From 62bb2ac5cb6c2f813e151617525ec518e2d1c649 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 17 Feb 2010 21:27:26 +0100 Subject: mac80211: deprecate RX status noise The noise value as is won't be used, isn't filled by most drivers and doesn't really make a whole lot of sense on a per packet basis -- proper cfg80211 survey support in mac80211 will need to be different. Mark the struct member as deprecated so it will be removed from drivers. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 45d7d44d7cb..936bc410d06 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -543,7 +543,7 @@ enum mac80211_rx_flags { * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* - * @noise: noise when receiving this frame, in dBm. + * @noise: noise when receiving this frame, in dBm (DEPRECATED). * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT rates are use (RX_FLAG_HT) @@ -554,7 +554,7 @@ struct ieee80211_rx_status { enum ieee80211_band band; int freq; int signal; - int noise; + int noise __deprecated; int antenna; int rate_idx; int flag; -- cgit v1.2.3-70-g09d2 From 372e6c8f1f7b2bb68f9992d2e664925c73552a1d Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:09 +0000 Subject: ipv6: convert temporary address list to list macros Use list macros instead of open coded linked list. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 4 ++-- net/ipv6/addrconf.c | 30 ++++++++++++------------------ 2 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 545d8b059be..09d906460a4 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -58,7 +58,7 @@ struct inet6_ifaddr { struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ #ifdef CONFIG_IPV6_PRIVACY - struct inet6_ifaddr *tmp_next; /* next addr in tempaddr_lst */ + struct list_head tmp_list; struct inet6_ifaddr *ifpub; int regen_count; #endif @@ -175,7 +175,7 @@ struct inet6_dev { #ifdef CONFIG_IPV6_PRIVACY u8 rndid[8]; struct timer_list regen_timer; - struct inet6_ifaddr *tempaddr_list; + struct list_head tempaddr_list; #endif struct neigh_parms *nd_parms; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8d41abc40db..f372f895cd4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -401,6 +401,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) #endif #ifdef CONFIG_IPV6_PRIVACY + INIT_LIST_HEAD(&ndev->tempaddr_list); setup_timer(&ndev->regen_timer, ipv6_regen_rndid, (unsigned long)ndev); if ((dev->flags&IFF_LOOPBACK) || dev->type == ARPHRD_TUNNEL || @@ -679,8 +680,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, #ifdef CONFIG_IPV6_PRIVACY if (ifa->flags&IFA_F_TEMPORARY) { - ifa->tmp_next = idev->tempaddr_list; - idev->tempaddr_list = ifa; + list_add(&ifa->tmp_list, &idev->tempaddr_list); in6_ifa_hold(ifa); } #endif @@ -732,19 +732,12 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) write_lock_bh(&idev->lock); #ifdef CONFIG_IPV6_PRIVACY if (ifp->flags&IFA_F_TEMPORARY) { - for (ifap = &idev->tempaddr_list; (ifa=*ifap) != NULL; - ifap = &ifa->tmp_next) { - if (ifa == ifp) { - *ifap = ifa->tmp_next; - if (ifp->ifpub) { - in6_ifa_put(ifp->ifpub); - ifp->ifpub = NULL; - } - __in6_ifa_put(ifp); - ifa->tmp_next = NULL; - break; - } + list_del(&ifp->tmp_list); + if (ifp->ifpub) { + in6_ifa_put(ifp->ifpub); + ifp->ifpub = NULL; } + __in6_ifa_put(ifp); } #endif @@ -1970,7 +1963,7 @@ ok: #ifdef CONFIG_IPV6_PRIVACY read_lock_bh(&in6_dev->lock); /* update all temporary addresses in the list */ - for (ift=in6_dev->tempaddr_list; ift; ift=ift->tmp_next) { + list_for_each_entry(ift, &in6_dev->tempaddr_list, tmp_list) { /* * When adjusting the lifetimes of an existing * temporary address, only lower the lifetimes. @@ -2675,9 +2668,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) in6_dev_put(idev); /* clear tempaddr list */ - while ((ifa = idev->tempaddr_list) != NULL) { - idev->tempaddr_list = ifa->tmp_next; - ifa->tmp_next = NULL; + while (!list_empty(&idev->tempaddr_list)) { + ifa = list_first_entry(&idev->tempaddr_list, + struct inet6_ifaddr, tmp_list); + list_del(&ifa->tmp_list); ifa->dead = 1; write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); -- cgit v1.2.3-70-g09d2 From c2e21293c054817c42eb5fa9c613d2ad51954136 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:10 +0000 Subject: ipv6: convert addrconf list to hlist Using hash list macros, simplifies code and helps later RCU. This patch includes some initialization that is not strictly necessary, since an empty hlist node/list is all zero; and list is in BSS and node is allocated with kzalloc. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/if_inet6.h | 2 +- net/ipv6/addrconf.c | 128 ++++++++++++++++++++----------------------------- 2 files changed, 54 insertions(+), 76 deletions(-) (limited to 'include/net') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 09d906460a4..49840154151 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -54,7 +54,7 @@ struct inet6_ifaddr { struct inet6_dev *idev; struct rt6_info *rt; - struct inet6_ifaddr *lst_next; /* next addr in addr_lst */ + struct hlist_node addr_lst; struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ #ifdef CONFIG_IPV6_PRIVACY diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f372f895cd4..0488b9f8071 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -126,7 +126,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev); /* * Configured unicast address hash table */ -static struct inet6_ifaddr *inet6_addr_lst[IN6_ADDR_HSIZE]; +static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; static DEFINE_RWLOCK(addrconf_hash_lock); static void addrconf_verify(unsigned long); @@ -528,7 +528,7 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { WARN_ON(ifp->if_next != NULL); - WARN_ON(ifp->lst_next != NULL); + WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG printk(KERN_DEBUG "inet6_ifa_finish_destroy\n"); @@ -643,6 +643,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, spin_lock_init(&ifa->lock); init_timer(&ifa->timer); + INIT_HLIST_NODE(&ifa->addr_lst); ifa->timer.data = (unsigned long) ifa; ifa->scope = scope; ifa->prefix_len = pfxlen; @@ -669,8 +670,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, /* Add to big hash table */ hash = ipv6_addr_hash(addr); - ifa->lst_next = inet6_addr_lst[hash]; - inet6_addr_lst[hash] = ifa; + hlist_add_head(&ifa->addr_lst, &inet6_addr_lst[hash]); in6_ifa_hold(ifa); write_unlock(&addrconf_hash_lock); @@ -718,15 +718,8 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ifp->dead = 1; write_lock_bh(&addrconf_hash_lock); - for (ifap = &inet6_addr_lst[hash]; (ifa=*ifap) != NULL; - ifap = &ifa->lst_next) { - if (ifa == ifp) { - *ifap = ifa->lst_next; - __in6_ifa_put(ifp); - ifa->lst_next = NULL; - break; - } - } + hlist_del_init(&ifp->addr_lst); + __in6_ifa_put(ifp); write_unlock_bh(&addrconf_hash_lock); write_lock_bh(&idev->lock); @@ -1277,11 +1270,12 @@ static int ipv6_count_addresses(struct inet6_dev *idev) int ipv6_chk_addr(struct net *net, struct in6_addr *addr, struct net_device *dev, int strict) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp = NULL; + struct hlist_node *node; u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -1300,10 +1294,11 @@ static int ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp; + struct hlist_node *node; u8 hash = ipv6_addr_hash(addr); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1342,11 +1337,12 @@ EXPORT_SYMBOL(ipv6_chk_prefix); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, struct net_device *dev, int strict) { - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp = NULL; + struct hlist_node *node; u8 hash = ipv6_addr_hash(addr); read_lock_bh(&addrconf_hash_lock); - for(ifp = inet6_addr_lst[hash]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -2612,7 +2608,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct inet6_dev *idev; struct inet6_ifaddr *ifa, *keep_list, **bifa; struct net *net = dev_net(dev); - int i; ASSERT_RTNL(); @@ -2637,25 +2632,6 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* Step 2: clear hash table */ - for (i=0; iidev == idev && - (how || !(ifa->flags&IFA_F_PERMANENT) || - ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { - *bifa = ifa->lst_next; - ifa->lst_next = NULL; - __in6_ifa_put(ifa); - continue; - } - bifa = &ifa->lst_next; - } - write_unlock_bh(&addrconf_hash_lock); - } - write_lock_bh(&idev->lock); /* Step 3: clear flags for stateless addrconf */ @@ -2721,6 +2697,12 @@ static int addrconf_ifdown(struct net_device *dev, int how) } write_unlock_bh(&idev->lock); + /* clear hash table */ + write_lock_bh(&addrconf_hash_lock); + hlist_del_init(&ifa->addr_lst); + __in6_ifa_put(ifa); + write_unlock_bh(&addrconf_hash_lock); + __ipv6_ifa_notify(RTM_DELADDR, ifa); atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); in6_ifa_put(ifa); @@ -2963,36 +2945,37 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { - ifa = inet6_addr_lst[state->bucket]; - - while (ifa && !net_eq(dev_net(ifa->idev->dev), net)) - ifa = ifa->lst_next; - if (ifa) - break; + struct hlist_node *n; + hlist_for_each_entry(ifa, n, + &inet6_addr_lst[state->bucket], addr_lst) { + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; + } } - return ifa; + return NULL; } -static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct inet6_ifaddr *ifa) +static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, + struct inet6_ifaddr *ifa) { struct if6_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + struct hlist_node *n = &ifa->addr_lst; - ifa = ifa->lst_next; -try_again: - if (ifa) { - if (!net_eq(dev_net(ifa->idev->dev), net)) { - ifa = ifa->lst_next; - goto try_again; - } + hlist_for_each_entry_continue(ifa, n, addr_lst) { + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; } - if (!ifa && ++state->bucket < IN6_ADDR_HSIZE) { - ifa = inet6_addr_lst[state->bucket]; - goto try_again; + while (++state->bucket < IN6_ADDR_HSIZE) { + hlist_for_each_entry(ifa, n, + &inet6_addr_lst[state->bucket], addr_lst) { + if (net_eq(dev_net(ifa->idev->dev), net)) + return ifa; + } } - return ifa; + return NULL; } static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) @@ -3094,10 +3077,12 @@ void if6_proc_exit(void) int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) { int ret = 0; - struct inet6_ifaddr * ifp; + struct inet6_ifaddr *ifp = NULL; + struct hlist_node *n; u8 hash = ipv6_addr_hash(addr); + read_lock_bh(&addrconf_hash_lock); - for (ifp = inet6_addr_lst[hash]; ifp; ifp = ifp->lst_next) { + hlist_for_each_entry(ifp, n, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3118,6 +3103,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) static void addrconf_verify(unsigned long foo) { struct inet6_ifaddr *ifp; + struct hlist_node *node; unsigned long now, next; int i; @@ -3131,7 +3117,7 @@ static void addrconf_verify(unsigned long foo) restart: read_lock(&addrconf_hash_lock); - for (ifp=inet6_addr_lst[i]; ifp; ifp=ifp->lst_next) { + hlist_for_each_entry(ifp, node, &inet6_addr_lst[i], addr_lst) { unsigned long age; #ifdef CONFIG_IPV6_PRIVACY unsigned long regen_advance; @@ -4550,7 +4536,7 @@ EXPORT_SYMBOL(unregister_inet6addr_notifier); int __init addrconf_init(void) { - int err; + int i, err; if ((err = ipv6_addr_label_init()) < 0) { printk(KERN_CRIT "IPv6 Addrconf: cannot initialize default policy table: %d.\n", @@ -4585,6 +4571,9 @@ int __init addrconf_init(void) if (err) goto errlo; + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_addr_lst[i]); + register_netdevice_notifier(&ipv6_dev_notf); addrconf_verify(0); @@ -4613,7 +4602,6 @@ errlo: void addrconf_cleanup(void) { - struct inet6_ifaddr *ifa; struct net_device *dev; int i; @@ -4634,18 +4622,8 @@ void addrconf_cleanup(void) * Check hash table. */ write_lock_bh(&addrconf_hash_lock); - for (i=0; i < IN6_ADDR_HSIZE; i++) { - for (ifa=inet6_addr_lst[i]; ifa; ) { - struct inet6_ifaddr *bifa; - - bifa = ifa; - ifa = ifa->lst_next; - printk(KERN_DEBUG "bug: IPv6 address leakage detected: ifa=%p\n", bifa); - /* Do not free it; something is wrong. - Now we can investigate it with debugger. - */ - } - } + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_addr_lst[i])); write_unlock_bh(&addrconf_hash_lock); del_timer(&addr_chk_timer); -- cgit v1.2.3-70-g09d2 From 5c578aedcb21d79eeb4e9cf04ca5b276ac82614c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:11 +0000 Subject: IPv6: convert addrconf hash list to RCU Convert from reader/writer lock to RCU and spinlock for addrconf hash list. Adds an additional helper macro for hlist_for_each_entry_continue_rcu to handle the continue case. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/linux/rculist.h | 13 ++++++++ include/net/if_inet6.h | 1 + net/ipv6/addrconf.c | 85 +++++++++++++++++++++++++------------------------ 3 files changed, 58 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 2c9b46cff3d..004908b104d 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -428,5 +428,18 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev, ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) +/** + * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point + * @tpos: the type * to use as a loop cursor. + * @pos: the &struct hlist_node to use as a loop cursor. + * @member: the name of the hlist_node within the struct. + */ +#define hlist_for_each_entry_continue_rcu(tpos, pos, member) \ + for (pos = rcu_dereference((pos)->next); \ + pos && ({ prefetch(pos->next); 1; }) && \ + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \ + pos = rcu_dereference(pos->next)) + + #endif /* __KERNEL__ */ #endif diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 49840154151..22a00b1d2c3 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,6 +64,7 @@ struct inet6_ifaddr { #endif int dead; + struct rcu_head rcu; }; struct ip6_sf_socklist { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 0488b9f8071..7ffd5eeab96 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -127,7 +127,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev); * Configured unicast address hash table */ static struct hlist_head inet6_addr_lst[IN6_ADDR_HSIZE]; -static DEFINE_RWLOCK(addrconf_hash_lock); +static DEFINE_SPINLOCK(addrconf_hash_lock); static void addrconf_verify(unsigned long); @@ -523,8 +523,13 @@ static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) } #endif -/* Nobody refers to this ifaddr, destroy it */ +static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head) +{ + struct inet6_ifaddr *ifp = container_of(head, struct inet6_ifaddr, rcu); + kfree(ifp); +} +/* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { WARN_ON(ifp->if_next != NULL); @@ -545,7 +550,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) } dst_release(&ifp->rt->u.dst); - kfree(ifp); + call_rcu(&ifp->rcu, inet6_ifa_finish_destroy_rcu); } static void @@ -616,7 +621,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out2; } - write_lock(&addrconf_hash_lock); + spin_lock(&addrconf_hash_lock); /* Ignore adding duplicate addresses on an interface */ if (ipv6_chk_same_addr(dev_net(idev->dev), addr, idev->dev)) { @@ -670,9 +675,9 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, /* Add to big hash table */ hash = ipv6_addr_hash(addr); - hlist_add_head(&ifa->addr_lst, &inet6_addr_lst[hash]); + hlist_add_head_rcu(&ifa->addr_lst, &inet6_addr_lst[hash]); in6_ifa_hold(ifa); - write_unlock(&addrconf_hash_lock); + spin_unlock(&addrconf_hash_lock); write_lock(&idev->lock); /* Add to inet6_dev unicast addr list. */ @@ -699,7 +704,7 @@ out2: return ifa; out: - write_unlock(&addrconf_hash_lock); + spin_unlock(&addrconf_hash_lock); goto out2; } @@ -717,10 +722,10 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ifp->dead = 1; - write_lock_bh(&addrconf_hash_lock); - hlist_del_init(&ifp->addr_lst); + spin_lock_bh(&addrconf_hash_lock); + hlist_del_init_rcu(&ifp->addr_lst); __in6_ifa_put(ifp); - write_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&addrconf_hash_lock); write_lock_bh(&idev->lock); #ifdef CONFIG_IPV6_PRIVACY @@ -1274,8 +1279,8 @@ int ipv6_chk_addr(struct net *net, struct in6_addr *addr, struct hlist_node *node; u8 hash = ipv6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -1285,7 +1290,8 @@ int ipv6_chk_addr(struct net *net, struct in6_addr *addr, break; } } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); + return ifp != NULL; } EXPORT_SYMBOL(ipv6_chk_addr); @@ -1341,8 +1347,8 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add struct hlist_node *node; u8 hash = ipv6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - hlist_for_each_entry(ifp, node, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr)) { @@ -1353,7 +1359,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add } } } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); return ifp; } @@ -2698,10 +2704,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_unlock_bh(&idev->lock); /* clear hash table */ - write_lock_bh(&addrconf_hash_lock); - hlist_del_init(&ifa->addr_lst); + spin_lock_bh(&addrconf_hash_lock); + hlist_del_init_rcu(&ifa->addr_lst); __in6_ifa_put(ifa); - write_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&addrconf_hash_lock); __ipv6_ifa_notify(RTM_DELADDR, ifa); atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); @@ -2946,11 +2952,10 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) { struct hlist_node *n; - hlist_for_each_entry(ifa, n, - &inet6_addr_lst[state->bucket], addr_lst) { + hlist_for_each_entry_rcu(ifa, n, &inet6_addr_lst[state->bucket], + addr_lst) if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; - } } return NULL; } @@ -2962,10 +2967,9 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct hlist_node *n = &ifa->addr_lst; - hlist_for_each_entry_continue(ifa, n, addr_lst) { + hlist_for_each_entry_continue_rcu(ifa, n, addr_lst) if (net_eq(dev_net(ifa->idev->dev), net)) return ifa; - } while (++state->bucket < IN6_ADDR_HSIZE) { hlist_for_each_entry(ifa, n, @@ -2989,9 +2993,9 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos) } static void *if6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(addrconf_hash_lock) + __acquires(rcu) { - read_lock_bh(&addrconf_hash_lock); + rcu_read_lock_bh(); return if6_get_idx(seq, *pos); } @@ -3005,9 +3009,9 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void if6_seq_stop(struct seq_file *seq, void *v) - __releases(addrconf_hash_lock) + __releases(rcu) { - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); } static int if6_seq_show(struct seq_file *seq, void *v) @@ -3081,8 +3085,8 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) struct hlist_node *n; u8 hash = ipv6_addr_hash(addr); - read_lock_bh(&addrconf_hash_lock); - hlist_for_each_entry(ifp, n, &inet6_addr_lst[hash], addr_lst) { + rcu_read_lock_bh(); + hlist_for_each_entry_rcu(ifp, n, &inet6_addr_lst[hash], addr_lst) { if (!net_eq(dev_net(ifp->idev->dev), net)) continue; if (ipv6_addr_equal(&ifp->addr, addr) && @@ -3091,7 +3095,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr) break; } } - read_unlock_bh(&addrconf_hash_lock); + rcu_read_unlock_bh(); return ret; } #endif @@ -3107,7 +3111,8 @@ static void addrconf_verify(unsigned long foo) unsigned long now, next; int i; - spin_lock_bh(&addrconf_verify_lock); + rcu_read_lock_bh(); + spin_lock(&addrconf_verify_lock); now = jiffies; next = now + ADDR_CHECK_FREQUENCY; @@ -3116,8 +3121,8 @@ static void addrconf_verify(unsigned long foo) for (i=0; i < IN6_ADDR_HSIZE; i++) { restart: - read_lock(&addrconf_hash_lock); - hlist_for_each_entry(ifp, node, &inet6_addr_lst[i], addr_lst) { + hlist_for_each_entry_rcu(ifp, node, + &inet6_addr_lst[i], addr_lst) { unsigned long age; #ifdef CONFIG_IPV6_PRIVACY unsigned long regen_advance; @@ -3139,7 +3144,6 @@ restart: age >= ifp->valid_lft) { spin_unlock(&ifp->lock); in6_ifa_hold(ifp); - read_unlock(&addrconf_hash_lock); ipv6_del_addr(ifp); goto restart; } else if (ifp->prefered_lft == INFINITY_LIFE_TIME) { @@ -3161,7 +3165,6 @@ restart: if (deprecate) { in6_ifa_hold(ifp); - read_unlock(&addrconf_hash_lock); ipv6_ifa_notify(0, ifp); in6_ifa_put(ifp); @@ -3179,7 +3182,7 @@ restart: in6_ifa_hold(ifp); in6_ifa_hold(ifpub); spin_unlock(&ifp->lock); - read_unlock(&addrconf_hash_lock); + spin_lock(&ifpub->lock); ifpub->regen_count = 0; spin_unlock(&ifpub->lock); @@ -3199,12 +3202,12 @@ restart: spin_unlock(&ifp->lock); } } - read_unlock(&addrconf_hash_lock); } addr_chk_timer.expires = time_before(next, jiffies + HZ) ? jiffies + HZ : next; add_timer(&addr_chk_timer); - spin_unlock_bh(&addrconf_verify_lock); + spin_unlock(&addrconf_verify_lock); + rcu_read_unlock_bh(); } static struct in6_addr *extract_addr(struct nlattr *addr, struct nlattr *local) @@ -4621,10 +4624,10 @@ void addrconf_cleanup(void) /* * Check hash table. */ - write_lock_bh(&addrconf_hash_lock); + spin_lock_bh(&addrconf_hash_lock); for (i = 0; i < IN6_ADDR_HSIZE; i++) WARN_ON(!hlist_empty(&inet6_addr_lst[i])); - write_unlock_bh(&addrconf_hash_lock); + spin_unlock_bh(&addrconf_hash_lock); del_timer(&addr_chk_timer); rtnl_unlock(); -- cgit v1.2.3-70-g09d2 From 502a2ffd7376ae27cfde6172257db0ff9d8cfec2 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 17 Mar 2010 20:31:13 +0000 Subject: ipv6: convert idev_list to list macros Convert to list macro's for the list of addresses per interface in IPv6. