry_rcu(rule, &ops->rules_list, list) { jumped: - if (!fib_rule_match(rule, ops, fl, flags)) + if (!fib_rule_match(rule, ops, fl, flags, arg)) continue; if (rule->action == FR_ACT_GOTO) { @@ -265,7 +269,7 @@ errout: return err; } -static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); @@ -336,6 +340,14 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) if (tb[FRA_TUN_ID]) rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + if (tb[FRA_L3MDEV]) { +#ifdef CONFIG_NET_L3_MASTER_DEV + rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]); + if (rule->l3mdev != 1) +#endif + goto errout_free; + } + rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); @@ -371,6 +383,9 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) } else if (rule->action == FR_ACT_GOTO) goto errout_free; + if (rule->l3mdev && rule->table) + goto errout_free; + err = ops->configure(rule, skb, frh, tb); if (err < 0) goto errout_free; @@ -424,8 +439,9 @@ errout: rules_ops_put(ops); return err; } +EXPORT_SYMBOL_GPL(fib_nl_newrule); -static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); @@ -483,6 +499,10 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh) (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) continue; + if (tb[FRA_L3MDEV] && + (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV]))) + continue; + if (!ops->compare(rule, frh, tb)) continue; @@ -536,6 +556,7 @@ errout: rules_ops_put(ops); return err; } +EXPORT_SYMBOL_GPL(fib_nl_delrule); static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) @@ -607,7 +628,9 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target)) || (rule->tun_id && - nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD))) + nla_put_be64(skb, FRA_TUN_ID, rule->tun_id, FRA_PAD)) || + (rule->l3mdev && + nla_put_u8(skb, FRA_L3MDEV, rule->l3mdev))) goto nla_put_failure; if (rule->suppress_ifgroup != -1) { diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 4573d81093fe..cad8e791f28e 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -84,6 +84,7 @@ struct gen_estimator struct gnet_stats_basic_packed *bstats; struct gnet_stats_rate_est64 *rate_est; spinlock_t *stats_lock; + seqcount_t *running; int ewma_log; u32 last_packets; unsigned long avpps; @@ -121,26 +122,28 @@ static void est_timer(unsigned long arg) unsigned long rate; u64 brate; - spin_lock(e->stats_lock); + if (e->stats_lock) + spin_lock(e->stats_lock); read_lock(&est_lock); if (e->bstats == NULL) goto skip; - __gnet_stats_copy_basic(&b, e->cpu_bstats, e->bstats); + __gnet_stats_copy_basic(e->running, &b, e->cpu_bstats, e->bstats); brate = (b.bytes - e->last_bytes)<<(7 - idx); e->last_bytes = b.bytes; e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log); - e->rate_est->bps = (e->avbps+0xF)>>5; + WRITE_ONCE(e->rate_est->bps, (e->avbps + 0xF) >> 5); rate = b.packets - e->last_packets; rate <<= (7 - idx); e->last_packets = b.packets; e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log); - e->rate_est->pps = (e->avpps + 0xF) >> 5; + WRITE_ONCE(e->rate_est->pps, (e->avpps + 0xF) >> 5); skip: read_unlock(&est_lock); - spin_unlock(e->stats_lock); + if (e->stats_lock) + spin_unlock(e->stats_lock); } if (!list_empty(&elist[idx].list)) @@ -194,6 +197,7 @@ struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock + * @running: qdisc running seqcount * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est @@ -209,6 +213,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt) { struct gen_estimator *est; @@ -226,12 +231,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, if (est == NULL) return -ENOBUFS; - __gnet_stats_copy_basic(&b, cpu_bstats, bstats); + __gnet_stats_copy_basic(running, &b, cpu_bstats, bstats); idx = parm->interval + 2; est->bstats = bstats; est->rate_est = rate_est; est->stats_lock = stats_lock; + est->running = running; est->ewma_log = parm->ewma_log; est->last_bytes = b.bytes; est->avbps = rate_est->bps<<5; @@ -291,6 +297,7 @@ EXPORT_SYMBOL(gen_kill_estimator); * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock + * @running: qdisc running seqcount (might be NULL) * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling @@ -301,10 +308,11 @@ EXPORT_SYMBOL(gen_kill_estimator); int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct gnet_stats_rate_est64 *rate_est, - spinlock_t *stats_lock, struct nlattr *opt) + spinlock_t *stats_lock, + seqcount_t *running, struct nlattr *opt) { gen_kill_estimator(bstats, rate_est); - return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt); + return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index be873e4e3125..508e051304fb 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -32,10 +32,11 @@ gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size, int padattr) return 0; nla_put_failure: + if (d->lock) + spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; - spin_unlock_bh(d->lock); return -1; } @@ -66,15 +67,16 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, { memset(d, 0, sizeof(*d)); - spin_lock_bh(lock); - d->lock = lock; if (type) d->tail = (struct nlattr *)skb_tail_pointer(skb); d->skb = skb; d->compat_tc_stats = tc_stats_type; d->compat_xstats = xstats_type; d->padattr = padattr; - + if (lock) { + d->lock = lock; + spin_lock_bh(lock); + } if (d->tail) return gnet_stats_copy(d, type, NULL, 0, padattr); @@ -128,21 +130,29 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, } void -__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats, +__gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) { + unsigned int seq; + if (cpu) { __gnet_stats_copy_basic_cpu(bstats, cpu); - } else { + return; + } + do { + if (running) + seq = read_seqcount_begin(running); bstats->bytes = b->bytes; bstats->packets = b->packets; - } + } while (running && read_seqcount_retry(running, seq)); } EXPORT_SYMBOL(__gnet_stats_copy_basic); /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV + * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics @@ -154,13 +164,14 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(struct gnet_dump *d, +gnet_stats_copy_basic(const seqcount_t *running, + struct gnet_dump *d, struct gnet_stats_basic_cpu __percpu *cpu, struct gnet_stats_basic_packed *b) { struct gnet_stats_basic_packed bstats = {0}; - __gnet_stats_copy_basic(&bstats, cpu, b); + __gnet_stats_copy_basic(running, &bstats, cpu, b); if (d->compat_tc_stats) { d->tc_stats.bytes = bstats.bytes; @@ -330,8 +341,9 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return 0; err_out: + if (d->lock) + spin_unlock_bh(d->lock); d->xstats_len = 0; - spin_unlock_bh(d->lock); return -1; } EXPORT_SYMBOL(gnet_stats_copy_app); @@ -365,10 +377,11 @@ gnet_stats_finish_copy(struct gnet_dump *d) return -1; } + if (d->lock) + spin_unlock_bh(d->lock); kfree(d->xstats); d->xstats = NULL; d->xstats_len = 0; - spin_unlock_bh(d->lock); return 0; } EXPORT_SYMBOL(gnet_stats_finish_copy); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e549c03..e7ec6d3ad5f0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -49,6 +49,7 @@ #include <linux/slab.h> #include <linux/tcp.h> #include <linux/udp.h> +#include <linux/sctp.h> #include <linux/netdevice.h> #ifdef CONFIG_NET_CLS_ACT #include <net/pkt_sched.h> @@ -3116,9 +3117,13 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, int hsize; int size; - len = head_skb->len - offset; - if (len > mss) - len = mss; + if (unlikely(mss == GSO_BY_FRAGS)) { + len = list_skb->len; + } else { + len = head_skb->len - offset; + if (len > mss) + len = mss; + } hsize = skb_headlen(head_skb) - offset; if (hsize < 0) @@ -3438,6 +3443,7 @@ done: NAPI_GRO_CB(skb)->same_flow = 1; return 0; } +EXPORT_SYMBOL_GPL(skb_gro_receive); void __init skb_init(void) { @@ -4378,6 +4384,8 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen += inner_tcp_hdrlen(skb); } else if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { thlen = tcp_hdrlen(skb); + } else if (unlikely(shinfo->gso_type & SKB_GSO_SCTP)) { + thlen = sizeof(struct sctphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already @@ -4387,6 +4395,38 @@ unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); +/** + * skb_gso_validate_mtu - Return in case such skb fits a given MTU + * + * @skb: GSO skb + * @mtu: MTU to validate against + * + * skb_gso_validate_mtu validates if a given skb will fit a wanted MTU + * once split. + */ +bool skb_gso_validate_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + const struct sk_buff *iter; + unsigned int hlen; + + hlen = skb_gso_network_seglen(skb); + + if (shinfo->gso_size != GSO_BY_FRAGS) + return hlen <= mtu; + + /* Undo this so we can re-use header sizes */ + hlen -= GSO_BY_FRAGS; + + skb_walk_frags(skb, iter) { + if (hlen + skb_headlen(iter) > mtu) + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(skb_gso_validate_mtu); + static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) { if (skb_cow(skb, skb_headroom(skb)) < 0) { diff --git a/net/dsa/Makefile b/net/dsa/Makefile index da06ed1df620..8af4ded70f1c 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,6 +1,6 @@ # the core obj-$(CONFIG_NET_DSA) += dsa_core.o -dsa_core-y += dsa.o slave.o +dsa_core-y += dsa.o slave.o dsa2.o # tagging formats dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index eff5dfc2e33f..766d2a525ada 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -29,6 +29,33 @@ char dsa_driver_version[] = "0.1"; +static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + /* Just return the original SKB */ + return skb; +} + +static const struct dsa_device_ops none_ops = { + .xmit = dsa_slave_notag_xmit, + .rcv = NULL, +}; + +const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_DSA + [DSA_TAG_PROTO_DSA] = &dsa_netdev_ops, +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = &trailer_netdev_ops, +#endif +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = &brcm_netdev_ops, +#endif + [DSA_TAG_PROTO_NONE] = &none_ops, +}; /* switch driver registration ***********************************************/ static DEFINE_MUTEX(dsa_switch_drivers_mutex); @@ -180,41 +207,100 @@ __ATTRIBUTE_GROUPS(dsa_hwmon); #endif /* CONFIG_NET_DSA_HWMON */ /* basic switch operations **************************************************/ -static int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct net_device *master) +int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, + struct device_node *port_dn, int port) { - struct dsa_chip_data *cd = ds->cd; - struct device_node *port_dn; struct phy_device *phydev; - int ret, port, mode; + int ret, mode; + + if (of_phy_is_fixed_link(port_dn)) { + ret = of_phy_register_fixed_link(port_dn); + if (ret) { + dev_err(dev, "failed to register fixed PHY\n"); + return ret; + } + phydev = of_phy_find_device(port_dn); + + mode = of_get_phy_mode(port_dn); + if (mode < 0) + mode = PHY_INTERFACE_MODE_NA; + phydev->interface = mode; + + genphy_config_init(phydev); + genphy_read_status(phydev); + if (ds->drv->adjust_link) + ds->drv->adjust_link(ds, port, phydev); + } + + return 0; +} + +static int dsa_cpu_dsa_setups(struct dsa_switch *ds, struct device *dev) +{ + struct device_node *port_dn; + int ret, port; for (port = 0; port < DSA_MAX_PORTS; port++) { if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) continue; - port_dn = cd->port_dn[port]; - if (of_phy_is_fixed_link(port_dn)) { - ret = of_phy_register_fixed_link(port_dn); - if (ret) { - netdev_err(master, - "failed to register fixed PHY\n"); - return ret; - } - phydev = of_phy_find_device(port_dn); + port_dn = ds->ports[port].dn; + ret = dsa_cpu_dsa_setup(ds, dev, port_dn, port); + if (ret) + return ret; + } + return 0; +} - mode = of_get_phy_mode(port_dn); - if (mode < 0) - mode = PHY_INTERFACE_MODE_NA; - phydev->interface = mode; +const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) +{ + const struct dsa_device_ops *ops; + + if (tag_protocol >= DSA_TAG_LAST) + return ERR_PTR(-EINVAL); + ops = dsa_device_ops[tag_protocol]; + + if (!ops) + return ERR_PTR(-ENOPROTOOPT); + + return ops; +} + +int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds) +{ + struct net_device *master; + struct ethtool_ops *cpu_ops; + + master = ds->dst->master_netdev; + if (ds->master_netdev) + master = ds->master_netdev; + + cpu_ops = devm_kzalloc(ds->dev, sizeof(*cpu_ops), GFP_KERNEL); + if (!cpu_ops) + return -ENOMEM; + + memcpy(&ds->dst->master_ethtool_ops, master->ethtool_ops, + sizeof(struct ethtool_ops)); + ds->dst->master_orig_ethtool_ops = master->ethtool_ops; + memcpy(cpu_ops, &ds->dst->master_ethtool_ops, + sizeof(struct ethtool_ops)); + dsa_cpu_port_ethtool_init(cpu_ops); + master->ethtool_ops = cpu_ops; - genphy_config_init(phydev); - genphy_read_status(phydev); - if (ds->drv->adjust_link) - ds->drv->adjust_link(ds, port, phydev); - } - } return 0; } +void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds) +{ + struct net_device *master; + + master = ds->dst->master_netdev; + if (ds->master_netdev) + master = ds->master_netdev; + + master->ethtool_ops = ds->dst->master_orig_ethtool_ops; +} + static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) { struct dsa_switch_driver *drv = ds->drv; @@ -243,6 +329,7 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) } dst->cpu_switch = index; dst->cpu_port = i; + ds->cpu_port_mask |= 1 << i; } else if (!strcmp(name, "dsa")) { ds->dsa_port_mask |= 1 << i; } else { @@ -267,37 +354,17 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) * switch. */ if (dst->cpu_switch == index) { - switch (drv->tag_protocol) { -#ifdef CONFIG_NET_DSA_TAG_DSA - case DSA_TAG_PROTO_DSA: - dst->rcv = dsa_netdev_ops.rcv; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_EDSA - case DSA_TAG_PROTO_EDSA: - dst->rcv = edsa_netdev_ops.rcv; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_TRAILER - case DSA_TAG_PROTO_TRAILER: - dst->rcv = trailer_netdev_ops.rcv; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_BRCM - case DSA_TAG_PROTO_BRCM: - dst->rcv = brcm_netdev_ops.rcv; - break; -#endif - case DSA_TAG_PROTO_NONE: - break; - default: - ret = -ENOPROTOOPT; + dst->tag_ops = dsa_resolve_tag_protocol(drv->tag_protocol); + if (IS_ERR(dst->tag_ops)) { + ret = PTR_ERR(dst->tag_ops); goto out; } - dst->tag_protocol = drv->tag_protocol; + dst->rcv = dst->tag_ops->rcv; } + memcpy(ds->rtable, cd->rtable, sizeof(ds->rtable)); + /* * Do basic register setup. */ @@ -309,22 +376,25 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) if (ret < 0) goto out; - ds->slave_mii_bus = devm_mdiobus_alloc(parent); - if (ds->slave_mii_bus == NULL) { - ret = -ENOMEM; - goto out; - } - dsa_slave_mii_bus_init(ds); - - ret = mdiobus_register(ds->slave_mii_bus); - if (ret < 0) - goto out; + if (!ds->slave_mii_bus && drv->phy_read) { + ds->slave_mii_bus = devm_mdiobus_alloc(parent); + if (!ds->slave_mii_bus) { + ret = -ENOMEM; + goto out; + } + dsa_slave_mii_bus_init(ds); + ret = mdiobus_register(ds->slave_mii_bus); + if (ret < 0) + goto out; + } /* * Create network devices for physical switch ports. */ for (i = 0; i < DSA_MAX_PORTS; i++) { + ds->ports[i].dn = cd->port_dn[i]; + if (!(ds->enabled_port_mask & (1 << i))) continue; @@ -337,13 +407,17 @@ static int dsa_switch_setup_one(struct dsa_switch *ds, struct device *parent) } /* Perform configuration of the CPU and DSA ports */ - ret = dsa_cpu_dsa_setup(ds, dst->master_netdev); + ret = dsa_cpu_dsa_setups(ds, parent); if (ret < 0) { netdev_err(dst->master_netdev, "[%d] : can't configure CPU and DSA ports\n", index); ret = 0; } + ret = dsa_cpu_port_ethtool_setup(ds); + if (ret) + return ret; + #ifdef CONFIG_NET_DSA_HWMON /* If the switch provides a temperature sensor, * register with hardware monitoring subsystem. @@ -420,11 +494,21 @@ dsa_switch_setup(struct dsa_switch_tree *dst, int index, return ds; } -static void dsa_switch_destroy(struct dsa_switch *ds) +void dsa_cpu_dsa_destroy(struct device_node *port_dn) { - struct device_node *port_dn; struct phy_device *phydev; - struct dsa_chip_data *cd = ds->cd; + + if (of_phy_is_fixed_link(port_dn)) { + phydev = of_phy_find_device(port_dn); + if (phydev) { + phy_device_free(phydev); + fixed_phy_unregister(phydev); + } + } +} + +static void dsa_switch_destroy(struct dsa_switch *ds) +{ int port; #ifdef CONFIG_NET_DSA_HWMON @@ -437,26 +521,25 @@ static void dsa_switch_destroy(struct dsa_switch *ds) if (!(ds->enabled_port_mask & (1 << port))) continue; - if (!ds->ports[port]) + if (!ds->ports[port].netdev) continue; - dsa_slave_destroy(ds->ports[port]); + dsa_slave_destroy(ds->ports[port].netdev); } - /* Remove any fixed link PHYs */ + /* Disable configuration of the CPU and DSA ports */ for (port = 0; port < DSA_MAX_PORTS; port++) { - port_dn = cd->port_dn[port]; - if (of_phy_is_fixed_link(port_dn)) { - phydev = of_phy_find_device(port_dn); - if (phydev) { - phy_device_free(phydev); - of_node_put(port_dn); - fixed_phy_unregister(phydev); - } - } + if (!(dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))) + continue; + dsa_cpu_dsa_destroy(ds->ports[port].dn); + + /* Clearing a bit which is not set does no harm */ + ds->cpu_port_mask |= ~(1 << port); + ds->dsa_port_mask |= ~(1 << port); } - mdiobus_unregister(ds->slave_mii_bus); + if (ds->slave_mii_bus && ds->drv->phy_read) + mdiobus_unregister(ds->slave_mii_bus); } #ifdef CONFIG_PM_SLEEP @@ -469,7 +552,7 @@ static int dsa_switch_suspend(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_suspend(ds->ports[i]); + ret = dsa_slave_suspend(ds->ports[i].netdev); if (ret) return ret; } @@ -495,7 +578,7 @@ static int dsa_switch_resume(struct dsa_switch *ds) if (!dsa_is_port_initialized(ds, i)) continue; - ret = dsa_slave_resume(ds->ports[i]); + ret = dsa_slave_resume(ds->ports[i].netdev); if (ret) return ret; } @@ -587,17 +670,6 @@ static int dsa_of_setup_routing_table(struct dsa_platform_data *pd, if (link_sw_addr >= pd->nr_chips) return -EINVAL; - /* First time routing table allocation */ - if (!cd->rtable) { - cd->rtable = kmalloc_array(pd->nr_chips, sizeof(s8), - GFP_KERNEL); - if (!cd->rtable) - return -ENOMEM; - - /* default to no valid uplink/downlink */ - memset(cd->rtable, -1, pd->nr_chips * sizeof(s8)); - } - cd->rtable[link_sw_addr] = port_index; return 0; @@ -639,7 +711,6 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) kfree(pd->chip[i].port_names[port_index]); port_index++; } - kfree(pd->chip[i].rtable); /* Drop our reference to the MDIO bus device */ if (pd->chip[i].host_dev) @@ -931,6 +1002,8 @@ static void dsa_remove_dst(struct dsa_switch_tree *dst) dsa_switch_destroy(ds); } + dsa_cpu_port_ethtool_restore(dst->ds[0]); + dev_put(dst->master_netdev); } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c new file mode 100644 index 000000000000..83b95fc4cede --- /dev/null +++ b/net/dsa/dsa2.c @@ -0,0 +1,690 @@ +/* + * net/dsa/dsa2.c - Hardware switch handling, binding version 2 + * Copyright (c) 2008-2009 Marvell Semiconductor + * Copyright (c) 2013 Florian Fainelli <florian@openwrt.org> + * Copyright (c) 2016 Andrew Lunn <andrew@lunn.ch> + * + * 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 <linux/device.h> +#include <linux/err.