diff options
Diffstat (limited to 'net')
155 files changed, 2657 insertions, 2004 deletions
diff --git a/net/atm/clip.c b/net/atm/clip.c index c12c258..5de42ea 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -46,8 +46,8 @@ static struct net_device *clip_devs; static struct atm_vcc *atmarpd; -static struct neigh_table clip_tbl; static struct timer_list idle_timer; +static const struct neigh_ops clip_neigh_ops; static int to_atmarpd(enum atmarp_ctrl_type type, int itf, __be32 ip) { @@ -123,6 +123,8 @@ static int neigh_check_cb(struct neighbour *n) struct atmarp_entry *entry = neighbour_priv(n); struct clip_vcc *cv; + if (n->ops != &clip_neigh_ops) + return 0; for (cv = entry->vccs; cv; cv = cv->next) { unsigned long exp = cv->last_use + cv->idle_timeout; @@ -154,10 +156,10 @@ static int neigh_check_cb(struct neighbour *n) static void idle_timer_check(unsigned long dummy) { - write_lock(&clip_tbl.lock); - __neigh_for_each_release(&clip_tbl, neigh_check_cb); + write_lock(&arp_tbl.lock); + __neigh_for_each_release(&arp_tbl, neigh_check_cb); mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - write_unlock(&clip_tbl.lock); + write_unlock(&arp_tbl.lock); } static int clip_arp_rcv(struct sk_buff *skb) @@ -328,6 +330,8 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, struct atmarp_entry *entry; struct neighbour *n; struct atm_vcc *vcc; + struct rtable *rt; + __be32 *daddr; int old; unsigned long flags; @@ -338,7 +342,12 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, dev->stats.tx_dropped++; return NETDEV_TX_OK; } - n = dst_get_neighbour_noref(dst); + rt = (struct rtable *) dst; + if (rt->rt_gateway) + daddr = &rt->rt_gateway; + else + daddr = &ip_hdr(skb)->daddr; + n = dst_neigh_lookup(dst, daddr); if (!n) { pr_err("NO NEIGHBOUR !\n"); dev_kfree_skb(skb); @@ -358,7 +367,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, dev_kfree_skb(skb); dev->stats.tx_dropped++; } - return NETDEV_TX_OK; + goto out_release_neigh; } pr_debug("neigh %p, vccs %p\n", entry, entry->vccs); ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; @@ -377,14 +386,14 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, old = xchg(&entry->vccs->xoff, 1); /* assume XOFF ... */ if (old) { pr_warning("XOFF->XOFF transition\n"); - return NETDEV_TX_OK; + goto out_release_neigh; } dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; vcc->send(vcc, skb); if (atm_may_send(vcc, 0)) { entry->vccs->xoff = 0; - return NETDEV_TX_OK; + goto out_release_neigh; } spin_lock_irqsave(&clip_priv->xoff_lock, flags); netif_stop_queue(dev); /* XOFF -> throttle immediately */ @@ -396,6 +405,8 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, of the brief netif_stop_queue. If this isn't true or if it changes, use netif_wake_queue instead. */ spin_unlock_irqrestore(&clip_priv->xoff_lock, flags); +out_release_neigh: + neigh_release(n); return NETDEV_TX_OK; } diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index df35d9a..614d3fc 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -44,7 +44,7 @@ #include <linux/atmdev.h> #include <linux/capability.h> #include <linux/ppp_defs.h> -#include <linux/if_ppp.h> +#include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/atmppp.h> diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index ce68611..4e392eb 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # -# Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_ogm.h b/net/batman-adv/bat_algo.h index 69329c1..9852a68 100644 --- a/net/batman-adv/bat_ogm.h +++ b/net/batman-adv/bat_algo.h @@ -1,7 +1,7 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2011-2012 B.A.T.M.A.N. contributors: * - * Marek Lindner, Simon Wunderlich + * Marek Lindner * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -19,17 +19,9 @@ * */ -#ifndef _NET_BATMAN_ADV_OGM_H_ -#define _NET_BATMAN_ADV_OGM_H_ +#ifndef _NET_BATMAN_ADV_BAT_ALGO_H_ +#define _NET_BATMAN_ADV_BAT_ALGO_H_ -#include "main.h" +int bat_iv_init(void); -void bat_ogm_init(struct hard_iface *hard_iface); -void bat_ogm_init_primary(struct hard_iface *hard_iface); -void bat_ogm_update_mac(struct hard_iface *hard_iface); -void bat_ogm_schedule(struct hard_iface *hard_iface, int tt_num_changes); -void bat_ogm_emit(struct forw_packet *forw_packet); -void bat_ogm_receive(const struct ethhdr *ethhdr, unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming); - -#endif /* _NET_BATMAN_ADV_OGM_H_ */ +#endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */ diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c index d0af9bf..c3b0548 100644 --- a/net/batman-adv/bat_debugfs.c +++ b/net/batman-adv/bat_debugfs.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -221,6 +221,11 @@ static void debug_log_cleanup(struct bat_priv *bat_priv) } #endif +static int bat_algorithms_open(struct inode *inode, struct file *file) +{ + return single_open(file, bat_algo_seq_print_text, NULL); +} + static int originators_open(struct inode *inode, struct file *file) { struct net_device *net_dev = (struct net_device *)inode->i_private; @@ -274,6 +279,7 @@ struct bat_debuginfo bat_debuginfo_##_name = { \ } \ }; +static BAT_DEBUGINFO(routing_algos, S_IRUGO, bat_algorithms_open); static BAT_DEBUGINFO(originators, S_IRUGO, originators_open); static BAT_DEBUGINFO(gateways, S_IRUGO, gateways_open); static BAT_DEBUGINFO(softif_neigh, S_IRUGO, softif_neigh_open); @@ -293,9 +299,25 @@ static struct bat_debuginfo *mesh_debuginfos[] = { void debugfs_init(void) { + struct bat_debuginfo *bat_debug; + struct dentry *file; + bat_debugfs = debugfs_create_dir(DEBUGFS_BAT_SUBDIR, NULL); if (bat_debugfs == ERR_PTR(-ENODEV)) bat_debugfs = NULL; + + if (!bat_debugfs) + goto out; + + bat_debug = &bat_debuginfo_routing_algos; + file = debugfs_create_file(bat_debug->attr.name, + S_IFREG | bat_debug->attr.mode, + bat_debugfs, NULL, &bat_debug->fops); + if (!file) + pr_err("Can't add debugfs file: %s\n", bat_debug->attr.name); + +out: + return; } void debugfs_destroy(void) diff --git a/net/batman-adv/bat_debugfs.h b/net/batman-adv/bat_debugfs.h index bc9cda3..d605c67 100644 --- a/net/batman-adv/bat_debugfs.h +++ b/net/batman-adv/bat_debugfs.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 3512e25..2b66dae 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -20,7 +20,6 @@ */ #include "main.h" -#include "bat_ogm.h" #include "translation-table.h" #include "ring_buffer.h" #include "originator.h" @@ -29,8 +28,9 @@ #include "gateway_client.h" #include "hard-interface.h" #include "send.h" +#include "bat_algo.h" -void bat_ogm_init(struct hard_iface *hard_iface) +static void bat_iv_ogm_init(struct hard_iface *hard_iface) { struct batman_ogm_packet *batman_ogm_packet; @@ -38,25 +38,25 @@ void bat_ogm_init(struct hard_iface *hard_iface) hard_iface->packet_buff = kmalloc(hard_iface->packet_len, GFP_ATOMIC); batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; - batman_ogm_packet->packet_type = BAT_OGM; - batman_ogm_packet->version = COMPAT_VERSION; + batman_ogm_packet->header.packet_type = BAT_OGM; + batman_ogm_packet->header.version = COMPAT_VERSION; + batman_ogm_packet->header.ttl = 2; batman_ogm_packet->flags = NO_FLAGS; - batman_ogm_packet->ttl = 2; batman_ogm_packet->tq = TQ_MAX_VALUE; batman_ogm_packet->tt_num_changes = 0; batman_ogm_packet->ttvn = 0; } -void bat_ogm_init_primary(struct hard_iface *hard_iface) +static void bat_iv_ogm_init_primary(struct hard_iface *hard_iface) { struct batman_ogm_packet *batman_ogm_packet; batman_ogm_packet = (struct batman_ogm_packet *)hard_iface->packet_buff; batman_ogm_packet->flags = PRIMARIES_FIRST_HOP; - batman_ogm_packet->ttl = TTL; + batman_ogm_packet->header.ttl = TTL; } -void bat_ogm_update_mac(struct hard_iface *hard_iface) +static void bat_iv_ogm_update_mac(struct hard_iface *hard_iface) { struct batman_ogm_packet *batman_ogm_packet; @@ -68,7 +68,7 @@ void bat_ogm_update_mac(struct hard_iface *hard_iface) } /* when do we schedule our own ogm to be sent */ -static unsigned long bat_ogm_emit_send_time(const struct bat_priv *bat_priv) +static unsigned long bat_iv_ogm_emit_send_time(const struct bat_priv *bat_priv) { return jiffies + msecs_to_jiffies( atomic_read(&bat_priv->orig_interval) - @@ -76,7 +76,7 @@ static unsigned long bat_ogm_emit_send_time(const struct bat_priv *bat_priv) } /* when do we schedule a ogm packet to be sent */ -static unsigned long bat_ogm_fwd_send_time(void) +static unsigned long bat_iv_ogm_fwd_send_time(void) { return jiffies + msecs_to_jiffies(random32() % (JITTER/2)); } @@ -89,8 +89,8 @@ static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) } /* is there another aggregated packet here? */ -static int bat_ogm_aggr_packet(int buff_pos, int packet_len, - int tt_num_changes) +static int bat_iv_ogm_aggr_packet(int buff_pos, int packet_len, + int tt_num_changes) { int next_buff_pos = buff_pos + BATMAN_OGM_LEN + tt_len(tt_num_changes); @@ -99,8 +99,8 @@ static int bat_ogm_aggr_packet(int buff_pos, int packet_len, } /* send a batman ogm to a given interface */ -static void bat_ogm_send_to_if(struct forw_packet *forw_packet, - struct hard_iface *hard_iface) +static void bat_iv_ogm_send_to_if(struct forw_packet *forw_packet, + struct hard_iface *hard_iface) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); char *fwd_str; @@ -117,8 +117,8 @@ static void bat_ogm_send_to_if(struct forw_packet *forw_packet, batman_ogm_packet = (struct batman_ogm_packet *)forw_packet->skb->data; /* adjust all flags and log packets */ - while (bat_ogm_aggr_packet(buff_pos, forw_packet->packet_len, - batman_ogm_packet->tt_num_changes)) { + while (bat_iv_ogm_aggr_packet(buff_pos, forw_packet->packet_len, + batman_ogm_packet->tt_num_changes)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -137,7 +137,7 @@ static void bat_ogm_send_to_if(struct forw_packet *forw_packet, fwd_str, (packet_num > 0 ? "aggregated " : ""), batman_ogm_packet->orig, ntohl(batman_ogm_packet->seqno), - batman_ogm_packet->tq, batman_ogm_packet->ttl, + batman_ogm_packet->tq, batman_ogm_packet->header.ttl, (batman_ogm_packet->flags & DIRECTLINK ? "on" : "off"), batman_ogm_packet->ttvn, hard_iface->net_dev->name, @@ -157,7 +157,7 @@ static void bat_ogm_send_to_if(struct forw_packet *forw_packet, } /* send a batman ogm packet */ -void bat_ogm_emit(struct forw_packet *forw_packet) +static void bat_iv_ogm_emit(struct forw_packet *forw_packet) { struct hard_iface *hard_iface; struct net_device *soft_iface; @@ -188,7 +188,7 @@ void bat_ogm_emit(struct forw_packet *forw_packet) /* multihomed peer assumed */ /* non-primary OGMs are only broadcasted on their interface */ - if ((directlink && (batman_ogm_packet->ttl == 1)) || + if ((directlink && (batman_ogm_packet->header.ttl == 1)) || (forw_packet->own && (forw_packet->if_incoming != primary_if))) { /* FIXME: what about aggregated packets ? */ @@ -198,7 +198,7 @@ void bat_ogm_emit(struct forw_packet *forw_packet) (forw_packet->own ? "Sending own" : "Forwarding"), batman_ogm_packet->orig, ntohl(batman_ogm_packet->seqno), - batman_ogm_packet->ttl, + batman_ogm_packet->header.ttl, forw_packet->if_incoming->net_dev->name, forw_packet->if_incoming->net_dev->dev_addr); @@ -216,7 +216,7 @@ void bat_ogm_emit(struct forw_packet *forw_packet) if (hard_iface->soft_iface != soft_iface) continue; - bat_ogm_send_to_if(forw_packet, hard_iface); + bat_iv_ogm_send_to_if(forw_packet, hard_iface); } rcu_read_unlock(); @@ -226,13 +226,13 @@ out: } /* return true if new_packet can be aggregated with forw_packet */ -static bool bat_ogm_can_aggregate(const struct batman_ogm_packet +static bool bat_iv_ogm_can_aggregate(const struct batman_ogm_packet *new_batman_ogm_packet, - struct bat_priv *bat_priv, - int packet_len, unsigned long send_time, - bool directlink, - const struct hard_iface *if_incoming, - const struct forw_packet *forw_packet) + struct bat_priv *bat_priv, + int packet_len, unsigned long send_time, + bool directlink, + const struct hard_iface *if_incoming, + const struct forw_packet *forw_packet) { struct batman_ogm_packet *batman_ogm_packet; int aggregated_bytes = forw_packet->packet_len + packet_len; @@ -272,7 +272,7 @@ static bool bat_ogm_can_aggregate(const struct batman_ogm_packet * are flooded through the net */ if ((!directlink) && (!(batman_ogm_packet->flags & DIRECTLINK)) && - (batman_ogm_packet->ttl != 1) && + (batman_ogm_packet->header.ttl != 1) && /* own packets originating non-primary * interfaces leave only that interface */ @@ -285,7 +285,7 @@ static bool bat_ogm_can_aggregate(const struct batman_ogm_packet /* if the incoming packet is sent via this one * interface only - we still can aggregate */ if ((directlink) && - (new_batman_ogm_packet->ttl == 1) && + (new_batman_ogm_packet->header.ttl == 1) && (forw_packet->if_incoming == if_incoming) && /* packets from direct neighbors or @@ -306,11 +306,11 @@ out: } /* create a new aggregated packet and add this packet to it */ -static void bat_ogm_aggregate_new(const unsigned char *packet_buff, - int packet_len, unsigned long send_time, - bool direct_link, - struct hard_iface *if_incoming, - int own_packet) +static void bat_iv_ogm_aggregate_new(const unsigned char *packet_buff, + int packet_len, unsigned long send_time, + bool direct_link, + struct hard_iface *if_incoming, + int own_packet) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct forw_packet *forw_packet_aggr; @@ -385,9 +385,9 @@ out: } /* aggregate a new packet into the existing ogm packet */ -static void bat_ogm_aggregate(struct forw_packet *forw_packet_aggr, - const unsigned char *packet_buff, - int packet_len, bool direct_link) +static void bat_iv_ogm_aggregate(struct forw_packet *forw_packet_aggr, + const unsigned char *packet_buff, + int packet_len, bool direct_link) { unsigned char *skb_buff; @@ -402,10 +402,10 @@ static void bat_ogm_aggregate(struct forw_packet *forw_packet_aggr, (1 << forw_packet_aggr->num_packets); } -static void bat_ogm_queue_add(struct bat_priv *bat_priv, - unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming, - int own_packet, unsigned long send_time) +static void bat_iv_ogm_queue_add(struct bat_priv *bat_priv, + unsigned char *packet_buff, + int packet_len, struct hard_iface *if_incoming, + int own_packet, unsigned long send_time) { /** * _aggr -> pointer to the packet we want to aggregate with @@ -425,11 +425,11 @@ static void bat_ogm_queue_add(struct bat_priv *bat_priv, if ((atomic_read(&bat_priv->aggregated_ogms)) && (!own_packet)) { hlist_for_each_entry(forw_packet_pos, tmp_node, &bat_priv->forw_bat_list, list) { - if (bat_ogm_can_aggregate(batman_ogm_packet, - bat_priv, packet_len, - send_time, direct_link, - if_incoming, - forw_packet_pos)) { + if (bat_iv_ogm_can_aggregate(batman_ogm_packet, + bat_priv, packet_len, + send_time, direct_link, + if_incoming, + forw_packet_pos)) { forw_packet_aggr = forw_packet_pos; break; } @@ -451,27 +451,27 @@ static void bat_ogm_queue_add(struct bat_priv *bat_priv, (atomic_read(&bat_priv->aggregated_ogms))) send_time += msecs_to_jiffies(MAX_AGGREGATION_MS); - bat_ogm_aggregate_new(packet_buff, packet_len, - send_time, direct_link, - if_incoming, own_packet); + bat_iv_ogm_aggregate_new(packet_buff, packet_len, + send_time, direct_link, + if_incoming, own_packet); } else { - bat_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, - direct_link); + bat_iv_ogm_aggregate(forw_packet_aggr, packet_buff, + packet_len, direct_link); spin_unlock_bh(&bat_priv->forw_bat_list_lock); } } -static void bat_ogm_forward(struct orig_node *orig_node, - const struct ethhdr *ethhdr, - struct batman_ogm_packet *batman_ogm_packet, - int directlink, struct hard_iface *if_incoming) +static void bat_iv_ogm_forward(struct orig_node *orig_node, + const struct ethhdr *ethhdr, + struct batman_ogm_packet *batman_ogm_packet, + int directlink, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct neigh_node *router; uint8_t in_tq, in_ttl, tq_avg = 0; uint8_t tt_num_changes; - if (batman_ogm_packet->ttl <= 1) { + if (batman_ogm_packet->header.ttl <= 1) { bat_dbg(DBG_BATMAN, bat_priv, "ttl exceeded\n"); return; } @@ -479,10 +479,10 @@ static void bat_ogm_forward(struct orig_node *orig_node, router = orig_node_get_router(orig_node); in_tq = batman_ogm_packet->tq; - in_ttl = batman_ogm_packet->ttl; + in_ttl = batman_ogm_packet->header.ttl; tt_num_changes = batman_ogm_packet->tt_num_changes; - batman_ogm_packet->ttl--; + batman_ogm_packet->header.ttl--; memcpy(batman_ogm_packet->prev_sender, ethhdr->h_source, ETH_ALEN); /* rebroadcast tq of our best ranking neighbor to ensure the rebroadcast @@ -494,7 +494,8 @@ static void bat_ogm_forward(struct orig_node *orig_node, batman_ogm_packet->tq = router->tq_avg; if (router->last_ttl) - batman_ogm_packet->ttl = router->last_ttl - 1; + batman_ogm_packet->header.ttl = + router->last_ttl - 1; } tq_avg = router->tq_avg; @@ -510,7 +511,7 @@ static void bat_ogm_forward(struct orig_node *orig_node, "Forwarding packet: tq_orig: %i, tq_avg: %i, " "tq_forw: %i, ttl_orig: %i, ttl_forw: %i\n", in_tq, tq_avg, batman_ogm_packet->tq, in_ttl - 1, - batman_ogm_packet->ttl); + batman_ogm_packet->header.ttl); batman_ogm_packet->seqno = htonl(batman_ogm_packet->seqno); batman_ogm_packet->tt_crc = htons(batman_ogm_packet->tt_crc); @@ -522,12 +523,13 @@ static void bat_ogm_forward(struct orig_node *orig_node, else batman_ogm_packet->flags &= ~DIRECTLINK; - bat_ogm_queue_add(bat_priv, (unsigned char *)batman_ogm_packet, - BATMAN_OGM_LEN + tt_len(tt_num_changes), - if_incoming, 0, bat_ogm_fwd_send_time()); + bat_iv_ogm_queue_add(bat_priv, (unsigned char *)batman_ogm_packet, + BATMAN_OGM_LEN + tt_len(tt_num_changes), + if_incoming, 0, bat_iv_ogm_fwd_send_time()); } -void bat_ogm_schedule(struct hard_iface *hard_iface, int tt_num_changes) +static void bat_iv_ogm_schedule(struct hard_iface *hard_iface, + int tt_num_changes) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct batman_ogm_packet *batman_ogm_packet; @@ -564,21 +566,22 @@ void bat_ogm_schedule(struct hard_iface *hard_iface, int tt_num_changes) atomic_inc(&hard_iface->seqno); slide_own_bcast_window(hard_iface); - bat_ogm_queue_add(bat_priv, hard_iface->packet_buff, - hard_iface->packet_len, hard_iface, 1, - bat_ogm_emit_send_time(bat_priv)); + bat_iv_ogm_queue_add(bat_priv, hard_iface->packet_buff, + hard_iface->packet_len, hard_iface, 1, + bat_iv_ogm_emit_send_time(bat_priv)); if (primary_if) hardif_free_ref(primary_if); } -static void bat_ogm_orig_update(struct bat_priv *bat_priv, - struct orig_node *orig_node, - const struct ethhdr *ethhdr, - const struct batman_ogm_packet +static void bat_iv_ogm_orig_update(struct bat_priv *bat_priv, + struct orig_node *orig_node, + const struct ethhdr *ethhdr, + const struct batman_ogm_packet *batman_ogm_packet, - struct hard_iface *if_incoming, - const unsigned char *tt_buff, int is_duplicate) + struct hard_iface *if_incoming, + const unsigned char *tt_buff, + int is_duplicate) { struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct neigh_node *router = NULL; @@ -642,8 +645,8 @@ static void bat_ogm_orig_update(struct bat_priv *bat_priv, spin_unlock_bh(&neigh_node->tq_lock); if (!is_duplicate) { - orig_node->last_ttl = batman_ogm_packet->ttl; - neigh_node->last_ttl = batman_ogm_packet->ttl; + orig_node->last_ttl = batman_ogm_packet->header.ttl; + neigh_node->last_ttl = batman_ogm_packet->header.ttl; } bonding_candidate_add(orig_node, neigh_node); @@ -683,7 +686,7 @@ update_tt: /* I have to check for transtable changes only if the OGM has been * sent through a primary interface */ if (((batman_ogm_packet->orig != ethhdr->h_source) && - (batman_ogm_packet->ttl > 2)) || + (batman_ogm_packet->header.ttl > 2)) || (batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) tt_update_orig(bat_priv, orig_node, tt_buff, batman_ogm_packet->tt_num_changes, @@ -713,10 +716,10 @@ out: neigh_node_free_ref(router); } -static int bat_ogm_calc_tq(struct orig_node *orig_node, - struct orig_node *orig_neigh_node, - struct batman_ogm_packet *batman_ogm_packet, - struct hard_iface *if_incoming) +static int bat_iv_ogm_calc_tq(struct orig_node *orig_node, + struct orig_node *orig_neigh_node, + struct batman_ogm_packet *batman_ogm_packet, + struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct neigh_node *neigh_node = NULL, *tmp_neigh_node; @@ -825,10 +828,10 @@ out: * -1 the packet is old and has been received while the seqno window * was protected. Caller should drop it. */ -static int bat_ogm_update_seqnos(const struct ethhdr *ethhdr, - const struct batman_ogm_packet +static int bat_iv_ogm_update_seqnos(const struct ethhdr *ethhdr, + const struct batman_ogm_packet *batman_ogm_packet, - const struct hard_iface *if_incoming) + const struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct orig_node *orig_node; @@ -890,10 +893,10 @@ out: return ret; } -static void bat_ogm_process(const struct ethhdr *ethhdr, - struct batman_ogm_packet *batman_ogm_packet, - const unsigned char *tt_buff, - struct hard_iface *if_incoming) +static void bat_iv_ogm_process(const struct ethhdr *ethhdr, + struct batman_ogm_packet *batman_ogm_packet, + const unsigned char *tt_buff, + struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct hard_iface *hard_iface; @@ -918,7 +921,7 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, * packet in an aggregation. Here we expect that the padding * is always zero (or not 0x01) */ - if (batman_ogm_packet->packet_type != BAT_OGM) + if (batman_ogm_packet->header.packet_type != BAT_OGM) return; /* could be changed by schedule_own_packet() */ @@ -938,8 +941,8 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, batman_ogm_packet->prev_sender, batman_ogm_packet->seqno, batman_ogm_packet->ttvn, batman_ogm_packet->tt_crc, batman_ogm_packet->tt_num_changes, batman_ogm_packet->tq, - batman_ogm_packet->ttl, batman_ogm_packet->version, - has_directlink_flag); + batman_ogm_packet->header.ttl, + batman_ogm_packet->header.version, has_directlink_flag); rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &hardif_list, list) { @@ -966,10 +969,10 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, } rcu_read_unlock(); - if (batman_ogm_packet->version != COMPAT_VERSION) { + if (batman_ogm_packet->header.version != COMPAT_VERSION) { bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: incompatible batman version (%i)\n", - batman_ogm_packet->version); + batman_ogm_packet->header.version); return; } @@ -1031,8 +1034,8 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, if (!orig_node) return; - is_duplicate = bat_ogm_update_seqnos(ethhdr, batman_ogm_packet, - if_incoming); + is_duplicate = bat_iv_ogm_update_seqnos(ethhdr, batman_ogm_packet, + if_incoming); if (is_duplicate == -1) { bat_dbg(DBG_BATMAN, bat_priv, @@ -1081,8 +1084,8 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, goto out_neigh; } - is_bidirectional = bat_ogm_calc_tq(orig_node, orig_neigh_node, - batman_ogm_packet, if_incoming); + is_bidirectional = bat_iv_ogm_calc_tq(orig_node, orig_neigh_node, + batman_ogm_packet, if_incoming); bonding_save_primary(orig_node, orig_neigh_node, batman_ogm_packet); @@ -1091,17 +1094,17 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, if (is_bidirectional && (!is_duplicate || ((orig_node->last_real_seqno == batman_ogm_packet->seqno) && - (orig_node->last_ttl - 3 <= batman_ogm_packet->ttl)))) - bat_ogm_orig_update(bat_priv, orig_node, ethhdr, - batman_ogm_packet, if_incoming, - tt_buff, is_duplicate); + (orig_node->last_ttl - 3 <= batman_ogm_packet->header.ttl)))) + bat_iv_ogm_orig_update(bat_priv, orig_node, ethhdr, + batman_ogm_packet, if_incoming, + tt_buff, is_duplicate); /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { /* mark direct link on incoming interface */ - bat_ogm_forward(orig_node, ethhdr, batman_ogm_packet, - 1, if_incoming); + bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, + 1, if_incoming); bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: " "rebroadcast neighbor packet with direct link flag\n"); @@ -1123,7 +1126,8 @@ static void bat_ogm_process(const struct ethhdr *ethhdr, bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); - bat_ogm_forward(orig_node, ethhdr, batman_ogm_packet, 0, if_incoming); + bat_iv_ogm_forward(orig_node, ethhdr, batman_ogm_packet, + 0, if_incoming); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) @@ -1139,13 +1143,17 @@ out: orig_node_free_ref(orig_node); } -void bat_ogm_receive(const struct ethhdr *ethhdr, unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming) +static void bat_iv_ogm_receive(struct hard_iface *if_incoming, + struct sk_buff *skb) { struct batman_ogm_packet *batman_ogm_packet; - int buff_pos = 0; - unsigned char *tt_buff; + struct ethhdr *ethhdr; + int buff_pos = 0, packet_len; + unsigned char *tt_buff, *packet_buff; + packet_len = skb_headlen(skb); + ethhdr = (struct ethhdr *)skb_mac_header(skb); + packet_buff = skb->data; batman_ogm_packet = (struct batman_ogm_packet *)packet_buff; /* unpack the aggregated packets and process them one by one */ @@ -1157,14 +1165,29 @@ void bat_ogm_receive(const struct ethhdr *ethhdr, unsigned char *packet_buff, tt_buff = packet_buff + buff_pos + BATMAN_OGM_LEN; - bat_ogm_process(ethhdr, batman_ogm_packet, - tt_buff, if_incoming); + bat_iv_ogm_process(ethhdr, batman_ogm_packet, + tt_buff, if_incoming); buff_pos += BATMAN_OGM_LEN + tt_len(batman_ogm_packet->tt_num_changes); batman_ogm_packet = (struct batman_ogm_packet *) (packet_buff + buff_pos); - } while (bat_ogm_aggr_packet(buff_pos, packet_len, - batman_ogm_packet->tt_num_changes)); + } while (bat_iv_ogm_aggr_packet(buff_pos, packet_len, + batman_ogm_packet->tt_num_changes)); +} + +static struct bat_algo_ops batman_iv __read_mostly = { + .name = "BATMAN IV", + .bat_ogm_init = bat_iv_ogm_init, + .bat_ogm_init_primary = bat_iv_ogm_init_primary, + .bat_ogm_update_mac = bat_iv_ogm_update_mac, + .bat_ogm_schedule = bat_iv_ogm_schedule, + .bat_ogm_emit = bat_iv_ogm_emit, + .bat_ogm_receive = bat_iv_ogm_receive, +}; + +int __init bat_iv_init(void) +{ + return bat_algo_register(&batman_iv); } diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index c25492f..b00101d 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -272,6 +272,13 @@ static ssize_t store_vis_mode(struct kobject *kobj, struct attribute *attr, return count; } +static ssize_t show_bat_algo(struct kobject *kobj, struct attribute *attr, + char *buff) +{ + struct bat_priv *bat_priv = kobj_to_batpriv(kobj); + return sprintf(buff, "%s\n", bat_priv->bat_algo_ops->name); +} + static void post_gw_deselect(struct net_device *net_dev) { struct bat_priv *bat_priv = netdev_priv(net_dev); @@ -314,11 +321,11 @@ static ssize_t store_gw_mode(struct kobject *kobj, struct attribute *attr, gw_mode_tmp = GW_MODE_OFF; if (strncmp(buff, GW_MODE_CLIENT_NAME, - strlen(GW_MODE_CLIENT_NAME)) == 0) + strlen(GW_MODE_CLIENT_NAME)) == 0) gw_mode_tmp = GW_MODE_CLIENT; if (strncmp(buff, GW_MODE_SERVER_NAME, - strlen(GW_MODE_SERVER_NAME)) == 0) + strlen(GW_MODE_SERVER_NAME)) == 0) gw_mode_tmp = GW_MODE_SERVER; if (gw_mode_tmp < 0) { @@ -382,6 +389,7 @@ BAT_ATTR_BOOL(bonding, S_IRUGO | S_IWUSR, NULL); BAT_ATTR_BOOL(fragmentation, S_IRUGO | S_IWUSR, update_min_mtu); BAT_ATTR_BOOL(ap_isolation, S_IRUGO | S_IWUSR, NULL); static BAT_ATTR(vis_mode, S_IRUGO | S_IWUSR, show_vis_mode, store_vis_mode); +static BAT_ATTR(routing_algo, S_IRUGO, show_bat_algo, NULL); static BAT_ATTR(gw_mode, S_IRUGO | S_IWUSR, show_gw_mode, store_gw_mode); BAT_ATTR_UINT(orig_interval, S_IRUGO | S_IWUSR, 2 * JITTER, INT_MAX, NULL); BAT_ATTR_UINT(hop_penalty, S_IRUGO | S_IWUSR, 0, TQ_MAX_VALUE, NULL); @@ -399,6 +407,7 @@ static struct bat_attribute *mesh_attrs[] = { &bat_attr_fragmentation, &bat_attr_ap_isolation, &bat_attr_vis_mode, + &bat_attr_routing_algo, &bat_attr_gw_mode, &bat_attr_orig_interval, &bat_attr_hop_penalty, diff --git a/net/batman-adv/bat_sysfs.h b/net/batman-adv/bat_sysfs.h index a3f75a7..fece77a 100644 --- a/net/batman-adv/bat_sysfs.h +++ b/net/batman-adv/bat_sysfs.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 9bc63b2..6d0aa21 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -154,8 +154,8 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, /* sequence number is much newer, probably missed a lot of packets */ - if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE) - && (seq_num_diff < EXPECTED_SEQNO_RANGE)) { + if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE) && + (seq_num_diff < EXPECTED_SEQNO_RANGE)) { bat_dbg(DBG_BATMAN, bat_priv, "We missed a lot of packets (%i) !\n", seq_num_diff - 1); @@ -170,8 +170,8 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, * packet should be dropped without calling this function if the * seqno window is protected. */ - if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) - || (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { + if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || + (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { bat_dbg(DBG_BATMAN, bat_priv, "Other host probably restarted!\n"); diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 9c04422..c613572 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 24403a7..0fa8e2d 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -396,7 +396,7 @@ void gw_node_purge(struct bat_priv *bat_priv) { struct gw_node *gw_node, *curr_gw; struct hlist_node *node, *node_tmp; - unsigned long timeout = 2 * PURGE_TIMEOUT * HZ; + unsigned long timeout = msecs_to_jiffies(2 * PURGE_TIMEOUT); int do_deselect = 0; curr_gw = gw_get_selected_gw_node(bat_priv); @@ -629,7 +629,7 @@ bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) /* check for bootp port */ if ((ntohs(ethhdr->h_proto) == ETH_P_IP) && - (ntohs(udphdr->dest) != 67)) + (ntohs(udphdr->dest) != 67)) return false; if ((ntohs(ethhdr->h_proto) == ETH_P_IPV6) && diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index e1edba0..bf56a5a 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index c4ac7b0..3ccb9c8 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -93,7 +93,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, multi = 1024; if ((strnicmp(tmp_ptr, "kbit", 4) == 0) || - (multi > 1)) + (multi > 1)) *tmp_ptr = '\0'; } @@ -118,7 +118,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, multi = 1024; if ((strnicmp(tmp_ptr, "kbit", 4) == 0) || - (multi > 1)) + (multi > 1)) *tmp_ptr = '\0'; } diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 55e527a..b8fb11c 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7704df4..409d027 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,6 @@ #include "bat_sysfs.h" #include "originator.h" #include "hash.h" -#include "bat_ogm.h" #include <linux/if_arp.h> @@ -147,7 +146,7 @@ static void primary_if_select(struct bat_priv *bat_priv, if (!new_hard_iface) return; - bat_ogm_init_primary(new_hard_iface); + bat_priv->bat_algo_ops->bat_ogm_init_primary(new_hard_iface); primary_if_update_addr(bat_priv); } @@ -233,7 +232,7 @@ static void hardif_activate_interface(struct hard_iface *hard_iface) bat_priv = netdev_priv(hard_iface->soft_iface); - bat_ogm_update_mac(hard_iface); + bat_priv->bat_algo_ops->bat_ogm_update_mac(hard_iface); hard_iface->if_status = IF_TO_BE_ACTIVATED; /** @@ -281,6 +280,14 @@ int hardif_enable_interface(struct hard_iface *hard_iface, if (!atomic_inc_not_zero(&hard_iface->refcount)) goto out; + /* hard-interface is part of a bridge */ + if (hard_iface->net_dev->priv_flags & IFF_BRIDGE_PORT) + pr_err("You are about to enable batman-adv on '%s' which " + "already is part of a bridge. Unless you know exactly " + "what you are doing this is probably wrong and won't " + "work the way you think it would.\n", + hard_iface->net_dev->name); + soft_iface = dev_get_by_name(&init_net, iface_name); if (!soft_iface) { @@ -307,7 +314,7 @@ int hardif_enable_interface(struct hard_iface *hard_iface, hard_iface->soft_iface = soft_iface; bat_priv = netdev_priv(hard_iface->soft_iface); - bat_ogm_init(hard_iface); + bat_priv->bat_algo_ops->bat_ogm_init(hard_iface); if (!hard_iface->packet_buff) { bat_err(hard_iface->soft_iface, "Can't add interface packet " @@ -334,23 +341,23 @@ int hardif_enable_interface(struct hard_iface *hard_iface, if (atomic_read(&bat_priv->fragmentation) && hard_iface->net_dev->mtu < ETH_DATA_LEN + BAT_HEADER_LEN) bat_info(hard_iface->soft_iface, - "The MTU of interface %s is too small (%i) to handle " - "the transport of batman-adv packets. Packets going " - "over this interface will be fragmented on layer2 " - "which could impact the performance. Setting the MTU " - "to %zi would solve the problem.\n", - hard_iface->net_dev->name, hard_iface->net_dev->mtu, - ETH_DATA_LEN + BAT_HEADER_LEN); + "The MTU of interface %s is too small (%i) to handle " + "the transport of batman-adv packets. Packets going " + "over this interface will be fragmented on layer2 " + "which could impact the performance. Setting the MTU " + "to %zi would solve the problem.\n", + hard_iface->net_dev->name, hard_iface->net_dev->mtu, + ETH_DATA_LEN + BAT_HEADER_LEN); if (!atomic_read(&bat_priv->fragmentation) && hard_iface->net_dev->mtu < ETH_DATA_LEN + BAT_HEADER_LEN) bat_info(hard_iface->soft_iface, - "The MTU of interface %s is too small (%i) to handle " - "the transport of batman-adv packets. If you experience" - " problems getting traffic through try increasing the " - "MTU to %zi.\n", - hard_iface->net_dev->name, hard_iface->net_dev->mtu, - ETH_DATA_LEN + BAT_HEADER_LEN); + "The MTU of interface %s is too small (%i) to handle " + "the transport of batman-adv packets. If you " + "experience problems getting traffic through try " + "increasing the MTU to %zi.