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- drivers/net/bonding/bond_ipv6.c | 9 ++--- include/net/if_inet6.h | 6 ++-- net/ipv6/addrconf.c | 78 ++++++++++++++++++++--------------------- net/sctp/ipv6.c | 2 +- 4 files changed, 48 insertions(+), 47 deletions(-) (limited to 'include/net') diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c index 6dd64cf3cb7..969ffed86b9 100644 --- a/drivers/net/bonding/bond_ipv6.c +++ b/drivers/net/bonding/bond_ipv6.c @@ -37,7 +37,6 @@ static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr) { struct inet6_dev *idev; - struct inet6_ifaddr *ifa; if (!dev) return; @@ -47,10 +46,12 @@ static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr) return; read_lock_bh(&idev->lock); - ifa = idev->addr_list; - if (ifa) + if (!list_empty(&idev->addr_list)) { + struct inet6_ifaddr *ifa + = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); ipv6_addr_copy(addr, &ifa->addr); - else + } else ipv6_addr_set(addr, 0, 0, 0, 0); read_unlock_bh(&idev->lock); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 22a00b1d2c3..13f9fc086d5 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -55,7 +55,7 @@ struct inet6_ifaddr { struct rt6_info *rt; struct hlist_node addr_lst; - struct inet6_ifaddr *if_next; /* next addr in inet6_dev */ + struct list_head if_list; #ifdef CONFIG_IPV6_PRIVACY struct list_head tmp_list; @@ -152,9 +152,9 @@ struct ipv6_devstat { }; struct inet6_dev { - struct net_device *dev; + struct net_device *dev; - struct inet6_ifaddr *addr_list; + struct list_head addr_list; struct ifmcaddr6 *mc_list; struct ifmcaddr6 *mc_tomb; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1e5e41fe92b..6dbf0f79b76 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -317,7 +317,7 @@ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; - WARN_ON(idev->addr_list != NULL); + WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(idev->mc_list != NULL); #ifdef NET_REFCNT_DEBUG @@ -350,6 +350,8 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) rwlock_init(&ndev->lock); ndev->dev = dev; + INIT_LIST_HEAD(&ndev->addr_list); + memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; @@ -466,7 +468,8 @@ static void dev_forward_change(struct inet6_dev *idev) else ipv6_dev_mc_dec(dev, &in6addr_linklocal_allrouters); } - for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) { + + list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa->flags&IFA_F_TENTATIVE) continue; if (idev->cnf.forwarding) @@ -532,7 +535,6 @@ static void inet6_ifa_finish_destroy_rcu(struct rcu_head *head) /* Nobody refers to this ifaddr, destroy it */ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) { - WARN_ON(ifp->if_next != NULL); WARN_ON(!hlist_unhashed(&ifp->addr_lst)); #ifdef NET_REFCNT_DEBUG @@ -556,21 +558,21 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) static void ipv6_link_dev_addr(struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifa, **ifap; + struct list_head *p; int ifp_scope = ipv6_addr_src_scope(&ifp->addr); /* * Each device address list is sorted in order of scope - * global before linklocal. */ - for (ifap = &idev->addr_list; (ifa = *ifap) != NULL; - ifap = &ifa->if_next) { + list_for_each(p, &idev->addr_list) { + struct inet6_ifaddr *ifa + = list_entry(p, struct inet6_ifaddr, if_list); if (ifp_scope >= ipv6_addr_src_scope(&ifa->addr)) break; } - ifp->if_next = *ifap; - *ifap = ifp; + list_add(&ifp->if_list, p); } static u32 ipv6_addr_hash(const struct in6_addr *addr) @@ -703,7 +705,7 @@ out: static void ipv6_del_addr(struct inet6_ifaddr *ifp) { - struct inet6_ifaddr *ifa, **ifap; + struct inet6_ifaddr *ifa, *ifn; struct inet6_dev *idev = ifp->idev; int hash; int deleted = 0, onlink = 0; @@ -730,11 +732,11 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } #endif - for (ifap = &idev->addr_list; (ifa=*ifap) != NULL;) { + list_for_each_entry_safe(ifa, ifn, &idev->addr_list, if_list) { if (ifa == ifp) { - *ifap = ifa->if_next; + list_del_init(&ifp->if_list); __in6_ifa_put(ifp); - ifa->if_next = NULL; + if (!(ifp->flags & IFA_F_PERMANENT) || onlink > 0) break; deleted = 1; @@ -767,7 +769,6 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } } } - ifap = &ifa->if_next; } write_unlock_bh(&idev->lock); @@ -1146,7 +1147,7 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, continue; read_lock_bh(&idev->lock); - for (score->ifa = idev->addr_list; score->ifa; score->ifa = score->ifa->if_next) { + list_for_each_entry(score->ifa, &idev->addr_list, if_list) { int i; /* @@ -1238,8 +1239,9 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { - if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & banned_flags)) { ipv6_addr_copy(addr, &ifp->addr); err = 0; break; @@ -1257,7 +1259,7 @@ static int ipv6_count_addresses(struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) + list_for_each_entry(ifp, &idev->addr_list, if_list) cnt++; read_unlock_bh(&idev->lock); return cnt; @@ -1317,7 +1319,7 @@ int ipv6_chk_prefix(struct in6_addr *addr, struct net_device *dev) idev = __in6_dev_get(dev); if (idev) { read_lock_bh(&idev->lock); - for (ifa = idev->addr_list; ifa; ifa = ifa->if_next) { + list_for_each_entry(ifa, &idev->addr_list, if_list) { onlink = ipv6_prefix_equal(addr, &ifa->addr, ifa->prefix_len); if (onlink) @@ -1555,7 +1557,7 @@ static int ipv6_inherit_eui64(u8 *eui, struct inet6_dev *idev) struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) { memcpy(eui, ifp->addr.s6_addr+8, 8); err = 0; @@ -2159,7 +2161,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, return -ENXIO; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; ifp=ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->prefix_len == plen && ipv6_addr_equal(pfx, &ifp->addr)) { in6_ifa_hold(ifp); @@ -2170,7 +2172,7 @@ static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, /* If the last address is deleted administratively, disable IPv6 on this interface. */ - if (idev->addr_list == NULL) + if (list_empty(&idev->addr_list)) addrconf_ifdown(idev->dev, 1); return 0; } @@ -2602,9 +2604,10 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event) static int addrconf_ifdown(struct net_device *dev, int how) { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa, *keep_list, **bifa; struct net *net = dev_net(dev); + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + LIST_HEAD(keep_list); ASSERT_RTNL(); @@ -2658,12 +2661,10 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); } #endif - keep_list = NULL; - bifa = &keep_list; - while ((ifa = idev->addr_list) != NULL) { - idev->addr_list = ifa->if_next; - ifa->if_next = NULL; + while (!list_empty(&idev->addr_list)) { + ifa = list_first_entry(&idev->addr_list, + struct inet6_ifaddr, if_list); addrconf_del_timer(ifa); /* If just doing link down, and address is permanent @@ -2671,10 +2672,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (how == 0 && (ifa->flags&IFA_F_PERMANENT) && !(ipv6_addr_type(&ifa->addr) & IPV6_ADDR_LINKLOCAL)) { - - /* Move to holding list */ - *bifa = ifa; - bifa = &ifa->if_next; + list_move_tail(&ifa->if_list, &keep_list); /* If not doing DAD on this address, just keep it. */ if ((dev->flags&(IFF_NOARP|IFF_LOOPBACK)) || @@ -2690,6 +2688,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) ifa->flags |= IFA_F_TENTATIVE; in6_ifa_hold(ifa); } else { + list_del(&ifa->if_list); ifa->dead = 1; } write_unlock_bh(&idev->lock); @@ -2707,7 +2706,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_lock_bh(&idev->lock); } - idev->addr_list = keep_list; + list_splice(&keep_list, &idev->addr_list); write_unlock_bh(&idev->lock); @@ -2917,7 +2916,7 @@ static void addrconf_dad_run(struct inet6_dev *idev) { struct inet6_ifaddr *ifp; read_lock_bh(&idev->lock); - for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { + list_for_each_entry(ifp, &idev->addr_list, if_list) { spin_lock(&ifp->lock); if (!(ifp->flags & IFA_F_TENTATIVE)) { spin_unlock(&ifp->lock); @@ -3500,7 +3499,6 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type, int s_ip_idx, int *p_ip_idx) { - struct inet6_ifaddr *ifa; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; int err = 1; @@ -3508,11 +3506,12 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, read_lock_bh(&idev->lock); switch (type) { - case UNICAST_ADDR: + case UNICAST_ADDR: { + struct inet6_ifaddr *ifa; + /* unicast address incl. temp addr */ - for (ifa = idev->addr_list; ifa; - ifa = ifa->if_next, ip_idx++) { - if (ip_idx < s_ip_idx) + list_for_each_entry(ifa, &idev->addr_list, if_list) { + if (++ip_idx < s_ip_idx) continue; err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, @@ -3523,6 +3522,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, break; } break; + } case MULTICAST_ADDR: /* multicast address */ for (ifmca = idev->mc_list; ifmca; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 1d7ac70ba39..240dceba06e 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -371,7 +371,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, } read_lock_bh(&in6_dev->lock); - for (ifp = in6_dev->addr_list; ifp; ifp = ifp->if_next) { + list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { /* Add the address to the local list. */ addr = t_new(struct sctp_sockaddr_entry, GFP_ATOMIC); if (addr) { -- cgit v1.2.3-70-g09d2 From ec733b15a3ef0b5759141a177f8044a2f40c41e7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Mar 2010 20:36:06 +0000 Subject: net: snmp mib cleanup There is no point to align or pad mibs to cache lines, they are per cpu allocated with a 8 bytes alignment anyway. This wastes space for no gain. This patch removes __SNMP_MIB_ALIGN__ Since SNMP mibs contain "unsigned long" fields only, we can relax the allocation alignment from "unsigned long long" to "unsigned long" Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 2 +- include/net/snmp.h | 29 +++++++---------------------- net/dccp/dccp.h | 2 +- net/ipv4/af_inet.c | 4 ++-- 4 files changed, 11 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 78740ec57d5..59151557406 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -268,7 +268,7 @@ enum { #define SCTP_MIB_MAX __SCTP_MIB_MAX struct sctp_mib { unsigned long mibs[SCTP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* Print debugging messages. */ diff --git a/include/net/snmp.h b/include/net/snmp.h index 692ee0061dc..884fdbb74b2 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -52,26 +52,11 @@ struct snmp_mib { * count on the 20Gb/s + networks people expect in a few years time! */ -/* - * The rule for padding: - * Best is power of two because then the right structure can be found by a - * simple shift. The structure should be always cache line aligned. - * gcc needs n=alignto(cachelinesize, popcnt(sizeof(bla_mib))) shift/add - * instructions to emulate multiply in case it is not power-of-two. - * Currently n is always <=3 for all sizes so simple cache line alignment - * is enough. - * - * The best solution would be a global CPU local area , especially on 64 - * and 128byte cacheline machine it makes a *lot* of sense -AK - */ - -#define __SNMP_MIB_ALIGN__ ____cacheline_aligned - /* IPstats */ #define IPSTATS_MIB_MAX __IPSTATS_MIB_MAX struct ipstats_mib { unsigned long mibs[IPSTATS_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* ICMP */ #define ICMP_MIB_DUMMY __ICMP_MIB_MAX @@ -79,36 +64,36 @@ struct ipstats_mib { struct icmp_mib { unsigned long mibs[ICMP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; #define ICMPMSG_MIB_MAX __ICMPMSG_MIB_MAX struct icmpmsg_mib { unsigned long mibs[ICMPMSG_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* ICMP6 (IPv6-ICMP) */ #define ICMP6_MIB_MAX __ICMP6_MIB_MAX struct icmpv6_mib { unsigned long mibs[ICMP6_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; #define ICMP6MSG_MIB_MAX __ICMP6MSG_MIB_MAX struct icmpv6msg_mib { unsigned long mibs[ICMP6MSG_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* TCP */ #define TCP_MIB_MAX __TCP_MIB_MAX struct tcp_mib { unsigned long mibs[TCP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* UDP */ #define UDP_MIB_MAX __UDP_MIB_MAX struct udp_mib { unsigned long mibs[UDP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; /* Linux */ #define LINUX_MIB_MAX __LINUX_MIB_MAX diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 5ef32c2f0d6..53f8e12d0c1 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -189,7 +189,7 @@ enum { #define DCCP_MIB_MAX __DCCP_MIB_MAX struct dccp_mib { unsigned long mibs[DCCP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); #define DCCP_INC_STATS(field) SNMP_INC_STATS(dccp_statistics, field) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 33b7dffa773..55e11906a73 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1401,10 +1401,10 @@ EXPORT_SYMBOL_GPL(snmp_fold_field); int snmp_mib_init(void __percpu *ptr[2], size_t mibsize) { BUG_ON(ptr == NULL); - ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); + ptr[0] = __alloc_percpu(mibsize, __alignof__(unsigned long)); if (!ptr[0]) goto err0; - ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long long)); + ptr[1] = __alloc_percpu(mibsize, __alignof__(unsigned long)); if (!ptr[1]) goto err1; return 0; -- cgit v1.2.3-70-g09d2 From 1e4dcd012423b6a28f968a55886d2b27896a1586 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Fri, 19 Mar 2010 07:14:53 +0200 Subject: mac80211: Add support for connection monitor in hardware This patch is based on a RFC patch by Kalle Valo. The wl1271 has a feature which handles the connection monitor logic in hardware, basically sending periodically nullfunc frames and reporting to the host if AP is lost, after attempting to recover by sending probe-requests to the AP. Add support to mac80211 by adding a new flag IEEE80211_HW_CONNECTION_MONITOR which prevents conn_mon_timer from triggering during idle periods, and prevents sending probe-requests to the AP if beacon-loss is indicated by the hardware. Cc: Kalle Valo Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 24 +++++++++++++++-- net/mac80211/ieee80211_i.h | 4 +-- net/mac80211/iface.c | 2 +- net/mac80211/mlme.c | 64 +++++++++++++++++++++++++++++++++++++++++----- 4 files changed, 82 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 936bc410d06..d14226f29ff 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -954,6 +954,11 @@ enum ieee80211_tkip_key_type { * Hardware can provide ack status reports of Tx frames to * the stack. * + * @IEEE80211_HW_CONNECTION_MONITOR: + * The hardware performs its own connection monitoring, including + * periodic keep-alives to the AP and probing the AP on beacon loss. + * When this flag is set, signaling beacon-loss will cause an immediate + * change to disassociated state. */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -975,6 +980,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_DYNAMIC_SMPS = 1<<16, IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, + IEEE80211_HW_CONNECTION_MONITOR = 1<<19, }; /** @@ -2364,12 +2370,26 @@ void ieee80211_sta_block_awake(struct ieee80211_hw *hw, * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * - * When beacon filtering is enabled with IEEE80211_HW_BEACON_FILTERING and - * IEEE80211_CONF_PS is set, the driver needs to inform whenever the + * When beacon filtering is enabled with %IEEE80211_HW_BEACON_FILTERING and + * %IEEE80211_CONF_PS is set, the driver needs to inform whenever the * hardware is not receiving beacons with this function. */ void ieee80211_beacon_loss(struct ieee80211_vif *vif); +/** + * ieee80211_connection_loss - inform hardware has lost connection to the AP + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * + * When beacon filtering is enabled with %IEEE80211_HW_BEACON_FILTERING, and + * %IEEE80211_CONF_PS and %IEEE80211_HW_CONNECTION_MONITOR are set, the driver + * needs to inform if the connection to the AP has been lost. + * + * This function will cause immediate change to disassociated state, + * without connection recovery attempts. + */ +void ieee80211_connection_loss(struct ieee80211_vif *vif); + /* Rate control API */ /** diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index b84126491ab..ab369e2a528 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -327,7 +327,7 @@ struct ieee80211_if_managed { struct work_struct work; struct work_struct monitor_work; struct work_struct chswitch_work; - struct work_struct beacon_loss_work; + struct work_struct beacon_connection_loss_work; unsigned long probe_timeout; int probe_send_count; @@ -1156,7 +1156,7 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local, int powersave); void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr); -void ieee80211_beacon_loss_work(struct work_struct *work); +void ieee80211_beacon_connection_loss_work(struct work_struct *work); void ieee80211_wake_queues_by_reason(struct ieee80211_hw *hw, enum queue_stop_reason reason); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d5571b9420c..b4ec59a8dc0 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -486,7 +486,7 @@ static int ieee80211_stop(struct net_device *dev) cancel_work_sync(&sdata->u.mgd.work); cancel_work_sync(&sdata->u.mgd.chswitch_work); cancel_work_sync(&sdata->u.mgd.monitor_work); - cancel_work_sync(&sdata->u.mgd.beacon_loss_work); + cancel_work_sync(&sdata->u.mgd.beacon_connection_loss_work); /* * When we get here, the interface is marked down. diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0ab284c3213..865ea1cfb7b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -851,6 +851,9 @@ void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata, if (is_multicast_ether_addr(hdr->addr1)) return; + if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) + return; + mod_timer(&sdata->u.mgd.conn_mon_timer, round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); } @@ -928,23 +931,68 @@ static void ieee80211_mgd_probe_ap(struct ieee80211_sub_if_data *sdata, mutex_unlock(&ifmgd->mtx); } -void ieee80211_beacon_loss_work(struct work_struct *work) +static void __ieee80211_connection_loss(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_local *local = sdata->local; + u8 bssid[ETH_ALEN]; + + mutex_lock(&ifmgd->mtx); + if (!ifmgd->associated) { + mutex_unlock(&ifmgd->mtx); + return; + } + + memcpy(bssid, ifmgd->associated->bssid, ETH_ALEN); + + printk(KERN_DEBUG "Connection to AP %pM lost.