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <linux/rtnetlink.h> +#include <net/dsa.h> +#include <linux/of.h> +#include <linux/of_net.h> +#include "dsa_priv.h" + +static LIST_HEAD(dsa_switch_trees); +static DEFINE_MUTEX(dsa2_mutex); + +static struct dsa_switch_tree *dsa_get_dst(u32 tree) +{ + struct dsa_switch_tree *dst; + + list_for_each_entry(dst, &dsa_switch_trees, list) + if (dst->tree == tree) + return dst; + return NULL; +} + +static void dsa_free_dst(struct kref *ref) +{ + struct dsa_switch_tree *dst = container_of(ref, struct dsa_switch_tree, + refcount); + + list_del(&dst->list); + kfree(dst); +} + +static void dsa_put_dst(struct dsa_switch_tree *dst) +{ + kref_put(&dst->refcount, dsa_free_dst); +} + +static struct dsa_switch_tree *dsa_add_dst(u32 tree) +{ + struct dsa_switch_tree *dst; + + dst = kzalloc(sizeof(*dst), GFP_KERNEL); + if (!dst) + return NULL; + dst->tree = tree; + dst->cpu_switch = -1; + INIT_LIST_HEAD(&dst->list); + list_add_tail(&dsa_switch_trees, &dst->list); + kref_init(&dst->refcount); + + return dst; +} + +static void dsa_dst_add_ds(struct dsa_switch_tree *dst, + struct dsa_switch *ds, u32 index) +{ + kref_get(&dst->refcount); + dst->ds[index] = ds; +} + +static void dsa_dst_del_ds(struct dsa_switch_tree *dst, + struct dsa_switch *ds, u32 index) +{ + dst->ds[index] = NULL; + kref_put(&dst->refcount, dsa_free_dst); +} + +static bool dsa_port_is_dsa(struct device_node *port) +{ + const char *name; + + name = of_get_property(port, "label", NULL); + if (!name) + return false; + + if (!strcmp(name, "dsa")) + return true; + + return false; +} + +static bool dsa_port_is_cpu(struct device_node *port) +{ + const char *name; + + name = of_get_property(port, "label", NULL); + if (!name) + return false; + + if (!strcmp(name, "cpu")) + return true; + + return false; +} + +static bool dsa_ds_find_port(struct dsa_switch *ds, + struct device_node *port) +{ + u32 index; + + for (index = 0; index < DSA_MAX_PORTS; index++) + if (ds->ports[index].dn == port) + return true; + return false; +} + +static struct dsa_switch *dsa_dst_find_port(struct dsa_switch_tree *dst, + struct device_node *port) +{ + struct dsa_switch *ds; + u32 index; + + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + if (dsa_ds_find_port(ds, port)) + return ds; + } + + return NULL; +} + +static int dsa_port_complete(struct dsa_switch_tree *dst, + struct dsa_switch *src_ds, + struct device_node *port, + u32 src_port) +{ + struct device_node *link; + int index; + struct dsa_switch *dst_ds; + + for (index = 0;; index++) { + link = of_parse_phandle(port, "link", index); + if (!link) + break; + + dst_ds = dsa_dst_find_port(dst, link); + of_node_put(link); + + if (!dst_ds) + return 1; + + src_ds->rtable[dst_ds->index] = src_port; + } + + return 0; +} + +/* A switch is complete if all the DSA ports phandles point to ports + * known in the tree. A return value of 1 means the tree is not + * complete. This is not an error condition. A value of 0 is + * success. + */ +static int dsa_ds_complete(struct dsa_switch_tree *dst, struct dsa_switch *ds) +{ + struct device_node *port; + u32 index; + int err; + + for (index = 0; index < DSA_MAX_PORTS; index++) { + port = ds->ports[index].dn; + if (!port) + continue; + + if (!dsa_port_is_dsa(port)) + continue; + + err = dsa_port_complete(dst, ds, port, index); + if (err != 0) + return err; + + ds->dsa_port_mask |= BIT(index); + } + + return 0; +} + +/* A tree is complete if all the DSA ports phandles point to ports + * known in the tree. A return value of 1 means the tree is not + * complete. This is not an error condition. A value of 0 is + * success. + */ +static int dsa_dst_complete(struct dsa_switch_tree *dst) +{ + struct dsa_switch *ds; + u32 index; + int err; + + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + err = dsa_ds_complete(dst, ds); + if (err != 0) + return err; + } + + return 0; +} + +static int dsa_dsa_port_apply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + int err; + + err = dsa_cpu_dsa_setup(ds, ds->dev, port, index); + if (err) { + dev_warn(ds->dev, "Failed to setup dsa port %d: %d\n", + index, err); + return err; + } + + return 0; +} + +static void dsa_dsa_port_unapply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + dsa_cpu_dsa_destroy(port); +} + +static int dsa_cpu_port_apply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + int err; + + err = dsa_cpu_dsa_setup(ds, ds->dev, port, index); + if (err) { + dev_warn(ds->dev, "Failed to setup cpu port %d: %d\n", + index, err); + return err; + } + + ds->cpu_port_mask |= BIT(index); + + return 0; +} + +static void dsa_cpu_port_unapply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + dsa_cpu_dsa_destroy(port); + ds->cpu_port_mask &= ~BIT(index); + +} + +static int dsa_user_port_apply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + const char *name; + int err; + + name = of_get_property(port, "label", NULL); + + err = dsa_slave_create(ds, ds->dev, index, name); + if (err) { + dev_warn(ds->dev, "Failed to create slave %d: %d\n", + index, err); + return err; + } + + return 0; +} + +static void dsa_user_port_unapply(struct device_node *port, u32 index, + struct dsa_switch *ds) +{ + if (ds->ports[index].netdev) { + dsa_slave_destroy(ds->ports[index].netdev); + ds->ports[index].netdev = NULL; + ds->enabled_port_mask &= ~(1 << index); + } +} + +static int dsa_ds_apply(struct dsa_switch_tree *dst, struct dsa_switch *ds) +{ + struct device_node *port; + u32 index; + int err; + + /* Initialize ds->phys_mii_mask before registering the slave MDIO bus + * driver and before drv->setup() has run, since the switch drivers and + * the slave MDIO bus driver rely on these values for probing PHY + * devices or not + */ + ds->phys_mii_mask = ds->enabled_port_mask; + + err = ds->drv->setup(ds); + if (err < 0) + return err; + + err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr); + if (err < 0) + return err; + + err = ds->drv->set_addr(ds, dst->master_netdev->dev_addr); + if (err < 0) + return err; + + if (!ds->slave_mii_bus && ds->drv->phy_read) { + ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev); + if (!ds->slave_mii_bus) + return -ENOMEM; + + dsa_slave_mii_bus_init(ds); + + err = mdiobus_register(ds->slave_mii_bus); + if (err < 0) + return err; + } + + for (index = 0; index < DSA_MAX_PORTS; index++) { + port = ds->ports[index].dn; + if (!port) + continue; + + if (dsa_port_is_dsa(port)) { + err = dsa_dsa_port_apply(port, index, ds); + if (err) + return err; + continue; + } + + if (dsa_port_is_cpu(port)) { + err = dsa_cpu_port_apply(port, index, ds); + if (err) + return err; + continue; + } + + err = dsa_user_port_apply(port, index, ds); + if (err) + continue; + } + + return 0; +} + +static void dsa_ds_unapply(struct dsa_switch_tree *dst, struct dsa_switch *ds) +{ + struct device_node *port; + u32 index; + + for (index = 0; index < DSA_MAX_PORTS; index++) { + port = ds->ports[index].dn; + if (!port) + continue; + + if (dsa_port_is_dsa(port)) { + dsa_dsa_port_unapply(port, index, ds); + continue; + } + + if (dsa_port_is_cpu(port)) { + dsa_cpu_port_unapply(port, index, ds); + continue; + } + + dsa_user_port_unapply(port, index, ds); + } + + if (ds->slave_mii_bus && ds->drv->phy_read) + mdiobus_unregister(ds->slave_mii_bus); +} + +static int dsa_dst_apply(struct dsa_switch_tree *dst) +{ + struct dsa_switch *ds; + u32 index; + int err; + + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + err = dsa_ds_apply(dst, ds); + if (err) + return err; + } + + err = dsa_cpu_port_ethtool_setup(dst->ds[0]); + 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->master_netdev->dsa_ptr = (void *)dst; + dst->applied = true; + + return 0; +} + +static void dsa_dst_unapply(struct dsa_switch_tree *dst) +{ + struct dsa_switch *ds; + u32 index; + + if (!dst->applied) + return; + + dst->master_netdev->dsa_ptr = NULL; + + /* If we used a tagging format that doesn't have an ethertype + * field, make sure that all packets from this point get sent + * without the tag and go through the regular receive path. + */ + wmb(); + + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + dsa_ds_unapply(dst, ds); + } + + dsa_cpu_port_ethtool_restore(dst->ds[0]); + + pr_info("DSA: tree %d unapplied\n", dst->tree); + dst->applied = false; +} + +static int dsa_cpu_parse(struct device_node *port, u32 index, + struct dsa_switch_tree *dst, + struct dsa_switch *ds) +{ + struct net_device *ethernet_dev; + struct device_node *ethernet; + + ethernet = of_parse_phandle(port, "ethernet", 0); + if (!ethernet) + return -EINVAL; + + ethernet_dev = of_find_net_device_by_node(ethernet); + if (!ethernet_dev) + return -EPROBE_DEFER; + + if (!ds->master_netdev) + ds->master_netdev = ethernet_dev; + + if (!dst->master_netdev) + dst->master_netdev = ethernet_dev; + + if (dst->cpu_switch == -1) { + dst->cpu_switch = ds->index; + dst->cpu_port = index; + } + + dst->tag_ops = dsa_resolve_tag_protocol(ds->drv->tag_protocol); + if (IS_ERR(dst->tag_ops)) { + dev_warn(ds->dev, "No tagger for this switch\n"); + return PTR_ERR(dst->tag_ops); + } + + dst->rcv = dst->tag_ops->rcv; + + return 0; +} + +static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds) +{ + struct device_node *port; + u32 index; + int err; + + for (index = 0; index < DSA_MAX_PORTS; index++) { + port = ds->ports[index].dn; + if (!port) + continue; + + if (dsa_port_is_cpu(port)) { + err = dsa_cpu_parse(port, index, dst, ds); + if (err) + return err; + } + } + + pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index); + + return 0; +} + +static int dsa_dst_parse(struct dsa_switch_tree *dst) +{ + struct dsa_switch *ds; + u32 index; + int err; + + for (index = 0; index < DSA_MAX_SWITCHES; index++) { + ds = dst->ds[index]; + if (!ds) + continue; + + err = dsa_ds_parse(dst, ds); + if (err) + return err; + } + + if (!dst->master_netdev) { + pr_warn("Tree has no master device\n"); + return -EINVAL; + } + + pr_info("DSA: tree %d parsed\n", dst->tree); + + return 0; +} + +static int dsa_parse_ports_dn(struct device_node *ports, struct dsa_switch *ds) +{ + struct device_node *port; + int err; + u32 reg; + + for_each_available_child_of_node(ports, port) { + err = of_property_read_u32(port, "reg", ®); + if (err) + return err; + + if (reg >= DSA_MAX_PORTS) + return -EINVAL; + + ds->ports[reg].dn = port; + + /* Initialize enabled_port_mask now for drv->setup() + * to have access to a correct value, just like what + * net/dsa/dsa.c::dsa_switch_setup_one does. + */ + if (!dsa_port_is_cpu(port)) + ds->enabled_port_mask |= 1 << reg; + } + + return 0; +} + +static int dsa_parse_member(struct device_node *np, u32 *tree, u32 *index) +{ + int err; + + *tree = *index = 0; + + err = of_property_read_u32_index(np, "dsa,member", 0, tree); + if (err) { + /* Does not exist, but it is optional */ + if (err == -EINVAL) + return 0; + return err; + } + + err = of_property_read_u32_index(np, "dsa,member", 1, index); + if (err) + return err; + + if (*index >= DSA_MAX_SWITCHES) + return -EINVAL; + + return 0; +} + +static struct device_node *dsa_get_ports(struct dsa_switch *ds, + struct device_node *np) +{ + struct device_node *ports; + + ports = of_get_child_by_name(np, "ports"); + if (!ports) { + dev_err(ds->dev, "no ports child node found\n"); + return ERR_PTR(-EINVAL); + } + + return ports; +} + +static int _dsa_register_switch(struct dsa_switch *ds, struct device_node *np) +{ + struct device_node *ports = dsa_get_ports(ds, np); + struct dsa_switch_tree *dst; + u32 tree, index; + int err; + + err = dsa_parse_member(np, &tree, &index); + if (err) + return err; + + if (IS_ERR(ports)) + return PTR_ERR(ports); + + err = dsa_parse_ports_dn(ports, ds); + if (err) + return err; + + dst = dsa_get_dst(tree); + if (!dst) { + dst = dsa_add_dst(tree); + if (!dst) + return -ENOMEM; + } + + if (dst->ds[index]) { + err = -EBUSY; + goto out; + } + + ds->dst = dst; + ds->index = index; + dsa_dst_add_ds(dst, ds, index); + + err = dsa_dst_complete(dst); + if (err < 0) + goto out_del_dst; + + if (err == 1) { + /* Not all switches registered yet */ + err = 0; + goto out; + } + + if (dst->applied) { + pr_info("DSA: Disjoint trees?\n"); + return -EINVAL; + } + + err = dsa_dst_parse(dst); + if (err) + goto out_del_dst; + + err = dsa_dst_apply(dst); + if (err) { + dsa_dst_unapply(dst); + goto out_del_dst; + } + + dsa_put_dst(dst); + return 0; + +out_del_dst: + dsa_dst_del_ds(dst, ds, ds->index); +out: + dsa_put_dst(dst); + + return err; +} + +int dsa_register_switch(struct dsa_switch *ds, struct device_node *np) +{ + int err; + + mutex_lock(&dsa2_mutex); + err = _dsa_register_switch(ds, np); + mutex_unlock(&dsa2_mutex); + + return err; +} +EXPORT_SYMBOL_GPL(dsa_register_switch); + +void _dsa_unregister_switch(struct dsa_switch *ds) +{ + struct dsa_switch_tree *dst = ds->dst; + + dsa_dst_unapply(dst); + + dsa_dst_del_ds(dst, ds, ds->index); +} + +void dsa_unregister_switch(struct dsa_switch *ds) +{ + mutex_lock(&dsa2_mutex); + _dsa_unregister_switch(ds); + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_unregister_switch); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index dfa33779d49c..00077a9c97f4 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -50,12 +50,19 @@ struct dsa_slave_priv { /* dsa.c */ extern char dsa_driver_version[]; +int dsa_cpu_dsa_setup(struct dsa_switch *ds, struct device *dev, + struct device_node *port_dn, int port); +void dsa_cpu_dsa_destroy(struct device_node *port_dn); +const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); +int dsa_cpu_port_ethtool_setup(struct dsa_switch *ds); +void dsa_cpu_port_ethtool_restore(struct dsa_switch *ds); /* 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_switch *ds, struct device *parent, - int port, char *name); + int port, const char *name); void dsa_slave_destroy(struct net_device *slave_dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 152436cdab30..7236eb26dc97 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -49,8 +49,8 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) ds->slave_mii_bus->name = "dsa slave smi"; ds->slave_mii_bus->read = dsa_slave_phy_read; ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d:%.2x", - ds->index, ds->cd->sw_addr); + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", + ds->dst->tree, ds->index); ds->slave_mii_bus->parent = ds->dev; ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; } @@ -522,14 +522,6 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - /* Just return the original SKB */ - return skb; -} - - /* ethtool operations *******************************************************/ static int dsa_slave_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) @@ -615,7 +607,7 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; - if (ds->cd->eeprom_len) + if (ds->cd && ds->cd->eeprom_len) return ds->cd->eeprom_len; if (ds->drv->get_eeprom_len) @@ -873,6 +865,13 @@ static void dsa_slave_poll_controller(struct net_device *dev) } #endif +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 const struct ethtool_ops dsa_slave_ethtool_ops = { .get_settings = dsa_slave_get_settings, .set_settings = dsa_slave_set_settings, @@ -893,8 +892,6 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_eee = dsa_slave_get_eee, }; -static struct ethtool_ops dsa_cpu_port_ethtool_ops; - static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_open = dsa_slave_open, .ndo_stop = dsa_slave_close, @@ -999,13 +996,12 @@ static int dsa_slave_phy_setup(struct dsa_slave_priv *p, struct net_device *slave_dev) { struct dsa_switch *ds = p->parent; - struct dsa_chip_data *cd = ds->cd; struct device_node *phy_dn, *port_dn; bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; - port_dn = cd->port_dn[p->port]; + port_dn = ds->ports[p->port].dn; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; @@ -1109,14 +1105,18 @@ int dsa_slave_resume(struct net_device *slave_dev) } int dsa_slave_create(struct dsa_switch *ds, struct device *parent, - int port, char *name) + int port, const char *name) { - struct net_device *master = ds->dst->master_netdev; struct dsa_switch_tree *dst = ds->dst; + struct net_device *master; struct net_device *slave_dev; struct dsa_slave_priv *p; int ret; + master = ds->dst->master_netdev; + if (ds->master_netdev) + master = ds->master_netdev; + slave_dev = alloc_netdev(sizeof(struct dsa_slave_priv), name, NET_NAME_UNKNOWN, ether_setup); if (slave_dev == NULL) @@ -1124,19 +1124,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, slave_dev->features = master->vlan_features; slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; - if (master->ethtool_ops != &dsa_cpu_port_ethtool_ops) { - memcpy(&dst->master_ethtool_ops, master->ethtool_ops, - sizeof(struct ethtool_ops)); - memcpy(&dsa_cpu_port_ethtool_ops, &dst->master_ethtool_ops, - sizeof(struct ethtool_ops)); - dsa_cpu_port_ethtool_ops.get_sset_count = - dsa_cpu_port_get_sset_count; - dsa_cpu_port_ethtool_ops.get_ethtool_stats = - dsa_cpu_port_get_ethtool_stats; - dsa_cpu_port_ethtool_ops.get_strings = - dsa_cpu_port_get_strings; - master->ethtool_ops = &dsa_cpu_port_ethtool_ops; - } eth_hw_addr_inherit(slave_dev, master); slave_dev->priv_flags |= IFF_NO_QUEUE; slave_dev->netdev_ops = &dsa_slave_netdev_ops; @@ -1147,49 +1134,24 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, NULL); SET_NETDEV_DEV(slave_dev, parent); - slave_dev->dev.of_node = ds->cd->port_dn[port]; + slave_dev->dev.of_node = ds->ports[port].dn; slave_dev->vlan_features = master->vlan_features; p = netdev_priv(slave_dev); p->parent = ds; p->port = port; - - switch (ds->dst->tag_protocol) { -#ifdef CONFIG_NET_DSA_TAG_DSA - case DSA_TAG_PROTO_DSA: - p->xmit = dsa_netdev_ops.xmit; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_EDSA - case DSA_TAG_PROTO_EDSA: - p->xmit = edsa_netdev_ops.xmit; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_TRAILER - case DSA_TAG_PROTO_TRAILER: - p->xmit = trailer_netdev_ops.xmit; - break; -#endif -#ifdef CONFIG_NET_DSA_TAG_BRCM - case DSA_TAG_PROTO_BRCM: - p->xmit = brcm_netdev_ops.xmit; - break; -#endif - default: - p->xmit = dsa_slave_notag_xmit; - break; - } + p->xmit = dst->tag_ops->xmit; p->old_pause = -1; p->old_link = -1; p->old_duplex = -1; - ds->ports[port] = slave_dev; + ds->ports[port].netdev = slave_dev; ret = register_netdev(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); - ds->ports[port] = NULL; + ds->ports[port].netdev = NULL; free_netdev(slave_dev); return ret; } diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index e2aadb73111d..21bffde6e4bf 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -127,7 +127,7 @@ static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, source_port = brcm_tag[3] & BRCM_EG_PID_MASK; /* Validate port against switch setup, either the port is totally */ - if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL) + if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev) goto out_drop; /* Remove Broadcom tag and update checksum */ @@ -140,7 +140,7 @@ static int brcm_tag_rcv(struct sk_buff *skb, struct net_device *dev, skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; - skb->dev = ds->ports[source_port]; + skb->dev = ds->ports[source_port].netdev; skb->protocol = eth_type_trans(skb, skb->dev); skb->dev->stats.rx_packets++; diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index aa780e4ac0bd..bce79ffe342b 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -107,10 +107,14 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, * Check that the source device exists and that the source * port is a registered DSA port. */ - if (source_device >= dst->pd->nr_chips) + if (source_device >= DSA_MAX_SWITCHES) goto out_drop; + ds = dst->ds[source_device]; - if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL) + if (!ds) + goto out_drop; + + if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev) goto out_drop; /* @@ -159,7 +163,7 @@ static int dsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port]; + skb->dev = ds->ports[source_port].netdev; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 2288c8098c42..6c1720e88537 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -120,10 +120,14 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, * Check that the source device exists and that the source * port is a registered DSA port. */ - if (source_device >= dst->pd->nr_chips) + if (source_device >= DSA_MAX_SWITCHES) goto out_drop; + ds = dst->ds[source_device]; - if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL) + if (!ds) + goto out_drop; + + if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev) goto out_drop; /* @@ -178,7 +182,7 @@ static int edsa_rcv(struct sk_buff *skb, struct net_device *dev, 2 * ETH_ALEN); } - skb->dev = ds->ports[source_port]; + skb->dev = ds->ports[source_port].netdev; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index b6ca0890d018..5e3903eb1afa 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -82,12 +82,12 @@ static int trailer_rcv(struct sk_buff *skb, struct net_device *dev, goto out_drop; source_port = trailer[1] & 7; - if (source_port >= DSA_MAX_PORTS || ds->ports[source_port] == NULL) + if (source_port >= DSA_MAX_PORTS || !ds->ports[source_port].netdev) goto out_drop; pskb_trim_rcsum(skb, skb->len - 4); - skb->dev = ds->ports[source_port]; + skb->dev = ds->ports[source_port].netdev; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index dd085db8580e..4e2b30894224 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -58,21 +58,10 @@ static struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; -static struct lock_class_key lowpan_tx_busylock; -static struct lock_class_key lowpan_netdev_xmit_lock_key; - -static void lowpan_set_lockdep_class_one(struct net_device *ldev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &lowpan_netdev_xmit_lock_key); -} - static int lowpan_dev_init(struct net_device *ldev) { - netdev_for_each_tx_queue(ldev, lowpan_set_lockdep_class_one, NULL); - ldev->qdisc_tx_busylock = &lowpan_tx_busylock; + netdev_lockdep_set_classes(ldev); + return 0; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f2bda9e89c61..6e9ea69e5f75 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -76,6 +76,7 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, { int err = -EAGAIN; struct fib_table *tbl; + u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: @@ -94,7 +95,8 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, rcu_read_lock(); - tbl = fib_get_table(rule->fr_net, rule->table); + tb_id = fib_rule_get_table(rule, arg); + tbl = fib_get_table(rule->fr_net, tb_id); if (tbl) err = fib_table_lookup(tbl, &flp->u.ip4, (struct