\n", + hard_iface->net_dev->name, hard_iface->net_dev->mtu, + ETH_DATA_LEN + BAT_HEADER_LEN); if (hardif_is_iface_up(hard_iface)) hardif_activate_interface(hard_iface); @@ -527,9 +534,10 @@ static int hard_if_event(struct notifier_block *this, goto hardif_put; check_known_mac_addr(hard_iface->net_dev); - bat_ogm_update_mac(hard_iface); bat_priv = netdev_priv(hard_iface->soft_iface); + bat_priv->bat_algo_ops->bat_ogm_update_mac(hard_iface); + primary_if = primary_if_get_selected(bat_priv); if (!primary_if) goto hardif_put; @@ -572,8 +580,8 @@ static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, goto err_free; /* expect a valid ethernet header here. */ - if (unlikely(skb->mac_len != sizeof(struct ethhdr) - || !skb_mac_header(skb))) + if (unlikely(skb->mac_len != sizeof(struct ethhdr) || + !skb_mac_header(skb))) goto err_free; if (!hard_iface->soft_iface) @@ -590,17 +598,17 @@ static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, batman_ogm_packet = (struct batman_ogm_packet *)skb->data; - if (batman_ogm_packet->version != COMPAT_VERSION) { + if (batman_ogm_packet->header.version != COMPAT_VERSION) { bat_dbg(DBG_BATMAN, bat_priv, "Drop packet: incompatible batman version (%i)\n", - batman_ogm_packet->version); + batman_ogm_packet->header.version); goto err_free; } /* all receive handlers return whether they received or reused * the supplied skb. if not, we have to free the skb. */ - switch (batman_ogm_packet->packet_type) { + switch (batman_ogm_packet->header.packet_type) { /* batman originator packet */ case BAT_OGM: ret = recv_bat_ogm_packet(skb, hard_iface); diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 67f78d1..e68c565 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index d1da29d..117687b 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 4768717..d4bd786 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2006-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2006-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index d9c1e7b..9b755f9 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -191,7 +191,7 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, goto free_skb; } - if (icmp_packet->packet_type != BAT_ICMP) { + if (icmp_packet->header.packet_type != BAT_ICMP) { bat_dbg(DBG_BATMAN, bat_priv, "Error - can't send packet from char device: " "got bogus packet type (expected: BAT_ICMP)\n"); @@ -209,9 +209,9 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff, icmp_packet->uid = socket_client->index; - if (icmp_packet->version != COMPAT_VERSION) { + if (icmp_packet->header.version != COMPAT_VERSION) { icmp_packet->msg_type = PARAMETER_PROBLEM; - icmp_packet->version = COMPAT_VERSION; + icmp_packet->header.version = COMPAT_VERSION; bat_socket_add_packet(socket_client, icmp_packet, packet_len); goto free_skb; } diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 462b190..380ed4c 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index fb87bdc..08f3b3a 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -32,11 +32,14 @@ #include "gateway_client.h" #include "vis.h" #include "hash.h" +#include "bat_algo.h" /* List manipulations on hardif_list have to be rtnl_lock()'ed, * list traversals just rcu-locked */ struct list_head hardif_list; +char bat_routing_algo[20] = "BATMAN IV"; +static struct hlist_head bat_algo_list; unsigned char broadcast_addr[] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; @@ -45,6 +48,9 @@ struct workqueue_struct *bat_event_workqueue; static int __init batman_init(void) { INIT_LIST_HEAD(&hardif_list); + INIT_HLIST_HEAD(&bat_algo_list); + + bat_iv_init(); /* the name should not be longer than 10 chars - see * http://lwn.net/Articles/23634/ */ @@ -170,9 +176,110 @@ int is_my_mac(const uint8_t *addr) } rcu_read_unlock(); return 0; +} + +static struct bat_algo_ops *bat_algo_get(char *name) +{ + struct bat_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp; + struct hlist_node *node; + + hlist_for_each_entry(bat_algo_ops_tmp, node, &bat_algo_list, list) { + if (strcmp(bat_algo_ops_tmp->name, name) != 0) + continue; + + bat_algo_ops = bat_algo_ops_tmp; + break; + } + + return bat_algo_ops; +} + +int bat_algo_register(struct bat_algo_ops *bat_algo_ops) +{ + struct bat_algo_ops *bat_algo_ops_tmp; + int ret = -1; + + bat_algo_ops_tmp = bat_algo_get(bat_algo_ops->name); + if (bat_algo_ops_tmp) { + pr_info("Trying to register already registered routing " + "algorithm: %s\n", bat_algo_ops->name); + goto out; + } + + /* all algorithms must implement all ops (for now) */ + if (!bat_algo_ops->bat_ogm_init || + !bat_algo_ops->bat_ogm_init_primary || + !bat_algo_ops->bat_ogm_update_mac || + !bat_algo_ops->bat_ogm_schedule || + !bat_algo_ops->bat_ogm_emit || + !bat_algo_ops->bat_ogm_receive) { + pr_info("Routing algo '%s' does not implement required ops\n", + bat_algo_ops->name); + goto out; + } + + INIT_HLIST_NODE(&bat_algo_ops->list); + hlist_add_head(&bat_algo_ops->list, &bat_algo_list); + ret = 0; + +out: + return ret; +} + +int bat_algo_select(struct bat_priv *bat_priv, char *name) +{ + struct bat_algo_ops *bat_algo_ops; + int ret = -1; + + bat_algo_ops = bat_algo_get(name); + if (!bat_algo_ops) + goto out; + + bat_priv->bat_algo_ops = bat_algo_ops; + ret = 0; + +out: + return ret; +} + +int bat_algo_seq_print_text(struct seq_file *seq, void *offset) +{ + struct bat_algo_ops *bat_algo_ops; + struct hlist_node *node; + + seq_printf(seq, "Available routing algorithms:\n"); + + hlist_for_each_entry(bat_algo_ops, node, &bat_algo_list, list) { + seq_printf(seq, "%s\n", bat_algo_ops->name); + } + + return 0; +} + +static int param_set_ra(const char *val, const struct kernel_param *kp) +{ + struct bat_algo_ops *bat_algo_ops; + bat_algo_ops = bat_algo_get((char *)val); + if (!bat_algo_ops) { + pr_err("Routing algorithm '%s' is not supported\n", val); + return -EINVAL; + } + + return param_set_copystring(val, kp); } +static const struct kernel_param_ops param_ops_ra = { + .set = param_set_ra, + .get = param_get_string, +}; + +static struct kparam_string __param_string_ra = { + .maxlen = sizeof(bat_routing_algo), + .string = bat_routing_algo, +}; + +module_param_cb(routing_algo, ¶m_ops_ra, &__param_string_ra, 0644); module_init(batman_init); module_exit(batman_exit); diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 86354e0..1468788 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,7 @@ #define DRIVER_DEVICE "batman-adv" #ifndef SOURCE_VERSION -#define SOURCE_VERSION "2012.0.0" +#define SOURCE_VERSION "2012.1.0" #endif /* B.A.T.M.A.N. parameters */ @@ -41,13 +41,14 @@ /* purge originators after time in seconds if no valid packet comes in * -> TODO: check influence on TQ_LOCAL_WINDOW_SIZE */ -#define PURGE_TIMEOUT 200 -#define TT_LOCAL_TIMEOUT 3600 /* in seconds */ -#define TT_CLIENT_ROAM_TIMEOUT 600 +#define PURGE_TIMEOUT 200000 /* 200 seconds */ +#define TT_LOCAL_TIMEOUT 3600000 /* in miliseconds */ +#define TT_CLIENT_ROAM_TIMEOUT 600000 /* in miliseconds */ /* sliding packet range of received originator messages in sequence numbers * (should be a multiple of our word size) */ #define TQ_LOCAL_WINDOW_SIZE 64 -#define TT_REQUEST_TIMEOUT 3 /* seconds we have to keep pending tt_req */ +#define TT_REQUEST_TIMEOUT 3000 /* miliseconds we have to keep + * pending tt_req */ #define TQ_GLOBAL_WINDOW_SIZE 5 #define TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 @@ -56,8 +57,8 @@ #define TT_OGM_APPEND_MAX 3 /* number of OGMs sent with the last tt diff */ -#define ROAMING_MAX_TIME 20 /* Time in which a client can roam at most - * ROAMING_MAX_COUNT times */ +#define ROAMING_MAX_TIME 20000 /* Time in which a client can roam at most + * ROAMING_MAX_COUNT times in miliseconds*/ #define ROAMING_MAX_COUNT 5 #define NO_FLAGS 0 @@ -147,6 +148,7 @@ enum dbg_level { #include <linux/seq_file.h> #include "types.h" +extern char bat_routing_algo[]; extern struct list_head hardif_list; extern unsigned char broadcast_addr[]; @@ -157,6 +159,9 @@ void mesh_free(struct net_device *soft_iface); void inc_module_count(void); void dec_module_count(void); int is_my_mac(const uint8_t *addr); +int bat_algo_register(struct bat_algo_ops *bat_algo_ops); +int bat_algo_select(struct bat_priv *bat_priv, char *name); +int bat_algo_seq_print_text(struct seq_file *seq, void *offset); #ifdef CONFIG_BATMAN_ADV_DEBUG int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) __printf(2, 3); @@ -202,6 +207,17 @@ static inline int compare_eth(const void *data1, const void *data2) return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } +/** + * has_timed_out - compares current time (jiffies) and timestamp + timeout + * @timestamp: base value to compare with (in jiffies) + * @timeout: added to base value before comparing (in milliseconds) + * + * Returns true if current time is after timestamp + timeout + */ +static inline bool has_timed_out(unsigned long timestamp, unsigned int timeout) +{ + return time_is_before_jiffies(timestamp + msecs_to_jiffies(timeout)); +} #define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 0bc2045..371cc93 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2009-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2009-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -143,7 +143,7 @@ static void orig_node_free_rcu(struct rcu_head *rcu) frag_list_free(&orig_node->frag_list); tt_global_del_orig(orig_node->bat_priv, orig_node, - "originator timed out"); + "originator timed out"); kfree(orig_node->tt_buff); kfree(orig_node->bcast_own); @@ -219,6 +219,7 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) /* extra reference for return */ atomic_set(&orig_node->refcount, 2); + orig_node->tt_initialised = false; orig_node->tt_poss_change = false; orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); @@ -281,8 +282,7 @@ static bool purge_orig_neighbors(struct bat_priv *bat_priv, hlist_for_each_entry_safe(neigh_node, node, node_tmp, &orig_node->neigh_list, list) { - if ((time_after(jiffies, - neigh_node->last_valid + PURGE_TIMEOUT * HZ)) || + if ((has_timed_out(neigh_node->last_valid, PURGE_TIMEOUT)) || (neigh_node->if_incoming->if_status == IF_INACTIVE) || (neigh_node->if_incoming->if_status == IF_NOT_IN_USE) || (neigh_node->if_incoming->if_status == IF_TO_BE_REMOVED)) { @@ -326,18 +326,15 @@ static bool purge_orig_node(struct bat_priv *bat_priv, { struct neigh_node *best_neigh_node; - if (time_after(jiffies, - orig_node->last_valid + 2 * PURGE_TIMEOUT * HZ)) { - + if (has_timed_out(orig_node->last_valid, 2 * PURGE_TIMEOUT)) { bat_dbg(DBG_BATMAN, bat_priv, "Originator timeout: originator %pM, last_valid %lu\n", orig_node->orig, (orig_node->last_valid / HZ)); return true; } else { if (purge_orig_neighbors(bat_priv, orig_node, - &best_neigh_node)) { + &best_neigh_node)) update_route(bat_priv, orig_node, best_neigh_node); - } } return false; @@ -371,8 +368,8 @@ static void _purge_orig(struct bat_priv *bat_priv) continue; } - if (time_after(jiffies, orig_node->last_frag_packet + - msecs_to_jiffies(FRAG_TIMEOUT))) + if (has_timed_out(orig_node->last_frag_packet, + FRAG_TIMEOUT)) frag_list_free(&orig_node->frag_list); } spin_unlock_bh(list_lock); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 67765ff..3fe2eda 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index 4d9e54c..441f3db 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -90,10 +90,14 @@ enum tt_client_flags { TT_CLIENT_PENDING = 1 << 10 }; -struct batman_ogm_packet { +struct batman_header { uint8_t packet_type; uint8_t version; /* batman version field */ uint8_t ttl; +} __packed; + +struct batman_ogm_packet { + struct batman_header header; uint8_t flags; /* 0x40: DIRECTLINK flag, 0x20 VIS_SERVER flag... */ uint32_t seqno; uint8_t orig[6]; @@ -108,9 +112,7 @@ struct batman_ogm_packet { #define BATMAN_OGM_LEN sizeof(struct batman_ogm_packet) struct icmp_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[6]; uint8_t orig[6]; @@ -124,9 +126,7 @@ struct icmp_packet { /* icmp_packet_rr must start with all fields from imcp_packet * as this is assumed by code that handles ICMP packets */ struct icmp_packet_rr { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[6]; uint8_t orig[6]; @@ -137,17 +137,13 @@ struct icmp_packet_rr { } __packed; struct unicast_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; uint8_t ttvn; /* destination translation table version number */ uint8_t dest[6]; } __packed; struct unicast_frag_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; uint8_t ttvn; /* destination translation table version number */ uint8_t dest[6]; uint8_t flags; @@ -157,18 +153,14 @@ struct unicast_frag_packet { } __packed; struct bcast_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; uint8_t reserved; uint32_t seqno; uint8_t orig[6]; } __packed; struct vis_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; /* TTL */ + struct batman_header header; uint8_t vis_type; /* which type of vis-participant sent this? */ uint32_t seqno; /* sequence number */ uint8_t entries; /* number of entries behind this struct */ @@ -179,9 +171,7 @@ struct vis_packet { } __packed; struct tt_query_packet { - uint8_t packet_type; - uint8_t version; /* batman version field */ - uint8_t ttl; + struct batman_header header; /* the flag field is a combination of: * - TT_REQUEST or TT_RESPONSE * - TT_FULL_TABLE */ @@ -202,9 +192,7 @@ struct tt_query_packet { } __packed; struct roam_adv_packet { - uint8_t packet_type; - uint8_t version; - uint8_t ttl; + struct batman_header header; uint8_t reserved; uint8_t dst[ETH_ALEN]; uint8_t src[ETH_ALEN]; diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index f1ccfa7..fd63951 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index 7cdfe62..8b58bd8 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 773e606..f535155 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -29,7 +29,6 @@ #include "originator.h" #include "vis.h" #include "unicast.h" -#include "bat_ogm.h" void slide_own_bcast_window(struct hard_iface *hard_iface) { @@ -73,7 +72,7 @@ static void _update_route(struct bat_priv *bat_priv, bat_dbg(DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", orig_node->orig); tt_global_del_orig(bat_priv, orig_node, - "Deleted route towards originator"); + "Deleted route towards originator"); /* route added */ } else if ((!curr_router) && (neigh_node)) { @@ -230,10 +229,9 @@ void bonding_save_primary(const struct orig_node *orig_node, int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, unsigned long *last_reset) { - if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) - || (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { - if (time_after(jiffies, *last_reset + - msecs_to_jiffies(RESET_PROTECTION_MS))) { + if ((seq_num_diff <= -TQ_LOCAL_WINDOW_SIZE) || + (seq_num_diff >= EXPECTED_SEQNO_RANGE)) { + if (has_timed_out(*last_reset, RESET_PROTECTION_MS)) { *last_reset = jiffies; bat_dbg(DBG_BATMAN, bat_priv, @@ -248,6 +246,7 @@ int window_protected(struct bat_priv *bat_priv, int32_t seq_num_diff, int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *hard_iface) { + struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); struct ethhdr *ethhdr; /* drop packet if it has not necessary minimum size */ @@ -272,9 +271,7 @@ int recv_bat_ogm_packet(struct sk_buff *skb, struct hard_iface *hard_iface) if (skb_linearize(skb) < 0) return NET_RX_DROP; - ethhdr = (struct ethhdr *)skb_mac_header(skb); - - bat_ogm_receive(ethhdr, skb->data, skb_headlen(skb), hard_iface); + bat_priv->bat_algo_ops->bat_ogm_receive(hard_iface, skb); kfree_skb(skb); return NET_RX_SUCCESS; @@ -320,7 +317,7 @@ static int recv_my_icmp_packet(struct bat_priv *bat_priv, memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); icmp_packet->msg_type = ECHO_REPLY; - icmp_packet->ttl = TTL; + icmp_packet->header.ttl = TTL; send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; @@ -376,7 +373,7 @@ static int recv_icmp_ttl_exceeded(struct bat_priv *bat_priv, memcpy(icmp_packet->dst, icmp_packet->orig, ETH_ALEN); memcpy(icmp_packet->orig, primary_if->net_dev->dev_addr, ETH_ALEN); icmp_packet->msg_type = TTL_EXCEEDED; - icmp_packet->ttl = TTL; + icmp_packet->header.ttl = TTL; send_skb_packet(skb, router->if_incoming, router->addr); ret = NET_RX_SUCCESS; @@ -432,7 +429,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) if ((hdr_size == sizeof(struct icmp_packet_rr)) && (icmp_packet->rr_cur < BAT_RR_LEN)) { memcpy(&(icmp_packet->rr[icmp_packet->rr_cur]), - ethhdr->h_dest, ETH_ALEN); + ethhdr->h_dest, ETH_ALEN); icmp_packet->rr_cur++; } @@ -441,7 +438,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) return recv_my_icmp_packet(bat_priv, skb, hdr_size); /* TTL exceeded */ - if (icmp_packet->ttl < 2) + if (icmp_packet->header.ttl < 2) return recv_icmp_ttl_exceeded(bat_priv, skb); /* get routing information */ @@ -460,7 +457,7 @@ int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if) icmp_packet = (struct icmp_packet_rr *)skb->data; /* decrement ttl */ - icmp_packet->ttl--; + icmp_packet->header.ttl--; /* route it */ send_skb_packet(skb, router->if_incoming, router->addr); @@ -815,7 +812,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) unicast_packet = (struct unicast_packet *)skb->data; /* TTL exceeded */ - if (unicast_packet->ttl < 2) { + if (unicast_packet->header.ttl < 2) { pr_debug("Warning - can't forward unicast packet from %pM to " "%pM: ttl exceeded\n", ethhdr->h_source, unicast_packet->dest); @@ -840,7 +837,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) unicast_packet = (struct unicast_packet *)skb->data; - if (unicast_packet->packet_type == BAT_UNICAST && + if (unicast_packet->header.packet_type == BAT_UNICAST && atomic_read(&bat_priv->fragmentation) && skb->len > neigh_node->if_incoming->net_dev->mtu) { ret = frag_send_skb(skb, bat_priv, @@ -848,7 +845,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) goto out; } - if (unicast_packet->packet_type == BAT_UNICAST_FRAG && + if (unicast_packet->header.packet_type == BAT_UNICAST_FRAG && frag_can_reassemble(skb, neigh_node->if_incoming->net_dev->mtu)) { ret = frag_reassemble_skb(skb, bat_priv, &new_skb); @@ -867,7 +864,7 @@ int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) } /* decrement ttl */ - unicast_packet->ttl--; + unicast_packet->header.ttl--; /* route it */ send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); @@ -1041,7 +1038,7 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) if (is_my_mac(bcast_packet->orig)) goto out; - if (bcast_packet->ttl < 2) + if (bcast_packet->header.ttl < 2) goto out; orig_node = orig_hash_find(bat_priv, bcast_packet->orig); diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 7aaee0f..92ac100 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 8a684eb..4137580 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -28,7 +28,6 @@ #include "vis.h" #include "gateway_common.h" #include "originator.h" -#include "bat_ogm.h" static void send_outstanding_bcast_packet(struct work_struct *work); @@ -168,7 +167,7 @@ void schedule_bat_ogm(struct hard_iface *hard_iface) if (primary_if) hardif_free_ref(primary_if); - bat_ogm_schedule(hard_iface, tt_num_changes); + bat_priv->bat_algo_ops->bat_ogm_schedule(hard_iface, tt_num_changes); } static void forw_packet_free(struct forw_packet *forw_packet) @@ -234,7 +233,7 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, /* as we have a copy now, it is safe to decrease the TTL */ bcast_packet = (struct bcast_packet *)newskb->data; - bcast_packet->ttl--; + bcast_packet->header.ttl--; skb_reset_mac_header(newskb); @@ -318,7 +317,7 @@ void send_outstanding_bat_ogm_packet(struct work_struct *work) if (atomic_read(&bat_priv->mesh_state) == MESH_DEACTIVATING) goto out; - bat_ogm_emit(forw_packet); + bat_priv->bat_algo_ops->bat_ogm_emit(forw_packet); /** * we have to have at least one packet in the queue diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index c8ca3ef..824ef06 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 987c75a..8fb16d2 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -396,8 +396,8 @@ void softif_neigh_purge(struct bat_priv *bat_priv) hlist_for_each_entry_safe(softif_neigh, node_tmp, node_tmp2, &softif_neigh_vid->softif_neigh_list, list) { - if ((!time_after(jiffies, softif_neigh->last_seen + - msecs_to_jiffies(SOFTIF_NEIGH_TIMEOUT))) && + if ((!has_timed_out(softif_neigh->last_seen, + SOFTIF_NEIGH_TIMEOUT)) && (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE)) continue; @@ -457,10 +457,10 @@ static void softif_batman_recv(struct sk_buff *skb, struct net_device *dev, batman_ogm_packet = (struct batman_ogm_packet *) (skb->data + ETH_HLEN); - if (batman_ogm_packet->version != COMPAT_VERSION) + if (batman_ogm_packet->header.version != COMPAT_VERSION) goto out; - if (batman_ogm_packet->packet_type != BAT_OGM) + if (batman_ogm_packet->header.packet_type != BAT_OGM) goto out; if (!(batman_ogm_packet->flags & PRIMARIES_FIRST_HOP)) @@ -541,6 +541,7 @@ static int interface_set_mac_addr(struct net_device *dev, void *p) } memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + dev->addr_assign_type &= ~NET_ADDR_RANDOM; return 0; } @@ -632,11 +633,11 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) goto dropped; bcast_packet = (struct bcast_packet *)skb->data; - bcast_packet->version = COMPAT_VERSION; - bcast_packet->ttl = TTL; + bcast_packet->header.version = COMPAT_VERSION; + bcast_packet->header.ttl = TTL; /* batman packet type: broadcast */ - bcast_packet->packet_type = BAT_BCAST; + bcast_packet->header.packet_type = BAT_BCAST; /* hw address of first interface is the orig mac because only * this mac is known throughout the mesh */ @@ -725,8 +726,8 @@ void interface_rx(struct net_device *soft_iface, skb_push(skb, hdr_size); unicast_packet = (struct unicast_packet *)skb->data; - if ((unicast_packet->packet_type != BAT_UNICAST) && - (unicast_packet->packet_type != BAT_UNICAST_FRAG)) + if ((unicast_packet->header.packet_type != BAT_UNICAST) && + (unicast_packet->header.packet_type != BAT_UNICAST_FRAG)) goto dropped; skb_reset_mac_header(skb); @@ -783,7 +784,6 @@ static const struct net_device_ops bat_netdev_ops = { static void interface_setup(struct net_device *dev) { struct bat_priv *priv = netdev_priv(dev); - char dev_addr[ETH_ALEN]; ether_setup(dev); @@ -800,8 +800,7 @@ static void interface_setup(struct net_device *dev) dev->hard_header_len = BAT_HEADER_LEN; /* generate random address */ - random_ether_addr(dev_addr); - memcpy(dev->dev_addr, dev_addr, ETH_ALEN); + eth_hw_addr_random(dev); SET_ETHTOOL_OPS(dev, &bat_ethtool_ops); @@ -855,6 +854,10 @@ struct net_device *softif_create(const char *name) bat_priv->primary_if = NULL; bat_priv->num_ifaces = 0; + ret = bat_algo_select(bat_priv, bat_routing_algo); + if (ret < 0) + goto unreg_soft_iface; + ret = sysfs_add_meshif(soft_iface); if (ret < 0) goto unreg_soft_iface; diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 001546f..756eab5 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index ab8dea8..c950705 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -108,14 +108,6 @@ static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, } -static bool is_out_of_time(unsigned long starting_time, unsigned long timeout) -{ - unsigned long deadline; - deadline = starting_time + msecs_to_jiffies(timeout); - - return time_after(jiffies, deadline); -} - static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry) { if (atomic_dec_and_test(&tt_local_entry->common.refcount)) @@ -218,6 +210,11 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, if (compare_eth(addr, soft_iface->dev_addr)) tt_local_entry->common.flags |= TT_CLIENT_NOPURGE; + /* The local entry has to be marked as NEW to avoid to send it in + * a full table response going out before the next ttvn increment + * (consistency check) */ + tt_local_entry->common.flags |= TT_CLIENT_NEW; + hash_added = hash_add(bat_priv->tt_local_hash, compare_tt, choose_orig, &tt_local_entry->common, &tt_local_entry->common.hash_entry); @@ -230,11 +227,6 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr, tt_local_event(bat_priv, addr, tt_local_entry->common.flags); - /* The local entry has to be marked as NEW to avoid to send it in - * a full table response going out before the next ttvn increment - * (consistency check) */ - tt_local_entry->common.flags |= TT_CLIENT_NEW; - /* remove address from global hash if present */ tt_global_entry = tt_global_hash_find(bat_priv, addr); @@ -269,7 +261,7 @@ int tt_changes_fill_buffer(struct bat_priv *bat_priv, atomic_set(&bat_priv->tt_local_changes, 0); list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list, - list) { + list) { if (count < tot_changes) { memcpy(buff + tt_len(count), &entry->change, sizeof(struct tt_change)); @@ -341,17 +333,17 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) { seq_printf(seq, " * %pM [%c%c%c%c%c]\n", - tt_common_entry->addr, - (tt_common_entry->flags & - TT_CLIENT_ROAM ? 'R' : '.'), - (tt_common_entry->flags & - TT_CLIENT_NOPURGE ? 'P' : '.'), - (tt_common_entry->flags & - TT_CLIENT_NEW ? 'N' : '.'), - (tt_common_entry->flags & - TT_CLIENT_PENDING ? 'X' : '.'), - (tt_common_entry->flags & - TT_CLIENT_WIFI ? 'W' : '.')); + tt_common_entry->addr, + (tt_common_entry->flags & + TT_CLIENT_ROAM ? 'R' : '.'), + (tt_common_entry->flags & + TT_CLIENT_NOPURGE ? 'P' : '.'), + (tt_common_entry->flags & + TT_CLIENT_NEW ? 'N' : '.'), + (tt_common_entry->flags & + TT_CLIENT_PENDING ? 'X' : '.'), + (tt_common_entry->flags & + TT_CLIENT_WIFI ? 'W' : '.')); } rcu_read_unlock(); } @@ -363,7 +355,7 @@ out: static void tt_local_set_pending(struct bat_priv *bat_priv, struct tt_local_entry *tt_local_entry, - uint16_t flags) + uint16_t flags, const char *message) { tt_local_event(bat_priv, tt_local_entry->common.addr, tt_local_entry->common.flags | flags); @@ -372,6 +364,9 @@ static void tt_local_set_pending(struct bat_priv *bat_priv, * to be kept in the table in order to send it in a full table * response issued before the net ttvn increment (consistency check) */ tt_local_entry->common.flags |= TT_CLIENT_PENDING; + + bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) pending to be removed: " + "%s\n", tt_local_entry->common.addr, message); } void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr, @@ -384,10 +379,7 @@ void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr, goto out; tt_local_set_pending(bat_priv, tt_local_entry, TT_CLIENT_DEL | - (roaming ? TT_CLIENT_ROAM : NO_FLAGS)); - - bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) pending to be removed: " - "%s\n", tt_local_entry->common.addr, message); + (roaming ? TT_CLIENT_ROAM : NO_FLAGS), message); out: if (tt_local_entry) tt_local_entry_free_ref(tt_local_entry); @@ -420,15 +412,12 @@ static void tt_local_purge(struct bat_priv *bat_priv) if (tt_local_entry->common.flags & TT_CLIENT_PENDING) continue; - if (!is_out_of_time(tt_local_entry->last_seen, - TT_LOCAL_TIMEOUT * 1000)) + if (!has_timed_out(tt_local_entry->last_seen, + TT_LOCAL_TIMEOUT)) continue; tt_local_set_pending(bat_priv, tt_local_entry, - TT_CLIENT_DEL); - bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) " - "pending to be removed: timed out\n", - tt_local_entry->common.addr); + TT_CLIENT_DEL, "timed out"); } spin_unlock_bh(list_lock); } @@ -614,7 +603,7 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) struct tt_global_entry, common); seq_printf(seq, " * %pM (%3u) via %pM (%3u) " - "[%c%c%c]\n", + "[%c%c]\n", tt_global_entry->common.addr, tt_global_entry->ttvn, tt_global_entry->orig_node->orig, @@ -624,8 +613,6 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) (tt_global_entry->common.flags & TT_CLIENT_ROAM ? 'R' : '.'), (tt_global_entry->common.flags & - TT_CLIENT_PENDING ? 'X' : '.'), - (tt_global_entry->common.flags & TT_CLIENT_WIFI ? 'W' : '.')); } rcu_read_unlock(); @@ -665,29 +652,31 @@ void tt_global_del(struct bat_priv *bat_priv, struct tt_local_entry *tt_local_entry = NULL; tt_global_entry = tt_global_hash_find(bat_priv, addr); - if (!tt_global_entry) + if (!tt_global_entry || tt_global_entry->orig_node != orig_node) goto out; - if (tt_global_entry->orig_node == orig_node) { - if (roaming) { - /* if we are deleting a global entry due to a roam - * event, there are two possibilities: - * 1) the client roamed from node A to node B => we mark - * it with TT_CLIENT_ROAM, we start a timer and we - * wait for node B to claim it. In case of timeout - * the entry is purged. - * 2) the client roamed to us => we can directly delete - * the global entry, since it is useless now. */ - tt_local_entry = tt_local_hash_find(bat_priv, - tt_global_entry->common.addr); - if (!tt_local_entry) { - tt_global_entry->common.flags |= TT_CLIENT_ROAM; - tt_global_entry->roam_at = jiffies; - goto out; - } - } - _tt_global_del(bat_priv, tt_global_entry, message); + if (!roaming) + goto out_del; + + /* if we are deleting a global entry due to a roam + * event, there are two possibilities: + * 1) the client roamed from node A to node B => we mark + * it with TT_CLIENT_ROAM, we start a timer and we + * wait for node B to claim it. In case of timeout + * the entry is purged. + * 2) the client roamed to us => we can directly delete + * the global entry, since it is useless now. */ + tt_local_entry = tt_local_hash_find(bat_priv, + tt_global_entry->common.addr); + if (!tt_local_entry) { + tt_global_entry->common.flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + goto out; } + +out_del: + _tt_global_del(bat_priv, tt_global_entry, message); + out: if (tt_global_entry) tt_global_entry_free_ref(tt_global_entry); @@ -715,7 +704,7 @@ void tt_global_del_orig(struct bat_priv *bat_priv, spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_common_entry, node, safe, - head, hash_entry) { + head, hash_entry) { tt_global_entry = container_of(tt_common_entry, struct tt_global_entry, common); @@ -733,6 +722,7 @@ void tt_global_del_orig(struct bat_priv *bat_priv, spin_unlock_bh(list_lock); } atomic_set(&orig_node->tt_size, 0); + orig_node->tt_initialised = false; } static void tt_global_roam_purge(struct bat_priv *bat_priv) @@ -757,8 +747,8 @@ static void tt_global_roam_purge(struct bat_priv *bat_priv) common); if (!(tt_global_entry->common.flags & TT_CLIENT_ROAM)) continue; - if (!is_out_of_time(tt_global_entry->roam_at, - TT_CLIENT_ROAM_TIMEOUT * 1000)) + if (!has_timed_out(tt_global_entry->roam_at, + TT_CLIENT_ROAM_TIMEOUT)) continue; bat_dbg(DBG_TT, bat_priv, "Deleting global " @@ -846,11 +836,6 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv, if (!atomic_inc_not_zero(&tt_global_entry->orig_node->refcount)) goto out; - /* A global client marked as PENDING has already moved from that - * originator */ - if (tt_global_entry->common.flags & TT_CLIENT_PENDING) - goto out; - orig_node = tt_global_entry->orig_node; out: @@ -977,8 +962,7 @@ static void tt_req_purge(struct bat_priv *bat_priv) spin_lock_bh(&bat_priv->tt_req_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { - if (is_out_of_time(node->issued_at, - TT_REQUEST_TIMEOUT * 1000)) { + if (has_timed_out(node->issued_at, TT_REQUEST_TIMEOUT)) { list_del(&node->list); kfree(node); } @@ -996,8 +980,8 @@ static struct tt_req_node *new_tt_req_node(struct bat_priv *bat_priv, spin_lock_bh(&bat_priv->tt_req_list_lock); list_for_each_entry(tt_req_node_tmp, &bat_priv->tt_req_list, list) { if (compare_eth(tt_req_node_tmp, orig_node) && - !is_out_of_time(tt_req_node_tmp->issued_at, - TT_REQUEST_TIMEOUT * 1000)) + !has_timed_out(tt_req_node_tmp->issued_at, + TT_REQUEST_TIMEOUT)) goto unlock; } @@ -1134,11 +1118,11 @@ static int send_tt_request(struct bat_priv *bat_priv, tt_request = (struct tt_query_packet *)skb_put(skb, sizeof(struct tt_query_packet)); - tt_request->packet_type = BAT_TT_QUERY; - tt_request->version = COMPAT_VERSION; + tt_request->header.packet_type = BAT_TT_QUERY; + tt_request->header.version = COMPAT_VERSION; memcpy(tt_request->src, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(tt_request->dst, dst_orig_node->orig, ETH_ALEN); - tt_request->ttl = TTL; + tt_request->header.ttl = TTL; tt_request->ttvn = ttvn; tt_request->tt_data = tt_crc; tt_request->flags = TT_REQUEST; @@ -1264,9 +1248,9 @@ static bool send_other_tt_response(struct bat_priv *bat_priv, tt_response = (struct tt_query_packet *)skb->data; } - tt_response->packet_type = BAT_TT_QUERY; - tt_response->version = COMPAT_VERSION; - tt_response->ttl = TTL; + tt_response->header.packet_type = BAT_TT_QUERY; + tt_response->header.version = COMPAT_VERSION; + tt_response->header.ttl = TTL; memcpy(tt_response->src, req_dst_orig_node->orig, ETH_ALEN); memcpy(tt_response->dst, tt_request->src, ETH_ALEN); tt_response->flags = TT_RESPONSE; @@ -1381,9 +1365,9 @@ static bool send_my_tt_response(struct bat_priv *bat_priv, tt_response = (struct tt_query_packet *)skb->data; } - tt_response->packet_type = BAT_TT_QUERY; - tt_response->version = COMPAT_VERSION; - tt_response->ttl = TTL; + tt_response->header.packet_type = BAT_TT_QUERY; + tt_response->header.version = COMPAT_VERSION; + tt_response->header.ttl = TTL; memcpy(tt_response->src, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(tt_response->dst, tt_request->src, ETH_ALEN); tt_response->flags = TT_RESPONSE; @@ -1450,6 +1434,7 @@ static void _tt_update_changes(struct bat_priv *bat_priv, */ return; } + orig_node->tt_initialised = true; } static void tt_fill_gtable(struct bat_priv *bat_priv, @@ -1589,8 +1574,7 @@ static void tt_roam_purge(struct bat_priv *bat_priv) spin_lock_bh(&bat_priv->tt_roam_list_lock); list_for_each_entry_safe(node, safe, &bat_priv->tt_roam_list, list) { - if (!is_out_of_time(node->first_time, - ROAMING_MAX_TIME * 1000)) + if (!has_timed_out(node->first_time, ROAMING_MAX_TIME)) continue; list_del(&node->list); @@ -1617,8 +1601,7 @@ static bool tt_check_roam_count(struct bat_priv *bat_priv, if (!compare_eth(tt_roam_node->addr, client)) continue; - if (is_out_of_time(tt_roam_node->first_time, - ROAMING_MAX_TIME * 1000)) + if (has_timed_out(tt_roam_node->first_time, ROAMING_MAX_TIME)) continue; if (!atomic_dec_not_zero(&tt_roam_node->counter)) @@ -1669,9 +1652,9 @@ void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, roam_adv_packet = (struct roam_adv_packet *)skb_put(skb, sizeof(struct roam_adv_packet)); - roam_adv_packet->packet_type = BAT_ROAM_ADV; - roam_adv_packet->version = COMPAT_VERSION; - roam_adv_packet->ttl = TTL; + roam_adv_packet->header.packet_type = BAT_ROAM_ADV; + roam_adv_packet->header.version = COMPAT_VERSION; + roam_adv_packet->header.ttl = TTL; primary_if = primary_if_get_selected(bat_priv); if (!primary_if) goto out; @@ -1854,8 +1837,10 @@ void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); bool full_table = true; - /* the ttvn increased by one -> we can apply the attached changes */ - if (ttvn - orig_ttvn == 1) { + /* orig table not initialised AND first diff is in the OGM OR the ttvn + * increased by one -> we can apply the attached changes */ + if ((!orig_node->tt_initialised && ttvn == 1) || + ttvn - orig_ttvn == 1) { /* the OGM could not contain the changes due to their size or * because they have already been sent TT_OGM_APPEND_MAX times. * In this case send a tt request */ @@ -1889,7 +1874,8 @@ void tt_update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, } else { /* if we missed more than one change or our tables are not * in sync anymore -> request fresh tt data */ - if (ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { + if (!orig_node->tt_initialised || ttvn != orig_ttvn || + orig_node->tt_crc != tt_crc) { request_table: bat_dbg(DBG_TT, bat_priv, "TT inconsistency for %pM. " "Need to retrieve the correct information " diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 30efd49..c753633 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index e9eb043..302efb5 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2007-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2007-2012 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -81,6 +81,7 @@ struct orig_node { int16_t tt_buff_len; spinlock_t tt_buff_lock; /* protects tt_buff */ atomic_t tt_size; + bool tt_initialised; /* The tt_poss_change flag is used to detect an ongoing roaming phase. * If true, then I sent a Roaming_adv to this orig_node and I have to * inspect every packet directed to it to check whether it is still @@ -205,6 +206,7 @@ struct bat_priv { atomic_t gw_reselect; struct hard_iface __rcu *primary_if; /* rcu protected pointer */ struct vis_info *my_vis_info; + struct bat_algo_ops *bat_algo_ops; }; struct socket_client { @@ -343,4 +345,23 @@ struct softif_neigh { struct rcu_head rcu; }; +struct bat_algo_ops { + struct hlist_node list; + char *name; + /* init OGM when hard-interface is enabled */ + void (*bat_ogm_init)(struct hard_iface *hard_iface); + /* init primary OGM when primary interface is selected */ + void (*bat_ogm_init_primary)(struct hard_iface *hard_iface); + /* init mac addresses of the OGM belonging to this hard-interface */ + void (*bat_ogm_update_mac)(struct hard_iface *hard_iface); + /* prepare a new outgoing OGM for the send queue */ + void (*bat_ogm_schedule)(struct hard_iface *hard_iface, + int tt_num_changes); + /* send scheduled OGM */ + void (*bat_ogm_emit)(struct forw_packet *forw_packet); + /* receive incoming OGM */ + void (*bat_ogm_receive)(struct hard_iface *if_incoming, + struct sk_buff *skb); +}; + #endif /* _NET_BATMAN_ADV_TYPES_H_ */ diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 07d1c1d..0897dfa 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Andreas Langer * @@ -67,7 +67,7 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, memmove(skb->data + uni_diff, skb->data, hdr_len); unicast_packet = (struct unicast_packet *) skb_pull(skb, uni_diff); - unicast_packet->packet_type = BAT_UNICAST; + unicast_packet->header.packet_type = BAT_UNICAST; return skb; @@ -251,9 +251,9 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, memcpy(frag1, &tmp_uc, sizeof(tmp_uc)); - frag1->ttl--; - frag1->version = COMPAT_VERSION; - frag1->packet_type = BAT_UNICAST_FRAG; + frag1->header.ttl--; + frag1->header.version = COMPAT_VERSION; + frag1->header.packet_type = BAT_UNICAST_FRAG; memcpy(frag1->orig, primary_if->net_dev->dev_addr, ETH_ALEN); memcpy(frag2, frag1, sizeof(*frag2)); @@ -320,11 +320,11 @@ find_router: unicast_packet = (struct unicast_packet *)skb->data; - unicast_packet->version = COMPAT_VERSION; + unicast_packet->header.version = COMPAT_VERSION; /* batman packet type: unicast */ - unicast_packet->packet_type = BAT_UNICAST; + unicast_packet->header.packet_type = BAT_UNICAST; /* set unicast ttl */ - unicast_packet->ttl = TTL; + unicast_packet->header.ttl = TTL; /* copy the destination for faster routing */ memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); /* set the destination tt version number */ @@ -335,7 +335,7 @@ find_router: data_len + sizeof(*unicast_packet) > neigh_node->if_incoming->net_dev->mtu) { /* send frag skb decreases ttl */ - unicast_packet->ttl++; + unicast_packet->header.ttl++; ret = frag_send_skb(skb, bat_priv, neigh_node->if_incoming, neigh_node->addr); goto out; diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 8fd5535..a9faf6b 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2010-2012 B.A.T.M.A.N. contributors: * * Andreas Langer * diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index cc3b9f2..c4a5b8c 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich * @@ -617,7 +617,7 @@ static int generate_vis_packet(struct bat_priv *bat_priv) packet->vis_type = atomic_read(&bat_priv->vis_mode); memcpy(packet->target_orig, broadcast_addr, ETH_ALEN); - packet->ttl = TTL; + packet->header.ttl = TTL; packet->seqno = htonl(ntohl(packet->seqno) + 1); packet->entries = 0; skb_trim(info->skb_packet, sizeof(*packet)); @@ -714,8 +714,7 @@ static void purge_vis_packets(struct bat_priv *bat_priv) if (info == bat_priv->my_vis_info) continue; - if (time_after(jiffies, - info->first_seen + VIS_TIMEOUT * HZ)) { + if (has_timed_out(info->first_seen, VIS_TIMEOUT)) { hlist_del(node); send_list_del(info); kref_put(&info->refcount, free_info); @@ -818,19 +817,19 @@ static void send_vis_packet(struct bat_priv *bat_priv, struct vis_info *info) goto out; packet = (struct vis_packet *)info->skb_packet->data; - if (packet->ttl < 2) { + if (packet->header.ttl < 2) { pr_debug("Error - can't send vis packet: ttl exceeded\n"); goto out; } memcpy(packet->sender_orig, primary_if->net_dev->dev_addr, ETH_ALEN); - packet->ttl--; + packet->header.ttl--; if (is_broadcast_ether_addr(packet->target_orig)) broadcast_vis_packet(bat_priv, info); else unicast_vis_packet(bat_priv, info); - packet->ttl++; /* restore TTL */ + packet->header.ttl++; /* restore TTL */ out: if (primary_if) @@ -910,9 +909,9 @@ int vis_init(struct bat_priv *bat_priv) INIT_LIST_HEAD(&bat_priv->my_vis_info->send_list); kref_init(&bat_priv->my_vis_info->refcount); bat_priv->my_vis_info->bat_priv = bat_priv; - packet->version = COMPAT_VERSION; - packet->packet_type = BAT_VIS; - packet->ttl = TTL; + packet->header.version = COMPAT_VERSION; + packet->header.packet_type = BAT_VIS; + packet->header.ttl = TTL; packet->seqno = 0; packet->entries = 0; diff --git a/net/batman-adv/vis.h b/net/batman-adv/vis.h index 31b820d..ee2e46e 100644 --- a/net/batman-adv/vis.h +++ b/net/batman-adv/vis.