\n", bssid); + + ieee80211_set_disassoc(sdata); + ieee80211_recalc_idle(local); + mutex_unlock(&ifmgd->mtx); + /* + * must be outside lock due to cfg80211, + * but that's not a problem. + */ + ieee80211_send_deauth_disassoc(sdata, bssid, + IEEE80211_STYPE_DEAUTH, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, + NULL); +} + +void ieee80211_beacon_connection_loss_work(struct work_struct *work) { struct ieee80211_sub_if_data *sdata = container_of(work, struct ieee80211_sub_if_data, - u.mgd.beacon_loss_work); + u.mgd.beacon_connection_loss_work); - ieee80211_mgd_probe_ap(sdata, true); + if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR) + __ieee80211_connection_loss(sdata); + else + ieee80211_mgd_probe_ap(sdata, true); } void ieee80211_beacon_loss(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_hw *hw = &sdata->local->hw; - ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_loss_work); + WARN_ON(hw->flags & IEEE80211_HW_CONNECTION_MONITOR); + ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work); } EXPORT_SYMBOL(ieee80211_beacon_loss); +void ieee80211_connection_loss(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_hw *hw = &sdata->local->hw; + + WARN_ON(!(hw->flags & IEEE80211_HW_CONNECTION_MONITOR)); + ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work); +} +EXPORT_SYMBOL(ieee80211_connection_loss); + + static enum rx_mgmt_action __must_check ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata, struct ieee80211_mgmt *mgmt, size_t len) @@ -1634,7 +1682,8 @@ static void ieee80211_sta_bcn_mon_timer(unsigned long data) if (local->quiescing) return; - ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.beacon_loss_work); + ieee80211_queue_work(&sdata->local->hw, + &sdata->u.mgd.beacon_connection_loss_work); } static void ieee80211_sta_conn_mon_timer(unsigned long data) @@ -1686,7 +1735,7 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) */ cancel_work_sync(&ifmgd->work); - cancel_work_sync(&ifmgd->beacon_loss_work); + cancel_work_sync(&ifmgd->beacon_connection_loss_work); if (del_timer_sync(&ifmgd->timer)) set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); @@ -1720,7 +1769,8 @@ void ieee80211_sta_setup_sdata(struct ieee80211_sub_if_data *sdata) INIT_WORK(&ifmgd->work, ieee80211_sta_work); INIT_WORK(&ifmgd->monitor_work, ieee80211_sta_monitor_work); INIT_WORK(&ifmgd->chswitch_work, ieee80211_chswitch_work); - INIT_WORK(&ifmgd->beacon_loss_work, ieee80211_beacon_loss_work); + INIT_WORK(&ifmgd->beacon_connection_loss_work, + ieee80211_beacon_connection_loss_work); setup_timer(&ifmgd->timer, ieee80211_sta_timer, (unsigned long) sdata); setup_timer(&ifmgd->bcn_mon_timer, ieee80211_sta_bcn_mon_timer, -- cgit v1.2.3-70-g09d2 From d6dc1a386358979e12366d1f35eeb68fc181e101 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 23 Mar 2010 09:02:33 +0200 Subject: cfg80211: Add connection quality monitoring support to nl80211 Add support for basic configuration of a connection quality monitoring to the nl80211 interface, and basic support for notifying about triggered monitoring events. Via this interface a user-space connection manager may configure and receive pre-warning events of deteriorating WLAN connection quality, and start preparing for roaming in advance, before the connection is already lost. An example usage of such a trigger is starting scanning for nearby AP's in an attempt to find one with better connection quality, and associate to it before the connection characteristics of the existing connection become too bad or the association is even lost, leading in a prolonged delay in connectivity. The interface currently supports only RSSI, but it could be later extended to include other parameters, such as signal-to-noise ratio, if need for that arises. Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/linux/nl80211.h | 46 +++++++++++++++++ include/net/cfg80211.h | 19 +++++++ net/wireless/mlme.c | 13 +++++ net/wireless/nl80211.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.h | 6 +++ 5 files changed, 215 insertions(+) (limited to 'include/net') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 28ba20fda3e..89947597b9c 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -323,6 +323,12 @@ * the TX command and %NL80211_ATTR_FRAME includes the contents of the * frame. %NL80211_ATTR_ACK flag is included if the recipient acknowledged * the frame. + * @NL80211_CMD_SET_CQM: Connection quality monitor configuration. This command + * is used to configure connection quality monitoring notification trigger + * levels. + * @NL80211_CMD_NOTIFY_CQM: Connection quality monitor notification. This + * command is used as an event to indicate the that a trigger level was + * reached. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -419,6 +425,9 @@ enum nl80211_commands { NL80211_CMD_SET_POWER_SAVE, NL80211_CMD_GET_POWER_SAVE, + NL80211_CMD_SET_CQM, + NL80211_CMD_NOTIFY_CQM, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -691,6 +700,9 @@ enum nl80211_commands { * @NL80211_ATTR_ACK: Flag attribute indicating that the frame was * acknowledged by the recipient. * + * @NL80211_ATTR_CQM: connection quality monitor configuration in a + * nested attribute with %NL80211_ATTR_CQM_* sub-attributes. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -842,6 +854,8 @@ enum nl80211_attrs { NL80211_ATTR_PS_STATE, + NL80211_ATTR_CQM, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -1583,4 +1597,36 @@ enum nl80211_ps_state { NL80211_PS_ENABLED, }; +/** + * enum nl80211_attr_cqm - connection quality monitor attributes + * @__NL80211_ATTR_CQM_INVALID: invalid + * @NL80211_ATTR_CQM_RSSI_THOLD: RSSI threshold in dBm (zero to disable) + * @NL80211_ATTR_CQM_RSSI_HYST: RSSI hysteresis in dBm + * @NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT: RSSI threshold event + * @__NL80211_ATTR_CQM_AFTER_LAST: internal + * @NL80211_ATTR_CQM_MAX: highest key attribute + */ +enum nl80211_attr_cqm { + __NL80211_ATTR_CQM_INVALID, + NL80211_ATTR_CQM_RSSI_THOLD, + NL80211_ATTR_CQM_RSSI_HYST, + NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + + /* keep last */ + __NL80211_ATTR_CQM_AFTER_LAST, + NL80211_ATTR_CQM_MAX = __NL80211_ATTR_CQM_AFTER_LAST - 1 +}; + +/** + * enum nl80211_cqm_rssi_threshold_event - RSSI threshold event + * @NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW - The RSSI level is lower than the + * configured threshold + * @NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH - The RSSI is higher than the + * configured threshold + */ +enum nl80211_cqm_rssi_threshold_event { + NL80211_CQM_RSSI_THRESHOLD_EVENT_LOW, + NL80211_CQM_RSSI_THRESHOLD_EVENT_HIGH, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 3d134a1fb96..868cfd3b972 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1007,6 +1007,7 @@ struct cfg80211_pmksa { * RSN IE. It allows for faster roaming between WPA2 BSSIDs. * @del_pmksa: Delete a cached PMKID. * @flush_pmksa: Flush all cached PMKIDs. + * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. * */ struct cfg80211_ops { @@ -1152,6 +1153,10 @@ struct cfg80211_ops { int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); + + int (*set_cqm_rssi_config)(struct wiphy *wiphy, + struct net_device *dev, + s32 rssi_thold, u32 rssi_hyst); }; /* @@ -2337,4 +2342,18 @@ bool cfg80211_rx_action(struct net_device *dev, int freq, const u8 *buf, void cfg80211_action_tx_status(struct net_device *dev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); + +/** + * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event + * @dev: network device + * @rssi_event: the triggered RSSI event + * @gfp: context flags + * + * This function is called when a configured connection quality monitoring + * rssi threshold reached event occurs. + */ +void cfg80211_cqm_rssi_notify(struct net_device *dev, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp); + #endif /* __NET_CFG80211_H */ diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 62bc8855e12..0855f0d3234 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -894,3 +894,16 @@ void cfg80211_action_tx_status(struct net_device *dev, u64 cookie, nl80211_send_action_tx_status(rdev, dev, cookie, buf, len, ack, gfp); } EXPORT_SYMBOL(cfg80211_action_tx_status); + +void cfg80211_cqm_rssi_notify(struct net_device *dev, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + /* Indicate roaming trigger event to user space */ + nl80211_send_cqm_rssi_notify(rdev, dev, rssi_event, gfp); +} +EXPORT_SYMBOL(cfg80211_cqm_rssi_notify); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e447db04cf7..a7fc3d83f5f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -149,6 +149,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { .len = IEEE80211_MAX_DATA_LEN }, [NL80211_ATTR_FRAME_MATCH] = { .type = NLA_BINARY, }, [NL80211_ATTR_PS_STATE] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM] = { .type = NLA_NESTED, }, }; /* policy for the attributes */ @@ -4778,6 +4779,84 @@ unlock_rtnl: return err; } +static struct nla_policy +nl80211_attr_cqm_policy[NL80211_ATTR_CQM_MAX + 1] __read_mostly = { + [NL80211_ATTR_CQM_RSSI_THOLD] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_RSSI_HYST] = { .type = NLA_U32 }, + [NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT] = { .type = NLA_U32 }, +}; + +static int nl80211_set_cqm_rssi(struct genl_info *info, + s32 threshold, u32 hysteresis) +{ + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + struct net_device *dev; + int err; + + if (threshold > 0) + return -EINVAL; + + rtnl_lock(); + + err = get_rdev_dev_by_info_ifindex(info, &rdev, &dev); + if (err) + goto unlock_rdev; + + wdev = dev->ieee80211_ptr; + + if (!rdev->ops->set_cqm_rssi_config) { + err = -EOPNOTSUPP; + goto unlock_rdev; + } + + if (wdev->iftype != NL80211_IFTYPE_STATION) { + err = -EOPNOTSUPP; + goto unlock_rdev; + } + + err = rdev->ops->set_cqm_rssi_config(wdev->wiphy, dev, + threshold, hysteresis); + +unlock_rdev: + cfg80211_unlock_rdev(rdev); + dev_put(dev); + rtnl_unlock(); + + return err; +} + +static int nl80211_set_cqm(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[NL80211_ATTR_CQM_MAX + 1]; + struct nlattr *cqm; + int err; + + cqm = info->attrs[NL80211_ATTR_CQM]; + if (!cqm) { + err = -EINVAL; + goto out; + } + + err = nla_parse_nested(attrs, NL80211_ATTR_CQM_MAX, cqm, + nl80211_attr_cqm_policy); + if (err) + goto out; + + if (attrs[NL80211_ATTR_CQM_RSSI_THOLD] && + attrs[NL80211_ATTR_CQM_RSSI_HYST]) { + s32 threshold; + u32 hysteresis; + threshold = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_THOLD]); + hysteresis = nla_get_u32(attrs[NL80211_ATTR_CQM_RSSI_HYST]); + err = nl80211_set_cqm_rssi(info, threshold, hysteresis); + } else + err = -EINVAL; + +out: + return err; +} + static struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_GET_WIPHY, @@ -5082,6 +5161,12 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, /* can be retrieved by unprivileged users */ }, + { + .cmd = NL80211_CMD_SET_CQM, + .doit = nl80211_set_cqm, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { @@ -5832,6 +5917,52 @@ void nl80211_send_action_tx_status(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void +nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *pinfoattr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_NOTIFY_CQM); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + + pinfoattr = nla_nest_start(msg, NL80211_ATTR_CQM); + if (!pinfoattr) + goto nla_put_failure; + + NLA_PUT_U32(msg, NL80211_ATTR_CQM_RSSI_THRESHOLD_EVENT, + rssi_event); + + nla_nest_end(msg, pinfoattr); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + static int nl80211_netlink_notify(struct notifier_block * nb, unsigned long state, void *_notify) diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 4ca511102c6..2ad7fbc7d9f 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -82,4 +82,10 @@ void nl80211_send_action_tx_status(struct cfg80211_registered_device *rdev, const u8 *buf, size_t len, bool ack, gfp_t gfp); +void +nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp); + #endif /* __NET_WIRELESS_NL80211_H */ -- cgit v1.2.3-70-g09d2 From a97c13c34509be460dea23c86f31c02daa2428b5 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 23 Mar 2010 09:02:34 +0200 Subject: mac80211: Add support for connection quality monitoring Add support for the set_cqm_config op. This op function configures the requested connection quality monitor rssi threshold and rssi hysteresis values to the hardware if the hardware supports IEEE80211_HW_SUPPORTS_CQM. For unsupported hardware, currently -EOPNOTSUPP is returned, so the mac80211 is currently not doing connection quality monitoring on the host. This could be added later, if needed. Signed-off-by: Juuso Oikarinen Reviewed-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 30 ++++++++++++++++++++++++++++++ net/mac80211/cfg.c | 27 +++++++++++++++++++++++++++ net/mac80211/mlme.c | 15 +++++++++++++++ 3 files changed, 72 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d14226f29ff..1a8f50af49a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -144,6 +144,7 @@ struct ieee80211_low_level_stats { * new beacon (beaconing modes) * @BSS_CHANGED_BEACON_ENABLED: Beaconing should be * enabled/disabled (beaconing modes) + * @BSS_CHANGED_CQM: Connection quality monitor config changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -156,6 +157,7 @@ enum ieee80211_bss_change { BSS_CHANGED_BSSID = 1<<7, BSS_CHANGED_BEACON = 1<<8, BSS_CHANGED_BEACON_ENABLED = 1<<9, + BSS_CHANGED_CQM = 1<<10, }; /** @@ -185,6 +187,9 @@ enum ieee80211_bss_change { * @enable_beacon: whether beaconing should be enabled or not * @ht_operation_mode: HT operation mode (like in &struct ieee80211_ht_info). * This field is only valid when the channel type is one of the HT types. + * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value + * implies disabled + * @cqm_rssi_hyst: Connection quality monitor RSSI hysteresis */ struct ieee80211_bss_conf { const u8 *bssid; @@ -202,6 +207,8 @@ struct ieee80211_bss_conf { u64 timestamp; u32 basic_rates; u16 ht_operation_mode; + s32 cqm_rssi_thold; + u32 cqm_rssi_hyst; }; /** @@ -959,6 +966,12 @@ enum ieee80211_tkip_key_type { * periodic keep-alives to the AP and probing the AP on beacon loss. * When this flag is set, signaling beacon-loss will cause an immediate * change to disassociated state. + * + * @IEEE80211_HW_SUPPORTS_CQM_RSSI: + * Hardware can do connection quality monitoring - i.e. it can monitor + * connection quality related parameters, such as the RSSI level and + * provide notifications if configured trigger levels are reached. + * */ enum ieee80211_hw_flags { IEEE80211_HW_HAS_RATE_CONTROL = 1<<0, @@ -981,6 +994,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_UAPSD = 1<<17, IEEE80211_HW_REPORTS_TX_ACK_STATUS = 1<<18, IEEE80211_HW_CONNECTION_MONITOR = 1<<19, + IEEE80211_HW_SUPPORTS_CQM_RSSI = 1<<20, }; /** @@ -2390,6 +2404,22 @@ void ieee80211_beacon_loss(struct ieee80211_vif *vif); */ void ieee80211_connection_loss(struct ieee80211_vif *vif); +/** + * ieee80211_cqm_rssi_notify - inform a configured connection quality monitoring + * rssi threshold triggered + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @rssi_event: the RSSI trigger event type + * @gfp: context flags + * + * When the %IEEE80211_HW_SUPPORTS_CQM_RSSI is set, and a connection quality + * monitoring is configured with an rssi threshold, the driver will inform + * whenever the rssi level reaches the threshold. + */ +void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp); + /* Rate control API */ /** diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index b7116ef84a3..c8f520529ee 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1402,6 +1402,32 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, return 0; } +static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, + struct net_device *dev, + s32 rssi_thold, u32 rssi_hyst) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_vif *vif = &sdata->vif; + struct ieee80211_bss_conf *bss_conf = &vif->bss_conf; + + if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_CQM_RSSI)) + return -EOPNOTSUPP; + + if (rssi_thold == bss_conf->cqm_rssi_thold && + rssi_hyst == bss_conf->cqm_rssi_hyst) + return 0; + + bss_conf->cqm_rssi_thold = rssi_thold; + bss_conf->cqm_rssi_hyst = rssi_hyst; + + /* tell the driver upon association, unless already associated */ + if (sdata->u.mgd.associated) + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_CQM); + + return 0; +} + static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct net_device *dev, const u8 *addr, @@ -1506,4 +1532,5 @@ struct cfg80211_ops mac80211_config_ops = { .remain_on_channel = ieee80211_remain_on_channel, .cancel_remain_on_channel = ieee80211_cancel_remain_on_channel, .action = ieee80211_action, + .set_cqm_rssi_config = ieee80211_set_cqm_rssi_config, }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 865ea1cfb7b..65eafda5738 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -750,6 +750,11 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, /* And the BSSID changed - we're associated now */ bss_info_changed |= BSS_CHANGED_BSSID; + /* Tell the driver to monitor connection quality (if supported) */ + if ((local->hw.flags & IEEE80211_HW_SUPPORTS_CQM_RSSI) && + sdata->vif.bss_conf.cqm_rssi_thold) + bss_info_changed |= BSS_CHANGED_CQM; + ieee80211_bss_info_change_notify(sdata, bss_info_changed); mutex_lock(&local->iflist_mtx); @@ -2182,3 +2187,13 @@ int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, *cookie = (unsigned long) skb; return 0; } + +void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, + enum nl80211_cqm_rssi_threshold_event rssi_event, + gfp_t gfp) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp); +} +EXPORT_SYMBOL(ieee80211_cqm_rssi_notify); -- cgit v1.2.3-70-g09d2 From 0c0dbfecbf217b47d0b508afb59b8b3639582a4c Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 27 Mar 2010 19:23:46 -0700 Subject: decnet: Remove unused FIB metric macros. Unlike the ipv4 side, these are completely unused. Signed-off-by: David S. Miller --- include/net/dn_fib.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/net') diff --git a/include/net/dn_fib.h b/include/net/dn_fib.h index 52da6c3dd50..bbcde3238e5 100644 --- a/include/net/dn_fib.h +++ b/include/net/dn_fib.h @@ -50,10 +50,6 @@ struct dn_fib_info { __le16 fib_prefsrc; __u32 fib_priority; __u32 fib_metrics[RTAX_MAX]; -#define dn_fib_mtu fib_metrics[RTAX_MTU-1] -#define dn_fib_window fib_metrics[RTAX_WINDOW-1] -#define dn_fib_rtt fib_metrics[RTAX_RTT-1] -#define dn_fib_advmss fib_metrics[RTAX_ADVMSS-1] int fib_nhs; int fib_power; struct dn_fib_nh fib_nh[0]; -- cgit v1.2.3-70-g09d2 From 09009f30de188c847d72039e6250bfea56a0f887 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:21 +0000 Subject: net-caif: add CAIF core protocol stack header files Add include files for the CAIF Core protocol stack. caif_layer.h - Defines the structure of the CAIF protocol layers cfcnfg.h - CAIF Configuration Module for services and link layers cfctrl.h - CAIF Control Protocol Layer cffrml.h - CAIF Framing Layer cfmuxl.h - CAIF Muxing Layer cfpkt.h - CAIF Packet layer (skb helper functions) cfserl.h - CAIF Serial Layer cfsrvl.h - CAIF Service Layer Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_layer.h | 283 ++++++++++++++++++++++++++++++++++++++++++ include/net/caif/cfcnfg.h | 133 ++++++++++++++++++++ include/net/caif/cfctrl.h | 138 ++++++++++++++++++++ include/net/caif/cffrml.h | 16 +++ include/net/caif/cfmuxl.h | 22 ++++ include/net/caif/cfpkt.h | 274 ++++++++++++++++++++++++++++++++++++++++ include/net/caif/cfserl.h | 12 ++ include/net/caif/cfsrvl.h | 34 +++++ 8 files changed, 912 insertions(+) create mode 100644 include/net/caif/caif_layer.h create mode 100644 include/net/caif/cfcnfg.h create mode 100644 include/net/caif/cfctrl.h create mode 100644 include/net/caif/cffrml.h create mode 100644 include/net/caif/cfmuxl.h create mode 100644 include/net/caif/cfpkt.h create mode 100644 include/net/caif/cfserl.h create mode 100644 include/net/caif/cfsrvl.h (limited to 'include/net') diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h new file mode 100644 index 00000000000..25c472f0e5b --- /dev/null +++ b/include/net/caif/caif_layer.h @@ -0,0 +1,283 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland / sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_LAYER_H_ +#define CAIF_LAYER_H_ + +#include + +struct cflayer; +struct cfpkt; +struct cfpktq; +struct caif_payload_info; +struct caif_packet_funcs; + +#define CAIF_MAX_FRAMESIZE 4096 +#define CAIF_MAX_PAYLOAD_SIZE (4096 - 64) +#define CAIF_NEEDED_HEADROOM (10) +#define CAIF_NEEDED_TAILROOM (2) + +#define CAIF_LAYER_NAME_SZ 16 +#define CAIF_SUCCESS 1 +#define CAIF_FAILURE 0 + +/** + * caif_assert() - Assert function for CAIF. + * @assert: expression to evaluate. + * + * This function will print a error message and a do WARN_ON if the + * assertion failes. Normally this will do a stack up at the current location. + */ +#define caif_assert(assert) \ +do { \ + if (!