fib_result *)arg->result, @@ -180,7 +182,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (err) goto errout; - if (rule->table == RT_TABLE_UNSPEC) { + if (rule->table == RT_TABLE_UNSPEC && !rule->l3mdev) { if (rule->action == FR_ACT_TO_TBL) { struct fib_table *table; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 5f9207c039e7..321d57f825ce 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -129,6 +129,36 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) guehdr = (struct guehdr *)&udp_hdr(skb)[1]; + switch (guehdr->version) { + case 0: /* Full GUE header present */ + break; + + case 1: { + /* Direct encasulation of IPv4 or IPv6 */ + + int prot; + + switch (((struct iphdr *)guehdr)->version) { + case 4: + prot = IPPROTO_IPIP; + break; + case 6: + prot = IPPROTO_IPV6; + break; + default: + goto drop; + } + + if (fou_recv_pull(skb, fou, sizeof(struct udphdr))) + goto drop; + + return -prot; + } + + default: /* Undefined version */ + goto drop; + } + optlen = guehdr->hlen << 2; len += optlen; @@ -289,6 +319,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, int flush = 1; struct fou *fou = fou_from_sock(sk); struct gro_remcsum grc; + u8 proto; skb_gro_remcsum_init(&grc); @@ -302,6 +333,25 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, goto out; } + switch (guehdr->version) { + case 0: + break; + case 1: + switch (((struct iphdr *)guehdr)->version) { + case 4: + proto = IPPROTO_IPIP; + break; + case 6: + proto = IPPROTO_IPV6; + break; + default: + goto out; + } + goto next_proto; + default: + goto out; + } + optlen = guehdr->hlen << 2; len += optlen; @@ -370,6 +420,10 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, } } + proto = guehdr->proto_ctype; + +next_proto: + /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are are simply @@ -383,7 +437,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; - ops = rcu_dereference(offloads[guehdr->proto_ctype]); + ops = rcu_dereference(offloads[proto]); if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out_unlock; @@ -404,13 +458,30 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) const struct net_offload **offloads; struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); const struct net_offload *ops; - unsigned int guehlen; + unsigned int guehlen = 0; u8 proto; int err = -ENOENT; - proto = guehdr->proto_ctype; - - guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); + switch (guehdr->version) { + case 0: + proto = guehdr->proto_ctype; + guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); + break; + case 1: + switch (((struct iphdr *)guehdr)->version) { + case 4: + proto = IPPROTO_IPIP; + break; + case 6: + proto = IPPROTO_IPV6; + break; + default: + return err; + } + break; + default: + return err; + } rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 3a88b0c73797..b5e9317eaf9e 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -355,7 +355,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, { struct inet_frag_queue *q; - if (frag_mem_limit(nf) > nf->high_thresh) { + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) { inet_frag_schedule_worker(f); return NULL; } diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index cbfb1808fcc4..9f0a7b96646f 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -54,7 +54,7 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) return false; return true; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 124bf0a66328..cbac493c913a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -225,7 +225,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, /* common case: locally created skb or seglen is <= mtu */ if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) || - skb_gso_network_seglen(skb) <= mtu) + skb_gso_validate_mtu(skb, mtu)) return ip_finish_output2(net, sk, skb); /* Slowpath - GSO segment length is exceeding the dst MTU. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d6c8f4cd0800..89dd8d82826f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5159,6 +5159,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, int syn_inerr) { struct tcp_sock *tp = tcp_sk(sk); + bool rst_seq_match = false; /* RFC1323: H1. Apply PAWS check first. */ if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && @@ -5195,13 +5196,32 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, /* Step 2: check RST bit */ if (th->rst) { - /* RFC 5961 3.2 : - * If sequence number exactly matches RCV.NXT, then + /* RFC 5961 3.2 (extend to match against SACK too if available): + * If seq num matches RCV.NXT or the right-most SACK block, + * then * RESET the connection * else * Send a challenge ACK */ - if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) + if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { + rst_seq_match = true; + } else if (tcp_is_sack(tp) && tp->rx_opt.num_sacks > 0) { + struct tcp_sack_block *sp = &tp->selective_acks[0]; + int max_sack = sp[0].end_seq; + int this_sack; + + for (this_sack = 1; this_sack < tp->rx_opt.num_sacks; + ++this_sack) { + max_sack = after(sp[this_sack].end_seq, + max_sack) ? + sp[this_sack].end_seq : max_sack; + } + + if (TCP_SKB_CB(skb)->seq == max_sack) + rst_seq_match = true; + } + + if (rst_seq_match) tcp_reset(sk); else tcp_send_challenge_ack(sk, skb); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index bfa86f040c16..2076c21107d0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -92,6 +92,12 @@ MODULE_PARM_DESC(disable_ipv6, "Disable IPv6 on all interfaces"); module_param_named(autoconf, ipv6_defaults.autoconf, int, 0444); MODULE_PARM_DESC(autoconf, "Enable IPv6 address autoconfiguration on all interfaces"); +bool ipv6_mod_enabled(void) +{ + return disable_ipv6_mod == 0; +} +EXPORT_SYMBOL_GPL(ipv6_mod_enabled); + static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) { const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo); diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index ed33abf57abd..5857c1fc8b67 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -67,6 +67,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; int err = 0; + u32 tb_id; switch (rule->action) { case FR_ACT_TO_TBL: @@ -86,7 +87,8 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, goto discard_pkt; } - table = fib6_get_table(net, rule->table); + tb_id = fib_rule_get_table(rule, arg); + table = fib6_get_table(net, tb_id); if (!table) { err = -EAGAIN; goto out; @@ -199,7 +201,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; - if (rule->action == FR_ACT_TO_TBL) { + if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { if (rule->table == RT6_TABLE_UNSPEC) goto errout; diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h index d08fd2d48a78..e0170f62bc39 100644 --- a/net/ipv6/ila/ila.h +++ b/net/ipv6/ila/ila.h @@ -109,7 +109,8 @@ static inline bool ila_csum_neutral_set(struct ila_identifier ident) return !!(ident.csum_neutral); } -void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p); +void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, + bool set_csum_neutral); void ila_init_saved_csum(struct ila_params *p); diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c index 0e94042d1289..b3d00be484d4 100644 --- a/net/ipv6/ila/ila_common.c +++ b/net/ipv6/ila/ila_common.c @@ -103,7 +103,8 @@ static void ila_csum_adjust_transport(struct sk_buff *skb, iaddr->loc = p->locator; } -void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) +void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, + bool set_csum_neutral) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); @@ -114,7 +115,8 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) * is a locator being translated to a SIR address. * Perform (receiver) checksum-neutral translation. */ - ila_csum_do_neutral(iaddr, p); + if (!set_csum_neutral) + ila_csum_do_neutral(iaddr, p); } else { switch (p->csum_mode) { case ILA_CSUM_ADJUST_TRANSPORT: diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index 1dfb64166d7d..c8314c6b6154 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -26,7 +26,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); + ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), true); return dst->lwtstate->orig_output(net, sk, skb); @@ -42,7 +42,7 @@ static int ila_input(struct sk_buff *skb) if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate)); + ila_update_ipv6_locator(skb, ila_params_lwtunnel(dst->lwtstate), false); return dst->lwtstate->orig_input(skb); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index a90e57229c6c..e6eca5fdf4c9 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -210,14 +210,14 @@ static void ila_free_cb(void *ptr, void *arg) } } -static int ila_xlat_addr(struct sk_buff *skb); +static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral); static unsigned int ila_nf_input(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - ila_xlat_addr(skb); + ila_xlat_addr(skb, false); return NF_ACCEPT; } @@ -597,7 +597,7 @@ static struct pernet_operations ila_net_ops = { .size = sizeof(struct ila_net), }; -static int ila_xlat_addr(struct sk_buff *skb) +static int ila_xlat_addr(struct sk_buff *skb, bool set_csum_neutral) { struct ila_map *ila; struct ipv6hdr *ip6h = ipv6_hdr(skb); @@ -616,7 +616,7 @@ static int ila_xlat_addr(struct sk_buff *skb) ila = ila_lookup_wildcards(iaddr, skb->dev->ifindex, ilan); if (ila) - ila_update_ipv6_locator(skb, &ila->xp.ip); + ila_update_ipv6_locator(skb, &ila->xp.ip, set_csum_neutral); rcu_read_unlock(); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 94611e450ec9..aacfb4bce153 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -323,6 +323,7 @@ int ip6_input(struct sk_buff *skb) dev_net(skb->dev), NULL, skb, skb->dev, NULL, ip6_input_finish); } +EXPORT_SYMBOL_GPL(ip6_input); int ip6_mc_input(struct sk_buff *skb) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 635b8d340cdb..fd3217579b65 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -368,7 +368,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->ignore_df) return false; - if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) return false; return true; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 0a5a255277e5..d9f2bd6ef72d 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -825,9 +825,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); - if (skb->protocol != htons(ETH_P_IPV6)) - goto tx_error; - if (tos == 1) tos = ipv6_get_dsfield(iph6); diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index e253c26f31ac..57fc5a46ce06 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -67,7 +67,6 @@ static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net) return net_generic(net, l2tp_eth_net_id); } -static struct lock_class_key l2tp_eth_tx_busylock; static int l2tp_eth_dev_init(struct net_device *dev) { struct l2tp_eth *priv = netdev_priv(dev); @@ -75,7 +74,8 @@ static int l2tp_eth_dev_init(struct net_device *dev) priv->dev = dev; eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); - dev->qdisc_tx_busylock = &l2tp_eth_tx_busylock; + netdev_lockdep_set_classes(dev); + return 0; } diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 6651a78e100c..7da97809a7e8 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -10,6 +10,7 @@ */ #include <linux/netdevice.h> +#include <net/fib_rules.h> #include <net/l3mdev.h> /** @@ -160,3 +161,40 @@ int l3mdev_get_saddr(struct net *net, int ifindex, struct flowi4 *fl4) return rc; } EXPORT_SYMBOL_GPL(l3mdev_get_saddr); + +/** + * l3mdev_fib_rule_match - Determine if flowi references an + * L3 master device + * @net: network namespace for device index lookup + * @fl: flow struct + */ + +int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, + struct fib_lookup_arg *arg) +{ + struct net_device *dev; + int rc = 0; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, fl->flowi_oif); + if (dev && netif_is_l3_master(dev) && + dev->l3mdev_ops->l3mdev_fib_table) { + arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev); + rc = 1; + goto out; + } + + dev = dev_get_by_index_rcu(net, fl->flowi_iif); + if (dev && netif_is_l3_master(dev) && + dev->l3mdev_ops->l3mdev_fib_table) { + arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev); + rc = 1; + goto out; + } + +out: + rcu_read_unlock(); + + return rc; +} diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 0b80a7140cc4..7a4aa3450dd7 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -91,7 +91,7 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) if (skb->len <= mtu) return false; - if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu)) return false; return true; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index 604df6fae6fc..515131f9e021 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -137,7 +137,7 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par) cfg.est.ewma_log = info->ewma_log; ret = gen_new_estimator(&est->bstats, NULL, &est->rstats, - &est->lock, &cfg.opt); + &est->lock, NULL, &cfg.opt); if (ret < 0) goto err2; diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h index e68ef9ccd703..3cfd6cc60504 100644 --- a/net/netlink/af_netlink.h +++ b/net/netlink/af_netlink.h @@ -8,20 +8,6 @@ #define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8) #define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long)) -struct netlink_ring { - void **pg_vec; - unsigned int head; - unsigned int frames_per_block; - unsigned int frame_size; - unsigned int frame_max; - - unsigned int pg_vec_order; - unsigned int pg_vec_pages; - unsigned int pg_vec_len; - - atomic_t pending; -}; - struct netlink_sock { /* struct sock has to be the first member of netlink_sock */ struct sock sk; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 2ee48e447b72..434e04c3a189 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -195,7 +195,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) } vport->dev = alloc_netdev(sizeof(struct internal_dev), - parms->name, NET_NAME_UNKNOWN, do_setup); + parms->name, NET_NAME_USER, do_setup); if (!vport->dev) { err = -ENOMEM; goto error_free_vport; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index e45e94ca030f..38512a200db6 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/net.h> @@ -137,33 +139,33 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) lock_sock(&rx->sk); - if (rx->sk.sk_state != RXRPC_UNCONNECTED) { + if (rx->sk.sk_state != RXRPC_UNBOUND) { ret = -EINVAL; goto error_unlock; } memcpy(&rx->srx, srx, sizeof(rx->srx)); - /* Find or create a local transport endpoint to use */ local = rxrpc_lookup_local(&rx->srx); if (IS_ERR(local)) { ret = PTR_ERR(local); goto error_unlock; } - rx->local = local; - if (srx->srx_service) { + if (rx->srx.srx_service) { write_lock_bh(&local->services_lock); list_for_each_entry(prx, &local->services, listen_link) { - if (prx->srx.srx_service == srx->srx_service) + if (prx->srx.srx_service == rx->srx.srx_service) goto service_in_use; } + rx->local = local; list_add_tail(&rx->listen_link, &local->services); write_unlock_bh(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; } else { + rx->local = local; rx->sk.sk_state = RXRPC_CLIENT_BOUND; } @@ -172,8 +174,9 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) return 0; service_in_use: - ret = -EADDRINUSE; write_unlock_bh(&local->services_lock); + rxrpc_put_local(local); + ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); error: @@ -195,11 +198,11 @@ static int rxrpc_listen(struct socket *sock, int backlog) lock_sock(&rx->sk); switch (rx->sk.sk_state) { - case RXRPC_UNCONNECTED: + case RXRPC_UNBOUND: ret = -EADDRNOTAVAIL; break; + case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: - case RXRPC_CLIENT_CONNECTED: default: ret = -EBUSY; break; @@ -219,20 +222,18 @@ static int rxrpc_listen(struct socket *sock, int backlog) /* * find a transport by address */ -static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock, - struct sockaddr *addr, - int addr_len, int flags, - gfp_t gfp) +struct rxrpc_transport *rxrpc_name_to_transport(struct rxrpc_sock *rx, + struct sockaddr *addr, + int addr_len, int flags, + gfp_t gfp) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr; struct rxrpc_transport *trans; - struct rxrpc_sock *rx = rxrpc_sk(sock->sk); struct rxrpc_peer *peer; _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); ASSERT(rx->local != NULL); - ASSERT(rx->sk.sk_state > RXRPC_UNCONNECTED); if (rx->srx.transport_type != srx->transport_type) return ERR_PTR(-ESOCKTNOSUPPORT); @@ -254,7 +255,7 @@ static struct rxrpc_transport *rxrpc_name_to_transport(struct socket *sock, /** * rxrpc_kernel_begin_call - Allow a kernel service to begin a call * @sock: The socket on which to make the call - * @srx: The address of the peer to contact (defaults to socket setting) + * @srx: The address of the peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use * @@ -280,25 +281,14 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, lock_sock(&rx->sk); - if (srx) { - trans = rxrpc_name_to_transport(sock, (struct sockaddr *) srx, - sizeof(*srx), 0, gfp); - if (IS_ERR(trans)) { - call = ERR_CAST(trans); - trans = NULL; - goto out_notrans; - } - } else { - trans = rx->trans; - if (!trans) { - call = ERR_PTR(-ENOTCONN); - goto out_notrans; - } - atomic_inc(&trans->usage); + trans = rxrpc_name_to_transport(rx, (struct sockaddr *)srx, + sizeof(*srx), 0, gfp); + if (IS_ERR(trans)) { + call = ERR_CAST(trans); + trans = NULL; + goto out_notrans; } - if (!srx) - srx = &rx->srx; if (!key) key = rx->key; if (key && !key->payload.data[0]) @@ -310,8 +300,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, goto out; } - call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, true, - gfp); + call = rxrpc_new_client_call(rx, trans, bundle, user_call_ID, gfp); rxrpc_put_bundle(trans, bundle); out: rxrpc_put_transport(trans); @@ -367,11 +356,8 @@ EXPORT_SYMBOL(rxrpc_kernel_intercept_rx_messages); static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, int addr_len, int flags) { - struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *) addr; - struct sock *sk = sock->sk; - struct rxrpc_transport *trans; - struct rxrpc_local *local; - struct rxrpc_sock *rx = rxrpc_sk(sk); + struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr; + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; _enter("%p,%p,%d,%d", rx, addr, addr_len, flags); @@ -384,45 +370,28 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, lock_sock(&rx->sk); + ret = -EISCONN; + if (test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) + goto error; + switch (rx->sk.sk_state) { - case RXRPC_UNCONNECTED: - /* find a local transport endpoint if we don't have one already */ - ASSERTCMP(rx->local, ==, NULL); - rx->srx.srx_family = AF_RXRPC; - rx->srx.srx_service = 0; - rx->srx.transport_type = srx->transport_type; - rx->srx.transport_len = sizeof(sa_family_t); - rx->srx.transport.family = srx->transport.family; - local = rxrpc_lookup_local(&rx->srx); - if (IS_ERR(local)) { - release_sock(&rx->sk); - return PTR_ERR(local); - } - rx->local = local; - rx->sk.sk_state = RXRPC_CLIENT_BOUND; + case RXRPC_UNBOUND: + rx->sk.sk_state = RXRPC_CLIENT_UNBOUND; + case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: break; - case RXRPC_CLIENT_CONNECTED: - release_sock(&rx->sk); - return -EISCONN; default: - release_sock(&rx->sk); - return -EBUSY; /* server sockets can't connect as well */ - } - - trans = rxrpc_name_to_transport(sock, addr, addr_len, flags, - GFP_KERNEL); - if (IS_ERR(trans)) { - release_sock(&rx->sk); - _leave(" = %ld", PTR_ERR(trans)); - return PTR_ERR(trans); + ret = -EBUSY; + goto error; } - rx->trans = trans; - rx->sk.sk_state = RXRPC_CLIENT_CONNECTED; + rx->connect_srx = *srx; + set_bit(RXRPC_SOCK_CONNECTED, &rx->flags); + ret = 0; +error: release_sock(&rx->sk); - return 0; + return ret; } /* @@ -436,7 +405,7 @@ static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, */ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) { - struct rxrpc_transport *trans; + struct rxrpc_local *local; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); int ret; @@ -453,48 +422,38 @@ static int rxrpc_sendmsg(struct socket *sock, struct msghdr *m, size_t len) } } - trans = NULL; lock_sock(&rx->sk); - if (m->msg_name) { - ret = -EISCONN; - trans = rxrpc_name_to_transport(sock, m->msg_name, - m->msg_namelen, 0, GFP_KERNEL); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - } else { - trans = rx->trans; - if (trans) - atomic_inc(&trans->usage); - } - switch (rx->sk.sk_state) { - case RXRPC_SERVER_LISTENING: - if (!m->msg_name) { - ret = rxrpc_server_sendmsg(rx, m, len); - break; + case RXRPC_UNBOUND: + local = rxrpc_lookup_local(&rx->srx); + if (IS_ERR(local)) { + ret = PTR_ERR(local); + goto error_unlock; } - case RXRPC_SERVER_BOUND: + + rx->local = local; + rx->sk.sk_state = RXRPC_CLIENT_UNBOUND; + /* Fall through */ + + case RXRPC_CLIENT_UNBOUND: case RXRPC_CLIENT_BOUND: - if (!m->msg_name) { - ret = -ENOTCONN; - break; + if (!m->msg_name && + test_bit(RXRPC_SOCK_CONNECTED, &rx->flags)) { + m->msg_name = &rx->connect_srx; + m->msg_namelen = sizeof(rx->connect_srx); } - case RXRPC_CLIENT_CONNECTED: - ret = rxrpc_client_sendmsg(rx, trans, m, len); + case RXRPC_SERVER_BOUND: + case RXRPC_SERVER_LISTENING: + ret = rxrpc_do_sendmsg(rx, m, len); break; default: - ret = -ENOTCONN; + ret = -EINVAL; break; } -out: +error_unlock: release_sock(&rx->sk); - if (trans) - rxrpc_put_transport(trans); _leave(" = %d", ret); return ret; } @@ -521,7 +480,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (optlen != 0) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; set_bit(RXRPC_SOCK_EXCLUSIVE_CONN, &rx->flags); goto success; @@ -531,7 +490,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (rx->key) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_request_key(rx, optval, optlen); goto error; @@ -541,7 +500,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (rx->key) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = rxrpc_server_keyring(rx, optval, optlen); goto error; @@ -551,7 +510,7 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname, if (optlen != sizeof(unsigned int)) goto error; ret = -EISCONN; - if (rx->sk.sk_state != RXRPC_UNCONNECTED) + if (rx->sk.sk_state != RXRPC_UNBOUND) goto error; ret = get_user(min_sec_level, (unsigned int __user *) optval); @@ -630,7 +589,7 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol, return -ENOMEM; sock_init_data(sock, sk); - sk->sk_state = RXRPC_UNCONNECTED; + sk->sk_state = RXRPC_UNBOUND; sk->sk_write_space = rxrpc_write_space; sk->sk_max_ack_backlog = sysctl_rxrpc_max_qlen; sk->sk_destruct = rxrpc_sock_destructor; @@ -703,14 +662,6 @@ static int rxrpc_release_sock(struct sock *sk) rx->conn = NULL; } - if (rx->bundle) { - rxrpc_put_bundle(rx->trans, rx->bundle); - rx->bundle = NULL; - } - if (rx->trans) { - rxrpc_put_transport(rx->trans); - rx->trans = NULL; - } if (rx->local) { rxrpc_put_local(rx->local); rx->local = NULL; @@ -796,49 +747,49 @@ static int __init af_rxrpc_init(void) "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, SLAB_HWCACHE_ALIGN, NULL); if (!rxrpc_call_jar) { - printk(KERN_NOTICE "RxRPC: Failed to allocate call jar\n"); + pr_notice("Failed to allocate call jar\n"); goto error_call_jar; } rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); if (!rxrpc_workqueue) { - printk(KERN_NOTICE "RxRPC: Failed to allocate work queue\n"); + pr_notice("Failed to allocate work queue\n"); goto error_work_queue; } ret = rxrpc_init_security(); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot initialise security\n"); + pr_crit("Cannot initialise security\n"); goto error_security; } ret = proto_register(&rxrpc_proto, 1); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register protocol\n"); + pr_crit("Cannot register protocol\n"); goto error_proto; } ret = sock_register(&rxrpc_family_ops); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register socket family\n"); + pr_crit("Cannot register socket family\n"); goto error_sock; } ret = register_key_type(&key_type_rxrpc); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register client key type\n"); + pr_crit("Cannot register client key type\n"); goto error_key_type; } ret = register_key_type(&key_type_rxrpc_s); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register server key type\n"); + pr_crit("Cannot register server key type\n"); goto error_key_type_s; } ret = rxrpc_sysctl_init(); if (ret < 0) { - printk(KERN_CRIT "RxRPC: Cannot register sysctls\n"); + pr_crit("Cannot register sysctls\n"); goto error_sysctls; } diff --git a/net/rxrpc/ar-accept.c b/net/rxrpc/ar-accept.c index e7a7f05f13e2..eea5f4a5d8b1 100644 --- a/net/rxrpc/ar-accept.c +++ b/net/rxrpc/ar-accept.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-ack.c b/net/rxrpc/ar-ack.c index 374478e006e7..18381783c2b1 100644 --- a/net/rxrpc/ar-ack.c +++ b/net/rxrpc/ar-ack.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/circ_buf.h> #include <linux/net.h> diff --git a/net/rxrpc/ar-call.c b/net/rxrpc/ar-call.c index 571a41fd5a32..68125dc4cb7c 100644 --- a/net/rxrpc/ar-call.c +++ b/net/rxrpc/ar-call.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/slab.h> #include <linux/module.h> #include <linux/circ_buf.h> @@ -194,6 +196,43 @@ struct rxrpc_call *rxrpc_find_call_hash( } /* + * find an extant server call + * - called in process context with IRQs enabled + */ +struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, + unsigned long user_call_ID) +{ + struct rxrpc_call *call; + struct rb_node *p; + + _enter("%p,%lx", rx, user_call_ID); + + read_lock(&rx->call_lock); + + p = rx->calls.rb_node; + while (p) { + call = rb_entry(p, struct rxrpc_call, sock_node); + + if (user_call_ID < call->user_call_ID) + p = p->rb_left; + else if (user_call_ID > call->user_call_ID) + p = p->rb_right; + else + goto found_extant_call; + } + + read_unlock(&rx->call_lock); + _leave(" = NULL"); + return NULL; + +found_extant_call: + rxrpc_get_call(call); + read_unlock(&rx->call_lock); + _leave(" = %p [%d]", call, atomic_read(&call->usage)); + return call; +} + +/* * allocate a new call */ static struct rxrpc_call *rxrpc_alloc_call(gfp_t gfp) @@ -309,51 +348,27 @@ static struct rxrpc_call *rxrpc_alloc_client_call( * set up a call for the given data * - called in process context with IRQs enabled */ -struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, +struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_transport *trans, struct rxrpc_conn_bundle *bundle, unsigned long user_call_ID, - int create, gfp_t gfp) { - struct rxrpc_call *call, *candidate; - struct rb_node *p, *parent, **pp; - - _enter("%p,%d,%d,%lx,%d", - rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1, - user_call_ID, create); - - /* search the extant calls first for one that matches the specified - * user ID */ - read_lock(&rx->call_lock); - - p = rx->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - p = p->rb_left; - else if (user_call_ID > call->user_call_ID) - p = p->rb_right; - else - goto found_extant_call; - } - - read_unlock(&rx->call_lock); + struct rxrpc_call *call, *xcall; + struct rb_node *parent, **pp; - if (!create || !trans) - return ERR_PTR(-EBADSLT); + _enter("%p,%d,%d,%lx", + rx, trans->debug_id, bundle ? bundle->debug_id : -1, + user_call_ID); - /* not yet present - create a candidate for a new record and then - * redo the search */ - candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp); - if (IS_ERR(candidate)) { - _leave(" = %ld", PTR_ERR(candidate)); - return candidate; + call = rxrpc_alloc_client_call(rx, trans, bundle, gfp); + if (IS_ERR(call)) { + _leave(" = %ld", PTR_ERR(call)); + return call; } - candidate->user_call_ID = user_call_ID; - __set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags); + call->user_call_ID = user_call_ID; + __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); write_lock(&rx->call_lock); @@ -361,19 +376,16 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, parent = NULL; while (*pp) { parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); + xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else - goto found_extant_second; + goto found_user_ID_now_present; } - /* second search also failed; add the new call */ - call = candidate; - candidate = NULL; rxrpc_get_call(call); rb_link_node(&call->sock_node, parent, pp); @@ -389,20 +401,16 @@ struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx, _leave(" = %p [new]", call); return call; - /* we found the call in the list immediately */ -found_extant_call: - rxrpc_get_call(call); - read_unlock(&rx->call_lock); - _leave(" = %p [extant %d]", call, atomic_read(&call->usage)); - return call; - - /* we found the call on the second time through the list */ -found_extant_second: - rxrpc_get_call(call); + /* We unexpectedly found the user ID in the list after taking + * the call_lock. This shouldn't happen unless the user races + * with itself and tries to add the same user ID twice at the + * same time in different threads. + */ +found_user_ID_now_present: write_unlock(&rx->call_lock); - rxrpc_put_call(candidate); - _leave(" = %p [second %d]", call, atomic_read(&call->usage)); - return call; + rxrpc_put_call(call); + _leave(" = -EEXIST [%p]", call); + return ERR_PTR(-EEXIST); } /* @@ -564,46 +572,6 @@ old_call: } /* - * find an extant server call - * - called in process context with IRQs enabled - */ -struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *rx, - unsigned long user_call_ID) -{ - struct rxrpc_call *call; - struct rb_node *p; - - _enter("%p,%lx", rx, user_call_ID); - - /* search the extant calls for one that matches the specified user - * ID */ - read_lock(&rx->call_lock); - - p = rx->calls.rb_node; - while (p) { - call = rb_entry(p, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - p = p->rb_left; - else if (user_call_ID > call->user_call_ID) - p = p->rb_right; - else - goto found_extant_call; - } - - read_unlock(&rx->call_lock); - _leave(" = NULL"); - return NULL; - - /* we found the call in the list immediately */ -found_extant_call: - rxrpc_get_call(call); - read_unlock(&rx->call_lock); - _leave(" = %p [%d]", call, atomic_read(&call->usage)); - return call; -} - -/* * detach a call from a socket and set up for release */ void rxrpc_release_call(struct rxrpc_call *call) @@ -669,8 +637,7 @@ void rxrpc_release_call(struct rxrpc_call *call) conn->channels[3] == NULL); break; default: - printk(KERN_ERR "RxRPC: conn->avail_calls=%d\n", - conn->avail_calls); + pr_err("conn->avail_calls=%d\n", conn->avail_calls); BUG(); } } @@ -935,16 +902,15 @@ void __exit rxrpc_destroy_all_calls(void) if (call->state != RXRPC_CALL_DEAD) break; default: - printk(KERN_ERR "RXRPC:" - " Call %p still in use (%d,%d,%s,%lx,%lx)!\n", + pr_err("Call %p still in use (%d,%d,%s,%lx,%lx)!\n", call, atomic_read(&call->usage), atomic_read(&call->ackr_not_idle), rxrpc_call_states[call->state], call->flags, call->events); if (!skb_queue_empty(&call->rx_queue)) - printk(KERN_ERR"RXRPC: Rx queue occupied\n"); + pr_err("Rx queue occupied\n"); if (!skb_queue_empty(&call->rx_oos_queue)) - printk(KERN_ERR"RXRPC: OOS queue occupied\n"); + pr_err("OOS queue occupied\n"); break; } diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 97f4fae74bca..8ecde4b77b55 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/net.h> @@ -78,11 +80,6 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx, _enter("%p{%x},%x,%hx,", rx, key_serial(key), trans->debug_id, service_id); - if (rx->trans == trans && rx->bundle) { - atomic_inc(&rx->bundle->usage); - return rx->bundle; - } - /* search the extant bundles first for one that matches the specified * user ID */ spin_lock(&trans->client_lock); @@ -136,10 +133,6 @@ struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx, rb_insert_color(&bundle->node, &trans->bundles); spin_unlock(&trans->client_lock); _net("BUNDLE new on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } _leave(" = %p [new]", bundle); return bundle; @@ -148,10 +141,6 @@ found_extant_bundle: atomic_inc(&bundle->usage); spin_unlock(&trans->client_lock); _net("BUNDLE old on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } _leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage)); return bundle; @@ -161,10 +150,6 @@ found_extant_second: spin_unlock(&trans->client_lock); kfree(candidate); _net("BUNDLE old2 on trans %d", trans->debug_id); - if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) { - atomic_inc(&bundle->usage); - rx->bundle = bundle; - } _leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage)); return bundle; } diff --git a/net/rxrpc/ar-connevent.c b/net/rxrpc/ar-connevent.c index 5f9563968a5b..8bdd692d4862 100644 --- a/net/rxrpc/ar-connevent.c +++ b/net/rxrpc/ar-connevent.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index 6ff97412a0bb..d7c2a0bc839e 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index f0b807a163fa..b89dcdcbc65a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -39,9 +39,9 @@ struct rxrpc_crypt { * sk_state for RxRPC sockets */ enum { - RXRPC_UNCONNECTED = 0, + RXRPC_UNBOUND = 0, + RXRPC_CLIENT_UNBOUND, /* Unbound socket used as client */ RXRPC_CLIENT_BOUND, /* client local address bound */ - RXRPC_CLIENT_CONNECTED, /* client is connected */ RXRPC_SERVER_BOUND, /* server local address bound */ RXRPC_SERVER_LISTENING, /* server listening for connections */ RXRPC_CLOSE, /* socket is being closed */ @@ -55,8 +55,6 @@ struct rxrpc_sock { struct sock sk; rxrpc_interceptor_t interceptor; /* kernel service Rx interceptor function */ struct rxrpc_local *local; /* local endpoint */ - struct rxrpc_transport *trans; /* transport handler */ - struct rxrpc_conn_bundle *bundle; /* virtual connection bundle */ struct rxrpc_connection *conn; /* exclusive virtual connection */ struct list_head listen_link; /* link in the local endpoint's listen list */ struct list_head secureq; /* calls awaiting connection security clearance */ @@ -65,11 +63,13 @@ struct rxrpc_sock { struct key *securities; /* list of server security descriptors */ struct rb_root calls; /* outstanding calls on this socket */ unsigned long flags; +#define RXRPC_SOCK_CONNECTED 0 /* connect_srx is set */ #define RXRPC_SOCK_EXCLUSIVE_CONN 1 /* exclusive connection for a client socket */ rwlock_t call_lock; /* lock for calls */ u32 min_sec_level; /* minimum security level */ #define RXRPC_SECURITY_MAX RXRPC_SECURITY_ENCRYPT struct sockaddr_rxrpc srx; /* local address */ + struct sockaddr_rxrpc connect_srx; /* Default client address from connect() */ sa_family_t proto; /* protocol created with */ }; @@ -477,6 +477,10 @@ extern u32 rxrpc_epoch; extern atomic_t rxrpc_debug_id; extern struct workqueue_struct *rxrpc_workqueue; +extern struct rxrpc_transport *rxrpc_name_to_transport(struct rxrpc_sock *, + struct sockaddr *, + int, int, gfp_t); + /* * ar-accept.c */ @@ -502,14 +506,14 @@ extern rwlock_t rxrpc_call_lock; struct rxrpc_call *rxrpc_find_call_hash(struct rxrpc_host_header *, void *, sa_family_t, const void *); -struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *, +struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); +struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_transport *, struct rxrpc_conn_bundle *, - unsigned long, int, gfp_t); + unsigned long, gfp_t); struct rxrpc_call *rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_connection *, struct rxrpc_host_header *); -struct rxrpc_call *rxrpc_find_server_call(struct rxrpc_sock *, unsigned long); void rxrpc_release_call(struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); void __rxrpc_put_call(struct rxrpc_call *); @@ -581,9 +585,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time_t, extern unsigned int rxrpc_resend_timeout; int rxrpc_send_packet(struct rxrpc_transport *, struct sk_buff *); -int rxrpc_client_sendmsg(struct rxrpc_sock *, struct rxrpc_transport *, - struct msghdr *, size_t); -int rxrpc_server_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); +int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* * ar-peer.c @@ -744,21 +746,18 @@ do { \ #define ASSERT(X) \ do { \ if (unlikely(!(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTCMP(X, OP, Y) \ do { \ - if (unlikely(!((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ - printk(KERN_ERR "%lu " #OP " %lu is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ + unsigned long _x = (unsigned long)(X); \ + unsigned long _y = (unsigned long)(Y); \ + if (unlikely(!(_x OP _y))) { \ + pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ + _x, _x, #OP, _y, _y); \ BUG(); \ } \ } while (0) @@ -766,21 +765,18 @@ do { \ #define ASSERTIF(C, X) \ do { \ if (unlikely((C) && !(X))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ + pr_err("Assertion failed\n"); \ BUG(); \ } \ } while (0) #define ASSERTIFCMP(C, X, OP, Y) \ do { \ - if (unlikely((C) && !((X) OP (Y)))) { \ - printk(KERN_ERR "\n"); \ - printk(KERN_ERR "RxRPC: Assertion failed\n"); \ - printk(KERN_ERR "%lu " #OP " %lu is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - printk(KERN_ERR "0x%lx " #OP " 0x%lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ + unsigned long _x = (unsigned long)(X); \ + unsigned long _y = (unsigned long)(Y); \ + if (unlikely((C) && !(_x OP _y))) { \ + pr_err("Assertion failed - %lu(0x%lx) %s %lu(0x%lx) is false\n", \ + _x, _x, #OP, _y, _y); \ BUG(); \ } \ } while (0) diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 1021b4c0bdd2..4ad56fafe3a7 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -12,6 +12,8 @@ * "afs@CAMBRIDGE.REDHAT.COM> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> @@ -800,7 +802,7 @@ static void rxrpc_free_token_list(struct rxrpc_key_token *token) rxrpc_rxk5_free(token->k5); break; default: - printk(KERN_ERR "Unknown token type %x on rxrpc key\n", + pr_err("Unknown token type %x on rxrpc key\n", token->security_index); BUG(); } diff --git a/net/rxrpc/ar-local.c b/net/rxrpc/ar-local.c index 4e1e6db0050b..701c42b7050e 100644 --- a/net/rxrpc/ar-local.c +++ b/net/rxrpc/ar-local.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index 51cb10062a8d..2e3c4064e29c 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/net.h> #include <linux/gfp.h> #include <linux/skbuff.h> @@ -30,13 +32,13 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* * extract control messages from the sendmsg() control buffer */ -static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, +static int rxrpc_sendmsg_cmsg(struct msghdr *msg, unsigned long *user_call_ID, enum rxrpc_command *command, - u32 *abort_code, - bool server) + u32 *abort_code) { struct cmsghdr *cmsg; + bool got_user_ID = false; int len; *command = RXRPC_CMD_SEND_DATA; @@ -68,6 +70,7 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, CMSG_DATA(cmsg); } _debug("User Call ID %lx", *user_call_ID); + got_user_ID = true; break; case RXRPC_ABORT: @@ -88,8 +91,6 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, *command = RXRPC_CMD_ACCEPT; if (len != 0) return -EINVAL; - if (!server) - return -EISCONN; break; default: @@ -97,6 +98,8 @@ static int rxrpc_sendmsg_cmsg(struct rxrpc_sock *rx, struct msghdr *msg, } } + if (!got_user_ID) + return -EINVAL; _leave(" = 0"); return 0; } @@ -124,55 +127,96 @@ static void rxrpc_send_abort(struct rxrpc_call *call, u32 abort_code) } /* + * Create a new client call for sendmsg(). + */ +static struct rxrpc_call * +rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, + unsigned long user_call_ID) +{ + struct rxrpc_conn_bundle *bundle; + struct rxrpc_transport *trans; + struct rxrpc_call *call; + struct key *key; + long ret; + + DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name); + + _enter(""); + + if (!msg->msg_name) + return ERR_PTR(-EDESTADDRREQ); + + trans = rxrpc_name_to_transport(rx, msg->msg_name, msg->msg_namelen, 0, + GFP_KERNEL); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out; + } + + key = rx->key; + if (key && !rx->key->payload.data[0]) + key = NULL; + bundle = rxrpc_get_bundle(rx, trans, key, srx->srx_service, GFP_KERNEL); + if (IS_ERR(bundle)) { + ret = PTR_ERR(bundle); + goto out_trans; + } + + call = rxrpc_new_client_call(rx, trans, bundle, user_call_ID, + GFP_KERNEL); + rxrpc_put_bundle(trans, bundle); + rxrpc_put_transport(trans); + if (IS_ERR(call)) { + ret = PTR_ERR(call); + goto out_trans; + } + + _leave(" = %p\n", call); + return call; + +out_trans: + rxrpc_put_transport(trans); +out: + _leave(" = %ld", ret); + return ERR_PTR(ret); +} + +/* * send a message forming part of a client call through an RxRPC socket * - caller holds the socket locked * - the socket may be either a client socket or a server socket */ -int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans, - struct msghdr *msg, size_t len) +int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) { - struct rxrpc_conn_bundle *bundle; enum rxrpc_command cmd; struct rxrpc_call *call; unsigned long user_call_ID = 0; - struct key *key; - u16 service_id; u32 abort_code = 0; int ret; _enter(""); - ASSERT(trans != NULL); - - ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, - false); + ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code); if (ret < 0) return ret; - bundle = NULL; - if (trans) { - service_id = rx->srx.srx_service; - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, - msg->msg_name); - service_id = srx->srx_service; - } - key = rx->key; - if (key && !rx->key->payload.data[0]) - key = NULL; - bundle = rxrpc_get_bundle(rx, trans, key, service_id, - GFP_KERNEL); - if (IS_ERR(bundle)) - return PTR_ERR(bundle); + if (cmd == RXRPC_CMD_ACCEPT) { + if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) + return -EINVAL; + call = rxrpc_accept_call(rx, user_call_ID); + if (IS_ERR(call)) + return PTR_ERR(call); + rxrpc_put_call(call); + return 0; } - call = rxrpc_get_client_call(rx, trans, bundle, user_call_ID, - abort_code == 0, GFP_KERNEL); - if (trans) - rxrpc_put_bundle(trans, bundle); - if (IS_ERR(call)) { - _leave(" = %ld", PTR_ERR(call)); - return PTR_ERR(call); + call = rxrpc_find_call_by_user_ID(rx, user_call_ID); + if (!call) { + if (cmd != RXRPC_CMD_SEND_DATA) + return -EBADSLT; + call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID); + if (IS_ERR(call)) + return PTR_ERR(call); } _debug("CALL %d USR %lx ST %d on CONN %p", @@ -180,14 +224,21 @@ int rxrpc_client_sendmsg(struct rxrpc_sock *rx, struct rxrpc_transport *trans, if (call->state >= RXRPC_CALL_COMPLETE) { /* it's too late for this call */ - ret = -ESHUTDOWN; + ret = -ECONNRESET; } else if (cmd == RXRPC_CMD_SEND_ABORT) { rxrpc_send_abort(call, abort_code); + ret = 0; } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; - } else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { + } else if (!call->in_clientflag && + call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) { /* request phase complete for this client call */ ret = -EPROTO; + } else if (call->in_clientflag && + call->state != RXRPC_CALL_SERVER_ACK_REQUEST && + call->state != RXRPC_CALL_SERVER_SEND_REPLY) { + /* Reply phase not begun or not complete for service call. */ + ret = -EPROTO; } else { ret = rxrpc_send_data(rx, call, msg, len); } @@ -266,67 +317,6 @@ void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code) EXPORT_SYMBOL(rxrpc_kernel_abort_call); /* - * send a message through a server socket - * - caller holds the socket locked - */ -int rxrpc_server_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) -{ - enum rxrpc_command cmd; - struct rxrpc_call *call; - unsigned long user_call_ID = 0; - u32 abort_code = 0; - int ret; - - _enter(""); - - ret = rxrpc_sendmsg_cmsg(rx, msg, &user_call_ID, &cmd, &abort_code, - true); - if (ret < 0) - return ret; - - if (cmd == RXRPC_CMD_ACCEPT) { - call = rxrpc_accept_call(rx, user_call_ID); - if (IS_ERR(call)) - return PTR_ERR(call); - rxrpc_put_call(call); - return 0; - } - - call = rxrpc_find_server_call(rx, user_call_ID); - if (!call) - return -EBADSLT; - if (call->state >= RXRPC_CALL_COMPLETE) { - ret = -ESHUTDOWN; - goto out; - } - - switch (cmd) { - case RXRPC_CMD_SEND_DATA: - if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST && - call->state != RXRPC_CALL_SERVER_ACK_REQUEST && - call->state != RXRPC_CALL_SERVER_SEND_REPLY) { - /* Tx phase not yet begun for this call */ - ret = -EPROTO; - break; - } - - ret = rxrpc_send_data(rx, call, msg, len); - break; - - case RXRPC_CMD_SEND_ABORT: - rxrpc_send_abort(call, abort_code); - break; - default: - BUG(); - } - - out: - rxrpc_put_call(call); - _leave(" = %d", ret); - return ret; -} - -/* * send a packet through the transport endpoint */ int rxrpc_send_packet(struct rxrpc_transport *trans, struct sk_buff *skb) diff --git a/net/rxrpc/ar-peer.c b/net/rxrpc/ar-peer.c index dc089b1976aa..0b54cda3d8e5 100644 --- a/net/rxrpc/ar-peer.c +++ b/net/rxrpc/ar-peer.