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2008-2011 B.A.T.M.A.N. contributors: + * Copyright (C) 2008-2012 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * @@ -22,7 +22,8 @@ #ifndef _NET_BATMAN_ADV_VIS_H_ #define _NET_BATMAN_ADV_VIS_H_ -#define VIS_TIMEOUT 200 /* timeout of vis packets in seconds */ +#define VIS_TIMEOUT 200000 /* timeout of vis packets + * in miliseconds */ int vis_seq_print_text(struct seq_file *seq, void *offset); void receive_server_sync_packet(struct bat_priv *bat_priv, diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 71773b0..ba829de 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -167,10 +167,11 @@ static int br_set_mac_address(struct net_device *dev, void *p) struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) - return -EINVAL; + return -EADDRNOTAVAIL; spin_lock_bh(&br->lock); if (compare_ether_addr(dev->dev_addr, addr->sa_data)) { + dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); br_fdb_change_mac_address(br, addr->sa_data); br_stp_change_bridge_id(br, addr->sa_data); @@ -334,7 +335,7 @@ void br_dev_setup(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); ether_setup(dev); dev->netdev_ops = &br_netdev_ops; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5864cc4..8aa4ad0 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1893,10 +1893,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, switch (compat_mwt) { case EBT_COMPAT_MATCH: - match = try_then_request_module(xt_find_match(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (match == NULL) - return -ENOENT; + match = xt_request_find_match(NFPROTO_BRIDGE, name, 0); if (IS_ERR(match)) return PTR_ERR(match); @@ -1915,10 +1912,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, break; case EBT_COMPAT_WATCHER: /* fallthrough */ case EBT_COMPAT_TARGET: - wt = try_then_request_module(xt_find_target(NFPROTO_BRIDGE, - name, 0), "ebt_%s", name); - if (wt == NULL) - return -ENOENT; + wt = xt_request_find_target(NFPROTO_BRIDGE, name, 0); if (IS_ERR(wt)) return PTR_ERR(wt); off = xt_compat_target_offset(wt); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 82c5706..aa6f716 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -162,7 +162,6 @@ void caif_flow_cb(struct sk_buff *skb) static int transmit(struct cflayer *layer, struct cfpkt *pkt) { int err, high = 0, qlen = 0; - struct caif_dev_common *caifdev; struct caif_device_entry *caifd = container_of(layer, struct caif_device_entry, layer); struct sk_buff *skb; @@ -174,7 +173,6 @@ static int transmit(struct cflayer *layer, struct cfpkt *pkt) skb->dev = caifd->netdev; skb_reset_network_header(skb); skb->protocol = htons(ETH_P_CAIF); - caifdev = netdev_priv(caifd->netdev); /* Check if we need to handle xoff */ if (likely(caifd->netdev->tx_queue_len == 0)) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index a986280..5016fa5 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -43,34 +43,9 @@ enum caif_states { #define TX_FLOW_ON_BIT 1 #define RX_FLOW_ON_BIT 2 -static struct dentry *debugfsdir; - -#ifdef CONFIG_DEBUG_FS -struct debug_fs_counter { - atomic_t caif_nr_socks; - atomic_t caif_sock_create; - atomic_t num_connect_req; - atomic_t num_connect_resp; - atomic_t num_connect_fail_resp; - atomic_t num_disconnect; - atomic_t num_remote_shutdown_ind; - atomic_t num_tx_flow_off_ind; - atomic_t num_tx_flow_on_ind; - atomic_t num_rx_flow_off; - atomic_t num_rx_flow_on; -}; -static struct debug_fs_counter cnt; -#define dbfs_atomic_inc(v) atomic_inc_return(v) -#define dbfs_atomic_dec(v) atomic_dec_return(v) -#else -#define dbfs_atomic_inc(v) 0 -#define dbfs_atomic_dec(v) 0 -#endif - struct caifsock { struct sock sk; /* must be first member */ struct cflayer layer; - char name[CAIF_LAYER_NAME_SZ]; /* Used for debugging */ u32 flow_state; struct caif_connect_request conn_req; struct mutex readlock; @@ -161,7 +136,6 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) atomic_read(&cf_sk->sk.sk_rmem_alloc), sk_rcvbuf_lowwater(cf_sk)); set_rx_flow_off(cf_sk); - dbfs_atomic_inc(&cnt.num_rx_flow_off); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } @@ -172,7 +146,6 @@ static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) set_rx_flow_off(cf_sk); if (net_ratelimit()) pr_debug("sending flow OFF due to rmem_schedule\n"); - dbfs_atomic_inc(&cnt.num_rx_flow_off); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ); } skb->dev = NULL; @@ -233,14 +206,12 @@ static void caif_ctrl_cb(struct cflayer *layr, switch (flow) { case CAIF_CTRLCMD_FLOW_ON_IND: /* OK from modem to start sending again */ - dbfs_atomic_inc(&cnt.num_tx_flow_on_ind); set_tx_flow_on(cf_sk); cf_sk->sk.sk_state_change(&cf_sk->sk); break; case CAIF_CTRLCMD_FLOW_OFF_IND: /* Modem asks us to shut up */ - dbfs_atomic_inc(&cnt.num_tx_flow_off_ind); set_tx_flow_off(cf_sk); cf_sk->sk.sk_state_change(&cf_sk->sk); break; @@ -249,7 +220,6 @@ static void caif_ctrl_cb(struct cflayer *layr, /* We're now connected */ caif_client_register_refcnt(&cf_sk->layer, cfsk_hold, cfsk_put); - dbfs_atomic_inc(&cnt.num_connect_resp); cf_sk->sk.sk_state = CAIF_CONNECTED; set_tx_flow_on(cf_sk); cf_sk->sk.sk_state_change(&cf_sk->sk); @@ -263,7 +233,6 @@ static void caif_ctrl_cb(struct cflayer *layr, case CAIF_CTRLCMD_INIT_FAIL_RSP: /* Connect request failed */ - dbfs_atomic_inc(&cnt.num_connect_fail_resp); cf_sk->sk.sk_err = ECONNREFUSED; cf_sk->sk.sk_state = CAIF_DISCONNECTED; cf_sk->sk.sk_shutdown = SHUTDOWN_MASK; @@ -277,7 +246,6 @@ static void caif_ctrl_cb(struct cflayer *layr, case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND: /* Modem has closed this connection, or device is down. */ - dbfs_atomic_inc(&cnt.num_remote_shutdown_ind); cf_sk->sk.sk_shutdown = SHUTDOWN_MASK; cf_sk->sk.sk_err = ECONNRESET; set_rx_flow_on(cf_sk); @@ -297,7 +265,6 @@ static void caif_check_flow_release(struct sock *sk) return; if (atomic_read(&sk->sk_rmem_alloc) <= sk_rcvbuf_lowwater(cf_sk)) { - dbfs_atomic_inc(&cnt.num_rx_flow_on); set_rx_flow_on(cf_sk); caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_ON_REQ); } @@ -539,8 +506,10 @@ static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk, pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb); memset(skb->cb, 0, sizeof(struct caif_payload_info)); - if (cf_sk->layer.dn == NULL) + if (cf_sk->layer.dn == NULL) { + kfree_skb(skb); return -EINVAL; + } return cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt); } @@ -683,10 +652,10 @@ static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, } err = transmit_skb(skb, cf_sk, msg->msg_flags&MSG_DONTWAIT, timeo); - if (err < 0) { - kfree_skb(skb); + if (err < 0) + /* skb is already freed */ goto pipe_err; - } + sent += size; } @@ -854,7 +823,6 @@ static int caif_connect(struct socket *sock, struct sockaddr *uaddr, /*ifindex = id of the interface.*/ cf_sk->conn_req.ifindex = cf_sk->sk.sk_bound_dev_if; - dbfs_atomic_inc(&cnt.num_connect_req); cf_sk->layer.receive = caif_sktrecv_cb; err = caif_connect_client(sock_net(sk), &cf_sk->conn_req, @@ -943,8 +911,6 @@ static int caif_release(struct socket *sock) spin_unlock_bh(&sk->sk_receive_queue.lock); sock->sk = NULL; - dbfs_atomic_inc(&cnt.num_disconnect); - WARN_ON(IS_ERR(cf_sk->debugfs_socket_dir)); if (cf_sk->debugfs_socket_dir != NULL) debugfs_remove_recursive(cf_sk->debugfs_socket_dir); @@ -1052,14 +1018,12 @@ static void caif_sock_destructor(struct sock *sk) return; } sk_stream_kill_queues(&cf_sk->sk); - dbfs_atomic_dec(&cnt.caif_nr_socks); caif_free_client(&cf_sk->layer); } static int caif_create(struct net *net, struct socket *sock, int protocol, int kern) { - int num; struct sock *sk = NULL; struct caifsock *cf_sk = NULL; static struct proto prot = {.name = "PF_CAIF", @@ -1120,34 +1084,6 @@ static int caif_create(struct net *net, struct socket *sock, int protocol, cf_sk->sk.sk_priority = CAIF_PRIO_NORMAL; cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY; cf_sk->conn_req.protocol = protocol; - /* Increase the number of sockets created. */ - dbfs_atomic_inc(&cnt.caif_nr_socks); - num = dbfs_atomic_inc(&cnt.caif_sock_create); -#ifdef CONFIG_DEBUG_FS - if (!IS_ERR(debugfsdir)) { - - /* Fill in some information concerning the misc socket. */ - snprintf(cf_sk->name, sizeof(cf_sk->name), "cfsk%d", num); - - cf_sk->debugfs_socket_dir = - debugfs_create_dir(cf_sk->name, debugfsdir); - - debugfs_create_u32("sk_state", S_IRUSR | S_IWUSR, - cf_sk->debugfs_socket_dir, - (u32 *) &cf_sk->sk.sk_state); - debugfs_create_u32("flow_state", S_IRUSR | S_IWUSR, - cf_sk->debugfs_socket_dir, &cf_sk->flow_state); - debugfs_create_u32("sk_rmem_alloc", S_IRUSR | S_IWUSR, - cf_sk->debugfs_socket_dir, - (u32 *) &cf_sk->sk.sk_rmem_alloc); - debugfs_create_u32("sk_wmem_alloc", S_IRUSR | S_IWUSR, - cf_sk->debugfs_socket_dir, - (u32 *) &cf_sk->sk.sk_wmem_alloc); - debugfs_create_u32("identity", S_IRUSR | S_IWUSR, - cf_sk->debugfs_socket_dir, - (u32 *) &cf_sk->layer.id); - } -#endif release_sock(&cf_sk->sk); return 0; } @@ -1159,7 +1095,7 @@ static struct net_proto_family caif_family_ops = { .owner = THIS_MODULE, }; -static int af_caif_init(void) +static int __init caif_sktinit_module(void) { int err = sock_register(&caif_family_ops); if (!err) @@ -1167,54 +1103,9 @@ static int af_caif_init(void) return 0; } -static int __init caif_sktinit_module(void) -{ -#ifdef CONFIG_DEBUG_FS - debugfsdir = debugfs_create_dir("caif_sk", NULL); - if (!IS_ERR(debugfsdir)) { - debugfs_create_u32("num_sockets", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.caif_nr_socks); - debugfs_create_u32("num_create", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.caif_sock_create); - debugfs_create_u32("num_connect_req", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_connect_req); - debugfs_create_u32("num_connect_resp", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_connect_resp); - debugfs_create_u32("num_connect_fail_resp", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_connect_fail_resp); - debugfs_create_u32("num_disconnect", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_disconnect); - debugfs_create_u32("num_remote_shutdown_ind", - S_IRUSR | S_IWUSR, debugfsdir, - (u32 *) &cnt.num_remote_shutdown_ind); - debugfs_create_u32("num_tx_flow_off_ind", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_tx_flow_off_ind); - debugfs_create_u32("num_tx_flow_on_ind", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_tx_flow_on_ind); - debugfs_create_u32("num_rx_flow_off", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_rx_flow_off); - debugfs_create_u32("num_rx_flow_on", S_IRUSR | S_IWUSR, - debugfsdir, - (u32 *) &cnt.num_rx_flow_on); - } -#endif - return af_caif_init(); -} - static void __exit caif_sktexit_module(void) { sock_unregister(PF_CAIF); - if (debugfsdir != NULL) - debugfs_remove_recursive(debugfsdir); } module_init(caif_sktinit_module); module_exit(caif_sktexit_module); diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index b36f24a..94b0861 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -248,7 +248,6 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, { struct cfmuxl *muxl = container_obj(layr); struct cflayer *layer; - int idx; rcu_read_lock(); list_for_each_entry_rcu(layer, &muxl->srvl_list, node) { @@ -257,14 +256,9 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && - layer->id != 0) { - - idx = layer->id % UP_CACHE_SIZE; - spin_lock_bh(&muxl->receive_lock); - RCU_INIT_POINTER(muxl->up_cache[idx], NULL); - list_del_rcu(&layer->node); - spin_unlock_bh(&muxl->receive_lock); - } + layer->id != 0) + cfmuxl_remove_uplayer(layr, layer->id); + /* NOTE: ctrlcmd is not allowed to block */ layer->ctrlcmd(layer, ctrl, phyid); } diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index 8656909..e866234 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -72,14 +72,12 @@ static void robust_list_del(struct list_head *delete_node) static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) { struct sk_buff *skb; - struct chnl_net *priv = container_of(layr, struct chnl_net, chnl); + struct chnl_net *priv; int pktlen; - int err = 0; const u8 *ip_version; u8 buf; priv = container_of(layr, struct chnl_net, chnl); - if (!priv) return -EINVAL; @@ -95,8 +93,7 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) /* check the version of IP */ ip_version = skb_header_pointer(skb, 0, 1, &buf); - if (!ip_version) - return -EINVAL; + switch (*ip_version >> 4) { case 4: skb->protocol = htons(ETH_P_IP); @@ -105,6 +102,7 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) skb->protocol = htons(ETH_P_IPV6); break; default: + priv->netdev->stats.rx_errors++; return -EINVAL; } @@ -123,7 +121,7 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt) priv->netdev->stats.rx_packets++; priv->netdev->stats.rx_bytes += pktlen; - return err; + return 0; } static int delete_device(struct chnl_net *dev) @@ -221,11 +219,13 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->len > priv->netdev->mtu) { pr_warn("Size of skb exceeded MTU\n"); + dev->stats.tx_errors++; return -ENOSPC; } if (!priv->flowenabled) { pr_debug("dropping packets flow off\n"); + dev->stats.tx_dropped++; return NETDEV_TX_BUSY; } @@ -240,8 +240,7 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Send the packet down the stack. */ result = priv->chnl.dn->transmit(priv->chnl.dn, pkt); if (result) { - if (result == -EAGAIN) - result = NETDEV_TX_BUSY; + dev->stats.tx_dropped++; return result; } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97f70e5..761ad9d 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -85,8 +85,6 @@ int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid) } else { pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid); memcpy(&client->fsid, fsid, sizeof(*fsid)); - ceph_debugfs_client_init(client); - client->have_fsid = true; } return 0; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index 0b62dea..1845cde 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -8,8 +8,8 @@ #include <linux/ceph/mon_client.h> #include <linux/ceph/libceph.h> +#include <linux/ceph/debugfs.h> #include <linux/ceph/decode.h> - #include <linux/ceph/auth.h> /* @@ -340,8 +340,19 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc, client->monc.monmap = monmap; kfree(old); + if (!client->have_fsid) { + client->have_fsid = true; + mutex_unlock(&monc->mutex); + /* + * do debugfs initialization without mutex to avoid + * creating a locking dependency + */ + ceph_debugfs_client_init(client); + goto out_unlocked; + } out: mutex_unlock(&monc->mutex); +out_unlocked: wake_up_all(&client->auth_wq); } diff --git a/net/core/datagram.c b/net/core/datagram.c index 68bbf9f..d3cf12f 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -132,6 +132,8 @@ out_noerr: * __skb_recv_datagram - Receive a datagram skbuff * @sk: socket * @flags: MSG_ flags + * @off: an offset in bytes to peek skb from. Returns an offset + * within an skb where data actually starts * @peeked: returns non-zero if this packet has been seen before * @err: error code returned * @@ -158,7 +160,7 @@ out_noerr: * the standard around please. */ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, - int *peeked, int *err) + int *peeked, int *off, int *err) { struct sk_buff *skb; long timeo; @@ -180,21 +182,25 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, * However, this function was correct in any case. 8) */ unsigned long cpu_flags; + struct sk_buff_head *queue = &sk->sk_receive_queue; - spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags); - skb = skb_peek(&sk->sk_receive_queue); - if (skb) { + spin_lock_irqsave(&queue->lock, cpu_flags); + skb_queue_walk(queue, skb) { *peeked = skb->peeked; if (flags & MSG_PEEK) { + if (*off >= skb->len) { + *off -= skb->len; + continue; + } skb->peeked = 1; atomic_inc(&skb->users); } else - __skb_unlink(skb, &sk->sk_receive_queue); - } - spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags); + __skb_unlink(skb, queue); - if (skb) + spin_unlock_irqrestore(&queue->lock, cpu_flags); return skb; + } + spin_unlock_irqrestore(&queue->lock, cpu_flags); /* User doesn't want to wait */ error = -EAGAIN; @@ -214,10 +220,10 @@ EXPORT_SYMBOL(__skb_recv_datagram); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err) { - int peeked; + int peeked, off = 0; return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, err); + &peeked, &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index 115dee1..763a0ed 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -446,7 +446,7 @@ void __dev_remove_pack(struct packet_type *pt) } } - printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); + pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } @@ -1039,8 +1039,7 @@ rollback: memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; } else { - printk(KERN_ERR - "%s: name change rollback failed: %d.\n", + pr_err("%s: name change rollback failed: %d\n", dev->name, ret); } } @@ -1139,9 +1138,8 @@ void dev_load(struct net *net, const char *name) no_module = request_module("netdev-%s", name); if (no_module && capable(CAP_SYS_MODULE)) { if (!request_module("%s", name)) - pr_err("Loading kernel module for a network device " -"with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s " -"instead\n", name); + pr_err("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); } } EXPORT_SYMBOL(dev_load); @@ -1655,10 +1653,9 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if (skb_network_header(skb2) < skb2->data || skb2->network_header > skb2->tail) { if (net_ratelimit()) - printk(KERN_CRIT "protocol %04x is " - "buggy, dev %s\n", - ntohs(skb2->protocol), - dev->name); + pr_crit("protocol %04x is buggy, dev %s\n", + ntohs(skb2->protocol), + dev->name); skb_reset_network_header(skb2); } @@ -1691,9 +1688,7 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { - pr_warning("Number of in use tx queues changed " - "invalidating tc mappings. Priority " - "traffic classification disabled!\n"); + pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } @@ -1704,11 +1699,8 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq) tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { - pr_warning("Number of in use tx queues " - "changed. Priority %i to tc " - "mapping %i is no longer valid " - "setting map to 0\n", - i, q); + pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", + i, q); netdev_set_prio_tc_map(dev, i, 0); } } @@ -2014,8 +2006,7 @@ EXPORT_SYMBOL(skb_gso_segment); void netdev_rx_csum_fault(struct net_device *dev) { if (net_ratelimit()) { - printk(KERN_ERR "%s: hw csum failure.\n", - dev ? dev->name : "<unknown>"); + pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); dump_stack(); } } @@ -2332,9 +2323,9 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { if (net_ratelimit()) { - pr_warning("%s selects TX queue %d, but " - "real number of TX queues is %d\n", - dev->name, queue_index, dev->real_num_tx_queues); + pr_warn("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); } return 0; } @@ -2578,16 +2569,16 @@ int dev_queue_xmit(struct sk_buff *skb) } HARD_TX_UNLOCK(dev, txq); if (net_ratelimit()) - printk(KERN_CRIT "Virtual device %s asks to " - "queue packet!\n", dev->name); + pr_crit("Virtual device %s asks to queue packet!\n", + dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: if (net_ratelimit()) - printk(KERN_CRIT "Dead loop on virtual device " - "%s, fix it urgently!\n", dev->name); + pr_crit("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); } } @@ -3069,8 +3060,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) if (unlikely(MAX_RED_LOOP < ttl++)) { if (net_ratelimit()) - pr_warning( "Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); + pr_warn("Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } @@ -3500,14 +3491,20 @@ static inline gro_result_t __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; for (p = napi->gro_list; p; p = p->next) { unsigned long diffs; diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; - diffs |= compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_gro_mac_header(skb), + maclen); NAPI_GRO_CB(p)->same_flow = !diffs; NAPI_GRO_CB(p)->flush = 0; } @@ -4491,16 +4488,15 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; - printk(KERN_WARNING "%s: promiscuity touches roof, " - "set promiscuity failed, promiscuity feature " - "of device might be broken.\n", dev->name); + pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } if (dev->flags != old_flags) { - printk(KERN_INFO "device %s %s promiscuous mode\n", - dev->name, (dev->flags & IFF_PROMISC) ? "entered" : - "left"); + pr_info("device %s %s promiscuous mode\n", + dev->name, + dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(current->audit_context, GFP_ATOMIC, @@ -4573,9 +4569,8 @@ int dev_set_allmulti(struct net_device *dev, int inc) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; - printk(KERN_WARNING "%s: allmulti touches roof, " - "set allmulti failed, allmulti feature of " - "device might be broken.\n", dev->name); + pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } @@ -5232,8 +5227,8 @@ static void rollback_registered_many(struct list_head *head) * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { - pr_debug("unregister_netdevice: device %s/%p never " - "was registered\n", dev->name, dev); + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); @@ -5465,7 +5460,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); if (!rx) { - pr_err("netdev: Unable to allocate %u rx queues.\n", count); + pr_err("netdev: Unable to allocate %u rx queues\n", count); return -ENOMEM; } dev->_rx = rx; @@ -5499,8 +5494,7 @@ static int netif_alloc_netdev_queues(struct net_device *dev) tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); if (!tx) { - pr_err("netdev: Unable to allocate %u tx queues.\n", - count); + pr_err("netdev: Unable to allocate %u tx queues\n", count); return -ENOMEM; } dev->_tx = tx; @@ -5759,10 +5753,8 @@ static void netdev_wait_allrefs(struct net_device *dev) refcnt = netdev_refcnt_read(dev); if (time_after(jiffies, warning_time + 10 * HZ)) { - printk(KERN_EMERG "unregister_netdevice: " - "waiting for %s to become free. Usage " - "count = %d\n", - dev->name, refcnt); + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, refcnt); warning_time = jiffies; } } @@ -5813,7 +5805,7 @@ void netdev_run_todo(void) list_del(&dev->todo_list); if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - printk(KERN_ERR "network todo '%s' but state %d\n", + pr_err("network todo '%s' but state %d\n", dev->name, dev->reg_state); dump_stack(); continue; @@ -5929,15 +5921,13 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { - pr_err("alloc_netdev: Unable to allocate device " - "with zero queues.\n"); + pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } #ifdef CONFIG_RPS if (rxqs < 1) { - pr_err("alloc_netdev: Unable to allocate device " - "with zero RX queues.\n"); + pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } #endif @@ -5953,7 +5943,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { - printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); + pr_err("alloc_netdev: Unable to allocate device\n"); return NULL; } @@ -6486,8 +6476,8 @@ static void __net_exit default_device_exit(struct net *net) snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { - printk(KERN_EMERG "%s: failed to move %s to init_net: %d\n", - __func__, dev->name, err); + pr_emerg("%s: failed to move %s to init_net: %d\n", + __func__, dev->name, err); BUG(); } } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 369b418..6d6d7d2 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -73,6 +73,8 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXCSUM_BIT] = "rx-checksum", [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", [NETIF_F_LOOPBACK_BIT] = "loopback", + [NETIF_F_RXFCS_BIT] = "rx-fcs", + [NETIF_F_RXALL_BIT] = "rx-all", }; static int ethtool_get_features(struct net_device *dev, void __user *useraddr) @@ -1190,6 +1192,8 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, if (!dev->ethtool_ops->flash_device) return -EOPNOTSUPP; + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + return dev->ethtool_ops->flash_device(dev, &efl); } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e287346..0a68045 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -826,6 +826,8 @@ next_elt: write_unlock_bh(&tbl->lock); cond_resched(); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); } /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 @@ -2165,6 +2167,35 @@ nla_put_failure: return -EMSGSIZE; } +static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, + u32 pid, u32 seq, int type, unsigned int flags, + struct neigh_table *tbl) +{ + struct nlmsghdr *nlh; + struct ndmsg *ndm; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -EMSGSIZE; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = tbl->family; + ndm->ndm_pad1 = 0; + ndm->ndm_pad2 = 0; + ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_type = NDA_DST; + ndm->ndm_ifindex = pn->dev->ifindex; + ndm->ndm_state = NUD_NONE; + + NLA_PUT(skb, NDA_DST, tbl->key_len, pn->key); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + nlmsg_cancel(skb, nlh); + return -EMSGSIZE; +} + static void neigh_update_notify(struct neighbour *neigh) { call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); @@ -2214,23 +2245,78 @@ out: return rc; } +static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct pneigh_entry *n; + struct net *net = sock_net(skb->sk); + int rc, h, s_h = cb->args[3]; + int idx, s_idx = idx = cb->args[4]; + + read_lock_bh(&tbl->lock); + + for (h = 0; h <= PNEIGH_HASHMASK; h++) { + if (h < s_h) + continue; + if (h > s_h) + s_idx = 0; + for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { + if (dev_net(n->dev) != net) + continue; + if (idx < s_idx) + goto next; + if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGH, + NLM_F_MULTI, tbl) <= 0) { + read_unlock_bh(&tbl->lock); + rc = -1; + goto out; + } + next: + idx++; + } + } + + read_unlock_bh(&tbl->lock); + rc = skb->len; +out: + cb->args[3] = h; + cb->args[4] = idx; + return rc; + +} + static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { struct neigh_table *tbl; int t, family, s_t; + int proxy = 0; + int err = 0; read_lock(&neigh_tbl_lock); family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; + + /* check for full ndmsg structure presence, family member is + * the same for both structures + */ + if (nlmsg_len(cb->nlh) >= sizeof(struct ndmsg) && + ((struct ndmsg *) nlmsg_data(cb->nlh))->ndm_flags == NTF_PROXY) + proxy = 1; + s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { + for (tbl = neigh_tables, t = 0; tbl && (err >= 0); + tbl = tbl->next, t++) { if (t < s_t || (family && tbl->family != family)) continue; if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); - if (neigh_dump_table(tbl, skb, cb) < 0) - break; + if (proxy) + err = pneigh_dump_table(tbl, skb, cb); + else + err = neigh_dump_table(tbl, skb, cb); } read_unlock(&neigh_tbl_lock); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 556b082..3d84fb9 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -9,6 +9,8 @@ * Copyright (C) 2002 Red Hat, Inc. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -45,9 +47,11 @@ static atomic_t trapped; #define NETPOLL_RX_ENABLED 1 #define NETPOLL_RX_DROP 2 -#define MAX_SKB_SIZE \ - (MAX_UDP_CHUNK + sizeof(struct udphdr) + \ - sizeof(struct iphdr) + sizeof(struct ethhdr)) +#define MAX_SKB_SIZE \ + (sizeof(struct ethhdr) + \ + sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + MAX_UDP_CHUNK) static void zap_completion_queue(void); static void arp_reply(struct sk_buff *skb); @@ -55,6 +59,13 @@ static void arp_reply(struct sk_buff *skb); static unsigned int carrier_timeout = 4; module_param(carrier_timeout, uint, 0644); +#define np_info(np, fmt, ...) \ + pr_info("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_err(np, fmt, ...) \ + pr_err("%s: " fmt, np->name, ##__VA_ARGS__) +#define np_notice(np, fmt, ...) \ + pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) + static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = @@ -194,7 +205,7 @@ static void netpoll_poll_dev(struct net_device *dev) poll_napi(dev); - if (dev->priv_flags & IFF_SLAVE) { + if (dev->flags & IFF_SLAVE) { if (dev->npinfo) { struct net_device *bond_dev = dev->master; struct sk_buff *skb; @@ -627,18 +638,12 @@ out: void netpoll_print_options(struct netpoll *np) { - printk(KERN_INFO "%s: local port %d\n", - np->name, np->local_port); - printk(KERN_INFO "%s: local IP %pI4\n", - np->name, &np->local_ip); - printk(KERN_INFO "%s: interface '%s'\n", - np->name, np->dev_name); - printk(KERN_INFO "%s: remote port %d\n", - np->name, np->remote_port); - printk(KERN_INFO "%s: remote IP %pI4\n", - np->name, &np->remote_ip); - printk(KERN_INFO "%s: remote ethernet address %pM\n", - np->name, np->remote_mac); + np_info(np, "local port %d\n", np->local_port); + np_info(np, "local IP %pI4\n", &np->local_ip); + np_info(np, "interface '%s'\n", np->dev_name); + np_info(np, "remote port %d\n", np->remote_port); + np_info(np, "remote IP %pI4\n", &np->remote_ip); + np_info(np, "remote ethernet address %pM\n", np->remote_mac); } EXPORT_SYMBOL(netpoll_print_options); @@ -680,8 +685,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) goto parse_failed; *delim = 0; if (*cur == ' ' || *cur == '\t') - printk(KERN_INFO "%s: warning: whitespace" - "is not allowed\n", np->name); + np_info(np, "warning: whitespace is not allowed\n"); np->remote_port = simple_strtol(cur, NULL, 10); cur = delim; } @@ -705,8 +709,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) return 0; parse_failed: - printk(KERN_INFO "%s: couldn't parse config at '%s'!\n", - np->name, cur); + np_info(np, "couldn't parse config at '%s'!\n", cur); return -1; } EXPORT_SYMBOL(netpoll_parse_options); @@ -721,8 +724,8 @@ int __netpoll_setup(struct netpoll *np) if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || !ndev->netdev_ops->ndo_poll_controller) { - printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", - np->name, np->dev_name); + np_err(np, "%s doesn't support polling, aborting\n", + np->dev_name); err = -ENOTSUPP; goto out; } @@ -785,14 +788,12 @@ int netpoll_setup(struct netpoll *np) if (np->dev_name) ndev = dev_get_by_name(&init_net, np->dev_name); if (!ndev) { - printk(KERN_ERR "%s: %s doesn't exist, aborting.\n", - np->name, np->dev_name); + np_err(np, "%s doesn't exist, aborting\n", np->dev_name); return -ENODEV; } if (ndev->master) { - printk(KERN_ERR "%s: %s is a slave device, aborting.