(assert)) { \ + pr_err("caif:Assert detected:'%s'\n", #assert); \ + WARN_ON(!(assert)); \ + } \ +} while (0) + + +/** + * enum caif_ctrlcmd - CAIF Stack Control Signaling sent in layer.ctrlcmd(). + * + * @CAIF_CTRLCMD_FLOW_OFF_IND: Flow Control is OFF, transmit function + * should stop sending data + * + * @CAIF_CTRLCMD_FLOW_ON_IND: Flow Control is ON, transmit function + * can start sending data + * + * @CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND: Remote end modem has decided to close + * down channel + * + * @CAIF_CTRLCMD_INIT_RSP: Called initially when the layer below + * has finished initialization + * + * @CAIF_CTRLCMD_DEINIT_RSP: Called when de-initialization is + * complete + * + * @CAIF_CTRLCMD_INIT_FAIL_RSP: Called if initialization fails + * + * @_CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND: CAIF Link layer temporarily cannot + * send more packets. + * @_CAIF_CTRLCMD_PHYIF_FLOW_ON_IND: Called if CAIF Link layer is able + * to send packets again. + * @_CAIF_CTRLCMD_PHYIF_DOWN_IND: Called if CAIF Link layer is going + * down. + * + * These commands are sent upwards in the CAIF stack to the CAIF Client. + * They are used for signaling originating from the modem or CAIF Link Layer. + * These are either responses (*_RSP) or events (*_IND). + */ +enum caif_ctrlcmd { + CAIF_CTRLCMD_FLOW_OFF_IND, + CAIF_CTRLCMD_FLOW_ON_IND, + CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND, + CAIF_CTRLCMD_INIT_RSP, + CAIF_CTRLCMD_DEINIT_RSP, + CAIF_CTRLCMD_INIT_FAIL_RSP, + _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, + _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND, + _CAIF_CTRLCMD_PHYIF_DOWN_IND, +}; + +/** + * enum caif_modemcmd - Modem Control Signaling, sent from CAIF Client + * to the CAIF Link Layer or modem. + * + * @CAIF_MODEMCMD_FLOW_ON_REQ: Flow Control is ON, transmit function + * can start sending data. + * + * @CAIF_MODEMCMD_FLOW_OFF_REQ: Flow Control is OFF, transmit function + * should stop sending data. + * + * @_CAIF_MODEMCMD_PHYIF_USEFULL: Notify physical layer that it is in use + * + * @_CAIF_MODEMCMD_PHYIF_USELESS: Notify physical layer that it is + * no longer in use. + * + * These are requests sent 'downwards' in the stack. + * Flow ON, OFF can be indicated to the modem. + */ +enum caif_modemcmd { + CAIF_MODEMCMD_FLOW_ON_REQ = 0, + CAIF_MODEMCMD_FLOW_OFF_REQ = 1, + _CAIF_MODEMCMD_PHYIF_USEFULL = 3, + _CAIF_MODEMCMD_PHYIF_USELESS = 4 +}; + +/** + * enum caif_direction - CAIF Packet Direction. + * Indicate if a packet is to be sent out or to be received in. + * @CAIF_DIR_IN: Incoming packet received. + * @CAIF_DIR_OUT: Outgoing packet to be transmitted. + */ +enum caif_direction { + CAIF_DIR_IN = 0, + CAIF_DIR_OUT = 1 +}; + +/** + * struct cflayer - CAIF Stack layer. + * Defines the framework for the CAIF Core Stack. + * @up: Pointer up to the layer above. + * @dn: Pointer down to the layer below. + * @node: List node used when layer participate in a list. + * @receive: Packet receive function. + * @transmit: Packet transmit funciton. + * @ctrlcmd: Used for control signalling upwards in the stack. + * @modemcmd: Used for control signaling downwards in the stack. + * @prio: Priority of this layer. + * @id: The identity of this layer + * @type: The type of this layer + * @name: Name of the layer. + * + * This structure defines the layered structure in CAIF. + * + * It defines CAIF layering structure, used by all CAIF Layers and the + * layers interfacing CAIF. + * + * In order to integrate with CAIF an adaptation layer on top of the CAIF stack + * and PHY layer below the CAIF stack + * must be implemented. These layer must follow the design principles below. + * + * Principles for layering of protocol layers: + * - All layers must use this structure. If embedding it, then place this + * structure first in the layer specific structure. + * + * - Each layer should not depend on any others layer private data. + * + * - In order to send data upwards do + * layer->up->receive(layer->up, packet); + * + * - In order to send data downwards do + * layer->dn->transmit(layer->dn, info, packet); + */ +struct cflayer { + struct cflayer *up; + struct cflayer *dn; + struct list_head node; + + /* + * receive() - Receive Function. + * Contract: Each layer must implement a receive function passing the + * CAIF packets upwards in the stack. + * Packet handling rules: + * - The CAIF packet (cfpkt) cannot be accessed after + * passing it to the next layer using up->receive(). + * - If parsing of the packet fails, the packet must be + * destroyed and -1 returned from the function. + * - If parsing succeeds (and above layers return OK) then + * the function must return a value > 0. + * + * Returns result < 0 indicates an error, 0 or positive value + * indicates success. + * + * @layr: Pointer to the current layer the receive function is + * implemented for (this pointer). + * @cfpkt: Pointer to CaifPacket to be handled. + */ + int (*receive)(struct cflayer *layr, struct cfpkt *cfpkt); + + /* + * transmit() - Transmit Function. + * Contract: Each layer must implement a transmit function passing the + * CAIF packet downwards in the stack. + * Packet handling rules: + * - The CAIF packet (cfpkt) ownership is passed to the + * transmit function. This means that the the packet + * cannot be accessed after passing it to the below + * layer using dn->transmit(). + * + * - If transmit fails, however, the ownership is returned + * to thecaller. The caller of "dn->transmit()" must + * destroy or resend packet. + * + * - Return value less than zero means error, zero or + * greater than zero means OK. + * + * result < 0 indicates an error, 0 or positive value + * indicate success. + * + * @layr: Pointer to the current layer the receive function + * isimplemented for (this pointer). + * @cfpkt: Pointer to CaifPacket to be handled. + */ + int (*transmit) (struct cflayer *layr, struct cfpkt *cfpkt); + + /* + * cttrlcmd() - Control Function upwards in CAIF Stack. + * Used for signaling responses (CAIF_CTRLCMD_*_RSP) + * and asynchronous events from the modem (CAIF_CTRLCMD_*_IND) + * + * @layr: Pointer to the current layer the receive function + * is implemented for (this pointer). + * @ctrl: Control Command. + */ + void (*ctrlcmd) (struct cflayer *layr, enum caif_ctrlcmd ctrl, + int phyid); + + /* + * modemctrl() - Control Function used for controlling the modem. + * Used to signal down-wards in the CAIF stack. + * Returns 0 on success, < 0 upon failure. + * + * @layr: Pointer to the current layer the receive function + * is implemented for (this pointer). + * @ctrl: Control Command. + */ + int (*modemcmd) (struct cflayer *layr, enum caif_modemcmd ctrl); + + unsigned short prio; + unsigned int id; + unsigned int type; + char name[CAIF_LAYER_NAME_SZ]; +}; + +/** + * layer_set_up() - Set the up pointer for a specified layer. + * @layr: Layer where up pointer shall be set. + * @above: Layer above. + */ +#define layer_set_up(layr, above) ((layr)->up = (struct cflayer *)(above)) + +/** + * layer_set_dn() - Set the down pointer for a specified layer. + * @layr: Layer where down pointer shall be set. + * @below: Layer below. + */ +#define layer_set_dn(layr, below) ((layr)->dn = (struct cflayer *)(below)) + +/** + * struct dev_info - Physical Device info information about physical layer. + * @dev: Pointer to native physical device. + * @id: Physical ID of the physical connection used by the + * logical CAIF connection. Used by service layers to + * identify their physical id to Caif MUX (CFMUXL)so + * that the MUX can add the correct physical ID to the + * packet. + */ +struct dev_info { + void *dev; + unsigned int id; +}; + +/** + * struct caif_payload_info - Payload information embedded in packet (sk_buff). + * + * @dev_info: Information about the receiving device. + * + * @hdr_len: Header length, used to align pay load on 32bit boundary. + * + * @channel_id: Channel ID of the logical CAIF connection. + * Used by mux to insert channel id into the caif packet. + */ +struct caif_payload_info { + struct dev_info *dev_info; + unsigned short hdr_len; + unsigned short channel_id; +}; + +#endif /* CAIF_LAYER_H_ */ diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h new file mode 100644 index 00000000000..366082c5d43 --- /dev/null +++ b/include/net/caif/cfcnfg.h @@ -0,0 +1,133 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFCNFG_H_ +#define CFCNFG_H_ +#include +#include +#include + +struct cfcnfg; + +/** + * enum cfcnfg_phy_type - Types of physical layers defined in CAIF Stack + * + * @CFPHYTYPE_FRAG: Fragmented frames physical interface. + * @CFPHYTYPE_CAIF: Generic CAIF physical interface + */ +enum cfcnfg_phy_type { + CFPHYTYPE_FRAG = 1, + CFPHYTYPE_CAIF, + CFPHYTYPE_MAX +}; + +/** + * enum cfcnfg_phy_preference - Physical preference HW Abstraction + * + * @CFPHYPREF_UNSPECIFIED: Default physical interface + * + * @CFPHYPREF_LOW_LAT: Default physical interface for low-latency + * traffic + * @CFPHYPREF_HIGH_BW: Default physical interface for high-bandwidth + * traffic + * @CFPHYPREF_LOOP: TEST only Loopback interface simulating modem + * responses. + * + */ +enum cfcnfg_phy_preference { + CFPHYPREF_UNSPECIFIED, + CFPHYPREF_LOW_LAT, + CFPHYPREF_HIGH_BW, + CFPHYPREF_LOOP +}; + +/** + * cfcnfg_create() - Create the CAIF configuration object. + */ +struct cfcnfg *cfcnfg_create(void); + +/** + * cfcnfg_remove() - Remove the CFCNFG object + * @cfg: config object + */ +void cfcnfg_remove(struct cfcnfg *cfg); + +/** + * cfcnfg_add_phy_layer() - Adds a physical layer to the CAIF stack. + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @phy_type: Specifies the type of physical interface, e.g. + * CFPHYTYPE_FRAG. + * @dev: Pointer to link layer device + * @phy_layer: Specify the physical layer. The transmit function + * MUST be set in the structure. + * @phyid: The assigned physical ID for this layer, used in + * cfcnfg_add_adapt_layer to specify PHY for the link. + * @pref: The phy (link layer) preference. + * @fcs: Specify if checksum is used in CAIF Framing Layer. + * @stx: Specify if Start Of Frame eXtention is used. + */ + +void +cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, + void *dev, struct cflayer *phy_layer, u16 *phyid, + enum cfcnfg_phy_preference pref, + bool fcs, bool stx); + +/** + * cfcnfg_del_phy_layer - Deletes an phy layer from the CAIF stack. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @phy_layer: Adaptation layer to be removed. + */ +int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer); + +/** + * cfcnfg_del_adapt_layer - Deletes an adaptation layer from the CAIF stack. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @adap_layer: Adaptation layer to be removed. + */ +int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer); + +/** + * cfcnfg_add_adaptation_layer - Add an adaptation layer to the CAIF stack. + * + * The adaptation Layer is where the interface to application or higher-level + * driver functionality is implemented. + * + * @cnfg: Pointer to a CAIF configuration object, created by + * cfcnfg_create(). + * @param: Link setup parameters. + * @adap_layer: Specify the adaptation layer; the receive and + * flow-control functions MUST be set in the structure. + * + */ +int +cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, + struct cfctrl_link_param *param, + struct cflayer *adap_layer); + +/** + * cfcnfg_get_phyid() - Get physical ID, given type. + * Returns one of the physical interfaces matching the given type. + * Zero if no match is found. + * @cnfg: Configuration object + * @phy_pref: Caif Link Layer preference + */ +struct dev_info *cfcnfg_get_phyid(struct cfcnfg *cnfg, + enum cfcnfg_phy_preference phy_pref); + +/** + * cfcnfg_get_named() - Get the Physical Identifier of CAIF Link Layer + * @cnfg: Configuration object + * @name: Name of the Physical Layer (Caif Link Layer) + */ +int cfcnfg_get_named(struct cfcnfg *cnfg, char *name); + +#endif /* CFCNFG_H_ */ diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h new file mode 100644 index 00000000000..dee25b86caa --- /dev/null +++ b/include/net/caif/cfctrl.h @@ -0,0 +1,138 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFCTRL_H_ +#define CFCTRL_H_ +#include +#include + +/* CAIF Control packet commands */ +enum cfctrl_cmd { + CFCTRL_CMD_LINK_SETUP = 0, + CFCTRL_CMD_LINK_DESTROY = 1, + CFCTRL_CMD_LINK_ERR = 2, + CFCTRL_CMD_ENUM = 3, + CFCTRL_CMD_SLEEP = 4, + CFCTRL_CMD_WAKE = 5, + CFCTRL_CMD_LINK_RECONF = 6, + CFCTRL_CMD_START_REASON = 7, + CFCTRL_CMD_RADIO_SET = 8, + CFCTRL_CMD_MODEM_SET = 9, + CFCTRL_CMD_MASK = 0xf +}; + +/* Channel types */ +enum cfctrl_srv { + CFCTRL_SRV_DECM = 0, + CFCTRL_SRV_VEI = 1, + CFCTRL_SRV_VIDEO = 2, + CFCTRL_SRV_DBG = 3, + CFCTRL_SRV_DATAGRAM = 4, + CFCTRL_SRV_RFM = 5, + CFCTRL_SRV_UTIL = 6, + CFCTRL_SRV_MASK = 0xf +}; + +#define CFCTRL_RSP_BIT 0x20 +#define CFCTRL_ERR_BIT 0x10 + +struct cfctrl_rsp { + void (*linksetup_rsp)(struct cflayer *layer, u8 linkid, + enum cfctrl_srv serv, u8 phyid, + struct cflayer *adapt_layer); + void (*linkdestroy_rsp)(struct cflayer *layer, u8 linkid, + struct cflayer *client_layer); + void (*linkerror_ind)(void); + void (*enum_rsp)(void); + void (*sleep_rsp)(void); + void (*wake_rsp)(void); + void (*restart_rsp)(void); + void (*radioset_rsp)(void); + void (*reject_rsp)(struct cflayer *layer, u8 linkid, + struct cflayer *client_layer);; +}; + +/* Link Setup Parameters for CAIF-Links. */ +struct cfctrl_link_param { + enum cfctrl_srv linktype;/* (T3,T0) Type of Channel */ + u8 priority; /* (P4,P0) Priority of the channel */ + u8 phyid; /* (U2-U0) Physical interface to connect */ + u8 endpoint; /* (E1,E0) Endpoint for data channels */ + u8 chtype; /* (H1,H0) Channel-Type, applies to + * VEI, DEBUG */ + union { + struct { + u8 connid; /* (D7,D0) Video LinkId */ + } video; + + struct { + u32 connid; /* (N31,Ngit0) Connection ID used + * for Datagram */ + } datagram; + + struct { + u32 connid; /* Connection ID used for RFM */ + char volume[20]; /* Volume to mount for RFM */ + } rfm; /* Configuration for RFM */ + + struct { + u16 fifosize_kb; /* Psock FIFO size in KB */ + u16 fifosize_bufs; /* Psock # signal buffers */ + char name[16]; /* Name of the PSOCK service */ + u8 params[255]; /* Link setup Parameters> */ + u16 paramlen; /* Length of Link Setup + * Parameters */ + } utility; /* Configuration for Utility Links (Psock) */ + } u; +}; + +/* This structure is used internally in CFCTRL */ +struct cfctrl_request_info { + int sequence_no; + enum cfctrl_cmd cmd; + u8 channel_id; + struct cfctrl_link_param param; + struct cfctrl_request_info *next; + struct cflayer *client_layer; +}; + +struct cfctrl { + struct cfsrvl serv; + struct cfctrl_rsp res; + atomic_t req_seq_no; + atomic_t rsp_seq_no; + struct cfctrl_request_info *first_req; + /* Protects from simultaneous access to first_req list */ + spinlock_t info_list_lock; +#ifndef CAIF_NO_LOOP + u8 loop_linkid; + int loop_linkused[256]; + /* Protects simultaneous access to loop_linkid and loop_linkused */ + spinlock_t loop_linkid_lock; +#endif + +}; + +void cfctrl_enum_req(struct cflayer *cfctrl, u8 physlinkid); +void cfctrl_linkup_request(struct cflayer *cfctrl, + struct cfctrl_link_param *param, + struct cflayer *user_layer); +int cfctrl_linkdown_req(struct cflayer *cfctrl, u8 linkid, + struct cflayer *client); +void cfctrl_sleep_req(struct cflayer *cfctrl); +void cfctrl_wake_req(struct cflayer *cfctrl); +void cfctrl_getstartreason_req(struct cflayer *cfctrl); +struct cflayer *cfctrl_create(void); +void cfctrl_set_dnlayer(struct cflayer *this, struct cflayer *dn); +void cfctrl_set_uplayer(struct cflayer *this, struct cflayer *up); +struct cfctrl_rsp *cfctrl_get_respfuncs(struct cflayer *layer); +bool cfctrl_req_eq(struct cfctrl_request_info *r1, + struct cfctrl_request_info *r2); +void cfctrl_insert_req(struct cfctrl *ctrl, + struct cfctrl_request_info *req); +struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, + struct cfctrl_request_info *req); +#endif /* CFCTRL_H_ */ diff --git a/include/net/caif/cffrml.h b/include/net/caif/cffrml.h new file mode 100644 index 00000000000..3f14d2e1ce6 --- /dev/null +++ b/include/net/caif/cffrml.h @@ -0,0 +1,16 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFFRML_H_ +#define CFFRML_H_ +#include + +struct cffrml; +struct cflayer *cffrml_create(u16 phyid, bool DoFCS); +void cffrml_set_uplayer(struct cflayer *this, struct cflayer *up); +void cffrml_set_dnlayer(struct cflayer *this, struct cflayer *dn); + +#endif /* CFFRML_H_ */ diff --git a/include/net/caif/cfmuxl.h b/include/net/caif/cfmuxl.h new file mode 100644 index 00000000000..4e1b4f33423 --- /dev/null +++ b/include/net/caif/cfmuxl.h @@ -0,0 +1,22 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFMUXL_H_ +#define CFMUXL_H_ +#include + +struct cfsrvl; +struct cffrml; + +struct cflayer *cfmuxl_create(void); +int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid); +struct cflayer *cfmuxl_remove_dnlayer(struct cflayer *layr, u8 phyid); +int cfmuxl_set_dnlayer(struct cflayer *layr, struct cflayer *up, u8 phyid); +struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 linkid); +bool cfmuxl_is_phy_inuse(struct cflayer *layr, u8 phyid); +u8 cfmuxl_get_phyid(struct cflayer *layr, u8 channel_id); + +#endif /* CFMUXL_H_ */ diff --git a/include/net/caif/cfpkt.h b/include/net/caif/cfpkt.h new file mode 100644 index 00000000000..fbc681beff5 --- /dev/null +++ b/include/net/caif/cfpkt.h @@ -0,0 +1,274 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFPKT_H_ +#define CFPKT_H_ +#include +#include +struct cfpkt; + +/* Create a CAIF packet. + * len: Length of packet to be created + * @return New packet. + */ +struct cfpkt *cfpkt_create(u16 len); + +/* Create a CAIF packet. + * data Data to copy. + * len Length of packet to be created + * @return New packet. + */ +struct cfpkt *cfpkt_create_uplink(const unsigned char *data, unsigned int len); +/* + * Destroy a CAIF Packet. + * pkt Packet to be destoyed. + */ +void cfpkt_destroy(struct cfpkt *pkt); + +/* + * Extract header from packet. + * + * pkt Packet to extract header data from. + * data Pointer to copy the header data into. + * len Length of head data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len); + +/* + * Peek header from packet. + * Reads data from packet without changing packet. + * + * pkt Packet to extract header data from. + * data Pointer to copy the header data into. + * len Length of head data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len); + +/* + * Extract header from trailer (end of packet). + * + * pkt Packet to extract header data from. + * data Pointer to copy the trailer data into. + * len Length of header data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_extr_trail(struct cfpkt *pkt, void *data, u16 len); + +/* + * Add header to packet. + * + * + * pkt Packet to add header data to. + * data Pointer to data to copy into the header. + * len Length of header data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_add_head(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Add trailer to packet. + * + * + * pkt Packet to add trailer data to. + * data Pointer to data to copy into the trailer. + * len Length of trailer data to copy. + * @return zero on success and error code upon failure + */ +int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Pad trailer on packet. + * Moves data pointer in