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c index 160f0927aa3e..59706b9f2f7a 100644 --- a/net/rxrpc/ar-recvmsg.c +++ b/net/rxrpc/ar-recvmsg.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/net.h> #include <linux/skbuff.h> #include <linux/export.h> @@ -307,7 +309,7 @@ receive_non_data_message: &abort_code); break; default: - pr_err("RxRPC: Unknown packet mark %u\n", skb->mark); + pr_err("Unknown packet mark %u\n", skb->mark); BUG(); break; } diff --git a/net/rxrpc/ar-skbuff.c b/net/rxrpc/ar-skbuff.c index 62a267472fce..eee0cfd9ac8c 100644 --- a/net/rxrpc/ar-skbuff.c +++ b/net/rxrpc/ar-skbuff.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 66a1a5676446..a1b65183b07d 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index bab56ed649ba..36a634027d9d 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -9,6 +9,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <crypto/skcipher.h> #include <linux/module.h> #include <linux/net.h> diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 336774a535c3..b6db56ec8117 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -283,10 +283,11 @@ err2: p->tcfc_index = index ? index : tcf_hash_new_index(tn); p->tcfc_tm.install = jiffies; p->tcfc_tm.lastuse = jiffies; + p->tcfc_tm.firstuse = 0; if (est) { err = gen_new_estimator(&p->tcfc_bstats, p->cpu_bstats, &p->tcfc_rate_est, - &p->tcfc_lock, est); + &p->tcfc_lock, NULL, est); if (err) { free_percpu(p->cpu_qstats); goto err2; @@ -503,8 +504,8 @@ nla_put_failure: } EXPORT_SYMBOL(tcf_action_dump_1); -int -tcf_action_dump(struct sk_buff *skb, struct list_head *actions, int bind, int ref) +int tcf_action_dump(struct sk_buff *skb, struct list_head *actions, + int bind, int ref) { struct tc_action *a; int err = -EINVAL; @@ -670,7 +671,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a, if (err < 0) goto errout; - if (gnet_stats_copy_basic(&d, p->cpu_bstats, &p->tcfc_bstats) < 0 || + if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfc_bstats) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfc_bstats, &p->tcfc_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, @@ -687,9 +688,9 @@ errout: return -1; } -static int -tca_get_fill(struct sk_buff *skb, struct list_head *actions, u32 portid, u32 seq, - u16 flags, int event, int bind, int ref) +static int tca_get_fill(struct sk_buff *skb, struct list_head *actions, + u32 portid, u32 seq, u16 flags, int event, int bind, + int ref) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -730,7 +731,8 @@ act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { + if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event, + 0, 0) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -838,7 +840,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (a.ops == NULL) /*some idjot trying to flush unknown action */ goto err_out; - nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); + nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, + sizeof(*t), 0); if (!nlh) goto out_module_put; t = nlmsg_data(nlh); @@ -1001,7 +1004,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; - if ((n->nlmsg_type != RTM_GETACTION) && !netlink_capable(skb, CAP_NET_ADMIN)) + if ((n->nlmsg_type != RTM_GETACTION) && + !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index c7123e01c2ca..f7b6cf49ea6f 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -154,10 +154,7 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act, if (ret) goto nla_put_failure; - tm.install = jiffies_to_clock_t(jiffies - prog->tcf_tm.install); - tm.lastuse = jiffies_to_clock_t(jiffies - prog->tcf_tm.lastuse); - tm.expires = jiffies_to_clock_t(prog->tcf_tm.expires); - + tcf_tm_dump(&tm, &prog->tcf_tm); if (nla_put_64bit(skb, TCA_ACT_BPF_TM, sizeof(tm), &tm, TCA_ACT_BPF_PAD)) goto nla_put_failure; @@ -172,7 +169,8 @@ nla_put_failure: static const struct nla_policy act_bpf_policy[TCA_ACT_BPF_MAX + 1] = { [TCA_ACT_BPF_PARMS] = { .len = sizeof(struct tc_act_bpf) }, [TCA_ACT_BPF_FD] = { .type = NLA_U32 }, - [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, .len = ACT_BPF_NAME_LEN }, + [TCA_ACT_BPF_NAME] = { .type = NLA_NUL_STRING, + .len = ACT_BPF_NAME_LEN }, [TCA_ACT_BPF_OPS_LEN] = { .type = NLA_U16 }, [TCA_ACT_BPF_OPS] = { .type = NLA_BINARY, .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2ba700c765e0..35a5270f289d 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -44,7 +44,7 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, int proto; spin_lock(&ca->tcf_lock); - ca->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); if (skb->protocol == htons(ETH_P_IP)) { @@ -160,9 +160,7 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - ci->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - ci->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(ci->tcf_tm.expires); + tcf_tm_dump(&t, &ci->tcf_tm); if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_PAD)) goto nla_put_failure; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 28e934ed038a..dcd9ababd351 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -501,7 +501,7 @@ static int tcf_csum(struct sk_buff *skb, u32 update_flags; spin_lock(&p->tcf_lock); - p->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&p->tcf_tm); bstats_update(&p->tcf_bstats, skb); action = p->tcf_action; update_flags = p->update_flags; @@ -546,9 +546,8 @@ static int tcf_csum_dump(struct sk_buff *skb, if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(p->tcf_tm.expires); + + tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD)) goto nla_put_failure; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index ec5cc8435238..19058a7f3e5c 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -162,7 +162,8 @@ static void tcf_gact_stats_update(struct tc_action *a, u64 bytes, u32 packets, tm->lastuse = lastuse; } -static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_gact *gact = a->priv; @@ -188,9 +189,7 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, int bind, int goto nla_put_failure; } #endif - t.install = jiffies_to_clock_t(jiffies - gact->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - gact->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(gact->tcf_tm.expires); + tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD)) goto nla_put_failure; return skb->len; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 658046dfe02d..02f5a8ba95d7 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -553,9 +553,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - ife->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - ife->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(ife->tcf_tm.expires); + tcf_tm_dump(&t, &ife->tcf_tm); if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; @@ -623,7 +621,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); - ife->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&ife->tcf_tm); spin_unlock(&ife->tcf_lock); ifehdrln = ntohs(ifehdrln); @@ -711,7 +709,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); - ife->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet @@ -802,7 +800,7 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, pr_info_ratelimited("unknown failure(policy neither de/encode\n"); spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); - ife->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&ife->tcf_tm); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 9f002ada7074..e7c0f4d944a2 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -34,7 +34,8 @@ static int ipt_net_id; static int xt_net_id; -static int ipt_init_target(struct xt_entry_target *t, char *table, unsigned int hook) +static int ipt_init_target(struct xt_entry_target *t, char *table, + unsigned int hook) { struct xt_tgchk_param par; struct xt_target *target; @@ -212,7 +213,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, spin_lock(&ipt->tcf_lock); - ipt->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&ipt->tcf_tm); bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev @@ -250,7 +251,8 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, } -static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) +static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, + int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_ipt *ipt = a->priv; @@ -277,11 +279,11 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int nla_put(skb, TCA_IPT_CNT, sizeof(struct tc_cnt), &c) || nla_put_string(skb, TCA_IPT_TABLE, ipt->tcfi_tname)) goto nla_put_failure; - tm.install = jiffies_to_clock_t(jiffies - ipt->tcf_tm.install); - tm.lastuse = jiffies_to_clock_t(jiffies - ipt->tcf_tm.lastuse); - tm.expires = jiffies_to_clock_t(ipt->tcf_tm.expires); + + tcf_tm_dump(&tm, &ipt->tcf_tm); if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD)) goto nla_put_failure; + kfree(t); return skb->len; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942bc9e42..787751a7981a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -157,7 +157,6 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, u32 at; tcf_lastuse_update(&m->tcf_tm); - bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); rcu_read_lock(); @@ -219,9 +218,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, i if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - m->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - m->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(m->tcf_tm.expires); + + tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; return skb->len; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index c0a879f940de..06ccb03f25da 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -103,7 +103,7 @@ static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, spin_lock(&p->tcf_lock); - p->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&p->tcf_tm); old_addr = p->old_addr; new_addr = p->new_addr; mask = p->mask; @@ -264,9 +264,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(p->tcf_tm.expires); + + tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index c6e18f230af6..82d3c1479029 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -121,7 +121,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, spin_lock(&p->tcf_lock); - p->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&p->tcf_tm); if (p->tcfp_nkeys > 0) { struct tc_pedit_key *tkey = p->tcfp_keys; @@ -200,11 +200,11 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_PEDIT_PARMS, s, opt)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - p->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - p->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(p->tcf_tm.expires); + + tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD)) goto nla_put_failure; + kfree(opt); return skb->len; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index c557789765dc..ff34dd3966eb 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -182,7 +182,8 @@ override: if (est) { err = gen_replace_estimator(&police->tcf_bstats, NULL, &police->tcf_rate_est, - &police->tcf_lock, est); + &police->tcf_lock, + NULL, est); if (err) goto failure_unlock; } else if (tb[TCA_POLICE_AVRATE] && @@ -336,6 +337,7 @@ tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); t.lastuse = jiffies_to_clock_t(jiffies - police->tcf_tm.lastuse); + t.firstuse = jiffies_to_clock_t(jiffies - police->tcf_tm.firstuse); t.expires = jiffies_to_clock_t(police->tcf_tm.expires); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e42f8daca147..be5fbb51cfed 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -35,7 +35,7 @@ static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, struct tcf_defact *d = a->priv; spin_lock(&d->tcf_lock); - d->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&d->tcf_tm); bstats_update(&d->tcf_bstats, skb); /* print policy string followed by _ then packet count @@ -158,9 +158,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) || nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(d->tcf_tm.expires); + + tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD)) goto nla_put_failure; return skb->len; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index e928802966bc..7e2bc3c2b6da 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -37,7 +37,7 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_skbedit *d = a->priv; spin_lock(&d->tcf_lock); - d->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&d->tcf_tm); bstats_update(&d->tcf_bstats, skb); if (d->flags & SKBEDIT_F_PRIORITY) @@ -168,9 +168,8 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, nla_put(skb, TCA_SKBEDIT_MARK, sizeof(d->mark), &d->mark)) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - d->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - d->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(d->tcf_tm.expires); + + tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; return skb->len; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index ac4adc812c12..b075d50e0fc3 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -31,7 +31,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a, int err; spin_lock(&v->tcf_lock); - v->tcf_tm.lastuse = jiffies; + tcf_lastuse_update(&v->tcf_tm); bstats_update(&v->tcf_bstats, skb); action = v->tcf_action; @@ -179,12 +179,11 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a, if (v->tcfv_action == TCA_VLAN_ACT_PUSH && (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) || - nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, v->tcfv_push_proto))) + nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL, + v->tcfv_push_proto))) goto nla_put_failure; - t.install = jiffies_to_clock_t(jiffies - v->tcf_tm.install); - t.lastuse = jiffies_to_clock_t(jiffies - v->tcf_tm.lastuse); - t.expires = jiffies_to_clock_t(v->tcf_tm.expires); + tcf_tm_dump(&t, &v->tcf_tm); if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD)) goto nla_put_failure; return skb->len; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index a75864d93142..aafa6bce173e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -351,8 +351,9 @@ errout: return err; } -static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, - unsigned long fh, u32 portid, u32 seq, u16 flags, int event) +static int tcf_fill_node(struct net *net, struct sk_buff *skb, + struct tcf_proto *tp, unsigned long fh, u32 portid, + u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -474,9 +475,11 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) TC_H_MIN(tcm->tcm_info) != tp->protocol) continue; if (t > s_t) - memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); + memset(&cb->args[1], 0, + sizeof(cb->args)-sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, 0, NETLINK_CB(cb->skb).portid, + if (tcf_fill_node(net, skb, tp, 0, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) break; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index b3b7978f4182..1ea6f76e64b6 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -66,6 +66,7 @@ struct cls_fl_filter { struct fl_flow_key key; struct list_head list; u32 handle; + u32 flags; struct rcu_head rcu; }; @@ -123,6 +124,9 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; + if (!atomic_read(&head->ht.nelems)) + return -1; + fl_clear_masked_range(&skb_key, &head->mask); skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown protocol, @@ -136,7 +140,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, f = rhashtable_lookup_fast(&head->ht, fl_key_get_start(&skb_mkey, &head->mask), head->ht_params); - if (f) { + if (f && !(f->flags & TCA_CLS_FLAGS_SKIP_SW)) { *res = f->res; return tcf_exts_exec(skb, &f->exts, res); } @@ -524,7 +528,6 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_filter *fnew; struct nlattr *tb[TCA_FLOWER_MAX + 1]; struct fl_flow_mask mask = {}; - u32 flags = 0; int err; if (!tca[TCA_OPTIONS]) @@ -552,8 +555,14 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, } fnew->handle = handle; - if (tb[TCA_FLOWER_FLAGS]) - flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + if (tb[TCA_FLOWER_FLAGS]) { + fnew->flags = nla_get_u32(tb[TCA_FLOWER_FLAGS]); + + if (!tc_flags_valid(fnew->flags)) { + err = -EINVAL; + goto errout; + } + } err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr); if (err) @@ -563,10 +572,12 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout; - err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, - head->ht_params); - if (err) - goto errout; + if (!(fnew->flags & TCA_CLS_FLAGS_SKIP_SW)) { + err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, + head->ht_params); + if (err) + goto errout; + } fl_hw_replace_filter(tp, &head->dissector, @@ -574,7 +585,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, &fnew->key, &fnew->exts, (unsigned long)fnew, - flags); + fnew->flags); if (fold) { rhashtable_remove_fast(&head->ht, &fold->ht_node, @@ -734,6 +745,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, sizeof(key->tp.dst)))) goto nla_put_failure; + nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags); + if (tcf_exts_dump(skb, &f->exts)) goto nla_put_failure; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index ddf047df5361..d4a8bbfcc953 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -982,7 +982,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - spinlock_t *root_lock; + seqcount_t *running; err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) @@ -991,14 +991,15 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, if ((sch->parent != TC_H_ROOT) && !(sch->flags & TCQ_F_INGRESS) && (!p || !