\n", - np->name, np->dev_name); + np_err(np, "%s is a slave device, aborting\n", np->dev_name); err = -EBUSY; goto put; } @@ -800,16 +801,14 @@ int netpoll_setup(struct netpoll *np) if (!netif_running(ndev)) { unsigned long atmost, atleast; - printk(KERN_INFO "%s: device %s not up yet, forcing it\n", - np->name, np->dev_name); + np_info(np, "device %s not up yet, forcing it\n", np->dev_name); rtnl_lock(); err = dev_open(ndev); rtnl_unlock(); if (err) { - printk(KERN_ERR "%s: failed to open %s\n", - np->name, ndev->name); + np_err(np, "failed to open %s\n", ndev->name); goto put; } @@ -817,9 +816,7 @@ int netpoll_setup(struct netpoll *np) atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { - printk(KERN_NOTICE - "%s: timeout waiting for carrier\n", - np->name); + np_notice(np, "timeout waiting for carrier\n"); break; } msleep(1); @@ -831,9 +828,7 @@ int netpoll_setup(struct netpoll *np) */ if (time_before(jiffies, atleast)) { - printk(KERN_NOTICE "%s: carrier detect appears" - " untrustworthy, waiting 4 seconds\n", - np->name); + np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n"); msleep(4000); } } @@ -844,15 +839,15 @@ int netpoll_setup(struct netpoll *np) if (!in_dev || !in_dev->ifa_list) { rcu_read_unlock(); - printk(KERN_ERR "%s: no IP address for %s, aborting\n", - np->name, np->dev_name); + np_err(np, "no IP address for %s, aborting\n", + np->dev_name); err = -EDESTADDRREQ; goto put; } np->local_ip = in_dev->ifa_list->ifa_local; rcu_read_unlock(); - printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip); + np_info(np, "local IP %pI4\n", &np->local_ip); } np->dev = ndev; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 3a9fd48..4dacc44 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -58,11 +58,12 @@ static int get_prioidx(u32 *prio) spin_lock_irqsave(&prioidx_map_lock, flags); prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) { + spin_unlock_irqrestore(&prioidx_map_lock, flags); + return -ENOSPC; + } set_bit(prioidx, prioidx_map); spin_unlock_irqrestore(&prioidx_map_lock, flags); - if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) - return -ENOSPC; - atomic_set(&max_prioidx, prioidx); *prio = prioidx; return 0; @@ -107,7 +108,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len) static void update_netdev_tables(void) { struct net_device *dev; - u32 max_len = atomic_read(&max_prioidx); + u32 max_len = atomic_read(&max_prioidx) + 1; struct netprio_map *map; rtnl_lock(); @@ -270,7 +271,6 @@ static int netprio_device_event(struct notifier_block *unused, { struct net_device *dev = ptr; struct netprio_map *old; - u32 max_len = atomic_read(&max_prioidx); /* * Note this is called with rtnl_lock held so we have update side @@ -278,11 +278,6 @@ static int netprio_device_event(struct notifier_block *unused, */ switch (event) { - - case NETDEV_REGISTER: - if (max_len) - extend_netdev_table(dev, max_len); - break; case NETDEV_UNREGISTER: old = rtnl_dereference(dev->priomap); RCU_INIT_POINTER(dev->priomap, NULL); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 65aebd4..2be1018 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -60,7 +60,6 @@ struct rtnl_link { }; static DEFINE_MUTEX(rtnl_mutex); -static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -724,10 +723,11 @@ static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) } /* All VF info */ -static inline int rtnl_vfinfo_size(const struct net_device *dev) +static inline int rtnl_vfinfo_size(const struct net_device *dev, + u32 ext_filter_mask) { - if (dev->dev.parent && dev_is_pci(dev->dev.parent)) { - + if (dev->dev.parent && dev_is_pci(dev->dev.parent) && + (ext_filter_mask & RTEXT_FILTER_VF)) { int num_vfs = dev_num_vf(dev->dev.parent); size_t size = nla_total_size(sizeof(struct nlattr)); size += nla_total_size(num_vfs * sizeof(struct nlattr)); @@ -766,7 +766,8 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static noinline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev, + u32 ext_filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -784,8 +785,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ - + nla_total_size(4) /* IFLA_NUM_VF */ - + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + nla_total_size(ext_filter_mask + & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ @@ -868,7 +870,7 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, - unsigned int flags) + unsigned int flags, u32 ext_filter_mask) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -941,10 +943,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); - if (dev->dev.parent) + if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF)) NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); - if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent + && (ext_filter_mask & RTEXT_FILTER_VF)) { int i; struct nlattr *vfinfo, *vf; @@ -1048,6 +1051,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct net_device *dev; struct hlist_head *head; struct hlist_node *node; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1055,6 +1060,12 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); cb->seq = net->dev_base_seq; + nlmsg_parse(cb->nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, + ifla_policy); + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1064,7 +1075,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + NLM_F_MULTI, + ext_filter_mask) <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1100,6 +1112,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, [IFLA_AF_SPEC] = { .type = NLA_NESTED }, + [IFLA_EXT_MASK] = { .type = NLA_U32 }, }; EXPORT_SYMBOL(ifla_policy); @@ -1119,6 +1132,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_vlan) }, [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, .len = sizeof(struct ifla_vf_tx_rate) }, + [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_spoofchk) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1509,8 +1524,6 @@ errout: if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - min_ifinfo_dump_size = max_t(u16, if_nlmsg_size(dev), - min_ifinfo_dump_size); return err; } @@ -1842,6 +1855,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) struct net_device *dev = NULL; struct sk_buff *nskb; int err; + u32 ext_filter_mask = 0; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); if (err < 0) @@ -1850,6 +1864,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); @@ -1861,12 +1878,12 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (dev == NULL) return -ENODEV; - nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL); if (nskb == NULL) return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -1877,8 +1894,31 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } -static u16 rtnl_calcit(struct sk_buff *skb) +static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { + struct net *net = sock_net(skb->sk); + struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + u32 ext_filter_mask = 0; + u16 min_ifinfo_dump_size = 0; + + nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, IFLA_MAX, ifla_policy); + + if (tb[IFLA_EXT_MASK]) + ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); + + if (!ext_filter_mask) + return NLMSG_GOODSIZE; + /* + * traverse the list of net devices and compute the minimum + * buffer size based upon the filter mask. + */ + list_for_each_entry(dev, &net->dev_base_head, dev_list) { + min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size, + if_nlmsg_size(dev, + ext_filter_mask)); + } + return min_ifinfo_dump_size; } @@ -1913,13 +1953,11 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) int err = -ENOBUFS; size_t if_info_size; - skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev, 0)), GFP_KERNEL); if (skb == NULL) goto errout; - min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); - - err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1977,12 +2015,17 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; calcit = rtnl_get_calcit(family, type); if (calcit) - min_dump_alloc = calcit(skb); + min_dump_alloc = calcit(skb, nlh); __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, - NULL, min_dump_alloc); + { + struct netlink_dump_control c = { + .dump = dumpit, + .min_dump_alloc = min_dump_alloc, + }; + err = netlink_dump_start(rtnl, skb, nlh, &c); + } rtnl_lock(); return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index da0c97f..6eb656a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -592,6 +592,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->rxhash = old->rxhash; new->ooo_okay = old->ooo_okay; new->l4_rxhash = old->l4_rxhash; + new->no_fcs = old->no_fcs; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -2906,7 +2907,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) nskb->prev = p; nskb->data_len += p->len; - nskb->truesize += p->len; + nskb->truesize += p->truesize; nskb->len += p->len; *head = nskb; @@ -2916,6 +2917,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: + p->truesize += skb->truesize - len; if (offset > headlen) { unsigned int eat = offset - headlen; diff --git a/net/core/sock.c b/net/core/sock.c index 3e81fd2..216719c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -793,6 +793,17 @@ set_rcvbuf: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; + case SO_PEEK_OFF: + if (sock->ops->set_peek_off) + sock->ops->set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + break; + + case SO_NOFCS: + sock_valbool_flag(sk, SOCK_NOFCS, valbool); + break; + default: ret = -ENOPROTOOPT; break; @@ -1018,6 +1029,15 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = !!sock_flag(sk, SOCK_WIFI_STATUS); break; + case SO_PEEK_OFF: + if (!sock->ops->set_peek_off) + return -EOPNOTSUPP; + + v.val = sk->sk_peek_off; + break; + case SO_NOFCS: + v.val = !!sock_flag(sk, SOCK_NOFCS); + break; default: return -ENOPROTOOPT; } @@ -1171,13 +1191,10 @@ EXPORT_SYMBOL(sock_update_classid); void sock_update_netprioidx(struct sock *sk) { - struct cgroup_netprio_state *state; if (in_interrupt()) return; - rcu_read_lock(); - state = task_netprio_state(current); - sk->sk_cgrp_prioidx = state ? state->prioidx : 0; - rcu_read_unlock(); + + sk->sk_cgrp_prioidx = task_netprioidx(current); } EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif @@ -2095,6 +2112,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; + sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 5606273..70bfaf2 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -98,6 +98,7 @@ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) { hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); + DCCP_BUG_ON(hc->tx_t_ipi == 0); ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi, hc->tx_s, (unsigned)(hc->tx_x >> 6)); } @@ -236,8 +237,6 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) * * Note that X_recv is scaled by 2^6 while X_calc is not */ - BUG_ON(hc->tx_p && !hc->tx_x_calc); - if (hc->tx_x_calc > (hc->tx_x_recv >> 5)) hc->tx_x_recv = max(hc->tx_x_recv / 2, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 1c67fe8..caf6e17 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -300,7 +300,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) */ WARN_ON(req->sk); - if (seq != dccp_rsk(req)->dreq_iss) { + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -639,11 +640,12 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * - * In fact we defer setting S.GSR, S.SWL, S.SWH to - * dccp_create_openreq_child. + * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v4_init_sequence(skb); + dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; if (dccp_v4_send_response(sk, req, NULL)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ce903f7..4dc588f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -193,7 +193,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ WARN_ON(req->sk != NULL); - if (seq != dccp_rsk(req)->dreq_iss) { + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -440,11 +441,12 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * - * In fact we defer setting S.GSR, S.SWL, S.SWH to - * dccp_create_openreq_child. + * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v6_init_sequence(skb); + dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; if (dccp_v6_send_response(sk, req, NULL)) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 5a7f90b..ea850ce 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -127,9 +127,11 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * activation below, as these windows all depend on the local * and remote Sequence Window feature values (7.5.2). */ - newdp->dccps_gss = newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gss = dreq->dreq_gss; newdp->dccps_gar = newdp->dccps_iss; - newdp->dccps_gsr = newdp->dccps_isr = dreq->dreq_isr; + newdp->dccps_isr = dreq->dreq_isr; + newdp->dccps_gsr = dreq->dreq_gsr; /* * Activate features: initialise CCIDs, sequence windows etc. @@ -164,9 +166,9 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { - if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_isr)) { + if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_gsr)) { dccp_pr_debug("Retransmitted REQUEST\n"); - dreq->dreq_isr = DCCP_SKB_CB(skb)->dccpd_seq; + dreq->dreq_gsr = DCCP_SKB_CB(skb)->dccpd_seq; /* * Send another RESPONSE packet * To protect against Request floods, increment retrans @@ -186,12 +188,14 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, goto drop; /* Invalid ACK */ - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != dreq->dreq_iss) { + if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq, + dreq->dreq_iss, dreq->dreq_gss)) { dccp_pr_debug("Invalid ACK number: ack_seq=%llu, " - "dreq_iss=%llu\n", + "dreq_iss=%llu, dreq_gss=%llu\n", (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq, - (unsigned long long) dreq->dreq_iss); + (unsigned long long) dreq->dreq_iss, + (unsigned long long) dreq->dreq_gss); goto drop; } diff --git a/net/dccp/output.c b/net/dccp/output.c index dede3ed..7873673 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -408,10 +408,10 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, skb_dst_set(skb, dst_clone(dst)); dreq = dccp_rsk(req); - if (inet_rsk(req)->acked) /* increase ISS upon retransmission */ - dccp_inc_seqno(&dreq->dreq_iss); + if (inet_rsk(req)->acked) /* increase GSS upon retransmission */ + dccp_inc_seqno(&dreq->dreq_gss); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE; - DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_iss; + DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_gss; /* Resolve feature dependencies resulting from choice of CCID */ if (dccp_feat_server_ccid_dependencies(dreq)) @@ -429,8 +429,8 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, DCCP_SKB_CB(skb)->dccpd_opt_len) / 4; dh->dccph_type = DCCP_PKT_RESPONSE; dh->dccph_x = 1; - dccp_hdr_set_seq(dh, dreq->dreq_iss); - dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_isr); + dccp_hdr_set_seq(dh, dreq->dreq_gss); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_gsr); dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service; dccp_csum_outgoing(skb); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index befe426..ee7013f 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -205,17 +205,23 @@ static int dn_neigh_output_packet(struct sk_buff *skb) struct neighbour *neigh = dst_get_neighbour_noref(dst); struct net_device *dev = neigh->dev; char mac_addr[ETH_ALEN]; + unsigned int seq; + int err; dn_dn2eth(mac_addr, rt->rt_local_src); - if (dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, - mac_addr, skb->len) >= 0) - return dev_queue_xmit(skb); - - if (net_ratelimit()) - printk(KERN_DEBUG "dn_neigh_output_packet: oops, can't send packet\n"); - - kfree_skb(skb); - return -EINVAL; + do { + seq = read_seqbegin(&neigh->ha_lock); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, mac_addr, skb->len); + } while (read_seqretry(&neigh->ha_lock, seq)); + + if (err >= 0) + err = dev_queue_xmit(skb); + else { + kfree_skb(skb); + err = -EINVAL; + } + return err; } static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index f31ce72..80a3de4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -724,11 +724,10 @@ static int dn_output(struct sk_buff *skb) struct dn_route *rt = (struct dn_route *)dst; struct net_device *dev = dst->dev; struct dn_skb_cb *cb = DN_SKB_CB(skb); - struct neighbour *neigh; int err = -EINVAL; - if ((neigh = dst_get_neighbour_noref(dst)) == NULL) + if (dst_get_neighbour_noref(dst) == NULL) goto error; skb->dev = dev; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index a246836..a93af86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -288,6 +288,8 @@ int eth_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN); + /* if device marked as NET_ADDR_RANDOM, reset it */ + dev->addr_assign_type &= ~NET_ADDR_RANDOM; return 0; } EXPORT_SYMBOL(eth_mac_addr); diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index e4ecc1e..3685158 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -55,6 +55,7 @@ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netdevice.h> +#include <linux/etherdevice.h> #include <net/af_ieee802154.h> #include <net/ieee802154.h> #include <net/ieee802154_netdev.h> @@ -924,19 +925,6 @@ drop: return -EINVAL; } -static int lowpan_set_address(struct net_device *dev, void *p) -{ - struct sockaddr *sa = p; - - if (netif_running(dev)) - return -EBUSY; - - /* TODO: validate addr */ - memcpy(dev->dev_addr, sa->sa_data, dev->addr_len); - - return 0; -} - static int lowpan_get_mac_header_length(struct sk_buff *skb) { /* @@ -1062,7 +1050,7 @@ static struct header_ops lowpan_header_ops = { static const struct net_device_ops lowpan_netdev_ops = { .ndo_start_xmit = lowpan_xmit, - .ndo_set_mac_address = lowpan_set_address, + .ndo_set_mac_address = eth_mac_addr, }; static void lowpan_setup(struct net_device *dev) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index aa2a2c7..d183262 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -409,7 +409,7 @@ config INET_TCP_DIAG config INET_UDP_DIAG tristate "UDP: socket monitoring interface" - depends on INET_DIAG + depends on INET_DIAG && (IPV6 || IPV6=n) default n ---help--- Support for UDP socket monitoring interface used by the ss tool. diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f7b5670..e588a34 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -381,6 +381,7 @@ lookup_protocol: inet->mc_all = 1; inet->mc_index = 0; inet->mc_list = NULL; + inet->rcv_tos = 0; sk_refcnt_debug_inc(sk); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 59402be..63e4989 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -863,7 +863,8 @@ static int arp_process(struct sk_buff *skb) if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || - pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { + (rt->dst.dev != dev && + pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index fcf2818..8d25a1c 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -960,9 +960,12 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; } - - return netlink_dump_start(sock_diag_nlsk, skb, nlh, - inet_diag_dump_compat, NULL, 0); + { + struct netlink_dump_control c = { + .dump = inet_diag_dump_compat, + }; + return netlink_dump_start(sock_diag_nlsk, skb, nlh, &c); + } } return inet_diag_get_exact_compat(skb, nlh); @@ -985,9 +988,12 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) inet_diag_bc_audit(nla_data(attr), nla_len(attr))) return -EINVAL; } - - return netlink_dump_start(sock_diag_nlsk, skb, h, - inet_diag_dump, NULL, 0); + { + struct netlink_dump_control c = { + .dump = inet_diag_dump, + }; + return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + } } return inet_diag_get_exact(skb, h, (struct inet_diag_req_v2 *)NLMSG_DATA(h)); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 6b3ca5b..6ef66af 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -65,7 +65,7 @@ it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good - solution, but it supposes maintaing new variable in ALL + solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu @@ -91,14 +91,14 @@ One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, - taking into account fragmentation. TO be short, tt is not solution at all. + taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu - fastly degrades to value <68, where looping stops. + rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made @@ -457,8 +457,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info) GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, - what the hell these idiots break standrads established - by themself??? + what the hell these idiots break standards established + by themselves??? */ const struct iphdr *iph = (const struct iphdr *)skb->data; @@ -730,15 +730,16 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { rt = skb_rtable(skb); - if ((dst = rt->rt_gateway) == 0) - goto tx_error_icmp; + dst = rt->rt_gateway; } #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb)); const struct in6_addr *addr6; + struct neighbour *neigh; + bool do_tx_error_icmp; int addr_type; + neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (neigh == NULL) goto tx_error; @@ -751,9 +752,14 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } if ((addr_type & IPV6_ADDR_COMPATv4) == 0) + do_tx_error_icmp = true; + else { + do_tx_error_icmp = false; + dst = addr6->s6_addr32[3]; + } + neigh_release(neigh); + if (do_tx_error_icmp) goto tx_error_icmp; - - dst = addr6->s6_addr32[3]; } #endif else @@ -914,9 +920,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; +#if IS_ENABLED(CONFIG_IPV6) tx_error_icmp: dst_link_failure(skb); - +#endif tx_error: dev->stats.tx_errors++; dev_kfree_skb(skb); @@ -1529,7 +1536,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla return -EEXIST; if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS]) - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); mtu = ipgre_tunnel_bind_dev(dev); if (!tb[IFLA_MTU]) diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 1e60f76..42dd1a9 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -573,8 +573,8 @@ void ip_forward_options(struct sk_buff *skb) } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; - ip_rt_get_source(&optptr[srrptr-1], skb, rt); ip_hdr(skb)->daddr = opt->nexthop; + ip_rt_get_source(&optptr[srrptr-1], skb, rt); optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 8aa87c1..ca50d9f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -469,6 +469,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) | (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) || + optname == IP_UNICAST_IF || optname == IP_MULTICAST_TTL || optname == IP_MULTICAST_ALL || optname == IP_MULTICAST_LOOP || @@ -628,6 +629,35 @@ static int do_ip_setsockopt(struct sock *sk, int level, goto e_inval; inet->mc_loop = !!val; break; + case IP_UNICAST_IF: + { + struct net_device *dev = NULL; + int ifindex; + + if (optlen != sizeof(int)) + goto e_inval; + + ifindex = (__force int)ntohl((__force __be32)val); + if (ifindex == 0) { + inet->uc_index = 0; + err = 0; + break; + } + + dev = dev_get_by_index(sock_net(sk), ifindex); + err = -EADDRNOTAVAIL; + if (!dev) + break; + dev_put(dev); + + err = -EINVAL; + if (sk->sk_bound_dev_if) + break; + + inet->uc_index = ifindex; + err = 0; + break; + } case IP_MULTICAST_IF: { struct ip_mreqn mreq; @@ -1178,6 +1208,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_MULTICAST_LOOP: val = inet->mc_loop; break; + case IP_UNICAST_IF: + val = (__force int)htonl((__u32) inet->uc_index); + break; case IP_MULTICAST_IF: { struct in_addr addr; @@ -1256,6 +1289,10 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, int hlim = inet->mc_ttl; put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim); } + if (inet->cmsg_flags & IP_CMSG_TOS) { + int tos = inet->rcv_tos; + put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); + } len -= msg.msg_controllen; return put_user(len, optlen); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 22a1993..f84ebff 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -454,8 +454,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_fifo_errors++; goto tx_error; } - if ((dst = rt->rt_gateway) == 0) - goto tx_error_icmp; + dst = rt->rt_gateway; } rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index aea5a19..4398a45 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -556,7 +556,8 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, @@ -630,6 +631,7 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); + err = -EOPNOTSUPP; if (flags & MSG_OOB) goto out; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 6afc807..02d6107 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -256,6 +256,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES), SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP), + SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 3ccda5a..ab46630 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = inet->mc_index; if (!saddr) saddr = inet->mc_addr; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bcacf54..0489ced 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1117,12 +1117,17 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo static const __be32 inaddr_any = 0; struct net_device *dev = dst->dev; const __be32 *pkey = daddr; + const struct rtable *rt; struct neighbour *n; + rt = (const struct rtable *) dst; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) pkey = &inaddr_any; + else if (rt->rt_gateway) + pkey = (const __be32 *) &rt->rt_gateway; - n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey); + n = __ipv4_neigh_lookup(dev, *(__force u32 *)pkey); if (n) return n; return neigh_create(&arp_tbl, pkey, dev); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 4cb9cd2..7a7724d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -778,7 +778,6 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; - unsigned long limit; table = ipv4_net_table; if (!net_eq(net, &init_net)) { @@ -815,11 +814,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_rt_cache_rebuild_count = 4; tcp_init_mem(net); - limit = nr_free_buffer_pages() / 8; - limit = max(limit, 128UL); - net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; - net->ipv4.sysctl_tcp_mem[1] = limit; - net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 06373b4..22ef5f9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1876,6 +1876,20 @@ void tcp_shutdown(struct sock *sk, int how) } EXPORT_SYMBOL(tcp_shutdown); +bool tcp_check_oom(struct sock *sk, int shift) +{ + bool too_many_orphans, out_of_socket_memory; + + too_many_orphans = tcp_too_many_orphans(sk, shift); + out_of_socket_memory = tcp_out_of_memory(sk); + + if (too_many_orphans && net_ratelimit()) + pr_info("TCP: too many orphaned sockets\n"); + if (out_of_socket_memory && net_ratelimit()) + pr_info("TCP: out of memory -- consider tuning tcp_mem\n"); + return too_many_orphans || out_of_socket_memory; +} + void tcp_close(struct sock *sk, long timeout) { struct sk_buff *skb; @@ -2015,10 +2029,7 @@ adjudge_to_death: } if (sk->sk_state != TCP_CLOSE) { sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, 0)) { - if (net_ratelimit()) - printk(KERN_INFO "TCP: too many of orphaned " - "sockets\n"); + if (tcp_check_oom(sk, 0)) { tcp_set_state(sk, TCP_CLOSE); tcp_send_active_reset(sk, GFP_ATOMIC); NET_INC_STATS_BH(sock_net(sk), @@ -3218,7 +3229,6 @@ __setup("thash_entries=", set_thash_entries); void tcp_init_mem(struct net *net) { - /* Set per-socket limits to no more than 1/128 the pressure threshold */ unsigned long limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; @@ -3230,7 +3240,8 @@ void __init tcp_init(void) { struct sk_buff *skb = NULL; unsigned long limit; - int i, max_share, cnt; + int max_share, cnt; + unsigned int i; unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -3273,7 +3284,7 @@ void __init tcp_init(void) &tcp_hashinfo.bhash_size, NULL, 64 * 1024); - tcp_hashinfo.bhash_size = 1 << tcp_hashinfo.bhash_size; + tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); @@ -3287,7 +3298,8 @@ void __init tcp_init(void) sysctl_max_syn_backlog = max(128, cnt / 256); tcp_init_mem(&init_net); - limit = nr_free_buffer_pages() / 8; + /* Set per-socket limits to no more than 1/128 the pressure threshold */ + limit = nr_free_buffer_pages() << (PAGE_SHIFT - 10); limit = max(limit, 128UL); max_share = min(4UL*1024*1024, limit); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 976034f..ee42d42 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1307,25 +1307,26 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, - struct tcp_sacktag_state *state, +/* Mark the given newly-SACKed range as such, adjusting counters and hints. */ +static u8 tcp_sacktag_one(struct sock *sk, + struct tcp_sacktag_state *state, u8 sacked, + u32 start_seq, u32 end_seq, int dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); - u8 sacked = TCP_SKB_CB(skb)->sacked; int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (tp->undo_marker && tp->undo_retrans && - after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) + after(end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + if (!after(end_seq, tp->snd_una)) return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { @@ -1344,13 +1345,13 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* New sack for not retransmitted frame, * which was in hole. It is reordering. */ - if (before(TCP_SKB_CB(skb)->seq, + if (before(start_seq, tcp_highest_sack_seq(tp))) state->reord = min(fack_count, state->reord); /* SACK enhanced F-RTO (RFC4138; Appendix B) */ - if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) + if (!after(end_seq, tp->frto_highmark)) state->flag |= FLAG_ONLY_ORIG_SACKED; } @@ -1368,8 +1369,7 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->lost_skb_hint)->seq)) + before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) @@ -1388,6 +1388,9 @@ static u8 tcp_sacktag_one(const struct sk_buff *skb, struct sock *sk, return sacked; } +/* Shift newly-SACKed bytes from this skb to the immediately previous + * already-SACKed sk_buff. Mark the newly-SACKed bytes as such. + */ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, struct tcp_sacktag_state *state, unsigned int pcount, int shifted, int mss, @@ -1395,9 +1398,20 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *prev = tcp_write_queue_prev(sk, skb); + u32 start_seq = TCP_SKB_CB(skb)->seq; /* start of newly-SACKed */ + u32 end_seq = start_seq + shifted; /* end of newly-SACKed */ BUG_ON(!pcount); + /* Adjust counters and hints for the newly sacked sequence + * range but discard the return value since prev is already + * marked. We must tag the range first because the seq + * advancement below implicitly advances + * tcp_highest_sack_seq() when skb is highest_sack. + */ + tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, + start_seq, end_seq, dup_sack, pcount); + if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1424,9 +1438,6 @@ static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, skb_shinfo(skb)->gso_type = 0; } - /* We discard results */ - tcp_sacktag_one(skb, sk, state, dup_sack, pcount); - /* Difference in this won't matter, both ACKed by the same cumul. ACK */ TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); @@ -1664,10 +1675,14 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, break; if (in_sack) { - TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk, - state, - dup_sack, - tcp_skb_pcount(skb)); + TCP_SKB_CB(skb)->sacked = + tcp_sacktag_one(sk, + state, + TCP_SKB_CB(skb)->sacked, + TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + dup_sack, + tcp_skb_pcount(skb)); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 337ba4c..94abee8 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -90,16 +90,8 @@ EXPORT_SYMBOL(sysctl_tcp_low_latency); #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, - __be32 addr); -static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); -#else -static inline -struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) -{ - return NULL; -} #endif struct inet_hashinfo tcp_hashinfo; @@ -601,6 +593,10 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; + const __u8 *hash_location = NULL; + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; #endif struct net *net; @@ -631,7 +627,36 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len = sizeof(rep.th); #ifdef CONFIG_TCP_MD5SIG - key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->saddr) : NULL; + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = __inet_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, ip_hdr(skb)->daddr, + ntohs(th->source), inet_iif(skb)); + /* don't send rst if it can't find key */ + if (!sk1) + return; + rcu_read_lock(); + key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, AF_INET); + if (!key) + goto release_sk1; + + genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_md5_do_lookup(sk, (union tcp_md5_addr *) + &ip_hdr(skb)->saddr, + AF_INET) : NULL; + } + if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -651,6 +676,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0; + /* When socket is gone, all binding information is lost. + * routing might fail in this case. using iif for oif to + * make sure we can deliver it + */ + arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb); net = dev_net(skb_dst(skb)->dev); arg.tos = ip_hdr(skb)->tos; @@ -659,6 +689,14 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); + +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states @@ -759,7 +797,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent, 0, - tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr), + tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, + AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } @@ -876,153 +915,137 @@ static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk, */ /* Find the Key structure for an address. */ -static struct tcp_md5sig_key * - tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) +struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, + const union tcp_md5_addr *addr, + int family) { struct tcp_sock *tp = tcp_sk(sk); - int i; - - if (!tp->md5sig_info || !tp->md5sig_info->entries4) + struct tcp_md5sig_key *key; + struct hlist_node *pos; + unsigned int size = sizeof(struct in_addr); + struct tcp_md5sig_info *md5sig; + + /* caller either holds rcu_read_lock() or socket lock */ + md5sig = rcu_dereference_check(tp->md5sig_info, + sock_owned_by_user(sk)); + if (!md5sig) return NULL; - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) - return &tp->md5sig_info->keys4[i].base; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + size = sizeof(struct in6_addr); +#endif + hlist_for_each_entry_rcu(key, pos, &md5sig->head, node) { + if (key->family != family) + continue; + if (!memcmp(&key->addr, addr, size)) + return key; } return NULL; } +EXPORT_SYMBOL(tcp_md5_do_lookup); struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr); + union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&inet_sk(addr_sk)->inet_daddr; + return tcp_md5_do_lookup(sk, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk, struct request_sock *req) { - return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr); + union tcp_md5_addr *addr; + + addr = (union tcp_md5_addr *)&inet_rsk(req)->rmt_addr; + return tcp_md5_do_lookup(sk, addr, AF_INET); } /* This can be called on a newly created socket, from other files */ -int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, - u8 *newkey, u8 newkeylen) +int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, + int family, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); - struct tcp4_md5sig_key *keys; + struct tcp_md5sig_info *md5sig; - key = tcp_v4_md5_do_lookup(sk, addr); + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); if (key) { /* Pre-existing entry - just update that one. */ - kfree(key->key); - key->key = newkey; + memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; - } else { - struct tcp_md5sig_info *md5sig; - - if (!tp->md5sig_info) { - tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), - GFP_ATOMIC); - if (!tp->md5sig_info) { - kfree(newkey); - return -ENOMEM; - } - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } + return 0; + } - md5sig = tp->md5sig_info; - if (md5sig->entries4 == 0 && - tcp_alloc_md5sig_pool(sk) == NULL) { - kfree(newkey); + md5sig = rcu_dereference_protected(tp->md5sig_info, + sock_owned_by_user(sk)); + if (!md5sig) { + md5sig = kmalloc(sizeof(*md5sig), gfp); + if (!md5sig) return -ENOMEM; - } - - if (md5sig->alloced4 == md5sig->entries4) { - keys = kmalloc((sizeof(*keys) * - (md5sig->entries4 + 1)), GFP_ATOMIC); - if (!keys) { - kfree(newkey); - if (md5sig->entries4 == 0) - tcp_free_md5sig_pool(); - return -ENOMEM; - } - if (md5sig->entries4) - memcpy(keys, md5sig->keys4, - sizeof(*keys) * md5sig->entries4); + sk_nocaps_add(sk, NETIF_F_GSO_MASK); + INIT_HLIST_HEAD(&md5sig->head); + rcu_assign_pointer(tp->md5sig_info, md5sig); + } - /* Free old key list, and reference new one */ - kfree(md5sig->keys4); - md5sig->keys4 = keys; - md5sig->alloced4++; - } - md5sig->entries4++; - md5sig->keys4[md5sig->entries4 - 1].addr = addr; - md5sig->keys4[md5sig->entries4 - 1].base.key = newkey; - md5sig->keys4[md5sig->entries4 - 1].base.keylen = newkeylen; + key = sock_kmalloc(sk, sizeof(*key), gfp); + if (!key) + return -ENOMEM; + if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) { + sock_kfree_s(sk, key, sizeof(*key)); + return -ENOMEM; } - return 0; -} -EXPORT_SYMBOL(tcp_v4_md5_do_add); -static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk, - u8 *newkey, u8 newkeylen) -{ - return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr, - newkey, newkeylen); + memcpy(key->key, newkey, newkeylen); + key->keylen = newkeylen; + key->family = family; + memcpy(&key->addr, addr, + (family == AF_INET6) ? sizeof(struct in6_addr) : + sizeof(struct in_addr)); + hlist_add_head_rcu(&key->node, &md5sig->head); + return 0; } +EXPORT_SYMBOL(tcp_md5_do_add); -int tcp_v4_md5_do_del(struct sock *sk, __be32 addr) +int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family) { struct tcp_sock *tp = tcp_sk(sk); - int i; - - for (i = 0; i < tp->md5sig_info->entries4; i++) { - if (tp->md5sig_info->keys4[i].addr == addr) { - /* Free the key */ - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4--; - - if (tp->md5sig_info->entries4 == 0) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; - tcp_free_md5sig_pool(); - } else if (tp->md5sig_info->entries4 != i) { - /* Need to do some manipulation */ - memmove(&tp->md5sig_info->keys4[i], - &tp->md5sig_info->keys4[i+1], - (tp->md5sig_info->entries4 - i) * - sizeof(struct tcp4_md5sig_key)); - } - return 0; - } - } - return -ENOENT; + struct tcp_md5sig_key *key; + struct tcp_md5sig_info *md5sig; + + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET); + if (!key) + return -ENOENT; + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); + md5sig = rcu_dereference_protected(tp->md5sig_info, + sock_owned_by_user(sk)); + if (hlist_empty(&md5sig->head)) + tcp_free_md5sig_pool(); + return 0; } -EXPORT_SYMBOL(tcp_v4_md5_do_del); +EXPORT_SYMBOL(tcp_md5_do_del); -static void tcp_v4_clear_md5_list(struct sock *sk) +void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct tcp_md5sig_key *key; + struct hlist_node *pos, *n; + struct tcp_md5sig_info *md5sig; - /* Free each key, then the set of key keys, - * the crypto element, and then decrement our - * hold on the last resort crypto. - */ - if (tp->md5sig_info->entries4) { - int i; - for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4 = 0; + md5sig = rcu_dereference_protected(tp->md5sig_info, 1); + + if (!hlist_empty(&md5sig->head)) tcp_free_md5sig_pool(); - } - if (tp->md5sig_info->keys4) { - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; + hlist_for_each_entry_safe(key, pos, n, &md5sig->head, node) { + hlist_del_rcu(&key->node); + atomic_sub(sizeof(*key), &sk->sk_omem_alloc); + kfree_rcu(key, rcu); } } @@ -1031,7 +1054,6 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; - u8 *newkey; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1042,32 +1064,16 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, if (sin->sin_family != AF_INET) return -EINVAL; - if (!cmd.tcpm_key || !cmd.tcpm_keylen) { - if (!tcp_sk(sk)->md5sig_info) - return -ENOENT; - return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr); - } + if (!cmd.tcpm_key || !cmd.tcpm_keylen) + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - if (!tcp_sk(sk)->md5sig_info) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p; - - p = kzalloc(sizeof(*p), sk->sk_allocation); - if (!p) - return -EINVAL; - - tp->md5sig_info = p; - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } - - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); - if (!newkey) - return -ENOMEM; - return tcp_v4_md5_do_add(sk, sin->sin_addr.s_addr, - newkey, cmd.tcpm_keylen); + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, + GFP_KERNEL); } static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, @@ -1093,7 +1099,7 @@ static int tcp_v4_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, return crypto_hash_update(&hp->md5_desc, &sg, sizeof(*bp)); } -static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key, +static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; @@ -1193,7 +1199,8 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) int genhash; unsigned char newhash[16]; - hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr); + hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, + AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ @@ -1456,6 +1463,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; + newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; @@ -1481,7 +1489,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr); + key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET); if (key != NULL) { /* * We're using one, so create a matching key @@ -1489,10 +1498,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); - if (newkey != NULL) - tcp_v4_md5_do_add(newsk, newinet->inet_daddr, - newkey, key->keylen); + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, + AF_INET, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1853,7 +1860,6 @@ EXPORT_SYMBOL(ipv4_specific); static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, - .md5_add = tcp_v4_md5_add_func, .md5_parse = tcp_v4_parse_md5_keys, }; #endif @@ -1942,8 +1948,8 @@ void tcp_v4_destroy_sock(struct sock *sk) #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { - tcp_v4_clear_md5_list(sk); - kfree(tp->md5sig_info); + tcp_clear_md5_list(sk); + kfree_rcu(tp->md5sig_info, rcu); tp->md5sig_info = NULL; } #endif diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 550e755..3cabafb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -359,13 +359,11 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) */ do { struct tcp_md5sig_key *key; - memset(tcptw->tw_md5_key, 0, sizeof(tcptw->tw_md5_key)); - tcptw->tw_md5_keylen = 0; + tcptw->tw_md5_key = NULL; key = tp->af_specific->md5_lookup(sk, sk); if (key != NULL) { - memcpy(&tcptw->tw_md5_key, key->key, key->keylen); - tcptw->tw_md5_keylen = key->keylen; - if (tcp_alloc_md5sig_pool(sk) == NULL) + tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); + if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL) BUG(); } } while (0); @@ -405,8 +403,10 @@ void tcp_twsk_destructor(struct sock *sk) { #ifdef CONFIG_TCP_MD5SIG struct tcp_timewait_sock *twsk = tcp_twsk(sk); - if (twsk->tw_md5_keylen) + if (twsk->tw_md5_key) { tcp_free_md5sig_pool(); + kfree_rcu(twsk->tw_md5_key, rcu); + } #endif } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4ff3b6d..364784a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2306,8 +2306,10 @@ begin_fwd: if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; - if (tcp_retransmit_skb(sk, skb)) + if (tcp_retransmit_skb(sk, skb)) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL); return; + } NET_INC_STATS_BH(sock_net(sk), mib_idx); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a516d1e..cd2e072 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -77,10 +77,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset) if (sk->sk_err_soft) shift++; - if (tcp_too_many_orphans(sk, shift)) { - if (net_ratelimit()) - printk(KERN_INFO "Out of socket memory\n"); - + if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5d075b5..7c41ab8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -917,7 +917,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (!saddr) saddr = inet->mc_addr; connected = 0; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); @@ -1166,7 +1167,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; unsigned int ulen, copied; - int peeked; + int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); bool slow; @@ -1182,7 +1183,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); + &peeked, &off, &err); if (!skb) goto out; diff --git a/net/ipv4/xfrm4_mode_beet.c b/net/ipv4/xfrm4_mode_beet.c index 6341818..e3db3f9 100644 --- a/net/ipv4/xfrm4_mode_beet.c +++ b/net/ipv4/xfrm4_mode_beet.c @@ -110,10 +110,7 @@ static int xfrm4_beet_input(struct xfrm_state *x, struct sk_buff *skb) skb_push(skb, sizeof(*iph)); skb_reset_network_header(skb); - - memmove(skb->data - skb->mac_len, skb_mac_header(skb), - skb->mac_len); - skb_set_mac_header(skb, -skb->mac_len); + skb_mac_header_rebuild(skb); xfrm4_beet_make_header(skb); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 534972e..ed4bf11 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -66,7 +66,6 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { - const unsigned char *old_mac; int err = -EINVAL; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPIP) @@ -84,10 +83,9 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 273f48d..5605f9d 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -214,6 +214,7 @@ lookup_protocol: inet->mc_ttl = 1; inet->mc_index = 0; inet->mc_list = NULL; + inet->rcv_tos = 0; if (ipv4_config.no_pmtu_disc) inet->pmtudisc = IP_PMTUDISC_DONT; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 59402b4..db00d27 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -211,35 +211,6 @@ void ipv6_sock_ac_close(struct sock *sk) rcu_read_unlock(); } -#if 0 -/* The function is not used, which is funny. Apparently, author - * supposed to use it to filter out datagrams inside udp/raw but forgot. - * - * It is OK, anycasts are not special comparing to delivery to unicasts. - */ - -int inet6_ac_check(struct sock *sk, struct in6_addr *addr, int ifindex) -{ - struct ipv6_ac_socklist *pac; - struct ipv6_pinfo *np = inet6_sk(sk); - int found; - - found = 0; - read_lock(&ipv6_sk_ac_lock); - for (pac=np->ipv6_ac_list; pac; pac=pac->acl_next) { - if (ifindex && pac->acl_ifindex != ifindex) - continue; - found = ipv6_addr_equal(&pac->acl_addr, addr); - if (found) - break; - } - read_unlock(&ipv6_sk_ac_lock); - - return found; -} - -#endif - static void aca_put(struct ifacaddr6 *ac) { if (atomic_dec_and_test(&ac->aca_refcnt)) { diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 251e7cd..76832c8 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -485,7 +485,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) } if (np->rxopt.bits.rxtclass) { - int tclass = (ntohl(*(__be32 *)ipv6_hdr(skb)) >> 20) & 0xff; + int tclass = ipv6_tclass(ipv6_hdr(skb)); put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 01d46bf..af88934 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -468,6 +468,8 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) @@ -553,6 +555,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb) if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; err = ip6_dst_lookup(sk, &dst, &fl6); if (err) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b82bcde..5b27fbc 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1552,11 +1552,20 @@ static int fib6_age(struct rt6_info *rt, void *arg) time_after_eq(now, rt->dst.lastuse + gc_args.timeout)) { RT6_TRACE("aging clone %p\n", rt); return -1; - } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(dst_get_neighbour_noref_raw(&rt->dst)->flags & NTF_ROUTER))) { - RT6_TRACE("purging route %p via non-router but gateway\n", - rt); - return -1; + } else if (rt->rt6i_flags & RTF_GATEWAY) { + struct neighbour *neigh; + __u8 neigh_flags = 0; + + neigh = dst_neigh_lookup(&rt->dst, &rt->rt6i_gateway); + if (neigh) { + neigh_flags = neigh->flags; + neigh_release(neigh); + } + if (neigh_flags & NTF_ROUTER) { + RT6_TRACE("purging route %p via non-router but gateway\n", + rt); + return -1; + } } gc_args.more++; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d97e071..7a98fc2 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -388,7 +388,6 @@ int ip6_forward(struct sk_buff *skb) struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); - struct neighbour *n; u32 mtu; if (net->ipv6.devconf_all->forwarding == 0) @@ -463,8 +462,7 @@ int ip6_forward(struct sk_buff *skb) send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - n = dst_get_neighbour_noref(dst); - if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) { + if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; @@ -474,8 +472,8 @@ int ip6_forward(struct sk_buff *skb) */ rt = (struct rt6_info *) dst; - if ((rt->rt6i_flags & RTF_GATEWAY)) - target = (struct in6_addr*)&n->primary_key; + if (rt->rt6i_flags & RTF_GATEWAY) + target = &rt->rt6i_gateway; else target = &hdr->daddr; @@ -486,7 +484,7 @@ int ip6_forward(struct sk_buff *skb) and by source (inside ndisc_send_redirect) */ if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) - ndisc_send_redirect(skb, n, target); + ndisc_send_redirect(skb, target); } else { int addrtype = ipv6_addr_type(&hdr->saddr); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index c7e95c8..5aa3981 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1926,8 +1926,10 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, }; dst = ip6_route_output(net, NULL, &fl6); - if (!dst) + if (dst->error) { + dst_release(dst); goto out_free; + } skb_dst_drop(skb); skb_dst_set(skb, dst); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 18a2719..63dd1f8 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -516,6 +516,36 @@ done: retv = 0; break; + case IPV6_UNICAST_IF: + { + struct net_device *dev = NULL; + int ifindex; + + if (optlen != sizeof(int)) + goto e_inval; + + ifindex = (__force int)ntohl((__force __be32)val); + if (ifindex == 0) { + np->ucast_oif = 0; + retv = 0; + break; + } + + dev = dev_get_by_index(net, ifindex); + retv = -EADDRNOTAVAIL; + if (!dev) + break; + dev_put(dev); + + retv = -EINVAL; + if (sk->sk_bound_dev_if) + break; + + np->ucast_oif = ifindex; + retv = 0; + break; + } + case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) break; @@ -987,6 +1017,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, int hlim = np->mcast_hops; put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim); } + if (np->rxopt.bits.rxtclass) { + int tclass = np->rcv_tclass; + put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass); + } if (np->rxopt.bits.rxoinfo) { struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : @@ -1160,6 +1194,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_UNICAST_IF: + val = (__force int)htonl((__u32) np->ucast_oif); + break; + case IPV6_MTU_DISCOVER: val = np->pmtudisc; break; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d8f02ef..3dcdb81 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1223,11 +1223,17 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); - if (rt) - neigh = dst_get_neighbour_noref(&rt->dst); - + if (rt) { + neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + if (!neigh) { + ND_PRINTK0(KERN_ERR + "ICMPv6 RA: %s() got default router without neighbour.\n", + __func__); + dst_release(&rt->dst); + return; + } + } if (rt && lifetime == 0) { - neigh_clone(neigh); ip6_del_rt(rt); rt = NULL; } @@ -1244,7 +1250,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = dst_get_neighbour_noref(&rt->dst); + neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (neigh == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() got default router without neighbour.\n", @@ -1411,7 +1417,7 @@ skip_routeinfo: out: if (rt) dst_release(&rt->dst); - else if (neigh) + if (neigh) neigh_release(neigh); } @@ -1506,8 +1512,7 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) } } -void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, - const struct in6_addr *target) +void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); @@ -1545,9 +1550,10 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return; - + } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; @@ -1565,6 +1571,13 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, goto release; if (dev->addr_len) { + struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); + if (!neigh) { + ND_PRINTK2(KERN_WARNING + "ICMPv6 Redirect: no neigh for target address\n"); + goto release; + } + read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); @@ -1573,6 +1586,8 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, len += ndisc_opt_addr_space(dev); } else read_unlock_bh(&neigh->lock); + + neigh_release(neigh); } rd_len = min_t(unsigned int, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index d02f7e4..5bddea7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -856,6 +856,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; + else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index b69fae7..9447bd6 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -336,12 +336,11 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } found: - /* RFC5722, Section 4: - * When reassembling an IPv6 datagram, if + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if * one or more its constituent fragments is determined to be an * overlapping fragment, the entire datagram (and any constituent - * fragments, including those not yet received) MUST be silently - * discarded. + * fragments) MUST be silently discarded. */ /* Check for overlap with preceding fragment. */ diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8c2e3ab..92be12b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -121,9 +121,22 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } +static inline const void *choose_neigh_daddr(struct rt6_info *rt, const void *daddr) +{ + struct in6_addr *p = &rt->rt6i_gateway; + + if (!ipv6_addr_any(p)) + return (const void *) p; + return daddr; +} + static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr) { - struct neighbour *n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); + struct rt6_info *rt = (struct rt6_info *) dst; + struct neighbour *n; + + daddr = choose_neigh_daddr(rt, daddr); + n = __ipv6_neigh_lookup(&nd_tbl, dst->dev, daddr); if (n) return n; return neigh_create(&nd_tbl, daddr, dst->dev); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 133768e..c4ffd17 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -680,9 +680,10 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; + bool do_tx_error = false; if (skb_dst(skb)) - neigh = dst_get_neighbour_noref(skb_dst(skb)); + neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { if (net_ratelimit()) @@ -697,6 +698,10 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, ipv6_addr_is_isatap(addr6)) dst = addr6->s6_addr32[3]; else + do_tx_error = true; + + neigh_release(neigh); + if (do_tx_error) goto tx_error; } @@ -705,9 +710,10 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, if (!dst) { struct neighbour *neigh = NULL; + bool do_tx_error = false; if (skb_dst(skb)) - neigh = dst_get_neighbour_noref(skb_dst(skb)); + neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (neigh == NULL) { if (net_ratelimit()) @@ -723,10 +729,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, addr_type = ipv6_addr_type(addr6); } - if ((addr_type & IPV6_ADDR_COMPATv4) == 0) - goto tx_error_icmp; + if ((addr_type & IPV6_ADDR_COMPATv4) != 0) + dst = addr6->s6_addr32[3]; + else + do_tx_error = true; - dst = addr6->s6_addr32[3]; + neigh_release(neigh); + if (do_tx_error) + goto tx_error; } rt = ip_route_output_ports(dev_net(dev), &fl4, NULL, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3edd05a..12c6ece 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -540,19 +540,7 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, const struct in6_addr *addr) { - struct tcp_sock *tp = tcp_sk(sk); - int i; - - BUG_ON(tp == NULL); - - if (!tp->md5sig_info || !tp->md5sig_info->entries6) - return NULL; - - for (i = 0; i < tp->md5sig_info->entries6; i++) { - if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, addr)) - return &tp->md5sig_info->keys6[i].base; - } - return NULL; + return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); } static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, @@ -567,136 +555,11 @@ static struct tcp_md5sig_key *tcp_v6_reqsk_md5_lookup(struct sock *sk, return tcp_v6_md5_do_lookup(sk, &inet6_rsk(req)->rmt_addr); } -static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, - char *newkey, u8 newkeylen) -{ - /* Add key to the list */ - struct tcp_md5sig_key *key; - struct tcp_sock *tp = tcp_sk(sk); - struct tcp6_md5sig_key *keys; - - key = tcp_v6_md5_do_lookup(sk, peer); - if (key) { - /* modify existing entry - just update that one */ - kfree(key->key); - key->key = newkey; - key->keylen = newkeylen; - } else { - /* reallocate new list if current one is full. */ - if (!tp->md5sig_info) { - tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info), GFP_ATOMIC); - if (!tp->md5sig_info) { - kfree(newkey); - return -ENOMEM; - } - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } - if (tp->md5sig_info->entries6 == 0 && - tcp_alloc_md5sig_pool(sk) == NULL) { - kfree(newkey); - return -ENOMEM; - } - if (tp->md5sig_info->alloced6 == tp->md5sig_info->entries6) { - keys = kmalloc((sizeof (tp->md5sig_info->keys6[0]) * - (tp->md5sig_info->entries6 + 1)), GFP_ATOMIC); - - if (!keys) { - kfree(newkey); - if (tp->md5sig_info->entries6 == 0) - tcp_free_md5sig_pool(); - return -ENOMEM; - } - - if (tp->md5sig_info->entries6) - memmove(keys, tp->md5sig_info->keys6, - (sizeof (tp->md5sig_info->keys6[0]) * - tp->md5sig_info->entries6)); - - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = keys; - tp->md5sig_info->alloced6++; - } - - tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer; - tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; - tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; - - tp->md5sig_info->entries6++; - } - return 0; -} - -static int tcp_v6_md5_add_func(struct sock *sk, struct sock *addr_sk, - u8 *newkey, __u8 newkeylen) -{ - return tcp_v6_md5_do_add(sk, &inet6_sk(addr_sk)->daddr, - newkey, newkeylen); -} - -static int tcp_v6_md5_do_del(struct sock *sk, const struct in6_addr *peer) -{ - struct tcp_sock *tp = tcp_sk(sk); - int i; - - for (i = 0; i < tp->md5sig_info->entries6; i++) { - if (ipv6_addr_equal(&tp->md5sig_info->keys6[i].addr, peer)) { - /* Free the key */ - kfree(tp->md5sig_info->keys6[i].base.key); - tp->md5sig_info->entries6--; - - if (tp->md5sig_info->entries6 == 0) { - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = NULL; - tp->md5sig_info->alloced6 = 0; - tcp_free_md5sig_pool(); - } else { - /* shrink the database */ - if (tp->md5sig_info->entries6 != i) - memmove(&tp->md5sig_info->keys6[i], - &tp->md5sig_info->keys6[i+1], - (tp->md5sig_info->entries6 - i) - * sizeof (tp->md5sig_info->keys6[0])); - } - return 0; - } - } - return -ENOENT; -} - -static void tcp_v6_clear_md5_list (struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - int i; - - if (tp->md5sig_info->entries6) { - for (i = 0; i < tp->md5sig_info->entries6; i++) - kfree(tp->md5sig_info->keys6[i].base.key); - tp->md5sig_info->entries6 = 0; - tcp_free_md5sig_pool(); - } - - kfree(tp->md5sig_info->keys6); - tp->md5sig_info->keys6 = NULL; - tp->md5sig_info->alloced6 = 0; - - if (tp->md5sig_info->entries4) { - for (i = 0; i < tp->md5sig_info->entries4; i++) - kfree(tp->md5sig_info->keys4[i].base.key); - tp->md5sig_info->entries4 = 0; - tcp_free_md5sig_pool(); - } - - kfree(tp->md5sig_info->keys4); - tp->md5sig_info->keys4 = NULL; - tp->md5sig_info->alloced4 = 0; -} - static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr; - u8 *newkey; if (optlen < sizeof(cmd)) return -EINVAL; @@ -708,36 +571,22 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, return -EINVAL; if (!cmd.tcpm_keylen) { - if (!tcp_sk(sk)->md5sig_info) - return -ENOENT; if (ipv6_addr_v4mapped(&sin6->sin6_addr)) - return tcp_v4_md5_do_del(sk, sin6->sin6_addr.s6_addr32[3]); - return tcp_v6_md5_do_del(sk, &sin6->sin6_addr); + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET); + return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6); } if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - if (!tcp_sk(sk)->md5sig_info) { - struct tcp_sock *tp = tcp_sk(sk); - struct tcp_md5sig_info *p; - - p = kzalloc(sizeof(struct tcp_md5sig_info), GFP_KERNEL); - if (!p) - return -ENOMEM; + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3], + AF_INET, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - tp->md5sig_info = p; - sk_nocaps_add(sk, NETIF_F_GSO_MASK); - } - - newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); - if (!newkey) - return -ENOMEM; - if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { - return tcp_v4_md5_do_add(sk, sin6->sin6_addr.s6_addr32[3], - newkey, cmd.tcpm_keylen); - } - return tcp_v6_md5_do_add(sk, &sin6->sin6_addr, newkey, cmd.tcpm_keylen); + return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr, + AF_INET6, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, @@ -1074,6 +923,13 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; struct tcp_md5sig_key *key = NULL; +#ifdef CONFIG_TCP_MD5SIG + const __u8 *hash_location = NULL; + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + unsigned char newhash[16]; + int genhash; + struct sock *sk1 = NULL; +#endif if (th->rst) return; @@ -1082,8 +938,32 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) return; #ifdef CONFIG_TCP_MD5SIG - if (sk) - key = tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr); + hash_location = tcp_parse_md5sig_option(th); + if (!sk && hash_location) { + /* + * active side is lost. Try to find listening socket through + * source port, and then find md5 key through listening socket. + * we are not loose security here: + * Incoming packet is checked with md5 hash with finding key, + * no RST generated if md5 hash doesn't match. + */ + sk1 = inet6_lookup_listener(dev_net(skb_dst(skb)->dev), + &tcp_hashinfo, &ipv6h->daddr, + ntohs(th->source), inet6_iif(skb)); + if (!sk1) + return; + + rcu_read_lock(); + key = tcp_v6_md5_do_lookup(sk1, &ipv6h->saddr); + if (!key) + goto release_sk1; + + genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, NULL, skb); + if (genhash || memcmp(hash_location, newhash, 16) != 0) + goto release_sk1; + } else { + key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; + } #endif if (th->ack) @@ -1093,6 +973,14 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) (th->doff << 2); tcp_v6_send_response(skb, seq, ack_seq, 0, 0, key, 1, 0); + +#ifdef CONFIG_TCP_MD5SIG +release_sk1: + if (sk1) { + rcu_read_unlock(); + sock_put(sk1); + } +#endif } static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts, @@ -1394,6 +1282,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); /* * No need to charge this sock to the relevant IPv6 refcnt debug socks count @@ -1472,6 +1361,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newnp->opt = NULL; newnp->mcast_oif = inet6_iif(skb); newnp->mcast_hops = ipv6_hdr(skb)->hop_limit; + newnp->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); /* Clone native IPv6 options from listening socket (if any) @@ -1510,10 +1400,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); - if (newkey != NULL) - tcp_v6_md5_do_add(newsk, &newnp->daddr, - newkey, key->keylen); + tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newnp->daddr, + AF_INET6, key->key, key->keylen, GFP_ATOMIC); } #endif @@ -1676,6 +1564,8 @@ ipv6_pktoptions: np->mcast_oif = inet6_iif(opt_skb); if (np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) np->mcast_hops = ipv6_hdr(opt_skb)->hop_limit; + if (np->rxopt.bits.rxtclass) + np->rcv_tclass = ipv6_tclass(ipv6_hdr(skb)); if (ipv6_opt_accepted(sk, opt_skb)) { skb_set_owner_r(opt_skb, sk); opt_skb = xchg(&np->pktoptions, opt_skb); @@ -1898,7 +1788,6 @@ static const struct inet_connection_sock_af_ops ipv6_specific = { static const struct tcp_sock_af_ops tcp_sock_ipv6_specific = { .md5_lookup = tcp_v6_md5_lookup, .calc_md5_hash = tcp_v6_md5_hash_skb, - .md5_add = tcp_v6_md5_add_func, .md5_parse = tcp_v6_parse_md5_keys, }; #endif @@ -1930,7 +1819,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = { static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, - .md5_add = tcp_v6_md5_add_func, .md5_parse = tcp_v6_parse_md5_keys, }; #endif @@ -2004,11 +1892,6 @@ static int tcp_v6_init_sock(struct sock *sk) static void tcp_v6_destroy_sock(struct sock *sk) { -#ifdef CONFIG_TCP_MD5SIG - /* Clean up the MD5 key list */ - if (tcp_sk(sk)->md5sig_info) - tcp_v6_clear_md5_list(sk); -#endif tcp_v4_destroy_sock(sk); inet6_destroy_sock(sk); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4f96b5c..37b0699 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -342,7 +342,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct sk_buff *skb; unsigned int ulen, copied; - int peeked; + int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); int is_udp4; @@ -359,7 +359,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); + &peeked, &off, &err); if (!skb) goto out; @@ -1130,7 +1130,8 @@ do_udp_sendmsg: if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) { fl6.flowi6_oif = np->mcast_oif; connected = 0; - } + } else if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index a81ce94..9949a35 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -80,7 +80,6 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) { struct ipv6hdr *ip6h; - const unsigned char *old_mac; int size = sizeof(struct ipv6hdr); int err; @@ -90,10 +89,7 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) __skb_push(skb, size); skb_reset_network_header(skb); - - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); + skb_mac_header_rebuild(skb); xfrm6_beet_make_header(skb); diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 261e6e6..9f2095b 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -63,7 +63,6 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) { int err = -EINVAL; - const unsigned char *old_mac; if (XFRM_MODE_SKB_CB(skb)->protocol != IPPROTO_IPV6) goto out; @@ -80,10 +79,9 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); - old_mac = skb_mac_header(skb); - skb_set_mac_header(skb, -skb->mac_len); - memmove(skb_mac_header(skb), old_mac, skb->mac_len); skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + err = 0; out: diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 4eeff89..8755a30 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -146,7 +146,7 @@ static int __xfrm6_output(struct sk_buff *skb) return -EMSGSIZE; } - if ((x && x->props.mode == XFRM_MODE_TUNNEL) && + if (x->props.mode == XFRM_MODE_TUNNEL && ((skb->len > mtu && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index 979ecb2..564eb0b 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -254,7 +254,7 @@ #include <linux/init.h> #include <linux/ppp_defs.h> -#include <linux/if_ppp.h> +#include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <net/irda/irda.h> diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d5c5b8f..98d1f0b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -90,6 +90,7 @@ do { \ static void iucv_sock_kill(struct sock *sk); static void iucv_sock_close(struct sock *sk); +static void iucv_sever_path(struct sock *, int); static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); @@ -130,17 +131,6 @@ static inline void low_nmcpy(unsigned char *dst, char *src) memcpy(&dst[8], src, 8); } -static void iucv_skb_queue_purge(struct sk_buff_head *list) -{ - struct sk_buff *skb; - - while ((skb = skb_dequeue(list)) != NULL) { - if (skb->dev) - dev_put(skb->dev); - kfree_skb(skb); - } -} - static int afiucv_pm_prepare(struct device *dev) { #ifdef CONFIG_PM_DEBUG @@ -175,17 +165,13 @@ static int afiucv_pm_freeze(struct device *dev) read_lock(&iucv_sk_list.lock); sk_for_each(sk, node, &iucv_sk_list.head) { iucv = iucv_sk(sk); - iucv_skb_queue_purge(&iucv->send_skb_q); + skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); switch (sk->sk_state) { case IUCV_DISCONN: case IUCV_CLOSING: case IUCV_CONNECTED: - if (iucv->path) { - err = pr_iucv->path_sever(iucv->path, NULL); - iucv_path_free(iucv->path); - iucv->path = NULL; - } + iucv_sever_path(sk, 0); break; case IUCV_OPEN: case IUCV_BOUND: @@ -194,6 +180,8 @@ static int afiucv_pm_freeze(struct device *dev) default: break; } + skb_queue_purge(&iucv->send_skb_q); + skb_queue_purge(&iucv->backlog_skb_q); } read_unlock(&iucv_sk_list.lock); return err; @@ -338,7 +326,6 @@ static void iucv_sock_wake_msglim(struct sock *sk) static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, struct sk_buff *skb, u8 flags) { - struct net *net = sock_net(sock); struct iucv_sock *iucv = iucv_sk(sock); struct af_iucv_trans_hdr *phs_hdr; struct sk_buff *nskb; @@ -375,10 +362,10 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, if (imsg) memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); - skb->dev = dev_get_by_index(net, sock->sk_bound_dev_if); + skb->dev = iucv->hs_dev; if (!skb->dev) return -ENODEV; - if (!