packet, no content copied. + * + * pkt Packet in which to pad trailer. + * len Length of padding to add. + * @return zero on success and error code upon failure + */ +int cfpkt_pad_trail(struct cfpkt *pkt, u16 len); + +/* + * Add a single byte to packet body (tail). + * + * pkt Packet in which to add byte. + * data Byte to add. + * @return zero on success and error code upon failure + */ +int cfpkt_addbdy(struct cfpkt *pkt, const u8 data); + +/* + * Add a data to packet body (tail). + * + * pkt Packet in which to add data. + * data Pointer to data to copy into the packet body. + * len Length of data to add. + * @return zero on success and error code upon failure + */ +int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len); + +/* + * Checks whether there are more data to process in packet. + * pkt Packet to check. + * @return true if more data are available in packet false otherwise + */ +bool cfpkt_more(struct cfpkt *pkt); + +/* + * Checks whether the packet is erroneous, + * i.e. if it has been attempted to extract more data than available in packet + * or writing more data than has been allocated in cfpkt_create(). + * pkt Packet to check. + * @return true on error false otherwise + */ +bool cfpkt_erroneous(struct cfpkt *pkt); + +/* + * Get the packet length. + * pkt Packet to get length from. + * @return Number of bytes in packet. + */ +u16 cfpkt_getlen(struct cfpkt *pkt); + +/* + * Set the packet length, by adjusting the trailer pointer according to length. + * pkt Packet to set length. + * len Packet length. + * @return Number of bytes in packet. + */ +int cfpkt_setlen(struct cfpkt *pkt, u16 len); + +/* + * cfpkt_append - Appends a packet's data to another packet. + * dstpkt: Packet to append data into, WILL BE FREED BY THIS FUNCTION + * addpkt: Packet to be appended and automatically released, + * WILL BE FREED BY THIS FUNCTION. + * expectlen: Packet's expected total length. This should be considered + * as a hint. + * NB: Input packets will be destroyed after appending and cannot be used + * after calling this function. + * @return The new appended packet. + */ +struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, struct cfpkt *addpkt, + u16 expectlen); + +/* + * cfpkt_split - Split a packet into two packets at the specified split point. + * pkt: Packet to be split (will contain the first part of the data on exit) + * pos: Position to split packet in two parts. + * @return The new packet, containing the second part of the data. + */ +struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos); + +/* + * Iteration function, iterates the packet buffers from start to end. + * + * Checksum iteration function used to iterate buffers + * (we may have packets consisting of a chain of buffers) + * pkt: Packet to calculate checksum for + * iter_func: Function pointer to iteration function + * chks: Checksum calculated so far. + * buf: Pointer to the buffer to checksum + * len: Length of buf. + * data: Initial checksum value. + * @return Checksum of buffer. + */ + +u16 cfpkt_iterate(struct cfpkt *pkt, + u16 (*iter_func)(u16 chks, void *buf, u16 len), + u16 data); + +/* Append by giving user access to packet buffer + * cfpkt Packet to append to + * buf Buffer inside pkt that user shall copy data into + * buflen Length of buffer and number of bytes added to packet + * @return 0 on error, 1 on success + */ +int cfpkt_raw_append(struct cfpkt *cfpkt, void **buf, unsigned int buflen); + +/* Extract by giving user access to packet buffer + * cfpkt Packet to extract from + * buf Buffer inside pkt that user shall copy data from + * buflen Length of buffer and number of bytes removed from packet + * @return 0 on error, 1 on success + */ +int cfpkt_raw_extract(struct cfpkt *cfpkt, void **buf, unsigned int buflen); + +/* Map from a "native" packet (e.g. Linux Socket Buffer) to a CAIF packet. + * dir - Direction indicating whether this packet is to be sent or received. + * nativepkt - The native packet to be transformed to a CAIF packet + * @return The mapped CAIF Packet CFPKT. + */ +struct cfpkt *cfpkt_fromnative(enum caif_direction dir, void *nativepkt); + +/* Map from a CAIF packet to a "native" packet (e.g. Linux Socket Buffer). + * pkt - The CAIF packet to be transformed into a "native" packet. + * @return The native packet transformed from a CAIF packet. + */ +void *cfpkt_tonative(struct cfpkt *pkt); + +/* + * Insert a packet in the packet queue. + * pktq Packet queue to insert into + * pkt Packet to be inserted in queue + * prio Priority of packet + */ +void cfpkt_queue(struct cfpktq *pktq, struct cfpkt *pkt, + unsigned short prio); + +/* + * Remove a packet from the packet queue. + * pktq Packet queue to fetch packets from. + * @return Dequeued packet. + */ +struct cfpkt *cfpkt_dequeue(struct cfpktq *pktq); + +/* + * Peek into a packet from the packet queue. + * pktq Packet queue to fetch packets from. + * @return Peeked packet. + */ +struct cfpkt *cfpkt_qpeek(struct cfpktq *pktq); + +/* + * Initiates the packet queue. + * @return Pointer to new packet queue. + */ +struct cfpktq *cfpktq_create(void); + +/* + * Get the number of packets in the queue. + * pktq Packet queue to fetch count from. + * @return Number of packets in queue. + */ +int cfpkt_qcount(struct cfpktq *pktq); + +/* + * Put content of packet into buffer for debuging purposes. + * pkt Packet to copy data from + * buf Buffer to copy data into + * buflen Length of data to copy + * @return Pointer to copied data + */ +char *cfpkt_log_pkt(struct cfpkt *pkt, char *buf, int buflen); + +/* + * Clones a packet and releases the original packet. + * This is used for taking ownership of a packet e.g queueing. + * pkt Packet to clone and release. + * @return Cloned packet. + */ +struct cfpkt *cfpkt_clone_release(struct cfpkt *pkt); + + +/* + * Returns packet information for a packet. + * pkt Packet to get info from; + * @return Packet information + */ +struct caif_payload_info *cfpkt_info(struct cfpkt *pkt); +/*! @} */ +#endif /* CFPKT_H_ */ diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h new file mode 100644 index 00000000000..b8374321b36 --- /dev/null +++ b/include/net/caif/cfserl.h @@ -0,0 +1,12 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFSERL_H_ +#define CFSERL_H_ +#include + +struct cflayer *cfserl_create(int type, int instance, bool use_stx); +#endif /* CFSERL_H_ */ diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h new file mode 100644 index 00000000000..b2a12db20cd --- /dev/null +++ b/include/net/caif/cfsrvl.h @@ -0,0 +1,34 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CFSRVL_H_ +#define CFSRVL_H_ +#include +#include +#include +struct cfsrvl { + struct cflayer layer; + bool open; + bool phy_flow_on; + bool modem_flow_on; + struct dev_info dev_info; +}; + +struct cflayer *cfvei_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfdgml_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfutill_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfvidl_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfrfml_create(u8 linkid, struct dev_info *dev_info); +struct cflayer *cfdbgl_create(u8 linkid, struct dev_info *dev_info); +bool cfsrvl_phyid_match(struct cflayer *layer, int phyid); +void cfservl_destroy(struct cflayer *layer); +void cfsrvl_init(struct cfsrvl *service, + u8 channel_id, + struct dev_info *dev_info); +bool cfsrvl_ready(struct cfsrvl *service, int *err); +u8 cfsrvl_getphyid(struct cflayer *layer); + +#endif /* CFSRVL_H_ */ -- cgit v1.2.3-70-g09d2 From 2721c5b9dd2a56a9710021c00146bb26ba8dd7b3 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Tue, 30 Mar 2010 13:56:22 +0000 Subject: net-caif: add CAIF Link layer device header files Header files for CAIF Link layer net-device, and link-layer registration. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_dev.h | 90 ++++++++++++++++++++++++++++++++++++++++++ include/net/caif/caif_device.h | 55 ++++++++++++++++++++++++++ 2 files changed, 145 insertions(+) create mode 100644 include/net/caif/caif_dev.h create mode 100644 include/net/caif/caif_device.h (limited to 'include/net') diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h new file mode 100644 index 00000000000..42a7c786784 --- /dev/null +++ b/include/net/caif/caif_dev.h @@ -0,0 +1,90 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_DEV_H_ +#define CAIF_DEV_H_ + +#include +#include +#include +#include + +/** + * struct caif_param - CAIF parameters. + * @size: Length of data + * @data: Binary Data Blob + */ +struct caif_param { + u16 size; + u8 data[256]; +}; + +/** + * caif_connect_request - Request data for CAIF channel setup. + * @sockaddr: Socket address to connect. + * @priority: Priority of the connection. + * @link_selector: Link selector (high bandwidth or low latency) + * @link_name: Name of the CAIF Link Layer to use. + * + * This struct is used when connecting a CAIF channel. + * It contains all CAIF channel configuration options. + */ +struct caif_connect_request { + int protocol; + struct sockaddr_caif sockaddr; + enum caif_channel_priority priority; + enum caif_link_selector link_selector; + char link_name[16]; + struct caif_param param; +}; + +/** + * caif_connect_client - Connect a client to CAIF Core Stack. + * @config: Channel setup parameters, specifying what address + * to connect on the Modem. + * @client_layer: User implementation of client layer. This layer + * MUST have receive and control callback functions + * implemented. + * + * This function connects a CAIF channel. The Client must implement + * the struct cflayer. This layer represents the Client layer and holds + * receive functions and control callback functions. Control callback + * function will receive information about connect/disconnect responses, + * flow control etc (see enum caif_control). + * E.g. CAIF Socket will call this function for each socket it connects + * and have one client_layer instance for each socket. + */ +int caif_connect_client(struct caif_connect_request *config, + struct cflayer *client_layer); + +/** + * caif_disconnect_client - Disconnects a client from the CAIF stack. + * + * @client_layer: Client layer to be removed. + */ +int caif_disconnect_client(struct cflayer *client_layer); + +/** + * connect_req_to_link_param - Translate configuration parameters + * from socket format to internal format. + * @cnfg: Pointer to configuration handler + * @con_req: Configuration parameters supplied in function + * caif_connect_client + * @channel_setup_param: Parameters supplied to the CAIF Core stack for + * setting up channels. + * + */ +int connect_req_to_link_param(struct cfcnfg *cnfg, + struct caif_connect_request *con_req, + struct cfctrl_link_param *channel_setup_param); + +/** + * get_caif_conf() - Get the configuration handler. + */ +struct cfcnfg *get_caif_conf(void); + + +#endif /* CAIF_DEV_H_ */ diff --git a/include/net/caif/caif_device.h b/include/net/caif/caif_device.h new file mode 100644 index 00000000000..d02f044adb8 --- /dev/null +++ b/include/net/caif/caif_device.h @@ -0,0 +1,55 @@ +/* + * Copyright (C) ST-Ericsson AB 2010 + * Author: Sjur Brendeland/ sjur.brandeland@stericsson.com + * License terms: GNU General Public License (GPL) version 2 + */ + +#ifndef CAIF_DEVICE_H_ +#define CAIF_DEVICE_H_ +#include +#include +#include +#include +#include + +/** + * struct caif_dev_common - data shared between CAIF drivers and stack. + * @flowctrl: Flow Control callback function. This function is + * supplied by CAIF Core Stack and is used by CAIF + * Link Layer to send flow-stop to CAIF Core. + * The flow information will be distributed to all + * clients of CAIF. + * + * @link_select: Profile of device, either high-bandwidth or + * low-latency. This member is set by CAIF Link + * Layer Device in order to indicate if this device + * is a high bandwidth or low latency device. + * + * @use_frag: CAIF Frames may be fragmented. + * Is set by CAIF Link Layer in order to indicate if the + * interface receives fragmented frames that must be + * assembled by CAIF Core Layer. + * + * @use_fcs: Indicate if Frame CheckSum (fcs) is used. + * Is set if the physical interface is + * using Frame Checksum on the CAIF Frames. + * + * @use_stx: Indicate STart of frame eXtension (stx) in use. + * Is set if the CAIF Link Layer expects + * CAIF Frames to start with the STX byte. + * + * This structure is shared between the CAIF drivers and the CAIF stack. + * It is used by the device to register its behavior. + * CAIF Core layer must set the member flowctrl in order to supply + * CAIF Link Layer with the flow control function. + * + */ + struct caif_dev_common { + void (*flowctrl)(struct net_device *net, int on); + enum caif_link_selector link_select; + int use_frag; + int use_fcs; + int use_stx; +}; + +#endif /* CAIF_DEVICE_H_ */ -- cgit v1.2.3-70-g09d2 From d57b8fb8a8f94bdf467a4435be7d8bbebf87fe2a Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Mon, 29 Mar 2010 06:00:05 +0000 Subject: ipv6: Use __fls() instead of fls() in __ipv6_addr_diff(). Because we have ensured that the argument is non-zero, it is better to use __fls() and generate better code. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index e72fb10ce57..033ddd4652a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -422,7 +422,7 @@ static inline int __ipv6_addr_diff(const void *token1, const void *token2, int a for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) - return i * 32 + 32 - fls(ntohl(xb)); + return i * 32 + 31 - __fls(ntohl(xb)); } /* -- cgit v1.2.3-70-g09d2 From e3cf8b3f7b9eefbe1d39b160726d6e5c2cbb4c5d Mon Sep 17 00:00:00 2001 From: Zhu Yi Date: Mon, 29 Mar 2010 17:35:07 +0800 Subject: mac80211: support paged rx SKBs Mac80211 drivers can now pass paged SKBs to mac80211 via ieee80211_rx{_irqsafe}. The implementation currently use skb_linearize() in a few places i.e. management frame handling, software decryption, defragmentation and A-MSDU process. We will optimize them one by one later. Signed-off-by: Zhu Yi Cc: Kalle Valo Cc: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 ++++- net/mac80211/rx.c | 36 ++++++++++++++++++++++++++++++++---- net/wireless/util.c | 24 ++++++++++++++++++------ 3 files changed, 54 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1a8f50af49a..ecaae10426f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1822,7 +1822,10 @@ void ieee80211_restart_hw(struct ieee80211_hw *hw); * ieee80211_rx - receive frame * * Use this function to hand received frames to mac80211. The receive - * buffer in @skb must start with an IEEE 802.11 header. + * buffer in @skb must start with an IEEE 802.11 header. In case of a + * paged @skb is used, the driver is recommended to put the ieee80211 + * header of the frame on the linear part of the @skb to avoid memory + * allocation and/or memcpy by the stack. * * This function may not be called in IRQ context. Calls to this function * for a single hardware must be synchronized against each other. Calls to diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1da57c8e849..11ed5aa90f8 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -38,7 +38,7 @@ static struct sk_buff *remove_monitor_info(struct ieee80211_local *local, { if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) { if (likely(skb->len > FCS_LEN)) - skb_trim(skb, skb->len - FCS_LEN); + __pskb_trim(skb, skb->len - FCS_LEN); else { /* driver bug */ WARN_ON(1); @@ -227,6 +227,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, if (local->hw.flags & IEEE80211_HW_RX_INCLUDES_FCS) present_fcs_len = FCS_LEN; + /* make sure hdr->frame_control is on the linear part */ + if (!pskb_may_pull(origskb, 2)) { + dev_kfree_skb(origskb); + return NULL; + } + if (!local->monitors) { if (should_drop_frame(origskb, present_fcs_len)) { dev_kfree_skb(origskb); @@ -931,6 +937,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } + if (skb_linearize(rx->skb)) + return RX_DROP_UNUSABLE; + /* Check for weak IVs if possible */ if (rx->sta && rx->key->conf.alg == ALG_WEP && ieee80211_is_data(hdr->frame_control) && @@ -1231,6 +1240,9 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) } I802_DEBUG_INC(rx->local->rx_handlers_fragments); + if (skb_linearize(rx->skb)) + return RX_DROP_UNUSABLE; + seq = (sc & IEEE80211_SCTL_SEQ) >> 4; if (frag == 0) { @@ -1588,6 +1600,9 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx) skb->dev = dev; __skb_queue_head_init(&frame_list); + if (skb_linearize(skb)) + return RX_DROP_UNUSABLE; + ieee80211_amsdu_to_8023s(skb, &frame_list, dev->dev_addr, rx->sdata->vif.type, rx->local->hw.extra_tx_headroom); @@ -2357,29 +2372,42 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, struct ieee80211_local *local = hw_to_local(hw); struct ieee80211_sub_if_data *sdata; struct ieee80211_hdr *hdr; + __le16 fc; struct ieee80211_rx_data rx; int prepares; struct ieee80211_sub_if_data *prev = NULL; struct sk_buff *skb_new; struct sta_info *sta, *tmp; bool found_sta = false; + int err = 0; - hdr = (struct ieee80211_hdr *)skb->data; + fc = ((struct ieee80211_hdr *)skb->data)->frame_control; memset(&rx, 0, sizeof(rx)); rx.skb = skb; rx.local = local; - if (ieee80211_is_data(hdr->frame_control) || ieee80211_is_mgmt(hdr->frame_control)) + if (ieee80211_is_data(fc) || ieee80211_is_mgmt(fc)) local->dot11ReceivedFragmentCount++; if (unlikely(test_bit(SCAN_HW_SCANNING, &local->scanning) || test_bit(SCAN_OFF_CHANNEL, &local->scanning))) rx.flags |= IEEE80211_RX_IN_SCAN; + if (ieee80211_is_mgmt(fc)) + err = skb_linearize(skb); + else + err = !pskb_may_pull(skb, ieee80211_hdrlen(fc)); + + if (err) { + dev_kfree_skb(skb); + return; + } + + hdr = (struct ieee80211_hdr *)skb->data; ieee80211_parse_qos(&rx); ieee80211_verify_alignment(&rx); - if (ieee80211_is_data(hdr->frame_control)) { + if (ieee80211_is_data(fc)) { for_each_sta_info(local, hdr->addr2, sta, tmp) { rx.sta = sta; found_sta = true; diff --git a/net/wireless/util.c b/net/wireless/util.c index be2ab8c59e3..7acb81b9675 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -330,11 +330,18 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, if (iftype == NL80211_IFTYPE_MESH_POINT) { struct ieee80211s_hdr *meshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); - hdrlen += ieee80211_get_mesh_hdrlen(meshdr); + /* make sure meshdr->flags is on the linear part */ + if (!pskb_may_pull(skb, hdrlen + 1)) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A5_A6) { - memcpy(dst, meshdr->eaddr1, ETH_ALEN); - memcpy(src, meshdr->eaddr2, ETH_ALEN); + skb_copy_bits(skb, hdrlen + + offsetof(struct ieee80211s_hdr, eaddr1), + dst, ETH_ALEN); + skb_copy_bits(skb, hdrlen + + offsetof(struct ieee80211s_hdr, eaddr2), + src, ETH_ALEN); } + hdrlen += ieee80211_get_mesh_hdrlen(meshdr); } break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): @@ -346,9 +353,14 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, if (iftype == NL80211_IFTYPE_MESH_POINT) { struct ieee80211s_hdr *meshdr = (struct ieee80211s_hdr *) (skb->data + hdrlen); - hdrlen += ieee80211_get_mesh_hdrlen(meshdr); + /* make sure meshdr->flags is on the linear part */ + if (!pskb_may_pull(skb, hdrlen + 1)) + return -1; if (meshdr->flags & MESH_FLAGS_AE_A4) - memcpy(src, meshdr->eaddr1, ETH_ALEN); + skb_copy_bits(skb, hdrlen + + offsetof(struct ieee80211s_hdr, eaddr1), + src, ETH_ALEN); + hdrlen += ieee80211_get_mesh_hdrlen(meshdr); } break; case cpu_to_le16(0): @@ -357,7 +369,7 @@ int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, break; } - if (unlikely(skb->len - hdrlen < 8)) + if (!pskb_may_pull(skb, hdrlen + 8)) return -1; payload = skb->data + hdrlen; -- cgit v1.2.3-70-g09d2 From e1b3ec1a2a336c328c336cfa5485a5f0484cc90d Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Mon, 29 Mar 2010 12:18:34 +0200 Subject: mac80211: explicitly disable/enable QoS Add interface to disable/enable QoS (aka WMM or WME). Currently drivers enable it explicitly when ->conf_tx method is called, and newer disable. Disabling is needed for some APs, which do not support QoS, such we should send QoS frames to them. Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 +++++ net/mac80211/mlme.c | 9 ++++++++- net/mac80211/util.c | 5 +++++ 3 files changed, 18 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index ecaae10426f..dcf3c5f23c9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -587,11 +587,15 @@ struct ieee80211_rx_status { * may turn the device off as much as possible. Typically, this flag will * be set when an interface is set UP but not associated or scanning, but * it can also be unset in that case when monitor interfaces are active. + * @IEEE80211_CONF_QOS: Enable 802.11e QoS also know as WMM (Wireless + * Multimedia). On some drivers (iwlwifi is one of know) we have + * to enable/disable QoS explicitly. */ enum ieee80211_conf_flags { IEEE80211_CONF_MONITOR = (1<<0), IEEE80211_CONF_PS = (1<<1), IEEE80211_CONF_IDLE = (1<<2), + IEEE80211_CONF_QOS = (1<<3), }; @@ -616,6 +620,7 @@ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_CHANNEL = BIT(6), IEEE80211_CONF_CHANGE_RETRY_LIMITS = BIT(7), IEEE80211_CONF_CHANGE_IDLE = BIT(8), + IEEE80211_CONF_CHANGE_QOS = BIT(9), }; /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 65eafda5738..c686d1b90f9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -586,6 +586,9 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, int count; u8 *pos, uapsd_queues = 0; + if (!local->ops->conf_tx) + return; + if (local->hw.queues < 4) return; @@ -660,11 +663,15 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, params.aifs, params.cw_min, params.cw_max, params.txop, params.uapsd); #endif - if (drv_conf_tx(local, queue, ¶ms) && local->ops->conf_tx) + if (drv_conf_tx(local, queue, ¶ms)) printk(KERN_DEBUG "%s: failed to set TX queue " "parameters for queue %d\n", wiphy_name(local->hw.wiphy), queue); } + + /* enable WMM or activate new settings */ + local->hw.conf.flags |= IEEE80211_CONF_QOS; + drv_config(local, IEEE80211_CONF_CHANGE_QOS); } static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c453226f06b..7b2c170af71 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -796,6 +796,11 @@ void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata) drv_conf_tx(local, queue, &qparam); } + + /* after reinitialize QoS TX queues setting to default, + * disable QoS at all */ + local->hw.conf.flags &= ~IEEE80211_CONF_QOS; + drv_config(local, IEEE80211_CONF_CHANGE_QOS); } void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, -- cgit v1.2.3-70-g09d2 From f9ea3eb44218b0e12a190f222400f8d56136915f Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 18 Mar 2010 18:29:34 -0700 Subject: include/net/iw_handler.h: Use SIOCIWFIRST not SIOCSIWCOMMIT in comment to match use in IW_IOCTL_IDX macro Signed-off-by: Joe Perches Signed-off-by: John W. Linville --- include/net/iw_handler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/iw_handler.h b/include/net/iw_handler.h index b2b98f3fa26..3afdb21cc31 100644 --- a/include/net/iw_handler.h +++ b/include/net/iw_handler.h @@ -323,7 +323,7 @@ typedef int (*iw_handler)(struct net_device *dev, struct iw_request_info *info, struct iw_handler_def { /* Array of handlers for standard ioctls - * We will call dev->wireless_handlers->standard[ioctl - SIOCSIWCOMMIT] + * We will call dev->wireless_handlers->standard[ioctl - SIOCIWFIRST] */ const iw_handler * standard; /* Number of handlers defined (more precisely, index of the -- cgit v1.2.3-70-g09d2 From 5d944c640b4ae5f37c537acf491c2f0eb89fa0d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 31 Mar 2010 07:06:04 +0000 Subject: gen_estimator: deadlock fix One of my test machine got a deadlock during "tc" sessions, adding/deleting classes & filters, using traffic estimators. After some analysis, I believe we have a potential use after free case in est_timer() : spin_lock(e->stats_lock); << HERE >> read_lock(&est_lock); if (e->bstats == NULL) << TEST >> goto skip; Test is done a bit late, because after estimator is killed, and before rcu grace period elapsed, we might already have freed/reuse memory where e->stats_locks points to (some qdisc->q.lock) A possible fix is to respect a rcu grace period at Qdisc dismantle time. On 64bit, sizeof(struct Qdisc) is exactly 192 bytes. Adding 16 bytes to it (for struct rcu_head) is a problem because it might change performance, given QDISC_ALIGNTO is 32 bytes. This is why I also change QDISC_ALIGNTO to 64 bytes, to satisfy most current alignment requirements. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 2 +- include/net/sch_generic.h | 1 + net/sched/sch_generic.c | 15 +++++++++++++-- 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index b6cdc33b39c..9d4d87cc970 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -12,7 +12,7 @@ struct qdisc_walker { int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *); }; -#define QDISC_ALIGNTO 32 +#define QDISC_ALIGNTO 64 #define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1)) static inline void *qdisc_priv(struct Qdisc *q) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 67dc08eaaa4..03ca5d82675 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -73,6 +73,7 @@ struct Qdisc { struct sk_buff_head q; struct gnet_stats_basic_packed bstats; struct gnet_stats_queue qstats; + struct rcu_head rcu_head; }; struct Qdisc_class_ops { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 5173c1e1b19..17513252e83 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -528,7 +528,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, unsigned int size; int err = -ENOBUFS; - /* ensure that the Qdisc and the private data are 32-byte aligned */ + /* ensure that the Qdisc and the private data are 64-byte aligned */ size = QDISC_ALIGN(sizeof(*sch)); size += ops->priv_size + (QDISC_ALIGNTO - 1); @@ -590,6 +590,13 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); +static void qdisc_rcu_free(struct rcu_head *head) +{ + struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); + + kfree((char *) qdisc - qdisc->padded); +} + void qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; @@ -613,7 +620,11 @@ void qdisc_destroy(struct Qdisc *qdisc) dev_put(qdisc_dev(qdisc)); kfree_skb(qdisc->gso_skb); - kfree((char *) qdisc - qdisc->padded); + /* + * gen_estimator est_timer() might access qdisc->q.lock, + * wait a RCU grace period before freeing qdisc. + */ + call_rcu(&qdisc->rcu_head, qdisc_rcu_free); } EXPORT_SYMBOL(qdisc_destroy); -- cgit v1.2.3-70-g09d2 From bd2c77a0a749589b45f2697ea446a4438d078f9b Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki / 吉藤英明 Date: Wed, 31 Mar 2010 22:24:22 +0000 Subject: ipv6 fib: Make rt6_info{} more cache-line aware. The head element of rt6_info{} is dst_entry{}, and IPv6 specific elements follow. Because elements at the end of dst_entry{} are frequently updated, it is not good to put frequently-used static elements, such as rt6i_idev, rt6i_dst or rt6i_flags in the same cache line. On the other hand, fib6_table, rt6i_node or rt6i_gateway are rarely used, so it is okay to stay in the same cache line. Let's rearrange rt6_info{}. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 86f46c49e31..4b1dc1161c3 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -88,34 +88,37 @@ struct rt6_info { struct dst_entry dst; } u; - struct inet6_dev *rt6i_idev; - #define rt6i_dev u.dst.dev #define rt6i_nexthop u.dst.neighbour #define rt6i_expires u.dst.expires + /* + * Tail elements of dst_entry (__refcnt etc.) + * and these elements (rarely used in hot path) are in + * the same cache line. + */ + struct fib6_table *rt6i_table; struct fib6_node *rt6i_node; struct in6_addr rt6i_gateway; - - u32 rt6i_flags; - u32 rt6i_metric; - atomic_t rt6i_ref; - /* more non-fragment space at head required */ - unsigned short rt6i_nfheader_len; - - u8 rt6i_protocol; + atomic_t rt6i_ref; - struct fib6_table *rt6i_table; + /* These are in a separate cache line. */ + struct rt6key rt6i_dst ____cacheline_aligned_in_smp; + u32 rt6i_flags; + struct rt6key rt6i_src; + u32 rt6i_metric; - struct rt6key rt6i_dst; + struct inet6_dev *rt6i_idev; #ifdef CONFIG_XFRM u32 rt6i_flow_cache_genid; #endif + /* more non-fragment space at head required */ + unsigned short rt6i_nfheader_len; - struct rt6key rt6i_src; + u8 rt6i_protocol; }; static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) -- cgit v1.2.3-70-g09d2 From 22bedad3ce112d5ca1eaf043d4990fa2ed698c87 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Apr 2010 21:22:57 +0000 Subject: net: convert multicast list to list_head Converts the list and the core manipulating with it to be the same as uc_list. +uses two functions for adding/removing mc address (normal and "global" variant) instead of a function parameter. +removes dev_mcast.c completely. +exposes netdev_hw_addr_list_* macros along with __hw_addr_* functions for manipulation with lists on a sandbox (used in bonding and 80211 drivers) Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/infiniband/hw/nes/nes_nic.c | 7 +- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 9 +- drivers/media/dvb/dvb-core/dvb_net.c | 10 +- drivers/net/3c505.c | 7 +- drivers/net/3c523.c | 7 +- drivers/net/3c527.c | 6 +- drivers/net/7990.c | 6 +- drivers/net/8139cp.c | 6 +- drivers/net/8139too.c | 6 +- drivers/net/82596.c | 6 +- drivers/net/a2065.c | 6 +- drivers/net/amd8111e.c | 6 +- drivers/net/arm/am79c961a.c | 6 +- drivers/net/arm/at91_ether.c | 6 +- drivers/net/arm/ixp4xx_eth.c | 8 +- drivers/net/arm/ks8695net.c | 10 +- drivers/net/at1700.c | 6 +- drivers/net/atl1c/atl1c_main.c | 6 +- drivers/net/atl1e/atl1e_main.c | 6 +- drivers/net/atlx/atl2.c | 6 +- drivers/net/atlx/atlx.c | 6 +- drivers/net/atp.c | 6 +- drivers/net/au1000_eth.c | 6 +- drivers/net/b44.c | 6 +- drivers/net/bcm63xx_enet.c | 6 +- drivers/net/benet/be_cmds.c | 6 +- drivers/net/bfin_mac.c | 6 +- drivers/net/bmac.c | 12 +- drivers/net/bnx2.c | 5 +- drivers/net/bnx2x_main.c | 18 +- drivers/net/bonding/bond_main.c | 157 +++++-------- drivers/net/bonding/bonding.h | 2 +- drivers/net/cassini.c | 12 +- drivers/net/chelsio/pm3393.c | 7 +- drivers/net/cpmac.c | 16 +- drivers/net/cris/eth_v10.c | 6 +- drivers/net/cxgb3/xgmac.c | 8 +- drivers/net/davinci_emac.c | 7 +- drivers/net/declance.c | 6 +- drivers/net/defxx.c | 6 +- drivers/net/depca.c | 6 +- drivers/net/dl2k.c | 6 +- drivers/net/dm9000.c | 6 +- drivers/net/e100.c | 6 +- drivers/net/e1000/e1000_main.c | 7 +- drivers/net/e1000e/netdev.c | 7 +- drivers/net/eepro.c | 6 +- drivers/net/eexpress.c | 6 +- drivers/net/ehea/ehea_main.c | 6 +- drivers/net/enic/enic_main.c | 6 +- drivers/net/epic100.c | 6 +- drivers/net/ethoc.c | 6 +- drivers/net/ewrk3.c | 6 +- drivers/net/fealnx.c | 6 +- drivers/net/fec.c | 10 +- drivers/net/fec_mpc52xx.c | 6 +- drivers/net/forcedeth.c | 10 +- drivers/net/fs_enet/mac-fcc.c | 6 +- drivers/net/fs_enet/mac-fec.c | 6 +- drivers/net/fs_enet/mac-scc.c | 6 +- drivers/net/gianfar.c | 9 +- drivers/net/greth.c | 6 +- drivers/net/hamachi.c | 8 +- drivers/net/hp100.c | 6 +- drivers/net/ibm_newemac/core.c | 11 +- drivers/net/ibmlana.c | 8 +- drivers/net/ibmveth.c | 6 +- drivers/net/igb/igb_main.c | 6 +- drivers/net/igbvf/netdev.c | 6 +- drivers/net/ioc3-eth.c | 6 +- drivers/net/ipg.c | 6 +- drivers/net/iseries_veth.c | 6 +- drivers/net/ixgb/ixgb_main.c | 6 +- drivers/net/ixgbe/ixgbe_common.c | 6 +- drivers/net/ixgbevf/vf.c | 6 +- drivers/net/jme.c | 6 +- drivers/net/korina.c | 6 +- drivers/net/ks8851.c | 6 +- drivers/net/ks8851_mll.c | 12 +- drivers/net/ksz884x.c | 11 +- drivers/net/lib82596.c | 6 +- drivers/net/lib8390.c | 6 +- drivers/net/ll_temac_main.c | 16 +- drivers/net/lp486e.c | 6 +- drivers/net/macb.c | 6 +- drivers/net/mace.c | 6 +- drivers/net/macmace.c | 6 +- drivers/net/mlx4/en_netdev.c | 6 +- drivers/net/mv643xx_eth.c | 6 +- drivers/net/myri10ge/myri10ge.c | 8 +- drivers/net/natsemi.c | 6 +- drivers/net/netxen/netxen_nic_hw.c | 12 +- drivers/net/ni52.c | 6 +- drivers/net/niu.c | 5 +- drivers/net/octeon/octeon_mgmt.c | 6 +- drivers/net/pci-skeleton.c | 6 +- drivers/net/pcmcia/axnet_cs.c | 6 +- drivers/net/pcmcia/fmvj18x_cs.c | 6 +- drivers/net/pcmcia/nmclan_cs.c | 6 +- drivers/net/pcmcia/smc91c92_cs.c | 8 +- drivers/net/pcmcia/xirc2ps_cs.c | 6 +- drivers/net/pcnet32.c | 6 +- drivers/net/ps3_gelic_net.c | 6 +- drivers/net/qlcnic/qlcnic_hw.c | 6 +- drivers/net/qlge/qlge_main.c | 6 +- drivers/net/r6040.c | 10 +- drivers/net/r8169.c | 6 +- drivers/net/s2io.c | 8 +- drivers/net/sb1250-mac.c | 6 +- drivers/net/sc92031.c | 6 +- drivers/net/sfc/efx.c | 6 +- drivers/net/sis190.c | 6 +- drivers/net/sis900.c | 10 +- drivers/net/skfp/skfddi.c | 12 +- drivers/net/skge.c | 12 +- drivers/net/sky2.c | 6 +- drivers/net/smc911x.c | 13 +- drivers/net/smc9194.c | 13 +- drivers/net/smc91x.c | 8 +- drivers/net/smsc911x.c | 6 +- drivers/net/smsc9420.c | 6 +- drivers/net/sonic.c | 6 +- drivers/net/spider_net.c | 6 +- drivers/net/starfire.c | 10 +- drivers/net/stmmac/dwmac100.c | 6 +- drivers/net/stmmac/dwmac1000_core.c | 6 +- drivers/net/sun3_82586.c | 6 +- drivers/net/sunbmac.c | 6 +- drivers/net/sundance.c | 6 +- drivers/net/sungem.c | 6 +- drivers/net/sunhme.c | 12 +- drivers/net/sunlance.c | 6 +- drivers/net/sunqe.c | 6 +- drivers/net/sunvnet.c | 8 +- drivers/net/tc35815.c | 6 +- drivers/net/tehuti.c | 6 +- drivers/net/tg3.c | 6 +- drivers/net/tlan.c | 8 +- drivers/net/tokenring/3c359.c | 12 +- drivers/net/tokenring/ibmtr.c | 12 +- drivers/net/tokenring/lanstreamer.c | 12 +- drivers/net/tokenring/olympic.c | 12 +- drivers/net/tokenring/tms380tr.c | 12 +- drivers/net/tsi108_eth.c | 6 +- drivers/net/tulip/de2104x.c | 12 +- drivers/net/tulip/de4x5.c | 10 +- drivers/net/tulip/dmfe.c | 12 +- drivers/net/tulip/tulip_core.c | 27 ++- drivers/net/tulip/uli526x.c | 6 +- drivers/net/tulip/winbond-840.c | 12 +- drivers/net/typhoon.c | 6 +- drivers/net/ucc_geth.c | 8 +- drivers/net/usb/asix.c | 16 +- drivers/net/usb/catc.c | 6 +- drivers/net/usb/dm9601.c | 6 +- drivers/net/usb/mcs7830.c | 6 +- drivers/net/usb/smsc75xx.c | 6 +- drivers/net/usb/smsc95xx.c | 6 +- drivers/net/via-rhine.c | 6 +- drivers/net/via-velocity.c | 6 +- drivers/net/virtio_net.c | 5 +- drivers/net/vmxnet3/vmxnet3_drv.c | 6 +- drivers/net/vxge/vxge-main.c | 6 +- drivers/net/wireless/adm8211.c | 12 +- drivers/net/wireless/ath/ar9170/main.c | 14 +- drivers/net/wireless/ath/ath5k/base.c | 17 +- drivers/net/wireless/libertas/main.c | 12 +- drivers/net/wireless/libertas_tf/main.c | 14 +- drivers/net/wireless/mwl8k.c | 24 +- drivers/net/wireless/orinoco/hw.c | 6 +- drivers/net/wireless/orinoco/hw.h | 1 - drivers/net/wireless/ray_cs.c | 12 +- drivers/net/wireless/rndis_wlan.c | 6 +- drivers/net/wireless/rtl818x/rtl8180_dev.c | 6 +- drivers/net/wireless/rtl818x/rtl8187_dev.c | 4 +- drivers/net/wireless/wl12xx/wl1271_main.c | 25 +- drivers/net/wireless/zd1201.c | 6 +- drivers/net/wireless/zd1211rw/zd_mac.c | 13 +- drivers/net/yellowfin.c | 12 +- drivers/s390/net/qeth_l2_main.c | 5 +- drivers/scsi/fcoe/fcoe.c | 4 +- drivers/staging/arlan/arlan-main.c | 9 +- drivers/staging/et131x/et131x_netdev.c | 6 +- drivers/staging/slicoss/slicoss.c | 6 +- drivers/staging/vt6655/device_main.c | 6 +- drivers/staging/vt6656/main_usb.c | 6 +- drivers/staging/wavelan/wavelan.c | 10 +- drivers/staging/wavelan/wavelan_cs.c | 12 +- drivers/staging/winbond/wbusb.c | 6 +- drivers/staging/wlags49_h2/wl_netdev.c | 12 +- include/linux/netdevice.h | 82 +++---- include/net/mac80211.h | 2 +- net/802/garp.c | 4 +- net/appletalk/ddp.c | 2 +- net/bluetooth/bnep/netdev.c | 8 +- net/core/Makefile | 5 +- net/core/dev.c | 145 +----------- net/core/dev_addr_lists.c | 305 +++++++++++++++++++++++-- net/core/dev_mcast.c | 232 ------------------- net/decnet/dn_dev.c | 12 +- net/ipv4/igmp.c | 4 +- net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 +- net/ipv6/mcast.c | 4 +- net/mac80211/driver-ops.h | 8 +- net/mac80211/ieee80211_i.h | 3 +- net/mac80211/iface.c | 6 +- net/mac80211/main.c | 2 +- net/packet/af_packet.c | 4 +- 208 files changed, 1137 insertions(+), 1327 deletions(-) delete mode 100644 net/core/dev_mcast.c (limited to 'include/net') diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c index 91fdde382e8..ce9ef6bc865 100644 --- a/drivers/infiniband/hw/nes/nes_nic.c +++ b/drivers/infiniband/hw/nes/nes_nic.c @@ -876,7 +876,7 @@ static void nes_netdev_set_multicast_list(struct net_device *netdev) if (!mc_all_on) { char *addrs; int i; - struct dev_mc_list *mcaddr; + struct netdev_hw_addr *ha; addrs = kmalloc(ETH_ALEN * mc_count, GFP_ATOMIC); if (!addrs) { @@ -884,9 +884,8 @@ static void nes_netdev_set_multicast_list(struct net_device *netdev) goto unlock; } i = 0; - netdev_for_each_mc_addr(mcaddr, netdev) - memcpy(get_addr(addrs, i++), - mcaddr->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, netdev) + memcpy(get_addr(addrs, i++), ha->addr, ETH_ALEN); perfect_filter_register_address = NES_IDX_PERFECT_FILTER_LOW + pft_entries_preallocated * 0x8; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 19eba3c877c..c8a0f7dab5b 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -783,7 +783,7 @@ void ipoib_mcast_restart_task(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, restart_task); struct net_device *dev = priv->dev; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct ipoib_mcast *mcast, *tmcast; LIST_HEAD(remove_list); unsigned long flags; @@ -808,14 +808,13 @@ void ipoib_mcast_restart_task(struct work_struct *work) clear_bit(IPOIB_MCAST_FLAG_FOUND, &mcast->flags); /* Mark all of the entries that are found or don't exist */ - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { union ib_gid mgid; - if (!ipoib_mcast_addr_is_valid(mclist->dmi_addr, - dev->broadcast)) + if (!ipoib_mcast_addr_is_valid(ha->addr, dev->broadcast)) continue; - memcpy(mgid.raw, mclist->dmi_addr + 4, sizeof mgid); + memcpy(mgid.raw, ha->addr + 4, sizeof mgid); mcast = __ipoib_mcast_find(dev, &mgid); if (!mcast || test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) { diff --git a/drivers/media/dvb/dvb-core/dvb_net.c b/drivers/media/dvb/dvb-core/dvb_net.c index dba1c84058b..cccea412088 100644 --- a/drivers/media/dvb/dvb-core/dvb_net.c +++ b/drivers/media/dvb/dvb-core/dvb_net.c @@ -1109,14 +1109,14 @@ static int dvb_net_feed_stop(struct net_device *dev) } -static int dvb_set_mc_filter (struct net_device *dev, struct dev_mc_list *mc) +static int dvb_set_mc_filter(struct net_device *dev, unsigned char *addr) { struct dvb_net_priv *priv = netdev_priv(dev); if (priv->multi_num == DVB_NET_MULTICAST_MAX) return -ENOMEM; - memcpy(priv->multi_macs[priv->multi_num], mc->dmi_addr, 6); + memcpy(priv->multi_macs[priv->multi_num], addr, ETH_ALEN); priv->multi_num++; return 0; @@ -1140,7 +1140,7 @@ static void wq_set_multicast_list (struct work_struct *work) dprintk("%s: allmulti mode\n", dev->name); priv->rx_mode = RX_MODE_ALL_MULTI; } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; dprintk("%s: set_mc_list, %d entries\n", dev->name, netdev_mc_count(dev)); @@ -1148,8 +1148,8 @@ static void wq_set_multicast_list (struct work_struct *work) priv->rx_mode = RX_MODE_MULTI; priv->multi_num = 0; - netdev_for_each_mc_addr(mc, dev) - dvb_set_mc_filter(dev, mc); + netdev_for_each_mc_addr(ha, dev) + dvb_set_mc_filter(dev, ha->addr); } netif_addr_unlock_bh(dev); diff --git a/drivers/net/3c505.c b/drivers/net/3c505.c index 04b5bba1902..81c8b31e629 100644 --- a/drivers/net/3c505.c +++ b/drivers/net/3c505.c @@ -1216,7 +1216,7 @@ static int elp_close(struct net_device *dev) static void elp_set_mc_list(struct net_device *dev) { elp_device *adapter = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i; unsigned long flags; @@ -1231,8 +1231,9 @@ static void elp_set_mc_list(struct net_device *dev) adapter->tx_pcb.command = CMD_LOAD_MULTICAST_LIST; adapter->tx_pcb.length = 6 * netdev_mc_count(dev); i = 0; - netdev_for_each_mc_addr(dmi, dev) - memcpy(adapter->tx_pcb.data.multicast[i++], dmi->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) + memcpy(adapter->tx_pcb.data.multicast[i++], + ha->addr, 6); adapter->got[CMD_LOAD_MULTICAST_LIST] = 0; if (!send_pcb(dev, &adapter->tx_pcb)) pr_err("%s: couldn't send set_multicast command\n", dev->name); diff --git a/drivers/net/3c523.c b/drivers/net/3c523.c index beed4fa10c6..966cb12e1e0 100644 --- a/drivers/net/3c523.c +++ b/drivers/net/3c523.c @@ -625,7 +625,7 @@ static int init586(struct net_device *dev) volatile struct iasetup_cmd_struct *ias_cmd; volatile struct tdr_cmd_struct *tdr_cmd; volatile struct mcsetup_cmd_struct *mc_cmd; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int num_addrs = netdev_mc_count(dev); ptr = (void *) ((char *) p->scb + sizeof(struct scb_struct)); @@ -788,8 +788,9 @@ static int init586(struct net_device *dev) mc_cmd->cmd_link = 0xffff; mc_cmd->mc_cnt = num_addrs * 6; i = 0; - netdev_for_each_mc_addr(dmi, dev) - memcpy((char *) mc_cmd->mc_list[i++], dmi->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) + memcpy((char *) mc_cmd->mc_list[i++], + ha->addr, 6); p->scb->cbl_offset = make16(mc_cmd); p->scb->cmd = CUC_START; elmc_id_attn586(); diff --git a/drivers/net/3c527.c b/drivers/net/3c527.c index 5c07b147ec9..38395dfa496 100644 --- a/drivers/net/3c527.c +++ b/drivers/net/3c527.c @@ -1533,7 +1533,7 @@ static void do_mc32_set_multicast_list(struct net_device *dev, int retry) { unsigned char block[62]; unsigned char *bp; - struct dev_mc_list *dmc; + struct netdev_hw_addr *ha; if(retry==0) lp->mc_list_valid = 0; @@ -1543,8 +1543,8 @@ static void do_mc32_set_multicast_list(struct net_device *dev, int retry) block[0]=netdev_mc_count(dev); bp=block+2; - netdev_for_each_mc_addr(dmc, dev) { - memcpy(bp, dmc->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) { + memcpy(bp, ha->addr, 6); bp+=6; } if(mc32_command_nowait(dev, 2, block, diff --git a/drivers/net/7990.c b/drivers/net/7990.c index 4e9a5a20b6a..818837d8ffe 100644 --- a/drivers/net/7990.c +++ b/drivers/net/7990.c @@ -595,7 +595,7 @@ static void lance_load_multicast (struct net_device *dev) struct lance_private *lp = netdev_priv(dev); volatile struct lance_init_block *ib = lp->init_block; volatile u16 *mcast_table = (u16 *)&ib->filter; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; @@ -610,8 +610,8 @@ static void lance_load_multicast (struct net_device *dev) ib->filter [1] = 0; /* Add addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* multicast address? */ if (!