(p->flags & TCQ_F_MQROOT))) - root_lock = qdisc_root_sleeping_lock(sch); + running = qdisc_root_sleeping_running(sch); else - root_lock = qdisc_lock(sch); + running = &sch->running; err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, - root_lock, + NULL, + running, tca[TCA_RATE]); if (err) goto err_out4; @@ -1061,7 +1062,8 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) gen_replace_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); } out: @@ -1369,8 +1371,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, - qdisc_root_sleeping_lock(q), &d, - TCA_PAD) < 0) + NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) @@ -1381,7 +1382,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, cpu_qstats = q->cpu_qstats; } - if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), + &d, cpu_bstats, &q->bstats) < 0 || gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; @@ -1684,8 +1686,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, - qdisc_root_sleeping_lock(q), &d, - TCA_PAD) < 0) + NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 1911af3ca7c0..7e6c12dfc66a 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -519,20 +519,6 @@ static struct sk_buff *atm_tc_peek(struct Qdisc *sch) return p->link.q->ops->peek(p->link.q); } -static unsigned int atm_tc_drop(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - unsigned int len; - - pr_debug("atm_tc_drop(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow->q->ops->drop && (len = flow->q->ops->drop(flow->q))) - return len; - } - return 0; -} - static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt) { struct atm_qdisc_data *p = qdisc_priv(sch); @@ -637,7 +623,8 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct atm_flow_data *flow = (struct atm_flow_data *)arg; - if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &flow->bstats) < 0 || gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) return -1; @@ -671,7 +658,6 @@ static struct Qdisc_ops atm_qdisc_ops __read_mostly = { .enqueue = atm_tc_enqueue, .dequeue = atm_tc_dequeue, .peek = atm_tc_peek, - .drop = atm_tc_drop, .init = atm_tc_init, .reset = atm_tc_reset, .destroy = atm_tc_destroy, diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index baafddf229ce..f2af31be6370 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -80,10 +80,6 @@ struct cbq_class { unsigned char priority; /* class priority */ unsigned char priority2; /* priority to be used after overlimit */ unsigned char ewma_log; /* time constant for idle time calculation */ - unsigned char ovl_strategy; -#ifdef CONFIG_NET_CLS_ACT - unsigned char police; -#endif u32 defmap; @@ -94,10 +90,6 @@ struct cbq_class { u32 avpkt; struct qdisc_rate_table *R_tab; - /* Overlimit strategy parameters */ - void (*overlimit)(struct cbq_class *cl); - psched_tdiff_t penalty; - /* General scheduler (WRR) parameters */ long allot; long quantum; /* Allotment per WRR round */ @@ -382,9 +374,6 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -#ifdef CONFIG_NET_CLS_ACT - cl->q->__parent = sch; -#endif ret = qdisc_enqueue(skb, cl->q); if (ret == NET_XMIT_SUCCESS) { sch->q.qlen++; @@ -402,11 +391,8 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -/* Overlimit actions */ - -/* TC_CBQ_OVL_CLASSIC: (default) penalize leaf class by adding offtime */ - -static void cbq_ovl_classic(struct cbq_class *cl) +/* Overlimit action: penalize leaf class by adding offtime */ +static void cbq_overlimit(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); psched_tdiff_t delay = cl->undertime - q->now; @@ -456,99 +442,6 @@ static void cbq_ovl_classic(struct cbq_class *cl) } } -/* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when - * they go overlimit - */ - -static void cbq_ovl_rclassic(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this = cl; - - do { - if (cl->level > q->toplevel) { - cl = NULL; - break; - } - } while ((cl = cl->borrow) != NULL); - - if (cl == NULL) - cl = this; - cbq_ovl_classic(cl); -} - -/* TC_CBQ_OVL_DELAY: delay until it will go to underlimit */ - -static void cbq_ovl_delay(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (test_bit(__QDISC_STATE_DEACTIVATED, - &qdisc_root_sleeping(cl->qdisc)->state)) - return; - - if (!cl->delayed) { - psched_time_t sched = q->now; - ktime_t expires; - - delay += cl->offtime; - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - cl->undertime = q->now + delay; - - if (delay > 0) { - sched += delay + cl->penalty; - cl->penalized = sched; - cl->cpriority = TC_CBQ_MAXPRIO; - q->pmask |= (1<<TC_CBQ_MAXPRIO); - - expires = ns_to_ktime(PSCHED_TICKS2NS(sched)); - if (hrtimer_try_to_cancel(&q->delay_timer) && - ktime_to_ns(ktime_sub( - hrtimer_get_expires(&q->delay_timer), - expires)) > 0) - hrtimer_set_expires(&q->delay_timer, expires); - hrtimer_restart(&q->delay_timer); - cl->delayed = 1; - cl->xstats.overactions++; - return; - } - delay = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; -} - -/* TC_CBQ_OVL_LOWPRIO: penalize class by lowering its priority band */ - -static void cbq_ovl_lowprio(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - cl->penalized = q->now + cl->penalty; - - if (cl->cpriority != cl->priority2) { - cl->cpriority = cl->priority2; - q->pmask |= (1<<cl->cpriority); - cl->xstats.overactions++; - } - cbq_ovl_classic(cl); -} - -/* TC_CBQ_OVL_DROP: penalize class by dropping */ - -static void cbq_ovl_drop(struct cbq_class *cl) -{ - if (cl->q->ops->drop) - if (cl->q->ops->drop(cl->q)) - cl->qdisc->q.qlen--; - cl->xstats.overactions++; - cbq_ovl_classic(cl); -} - static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, psched_time_t now) { @@ -625,40 +518,6 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) return HRTIMER_NORESTART; } -#ifdef CONFIG_NET_CLS_ACT -static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) -{ - struct Qdisc *sch = child->__parent; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = q->rx_class; - - q->rx_class = NULL; - - if (cl && (cl = cbq_reclassify(skb, cl)) != NULL) { - int ret; - - cbq_mark_toplevel(q, cl); - - q->rx_class = cl; - cl->q->__parent = sch; - - ret = qdisc_enqueue(skb, cl->q); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - if (!cl->next_alive) - cbq_activate_class(cl); - return 0; - } - if (net_xmit_drop_count(ret)) - qdisc_qstats_drop(sch); - return 0; - } - - qdisc_qstats_drop(sch); - return -1; -} -#endif - /* * It is mission critical procedure. * @@ -807,7 +666,7 @@ cbq_under_limit(struct cbq_class *cl) cl = cl->borrow; if (!cl) { this_cl->qstats.overlimits++; - this_cl->overlimit(this_cl); + cbq_overlimit(this_cl); return NULL; } if (cl->level > q->toplevel) @@ -1166,31 +1025,6 @@ static void cbq_link_class(struct cbq_class *this) } } -static unsigned int cbq_drop(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl, *cl_head; - int prio; - unsigned int len; - - for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) { - cl_head = q->active[prio]; - if (!cl_head) - continue; - - cl = cl_head; - do { - if (cl->q->ops->drop && (len = cl->q->ops->drop(cl->q))) { - sch->q.qlen--; - if (!cl->q->q.qlen) - cbq_deactivate_class(cl); - return len; - } - } while ((cl = cl->next_alive) != cl_head); - } - return 0; -} - static void cbq_reset(struct Qdisc *sch) { @@ -1280,50 +1114,6 @@ static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) return 0; } -static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) -{ - switch (ovl->strategy) { - case TC_CBQ_OVL_CLASSIC: - cl->overlimit = cbq_ovl_classic; - break; - case TC_CBQ_OVL_DELAY: - cl->overlimit = cbq_ovl_delay; - break; - case TC_CBQ_OVL_LOWPRIO: - if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO || - ovl->priority2 - 1 <= cl->priority) - return -EINVAL; - cl->priority2 = ovl->priority2 - 1; - cl->overlimit = cbq_ovl_lowprio; - break; - case TC_CBQ_OVL_DROP: - cl->overlimit = cbq_ovl_drop; - break; - case TC_CBQ_OVL_RCLASSIC: - cl->overlimit = cbq_ovl_rclassic; - break; - default: - return -EINVAL; - } - cl->penalty = ovl->penalty; - return 0; -} - -#ifdef CONFIG_NET_CLS_ACT -static int cbq_set_police(struct cbq_class *cl, struct tc_cbq_police *p) -{ - cl->police = p->police; - - if (cl->q->handle) { - if (p->police == TC_POLICE_RECLASSIFY) - cl->q->reshape_fail = cbq_reshape_fail; - else - cl->q->reshape_fail = NULL; - } - return 0; -} -#endif - static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) { cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); @@ -1375,8 +1165,6 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.priority = TC_CBQ_MAXPRIO - 1; q->link.priority2 = TC_CBQ_MAXPRIO - 1; q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC; - q->link.overlimit = cbq_ovl_classic; q->link.allot = psched_mtu(qdisc_dev(sch)); q->link.quantum = q->link.allot; q->link.weight = q->link.R_tab->rate.rate; @@ -1463,24 +1251,6 @@ nla_put_failure: return -1; } -static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_ovl opt; - - opt.strategy = cl->ovl_strategy; - opt.priority2 = cl->priority2 + 1; - opt.pad = 0; - opt.penalty = cl->penalty; - if (nla_put(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1500,36 +1270,11 @@ nla_put_failure: return -1; } -#ifdef CONFIG_NET_CLS_ACT -static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_police opt; - - if (cl->police) { - opt.police = cl->police; - opt.__res1 = 0; - opt.__res2 = 0; - if (nla_put(skb, TCA_CBQ_POLICE, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} -#endif - static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) { if (cbq_dump_lss(skb, cl) < 0 || cbq_dump_rate(skb, cl) < 0 || cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_ovl(skb, cl) < 0 || -#ifdef CONFIG_NET_CLS_ACT - cbq_dump_police(skb, cl) < 0 || -#endif cbq_dump_fopt(skb, cl) < 0) return -1; return 0; @@ -1600,7 +1345,8 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (cl->undertime != PSCHED_PASTPERFECT) cl->xstats.undertime = cl->undertime - q->now; - if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0) return -1; @@ -1618,11 +1364,6 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, &pfifo_qdisc_ops, cl->common.classid); if (new == NULL) return -ENOBUFS; - } else { -#ifdef CONFIG_NET_CLS_ACT - if (cl->police == TC_POLICE_RECLASSIFY) - new->reshape_fail = cbq_reshape_fail; -#endif } *old = qdisc_replace(sch, new, &cl->q); @@ -1735,6 +1476,9 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (err < 0) return err; + if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) + return -EOPNOTSUPP; + if (cl) { /* Check parent */ if (parentid) { @@ -1755,7 +1499,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { qdisc_put_rtab(rtab); @@ -1782,14 +1527,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); } - if (tb[TCA_CBQ_OVL_STRATEGY]) - cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY])); - -#ifdef CONFIG_NET_CLS_ACT - if (tb[TCA_CBQ_POLICE]) - cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE])); -#endif - if (tb[TCA_CBQ_FOPT]) cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); @@ -1848,7 +1585,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { kfree(cl); @@ -1884,13 +1622,6 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->maxidle = q->link.maxidle; if (cl->avpkt == 0) cl->avpkt = q->link.avpkt; - cl->overlimit = cbq_ovl_classic; - if (tb[TCA_CBQ_OVL_STRATEGY]) - cbq_set_overlimit(cl, nla_data(tb[TCA_CBQ_OVL_STRATEGY])); -#ifdef CONFIG_NET_CLS_ACT - if (tb[TCA_CBQ_POLICE]) - cbq_set_police(cl, nla_data(tb[TCA_CBQ_POLICE])); -#endif if (tb[TCA_CBQ_FOPT]) cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); sch_tree_unlock(sch); @@ -2035,7 +1766,6 @@ static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { .enqueue = cbq_enqueue, .dequeue = cbq_dequeue, .peek = qdisc_peek_dequeued, - .drop = cbq_drop, .init = cbq_init, .reset = cbq_reset, .destroy = cbq_destroy, diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 0a08c860eee4..04e0b0583e00 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -365,22 +365,6 @@ static struct sk_buff *choke_dequeue(struct Qdisc *sch) return skb; } -static unsigned int choke_drop(struct Qdisc *sch) -{ - struct choke_sched_data *q = qdisc_priv(sch); - unsigned int len; - - len = qdisc_queue_drop(sch); - if (len > 0) - q->stats.other++; - else { - if (!red_is_idling(&q->vars)) - red_start_of_idle_period(&q->vars); - } - - return len; -} - static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); @@ -569,7 +553,6 @@ static struct Qdisc_ops choke_qdisc_ops __read_mostly = { .enqueue = choke_enqueue, .dequeue = choke_dequeue, .peek = choke_peek_head, - .drop = choke_drop, .init = choke_init, .destroy = choke_destroy, .reset = choke_reset, diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index bf8af2c43c2c..22609e4e845f 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -91,7 +91,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) return err; @@ -119,7 +120,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { qdisc_destroy(cl->qdisc); @@ -279,7 +281,8 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (qlen) xstats.deficit = cl->deficit; - if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0) return -1; @@ -420,27 +423,6 @@ out: return NULL; } -static unsigned int drr_drop(struct Qdisc *sch) -{ - struct drr_sched *q = qdisc_priv(sch); - struct drr_class *cl; - unsigned int len; - - list_for_each_entry(cl, &q->active, alist) { - if (cl->qdisc->ops->drop) { - len = cl->qdisc->ops->drop(cl->qdisc); - if (len > 0) { - sch->qstats.backlog -= len; - sch->q.qlen--; - if (cl->qdisc->q.qlen == 0) - list_del(&cl->alist); - return len; - } - } - } - return 0; -} - static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt) { struct drr_sched *q = qdisc_priv(sch); @@ -510,7 +492,6 @@ static struct Qdisc_ops drr_qdisc_ops __read_mostly = { .enqueue = drr_enqueue, .dequeue = drr_dequeue, .peek = qdisc_peek_dequeued, - .drop = drr_drop, .init = drr_init_qdisc, .reset = drr_reset_qdisc, .destroy = drr_destroy_qdisc, diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 34b4ddaca27c..b9ba5f658528 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -320,23 +320,6 @@ static struct sk_buff *dsmark_peek(struct Qdisc *sch) return p->q->ops->peek(p->q); } -static unsigned int dsmark_drop(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - unsigned int len; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - if (p->q->ops->drop == NULL) - return 0; - - len = p->q->ops->drop(p->q); - if (len) - sch->q.qlen--; - - return len; -} - static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) { struct dsmark_qdisc_data *p = qdisc_priv(sch); @@ -489,7 +472,6 @@ static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { .enqueue = dsmark_enqueue, .dequeue = dsmark_dequeue, .peek = dsmark_peek, - .drop = dsmark_drop, .init = dsmark_init, .reset = dsmark_reset, .destroy = dsmark_destroy, diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index 2177eac0a61e..dea70e3ef0ba 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -24,7 +24,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) return qdisc_enqueue_tail(skb, sch); - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); } static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) @@ -32,7 +32,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (likely(skb_queue_len(&sch->q) < sch->limit)) return qdisc_enqueue_tail(skb, sch); - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); } static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch) @@ -99,7 +99,6 @@ struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .enqueue = pfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, - .drop = qdisc_queue_drop, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, @@ -114,7 +113,6 @@ struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .enqueue = bfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, - .drop = qdisc_queue_drop, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, @@ -129,7 +127,6 @@ struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, - .drop = qdisc_queue_drop_head, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index da250b2e06ae..a302e8ef5498 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -184,15 +184,6 @@ static unsigned int fq_codel_drop(struct Qdisc *sch, unsigned int max_packets) return idx; } -static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch) -{ - unsigned int prev_backlog; - - prev_backlog = sch->qstats.backlog; - fq_codel_drop(sch, 1U); - return prev_backlog - sch->qstats.backlog; -} - static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); @@ -578,11 +569,13 @@ static int fq_codel_dump_stats(struct Qdisc *sch, struct gnet_dump *d) st.qdisc_stats.memory_usage = q->memory_usage; st.qdisc_stats.drop_overmemory = q->drop_overmemory; + sch_tree_lock(sch); list_for_each(pos, &q->new_flows) st.qdisc_stats.new_flows_len++; list_for_each(pos, &q->old_flows) st.qdisc_stats.old_flows_len++; + sch_tree_unlock(sch); return gnet_stats_copy_app(d, &st, sizeof(st)); } @@ -636,7 +629,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, if (idx < q->flows_cnt) { const struct fq_codel_flow *flow = &q->flows[idx]; - const struct sk_buff *skb = flow->head; + const struct sk_buff *skb; memset(&xstats, 0, sizeof(xstats)); xstats.type = TCA_FQ_CODEL_XSTATS_CLASS; @@ -654,9 +647,14 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl, codel_time_to_us(delta) : -codel_time_to_us(-delta); } - while (skb) { - qs.qlen++; - skb = skb->next; + if (flow->head) { + sch_tree_lock(sch); + skb = flow->head; + while (skb) { + qs.qlen++; + skb = skb->next; + } + sch_tree_unlock(sch); } qs.backlog = q->backlogs[idx]; qs.drops = flow->dropped; @@ -709,7 +707,6 @@ static struct Qdisc_ops fq_codel_qdisc_ops __read_mostly = { .enqueue = fq_codel_enqueue, .dequeue = fq_codel_dequeue, .peek = qdisc_peek_dequeued, - .drop = fq_codel_qdisc_drop, .init = fq_codel_init, .reset = fq_codel_reset, .destroy = fq_codel_destroy, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index f9e0e9c03d0a..0c9cb516f2e3 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -112,7 +112,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, /* * Transmit possibly several skbs, and handle the return status as - * required. Holding the __QDISC___STATE_RUNNING bit guarantees that + * required. Owning running seqcount bit guarantees that * only one CPU can execute this function. * * Returns to the caller: @@ -165,7 +165,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, /* * NOTE: Called under qdisc_lock(q) with locally disabled BH. * - * __QDISC___STATE_RUNNING guarantees only one CPU can process + * running seqcount guarantees only one CPU can process * this qdisc at a time. qdisc_lock(q) serializes queue accesses for * this queue. * @@ -381,6 +381,7 @@ struct Qdisc noop_qdisc = { .list = LIST_HEAD_INIT(noop_qdisc.list), .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, + .running = SEQCNT_ZERO(noop_qdisc.running), .