(skb->dev->flags & IFF_UP)) + if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) return -ENETDOWN; if (skb->len > skb->dev->mtu) { if (sock->sk_type == SOCK_SEQPACKET) @@ -393,15 +380,14 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, return -ENOMEM; skb_queue_tail(&iucv->send_skb_q, nskb); err = dev_queue_xmit(skb); - if (err) { + if (net_xmit_eval(err)) { skb_unlink(nskb, &iucv->send_skb_q); - dev_put(nskb->dev); kfree_skb(nskb); } else { atomic_sub(confirm_recv, &iucv->msg_recv); WARN_ON(atomic_read(&iucv->msg_recv) < 0); } - return err; + return net_xmit_eval(err); } static struct sock *__iucv_get_sock_by_name(char *nm) @@ -447,13 +433,33 @@ static void iucv_sock_kill(struct sock *sk) sock_put(sk); } +/* Terminate an IUCV path */ +static void iucv_sever_path(struct sock *sk, int with_user_data) +{ + unsigned char user_data[16]; + struct iucv_sock *iucv = iucv_sk(sk); + struct iucv_path *path = iucv->path; + + if (iucv->path) { + iucv->path = NULL; + if (with_user_data) { + low_nmcpy(user_data, iucv->src_name); + high_nmcpy(user_data, iucv->dst_name); + ASCEBC(user_data, sizeof(user_data)); + pr_iucv->path_sever(path, user_data); + } else + pr_iucv->path_sever(path, NULL); + iucv_path_free(path); + } +} + /* Close an IUCV socket */ static void iucv_sock_close(struct sock *sk) { - unsigned char user_data[16]; struct iucv_sock *iucv = iucv_sk(sk); unsigned long timeo; - int err, blen; + int err = 0; + int blen; struct sk_buff *skb; lock_sock(sk); @@ -480,7 +486,7 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_CLOSING; sk->sk_state_change(sk); - if (!skb_queue_empty(&iucv->send_skb_q)) { + if (!err && !skb_queue_empty(&iucv->send_skb_q)) { if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) timeo = sk->sk_lingertime; else @@ -494,25 +500,20 @@ static void iucv_sock_close(struct sock *sk) sk->sk_state = IUCV_CLOSED; sk->sk_state_change(sk); - if (iucv->path) { - low_nmcpy(user_data, iucv->src_name); - high_nmcpy(user_data, iucv->dst_name); - ASCEBC(user_data, sizeof(user_data)); - pr_iucv->path_sever(iucv->path, user_data); - iucv_path_free(iucv->path); - iucv->path = NULL; - } - sk->sk_err = ECONNRESET; sk->sk_state_change(sk); - iucv_skb_queue_purge(&iucv->send_skb_q); + skb_queue_purge(&iucv->send_skb_q); skb_queue_purge(&iucv->backlog_skb_q); - break; - default: - /* nothing to do here */ - break; + default: /* fall through */ + iucv_sever_path(sk, 1); + } + + if (iucv->hs_dev) { + dev_put(iucv->hs_dev); + iucv->hs_dev = NULL; + sk->sk_bound_dev_if = 0; } /* mark socket for deletion by iucv_sock_kill() */ @@ -706,7 +707,6 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, goto done_unlock; /* Bind the socket */ - if (pr_iucv) if (!memcmp(sa->siucv_user_id, iucv_userid, 8)) goto vm_bind; /* VM IUCV transport */ @@ -720,6 +720,8 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, memcpy(iucv->src_name, sa->siucv_name, 8); memcpy(iucv->src_user_id, sa->siucv_user_id, 8); sk->sk_bound_dev_if = dev->ifindex; + iucv->hs_dev = dev; + dev_hold(dev); sk->sk_state = IUCV_BOUND; iucv->transport = AF_IUCV_TRANS_HIPER; if (!iucv->msglimit) @@ -894,11 +896,8 @@ static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, if (sk->sk_state == IUCV_DISCONN || sk->sk_state == IUCV_CLOSED) err = -ECONNREFUSED; - if (err && iucv->transport == AF_IUCV_TRANS_IUCV) { - pr_iucv->path_sever(iucv->path, NULL); - iucv_path_free(iucv->path); - iucv->path = NULL; - } + if (err && iucv->transport == AF_IUCV_TRANS_IUCV) + iucv_sever_path(sk, 0); done: release_sock(sk); @@ -1124,8 +1123,10 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, noblock, &err); else skb = sock_alloc_send_skb(sk, len, noblock, &err); - if (!skb) + if (!skb) { + err = -ENOMEM; goto out; + } if (iucv->transport == AF_IUCV_TRANS_HIPER) skb_reserve(skb, sizeof(struct af_iucv_trans_hdr) + ETH_HLEN); if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) { @@ -1148,6 +1149,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_sent); err = afiucv_hs_send(&txmsg, sk, skb, 0); @@ -1202,8 +1204,6 @@ release: return len; fail: - if (skb->dev) - dev_put(skb->dev); kfree_skb(skb); out: release_sock(sk); @@ -1396,7 +1396,14 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, } kfree_skb(skb); - atomic_inc(&iucv->msg_recv); + if (iucv->transport == AF_IUCV_TRANS_HIPER) { + atomic_inc(&iucv->msg_recv); + if (atomic_read(&iucv->msg_recv) > iucv->msglimit) { + WARN_ON(1); + iucv_sock_close(sk); + return -EFAULT; + } + } /* Queue backlog skbs */ spin_lock_bh(&iucv->message_q.lock); @@ -1486,7 +1493,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == IUCV_DISCONN) mask |= POLLIN; - if (sock_writeable(sk)) + if (sock_writeable(sk) && iucv_below_msglim(sk)) mask |= POLLOUT | POLLWRNORM | POLLWRBAND; else set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -1565,13 +1572,6 @@ static int iucv_sock_release(struct socket *sock) iucv_sock_close(sk); - /* Unregister with IUCV base support */ - if (iucv_sk(sk)->path) { - pr_iucv->path_sever(iucv_sk(sk)->path, NULL); - iucv_path_free(iucv_sk(sk)->path); - iucv_sk(sk)->path = NULL; - } - sock_orphan(sk); iucv_sock_kill(sk); return err; @@ -1633,7 +1633,8 @@ static int iucv_sock_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct iucv_sock *iucv = iucv_sk(sk); - int val, len; + unsigned int val; + int len; if (level != SOL_IUCV) return -ENOPROTOOPT; @@ -1656,6 +1657,13 @@ static int iucv_sock_getsockopt(struct socket *sock, int level, int optname, : iucv->msglimit; /* default */ release_sock(sk); break; + case SO_MSGSIZE: + if (sk->sk_state == IUCV_OPEN) + return -EBADFD; + val = (iucv->hs_dev) ? iucv->hs_dev->mtu - + sizeof(struct af_iucv_trans_hdr) - ETH_HLEN : + 0x7fffffff; + break; default: return -ENOPROTOOPT; } @@ -1750,8 +1758,7 @@ static int iucv_callback_connreq(struct iucv_path *path, path->msglim = iucv->msglimit; err = pr_iucv->path_accept(path, &af_iucv_handler, nuser_data, nsk); if (err) { - err = pr_iucv->path_sever(path, user_data); - iucv_path_free(path); + iucv_sever_path(nsk, 1); iucv_sock_kill(nsk); goto fail; } @@ -1828,6 +1835,7 @@ static void iucv_callback_txdone(struct iucv_path *path, struct sk_buff *list_skb = list->next; unsigned long flags; + bh_lock_sock(sk); if (!skb_queue_empty(list)) { spin_lock_irqsave(&list->lock, flags); @@ -1849,7 +1857,6 @@ static void iucv_callback_txdone(struct iucv_path *path, iucv_sock_wake_msglim(sk); } } - BUG_ON(!this); if (sk->sk_state == IUCV_CLOSING) { if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { @@ -1857,6 +1864,7 @@ static void iucv_callback_txdone(struct iucv_path *path, sk->sk_state_change(sk); } } + bh_unlock_sock(sk); } @@ -1864,9 +1872,15 @@ static void iucv_callback_connrej(struct iucv_path *path, u8 ipuser[16]) { struct sock *sk = path->private; + if (sk->sk_state == IUCV_CLOSED) + return; + + bh_lock_sock(sk); + iucv_sever_path(sk, 1); sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); + bh_unlock_sock(sk); } /* called if the other communication side shuts down its RECV direction; @@ -1954,6 +1968,8 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb) memcpy(niucv->src_name, iucv->src_name, 8); memcpy(niucv->src_user_id, iucv->src_user_id, 8); nsk->sk_bound_dev_if = sk->sk_bound_dev_if; + niucv->hs_dev = iucv->hs_dev; + dev_hold(niucv->hs_dev); afiucv_swap_src_dest(skb); trans_hdr->flags = AF_IUCV_FLAG_SYN | AF_IUCV_FLAG_ACK; trans_hdr->window = niucv->msglimit; @@ -2022,12 +2038,15 @@ static int afiucv_hs_callback_fin(struct sock *sk, struct sk_buff *skb) struct iucv_sock *iucv = iucv_sk(sk); /* other end of connection closed */ - if (iucv) { - bh_lock_sock(sk); + if (!iucv) + goto out; + bh_lock_sock(sk); + if (sk->sk_state == IUCV_CONNECTED) { sk->sk_state = IUCV_DISCONN; sk->sk_state_change(sk); - bh_unlock_sock(sk); } + bh_unlock_sock(sk); +out: kfree_skb(skb); return NET_RX_SUCCESS; } @@ -2172,11 +2191,11 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, break; case (AF_IUCV_FLAG_WIN): err = afiucv_hs_callback_win(sk, skb); - if (skb->len > sizeof(struct af_iucv_trans_hdr)) - err = afiucv_hs_callback_rx(sk, skb); - else - kfree(skb); - break; + if (skb->len == sizeof(struct af_iucv_trans_hdr)) { + kfree_skb(skb); + break; + } + /* fall through */ case 0: /* plain data frame */ memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class, @@ -2202,65 +2221,64 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb, struct iucv_sock *iucv = NULL; struct sk_buff_head *list; struct sk_buff *list_skb; - struct sk_buff *this = NULL; + struct sk_buff *nskb; unsigned long flags; struct hlist_node *node; - read_lock(&iucv_sk_list.lock); + read_lock_irqsave(&iucv_sk_list.lock, flags); sk_for_each(sk, node, &iucv_sk_list.head) if (sk == isk) { iucv = iucv_sk(sk); break; } - read_unlock(&iucv_sk_list.lock); + read_unlock_irqrestore(&iucv_sk_list.lock, flags); - if (!iucv) + if (!iucv || sock_flag(sk, SOCK_ZAPPED)) return; - bh_lock_sock(sk); list = &iucv->send_skb_q; - list_skb = list->next; + spin_lock_irqsave(&list->lock, flags); if (skb_queue_empty(list)) goto out_unlock; - - spin_lock_irqsave(&list->lock, flags); + list_skb = list->next; + nskb = list_skb->next; while (list_skb != (struct sk_buff *)list) { if (skb_shinfo(list_skb) == skb_shinfo(skb)) { - this = list_skb; switch (n) { case TX_NOTIFY_OK: - __skb_unlink(this, list); + __skb_unlink(list_skb, list); + kfree_skb(list_skb); iucv_sock_wake_msglim(sk); - dev_put(this->dev); - kfree_skb(this); break; case TX_NOTIFY_PENDING: atomic_inc(&iucv->pendings); break; case TX_NOTIFY_DELAYED_OK: - __skb_unlink(this, list); + __skb_unlink(list_skb, list); atomic_dec(&iucv->pendings); if (atomic_read(&iucv->pendings) <= 0) iucv_sock_wake_msglim(sk); - dev_put(this->dev); - kfree_skb(this); + kfree_skb(list_skb); break; case TX_NOTIFY_UNREACHABLE: case TX_NOTIFY_DELAYED_UNREACHABLE: case TX_NOTIFY_TPQFULL: /* not yet used */ case TX_NOTIFY_GENERALERROR: case TX_NOTIFY_DELAYED_GENERALERROR: - __skb_unlink(this, list); - dev_put(this->dev); - kfree_skb(this); - sk->sk_state = IUCV_DISCONN; - sk->sk_state_change(sk); + __skb_unlink(list_skb, list); + kfree_skb(list_skb); + if (sk->sk_state == IUCV_CONNECTED) { + sk->sk_state = IUCV_DISCONN; + sk->sk_state_change(sk); + } break; } break; } - list_skb = list_skb->next; + list_skb = nskb; + nskb = nskb->next; } +out_unlock: spin_unlock_irqrestore(&list->lock, flags); if (sk->sk_state == IUCV_CLOSING) { @@ -2270,8 +2288,6 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *skb, } } -out_unlock: - bh_unlock_sock(sk); } static const struct proto_ops iucv_sock_ops = { .family = PF_IUCV, diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index d2726a7..63fe5f3 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -64,7 +64,7 @@ static int l2tp_eth_dev_init(struct net_device *dev) struct l2tp_eth *priv = netdev_priv(dev); priv->dev = dev; - random_ether_addr(dev->dev_addr); + eth_hw_addr_random(dev); memset(&dev->broadcast[0], 0xff, 6); return 0; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 8a90d75..96bc7a6 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -82,7 +82,7 @@ #include <net/sock.h> #include <linux/ppp_channel.h> #include <linux/ppp_defs.h> -#include <linux/if_ppp.h> +#include <linux/ppp-ioctl.h> #include <linux/file.h> #include <linux/hash.h> #include <linux/sort.h> diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 32dbf0f..e7f90e7 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1162,9 +1162,13 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb, if (unlikely(protocol_failed(attr))) return -IPSET_ERR_PROTOCOL; - return netlink_dump_start(ctnl, skb, nlh, - ip_set_dump_start, - ip_set_dump_done, 0); + { + struct netlink_dump_control c = { + .dump = ip_set_dump_start, + .done = ip_set_dump_done, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); + } } /* Add, del and test */ diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 611c335..2555816 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -232,6 +232,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, __be16 dport = 0; /* destination port to forward */ unsigned int flags; struct ip_vs_conn_param param; + const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ @@ -267,7 +268,6 @@ ip_vs_sched_persist(struct ip_vs_service *svc, { int protocol = iph.protocol; const union nf_inet_addr *vaddr = &iph.daddr; - const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; if (dst_port == svc->port) { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 76613f5..ed86a3b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -404,19 +404,49 @@ static void __nf_conntrack_hash_insert(struct nf_conn *ct, &net->ct.hash[repl_hash]); } -void nf_conntrack_hash_insert(struct nf_conn *ct) +int +nf_conntrack_hash_check_insert(struct nf_conn *ct) { struct net *net = nf_ct_net(ct); unsigned int hash, repl_hash; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; u16 zone; zone = nf_ct_zone(ct); - hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - repl_hash = hash_conntrack(net, zone, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + repl_hash = hash_conntrack(net, zone, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + spin_lock_bh(&nf_conntrack_lock); + /* See if there's one in the list already, including reverse */ + hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode) + if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple, + &h->tuple) && + zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h))) + goto out; + + add_timer(&ct->timeout); + nf_conntrack_get(&ct->ct_general); __nf_conntrack_hash_insert(ct, hash, repl_hash); + NF_CT_STAT_INC(net, insert); + spin_unlock_bh(&nf_conntrack_lock); + + return 0; + +out: + NF_CT_STAT_INC(net, insert_failed); + spin_unlock_bh(&nf_conntrack_lock); + return -EEXIST; } -EXPORT_SYMBOL_GPL(nf_conntrack_hash_insert); +EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert); /* Confirm a connection given skb; places it in hash table */ int diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 9307b03..04fb409 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -691,9 +691,18 @@ static int ctnetlink_done(struct netlink_callback *cb) { if (cb->args[1]) nf_ct_put((struct nf_conn *)cb->args[1]); + if (cb->data) + kfree(cb->data); return 0; } +struct ctnetlink_dump_filter { + struct { + u_int32_t val; + u_int32_t mask; + } mark; +}; + static int ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) { @@ -703,7 +712,9 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_nulls_node *n; struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); u_int8_t l3proto = nfmsg->nfgen_family; - +#ifdef CONFIG_NF_CONNTRACK_MARK + const struct ctnetlink_dump_filter *filter = cb->data; +#endif spin_lock_bh(&nf_conntrack_lock); last = (struct nf_conn *)cb->args[1]; for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) { @@ -723,6 +734,12 @@ restart: continue; cb->args[1] = 0; } +#ifdef CONFIG_NF_CONNTRACK_MARK + if (filter && !((ct->mark & filter->mark.mask) == + filter->mark.val)) { + continue; + } +#endif if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE( @@ -894,6 +911,7 @@ static const struct nla_policy ct_nla_policy[CTA_MAX+1] = { [CTA_NAT_DST] = { .type = NLA_NESTED }, [CTA_TUPLE_MASTER] = { .type = NLA_NESTED }, [CTA_ZONE] = { .type = NLA_U16 }, + [CTA_MARK_MASK] = { .type = NLA_U32 }, }; static int @@ -977,9 +995,28 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, u16 zone; int err; - if (nlh->nlmsg_flags & NLM_F_DUMP) - return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, - ctnetlink_done, 0); + if (nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = ctnetlink_dump_table, + .done = ctnetlink_done, + }; +#ifdef CONFIG_NF_CONNTRACK_MARK + if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) { + struct ctnetlink_dump_filter *filter; + + filter = kzalloc(sizeof(struct ctnetlink_dump_filter), + GFP_ATOMIC); + if (filter == NULL) + return -ENOMEM; + + filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); + filter->mark.mask = + ntohl(nla_get_be32(cda[CTA_MARK_MASK])); + c.data = filter; + } +#endif + return netlink_dump_start(ctnl, skb, nlh, &c); + } err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) @@ -1367,15 +1404,12 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); - spin_unlock_bh(&nf_conntrack_lock); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { - spin_lock_bh(&nf_conntrack_lock); err = -EOPNOTSUPP; goto err1; } - spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), @@ -1468,8 +1502,10 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, if (tstamp) tstamp->start = ktime_to_ns(ktime_get_real()); - add_timer(&ct->timeout); - nf_conntrack_hash_insert(ct); + err = nf_conntrack_hash_check_insert(ct); + if (err < 0) + goto err2; + rcu_read_unlock(); return ct; @@ -1490,6 +1526,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, struct nf_conntrack_tuple otuple, rtuple; struct nf_conntrack_tuple_hash *h = NULL; struct nfgenmsg *nfmsg = nlmsg_data(nlh); + struct nf_conn *ct; u_int8_t u3 = nfmsg->nfgen_family; u16 zone; int err; @@ -1510,27 +1547,22 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, return err; } - spin_lock_bh(&nf_conntrack_lock); if (cda[CTA_TUPLE_ORIG]) - h = __nf_conntrack_find(net, zone, &otuple); + h = nf_conntrack_find_get(net, zone, &otuple); else if (cda[CTA_TUPLE_REPLY]) - h = __nf_conntrack_find(net, zone, &rtuple); + h = nf_conntrack_find_get(net, zone, &rtuple); if (h == NULL) { err = -ENOENT; if (nlh->nlmsg_flags & NLM_F_CREATE) { - struct nf_conn *ct; enum ip_conntrack_events events; ct = ctnetlink_create_conntrack(net, zone, cda, &otuple, &rtuple, u3); - if (IS_ERR(ct)) { - err = PTR_ERR(ct); - goto out_unlock; - } + if (IS_ERR(ct)) + return PTR_ERR(ct); + err = 0; - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); if (test_bit(IPS_EXPECTED_BIT, &ct->status)) events = IPCT_RELATED; else @@ -1545,23 +1577,19 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); + } return err; } /* implicit 'else' */ - /* We manipulate the conntrack inside the global conntrack table lock, - * so there's no need to increase the refcount */ err = -EEXIST; + ct = nf_ct_tuplehash_to_ctrack(h); if (!(nlh->nlmsg_flags & NLM_F_EXCL)) { - struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); - + spin_lock_bh(&nf_conntrack_lock); err = ctnetlink_change_conntrack(ct, cda); + spin_unlock_bh(&nf_conntrack_lock); if (err == 0) { - nf_conntrack_get(&ct->ct_general); - spin_unlock_bh(&nf_conntrack_lock); nf_conntrack_eventmask_report((1 << IPCT_REPLY) | (1 << IPCT_ASSURED) | (1 << IPCT_HELPER) | @@ -1570,15 +1598,10 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_MARK), ct, NETLINK_CB(skb).pid, nlmsg_report(nlh)); - nf_ct_put(ct); - } else - spin_unlock_bh(&nf_conntrack_lock); - - return err; + } } -out_unlock: - spin_unlock_bh(&nf_conntrack_lock); + nf_ct_put(ct); return err; } @@ -1850,9 +1873,11 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, int err; if (nlh->nlmsg_flags & NLM_F_DUMP) { - return netlink_dump_start(ctnl, skb, nlh, - ctnetlink_exp_dump_table, - ctnetlink_exp_done, 0); + struct netlink_dump_control c = { + .dump = ctnetlink_exp_dump_table, + .done = ctnetlink_exp_done, + }; + return netlink_dump_start(ctnl, skb, nlh, &c); } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index b3a7db6..ce60cf0 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -203,6 +203,27 @@ err: return status; } +#ifdef CONFIG_BRIDGE_NETFILTER +/* When called from bridge netfilter, skb->data must point to MAC header + * before calling skb_gso_segment(). Else, original MAC header is lost + * and segmented skbs will be sent to wrong destination. + */ +static void nf_bridge_adjust_skb_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_push(skb, skb->network_header - skb->mac_header); +} + +static void nf_bridge_adjust_segmented_data(struct sk_buff *skb) +{ + if (skb->nf_bridge) + __skb_pull(skb, skb->network_header - skb->mac_header); +} +#else +#define nf_bridge_adjust_skb_data(s) do {} while (0) +#define nf_bridge_adjust_segmented_data(s) do {} while (0) +#endif + int nf_queue(struct sk_buff *skb, struct list_head *elem, u_int8_t pf, unsigned int hook, @@ -212,7 +233,7 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; - int err; + int err = -EINVAL; unsigned int queued; if (!skb_is_gso(skb)) @@ -228,23 +249,25 @@ int nf_queue(struct sk_buff *skb, break; } + nf_bridge_adjust_skb_data(skb); segs = skb_gso_segment(skb, 0); /* Does not use PTR_ERR to limit the number of error codes that can be * returned by nf_queue. For instance, callers rely on -ECANCELED to mean * 'ignore this hook'. */ if (IS_ERR(segs)) - return -EINVAL; - + goto out_err; queued = 0; err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (err == 0) + if (err == 0) { + nf_bridge_adjust_segmented_data(segs); err = __nf_queue(segs, elem, pf, hook, indev, outdev, okfn, queuenum); + } if (err == 0) queued++; else @@ -252,11 +275,12 @@ int nf_queue(struct sk_buff *skb, segs = nskb; } while (segs); - /* also free orig skb if only some segments were queued */ - if (unlikely(err && queued)) - err = 0; - if (err == 0) + if (queued) { kfree_skb(skb); + return 0; + } + out_err: + nf_bridge_adjust_segmented_data(skb); return err; } diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 11ba013..3eb348b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -171,8 +171,10 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, char *acct_name; if (nlh->nlmsg_flags & NLM_F_DUMP) { - return netlink_dump_start(nfnl, skb, nlh, nfnl_acct_dump, - NULL, 0); + struct netlink_dump_control c = { + .dump = nfnl_acct_dump, + }; + return netlink_dump_start(nfnl, skb, nlh, &c); } if (!tb[NFACCT_NAME]) diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3aae66f..4d50579 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -152,9 +152,10 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info) fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) | (iph->flow_lbl[1] << 8) | iph->flow_lbl[2]; dst = ip6_route_output(net, NULL, &fl6); - if (dst == NULL) + if (dst->error) { + dst_release(dst); return false; - + } skb_dst_drop(skb); skb_dst_set(skb, dst); skb->dev = dst->dev; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 629b061..32bb753 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1645,6 +1645,24 @@ static void netlink_destroy_callback(struct netlink_callback *cb) kfree(cb); } +struct nlmsghdr * +__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) +{ + struct nlmsghdr *nlh; + int size = NLMSG_LENGTH(len); + + nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size)); + nlh->nlmsg_type = type; + nlh->nlmsg_len = size; + nlh->nlmsg_flags = flags; + nlh->nlmsg_pid = pid; + nlh->nlmsg_seq = seq; + if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) + memset(NLMSG_DATA(nlh) + len, 0, NLMSG_ALIGN(size) - size); + return nlh; +} +EXPORT_SYMBOL(__nlmsg_put); + /* * It looks a bit ugly. * It would be better to create kernel thread. @@ -1718,10 +1736,7 @@ errout_skb: int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, - int (*dump)(struct sk_buff *skb, - struct netlink_callback *), - int (*done)(struct netlink_callback *), - u16 min_dump_alloc) + struct netlink_dump_control *control) { struct netlink_callback *cb; struct sock *sk; @@ -1732,10 +1747,11 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, if (cb == NULL) return -ENOBUFS; - cb->dump = dump; - cb->done = done; + cb->dump = control->dump; + cb->done = control->done; cb->nlh = nlh; - cb->min_dump_alloc = min_dump_alloc; + cb->data = control->data; + cb->min_dump_alloc = control->min_dump_alloc; atomic_inc(&skb->users); cb->skb = skb; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c29d256..9f40441 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -498,6 +498,37 @@ int genl_unregister_family(struct genl_family *family) } EXPORT_SYMBOL(genl_unregister_family); +/** + * genlmsg_put - Add generic netlink header to netlink message + * @skb: socket buffer holding the message + * @pid: netlink pid the message is addressed to + * @seq: sequence number (usually the one of the sender) + * @family: generic netlink family + * @flags netlink message flags + * @cmd: generic netlink command + * + * Returns pointer to user specific header + */ +void *genlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, + struct genl_family *family, int flags, u8 cmd) +{ + struct nlmsghdr *nlh; + struct genlmsghdr *hdr; + + nlh = nlmsg_put(skb, pid, seq, family->id, GENL_HDRLEN + + family->hdrsize, flags); + if (nlh == NULL) + return NULL; + + hdr = nlmsg_data(nlh); + hdr->cmd = cmd; + hdr->version = family->version; + hdr->reserved = 0; + + return (char *) hdr + GENL_HDRLEN; +} +EXPORT_SYMBOL(genlmsg_put); + static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { struct genl_ops *ops; @@ -532,8 +563,13 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EOPNOTSUPP; genl_unlock(); - err = netlink_dump_start(net->genl_sock, skb, nlh, - ops->dumpit, ops->done, 0); + { + struct netlink_dump_control c = { + .dump = ops->dumpit, + .done = ops->done, + }; + err = netlink_dump_start(net->genl_sock, skb, nlh, &c); + } genl_lock(); return err; } diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 322b8d2..b6b1d7d 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -66,6 +66,7 @@ static int internal_dev_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + dev->addr_assign_type &= ~NET_ADDR_RANDOM; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); return 0; } @@ -145,7 +146,7 @@ static void do_setup(struct net_device *netdev) netdev->vlan_features = netdev->features; netdev->features |= NETIF_F_HW_VLAN_TX; netdev->hw_features = netdev->features & ~NETIF_F_LLTX; - random_ether_addr(netdev->dev_addr); + eth_hw_addr_random(netdev); } static struct vport *internal_dev_create(const struct vport_parms *parms) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 2dbb32b..ae2d484 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1459,6 +1459,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, struct net_device *dev; __be16 proto = 0; int err; + int extra_len = 0; /* * Get and verify the address. @@ -1493,8 +1494,16 @@ retry: * raw protocol and you must do your own fragmentation at this level. */ + if (unlikely(sock_flag(sk, SOCK_NOFCS))) { + if (!netif_supports_nofcs(dev)) { + err = -EPROTONOSUPPORT; + goto out_unlock; + } + extra_len = 4; /* We're doing our own CRC */ + } + err = -EMSGSIZE; - if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN) + if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { @@ -1526,7 +1535,7 @@ retry: goto retry; } - if (len > (dev->mtu + dev->hard_header_len)) { + if (len > (dev->mtu + dev->hard_header_len + extra_len)) { /* Earlier code assumed this would be a VLAN pkt, * double-check this now that we have the actual * packet in hand. @@ -1548,6 +1557,9 @@ retry: if (err < 0) goto out_unlock; + if (unlikely(extra_len == 4)) + skb->no_fcs = 1; + dev_queue_xmit(skb); rcu_read_unlock(); return len; @@ -2209,6 +2221,7 @@ static int packet_snd(struct socket *sock, struct packet_sock *po = pkt_sk(sk); unsigned short gso_type = 0; int hlen, tlen; + int extra_len = 0; /* * Get and verify the address. @@ -2288,8 +2301,16 @@ static int packet_snd(struct socket *sock, } } + if (unlikely(sock_flag(sk, SOCK_NOFCS))) { + if (!netif_supports_nofcs(dev)) { + err = -EPROTONOSUPPORT; + goto out_unlock; + } + extra_len = 4; /* We're doing our own CRC */ + } + err = -EMSGSIZE; - if (!gso_type && (len > dev->mtu + reserve + VLAN_HLEN)) + if (!gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; @@ -2315,7 +2336,7 @@ static int packet_snd(struct socket *sock, if (err < 0) goto out_free; - if (!gso_type && (len > dev->mtu + reserve)) { + if (!gso_type && (len > dev->mtu + reserve + extra_len)) { /* Earlier code assumed this would be a VLAN pkt, * double-check this now that we have the actual * packet in hand. @@ -2353,6 +2374,9 @@ static int packet_snd(struct socket *sock, len += vnet_hdr_len; } + if (unlikely(extra_len == 4)) + skb->no_fcs = 1; + /* * Now send it */ diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 4cba13e..ae3a035 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -232,7 +232,7 @@ static int rxrpc_krb5_decode_principal(struct krb5_principal *princ, if (toklen <= (n_parts + 1) * 4) return -EINVAL; - princ->name_parts = kcalloc(sizeof(char *), n_parts, GFP_KERNEL); + princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL); if (!princ->name_parts) return -ENOMEM; @@ -355,7 +355,7 @@ static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td, _debug("n_elem %d", n_elem); - td = kcalloc(sizeof(struct krb5_tagged_data), n_elem, + td = kcalloc(n_elem, sizeof(struct krb5_tagged_data), GFP_KERNEL); if (!td) return -ENOMEM; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2590e91..75b58f8 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -260,6 +260,32 @@ config NET_SCH_INGRESS To compile this code as a module, choose M here: the module will be called sch_ingress. +config NET_SCH_PLUG + tristate "Plug network traffic until release (PLUG)" + ---help--- + + This queuing discipline allows userspace to plug/unplug a network + output queue, using the netlink interface. When it receives an + enqueue command it inserts a plug into the outbound queue that + causes following packets to enqueue until a dequeue command arrives + over netlink, causing the plug to be removed and resuming the normal + packet flow. + + This module also provides a generic "network output buffering" + functionality (aka output commit), wherein upon arrival of a dequeue + command, only packets up to the first plug are released for delivery. + The Remus HA project uses this module to enable speculative execution + of virtual machines by allowing the generated network output to be rolled + back if needed. + + For more information, please refer to http://wiki.xensource.com/xenwiki/Remus + + Say Y here if you are using this kernel for Xen dom0 and + want to protect Xen guests with Remus. + + To compile this code as a module, choose M here: the + module will be called sch_plug. + comment "Classification" config NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index dc5889c..8cdf4e2 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -33,6 +33,7 @@ obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o +obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index e465064..7e267d7 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -148,8 +148,7 @@ struct choke_skb_cb { static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct choke_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb)); return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 2776012..5da548f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -130,8 +130,7 @@ struct netem_skb_cb { static inline struct netem_skb_cb *netem_skb_cb(struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct netem_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct netem_skb_cb)); return (struct netem_skb_cb *)qdisc_skb_cb(skb)->data; } @@ -502,9 +501,8 @@ tfifo_dequeue: /* if more time remaining? */ if (cb->time_to_send <= psched_get_time()) { - skb = qdisc_dequeue_tail(sch); - if (unlikely(!skb)) - goto qdisc_dequeue; + __skb_unlink(skb, &sch->q); + sch->qstats.backlog -= qdisc_pkt_len(skb); #ifdef CONFIG_NET_CLS_ACT /* @@ -540,7 +538,6 @@ deliver: qdisc_watchdog_schedule(&q->watchdog, cb->time_to_send); } -qdisc_dequeue: if (q->qdisc) { skb = q->qdisc->ops->dequeue(q->qdisc); if (skb) diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c new file mode 100644 index 0000000..89f8fcf --- /dev/null +++ b/net/sched/sch_plug.c @@ -0,0 +1,233 @@ +/* + * sch_plug.c Queue traffic until an explicit release command + * + * 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. + * + * There are two ways to use this qdisc: + * 1. A simple "instantaneous" plug/unplug operation, by issuing an alternating + * sequence of TCQ_PLUG_BUFFER & TCQ_PLUG_RELEASE_INDEFINITE commands. + * + * 2. For network output buffering (a.k.a output commit) functionality. + * Output commit property is commonly used by applications using checkpoint + * based fault-tolerance to ensure that the checkpoint from which a system + * is being restored is consistent w.r.t outside world. + * + * Consider for e.g. Remus - a Virtual Machine checkpointing system, + * wherein a VM is checkpointed, say every 50ms. The checkpoint is replicated + * asynchronously to the backup host, while the VM continues executing the + * next epoch speculatively. + * + * The following is a typical sequence of output buffer operations: + * 1.At epoch i, start_buffer(i) + * 2. At end of epoch i (i.e. after 50ms): + * 2.1 Stop VM and take checkpoint(i). + * 2.2 start_buffer(i+1) and Resume VM + * 3. While speculatively executing epoch(i+1), asynchronously replicate + * checkpoint(i) to backup host. + * 4. When checkpoint_ack(i) is received from backup, release_buffer(i) + * Thus, this Qdisc would receive the following sequence of commands: + * TCQ_PLUG_BUFFER (epoch i) + * .. TCQ_PLUG_BUFFER (epoch i+1) + * ....TCQ_PLUG_RELEASE_ONE (epoch i) + * ......TCQ_PLUG_BUFFER (epoch i+2) + * ........ + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/pkt_sched.h> + +/* + * State of the queue, when used for network output buffering: + * + * plug(i+1) plug(i) head + * ------------------+--------------------+----------------> + * | | + * | | + * pkts_current_epoch| pkts_last_epoch |pkts_to_release + * ----------------->|<--------+--------->|+---------------> + * v v + * + */ + +struct plug_sched_data { + /* If true, the dequeue function releases all packets + * from head to end of the queue. The queue turns into + * a pass-through queue for newly arriving packets. + */ + bool unplug_indefinite; + + /* Queue Limit in bytes */ + u32 limit; + + /* Number of packets (output) from the current speculatively + * executing epoch. + */ + u32 pkts_current_epoch; + + /* Number of packets corresponding to the recently finished + * epoch. These will be released when we receive a + * TCQ_PLUG_RELEASE_ONE command. This command is typically + * issued after committing a checkpoint at the target. + */ + u32 pkts_last_epoch; + + /* + * Number of packets from the head of the queue, that can + * be released (committed checkpoint). + */ + u32 pkts_to_release; +}; + +static int plug_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + struct plug_sched_data *q = qdisc_priv(sch); + + if (likely(sch->qstats.backlog + skb->len <= q->limit)) { + if (!q->unplug_indefinite) + q->pkts_current_epoch++; + return qdisc_enqueue_tail(skb, sch); + } + + return qdisc_reshape_fail(skb, sch); +} + +static struct sk_buff *plug_dequeue(struct Qdisc *sch) +{ + struct plug_sched_data *q = qdisc_priv(sch); + + if (qdisc_is_throttled(sch)) + return NULL; + + if (!q->unplug_indefinite) { + if (!q->pkts_to_release) { + /* No more packets to dequeue. Block the queue + * and wait for the next release command. + */ + qdisc_throttled(sch); + return NULL; + } + q->pkts_to_release--; + } + + return qdisc_dequeue_head(sch); +} + +static int plug_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct plug_sched_data *q = qdisc_priv(sch); + + q->pkts_current_epoch = 0; + q->pkts_last_epoch = 0; + q->pkts_to_release = 0; + q->unplug_indefinite = false; + + if (opt == NULL) { + /* We will set a default limit of 100 pkts (~150kB) + * in case tx_queue_len is not available. The + * default value is completely arbitrary. + */ + u32 pkt_limit = qdisc_dev(sch)->tx_queue_len ? : 100; + q->limit = pkt_limit * psched_mtu(qdisc_dev(sch)); + } else { + struct tc_plug_qopt *ctl = nla_data(opt); + + if (nla_len(opt) < sizeof(*ctl)) + return -EINVAL; + + q->limit = ctl->limit; + } + + qdisc_throttled(sch); + return 0; +} + +/* Receives 4 types of messages: + * TCQ_PLUG_BUFFER: Inset a plug into the queue and + * buffer any incoming packets + * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head + * to beginning of the next plug. + * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue. + * Stop buffering packets until the next TCQ_PLUG_BUFFER + * command is received (just act as a pass-thru queue). + * TCQ_PLUG_LIMIT: Increase/decrease queue size + */ +static int plug_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct plug_sched_data *q = qdisc_priv(sch); + struct tc_plug_qopt *msg; + + if (opt == NULL) + return -EINVAL; + + msg = nla_data(opt); + if (nla_len(opt) < sizeof(*msg)) + return -EINVAL; + + switch (msg->action) { + case TCQ_PLUG_BUFFER: + /* Save size of the current buffer */ + q->pkts_last_epoch = q->pkts_current_epoch; + q->pkts_current_epoch = 0; + if (q->unplug_indefinite) + qdisc_throttled(sch); + q->unplug_indefinite = false; + break; + case TCQ_PLUG_RELEASE_ONE: + /* Add packets from the last complete buffer to the + * packets to be released set. + */ + q->pkts_to_release += q->pkts_last_epoch; + q->pkts_last_epoch = 0; + qdisc_unthrottled(sch); + netif_schedule_queue(sch->dev_queue); + break; + case TCQ_PLUG_RELEASE_INDEFINITE: + q->unplug_indefinite = true; + q->pkts_to_release = 0; + q->pkts_last_epoch = 0; + q->pkts_current_epoch = 0; + qdisc_unthrottled(sch); + netif_schedule_queue(sch->dev_queue); + break; + case TCQ_PLUG_LIMIT: + /* Limit is supplied in bytes */ + q->limit = msg->limit; + break; + default: + return -EINVAL; + } + + return 0; +} + +static struct Qdisc_ops plug_qdisc_ops __read_mostly = { + .id = "plug", + .priv_size = sizeof(struct plug_sched_data), + .enqueue = plug_enqueue, + .dequeue = plug_dequeue, + .peek = qdisc_peek_head, + .init = plug_init, + .change = plug_change, + .owner = THIS_MODULE, +}; + +static int __init plug_module_init(void) +{ + return register_qdisc(&plug_qdisc_ops); +} + +static void __exit plug_module_exit(void) +{ + unregister_qdisc(&plug_qdisc_ops); +} +module_init(plug_module_init) +module_exit(plug_module_exit) +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 96e42ca..d7eea99 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -94,8 +94,7 @@ struct sfb_skb_cb { static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb)); + qdisc_cb_private_validate(skb, sizeof(struct sfb_skb_cb)); return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 67494ae..60d4718 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -166,9 +166,8 @@ struct sfq_skb_cb { static inline struct sfq_skb_cb *sfq_skb_cb(const struct sk_buff *skb) { - BUILD_BUG_ON(sizeof(skb->cb) < - sizeof(struct qdisc_skb_cb) + sizeof(struct sfq_skb_cb)); - return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; + qdisc_cb_private_validate(skb, sizeof(struct sfq_skb_cb)); + return (struct sfq_skb_cb *)qdisc_skb_cb(skb)->data; } static unsigned int sfq_hash(const struct sfq_sched_data *q, diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c index 1426ec3..75762f3 100644 --- a/net/sunrpc/auth_generic.c +++ b/net/sunrpc/auth_generic.c @@ -92,6 +92,7 @@ generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) if (gcred->acred.group_info != NULL) get_group_info(gcred->acred.group_info); gcred->acred.machine_cred = acred->machine_cred; + gcred->acred.principal = acred->principal; dprintk("RPC: allocated %s cred %p for uid %d gid %d\n", gcred->acred.machine_cred ? "machine" : "generic", @@ -123,6 +124,17 @@ generic_destroy_cred(struct rpc_cred *cred) call_rcu(&cred->cr_rcu, generic_free_cred_callback); } +static int +machine_cred_match(struct auth_cred *acred, struct generic_cred *gcred, int flags) +{ + if (!gcred->acred.machine_cred || + gcred->acred.principal != acred->principal || + gcred->acred.uid != acred->uid || + gcred->acred.gid != acred->gid) + return 0; + return 1; +} + /* * Match credentials against current process creds. */ @@ -132,9 +144,12 @@ generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); int i; + if (acred->machine_cred) + return machine_cred_match(acred, gcred, flags); + if (gcred->acred.uid != acred->uid || gcred->acred.gid != acred->gid || - gcred->acred.machine_cred != acred->machine_cred) + gcred->acred.machine_cred != 0) goto out_nomatch; /* Optimisation in the case where pointers are identical... */ diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 8eb87b1..e00441a2 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -157,39 +157,14 @@ u32 tipc_bclink_get_last_sent(void) return bcl->fsm_msg_cnt; } -/** - * bclink_set_gap - set gap according to contents of current deferred pkt queue - * - * Called with 'node' locked, bc_lock unlocked - */ - -static void bclink_set_gap(struct tipc_node *n_ptr) -{ - struct sk_buff *buf = n_ptr->bclink.deferred_head; - - n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = - mod(n_ptr->bclink.last_in); - if (unlikely(buf != NULL)) - n_ptr->bclink.gap_to = mod(buf_seqno(buf) - 1); -} - -/** - * bclink_ack_allowed - test if ACK or NACK message can be sent at this moment - * - * This mechanism endeavours to prevent all nodes in network from trying - * to ACK or NACK at the same time. - * - * Note: TIPC uses a different trigger to distribute ACKs than it does to - * distribute NACKs, but tries to use the same spacing (divide by 16). - */ - -static int bclink_ack_allowed(u32 n) +static void bclink_update_last_sent(struct tipc_node *node, u32 seqno) { - return (n % TIPC_MIN_LINK_WIN) == tipc_own_tag; + node->bclink.last_sent = less_eq(node->bclink.last_sent, seqno) ? + seqno : node->bclink.last_sent; } -/** +/* * tipc_bclink_retransmit_to - get most recent node to request retransmission * * Called with bc_lock locked @@ -281,7 +256,7 @@ void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked) if (bcbuf_acks(crs) == 0) { bcl->first_out = next; bcl->out_queue_size--; - buf_discard(crs); + kfree_skb(crs); released = 1; } crs = next; @@ -300,140 +275,94 @@ exit: spin_unlock_bh(&bc_lock); } -/** - * bclink_send_ack - unicast an ACK msg +/* + * tipc_bclink_update_link_state - update broadcast link state * * tipc_net_lock and node lock set */ -static void bclink_send_ack(struct tipc_node *n_ptr) +void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent) { - struct tipc_link *l_ptr = n_ptr->active_links[n_ptr->addr & 1]; + struct sk_buff *buf; - if (l_ptr != NULL) - tipc_link_send_proto_msg(l_ptr, STATE_MSG, 0, 0, 0, 0, 0); -} + /* Ignore "stale" link state info */ -/** - * bclink_send_nack- broadcast a NACK msg - * - * tipc_net_lock and node lock set - */ + if (less_eq(last_sent, n_ptr->bclink.last_in)) + return; -static void bclink_send_nack(struct tipc_node *n_ptr) -{ - struct sk_buff *buf; - struct tipc_msg *msg; + /* Update link synchronization state; quit if in sync */ + + bclink_update_last_sent(n_ptr, last_sent); + + if (n_ptr->bclink.last_sent == n_ptr->bclink.last_in) + return; + + /* Update out-of-sync state; quit if loss is still unconfirmed */ + + if ((++n_ptr->bclink.oos_state) == 1) { + if (n_ptr->bclink.deferred_size < (TIPC_MIN_LINK_WIN / 2)) + return; + n_ptr->bclink.oos_state++; + } - if (!less(n_ptr->bclink.gap_after, n_ptr->bclink.gap_to)) + /* Don't NACK if one has been recently sent (or seen) */ + + if (n_ptr->bclink.oos_state & 0x1) return; + /* Send NACK */ + buf = tipc_buf_acquire(INT_H_SIZE); if (buf) { - msg = buf_msg(buf); + struct tipc_msg *msg = buf_msg(buf); + tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, - INT_H_SIZE, n_ptr->addr); + INT_H_SIZE, n_ptr->addr); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); - msg_set_bcast_ack(msg, mod(n_ptr->bclink.last_in)); - msg_set_bcgap_after(msg, n_ptr->bclink.gap_after); - msg_set_bcgap_to(msg, n_ptr->bclink.gap_to); - msg_set_bcast_tag(msg, tipc_own_tag); + msg_set_bcast_ack(msg, n_ptr->bclink.last_in); + msg_set_bcgap_after(msg, n_ptr->bclink.last_in); + msg_set_bcgap_to(msg, n_ptr->bclink.deferred_head + ? buf_seqno(n_ptr->bclink.deferred_head) - 1 + : n_ptr->bclink.last_sent); + spin_lock_bh(&bc_lock); tipc_bearer_send(&bcbearer->bearer, buf, NULL); bcl->stats.sent_nacks++; - buf_discard(buf); - - /* - * Ensure we doesn't send another NACK msg to the node - * until 16 more deferred messages arrive from it - * (i.e. helps prevent all nodes from NACK'ing at same time) - */ + spin_unlock_bh(&bc_lock); + kfree_skb(buf); - n_ptr->bclink.nack_sync = tipc_own_tag; + n_ptr->bclink.oos_state++; } } -/** - * tipc_bclink_check_gap - send a NACK if a sequence gap exists +/* + * bclink_peek_nack - monitor retransmission requests sent by other nodes * - * tipc_net_lock and node lock set - */ - -void tipc_bclink_check_gap(struct tipc_node *n_ptr, u32 last_sent) -{ - if (!n_ptr->bclink.supported || - less_eq(last_sent, mod(n_ptr->bclink.last_in))) - return; - - bclink_set_gap(n_ptr); - if (n_ptr->bclink.gap_after == n_ptr->bclink.gap_to) - n_ptr->bclink.gap_to = last_sent; - bclink_send_nack(n_ptr); -} - -/** - * tipc_bclink_peek_nack - process a NACK msg meant for another node + * Delay any upcoming NACK by this node if another node has already + * requested the first message this node is going to ask for. * * Only tipc_net_lock set. */ -static void tipc_bclink_peek_nack(u32 dest, u32 sender_tag, u32 gap_after, u32 gap_to) +static void bclink_peek_nack(struct tipc_msg *msg) { - struct tipc_node *n_ptr = tipc_node_find(dest); - u32 my_after, my_to; + struct tipc_node *n_ptr = tipc_node_find(msg_destnode(msg)); - if (unlikely(!n_ptr || !tipc_node_is_up(n_ptr))) + if (unlikely(!n_ptr)) return; + tipc_node_lock(n_ptr); - /* - * Modify gap to suppress unnecessary NACKs from this node - */ - my_after = n_ptr->bclink.gap_after; - my_to = n_ptr->bclink.gap_to; - - if (less_eq(gap_after, my_after)) { - if (less(my_after, gap_to) && less(gap_to, my_to)) - n_ptr->bclink.gap_after = gap_to; - else if (less_eq(my_to, gap_to)) - n_ptr->bclink.gap_to = n_ptr->bclink.gap_after; - } else if (less_eq(gap_after, my_to)) { - if (less_eq(my_to, gap_to)) - n_ptr->bclink.gap_to = gap_after; - } else { - /* - * Expand gap if missing bufs not in deferred queue: - */ - struct sk_buff *buf = n_ptr->bclink.deferred_head; - u32 prev = n_ptr->bclink.gap_to; - for (; buf; buf = buf->next) { - u32 seqno = buf_seqno(buf); + if (n_ptr->bclink.supported && + (n_ptr->bclink.last_in != n_ptr->bclink.last_sent) && + (n_ptr->bclink.last_in == msg_bcgap_after(msg))) + n_ptr->bclink.oos_state = 2; - if (mod(seqno - prev) != 1) { - buf = NULL; - break; - } - if (seqno == gap_after) - break; - prev = seqno; - } - if (buf == NULL) - n_ptr->bclink.gap_to = gap_after; - } - /* - * Some nodes may send a complementary NACK now: - */ - if (bclink_ack_allowed(sender_tag + 1)) { - if (n_ptr->bclink.gap_to != n_ptr->bclink.gap_after) { - bclink_send_nack(n_ptr); - bclink_set_gap(n_ptr); - } - } tipc_node_unlock(n_ptr); } -/** +/* * tipc_bclink_send_msg - broadcast a packet to all nodes in cluster */ @@ -445,7 +374,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf) if (!bclink->bcast_nodes.count) { res = msg_data_sz(buf_msg(buf)); - buf_discard(buf); + kfree_skb(buf); goto exit; } @@ -460,7 +389,33 @@ exit: return res; } -/** +/* + * bclink_accept_pkt - accept an incoming, in-sequence broadcast packet + * + * Called with both sending node's lock and bc_lock taken. + */ + +static void bclink_accept_pkt(struct tipc_node *node, u32 seqno) +{ + bclink_update_last_sent(node, seqno); + node->bclink.last_in = seqno; + node->bclink.oos_state = 0; + bcl->stats.recv_info++; + + /* + * Unicast an ACK periodically, ensuring that + * all nodes in the cluster don't ACK at the same time + */ + + if (((seqno - tipc_own_addr) % TIPC_MIN_LINK_WIN) == 0) { + tipc_link_send_proto_msg( + node->active_links[node->addr & 1], + STATE_MSG, 0, 0, 0, 0, 0); + bcl->stats.sent_acks++; + } +} + +/* * tipc_bclink_recv_pkt - receive a broadcast packet, and deliver upwards * * tipc_net_lock is read_locked, no other locks set @@ -472,7 +427,7 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) struct tipc_node *node; u32 next_in; u32 seqno; - struct sk_buff *deferred; + int deferred; /* Screen out unwanted broadcast messages */ @@ -487,6 +442,8 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) if (unlikely(!node->bclink.supported)) goto unlock; + /* Handle broadcast protocol message */ + if (unlikely(msg_user(msg) == BCAST_PROTOCOL)) { if (msg_type(msg) != STATE_MSG) goto unlock; @@ -501,89 +458,118 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) spin_unlock_bh(&bc_lock); } else { tipc_node_unlock(node); - tipc_bclink_peek_nack(msg_destnode(msg), - msg_bcast_tag(msg), - msg_bcgap_after(msg), - msg_bcgap_to(msg)); + bclink_peek_nack(msg); } goto exit; } /* Handle in-sequence broadcast message */ -receive: - next_in = mod(node->bclink.last_in + 1); seqno = msg_seqno(msg); + next_in = mod(node->bclink.last_in + 1); if (likely(seqno == next_in)) { - bcl->stats.recv_info++; - node->bclink.last_in++; - bclink_set_gap(node); - if (unlikely(bclink_ack_allowed(seqno))) { - bclink_send_ack(node); - bcl->stats.sent_acks++; - } +receive: + /* Deliver message to destination */ + if (likely(msg_isdata(msg))) { + spin_lock_bh(&bc_lock); + bclink_accept_pkt(node, seqno); + spin_unlock_bh(&bc_lock); tipc_node_unlock(node); if (likely(msg_mcast(msg))) tipc_port_recv_mcast(buf, NULL); else - buf_discard(buf); + kfree_skb(buf); } else if (msg_user(msg) == MSG_BUNDLER) { + spin_lock_bh(&bc_lock); + bclink_accept_pkt(node, seqno); bcl->stats.recv_bundles++; bcl->stats.recv_bundled += msg_msgcnt(msg); + spin_unlock_bh(&bc_lock); tipc_node_unlock(node); tipc_link_recv_bundle(buf); } else if (msg_user(msg) == MSG_FRAGMENTER) { + int ret = tipc_link_recv_fragment(&node->bclink.defragm, + &buf, &msg); + if (ret < 0) + goto unlock; + spin_lock_bh(&bc_lock); + bclink_accept_pkt(node, seqno); bcl->stats.recv_fragments++; - if (tipc_link_recv_fragment(&node->bclink.defragm, - &buf, &msg)) + if (ret > 0) bcl->stats.recv_fragmented++; + spin_unlock_bh(&bc_lock); tipc_node_unlock(node); tipc_net_route_msg(buf); } else if (msg_user(msg) == NAME_DISTRIBUTOR) { + spin_lock_bh(&bc_lock); + bclink_accept_pkt(node, seqno); + spin_unlock_bh(&bc_lock); tipc_node_unlock(node); tipc_named_recv(buf); } else { + spin_lock_bh(&bc_lock); + bclink_accept_pkt(node, seqno); + spin_unlock_bh(&bc_lock); tipc_node_unlock(node); - buf_discard(buf); + kfree_skb(buf); } buf = NULL; + + /* Determine new synchronization state */ + tipc_node_lock(node); - deferred = node->bclink.deferred_head; - if (deferred && (buf_seqno(deferred) == mod(next_in + 1))) { - buf = deferred; - msg = buf_msg(buf); - node->bclink.deferred_head = deferred->next; - goto receive; - } - } else if (less(next_in, seqno)) { - u32 gap_after = node->bclink.gap_after; - u32 gap_to = node->bclink.gap_to; - - if (tipc_link_defer_pkt(&node->bclink.deferred_head, - &node->bclink.deferred_tail, - buf)) { - node->bclink.nack_sync++; - bcl->stats.deferred_recv++; - if (seqno == mod(gap_after + 1)) - node->bclink.gap_after = seqno; - else if (less(gap_after, seqno) && less(seqno, gap_to)) - node->bclink.gap_to = seqno; + if (unlikely(!tipc_node_is_up(node))) + goto unlock; + + if (node->bclink.last_in == node->bclink.last_sent) + goto unlock; + + if (!node->bclink.deferred_head) { + node->bclink.oos_state = 1; + goto unlock; } + + msg = buf_msg(node->bclink.deferred_head); + seqno = msg_seqno(msg); + next_in = mod(next_in + 1); + if (seqno != next_in) + goto unlock; + + /* Take in-sequence message from deferred queue & deliver it */ + + buf = node->bclink.deferred_head; + node->bclink.deferred_head = buf->next; + node->bclink.deferred_size--; + goto receive; + } + + /* Handle out-of-sequence broadcast message */ + + if (less(next_in, seqno)) { + deferred = tipc_link_defer_pkt(&node->bclink.deferred_head, + &node->bclink.deferred_tail, + buf); + node->bclink.deferred_size += deferred; + bclink_update_last_sent(node, seqno); buf = NULL; - if (bclink_ack_allowed(node->bclink.nack_sync)) { - if (gap_to != gap_after) - bclink_send_nack(node); - bclink_set_gap(node); - } - } else { + } else + deferred = 0; + + spin_lock_bh(&bc_lock); + + if (deferred) + bcl->stats.deferred_recv++; + else bcl->stats.duplicates++; - } + + spin_unlock_bh(&bc_lock); + unlock: tipc_node_unlock(node); exit: - buf_discard(buf); + kfree_skb(buf); } u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr) diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index b009666..5571394 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -96,7 +96,7 @@ int tipc_bclink_send_msg(struct sk_buff *buf); void tipc_bclink_recv_pkt(struct sk_buff *buf); u32 tipc_bclink_get_last_sent(void); u32 tipc_bclink_acks_missing(struct tipc_node *n_ptr); -void tipc_bclink_check_gap(struct tipc_node *n_ptr, u32 seqno); +void tipc_bclink_update_link_state(struct tipc_node *n_ptr, u32 last_sent); int tipc_bclink_stats(char *stats_buf, const u32 buf_size); int tipc_bclink_reset_stats(void); int tipc_bclink_set_queue_limits(u32 limit); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 329fb65..5dfd89c 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -435,7 +435,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) u32 i; int res = -EINVAL; - if (tipc_mode != TIPC_NET_MODE) { + if (!tipc_own_addr) { warn("Bearer <%s> rejected, not supported in standalone mode\n", name); return -ENOPROTOOPT; @@ -456,8 +456,7 @@ int tipc_enable_bearer(const char *name, u32 disc_domain, u32 priority) warn("Bearer <%s> rejected, illegal discovery domain\n", name); return -EINVAL; } - if ((priority < TIPC_MIN_LINK_PRI || - priority > TIPC_MAX_LINK_PRI) && + if ((priority > TIPC_MAX_LINK_PRI) && (priority != TIPC_MEDIA_LINK_PRI)) { warn("Bearer <%s> rejected, illegal priority\n", name); return -EINVAL; diff --git a/net/tipc/config.c b/net/tipc/config.c index 4785bf2..f76d3b1 100644 --- a/net/tipc/config.c +++ b/net/tipc/config.c @@ -179,7 +179,7 @@ static struct sk_buff *cfg_set_own_addr(void) if (!tipc_addr_node_valid(addr)) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (node address)"); - if (tipc_mode == TIPC_NET_MODE) + if (tipc_own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change node address once assigned)"); @@ -218,7 +218,7 @@ static struct sk_buff *cfg_set_max_publications(void) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value != delimit(value, 1, 65535)) + if (value < 1 || value > 65535) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (max publications must be 1-65535)"); tipc_max_publications = value; @@ -233,7 +233,7 @@ static struct sk_buff *cfg_set_max_subscriptions(void) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value != delimit(value, 1, 65535)) + if (value < 1 || value > 65535) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (max subscriptions must be 1-65535"); tipc_max_subscriptions = value; @@ -249,14 +249,11 @@ static struct sk_buff *cfg_set_max_ports(void) value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); if (value == tipc_max_ports) return tipc_cfg_reply_none(); - if (value != delimit(value, 127, 65535)) + if (value < 127 || value > 65535) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (max ports must be 127-65535)"); - if (tipc_mode != TIPC_NOT_RUNNING) - return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED - " (cannot change max ports while TIPC is active)"); - tipc_max_ports = value; - return tipc_cfg_reply_none(); + return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED + " (cannot change max ports while TIPC is active)"); } static struct sk_buff *cfg_set_netid(void) @@ -268,10 +265,10 @@ static struct sk_buff *cfg_set_netid(void) value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); if (value == tipc_net_id) return tipc_cfg_reply_none(); - if (value != delimit(value, 1, 9999)) + if (value < 1 || value > 9999) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network id must be 1-9999)"); - if (tipc_mode == TIPC_NET_MODE) + if (tipc_own_addr) return tipc_cfg_reply_error_string(TIPC_CFG_NOT_SUPPORTED " (cannot change network id once TIPC has joined a network)"); tipc_net_id = value; @@ -481,7 +478,7 @@ int tipc_cfg_init(void) seq.type = TIPC_CFG_SRV; seq.lower = seq.upper = tipc_own_addr; - res = tipc_nametbl_publish_rsv(config_port_ref, TIPC_ZONE_SCOPE, &seq); + res = tipc_publish(config_port_ref, TIPC_ZONE_SCOPE, &seq); if (res) goto failed; diff --git a/net/tipc/core.c b/net/tipc/core.c index 2691cd5..68eba03 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -53,7 +53,6 @@ /* global variables used by multiple sub-systems within TIPC */ -int tipc_mode = TIPC_NOT_RUNNING; int tipc_random; const char tipc_alphabet[] = @@ -125,11 +124,6 @@ int tipc_core_start_net(unsigned long addr) static void tipc_core_stop(void) { - if (tipc_mode != TIPC_NODE_MODE) - return; - - tipc_mode = TIPC_NOT_RUNNING; - tipc_netlink_stop(); tipc_handler_stop(); tipc_cfg_stop(); @@ -148,11 +142,7 @@ static int tipc_core_start(void) { int res; - if (tipc_mode != TIPC_NOT_RUNNING) - return -ENOPROTOOPT; - get_random_bytes(&tipc_random, sizeof(tipc_random)); - tipc_mode = TIPC_NODE_MODE; res = tipc_handler_start(); if (!res) diff --git a/net/tipc/core.h b/net/tipc/core.h index 2761af3..13837e0 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -130,13 +130,6 @@ void tipc_msg_dbg(struct print_buf *, struct tipc_msg *, const char *); #define ELINKCONG EAGAIN /* link congestion <=> resource unavailable */ /* - * TIPC operating mode routines - */ -#define TIPC_NOT_RUNNING 0 -#define TIPC_NODE_MODE 1 -#define TIPC_NET_MODE 2 - -/* * Global configuration variables */ @@ -151,7 +144,6 @@ extern int tipc_remote_management; * Other global variables */ -extern int tipc_mode; extern int tipc_random; extern const char tipc_alphabet[]; @@ -168,16 +160,6 @@ extern void tipc_netlink_stop(void); extern int tipc_socket_init(void); extern void tipc_socket_stop(void); -static inline int delimit(int val, int min, int max) -{ - if (val > max) - return max; - if (val < min) - return min; - return val; -} - - /* * TIPC timer and signal code */ @@ -279,28 +261,4 @@ static inline struct tipc_msg *buf_msg(struct sk_buff *skb) extern struct sk_buff *tipc_buf_acquire(u32 size); -/** - * buf_discard - frees a TIPC message buffer - * @skb: message buffer - * - * Frees a message buffer. If passed NULL, just returns. - */ - -static inline void buf_discard(struct sk_buff *skb) -{ - kfree_skb(skb); -} - -/** - * buf_linearize - convert a TIPC message buffer into a single contiguous piece - * @skb: message buffer - * - * Returns 0 on success. - */ - -static inline int buf_linearize(struct sk_buff *skb) -{ - return skb_linearize(skb); -} - #endif diff --git a/net/tipc/discover.c b/net/tipc/discover.c index a00e5f8..c630a21 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -82,6 +82,7 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, msg = buf_msg(buf); tipc_msg_init(msg, LINK_CONFIG, type, INT_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); + msg_set_node_sig(msg, tipc_random); msg_set_dest_domain(msg, dest_domain); msg_set_bc_netid(msg, tipc_net_id); b_ptr->media->addr2msg(&b_ptr->addr, msg_media_addr(msg)); @@ -121,20 +122,22 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) { struct tipc_node *n_ptr; struct tipc_link *link; - struct tipc_media_addr media_addr, *addr; + struct tipc_media_addr media_addr; struct sk_buff *rbuf; struct tipc_msg *msg = buf_msg(buf); u32 dest = msg_dest_domain(msg); u32 orig = msg_prevnode(msg); u32 net_id = msg_bc_netid(msg); u32 type = msg_type(msg); + u32 signature = msg_node_sig(msg); + int addr_mismatch; int link_fully_up; media_addr.broadcast = 1; b_ptr->media->msg2addr(&media_addr, msg_media_addr(msg)); - buf_discard(buf); + kfree_skb(buf); - /* Validate discovery message from requesting node */ + /* Ensure message from node is valid and communication is permitted */ if (net_id != tipc_net_id) return; if (media_addr.broadcast) @@ -162,15 +165,50 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) } tipc_node_lock(n_ptr); + /* Prepare to validate requesting node's signature and media address */ link = n_ptr->links[b_ptr->identity]; + addr_mismatch = (link != NULL) && + memcmp(&link->media_addr, &media_addr, sizeof(media_addr)); - /* Create a link endpoint for this bearer, if necessary */ - if (!link) { - link = tipc_link_create(n_ptr, b_ptr, &media_addr); - if (!link) { + /* + * Ensure discovery message's signature is correct + * + * If signature is incorrect and there is no working link to the node, + * accept the new signature but invalidate all existing links to the + * node so they won't re-activate without a new discovery message. + * + * If signature is incorrect and the requested link to the node is + * working, accept the new signature. (This is an instance of delayed + * rediscovery, where a link endpoint was able to re-establish contact + * with its peer endpoint on a node that rebooted before receiving a + * discovery message from that node.) + * + * If signature is incorrect and there is a working link to the node + * that is not the requested link, reject the request (must be from + * a duplicate node). + */ + if (signature != n_ptr->signature) { + if (n_ptr->working_links == 0) { + struct tipc_link *curr_link; + int i; + + for (i = 0; i < MAX_BEARERS; i++) { + curr_link = n_ptr->links[i]; + if (curr_link) { + memset(&curr_link->media_addr, 0, + sizeof(media_addr)); + tipc_link_reset(curr_link); + } + } + addr_mismatch = (link != NULL); + } else if (tipc_link_is_up(link) && !addr_mismatch) { + /* delayed rediscovery */ + } else { + disc_dupl_alert(b_ptr, orig, &media_addr); tipc_node_unlock(n_ptr); return; } + n_ptr->signature = signature; } /* @@ -183,17 +221,26 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) * the new media address and reset the link to ensure it starts up * cleanly. */ - addr = &link->media_addr; - if (memcmp(addr, &media_addr, sizeof(*addr))) { - if (tipc_link_is_up(link) || (!link->started)) { + + if (addr_mismatch) { + if (tipc_link_is_up(link)) { disc_dupl_alert(b_ptr, orig, &media_addr); tipc_node_unlock(n_ptr); return; + } else { + memcpy(&link->media_addr, &media_addr, + sizeof(media_addr)); + tipc_link_reset(link); + } + } + + /* Create a link endpoint for this bearer, if necessary */ + if (!link) { + link = tipc_link_create(n_ptr, b_ptr, &media_addr); + if (!link) { + tipc_node_unlock(n_ptr); + return; } - warn("Resetting link <%s>, peer interface address changed\n", - link->name); - memcpy(addr, &media_addr, sizeof(*addr)); - tipc_link_reset(link); } /* Accept discovery message & send response, if necessary */ @@ -203,7 +250,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr); if (rbuf) { b_ptr->media->send_msg(rbuf, b_ptr, &media_addr); - buf_discard(rbuf); + kfree_skb(rbuf); } } @@ -349,7 +396,7 @@ void tipc_disc_delete(struct tipc_link_req *req) { k_cancel_timer(&req->timer); k_term_timer(&req->timer); - buf_discard(req->buf); + kfree_skb(req->buf); kfree(req); } diff --git a/net/tipc/link.c b/net/tipc/link.c index ac1832a..b4b9b30 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -484,7 +484,7 @@ static void link_release_outqueue(struct tipc_link *l_ptr) while (buf) { next = buf->next; - buf_discard(buf); + kfree_skb(buf); buf = next; } l_ptr->first_out = NULL; @@ -503,7 +503,7 @@ void tipc_link_reset_fragments(struct tipc_link *l_ptr) while (buf) { next = buf->next; - buf_discard(buf); + kfree_skb(buf); buf = next; } l_ptr->defragm_buf = NULL; @@ -522,20 +522,20 @@ void tipc_link_stop(struct tipc_link *l_ptr) buf = l_ptr->oldest_deferred_in; while (buf) { next = buf->next; - buf_discard(buf); + kfree_skb(buf); buf = next; } buf = l_ptr->first_out; while (buf) { next = buf->next; - buf_discard(buf); + kfree_skb(buf); buf = next; } tipc_link_reset_fragments(l_ptr); - buf_discard(l_ptr->proto_msg_queue); + kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; } @@ -571,12 +571,12 @@ void tipc_link_reset(struct tipc_link *l_ptr) /* Clean up all queues: */ link_release_outqueue(l_ptr); - buf_discard(l_ptr->proto_msg_queue); + kfree_skb(l_ptr->proto_msg_queue); l_ptr->proto_msg_queue = NULL; buf = l_ptr->oldest_deferred_in; while (buf) { struct sk_buff *next = buf->next; - buf_discard(buf); + kfree_skb(buf); buf = next; } if (!list_empty(&l_ptr->waiting_ports)) @@ -810,7 +810,7 @@ static int link_bundle_buf(struct tipc_link *l_ptr, skb_copy_to_linear_data_offset(bundler, to_pos, buf->data, size); msg_set_size(bundler_msg, to_pos + size); msg_set_msgcnt(bundler_msg, msg_msgcnt(bundler_msg) + 1); - buf_discard(buf); + kfree_skb(buf); l_ptr->stats.sent_bundled++; return 1; } @@ -871,17 +871,15 @@ int tipc_link_send_buf(struct tipc_link *l_ptr, struct sk_buff *buf) u32 queue_limit = l_ptr->queue_limit[imp]; u32 max_packet = l_ptr->max_pkt; - msg_set_prevnode(msg, tipc_own_addr); /* If routed message */ - /* Match msg importance against queue limits: */ if (unlikely(queue_size >= queue_limit)) { if (imp <= TIPC_CRITICAL_IMPORTANCE) { link_schedule_port(l_ptr, msg_origport(msg), size); - buf_discard(buf); + kfree_skb(buf); return -ELINKCONG; } - buf_discard(buf); + kfree_skb(buf); if (imp > CONN_MANAGER) { warn("Resetting link <%s>, send queue full", l_ptr->name); tipc_link_reset(l_ptr); @@ -968,10 +966,10 @@ int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector) if (l_ptr) res = tipc_link_send_buf(l_ptr, buf); else - buf_discard(buf); + kfree_skb(buf); tipc_node_unlock(n_ptr); } else { - buf_discard(buf); + kfree_skb(buf); } read_unlock_bh(&tipc_net_lock); return res; @@ -1018,7 +1016,7 @@ void tipc_link_send_names(struct list_head *message_list, u32 dest) list_for_each_safe(buf, temp_buf, ((struct sk_buff *)message_list)) { list_del((struct list_head *)buf); - buf_discard(buf); + kfree_skb(buf); } } @@ -1262,7 +1260,7 @@ again: error: for (; buf_chain; buf_chain = buf) { buf = buf_chain->next; - buf_discard(buf_chain); + kfree_skb(buf_chain); } return -EFAULT; } @@ -1316,7 +1314,7 @@ error: tipc_node_unlock(node); for (; buf_chain; buf_chain = buf) { buf = buf_chain->next; - buf_discard(buf_chain); + kfree_skb(buf_chain); } goto again; } @@ -1324,7 +1322,7 @@ error: reject: for (; buf_chain; buf_chain = buf) { buf = buf_chain->next; - buf_discard(buf_chain); + kfree_skb(buf_chain); } return tipc_port_reject_sections(sender, hdr, msg_sect, num_sect, total_len, TIPC_ERR_NO_NODE); @@ -1390,7 +1388,7 @@ u32 tipc_link_push_packet(struct tipc_link *l_ptr) msg_set_bcast_ack(buf_msg(buf), l_ptr->owner->bclink.last_in); if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { l_ptr->unacked_window = 0; - buf_discard(buf); + kfree_skb(buf); l_ptr->proto_msg_queue = NULL; return 0; } else { @@ -1501,13 +1499,13 @@ static void link_retransmit_failure(struct tipc_link *l_ptr, tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); - info("Multicast link info for %s\n", addr_string); + info("Broadcast link info for %s\n", addr_string); + info("Supportable: %d, ", n_ptr->bclink.supportable); info("Supported: %d, ", n_ptr->bclink.supported); info("Acked: %u\n", n_ptr->bclink.acked); info("Last in: %u, ", n_ptr->bclink.last_in); - info("Gap after: %u, ", n_ptr->bclink.gap_after); - info("Gap to: %u\n", n_ptr->bclink.gap_to); - info("Nack sync: %u\n\n", n_ptr->bclink.nack_sync); + info("Oos state: %u, ", n_ptr->bclink.oos_state); + info("Last sent: %u\n", n_ptr->bclink.last_sent); tipc_k_signal((Handler)link_reset_all, (unsigned long)n_ptr->addr); @@ -1679,7 +1677,7 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Ensure message data is a single contiguous unit */ - if (unlikely(buf_linearize(buf))) + if (unlikely(skb_linearize(buf))) goto cont; /* Handle arrival of a non-unicast link message */ @@ -1736,7 +1734,7 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) /* Release acked messages */ - if (tipc_node_is_up(n_ptr) && n_ptr->bclink.supported) + if (n_ptr->bclink.supported) tipc_bclink_acknowledge(n_ptr, msg_bcast_ack(msg)); crs = l_ptr->first_out; @@ -1744,7 +1742,7 @@ void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) less_eq(buf_seqno(crs), ackd)) { struct sk_buff *next = crs->next; - buf_discard(crs); + kfree_skb(crs); crs = next; released++; } @@ -1773,52 +1771,56 @@ protocol_check: if (unlikely(l_ptr->oldest_deferred_in)) head = link_insert_deferred_queue(l_ptr, head); - if (likely(msg_is_dest(msg, tipc_own_addr))) { deliver: - if (likely(msg_isdata(msg))) { - tipc_node_unlock(n_ptr); - tipc_port_recv_msg(buf); - continue; + if (likely(msg_isdata(msg))) { + tipc_node_unlock(n_ptr); + tipc_port_recv_msg(buf); + continue; + } + switch (msg_user(msg)) { + int ret; + case MSG_BUNDLER: + l_ptr->stats.recv_bundles++; + l_ptr->stats.recv_bundled += + msg_msgcnt(msg); + tipc_node_unlock(n_ptr); + tipc_link_recv_bundle(buf); + continue; + case NAME_DISTRIBUTOR: + tipc_node_unlock(n_ptr); + tipc_named_recv(buf); + continue; + case CONN_MANAGER: + tipc_node_unlock(n_ptr); + tipc_port_recv_proto_msg(buf); + continue; + case MSG_FRAGMENTER: + l_ptr->stats.recv_fragments++; + ret = tipc_link_recv_fragment( + &l_ptr->defragm_buf, + &buf, &msg); + if (ret == 1) { + l_ptr->stats.recv_fragmented++; + goto deliver; } - switch (msg_user(msg)) { - case MSG_BUNDLER: - l_ptr->stats.recv_bundles++; - l_ptr->stats.recv_bundled += - msg_msgcnt(msg); - tipc_node_unlock(n_ptr); - tipc_link_recv_bundle(buf); - continue; - case NAME_DISTRIBUTOR: - tipc_node_unlock(n_ptr); - tipc_named_recv(buf); - continue; - case CONN_MANAGER: - tipc_node_unlock(n_ptr); - tipc_port_recv_proto_msg(buf); - continue; - case MSG_FRAGMENTER: - l_ptr->stats.recv_fragments++; - if (tipc_link_recv_fragment(&l_ptr->defragm_buf, - &buf, &msg)) { - l_ptr->stats.recv_fragmented++; + if (ret == -1) + l_ptr->next_in_no--; + break; + case CHANGEOVER_PROTOCOL: + type = msg_type(msg); + if (link_recv_changeover_msg(&l_ptr, + &buf)) { + msg = buf_msg(buf); + seq_no = msg_seqno(msg); + if (type == ORIGINAL_MSG) goto deliver; - } - break; - case CHANGEOVER_PROTOCOL: - type = msg_type(msg); - if (link_recv_changeover_msg(&l_ptr, &buf)) { - msg = buf_msg(buf); - seq_no = msg_seqno(msg); - if (type == ORIGINAL_MSG) - goto deliver; - goto protocol_check; - } - break; - default: - buf_discard(buf); - buf = NULL; - break; + goto protocol_check; } + break; + default: + kfree_skb(buf); + buf = NULL; + break; } tipc_node_unlock(n_ptr); tipc_net_route_msg(buf); @@ -1847,23 +1849,22 @@ deliver: } tipc_node_unlock(n_ptr); cont: - buf_discard(buf); + kfree_skb(buf); } read_unlock_bh(&tipc_net_lock); } /* - * link_defer_buf(): Sort a received out-of-sequence packet - * into the deferred reception queue. - * Returns the increase of the queue length,i.e. 0 or 1 + * tipc_link_defer_pkt - Add out-of-sequence message to deferred reception queue + * + * Returns increase in queue length (i.e. 0 or 1) */ -u32 tipc_link_defer_pkt(struct sk_buff **head, - struct sk_buff **tail, +u32 tipc_link_defer_pkt(struct sk_buff **head, struct sk_buff **tail, struct sk_buff *buf) { - struct sk_buff *prev = NULL; - struct sk_buff *crs = *head; + struct sk_buff *queue_buf; + struct sk_buff **prev; u32 seq_no = buf_seqno(buf); buf->next = NULL; @@ -1881,31 +1882,30 @@ u32 tipc_link_defer_pkt(struct sk_buff **head, return 1; } - /* Scan through queue and sort it in */ - do { - struct tipc_msg *msg = buf_msg(crs); + /* Locate insertion point in queue, then insert; discard if duplicate */ + prev = head; + queue_buf = *head; + for (;;) { + u32 curr_seqno = buf_seqno(queue_buf); - if (less(seq_no, msg_seqno(msg))) { - buf->next = crs; - if (prev) - prev->next = buf; - else - *head = buf; - return 1; + if (seq_no == curr_seqno) { + kfree_skb(buf); + return 0; } - if (seq_no == msg_seqno(msg)) + + if (less(seq_no, curr_seqno)) break; - prev = crs; - crs = crs->next; - } while (crs); - /* Message is a duplicate of an existing message */ + prev = &queue_buf->next; + queue_buf = queue_buf->next; + } - buf_discard(buf); - return 0; + buf->next = queue_buf; + *prev = buf; + return 