(*addrs & 1)) diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c index 3d4406b1665..e4e2aef1101 100644 --- a/drivers/net/8139cp.c +++ b/drivers/net/8139cp.c @@ -909,11 +909,11 @@ static void __cp_set_rx_mode (struct net_device *dev) rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); rx_mode |= AcceptMulticast; diff --git a/drivers/net/8139too.c b/drivers/net/8139too.c index b4efc913978..f61784c3c4a 100644 --- a/drivers/net/8139too.c +++ b/drivers/net/8139too.c @@ -2502,11 +2502,11 @@ static void __set_rx_mode (struct net_device *dev) rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); rx_mode |= AcceptMulticast; diff --git a/drivers/net/82596.c b/drivers/net/82596.c index f94d17d78bb..3a28b1f451d 100644 --- a/drivers/net/82596.c +++ b/drivers/net/82596.c @@ -1542,7 +1542,7 @@ static void set_multicast_list(struct net_device *dev) } if (!netdev_mc_empty(dev)) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char *cp; struct mc_cmd *cmd; @@ -1552,10 +1552,10 @@ static void set_multicast_list(struct net_device *dev) cmd->cmd.command = CmdMulticastList; cmd->mc_cnt = cnt * ETH_ALEN; cp = cmd->mc_addrs; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if (!cnt--) break; - memcpy(cp, dmi->dmi_addr, ETH_ALEN); + memcpy(cp, ha->addr, ETH_ALEN); if (i596_debug > 1) DEB(DEB_MULTI,printk(KERN_INFO "%s: Adding address %pM\n", dev->name, cp)); diff --git a/drivers/net/a2065.c b/drivers/net/a2065.c index bd4d829eca1..7cce643793c 100644 --- a/drivers/net/a2065.c +++ b/drivers/net/a2065.c @@ -603,7 +603,7 @@ static void lance_load_multicast (struct net_device *dev) struct lance_private *lp = netdev_priv(dev); volatile struct lance_init_block *ib = lp->init_block; volatile u16 *mcast_table = (u16 *)&ib->filter; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; @@ -618,8 +618,8 @@ static void lance_load_multicast (struct net_device *dev) ib->filter [1] = 0; /* Add addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* multicast address? */ if (!(*addrs & 1)) diff --git a/drivers/net/amd8111e.c b/drivers/net/amd8111e.c index b8a59d255b4..d002c764a26 100644 --- a/drivers/net/amd8111e.c +++ b/drivers/net/amd8111e.c @@ -1377,7 +1377,7 @@ list to the device. */ static void amd8111e_set_multicast_list(struct net_device *dev) { - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; struct amd8111e_priv *lp = netdev_priv(dev); u32 mc_filter[2] ; int bit_num; @@ -1408,8 +1408,8 @@ static void amd8111e_set_multicast_list(struct net_device *dev) /* load all the multicast addresses in the logic filter */ lp->options |= OPTION_MULTICAST_ENABLE; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mc_ptr, dev) { - bit_num = (ether_crc_le(ETH_ALEN, mc_ptr->dmi_addr) >> 26) & 0x3f; + netdev_for_each_mc_addr(ha, dev) { + bit_num = (ether_crc_le(ETH_ALEN, ha->addr) >> 26) & 0x3f; mc_filter[bit_num >> 5] |= 1 << (bit_num & 31); } amd8111e_writeq(*(u64*)mc_filter,lp->mmio+ LADRF); diff --git a/drivers/net/arm/am79c961a.c b/drivers/net/arm/am79c961a.c index f1f58c5e27b..a4b5b08276f 100644 --- a/drivers/net/arm/am79c961a.c +++ b/drivers/net/arm/am79c961a.c @@ -383,12 +383,12 @@ static void am79c961_setmulticastlist (struct net_device *dev) } else if (dev->flags & IFF_ALLMULTI) { memset(multi_hash, 0xff, sizeof(multi_hash)); } else { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; memset(multi_hash, 0x00, sizeof(multi_hash)); - netdev_for_each_mc_addr(dmi, dev) - am79c961_mc_hash(dmi->dmi_addr, multi_hash); + netdev_for_each_mc_addr(ha, dev) + am79c961_mc_hash(ha->addr, multi_hash); } spin_lock_irqsave(&priv->chip_lock, flags); diff --git a/drivers/net/arm/at91_ether.c b/drivers/net/arm/at91_ether.c index 8b23d5a175b..f31e8b6cbf7 100644 --- a/drivers/net/arm/at91_ether.c +++ b/drivers/net/arm/at91_ether.c @@ -556,14 +556,14 @@ static int hash_get_index(__u8 *addr) */ static void at91ether_sethashtable(struct net_device *dev) { - struct dev_mc_list *curr; + struct netdev_hw_addr *ha; unsigned long mc_filter[2]; unsigned int bitnr; mc_filter[0] = mc_filter[1] = 0; - netdev_for_each_mc_addr(curr, dev) { - bitnr = hash_get_index(curr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + bitnr = hash_get_index(ha->addr); mc_filter[bitnr >> 5] |= 1 << (bitnr & 31); } diff --git a/drivers/net/arm/ixp4xx_eth.c b/drivers/net/arm/ixp4xx_eth.c index 6e2ae1d06df..f9d168775d0 100644 --- a/drivers/net/arm/ixp4xx_eth.c +++ b/drivers/net/arm/ixp4xx_eth.c @@ -735,7 +735,7 @@ static int eth_xmit(struct sk_buff *skb, struct net_device *dev) static void eth_set_mcast_list(struct net_device *dev) { struct port *port = netdev_priv(dev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u8 diffs[ETH_ALEN], *addr; int i; @@ -748,11 +748,11 @@ static void eth_set_mcast_list(struct net_device *dev) memset(diffs, 0, ETH_ALEN); addr = NULL; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { if (!addr) - addr = mclist->dmi_addr; /* first MAC address */ + addr = ha->addr; /* first MAC address */ for (i = 0; i < ETH_ALEN; i++) - diffs[i] |= addr[i] ^ mclist->dmi_addr[i]; + diffs[i] |= addr[i] ^ ha->addr[i]; } for (i = 0; i < ETH_ALEN; i++) { diff --git a/drivers/net/arm/ks8695net.c b/drivers/net/arm/ks8695net.c index e7810b74f39..6ec245c6394 100644 --- a/drivers/net/arm/ks8695net.c +++ b/drivers/net/arm/ks8695net.c @@ -331,16 +331,16 @@ ks8695_init_partial_multicast(struct ks8695_priv *ksp, { u32 low, high; int i; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; i = 0; - netdev_for_each_mc_addr(dmi, ndev) { + netdev_for_each_mc_addr(ha, ndev) { /* Ran out of space in chip? */ BUG_ON(i == KS8695_NR_ADDRESSES); - low = (dmi->dmi_addr[2] << 24) | (dmi->dmi_addr[3] << 16) | - (dmi->dmi_addr[4] << 8) | (dmi->dmi_addr[5]); - high = (dmi->dmi_addr[0] << 8) | (dmi->dmi_addr[1]); + low = (ha->addr[2] << 24) | (ha->addr[3] << 16) | + (ha->addr[4] << 8) | (ha->addr[5]); + high = (ha->addr[0] << 8) | (ha->addr[1]); ks8695_writereg(ksp, KS8695_AAL_(i), low); ks8695_writereg(ksp, KS8695_AAH_(i), AAH_E | high); diff --git a/drivers/net/at1700.c b/drivers/net/at1700.c index 309843ab886..e2a549a60e2 100644 --- a/drivers/net/at1700.c +++ b/drivers/net/at1700.c @@ -848,12 +848,12 @@ set_rx_mode(struct net_device *dev) memset(mc_filter, 0x00, sizeof(mc_filter)); outb(1, ioaddr + RX_MODE); /* Ignore almost all multicasts. */ } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { unsigned int bit = - ether_crc_le(ETH_ALEN, mclist->dmi_addr) >> 26; + ether_crc_le(ETH_ALEN, ha->addr) >> 26; mc_filter[bit >> 3] |= (1 << bit); } outb(0x02, ioaddr + RX_MODE); /* Use normal mode. */ diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c index a5508e1b261..3d7051135c3 100644 --- a/drivers/net/atl1c/atl1c_main.c +++ b/drivers/net/atl1c/atl1c_main.c @@ -354,7 +354,7 @@ static void atl1c_set_multi(struct net_device *netdev) { struct atl1c_adapter *adapter = netdev_priv(netdev); struct atl1c_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u32 mac_ctrl_data; u32 hash_value; @@ -377,8 +377,8 @@ static void atl1c_set_multi(struct net_device *netdev) AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, 1, 0); /* comoute mc addresses' hash value ,and put it into hash table */ - netdev_for_each_mc_addr(mc_ptr, netdev) { - hash_value = atl1c_hash_mc_addr(hw, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + hash_value = atl1c_hash_mc_addr(hw, ha->addr); atl1c_hash_set(hw, hash_value); } } diff --git a/drivers/net/atl1e/atl1e_main.c b/drivers/net/atl1e/atl1e_main.c index 7231b577912..b6605d433e9 100644 --- a/drivers/net/atl1e/atl1e_main.c +++ b/drivers/net/atl1e/atl1e_main.c @@ -284,7 +284,7 @@ static void atl1e_set_multi(struct net_device *netdev) { struct atl1e_adapter *adapter = netdev_priv(netdev); struct atl1e_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u32 mac_ctrl_data = 0; u32 hash_value; @@ -307,8 +307,8 @@ static void atl1e_set_multi(struct net_device *netdev) AT_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, 1, 0); /* comoute mc addresses' hash value ,and put it into hash table */ - netdev_for_each_mc_addr(mc_ptr, netdev) { - hash_value = atl1e_hash_mc_addr(hw, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + hash_value = atl1e_hash_mc_addr(hw, ha->addr); atl1e_hash_set(hw, hash_value); } } diff --git a/drivers/net/atlx/atl2.c b/drivers/net/atlx/atl2.c index 199f2c9ce74..078d9d1b427 100644 --- a/drivers/net/atlx/atl2.c +++ b/drivers/net/atlx/atl2.c @@ -135,7 +135,7 @@ static void atl2_set_multi(struct net_device *netdev) { struct atl2_adapter *adapter = netdev_priv(netdev); struct atl2_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u32 rctl; u32 hash_value; @@ -157,8 +157,8 @@ static void atl2_set_multi(struct net_device *netdev) ATL2_WRITE_REG_ARRAY(hw, REG_RX_HASH_TABLE, 1, 0); /* comoute mc addresses' hash value ,and put it into hash table */ - netdev_for_each_mc_addr(mc_ptr, netdev) { - hash_value = atl2_hash_mc_addr(hw, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + hash_value = atl2_hash_mc_addr(hw, ha->addr); atl2_hash_set(hw, hash_value); } } diff --git a/drivers/net/atlx/atlx.c b/drivers/net/atlx/atlx.c index 72f3306352e..f979ea2d6d3 100644 --- a/drivers/net/atlx/atlx.c +++ b/drivers/net/atlx/atlx.c @@ -123,7 +123,7 @@ static void atlx_set_multi(struct net_device *netdev) { struct atlx_adapter *adapter = netdev_priv(netdev); struct atlx_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u32 rctl; u32 hash_value; @@ -144,8 +144,8 @@ static void atlx_set_multi(struct net_device *netdev) iowrite32(0, (hw->hw_addr + REG_RX_HASH_TABLE) + (1 << 2)); /* compute mc addresses' hash value ,and put it into hash table */ - netdev_for_each_mc_addr(mc_ptr, netdev) { - hash_value = atlx_hash_mc_addr(hw, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + hash_value = atlx_hash_mc_addr(hw, ha->addr); atlx_hash_set(hw, hash_value); } } diff --git a/drivers/net/atp.c b/drivers/net/atp.c index 6ad16205dc1..0d730c8329d 100644 --- a/drivers/net/atp.c +++ b/drivers/net/atp.c @@ -883,11 +883,11 @@ static void set_rx_mode_8012(struct net_device *dev) memset(mc_filter, 0xff, sizeof(mc_filter)); new_mode = CMR2h_Normal; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int filterbit = ether_crc_le(ETH_ALEN, mclist->dmi_addr) & 0x3f; + netdev_for_each_mc_addr(ha, dev) { + int filterbit = ether_crc_le(ETH_ALEN, ha->addr) & 0x3f; mc_filter[filterbit >> 5] |= 1 << (filterbit & 31); } new_mode = CMR2h_Normal; diff --git a/drivers/net/au1000_eth.c b/drivers/net/au1000_eth.c index 4da191b87b0..29631593cc2 100644 --- a/drivers/net/au1000_eth.c +++ b/drivers/net/au1000_eth.c @@ -957,12 +957,12 @@ static void au1000_multicast_list(struct net_device *dev) aup->mac->control &= ~MAC_PROMISCUOUS; printk(KERN_INFO "%s: Pass all multicast\n", dev->name); } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u32 mc_filter[2]; /* Multicast hash filter */ mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) - set_bit(ether_crc(ETH_ALEN, mclist->dmi_addr)>>26, + netdev_for_each_mc_addr(ha, dev) + set_bit(ether_crc(ETH_ALEN, ha->addr)>>26, (long *)mc_filter); aup->mac->multi_hash_high = mc_filter[1]; aup->mac->multi_hash_low = mc_filter[0]; diff --git a/drivers/net/b44.c b/drivers/net/b44.c index 332c6035628..b2c5fd7b63a 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -1680,15 +1680,15 @@ static struct net_device_stats *b44_get_stats(struct net_device *dev) static int __b44_load_mcast(struct b44 *bp, struct net_device *dev) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i, num_ents; num_ents = min_t(int, netdev_mc_count(dev), B44_MCAST_TABLE_SIZE); i = 0; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { if (i == num_ents) break; - __b44_cam_write(bp, mclist->dmi_addr, i++ + 1); + __b44_cam_write(bp, ha->addr, i++ + 1); } return i+1; } diff --git a/drivers/net/bcm63xx_enet.c b/drivers/net/bcm63xx_enet.c index 37eb8021de1..51733404478 100644 --- a/drivers/net/bcm63xx_enet.c +++ b/drivers/net/bcm63xx_enet.c @@ -603,7 +603,7 @@ static int bcm_enet_set_mac_address(struct net_device *dev, void *p) static void bcm_enet_set_multicast_list(struct net_device *dev) { struct bcm_enet_priv *priv; - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; u32 val; int i; @@ -631,14 +631,14 @@ static void bcm_enet_set_multicast_list(struct net_device *dev) } i = 0; - netdev_for_each_mc_addr(mc_list, dev) { + netdev_for_each_mc_addr(ha, dev) { u8 *dmi_addr; u32 tmp; if (i == 3) break; /* update perfect match registers */ - dmi_addr = mc_list->dmi_addr; + dmi_addr = ha->addr; tmp = (dmi_addr[2] << 24) | (dmi_addr[3] << 16) | (dmi_addr[4] << 8) | dmi_addr[5]; enet_writel(priv, tmp, ENET_PML_REG(i + 1)); diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 9f53d9e86e2..61a9afdb83f 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -1159,13 +1159,13 @@ int be_cmd_multicast_set(struct be_adapter *adapter, u32 if_id, req->interface_id = if_id; if (netdev) { int i; - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; req->num_mac = cpu_to_le16(netdev_mc_count(netdev)); i = 0; - netdev_for_each_mc_addr(mc, netdev) - memcpy(req->mac[i].byte, mc->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, netdev) + memcpy(req->mac[i].byte, ha->addr, ETH_ALEN); } else { req->promiscuous = 1; } diff --git a/drivers/net/bfin_mac.c b/drivers/net/bfin_mac.c index 587f93cf03f..c488cea8f45 100644 --- a/drivers/net/bfin_mac.c +++ b/drivers/net/bfin_mac.c @@ -812,14 +812,14 @@ static void bfin_mac_timeout(struct net_device *dev) static void bfin_mac_multicast_hash(struct net_device *dev) { u32 emac_hashhi, emac_hashlo; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; emac_hashhi = emac_hashlo = 0; - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* skip non-multicast addresses */ if (!(*addrs & 1)) diff --git a/drivers/net/bmac.c b/drivers/net/bmac.c index 119468e7632..1245e983576 100644 --- a/drivers/net/bmac.c +++ b/drivers/net/bmac.c @@ -971,7 +971,7 @@ bmac_remove_multi(struct net_device *dev, */ static void bmac_set_multicast(struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; struct bmac_data *bp = netdev_priv(dev); int num_addrs = netdev_mc_count(dev); unsigned short rx_cfg; @@ -1000,8 +1000,8 @@ static void bmac_set_multicast(struct net_device *dev) rx_cfg = bmac_rx_on(dev, 0, 0); XXDEBUG(("bmac: multi disabled, rx_cfg=%#08x\n", rx_cfg)); } else { - netdev_for_each_mc_addr(dmi, dev) - bmac_addhash(bp, dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + bmac_addhash(bp, ha->addr); bmac_update_hash_table_mask(dev, bp); rx_cfg = bmac_rx_on(dev, 1, 0); XXDEBUG(("bmac: multi enabled, rx_cfg=%#08x\n", rx_cfg)); @@ -1015,7 +1015,7 @@ static void bmac_set_multicast(struct net_device *dev) static void bmac_set_multicast(struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; int i; unsigned short rx_cfg; @@ -1039,8 +1039,8 @@ static void bmac_set_multicast(struct net_device *dev) for(i = 0; i < 4; i++) hash_table[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if(!