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), }; EXPORT_SYMBOL(noop_qdisc); @@ -539,6 +540,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; +static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops) @@ -572,6 +574,10 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); + seqcount_init(&sch->running); + lockdep_set_class(&sch->running, + dev->qdisc_running_key ?: &qdisc_running_key); + sch->ops = ops; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 80105109f756..b5fb63c7be02 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -276,40 +276,6 @@ static struct sk_buff *gred_dequeue(struct Qdisc *sch) return NULL; } -static unsigned int gred_drop(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct gred_sched *t = qdisc_priv(sch); - - skb = qdisc_dequeue_tail(sch); - if (skb) { - unsigned int len = qdisc_pkt_len(skb); - struct gred_sched_data *q; - u16 dp = tc_index_to_dp(skb); - - if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { - net_warn_ratelimited("GRED: Unable to relocate VQ 0x%x while dropping, screwing up backlog\n", - tc_index_to_dp(skb)); - } else { - q->backlog -= len; - q->stats.other++; - - if (gred_wred_mode(t)) { - if (!sch->qstats.backlog) - red_start_of_idle_period(&t->wred_set); - } else { - if (!q->backlog) - red_start_of_idle_period(&q->vars); - } - } - - qdisc_drop(skb, sch); - return len; - } - - return 0; -} - static void gred_reset(struct Qdisc *sch) { int i; @@ -623,7 +589,6 @@ static struct Qdisc_ops gred_qdisc_ops __read_mostly = { .enqueue = gred_enqueue, .dequeue = gred_dequeue, .peek = qdisc_peek_head, - .drop = gred_drop, .init = gred_init, .reset = gred_reset, .destroy = gred_destroy, diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 1ac9f9f03fe3..eb3d3f5aba80 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1015,11 +1015,10 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cur_time = psched_get_time(); if (tca[TCA_RATE]) { - spinlock_t *lock = qdisc_root_sleeping_lock(sch); - err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - lock, + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) return err; @@ -1068,7 +1067,8 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) { kfree(cl); @@ -1373,7 +1373,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; - if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0) return -1; @@ -1672,32 +1672,6 @@ hfsc_dequeue(struct Qdisc *sch) return skb; } -static unsigned int -hfsc_drop(struct Qdisc *sch) -{ - struct hfsc_sched *q = qdisc_priv(sch); - struct hfsc_class *cl; - unsigned int len; - - list_for_each_entry(cl, &q->droplist, dlist) { - if (cl->qdisc->ops->drop != NULL && - (len = cl->qdisc->ops->drop(cl->qdisc)) > 0) { - if (cl->qdisc->q.qlen == 0) { - update_vf(cl, 0, 0); - set_passive(cl); - } else { - list_move_tail(&cl->dlist, &q->droplist); - } - cl->qstats.drops++; - qdisc_qstats_drop(sch); - sch->qstats.backlog -= len; - sch->q.qlen--; - return len; - } - } - return 0; -} - static const struct Qdisc_class_ops hfsc_class_ops = { .change = hfsc_change_class, .delete = hfsc_delete_class, @@ -1724,7 +1698,6 @@ static struct Qdisc_ops hfsc_qdisc_ops __read_mostly = { .enqueue = hfsc_enqueue, .dequeue = hfsc_dequeue, .peek = qdisc_peek_dequeued, - .drop = hfsc_drop, .cl_ops = &hfsc_class_ops, .priv_size = sizeof(struct hfsc_sched), .owner = THIS_MODULE diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 13d6f83ec491..c51791848a38 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -368,15 +368,6 @@ static unsigned int hhf_drop(struct Qdisc *sch) return bucket - q->buckets; } -static unsigned int hhf_qdisc_drop(struct Qdisc *sch) -{ - unsigned int prev_backlog; - - prev_backlog = sch->qstats.backlog; - hhf_drop(sch); - return prev_backlog - sch->qstats.backlog; -} - static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct hhf_sched_data *q = qdisc_priv(sch); @@ -709,7 +700,6 @@ static struct Qdisc_ops hhf_qdisc_ops __read_mostly = { .enqueue = hhf_enqueue, .dequeue = hhf_dequeue, .peek = qdisc_peek_dequeued, - .drop = hhf_qdisc_drop, .init = hhf_init, .reset = hhf_reset, .destroy = hhf_destroy, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index d4b4218af6b1..b74d06668ab4 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -936,31 +936,6 @@ fin: return skb; } -/* try to drop from each class (by prio) until one succeed */ -static unsigned int htb_drop(struct Qdisc *sch) -{ - struct htb_sched *q = qdisc_priv(sch); - int prio; - - for (prio = TC_HTB_NUMPRIO - 1; prio >= 0; prio--) { - struct list_head *p; - list_for_each(p, q->drops + prio) { - struct htb_class *cl = list_entry(p, struct htb_class, - un.leaf.drop_list); - unsigned int len; - if (cl->un.leaf.q->ops->drop && - (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) { - sch->qstats.backlog -= len; - sch->q.qlen--; - if (!cl->un.leaf.q->q.qlen) - htb_deactivate(q, cl); - return len; - } - } - } - return 0; -} - /* reset all classes */ /* always caled under BH & queue lock */ static void htb_reset(struct Qdisc *sch) @@ -1141,7 +1116,8 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens); cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens); - if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1395,7 +1371,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (htb_rate_est || tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE] ? : &est.nla); if (err) { kfree(cl); @@ -1457,11 +1434,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, parent->children++; } else { if (tca[TCA_RATE]) { - spinlock_t *lock = qdisc_root_sleeping_lock(sch); - err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - lock, + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) return err; @@ -1599,7 +1575,6 @@ static struct Qdisc_ops htb_qdisc_ops __read_mostly = { .enqueue = htb_enqueue, .dequeue = htb_dequeue, .peek = qdisc_peek_dequeued, - .drop = htb_drop, .init = htb_init, .reset = htb_reset, .destroy = htb_destroy, diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 56a77b878eb3..b9439827c172 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -199,7 +199,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index b8002ce3d010..549c66359924 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -342,7 +342,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, * hold here is the look on dev_queue->qdisc_sleeping * also acquired below. */ - spin_unlock_bh(d->lock); + if (d->lock) + spin_unlock_bh(d->lock); for (i = tc.offset; i < tc.offset + tc.count; i++) { struct netdev_queue *q = netdev_get_tx_queue(dev, i); @@ -359,15 +360,17 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, spin_unlock_bh(qdisc_lock(qdisc)); } /* Reclaim root sleeping lock before completing stats */ - spin_lock_bh(d->lock); - if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 || + if (d->lock) + spin_lock_bh(d->lock); + if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 || gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0) return -1; } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &sch->bstats) < 0 || gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) return -1; diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index bcdd54bb101c..5ea93305d705 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -151,27 +151,6 @@ static struct sk_buff *multiq_peek(struct Qdisc *sch) } -static unsigned int multiq_drop(struct Qdisc *sch) -{ - struct multiq_sched_data *q = qdisc_priv(sch); - int band; - unsigned int len; - struct Qdisc *qdisc; - - for (band = q->bands - 1; band >= 0; band--) { - qdisc = q->queues[band]; - if (qdisc->ops->drop) { - len = qdisc->ops->drop(qdisc); - if (len != 0) { - sch->q.qlen--; - return len; - } - } - } - return 0; -} - - static void multiq_reset(struct Qdisc *sch) { @@ -356,7 +335,8 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl_q->bstats) < 0 || gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) return -1; @@ -415,7 +395,6 @@ static struct Qdisc_ops multiq_qdisc_ops __read_mostly = { .enqueue = multiq_enqueue, .dequeue = multiq_dequeue, .peek = multiq_peek, - .drop = multiq_drop, .init = multiq_init, .reset = multiq_reset, .destroy = multiq_destroy, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 205bed00dd34..9ca7947ab643 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -407,7 +407,7 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch) segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { - qdisc_reshape_fail(skb, sch); + qdisc_drop(skb, sch); return NULL; } consume_skb(skb); @@ -499,7 +499,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } if (unlikely(skb_queue_len(&sch->q) >= sch->limit)) - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); qdisc_qstats_backlog_inc(sch, skb); @@ -576,35 +576,6 @@ finish_segs: return NET_XMIT_SUCCESS; } -static unsigned int netem_drop(struct Qdisc *sch) -{ - struct netem_sched_data *q = qdisc_priv(sch); - unsigned int len; - - len = qdisc_queue_drop(sch); - - if (!len) { - struct rb_node *p = rb_first(&q->t_root); - - if (p) { - struct sk_buff *skb = netem_rb_to_skb(p); - - rb_erase(p, &q->t_root); - sch->q.qlen--; - skb->next = NULL; - skb->prev = NULL; - qdisc_qstats_backlog_dec(sch, skb); - kfree_skb(skb); - } - } - if (!len && q->qdisc && q->qdisc->ops->drop) - len = q->qdisc->ops->drop(q->qdisc); - if (len) - qdisc_qstats_drop(sch); - - return len; -} - static struct sk_buff *netem_dequeue(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); @@ -1143,7 +1114,6 @@ static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .enqueue = netem_enqueue, .dequeue = netem_dequeue, .peek = qdisc_peek_dequeued, - .drop = netem_drop, .init = netem_init, .reset = netem_reset, .destroy = netem_destroy, diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c index 5abfe44678d4..ff0d968750df 100644 --- a/net/sched/sch_plug.c +++ b/net/sched/sch_plug.c @@ -96,7 +96,7 @@ static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch) return qdisc_enqueue_tail(skb, sch); } - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); } static struct sk_buff *plug_dequeue(struct Qdisc *sch) diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 4b0a82191bc4..de492682caee 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -127,25 +127,6 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch) } -static unsigned int prio_drop(struct Qdisc *sch) -{ - struct prio_sched_data *q = qdisc_priv(sch); - int prio; - unsigned int len; - struct Qdisc *qdisc; - - for (prio = q->bands-1; prio >= 0; prio--) { - qdisc = q->queues[prio]; - if (qdisc->ops->drop && (len = qdisc->ops->drop(qdisc)) != 0) { - sch->qstats.backlog -= len; - sch->q.qlen--; - return len; - } - } - return 0; -} - - static void prio_reset(struct Qdisc *sch) { @@ -323,7 +304,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl_q->bstats) < 0 || gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0) return -1; @@ -382,7 +364,6 @@ static struct Qdisc_ops prio_qdisc_ops __read_mostly = { .enqueue = prio_enqueue, .dequeue = prio_dequeue, .peek = prio_peek, - .drop = prio_drop, .init = prio_init, .reset = prio_reset, .destroy = prio_destroy, diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f18857febdad..0427fa8b23f2 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -460,7 +460,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) return err; @@ -486,7 +487,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - qdisc_root_sleeping_lock(sch), + NULL, + qdisc_root_sleeping_running(sch), tca[TCA_RATE]); if (err) goto destroy_class; @@ -663,7 +665,8 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; - if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), + d, NULL, &cl->bstats) < 0 || gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0) @@ -1422,52 +1425,6 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg) qfq_deactivate_class(q, cl); } -static unsigned int qfq_drop_from_slot(struct qfq_sched *q, - struct hlist_head *slot) -{ - struct qfq_aggregate *agg; - struct qfq_class *cl; - unsigned int len; - - hlist_for_each_entry(agg, slot, next) { - list_for_each_entry(cl, &agg->active, alist) { - - if (!cl->qdisc->ops->drop) - continue; - - len = cl->qdisc->ops->drop(cl->qdisc); - if (len > 0) { - if (cl->qdisc->q.qlen == 0) - qfq_deactivate_class(q, cl); - - return len; - } - } - } - return 0; -} - -static unsigned int qfq_drop(struct Qdisc *sch) -{ - struct qfq_sched *q = qdisc_priv(sch); - struct qfq_group *grp; - unsigned int i, j, len; - - for (i = 0; i <= QFQ_MAX_INDEX; i++) { - grp = &q->groups[i]; - for (j = 0; j < QFQ_MAX_SLOTS; j++) { - len = qfq_drop_from_slot(q, &grp->slots[j]); - if (len > 0) { - sch->q.qlen--; - return len; - } - } - - } - - return 0; -} - static int qfq_init_qdisc(struct Qdisc *sch, struct nlattr *opt) { struct qfq_sched *q = qdisc_priv(sch); @@ -1562,7 +1519,6 @@ static struct Qdisc_ops qfq_qdisc_ops __read_mostly = { .enqueue = qfq_enqueue, .dequeue = qfq_dequeue, .peek = qdisc_peek_dequeued, - .drop = qfq_drop, .init = qfq_init_qdisc, .reset = qfq_reset_qdisc, .destroy = qfq_destroy_qdisc, diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 91578bdd378c..a0d57530335e 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -136,26 +136,6 @@ static struct sk_buff *red_peek(struct Qdisc *sch) return child->ops->peek(child); } -static unsigned int red_drop(struct Qdisc *sch) -{ - struct red_sched_data *q = qdisc_priv(sch); - struct Qdisc *child = q->qdisc; - unsigned int len; - - if (child->ops->drop && (len = child->ops->drop(child)) > 0) { - q->stats.other++; - qdisc_qstats_drop(sch); - sch->qstats.backlog -= len; - sch->q.qlen--; - return len; - } - - if (!red_is_idling(&q->vars)) - red_start_of_idle_period(&q->vars); - - return 0; -} - static void red_reset(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); @@ -365,7 +345,6 @@ static struct Qdisc_ops red_qdisc_ops __read_mostly = { .enqueue = red_enqueue, .dequeue = red_dequeue, .peek = red_peek, - .drop = red_drop, .init = red_init, .reset = red_reset, .destroy = red_destroy, diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 498f0a2cb47f..a2e0b855d1c8 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -896,7 +896,6 @@ static struct Qdisc_ops sfq_qdisc_ops __read_mostly = { .enqueue = sfq_enqueue, .dequeue = sfq_dequeue, .peek = qdisc_peek_dequeued, - .drop = sfq_drop, .init = sfq_init, .reset = sfq_reset, .destroy = sfq_destroy, diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 3161e491990b..7fa3d6e1291c 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -166,7 +166,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); nb = 0; while (segs) { @@ -198,7 +198,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (qdisc_pkt_len(skb) > q->max_size) { if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) return tbf_segment(skb, sch); - return qdisc_reshape_fail(skb, sch); + return qdisc_drop(skb, sch); } ret = qdisc_enqueue(skb, q->qdisc); if (ret != NET_XMIT_SUCCESS) { @@ -212,19 +212,6 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_SUCCESS; } -static unsigned int tbf_drop(struct Qdisc *sch) -{ - struct tbf_sched_data *q = qdisc_priv(sch); - unsigned int len = 0; - - if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) { - sch->qstats.backlog -= len; - sch->q.qlen--; - qdisc_qstats_drop(sch); - } - return len; -} - static bool tbf_peak_present(const struct tbf_sched_data *q) { return q->peak.rate_bytes_ps; @@ -559,7 +546,6 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = { .enqueue = tbf_enqueue, .dequeue = tbf_dequeue, .peek = qdisc_peek_dequeued, - .drop = tbf_drop, .init = tbf_init, .reset = tbf_reset, .destroy = tbf_destroy, diff --git a/net/sctp/Makefile b/net/sctp/Makefile index 0fca5824ad0e..6c4f7496cec6 100644 --- a/net/sctp/Makefile +++ b/net/sctp/Makefile @@ -11,7 +11,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \ transport.o chunk.o sm_make_chunk.o ulpevent.o \ inqueue.o outqueue.o ulpqueue.o \ tsnmap.o bind_addr.o socket.o primitive.o \ - output.o input.o debug.o ssnmap.o auth.o + output.o input.o debug.o ssnmap.o auth.o \ + offload.o sctp_probe-y := probe.o diff --git a/net/sctp/input.c b/net/sctp/input.c index a701527a9480..6f8e676d285e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -112,7 +112,6 @@ int sctp_rcv(struct sk_buff *skb) struct sctp_ep_common *rcvr; struct sctp_transport *transport = NULL; struct sctp_chunk *chunk; - struct sctphdr *sh; union sctp_addr src; union sctp_addr dest; int family; @@ -124,28 +123,29 @@ int sctp_rcv(struct sk_buff *skb) __SCTP_INC_STATS(net, SCTP_MIB_INSCTPPACKS); - if (skb_linearize(skb)) + /* If packet is too small to contain a single chunk, let's not + * waste time on it anymore. + */ + if (skb->len < sizeof(struct sctphdr) + sizeof(struct sctp_chunkhdr) + + skb_transport_offset(skb)) goto discard_it; - sh = sctp_hdr(skb); + if (!pskb_may_pull(skb, sizeof(struct sctphdr))) + goto discard_it; - /* Pull up the IP and SCTP headers. */ + /* Pull up the IP header. */ __skb_pull(skb, skb_transport_offset(skb)); - if (skb->len < sizeof(struct sctphdr)) - goto discard_it; skb->csum_valid = 0; /* Previous value not applicable */ if (skb_csum_unnecessary(skb)) __skb_decr_checksum_unnecessary(skb); - else if (!sctp_checksum_disable && sctp_rcv_checksum(net, skb) < 0) + else if (!sctp_checksum_disable && + !(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) && + sctp_rcv_checksum(net, skb) < 0) goto discard_it; skb->csum_valid = 1; - skb_pull(skb, sizeof(struct sctphdr)); - - /* Make sure we at least have chunk headers worth of data left. */ - if (skb->len < sizeof(struct sctp_chunkhdr)) - goto discard_it; + __skb_pull(skb, sizeof(struct sctphdr)); family = ipver2af(ip_hdr(skb)->version); af = sctp_get_af_specific(family); @@ -230,7 +230,7 @@ int sctp_rcv(struct sk_buff *skb) chunk->rcvr = rcvr; /* Remember the SCTP header. */ - chunk->sctp_hdr = sh; + chunk->sctp_hdr = sctp_hdr(skb); /* Set the source and destination addresses of the incoming chunk. */ sctp_init_addrs(chunk, &src, &dest); @@ -660,19 +660,23 @@ out_unlock: */ static int sctp_rcv_ootb(struct sk_buff *skb) { - sctp_chunkhdr_t *ch; - __u8 *ch_end; - - ch = (sctp_chunkhdr_t *) skb->data; + sctp_chunkhdr_t *ch, _ch; + int ch_end, offset = 0; /* Scan through all the chunks in the packet. */ do { + /* Make sure we have at least the header there */ + if (offset + sizeof(sctp_chunkhdr_t) > skb->len) + break; + + ch = skb_header_pointer(skb, offset, sizeof(*ch), &_ch); + /* Break out if chunk length is less then minimal. */ if (ntohs(ch->length) < sizeof(sctp_chunkhdr_t)) break; - ch_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - if (ch_end > skb_tail_pointer(skb)) + ch_end = offset + WORD_ROUND(ntohs(ch->length)); + if (ch_end > skb->len) break; /* RFC 8.4, 2) If the OOTB packet contains an ABORT chunk, the @@ -697,8 +701,8 @@ static int sctp_rcv_ootb(struct sk_buff *skb) if (SCTP_CID_INIT == ch->type && (void *)ch != skb->data) goto discard; - ch = (sctp_chunkhdr_t *) ch_end; - } while (ch_end < skb_tail_pointer(skb)); + offset = ch_end; + } while (ch_end < skb->len); return 0; @@ -1173,6 +1177,17 @@ static struct sctp_association *__sctp_rcv_lookup_harder(struct net *net, { sctp_chunkhdr_t *ch; + /* We do not allow GSO frames here as we need to linearize and + * then cannot guarantee frame boundaries. This shouldn't be an + * issue as packets hitting this are mostly INIT or INIT-ACK and + * those cannot be on GSO-style anyway. + */ + if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) + return NULL; + + if (skb_linearize(skb)) + return NULL; + ch = (sctp_chunkhdr_t *) skb->data; /* The code below will attempt to walk the chunk and extract diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 9d87bba0ff1d..edabbbdfca54 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -130,13 +130,25 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) * at this time. */ - if ((chunk = queue->in_progress)) { + chunk = queue->in_progress; + if (chunk) { /* There is a packet that we have been working on. * Any post processing work to do before we move on? */ if (chunk->singleton || chunk->end_of_packet || chunk->pdiscard) { + if (chunk->head_skb == chunk->skb) { + chunk->skb = skb_shinfo(chunk->skb)->frag_list; + goto new_skb; + } + if (chunk->skb->next) { + chunk->skb = chunk->skb->next; + goto new_skb; + } + + if (chunk->head_skb) + chunk->skb = chunk->head_skb; sctp_chunk_free(chunk); chunk = queue->in_progress = NULL; } else { @@ -152,34 +164,64 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) if (!chunk) { struct list_head *entry; +next_chunk: /* Is the queue empty? */ - if (list_empty(&queue->in_chunk_list)) + entry = sctp_list_dequeue(&queue->in_chunk_list); + if (!entry) return NULL; - entry = queue->in_chunk_list.next; - chunk = queue->in_progress = - list_entry(entry, struct sctp_chunk, list); - list_del_init(entry); + chunk = list_entry(entry, struct sctp_chunk, list); - /* This is the first chunk in the packet. */ - chunk->singleton = 1; - ch = (sctp_chunkhdr_t *) chunk->skb->data; - chunk->data_accepted = 0; + /* Linearize if it's not GSO */ + if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP && + skb_is_nonlinear(chunk->skb)) { + if (skb_linearize(chunk->skb)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } + + /* Update sctp_hdr as it probably changed */ + chunk->sctp_hdr = sctp_hdr(chunk->skb); + } + + if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) { + /* GSO-marked skbs but without frags, handle + * them normally + */ + if (skb_shinfo(chunk->skb)->frag_list) + chunk->head_skb = chunk->skb; + + /* skbs with "cover letter" */ + if (chunk->head_skb && chunk->skb->data_len == chunk->skb->len) + chunk->skb = skb_shinfo(chunk->skb)->frag_list; + + if (WARN_ON(!chunk->skb)) { + __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS); + sctp_chunk_free(chunk); + goto next_chunk; + } + } if (chunk->asoc) sock_rps_save_rxhash(chunk->asoc->base.sk, chunk->skb); + + queue->in_progress = chunk; + +new_skb: + /* This is the first chunk in the packet. */ + ch = (sctp_chunkhdr_t *) chunk->skb->data; + chunk->singleton = 1; + chunk->data_accepted = 0; + chunk->pdiscard = 0; + chunk->auth = 0; + chunk->has_asconf = 0; + chunk->end_of_packet = 0; + chunk->ecn_ce_done = 0; } chunk->chunk_hdr = ch; chunk->chunk_end = ((__u8 *)ch) + WORD_ROUND(ntohs(ch->length)); - /* In the unlikely case of an IP reassembly, the skb could be - * non-linear. If so, update chunk_end so that it doesn't go past - * the skb->tail. - */ - if (unlikely(skb_is_nonlinear(chunk->skb))) { - if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) - chunk->chunk_end = skb_tail_pointer(chunk->skb); - } skb_pull(chunk->skb, sizeof(sctp_chunkhdr_t)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ diff --git a/net/sctp/offload.c b/net/sctp/offload.c new file mode 100644 index 000000000000..a37887b373a7 --- /dev/null +++ b/net/sctp/offload.c @@ -0,0 +1,98 @@ +/* + * sctp_offload - GRO/GSO Offloading for SCTP + * + * Copyright (C) 2015, Marcelo Ricardo Leitner <marcelo.leitner@gmail.