1; } -/** +/* * link_handle_out_of_seq_msg - handle arrival of out-of-sequence packet */ @@ -1930,7 +1930,7 @@ static void link_handle_out_of_seq_msg(struct tipc_link *l_ptr, if (less(seq_no, mod(l_ptr->next_in_no))) { l_ptr->stats.duplicates++; - buf_discard(buf); + kfree_skb(buf); return; } @@ -1956,6 +1956,13 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, u32 msg_size = sizeof(l_ptr->proto_msg); int r_flag; + /* Discard any previous message that was deferred due to congestion */ + + if (l_ptr->proto_msg_queue) { + kfree_skb(l_ptr->proto_msg_queue); + l_ptr->proto_msg_queue = NULL; + } + if (link_blocked(l_ptr)) return; @@ -1964,9 +1971,11 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, if ((l_ptr->owner->block_setup) && (msg_typ != RESET_MSG)) return; + /* Create protocol message with "out-of-sequence" sequence number */ + msg_set_type(msg, msg_typ); msg_set_net_plane(msg, l_ptr->b_ptr->net_plane); - msg_set_bcast_ack(msg, mod(l_ptr->owner->bclink.last_in)); + msg_set_bcast_ack(msg, l_ptr->owner->bclink.last_in); msg_set_last_bcast(msg, tipc_bclink_get_last_sent()); if (msg_typ == STATE_MSG) { @@ -2020,44 +2029,36 @@ void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, r_flag = (l_ptr->owner->working_links > tipc_link_is_up(l_ptr)); msg_set_redundant_link(msg, r_flag); msg_set_linkprio(msg, l_ptr->priority); - - /* Ensure sequence number will not fit : */ + msg_set_size(msg, msg_size); msg_set_seqno(msg, mod(l_ptr->next_out_no + (0xffff/2))); - /* Congestion? */ - - if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { - if (!l_ptr->proto_msg_queue) { - l_ptr->proto_msg_queue = - tipc_buf_acquire(sizeof(l_ptr->proto_msg)); - } - buf = l_ptr->proto_msg_queue; - if (!buf) - return; - skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - return; - } - - /* Message can be sent */ - buf = tipc_buf_acquire(msg_size); if (!buf) return; skb_copy_to_linear_data(buf, msg, sizeof(l_ptr->proto_msg)); - msg_set_size(buf_msg(buf), msg_size); - if (tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { - l_ptr->unacked_window = 0; - buf_discard(buf); + /* Defer message if bearer is already congested */ + + if (tipc_bearer_congested(l_ptr->b_ptr, l_ptr)) { + l_ptr->proto_msg_queue = buf; return; } - /* New congestion */ - tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); - l_ptr->proto_msg_queue = buf; - l_ptr->stats.bearer_congs++; + /* Defer message if attempting to send results in bearer congestion */ + + if (!tipc_bearer_send(l_ptr->b_ptr, buf, &l_ptr->media_addr)) { + tipc_bearer_schedule(l_ptr->b_ptr, l_ptr); + l_ptr->proto_msg_queue = buf; + l_ptr->stats.bearer_congs++; + return; + } + + /* Discard message if it was sent successfully */ + + l_ptr->unacked_window = 0; + kfree_skb(buf); } /* @@ -2105,6 +2106,8 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) l_ptr->owner->block_setup = WAIT_NODE_DOWN; } + link_state_event(l_ptr, RESET_MSG); + /* fall thru' */ case ACTIVATE_MSG: /* Update link settings according other endpoint's values */ @@ -2127,16 +2130,22 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) } else { l_ptr->max_pkt = l_ptr->max_pkt_target; } - l_ptr->owner->bclink.supported = (max_pkt_info != 0); + l_ptr->owner->bclink.supportable = (max_pkt_info != 0); - link_state_event(l_ptr, msg_type(msg)); + /* Synchronize broadcast link info, if not done previously */ + + if (!tipc_node_is_up(l_ptr->owner)) { + l_ptr->owner->bclink.last_sent = + l_ptr->owner->bclink.last_in = + msg_last_bcast(msg); + l_ptr->owner->bclink.oos_state = 0; + } l_ptr->peer_session = msg_session(msg); l_ptr->peer_bearer_id = msg_bearer_id(msg); - /* Synchronize broadcast sequence numbers */ - if (!tipc_node_redundant_links(l_ptr->owner)) - l_ptr->owner->bclink.last_in = mod(msg_last_bcast(msg)); + if (msg_type(msg) == ACTIVATE_MSG) + link_state_event(l_ptr, ACTIVATE_MSG); break; case STATE_MSG: @@ -2177,7 +2186,9 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) /* Protocol message before retransmits, reduce loss risk */ - tipc_bclink_check_gap(l_ptr->owner, msg_last_bcast(msg)); + if (l_ptr->owner->bclink.supported) + tipc_bclink_update_link_state(l_ptr->owner, + msg_last_bcast(msg)); if (rec_gap || (msg_probe(msg))) { tipc_link_send_proto_msg(l_ptr, STATE_MSG, @@ -2191,7 +2202,7 @@ static void link_recv_proto_msg(struct tipc_link *l_ptr, struct sk_buff *buf) break; } exit: - buf_discard(buf); + kfree_skb(buf); } @@ -2389,7 +2400,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, warn("Link changeover error, duplicate msg dropped\n"); goto exit; } - buf_discard(tunnel_buf); + kfree_skb(tunnel_buf); return 1; } @@ -2421,7 +2432,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, } else { *buf = buf_extract(tunnel_buf, INT_H_SIZE); if (*buf != NULL) { - buf_discard(tunnel_buf); + kfree_skb(tunnel_buf); return 1; } else { warn("Link changeover error, original msg dropped\n"); @@ -2429,7 +2440,7 @@ static int link_recv_changeover_msg(struct tipc_link **l_ptr, } exit: *buf = NULL; - buf_discard(tunnel_buf); + kfree_skb(tunnel_buf); return 0; } @@ -2451,7 +2462,7 @@ void tipc_link_recv_bundle(struct sk_buff *buf) pos += align(msg_size(buf_msg(obuf))); tipc_net_route_msg(obuf); } - buf_discard(buf); + kfree_skb(buf); } /* @@ -2500,11 +2511,11 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) } fragm = tipc_buf_acquire(fragm_sz + INT_H_SIZE); if (fragm == NULL) { - buf_discard(buf); + kfree_skb(buf); while (buf_chain) { buf = buf_chain; buf_chain = buf_chain->next; - buf_discard(buf); + kfree_skb(buf); } return -ENOMEM; } @@ -2521,7 +2532,7 @@ static int link_send_long_buf(struct tipc_link *l_ptr, struct sk_buff *buf) crs += fragm_sz; msg_set_type(&fragm_hdr, FRAGMENT); } - buf_discard(buf); + kfree_skb(buf); /* Append chain of fragments to send queue & send them */ @@ -2608,7 +2619,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, if (msg_type(imsg) == TIPC_MCAST_MSG) max = TIPC_MAX_USER_MSG_SIZE + MCAST_H_SIZE; if (msg_size(imsg) > max) { - buf_discard(fbuf); + kfree_skb(fbuf); return 0; } pbuf = tipc_buf_acquire(msg_size(imsg)); @@ -2623,9 +2634,11 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, set_fragm_size(pbuf, fragm_sz); set_expected_frags(pbuf, exp_fragm_cnt - 1); } else { - warn("Link unable to reassemble fragmented message\n"); + dbg("Link unable to reassemble fragmented message\n"); + kfree_skb(fbuf); + return -1; } - buf_discard(fbuf); + kfree_skb(fbuf); return 0; } else if (pbuf && (msg_type(fragm) != FIRST_FRAGMENT)) { u32 dsz = msg_data_sz(fragm); @@ -2634,7 +2647,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, u32 exp_frags = get_expected_frags(pbuf) - 1; skb_copy_to_linear_data_offset(pbuf, crs, msg_data(fragm), dsz); - buf_discard(fbuf); + kfree_skb(fbuf); /* Is message complete? */ @@ -2651,7 +2664,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, set_expected_frags(pbuf, exp_frags); return 0; } - buf_discard(fbuf); + kfree_skb(fbuf); return 0; } @@ -2682,7 +2695,7 @@ static void link_check_defragm_bufs(struct tipc_link *l_ptr) prev->next = buf->next; else l_ptr->defragm_buf = buf->next; - buf_discard(buf); + kfree_skb(buf); } buf = next; } @@ -3057,7 +3070,7 @@ struct sk_buff *tipc_link_cmd_show_stats(const void *req_tlv_area, int req_tlv_s str_len = tipc_link_stats((char *)TLV_DATA(req_tlv_area), (char *)TLV_DATA(rep_tlv), MAX_LINK_STATS_INFO); if (!str_len) { - buf_discard(buf); + kfree_skb(buf); return tipc_cfg_reply_error_string("link not found"); } diff --git a/net/tipc/log.c b/net/tipc/log.c index 952c39f..895c6e5 100644 --- a/net/tipc/log.c +++ b/net/tipc/log.c @@ -304,7 +304,7 @@ struct sk_buff *tipc_log_resize_cmd(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_TLV_ERROR); value = ntohl(*(__be32 *)TLV_DATA(req_tlv_area)); - if (value != delimit(value, 0, 32768)) + if (value > 32768) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (log size must be 0-32768)"); if (tipc_log_resize(value)) diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 3e4d3e2..e3afe16 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -106,7 +106,7 @@ int tipc_msg_build(struct tipc_msg *hdr, struct iovec const *msg_sect, if (likely(res)) return dsz; - buf_discard(*buf); + kfree_skb(*buf); *buf = NULL; return -EFAULT; } diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 7b0cda1..eba524e3 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -384,11 +384,6 @@ static inline void msg_set_destnode(struct tipc_msg *m, u32 a) msg_set_word(m, 7, a); } -static inline int msg_is_dest(struct tipc_msg *m, u32 d) -{ - return msg_short(m) || (msg_destnode(m) == d); -} - static inline u32 msg_nametype(struct tipc_msg *m) { return msg_word(m, 8); @@ -517,6 +512,16 @@ static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 16, 0x1fff, n); } +static inline u32 msg_node_sig(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_node_sig(struct tipc_msg *m, u32 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} + /* * Word 2 diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 98ebb37..d57da61 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -120,7 +120,7 @@ static void named_cluster_distribute(struct sk_buff *buf) } } - buf_discard(buf); + kfree_skb(buf); } /** @@ -239,9 +239,6 @@ exit: * * Invoked for each publication issued by a newly failed node. * Removes publication structure from name table & deletes it. - * In rare cases the link may have come back up again when this - * function is called, and we have two items representing the same - * publication. Nudge this item's key to distinguish it from the other. */ static void named_purge_publ(struct publication *publ) @@ -249,7 +246,6 @@ static void named_purge_publ(struct publication *publ) struct publication *p; write_lock_bh(&tipc_nametbl_lock); - publ->key += 1222345; p = tipc_nametbl_remove_publ(publ->type, publ->lower, publ->node, publ->ref, publ->key); if (p) @@ -316,7 +312,7 @@ void tipc_named_recv(struct sk_buff *buf) item++; } write_unlock_bh(&tipc_nametbl_lock); - buf_discard(buf); + kfree_skb(buf); } /** diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 89eb562..c6a1ae3 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -114,10 +114,8 @@ struct name_table { }; static struct name_table table; -static atomic_t rsv_publ_ok = ATOMIC_INIT(0); DEFINE_RWLOCK(tipc_nametbl_lock); - static int hash(int x) { return x & (tipc_nametbl_size - 1); @@ -270,6 +268,13 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, } info = sseq->info; + + /* Check if an identical publication already exists */ + list_for_each_entry(publ, &info->zone_list, zone_list) { + if ((publ->ref == port) && (publ->key == key) && + (!publ->node || (publ->node == node))) + return NULL; + } } else { u32 inspos; struct sub_seq *freesseq; @@ -534,10 +539,17 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, } /* - * tipc_nametbl_translate - translate name to port id + * tipc_nametbl_translate - perform name translation + * + * On entry, 'destnode' is the search domain used during translation. * - * Note: on entry 'destnode' is the search domain used during translation; - * on exit it passes back the node address of the matching port (if any) + * On exit: + * - if name translation is deferred to another node/cluster/zone, + * leaves 'destnode' unchanged (will be non-zero) and returns 0 + * - if name translation is attempted and succeeds, sets 'destnode' + * to publishing node and returns port reference (will be non-zero) + * - if name translation is attempted and fails, sets 'destnode' to 0 + * and returns 0 */ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) @@ -547,6 +559,7 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) struct publication *publ; struct name_seq *seq; u32 ref = 0; + u32 node = 0; if (!tipc_in_scope(*destnode, tipc_own_addr)) return 0; @@ -604,11 +617,12 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) } ref = publ->ref; - *destnode = publ->node; + node = publ->node; no_match: spin_unlock_bh(&seq->lock); not_found: read_unlock_bh(&tipc_nametbl_lock); + *destnode = node; return ref; } @@ -665,22 +679,7 @@ exit: return res; } -/** - * tipc_nametbl_publish_rsv - publish port name using a reserved name type - */ - -int tipc_nametbl_publish_rsv(u32 ref, unsigned int scope, - struct tipc_name_seq const *seq) -{ - int res; - - atomic_inc(&rsv_publ_ok); - res = tipc_publish(ref, scope, seq); - atomic_dec(&rsv_publ_ok); - return res; -} - -/** +/* * tipc_nametbl_publish - add name publication to network name tables */ @@ -694,11 +693,6 @@ struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, tipc_max_publications); return NULL; } - if ((type < TIPC_RESERVED_TYPES) && !atomic_read(&rsv_publ_ok)) { - warn("Publication failed, reserved name {%u,%u,%u}\n", - type, lower, upper); - return NULL; - } write_lock_bh(&tipc_nametbl_lock); table.local_publ_count++; diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 8086b42..207d59e 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -91,8 +91,6 @@ struct sk_buff *tipc_nametbl_get(const void *req_tlv_area, int req_tlv_space); u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *node); int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, struct tipc_port_list *dports); -int tipc_nametbl_publish_rsv(u32 ref, unsigned int scope, - struct tipc_name_seq const *seq); struct publication *tipc_nametbl_publish(u32 type, u32 lower, u32 upper, u32 scope, u32 port_ref, u32 key); int tipc_nametbl_withdraw(u32 type, u32 lower, u32 ref, u32 key); diff --git a/net/tipc/net.c b/net/tipc/net.c index 61afee7..d4531b0 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -117,7 +117,7 @@ static void net_route_named_msg(struct sk_buff *buf) u32 dport; if (!msg_named(msg)) { - buf_discard(buf); + kfree_skb(buf); return; } @@ -161,7 +161,7 @@ void tipc_net_route_msg(struct sk_buff *buf) tipc_port_recv_proto_msg(buf); break; default: - buf_discard(buf); + kfree_skb(buf); } return; } @@ -175,14 +175,10 @@ int tipc_net_start(u32 addr) { char addr_string[16]; - if (tipc_mode != TIPC_NODE_MODE) - return -ENOPROTOOPT; - tipc_subscr_stop(); tipc_cfg_stop(); tipc_own_addr = addr; - tipc_mode = TIPC_NET_MODE; tipc_named_reinit(); tipc_port_reinit(); @@ -201,10 +197,9 @@ void tipc_net_stop(void) { struct tipc_node *node, *t_node; - if (tipc_mode != TIPC_NET_MODE) + if (!tipc_own_addr) return; write_lock_bh(&tipc_net_lock); - tipc_mode = TIPC_NODE_MODE; tipc_bearer_stop(); tipc_bclink_stop(); list_for_each_entry_safe(node, t_node, &tipc_node_list, list) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6b226fa..a34cabc 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -39,6 +39,8 @@ #include "node.h" #include "name_distr.h" +#define NODE_HTABLE_SIZE 512 + static void node_lost_contact(struct tipc_node *n_ptr); static void node_established_contact(struct tipc_node *n_ptr); @@ -49,9 +51,19 @@ LIST_HEAD(tipc_node_list); static u32 tipc_num_nodes; static atomic_t tipc_num_links = ATOMIC_INIT(0); -u32 tipc_own_tag; -/** +/* + * A trivial power-of-two bitmask technique is used for speed, since this + * operation is done for every incoming TIPC packet. The number of hash table + * entries has been chosen so that no hash chain exceeds 8 nodes and will + * usually be much smaller (typically only a single node). + */ +static inline unsigned int tipc_hashfn(u32 addr) +{ + return addr & (NODE_HTABLE_SIZE - 1); +} + +/* * tipc_node_find - locate specified node object, if it exists */ @@ -113,6 +125,7 @@ struct tipc_node *tipc_node_create(u32 addr) } list_add_tail(&n_ptr->list, &temp_node->list); n_ptr->block_setup = WAIT_PEER_DOWN; + n_ptr->signature = INVALID_NODE_SIG; tipc_num_nodes++; @@ -253,63 +266,14 @@ void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr) n_ptr->link_cnt--; } -/* - * Routing table management - five cases to handle: - * - * 1: A link towards a zone/cluster external node comes up. - * => Send a multicast message updating routing tables of all - * system nodes within own cluster that the new destination - * can be reached via this node. - * (node.establishedContact()=>cluster.multicastNewRoute()) - * - * 2: A link towards a slave node comes up. - * => Send a multicast message updating routing tables of all - * system nodes within own cluster that the new destination - * can be reached via this node. - * (node.establishedContact()=>cluster.multicastNewRoute()) - * => Send a message to the slave node about existence - * of all system nodes within cluster: - * (node.establishedContact()=>cluster.sendLocalRoutes()) - * - * 3: A new cluster local system node becomes available. - * => Send message(s) to this particular node containing - * information about all cluster external and slave - * nodes which can be reached via this node. - * (node.establishedContact()==>network.sendExternalRoutes()) - * (node.establishedContact()==>network.sendSlaveRoutes()) - * => Send messages to all directly connected slave nodes - * containing information about the existence of the new node - * (node.establishedContact()=>cluster.multicastNewRoute()) - * - * 4: The link towards a zone/cluster external node or slave - * node goes down. - * => Send a multcast message updating routing tables of all - * nodes within cluster that the new destination can not any - * longer be reached via this node. - * (node.lostAllLinks()=>cluster.bcastLostRoute()) - * - * 5: A cluster local system node becomes unavailable. - * => Remove all references to this node from the local - * routing tables. Note: This is a completely node - * local operation. - * (node.lostAllLinks()=>network.removeAsRouter()) - * => Send messages to all directly connected slave nodes - * containing information about loss of the node - * (node.establishedContact()=>cluster.multicastLostRoute()) - * - */ - static void node_established_contact(struct tipc_node *n_ptr) { tipc_k_signal((Handler)tipc_named_node_up, n_ptr->addr); - /* Syncronize broadcast acks */ - n_ptr->bclink.acked = tipc_bclink_get_last_sent(); - - if (n_ptr->bclink.supported) { + if (n_ptr->bclink.supportable) { + n_ptr->bclink.acked = tipc_bclink_get_last_sent(); tipc_bclink_add_node(n_ptr->addr); - if (n_ptr->addr < tipc_own_addr) - tipc_own_tag++; + n_ptr->bclink.supported = 1; } } @@ -338,22 +302,20 @@ static void node_lost_contact(struct tipc_node *n_ptr) /* Flush broadcast link info associated with lost node */ if (n_ptr->bclink.supported) { - n_ptr->bclink.gap_after = n_ptr->bclink.gap_to = 0; while (n_ptr->bclink.deferred_head) { struct sk_buff *buf = n_ptr->bclink.deferred_head; n_ptr->bclink.deferred_head = buf->next; - buf_discard(buf); + kfree_skb(buf); } + n_ptr->bclink.deferred_size = 0; if (n_ptr->bclink.defragm) { - buf_discard(n_ptr->bclink.defragm); + kfree_skb(n_ptr->bclink.defragm); n_ptr->bclink.defragm = NULL; } tipc_bclink_remove_node(n_ptr->addr); tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ); - if (n_ptr->addr < tipc_own_addr) - tipc_own_tag--; n_ptr->bclink.supported = 0; } @@ -444,12 +406,12 @@ struct sk_buff *tipc_node_get_links(const void *req_tlv_area, int req_tlv_space) return tipc_cfg_reply_error_string(TIPC_CFG_INVALID_VALUE " (network address)"); - if (tipc_mode != TIPC_NET_MODE) + if (!tipc_own_addr) return tipc_cfg_reply_none(); read_lock_bh(&tipc_net_lock); - /* Get space for all unicast links + multicast link */ + /* Get space for all unicast links + broadcast link */ payload_size = TLV_SPACE(sizeof(link_info)) * (atomic_read(&tipc_num_links) + 1); diff --git a/net/tipc/node.h b/net/tipc/node.h index 0b1c5f8..72561c9 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -42,6 +42,11 @@ #include "net.h" #include "bearer.h" +/* + * Out-of-range value for node signature + */ +#define INVALID_NODE_SIG 0x10000 + /* Flags used to block (re)establishment of contact with a neighboring node */ #define WAIT_PEER_DOWN 0x0001 /* wait to see that peer's links are down */ @@ -61,13 +66,15 @@ * @block_setup: bit mask of conditions preventing link establishment to node * @link_cnt: number of links to node * @permit_changeover: non-zero if node has redundant links to this system + * @signature: node instance identifier * @bclink: broadcast-related info + * @supportable: non-zero if node supports TIPC b'cast link capability * @supported: non-zero if node supports TIPC b'cast capability * @acked: sequence # of last outbound b'cast message acknowledged by node * @last_in: sequence # of last in-sequence b'cast message received from node - * @gap_after: sequence # of last message not requiring a NAK request - * @gap_to: sequence # of last message requiring a NAK request - * @nack_sync: counter that determines when NAK requests should be sent + * @last_sent: sequence # of last b'cast message sent by node + * @oos_state: state tracker for handling OOS b'cast messages + * @deferred_size: number of OOS b'cast messages in deferred queue * @deferred_head: oldest OOS b'cast message received from node * @deferred_tail: newest OOS b'cast message received from node * @defragm: list of partially reassembled b'cast message fragments from node @@ -85,35 +92,23 @@ struct tipc_node { int working_links; int block_setup; int permit_changeover; + u32 signature; struct { - int supported; + u8 supportable; + u8 supported; u32 acked; u32 last_in; - u32 gap_after; - u32 gap_to; - u32 nack_sync; + u32 last_sent; + u32 oos_state; + u32 deferred_size; struct sk_buff *deferred_head; struct sk_buff *deferred_tail; struct sk_buff *defragm; } bclink; }; -#define NODE_HTABLE_SIZE 512 extern struct list_head tipc_node_list; -/* - * A trivial power-of-two bitmask technique is used for speed, since this - * operation is done for every incoming TIPC packet. The number of hash table - * entries has been chosen so that no hash chain exceeds 8 nodes and will - * usually be much smaller (typically only a single node). - */ -static inline unsigned int tipc_hashfn(u32 addr) -{ - return addr & (NODE_HTABLE_SIZE - 1); -} - -extern u32 tipc_own_tag; - struct tipc_node *tipc_node_find(u32 addr); struct tipc_node *tipc_node_create(u32 addr); void tipc_node_delete(struct tipc_node *n_ptr); diff --git a/net/tipc/port.c b/net/tipc/port.c index d91efc6..94d2904 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -116,13 +116,13 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, ibuf = skb_copy(buf, GFP_ATOMIC); if (ibuf == NULL) { tipc_port_list_free(&dports); - buf_discard(buf); + kfree_skb(buf); return -ENOMEM; } } res = tipc_bclink_send_msg(buf); if ((res < 0) && (dports.count != 0)) - buf_discard(ibuf); + kfree_skb(ibuf); } else { ibuf = buf; } @@ -187,7 +187,7 @@ void tipc_port_recv_mcast(struct sk_buff *buf, struct tipc_port_list *dp) } } exit: - buf_discard(buf); + kfree_skb(buf); tipc_port_list_free(dp); } @@ -400,15 +400,16 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) /* send self-abort message when rejecting on a connected port */ if (msg_connected(msg)) { - struct sk_buff *abuf = NULL; struct tipc_port *p_ptr = tipc_port_lock(msg_destport(msg)); if (p_ptr) { + struct sk_buff *abuf = NULL; + if (p_ptr->connected) abuf = port_build_self_abort_msg(p_ptr, err); tipc_port_unlock(p_ptr); + tipc_net_route_msg(abuf); } - tipc_net_route_msg(abuf); } /* send returned message & dispose of rejected message */ @@ -419,7 +420,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) else tipc_link_send(rbuf, src_node, msg_link_selector(rmsg)); exit: - buf_discard(buf); + kfree_skb(buf); return data_sz; } @@ -567,7 +568,7 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) tipc_port_unlock(p_ptr); exit: tipc_net_route_msg(r_buf); - buf_discard(buf); + kfree_skb(buf); } static void port_print(struct tipc_port *p_ptr, struct print_buf *buf, int full_id) @@ -758,7 +759,7 @@ static void port_dispatcher_sigh(void *dummy) } } if (buf) - buf_discard(buf); + kfree_skb(buf); buf = next; continue; err: @@ -812,7 +813,7 @@ err: } } if (buf) - buf_discard(buf); + kfree_skb(buf); buf = next; continue; reject: @@ -1053,8 +1054,6 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) msg = &p_ptr->phdr; msg_set_destnode(msg, peer->node); msg_set_destport(msg, peer->ref); - msg_set_orignode(msg, tipc_own_addr); - msg_set_origport(msg, p_ptr->ref); msg_set_type(msg, TIPC_CONN_MSG); msg_set_lookup_scope(msg, 0); msg_set_hdr_sz(msg, SHORT_H_SIZE); @@ -1132,6 +1131,49 @@ int tipc_shutdown(u32 ref) return tipc_disconnect(ref); } +/** + * tipc_port_recv_msg - receive message from lower layer and deliver to port user + */ + +int tipc_port_recv_msg(struct sk_buff *buf) +{ + struct tipc_port *p_ptr; + struct tipc_msg *msg = buf_msg(buf); + u32 destport = msg_destport(msg); + u32 dsz = msg_data_sz(msg); + u32 err; + + /* forward unresolved named message */ + if (unlikely(!destport)) { + tipc_net_route_msg(buf); + return dsz; + } + + /* validate destination & pass to port, otherwise reject message */ + p_ptr = tipc_port_lock(destport); + if (likely(p_ptr)) { + if (likely(p_ptr->connected)) { + if ((unlikely(msg_origport(msg) != + tipc_peer_port(p_ptr))) || + (unlikely(msg_orignode(msg) != + tipc_peer_node(p_ptr))) || + (unlikely(!msg_connected(msg)))) { + err = TIPC_ERR_NO_PORT; + tipc_port_unlock(p_ptr); + goto reject; + } + } + err = p_ptr->dispatcher(p_ptr, buf); + tipc_port_unlock(p_ptr); + if (likely(!err)) + return dsz; + } else { + err = TIPC_ERR_NO_PORT; + } +reject: + return tipc_reject_msg(buf, err); +} + /* * tipc_port_recv_sections(): Concatenate and deliver sectioned * message for this node. @@ -1210,8 +1252,6 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, msg = &p_ptr->phdr; msg_set_type(msg, TIPC_NAMED_MSG); - msg_set_orignode(msg, tipc_own_addr); - msg_set_origport(msg, ref); msg_set_hdr_sz(msg, NAMED_H_SIZE); msg_set_nametype(msg, name->type); msg_set_nameinst(msg, name->instance); @@ -1220,7 +1260,7 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, msg_set_destnode(msg, destnode); msg_set_destport(msg, destport); - if (likely(destport)) { + if (likely(destport || destnode)) { if (likely(destnode == tipc_own_addr)) res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, total_len); @@ -1261,8 +1301,6 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg = &p_ptr->phdr; msg_set_type(msg, TIPC_DIRECT_MSG); msg_set_lookup_scope(msg, 0); - msg_set_orignode(msg, tipc_own_addr); - msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); msg_set_destport(msg, dest->ref); msg_set_hdr_sz(msg, BASIC_H_SIZE); @@ -1301,8 +1339,6 @@ int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, msg = &p_ptr->phdr; msg_set_type(msg, TIPC_DIRECT_MSG); - msg_set_orignode(msg, tipc_own_addr); - msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); msg_set_destport(msg, dest->ref); msg_set_hdr_sz(msg, BASIC_H_SIZE); diff --git a/net/tipc/port.h b/net/tipc/port.h index f751807..9b88531 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -205,6 +205,7 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr); /* * TIPC messaging routines */ +int tipc_port_recv_msg(struct sk_buff *buf); int tipc_send(u32 portref, unsigned int num_sect, struct iovec const *msg_sect, unsigned int total_len); @@ -271,45 +272,4 @@ static inline int tipc_port_congested(struct tipc_port *p_ptr) return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); } -/** - * tipc_port_recv_msg - receive message from lower layer and deliver to port user - */ - -static inline int tipc_port_recv_msg(struct sk_buff *buf) -{ - struct tipc_port *p_ptr; - struct tipc_msg *msg = buf_msg(buf); - u32 destport = msg_destport(msg); - u32 dsz = msg_data_sz(msg); - u32 err; - - /* forward unresolved named message */ - if (unlikely(!destport)) { - tipc_net_route_msg(buf); - return dsz; - } - - /* validate destination & pass to port, otherwise reject message */ - p_ptr = tipc_port_lock(destport); - if (likely(p_ptr)) { - if (likely(p_ptr->connected)) { - if ((unlikely(msg_origport(msg) != tipc_peer_port(p_ptr))) || - (unlikely(msg_orignode(msg) != tipc_peer_node(p_ptr))) || - (unlikely(!msg_connected(msg)))) { - err = TIPC_ERR_NO_PORT; - tipc_port_unlock(p_ptr); - goto reject; - } - } - err = p_ptr->dispatcher(p_ptr, buf); - tipc_port_unlock(p_ptr); - if (likely(!err)) - return dsz; - } else { - err = TIPC_ERR_NO_PORT; - } -reject: - return tipc_reject_msg(buf, err); -} - #endif diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e2f7c5d..29e957f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -126,7 +126,7 @@ static atomic_t tipc_queue_size = ATOMIC_INIT(0); static void advance_rx_queue(struct sock *sk) { - buf_discard(__skb_dequeue(&sk->sk_receive_queue)); + kfree_skb(__skb_dequeue(&sk->sk_receive_queue)); atomic_dec(&tipc_queue_size); } @@ -142,7 +142,7 @@ static void discard_rx_queue(struct sock *sk) while ((buf = __skb_dequeue(&sk->sk_receive_queue))) { atomic_dec(&tipc_queue_size); - buf_discard(buf); + kfree_skb(buf); } } @@ -288,7 +288,7 @@ static int release(struct socket *sock) break; atomic_dec(&tipc_queue_size); if (TIPC_SKB_CB(buf)->handle != 0) - buf_discard(buf); + kfree_skb(buf); else { if ((sock->state == SS_CONNECTING) || (sock->state == SS_CONNECTED)) { @@ -355,6 +355,9 @@ static int bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) else if (addr->addrtype != TIPC_ADDR_NAMESEQ) return -EAFNOSUPPORT; + if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) + return -EACCES; + return (addr->scope > 0) ? tipc_publish(portref, addr->scope, &addr->addr.nameseq) : tipc_withdraw(portref, -addr->scope, &addr->addr.nameseq); @@ -1612,7 +1615,7 @@ restart: if (buf) { atomic_dec(&tipc_queue_size); if (TIPC_SKB_CB(buf)->handle != 0) { - buf_discard(buf); + kfree_skb(buf); goto restart; } tipc_disconnect(tport->ref); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 8c49566..b2964e9 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -552,7 +552,7 @@ int tipc_subscr_start(void) if (res) goto failed; - res = tipc_nametbl_publish_rsv(topsrv.setup_port, TIPC_NODE_SCOPE, &seq); + res = tipc_publish(topsrv.setup_port, TIPC_NODE_SCOPE, &seq); if (res) { tipc_deleteport(topsrv.setup_port); topsrv.setup_port = 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 85d3bb7..8ee85aa 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -530,6 +530,16 @@ static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *, static int unix_seqpacket_recvmsg(struct kiocb *, struct socket *, struct msghdr *, size_t, int); +static void unix_set_peek_off(struct sock *sk, int val) +{ + struct unix_sock *u = unix_sk(sk); + + mutex_lock(&u->readlock); + sk->sk_peek_off = val; + mutex_unlock(&u->readlock); +} + + static const struct proto_ops unix_stream_ops = { .family = PF_UNIX, .owner = THIS_MODULE, @@ -549,6 +559,7 @@ static const struct proto_ops unix_stream_ops = { .recvmsg = unix_stream_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static const struct proto_ops unix_dgram_ops = { @@ -570,6 +581,7 @@ static const struct proto_ops unix_dgram_ops = { .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static const struct proto_ops unix_seqpacket_ops = { @@ -591,6 +603,7 @@ static const struct proto_ops unix_seqpacket_ops = { .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, + .set_peek_off = unix_set_peek_off, }; static struct proto unix_proto = { @@ -1756,6 +1769,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, int noblock = flags & MSG_DONTWAIT; struct sk_buff *skb; int err; + int peeked, skip; err = -EOPNOTSUPP; if (flags&MSG_OOB) @@ -1769,7 +1783,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; } - skb = skb_recv_datagram(sk, flags, noblock, &err); + skip = sk_peek_offset(sk, flags); + + skb = __skb_recv_datagram(sk, flags, &peeked, &skip, &err); if (!skb) { unix_state_lock(sk); /* Signal EOF on disconnected non-blocking SEQPACKET socket. */ @@ -1786,12 +1802,12 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (msg->msg_name) unix_copy_addr(msg, skb->sk); - if (size > skb->len) - size = skb->len; - else if (size < skb->len) + if (size > skb->len - skip) + size = skb->len - skip; + else if (size < skb->len - skip) msg->msg_flags |= MSG_TRUNC; - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size); + err = skb_copy_datagram_iovec(skb, skip, msg->msg_iov, size); if (err) goto out_free; @@ -1808,6 +1824,8 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (!(flags & MSG_PEEK)) { if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); + + sk_peek_offset_bwd(sk, skb->len); } else { /* It is questionable: on PEEK we could: - do not return fds - good, but too simple 8) @@ -1821,10 +1839,13 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, clearly however! */ + + sk_peek_offset_fwd(sk, size); + if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); } - err = size; + err = (flags & MSG_TRUNC) ? skb->len - skip : size; scm_recv(sock, msg, siocb->scm, flags); @@ -1884,6 +1905,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, int target; int err = 0; long timeo; + int skip; err = -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) @@ -1913,12 +1935,15 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; } + skip = sk_peek_offset(sk, flags); + do { int chunk; struct sk_buff *skb; unix_state_lock(sk); skb = skb_peek(&sk->sk_receive_queue); +again: if (skb == NULL) { unix_sk(sk)->recursion_level = 0; if (copied >= target) @@ -1953,6 +1978,13 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, unix_state_unlock(sk); break; } + + if (skip >= skb->len) { + skip -= skb->len; + skb = skb_peek_next(skb, &sk->sk_receive_queue); + goto again; + } + unix_state_unlock(sk); if (check_creds) { @@ -1972,8 +2004,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, sunaddr = NULL; } - chunk = min_t(unsigned int, skb->len, size); - if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { + chunk = min_t(unsigned int, skb->len - skip, size); + if (memcpy_toiovec(msg->msg_iov, skb->data + skip, chunk)) { if (copied == 0) copied = -EFAULT; break; @@ -1985,6 +2017,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (!(flags & MSG_PEEK)) { skb_pull(skb, chunk); + sk_peek_offset_bwd(sk, chunk); + if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); @@ -2002,6 +2036,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); + sk_peek_offset_fwd(sk, chunk); + break; } } while (size); diff --git a/net/unix/diag.c b/net/unix/diag.c index 6b7697fd..4195555 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -301,10 +301,12 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) if (nlmsg_len(h) < hdrlen) return -EINVAL; - if (h->nlmsg_flags & NLM_F_DUMP) - return netlink_dump_start(sock_diag_nlsk, skb, h, - unix_diag_dump, NULL, 0); - else + if (h->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .dump = unix_diag_dump, + }; + return netlink_dump_start(sock_diag_nlsk, skb, h, &c); + } else return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h)); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 66b84fb..7128dde 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2299,8 +2299,13 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; - return netlink_dump_start(net->xfrm.nlsk, skb, nlh, - link->dump, link->done, 0); + { + struct netlink_dump_control c = { + .dump = link->dump, + .done = link->done, + }; + return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c); + } } err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs, XFRMA_MAX, |