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. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/socket.h> +#include <linux/sctp.h> +#include <linux/proc_fs.h> +#include <linux/vmalloc.h> +#include <linux/module.h> +#include <linux/kfifo.h> +#include <linux/time.h> +#include <net/net_namespace.h> + +#include <linux/skbuff.h> +#include <net/sctp/sctp.h> +#include <net/sctp/checksum.h> +#include <net/protocol.h> + +static __le32 sctp_gso_make_checksum(struct sk_buff *skb) +{ + skb->ip_summed = CHECKSUM_NONE; + return sctp_compute_cksum(skb, skb_transport_offset(skb)); +} + +static struct sk_buff *sctp_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct sctphdr *sh; + + sh = sctp_hdr(skb); + if (!pskb_may_pull(skb, sizeof(*sh))) + goto out; + + __skb_pull(skb, sizeof(*sh)); + + if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + struct skb_shared_info *pinfo = skb_shinfo(skb); + struct sk_buff *frag_iter; + + pinfo->gso_segs = 0; + if (skb->len != skb->data_len) { + /* Means we have chunks in here too */ + pinfo->gso_segs++; + } + + skb_walk_frags(skb, frag_iter) + pinfo->gso_segs++; + + segs = NULL; + goto out; + } + + segs = skb_segment(skb, features | NETIF_F_HW_CSUM); + if (IS_ERR(segs)) + goto out; + + /* All that is left is update SCTP CRC if necessary */ + if (!(features & NETIF_F_SCTP_CRC)) { + for (skb = segs; skb; skb = skb->next) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { + sh = sctp_hdr(skb); + sh->checksum = sctp_gso_make_checksum(skb); + } + } + } + +out: + return segs; +} + +static const struct net_offload sctp_offload = { + .callbacks = { + .gso_segment = sctp_gso_segment, + }, +}; + +int __init sctp_offload_init(void) +{ + return inet_add_offload(&sctp_offload, IPPROTO_SCTP); +} diff --git a/net/sctp/output.c b/net/sctp/output.c index 9844fe573029..1541a91d6d9d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -84,18 +84,42 @@ static void sctp_packet_reset(struct sctp_packet *packet) struct sctp_packet *sctp_packet_config(struct sctp_packet *packet, __u32 vtag, int ecn_capable) { - struct sctp_chunk *chunk = NULL; + struct sctp_transport *tp = packet->transport; + struct sctp_association *asoc = tp->asoc; pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); packet->vtag = vtag; + if (asoc && tp->dst) { + struct sock *sk = asoc->base.sk; + + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + + if (sk_can_gso(sk)) { + struct net_device *dev = tp->dst->dev; + + packet->max_size = dev->gso_max_size; + } else { + packet->max_size = asoc->pathmtu; + } + rcu_read_unlock(); + + } else { + packet->max_size = tp->pathmtu; + } + if (ecn_capable && sctp_packet_empty(packet)) { - chunk = sctp_get_ecne_prepend(packet->transport->asoc); + struct sctp_chunk *chunk; /* If there a is a prepend chunk stick it on the list before * any other chunks get appended. */ + chunk = sctp_get_ecne_prepend(asoc); if (chunk) sctp_packet_append_chunk(packet, chunk); } @@ -158,7 +182,8 @@ sctp_xmit_t sctp_packet_transmit_chunk(struct sctp_packet *packet, sctp_xmit_t retval; int error = 0; - pr_debug("%s: packet:%p chunk:%p\n", __func__, packet, chunk); + pr_debug("%s: packet:%p size:%Zu chunk:%p size:%d\n", __func__, + packet, packet->size, chunk, chunk->skb ? chunk->skb->len : -1); switch ((retval = (sctp_packet_append_chunk(packet, chunk)))) { case SCTP_XMIT_PMTU_FULL: @@ -381,12 +406,15 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; struct sctphdr *sh; - struct sk_buff *nskb; + struct sk_buff *nskb = NULL, *head = NULL; struct sctp_chunk *chunk, *tmp; struct sock *sk; int err = 0; int padding; /* How much padding do we need? */ + int pkt_size; __u8 has_data = 0; + int gso = 0; + int pktcount = 0; struct dst_entry *dst; unsigned char *auth = NULL; /* pointer to auth in skb data */ @@ -400,18 +428,37 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list); sk = chunk->skb->sk; - /* Allocate the new skb. */ - nskb = alloc_skb(packet->size + MAX_HEADER, gfp); - if (!nskb) + /* Allocate the head skb, or main one if not in GSO */ + if (packet->size > tp->pathmtu && !packet->ipfragok) { + if (sk_can_gso(sk)) { + gso = 1; + pkt_size = packet->overhead; + } else { + /* If this happens, we trash this packet and try + * to build a new one, hopefully correct this + * time. Application may notice this error. + */ + pr_err_once("Trying to GSO but underlying device doesn't support it."); + goto nomem; + } + } else { + pkt_size = packet->size; + } + head = alloc_skb(pkt_size + MAX_HEADER, gfp); + if (!head) goto nomem; + if (gso) { + NAPI_GRO_CB(head)->last = head; + skb_shinfo(head)->gso_type = sk->sk_gso_type; + } /* Make sure the outbound skb has enough header room reserved. */ - skb_reserve(nskb, packet->overhead + MAX_HEADER); + skb_reserve(head, packet->overhead + MAX_HEADER); /* Set the owning socket so that we know where to get the * destination IP address. */ - sctp_packet_set_owner_w(nskb, sk); + sctp_packet_set_owner_w(head, sk); if (!sctp_transport_dst_check(tp)) { sctp_transport_route(tp, NULL, sctp_sk(sk)); @@ -422,11 +469,11 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) dst = dst_clone(tp->dst); if (!dst) goto no_route; - skb_dst_set(nskb, dst); + skb_dst_set(head, dst); /* Build the SCTP header. */ - sh = (struct sctphdr *)skb_push(nskb, sizeof(struct sctphdr)); - skb_reset_transport_header(nskb); + sh = (struct sctphdr *)skb_push(head, sizeof(struct sctphdr)); + skb_reset_transport_header(head); sh->source = htons(packet->source_port); sh->dest = htons(packet->destination_port); @@ -441,90 +488,133 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sh->vtag = htonl(packet->vtag); sh->checksum = 0; - /** - * 6.10 Bundling - * - * An endpoint bundles chunks by simply including multiple - * chunks in one outbound SCTP packet. ... - */ - - /** - * 3.2 Chunk Field Descriptions - * - * The total length of a chunk (including Type, Length and - * Value fields) MUST be a multiple of 4 bytes. If the length - * of the chunk is not a multiple of 4 bytes, the sender MUST - * pad the chunk with all zero bytes and this padding is not - * included in the chunk length field. The sender should - * never pad with more than 3 bytes. - * - * [This whole comment explains WORD_ROUND() below.] - */ - pr_debug("***sctp_transmit_packet***\n"); - list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { - list_del_init(&chunk->list); - if (sctp_chunk_is_data(chunk)) { - /* 6.3.1 C4) When data is in flight and when allowed - * by rule C5, a new RTT measurement MUST be made each - * round trip. Furthermore, new RTT measurements - * SHOULD be made no more than once per round-trip - * for a given destination transport address. - */ + do { + /* Set up convenience variables... */ + chunk = list_entry(packet->chunk_list.next, struct sctp_chunk, list); + pktcount++; - if (!chunk->resent && !tp->rto_pending) { - chunk->rtt_in_progress = 1; - tp->rto_pending = 1; + /* Calculate packet size, so it fits in PMTU. Leave + * other chunks for the next packets. + */ + if (gso) { + pkt_size = packet->overhead; + list_for_each_entry(chunk, &packet->chunk_list, list) { + int padded = WORD_ROUND(chunk->skb->len); + + if (pkt_size + padded > tp->pathmtu) + break; + pkt_size += padded; } - has_data = 1; - } + /* Allocate a new skb. */ + nskb = alloc_skb(pkt_size + MAX_HEADER, gfp); + if (!nskb) + goto nomem; - padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len; - if (padding) - memset(skb_put(chunk->skb, padding), 0, padding); + /* Make sure the outbound skb has enough header + * room reserved. + */ + skb_reserve(nskb, packet->overhead + MAX_HEADER); + } else { + nskb = head; + } - /* if this is the auth chunk that we are adding, - * store pointer where it will be added and put - * the auth into the packet. + /** + * 3.2 Chunk Field Descriptions + * + * The total length of a chunk (including Type, Length and + * Value fields) MUST be a multiple of 4 bytes. If the length + * of the chunk is not a multiple of 4 bytes, the sender MUST + * pad the chunk with all zero bytes and this padding is not + * included in the chunk length field. The sender should + * never pad with more than 3 bytes. + * + * [This whole comment explains WORD_ROUND() below.] */ - if (chunk == packet->auth) - auth = skb_tail_pointer(nskb); - memcpy(skb_put(nskb, chunk->skb->len), + pkt_size -= packet->overhead; + list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { + list_del_init(&chunk->list); + if (sctp_chunk_is_data(chunk)) { + /* 6.3.1 C4) When data is in flight and when allowed + * by rule C5, a new RTT measurement MUST be made each + * round trip. Furthermore, new RTT measurements + * SHOULD be made no more than once per round-trip + * for a given destination transport address. + */ + + if (!chunk->resent && !tp->rto_pending) { + chunk->rtt_in_progress = 1; + tp->rto_pending = 1; + } + + has_data = 1; + } + + padding = WORD_ROUND(chunk->skb->len) - chunk->skb->len; + if (padding) + memset(skb_put(chunk->skb, padding), 0, padding); + + /* if this is the auth chunk that we are adding, + * store pointer where it will be added and put + * the auth into the packet. + */ + if (chunk == packet->auth) + auth = skb_tail_pointer(nskb); + + memcpy(skb_put(nskb, chunk->skb->len), chunk->skb->data, chunk->skb->len); - pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, " - "rtt_in_progress:%d\n", chunk, - sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), - chunk->has_tsn ? "TSN" : "No TSN", - chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0, - ntohs(chunk->chunk_hdr->length), chunk->skb->len, - chunk->rtt_in_progress); - - /* - * If this is a control chunk, this is our last - * reference. Free data chunks after they've been - * acknowledged or have failed. - */ - if (!sctp_chunk_is_data(chunk)) - sctp_chunk_free(chunk); - } + pr_debug("*** Chunk:%p[%s] %s 0x%x, length:%d, chunk->skb->len:%d, rtt_in_progress:%d\n", + chunk, + sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)), + chunk->has_tsn ? "TSN" : "No TSN", + chunk->has_tsn ? ntohl(chunk->subh.data_hdr->tsn) : 0, + ntohs(chunk->chunk_hdr->length), chunk->skb->len, + chunk->rtt_in_progress); + + /* If this is a control chunk, this is our last + * reference. Free data chunks after they've been + * acknowledged or have failed. + * Re-queue auth chunks if needed. + */ + pkt_size -= WORD_ROUND(chunk->skb->len); - /* SCTP-AUTH, Section 6.2 - * The sender MUST calculate the MAC as described in RFC2104 [2] - * using the hash function H as described by the MAC Identifier and - * the shared association key K based on the endpoint pair shared key - * described by the shared key identifier. The 'data' used for the - * computation of the AUTH-chunk is given by the AUTH chunk with its - * HMAC field set to zero (as shown in Figure 6) followed by all - * chunks that are placed after the AUTH chunk in the SCTP packet. - */ - if (auth) - sctp_auth_calculate_hmac(asoc, nskb, - (struct sctp_auth_chunk *)auth, - gfp); + if (chunk == packet->auth && !list_empty(&packet->chunk_list)) + list_add(&chunk->list, &packet->chunk_list); + else if (!sctp_chunk_is_data(chunk)) + sctp_chunk_free(chunk); + + if (!pkt_size) + break; + } + + /* SCTP-AUTH, Section 6.2 + * The sender MUST calculate the MAC as described in RFC2104 [2] + * using the hash function H as described by the MAC Identifier and + * the shared association key K based on the endpoint pair shared key + * described by the shared key identifier. The 'data' used for the + * computation of the AUTH-chunk is given by the AUTH chunk with its + * HMAC field set to zero (as shown in Figure 6) followed by all + * chunks that are placed after the AUTH chunk in the SCTP packet. + */ + if (auth) + sctp_auth_calculate_hmac(asoc, nskb, + (struct sctp_auth_chunk *)auth, + gfp); + + if (!gso) + break; + + if (skb_gro_receive(&head, nskb)) + goto nomem; + nskb = NULL; + if (WARN_ON_ONCE(skb_shinfo(head)->gso_segs >= + sk->sk_gso_max_segs)) + goto nomem; + } while (!list_empty(&packet->chunk_list)); /* 2) Calculate the Adler-32 checksum of the whole packet, * including the SCTP common header and all the @@ -532,16 +622,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * * Note: Adler-32 is no longer applicable, as has been replaced * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. + * + * If it's a GSO packet, it's postponed to sctp_skb_segment. */ - if (!sctp_checksum_disable) { - if (!(dst->dev->features & NETIF_F_SCTP_CRC) || - (dst_xfrm(dst) != NULL) || packet->ipfragok) { - sh->checksum = sctp_compute_cksum(nskb, 0); + if (!sctp_checksum_disable || gso) { + if (!gso && (!(dst->dev->features & NETIF_F_SCTP_CRC) || + dst_xfrm(dst) || packet->ipfragok)) { + sh->checksum = sctp_compute_cksum(head, 0); } else { /* no need to seed pseudo checksum for SCTP */ - nskb->ip_summed = CHECKSUM_PARTIAL; - nskb->csum_start = skb_transport_header(nskb) - nskb->head; - nskb->csum_offset = offsetof(struct sctphdr, checksum); + head->ip_summed = CHECKSUM_PARTIAL; + head->csum_start = skb_transport_header(head) - head->head; + head->csum_offset = offsetof(struct sctphdr, checksum); } } @@ -557,7 +649,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - tp->af_specific->ecn_capable(nskb->sk); + tp->af_specific->ecn_capable(sk); /* Set up the IP options. */ /* BUG: not implemented @@ -566,7 +658,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) /* Dump that on IP! */ if (asoc) { - asoc->stats.opackets++; + asoc->stats.opackets += pktcount; if (asoc->peer.last_sent_to != tp) /* Considering the multiple CPU scenario, this is a * "correcter" place for last_sent_to. --xguo @@ -589,16 +681,36 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) } } - pr_debug("***sctp_transmit_packet*** skb->len:%d\n", nskb->len); + pr_debug("***sctp_transmit_packet*** skb->len:%d\n", head->len); + + if (gso) { + /* Cleanup our debris for IP stacks */ + memset(head->cb, 0, max(sizeof(struct inet_skb_parm), + sizeof(struct inet6_skb_parm))); - nskb->ignore_df = packet->ipfragok; - tp->af_specific->sctp_xmit(nskb, tp); + skb_shinfo(head)->gso_segs = pktcount; + skb_shinfo(head)->gso_size = GSO_BY_FRAGS; + + /* We have to refresh this in case we are xmiting to + * more than one transport at a time + */ + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + rcu_read_unlock(); + } + head->ignore_df = packet->ipfragok; + tp->af_specific->sctp_xmit(head, tp); out: sctp_packet_reset(packet); return err; no_route: - kfree_skb(nskb); + kfree_skb(head); + if (nskb != head) + kfree_skb(nskb); if (asoc) IP_INC_STATS(sock_net(asoc->base.sk), IPSTATS_MIB_OUTNOROUTES); @@ -751,39 +863,63 @@ static sctp_xmit_t sctp_packet_will_fit(struct sctp_packet *packet, struct sctp_chunk *chunk, u16 chunk_len) { - size_t psize; - size_t pmtu; - int too_big; + size_t psize, pmtu; sctp_xmit_t retval = SCTP_XMIT_OK; psize = packet->size; - pmtu = ((packet->transport->asoc) ? - (packet->transport->asoc->pathmtu) : - (packet->transport->pathmtu)); - - too_big = (psize + chunk_len > pmtu); + if (packet->transport->asoc) + pmtu = packet->transport->asoc->pathmtu; + else + pmtu = packet->transport->pathmtu; /* Decide if we need to fragment or resubmit later. */ - if (too_big) { - /* It's OK to fragmet at IP level if any one of the following + if (psize + chunk_len > pmtu) { + /* It's OK to fragment at IP level if any one of the following * is true: - * 1. The packet is empty (meaning this chunk is greater - * the MTU) - * 2. The chunk we are adding is a control chunk - * 3. The packet doesn't have any data in it yet and data - * requires authentication. + * 1. The packet is empty (meaning this chunk is greater + * the MTU) + * 2. The packet doesn't have any data in it yet and data + * requires authentication. */ - if (sctp_packet_empty(packet) || !sctp_chunk_is_data(chunk) || + if (sctp_packet_empty(packet) || (!packet->has_data && chunk->auth)) { /* We no longer do re-fragmentation. * Just fragment at the IP layer, if we * actually hit this condition */ packet->ipfragok = 1; - } else { - retval = SCTP_XMIT_PMTU_FULL; + goto out; } + + /* It is also okay to fragment if the chunk we are + * adding is a control chunk, but only if current packet + * is not a GSO one otherwise it causes fragmentation of + * a large frame. So in this case we allow the + * fragmentation by forcing it to be in a new packet. + */ + if (!sctp_chunk_is_data(chunk) && packet->has_data) + retval = SCTP_XMIT_PMTU_FULL; + + if (psize + chunk_len > packet->max_size) + /* Hit GSO/PMTU limit, gotta flush */ + retval = SCTP_XMIT_PMTU_FULL; + + if (!packet->transport->burst_limited && + psize + chunk_len > (packet->transport->cwnd >> 1)) + /* Do not allow a single GSO packet to use more + * than half of cwnd. + */ + retval = SCTP_XMIT_PMTU_FULL; + + if (packet->transport->burst_limited && + psize + chunk_len > (packet->transport->burst_limited >> 1)) + /* Do not allow a single GSO packet to use more + * than half of original cwnd. + */ + retval = SCTP_XMIT_PMTU_FULL; + /* Otherwise it will fit in the GSO packet */ } +out: return retval; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index d3d50daa248b..40022ee885d7 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1516,6 +1516,9 @@ static __init int sctp_init(void) if (status) goto err_v6_add_protocol; + if (sctp_offload_init() < 0) + pr_crit("%s: Cannot add SCTP protocol offload\n", __func__); + out: return status; err_v6_add_protocol: diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 67154b848aa9..712fb2339baa 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4003,6 +4003,8 @@ static int sctp_init_sock(struct sock *sk) return -ESOCKTNOSUPPORT; } + sk->sk_gso_type = SKB_GSO_SCTP; + /* Initialize default send parameters. These parameters can be * modified with the SCTP_DEFAULT_SEND_PARAM socket option. */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 7059c94f33c5..a904ccd5a93a 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -87,7 +87,6 @@ struct tipc_stats { * @peer_bearer_id: bearer id used by link's peer endpoint * @bearer_id: local bearer id used by link * @tolerance: minimum link continuity loss needed to reset link [in ms] - * @keepalive_intv: link keepalive timer interval * @abort_limit: # of unacknowledged continuity probes needed to reset link * @state: current state of link FSM * @peer_caps: bitmap describing capabilities of peer node @@ -131,7 +130,6 @@ struct tipc_link { u32 peer_bearer_id; u32 bearer_id; u32 tolerance; - unsigned long keepalive_intv; u32 abort_limit; u32 state; u16 peer_caps; diff --git a/net/tipc/node.c b/net/tipc/node.c index e01e2c71b5a1..d6a490f991a4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -378,14 +378,13 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l) { unsigned long tol = tipc_link_tolerance(l); unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4; - unsigned long keepalive_intv = msecs_to_jiffies(intv); /* Link with lowest tolerance determines timer interval */ - if (keepalive_intv < n->keepalive_intv) - n->keepalive_intv = keepalive_intv; + if (intv < n->keepalive_intv) + n->keepalive_intv = intv; - /* Ensure link's abort limit corresponds to current interval */ - tipc_link_set_abort_limit(l, tol / jiffies_to_msecs(n->keepalive_intv)); + /* Ensure link's abort limit corresponds to current tolerance */ + tipc_link_set_abort_limit(l, tol / n->keepalive_intv); } static void tipc_node_delete(struct tipc_node *node) @@ -526,7 +525,7 @@ static void tipc_node_timeout(unsigned long data) if (rc & TIPC_LINK_DOWN_EVT) tipc_node_link_down(n, bearer_id, false); } - mod_timer(&n->timer, jiffies + n->keepalive_intv); + mod_timer(&n->timer, jiffies + msecs_to_jiffies(n->keepalive_intv)); } /** @@ -735,6 +734,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, bool accept_addr = false; bool reset = true; char *if_name; + unsigned long intv; *dupl_addr = false; *respond = false; @@ -840,9 +840,11 @@ void tipc_node_check_dest(struct net *net, u32 onode, le->link = l; n->link_cnt++; tipc_node_calculate_timer(n, l); - if (n->link_cnt == 1) - if (!mod_timer(&n->timer, jiffies + n->keepalive_intv)) + if (n->link_cnt == 1) { + intv = jiffies + msecs_to_jiffies(n->keepalive_intv); + if (!mod_timer(&n->timer, intv)) tipc_node_get(n); + } } memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: @@ -950,7 +952,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case SELF_LOST_CONTACT_EVT: - state = SELF_DOWN_PEER_LEAVING; + state = SELF_DOWN_PEER_DOWN; break; case SELF_ESTABL_CONTACT_EVT: case PEER_LOST_CONTACT_EVT: @@ -969,7 +971,7 @@ static void tipc_node_fsm_evt(struct tipc_node *n, int evt) state = SELF_UP_PEER_UP; break; case PEER_LOST_CONTACT_EVT: - state = SELF_LEAVING_PEER_DOWN; + state = SELF_DOWN_PEER_DOWN; break; case SELF_LOST_CONTACT_EVT: case PEER_ESTABL_CONTACT_EVT: |