(*addrs & 1)) continue; diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 381887ba677..0b69ffb7951 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -3544,7 +3544,6 @@ bnx2_set_rx_mode(struct net_device *dev) } else { /* Accept one or more multicast(s). */ - struct dev_mc_list *mclist; u32 mc_filter[NUM_MC_HASH_REGISTERS]; u32 regidx; u32 bit; @@ -3552,8 +3551,8 @@ bnx2_set_rx_mode(struct net_device *dev) memset(mc_filter, 0, 4 * NUM_MC_HASH_REGISTERS); - netdev_for_each_mc_addr(mclist, dev) { - crc = ether_crc_le(ETH_ALEN, mclist->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(ETH_ALEN, ha->addr); bit = crc & 0xff; regidx = (bit & 0xe0) >> 5; bit &= 0x1f; diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c index f4ea99d06c7..fa9275c2ef5 100644 --- a/drivers/net/bnx2x_main.c +++ b/drivers/net/bnx2x_main.c @@ -11496,21 +11496,21 @@ static void bnx2x_set_rx_mode(struct net_device *dev) else { /* some multicasts */ if (CHIP_IS_E1(bp)) { int i, old, offset; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct mac_configuration_cmd *config = bnx2x_sp(bp, mcast_config); i = 0; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { config->config_table[i]. cam_entry.msb_mac_addr = - swab16(*(u16 *)&mclist->dmi_addr[0]); + swab16(*(u16 *)&ha->addr[0]); config->config_table[i]. cam_entry.middle_mac_addr = - swab16(*(u16 *)&mclist->dmi_addr[2]); + swab16(*(u16 *)&ha->addr[2]); config->config_table[i]. cam_entry.lsb_mac_addr = - swab16(*(u16 *)&mclist->dmi_addr[4]); + swab16(*(u16 *)&ha->addr[4]); config->config_table[i].cam_entry.flags = cpu_to_le16(port); config->config_table[i]. @@ -11564,18 +11564,18 @@ static void bnx2x_set_rx_mode(struct net_device *dev) 0); } else { /* E1H */ /* Accept one or more multicasts */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u32 mc_filter[MC_HASH_SIZE]; u32 crc, bit, regidx; int i; memset(mc_filter, 0, 4 * MC_HASH_SIZE); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { DP(NETIF_MSG_IFUP, "Adding mcast MAC: %pM\n", - mclist->dmi_addr); + ha->addr); - crc = crc32c_le(0, mclist->dmi_addr, ETH_ALEN); + crc = crc32c_le(0, ha->addr, ETH_ALEN); bit = (crc >> 24) & 0xff; regidx = bit >> 5; bit &= 0x1f; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d6ae63b2cf0..22682f1c847 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -761,32 +761,6 @@ static int bond_check_dev_link(struct bonding *bond, /*----------------------------- Multicast list ------------------------------*/ -/* - * Returns 0 if dmi1 and dmi2 are the same, non-0 otherwise - */ -static inline int bond_is_dmi_same(const struct dev_mc_list *dmi1, - const struct dev_mc_list *dmi2) -{ - return memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0 && - dmi1->dmi_addrlen == dmi2->dmi_addrlen; -} - -/* - * returns dmi entry if found, NULL otherwise - */ -static struct dev_mc_list *bond_mc_list_find_dmi(struct dev_mc_list *dmi, - struct dev_mc_list *mc_list) -{ - struct dev_mc_list *idmi; - - for (idmi = mc_list; idmi; idmi = idmi->next) { - if (bond_is_dmi_same(dmi, idmi)) - return idmi; - } - - return NULL; -} - /* * Push the promiscuity flag down to appropriate slaves */ @@ -839,18 +813,18 @@ static int bond_set_allmulti(struct bonding *bond, int inc) * Add a Multicast address to slaves * according to mode */ -static void bond_mc_add(struct bonding *bond, void *addr, int alen) +static void bond_mc_add(struct bonding *bond, void *addr) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) - dev_mc_add(bond->curr_active_slave->dev, addr, alen, 0); + dev_mc_add(bond->curr_active_slave->dev, addr); } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) - dev_mc_add(slave->dev, addr, alen, 0); + dev_mc_add(slave->dev, addr); } } @@ -858,18 +832,17 @@ static void bond_mc_add(struct bonding *bond, void *addr, int alen) * Remove a multicast address from slave * according to mode */ -static void bond_mc_delete(struct bonding *bond, void *addr, int alen) +static void bond_mc_del(struct bonding *bond, void *addr) { if (USES_PRIMARY(bond->params.mode)) { /* write lock already acquired */ if (bond->curr_active_slave) - dev_mc_delete(bond->curr_active_slave->dev, addr, - alen, 0); + dev_mc_del(bond->curr_active_slave->dev, addr); } else { struct slave *slave; int i; bond_for_each_slave(bond, slave, i) { - dev_mc_delete(slave->dev, addr, alen, 0); + dev_mc_del(slave->dev, addr); } } } @@ -895,50 +868,6 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) rcu_read_unlock(); } -/* - * Totally destroys the mc_list in bond - */ -static void bond_mc_list_destroy(struct bonding *bond) -{ - struct dev_mc_list *dmi; - - dmi = bond->mc_list; - while (dmi) { - bond->mc_list = dmi->next; - kfree(dmi); - dmi = bond->mc_list; - } - - bond->mc_list = NULL; -} - -/* - * Copy all the Multicast addresses from src to the bonding device dst - */ -static int bond_mc_list_copy(struct dev_mc_list *mc_list, struct bonding *bond, - gfp_t gfp_flag) -{ - struct dev_mc_list *dmi, *new_dmi; - - for (dmi = mc_list; dmi; dmi = dmi->next) { - new_dmi = kmalloc(sizeof(struct dev_mc_list), gfp_flag); - - if (!new_dmi) { - /* FIXME: Potential memory leak !!! */ - return -ENOMEM; - } - - new_dmi->next = bond->mc_list; - bond->mc_list = new_dmi; - new_dmi->dmi_addrlen = dmi->dmi_addrlen; - memcpy(new_dmi->dmi_addr, dmi->dmi_addr, dmi->dmi_addrlen); - new_dmi->dmi_users = dmi->dmi_users; - new_dmi->dmi_gusers = dmi->dmi_gusers; - } - - return 0; -} - /* * flush all members of flush->mc_list from device dev->mc_list */ @@ -946,16 +875,16 @@ static void bond_mc_list_flush(struct net_device *bond_dev, struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) - dev_mc_delete(slave_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); + netdev_for_each_mc_addr(ha, bond_dev) + dev_mc_del(slave_dev, ha->addr); if (bond->params.mode == BOND_MODE_8023AD) { /* del lacpdu mc addr from mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; - dev_mc_delete(slave_dev, lacpdu_multicast, ETH_ALEN, 0); + dev_mc_del(slave_dev, lacpdu_multicast); } } @@ -969,7 +898,7 @@ static void bond_mc_list_flush(struct net_device *bond_dev, static void bond_mc_swap(struct bonding *bond, struct slave *new_active, struct slave *old_active) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; if (!USES_PRIMARY(bond->params.mode)) /* nothing to do - mc list is already up-to-date on @@ -984,9 +913,8 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(old_active->dev, -1); - for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) - dev_mc_delete(old_active->dev, dmi->dmi_addr, - dmi->dmi_addrlen, 0); + netdev_for_each_mc_addr(ha, bond->dev) + dev_mc_del(old_active->dev, ha->addr); } if (new_active) { @@ -997,9 +925,8 @@ static void bond_mc_swap(struct bonding *bond, struct slave *new_active, if (bond->dev->flags & IFF_ALLMULTI) dev_set_allmulti(new_active->dev, 1); - for (dmi = bond->dev->mc_list; dmi; dmi = dmi->next) - dev_mc_add(new_active->dev, dmi->dmi_addr, - dmi->dmi_addrlen, 0); + netdev_for_each_mc_addr(ha, bond->dev) + dev_mc_add(new_active->dev, ha->addr); bond_resend_igmp_join_requests(bond); } } @@ -1406,7 +1333,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) struct bonding *bond = netdev_priv(bond_dev); const struct net_device_ops *slave_ops = slave_dev->netdev_ops; struct slave *new_slave = NULL; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; struct sockaddr addr; int link_reporting; int old_features = bond_dev->features; @@ -1492,7 +1419,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* Flush unicast and multicast addresses */ dev_uc_flush(bond_dev); - dev_addr_discard(bond_dev); + dev_mc_flush(bond_dev); if (slave_dev->type != ARPHRD_ETHER) bond_setup_by_slave(bond_dev, slave_dev); @@ -1601,9 +1528,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) netif_addr_lock_bh(bond_dev); /* upload master's mc_list to new slave */ - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) - dev_mc_add(slave_dev, dmi->dmi_addr, - dmi->dmi_addrlen, 0); + netdev_for_each_mc_addr(ha, bond_dev) + dev_mc_add(slave_dev, ha->addr); netif_addr_unlock_bh(bond_dev); } @@ -1611,7 +1537,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* add lacpdu mc addr to mc list */ u8 lacpdu_multicast[ETH_ALEN] = MULTICAST_LACPDU_ADDR; - dev_mc_add(slave_dev, lacpdu_multicast, ETH_ALEN, 0); + dev_mc_add(slave_dev, lacpdu_multicast); } bond_add_vlans_on_slave(bond, slave_dev); @@ -3913,10 +3839,24 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd return res; } +static bool bond_addr_in_mc_list(unsigned char *addr, + struct netdev_hw_addr_list *list, + int addrlen) +{ + struct netdev_hw_addr *ha; + + netdev_hw_addr_list_for_each(ha, list) + if (!memcmp(ha->addr, addr, addrlen)) + return true; + + return false; +} + static void bond_set_multicast_list(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; + bool found; /* * Do promisc before checking multicast_mode @@ -3951,20 +3891,25 @@ static void bond_set_multicast_list(struct net_device *bond_dev) bond->flags = bond_dev->flags; /* looking for addresses to add to slaves' mc list */ - for (dmi = bond_dev->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond->mc_list)) - bond_mc_add(bond, dmi->dmi_addr, dmi->dmi_addrlen); + netdev_for_each_mc_addr(ha, bond_dev) { + found = bond_addr_in_mc_list(ha->addr, &bond->mc_list, + bond_dev->addr_len); + if (!found) + bond_mc_add(bond, ha->addr); } /* looking for addresses to delete from slaves' list */ - for (dmi = bond->mc_list; dmi; dmi = dmi->next) { - if (!bond_mc_list_find_dmi(dmi, bond_dev->mc_list)) - bond_mc_delete(bond, dmi->dmi_addr, dmi->dmi_addrlen); + netdev_hw_addr_list_for_each(ha, &bond->mc_list) { + found = bond_addr_in_mc_list(ha->addr, &bond_dev->mc, + bond_dev->addr_len); + if (!found) + bond_mc_del(bond, ha->addr); } /* save master's multicast list */ - bond_mc_list_destroy(bond); - bond_mc_list_copy(bond_dev->mc_list, bond, GFP_ATOMIC); + __hw_addr_flush(&bond->mc_list); + __hw_addr_add_multiple(&bond->mc_list, &bond_dev->mc, + bond_dev->addr_len, NETDEV_HW_ADDR_T_MULTICAST); read_unlock(&bond->lock); } @@ -4534,9 +4479,7 @@ static void bond_uninit(struct net_device *bond_dev) if (bond->wq) destroy_workqueue(bond->wq); - netif_addr_lock_bh(bond_dev); - bond_mc_list_destroy(bond); - netif_addr_unlock_bh(bond_dev); + __hw_addr_flush(&bond->mc_list); } /*------------------------- Module initialization ---------------------------*/ @@ -4908,6 +4851,8 @@ static int bond_init(struct net_device *bond_dev) list_add_tail(&bond->bond_list, &bn->dev_list); bond_prepare_sysfs_group(bond); + + __hw_addr_init(&bond->mc_list); return 0; } diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 257a7a4dfce..2aa33672059 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -202,7 +202,7 @@ struct bonding { char proc_file_name[IFNAMSIZ]; #endif /* CONFIG_PROC_FS */ struct list_head bond_list; - struct dev_mc_list *mc_list; + struct netdev_hw_addr_list mc_list; int (*xmit_hash_policy)(struct sk_buff *, int); __be32 master_ip; u16 flags; diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c index 9bd155e4111..bd857a20a75 100644 --- a/drivers/net/cassini.c +++ b/drivers/net/cassini.c @@ -2957,20 +2957,20 @@ static void cas_process_mc_list(struct cas *cp) { u16 hash_table[16]; u32 crc; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i = 1; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(dmi, cp->dev) { + netdev_for_each_mc_addr(ha, cp->dev) { if (i <= CAS_MC_EXACT_MATCH_SIZE) { /* use the alternate mac address registers for the * first 15 multicast addresses */ - writel((dmi->dmi_addr[4] << 8) | dmi->dmi_addr[5], + writel((ha->addr[4] << 8) | ha->addr[5], cp->regs + REG_MAC_ADDRN(i*3 + 0)); - writel((dmi->dmi_addr[2] << 8) | dmi->dmi_addr[3], + writel((ha->addr[2] << 8) | ha->addr[3], cp->regs + REG_MAC_ADDRN(i*3 + 1)); - writel((dmi->dmi_addr[0] << 8) | dmi->dmi_addr[1], + writel((ha->addr[0] << 8) | ha->addr[1], cp->regs + REG_MAC_ADDRN(i*3 + 2)); i++; } @@ -2978,7 +2978,7 @@ static void cas_process_mc_list(struct cas *cp) /* use hw hash table for the next series of * multicast addresses */ - crc = ether_crc_le(ETH_ALEN, dmi->dmi_addr); + crc = ether_crc_le(ETH_ALEN, ha->addr); crc >>= 24; hash_table[crc >> 4] |= 1 << (15 - (crc & 0xf)); } diff --git a/drivers/net/chelsio/pm3393.c b/drivers/net/chelsio/pm3393.c index a6eb30a6e2b..13fd9628db1 100644 --- a/drivers/net/chelsio/pm3393.c +++ b/drivers/net/chelsio/pm3393.c @@ -376,12 +376,13 @@ static int pm3393_set_rx_mode(struct cmac *cmac, struct t1_rx_mode *rm) rx_mode |= SUNI1x10GEXP_BITMSK_RXXG_MHASH_EN; } else if (t1_rx_mode_mc_cnt(rm)) { /* Accept one or more multicast(s). */ - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int bit; u16 mc_filter[4] = { 0, }; - netdev_for_each_mc_addr(dmi, t1_get_netdev(rm)) { - bit = (ether_crc(ETH_ALEN, dmi->dmi_addr) >> 23) & 0x3f; /* bit[23:28] */ + netdev_for_each_mc_addr(ha, t1_get_netdev(rm)) { + /* bit[23:28] */ + bit = (ether_crc(ETH_ALEN, ha->addr) >> 23) & 0x3f; mc_filter[bit >> 4] |= 1 << (bit & 0xf); } pmwrite(cmac, SUNI1x10GEXP_REG_RXXG_MULTICAST_HASH_LOW, mc_filter[0]); diff --git a/drivers/net/cpmac.c b/drivers/net/cpmac.c index 60777fd90b3..bdfff784645 100644 --- a/drivers/net/cpmac.c +++ b/drivers/net/cpmac.c @@ -328,7 +328,7 @@ static int cpmac_config(struct net_device *dev, struct ifmap *map) static void cpmac_set_multicast_list(struct net_device *dev) { - struct dev_mc_list *iter; + struct netdev_hw_addr *ha; u8 tmp; u32 mbp, bit, hash[2] = { 0, }; struct cpmac_priv *priv = netdev_priv(dev); @@ -348,19 +348,19 @@ static void cpmac_set_multicast_list(struct net_device *dev) * cpmac uses some strange mac address hashing * (not crc32) */ - netdev_for_each_mc_addr(iter, dev) { + netdev_for_each_mc_addr(ha, dev) { bit = 0; - tmp = iter->dmi_addr[0]; + tmp = ha->addr[0]; bit ^= (tmp >> 2) ^ (tmp << 4); - tmp = iter->dmi_addr[1]; + tmp = ha->addr[1]; bit ^= (tmp >> 4) ^ (tmp << 2); - tmp = iter->dmi_addr[2]; + tmp = ha->addr[2]; bit ^= (tmp >> 6) ^ tmp; - tmp = iter->dmi_addr[3]; + tmp = ha->addr[3]; bit ^= (tmp >> 2) ^ (tmp << 4); - tmp = iter->dmi_addr[4]; + tmp = ha->addr[4]; bit ^= (tmp >> 4) ^ (tmp << 2); - tmp = iter->dmi_addr[5]; + tmp = ha->addr[5]; bit ^= (tmp >> 6) ^ tmp; bit &= 0x3f; hash[bit / 32] |= 1 << (bit % 32); diff --git a/drivers/net/cris/eth_v10.c b/drivers/net/cris/eth_v10.c index dd24aadb778..59110bc119a 100644 --- a/drivers/net/cris/eth_v10.c +++ b/drivers/net/cris/eth_v10.c @@ -1596,16 +1596,16 @@ set_multicast_list(struct net_device *dev) } else { /* MC mode, receive normal and MC packets */ char hash_ix; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *baddr; lo_bits = 0x00000000ul; hi_bits = 0x00000000ul; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { /* Calculate the hash index for the GA registers */ hash_ix = 0; - baddr = dmi->dmi_addr; + baddr = ha->addr; hash_ix ^= (*baddr) & 0x3f; hash_ix ^= ((*baddr) >> 6) & 0x03; ++baddr; diff --git a/drivers/net/cxgb3/xgmac.c b/drivers/net/cxgb3/xgmac.c index c142a2132e9..3af19a55037 100644 --- a/drivers/net/cxgb3/xgmac.c +++ b/drivers/net/cxgb3/xgmac.c @@ -311,16 +311,16 @@ int t3_mac_set_rx_mode(struct cmac *mac, struct net_device *dev) if (dev->flags & IFF_ALLMULTI) hash_lo = hash_hi = 0xffffffff; else { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int exact_addr_idx = mac->nucast; hash_lo = hash_hi = 0; - netdev_for_each_mc_addr(dmi, dev) + netdev_for_each_mc_addr(ha, dev) if (exact_addr_idx < EXACT_ADDR_FILTERS) set_addr_filter(mac, exact_addr_idx++, - dmi->dmi_addr); + ha->addr); else { - int hash = hash_hw_addr(dmi->dmi_addr); + int hash = hash_hw_addr(ha->addr); if (hash < 32) hash_lo |= (1 << hash); diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c index 2b8edd2efbf..1f9df5c6a75 100644 --- a/drivers/net/davinci_emac.c +++ b/drivers/net/davinci_emac.c @@ -952,13 +952,14 @@ static void emac_dev_mcast_set(struct net_device *ndev) emac_add_mcast(priv, EMAC_ALL_MULTI_SET, NULL); } if (!netdev_mc_empty(ndev)) { - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; + mbp_enable = (mbp_enable | EMAC_MBP_RXMCAST); emac_add_mcast(priv, EMAC_ALL_MULTI_CLR, NULL); /* program multicast address list into EMAC hardware */ - netdev_for_each_mc_addr(mc_ptr, ndev) { + netdev_for_each_mc_addr(ha, ndev) { emac_add_mcast(priv, EMAC_MULTICAST_ADD, - (u8 *) mc_ptr->dmi_addr); + (u8 *) ha->addr); } } else { mbp_enable = (mbp_enable & ~EMAC_MBP_RXMCAST); diff --git a/drivers/net/declance.c b/drivers/net/declance.c index 8cf3cc6f20e..fb3f0984c28 100644 --- a/drivers/net/declance.c +++ b/drivers/net/declance.c @@ -940,7 +940,7 @@ static void lance_load_multicast(struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); volatile u16 *ib = (volatile u16 *)dev->mem_start; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; @@ -959,8 +959,8 @@ static void lance_load_multicast(struct net_device *dev) *lib_ptr(ib, filter[3], lp->type) = 0; /* Add addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* multicast address? */ if (!(*addrs & 1)) diff --git a/drivers/net/defxx.c b/drivers/net/defxx.c index ed53a8d45f4..e5667c55844 100644 --- a/drivers/net/defxx.c +++ b/drivers/net/defxx.c @@ -2195,7 +2195,7 @@ static void dfx_ctl_set_multicast_list(struct net_device *dev) { DFX_board_t *bp = netdev_priv(dev); int i; /* used as index in for loop */ - struct dev_mc_list *dmi; /* ptr to multicast addr entry */ + struct netdev_hw_addr *ha; /* Enable LLC frame promiscuous mode, if necessary */ @@ -2241,9 +2241,9 @@ static void dfx_ctl_set_multicast_list(struct net_device *dev) /* Copy addresses to multicast address table, then update adapter CAM */ i = 0; - netdev_for_each_mc_addr(dmi, dev) + netdev_for_each_mc_addr(ha, dev) memcpy(&bp->mc_table[i++ * FDDI_K_ALEN], - dmi->dmi_addr, FDDI_K_ALEN); + ha->addr, FDDI_K_ALEN); if (dfx_ctl_update_cam(bp) != DFX_K_SUCCESS) { diff --git a/drivers/net/depca.c b/drivers/net/depca.c index 744c1928dfc..a88300a0d1e 100644 --- a/drivers/net/depca.c +++ b/drivers/net/depca.c @@ -1272,7 +1272,7 @@ static void set_multicast_list(struct net_device *dev) static void SetMulticastFilter(struct net_device *dev) { struct depca_private *lp = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; int i, j, bit, byte; u16 hashcode; @@ -1287,8 +1287,8 @@ static void SetMulticastFilter(struct net_device *dev) lp->init_block.mcast_table[i] = 0; } /* Add multicast addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if ((*addrs & 0x01) == 1) { /* multicast address? */ crc = ether_crc(ETH_ALEN, addrs); hashcode = (crc & 1); /* hashcode is 6 LSb of CRC ... */ diff --git a/drivers/net/dl2k.c b/drivers/net/dl2k.c index b05bad82982..6579225dbd9 100644 --- a/drivers/net/dl2k.c +++ b/drivers/net/dl2k.c @@ -1132,14 +1132,14 @@ set_multicast (struct net_device *dev) /* Receive broadcast and multicast frames */ rx_mode = ReceiveBroadcast | ReceiveMulticast | ReceiveUnicast; } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; /* Receive broadcast frames and multicast frames filtering by Hashtable */ rx_mode = ReceiveBroadcast | ReceiveMulticastHash | ReceiveUnicast; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { int bit, index = 0; - int crc = ether_crc_le (ETH_ALEN, mclist->dmi_addr); + int crc = ether_crc_le(ETH_ALEN, ha->addr); /* The inverted high significant 6 bits of CRC are used as an index to hashtable */ for (bit = 0; bit < 6; bit++) diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c index 1c67f1138ca..989f2beb123 100644 --- a/drivers/net/dm9000.c +++ b/drivers/net/dm9000.c @@ -724,7 +724,7 @@ static void dm9000_hash_table(struct net_device *dev) { board_info_t *db = netdev_priv(dev); - struct dev_mc_list *mcptr; + struct netdev_hw_addr *ha; int i, oft; u32 hash_val; u16 hash_table[4]; @@ -752,8 +752,8 @@ dm9000_hash_table(struct net_device *dev) rcr |= RCR_ALL; /* the multicast address in Hash Table : 64 bits */ - netdev_for_each_mc_addr(mcptr, dev) { - hash_val = ether_crc_le(6, mcptr->dmi_addr) & 0x3f; + netdev_for_each_mc_addr(ha, dev) { + hash_val = ether_crc_le(6, ha->addr) & 0x3f; hash_table[hash_val / 16] |= (u16) 1 << (hash_val % 16); } diff --git a/drivers/net/e100.c b/drivers/net/e100.c index c0cd5765668..3e8d0005540 100644 --- a/drivers/net/e100.c +++ b/drivers/net/e100.c @@ -1545,16 +1545,16 @@ static int e100_hw_init(struct nic *nic) static void e100_multi(struct nic *nic, struct cb *cb, struct sk_buff *skb) { struct net_device *netdev = nic->netdev; - struct dev_mc_list *list; + struct netdev_hw_addr *ha; u16 i, count = min(netdev_mc_count(netdev), E100_MAX_MULTICAST_ADDRS); cb->command = cpu_to_le16(cb_multi); cb->u.multi.count = cpu_to_le16(count * ETH_ALEN); i = 0; - netdev_for_each_mc_addr(list, netdev) { + netdev_for_each_mc_addr(ha, netdev) { if (i == count) break; - memcpy(&cb->u.multi.addr[i++ * ETH_ALEN], &list->dmi_addr, + memcpy(&cb->u.multi.addr[i++ * ETH_ALEN], &ha->addr, ETH_ALEN); } } diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index 8be6faee43e..41330349b07 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2101,7 +2101,6 @@ static void e1000_set_rx_mode(struct net_device *netdev) struct e1000_hw *hw = &adapter->hw; struct netdev_hw_addr *ha; bool use_uc = false; - struct dev_addr_list *mc_ptr; u32 rctl; u32 hash_value; int i, rar_entries = E1000_RAR_ENTRIES; @@ -2161,17 +2160,17 @@ static void e1000_set_rx_mode(struct net_device *netdev) WARN_ON(i == rar_entries); - netdev_for_each_mc_addr(mc_ptr, netdev) { + netdev_for_each_mc_addr(ha, netdev) { if (i == rar_entries) { /* load any remaining addresses into the hash table */ u32 hash_reg, hash_bit, mta; - hash_value = e1000_hash_mc_addr(hw, mc_ptr->da_addr); + hash_value = e1000_hash_mc_addr(hw, ha->addr); hash_reg = (hash_value >> 5) & 0x7F; hash_bit = hash_value & 0x1F; mta = (1 << hash_bit); mcarray[hash_reg] |= mta; } else { - e1000_rar_set(hw, mc_ptr->da_addr, i++); + e1000_rar_set(hw, ha->addr, i++); } } diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 5304959ae1f..02f7d20f3c8 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -2567,7 +2567,7 @@ static void e1000_set_multi(struct net_device *netdev) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 *mta_list; u32 rctl; int i; @@ -2599,9 +2599,8 @@ static void e1000_set_multi(struct net_device *netdev) /* prepare a packed array of only addresses. */ i = 0; - netdev_for_each_mc_addr(mc_ptr, netdev) - memcpy(mta_list + (i++ * ETH_ALEN), - mc_ptr->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, netdev) + memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); e1000_update_mc_addr_list(hw, mta_list, i); kfree(mta_list); diff --git a/drivers/net/eepro.c b/drivers/net/eepro.c index 15d6266b80c..b01e6997403 100644 --- a/drivers/net/eepro.c +++ b/drivers/net/eepro.c @@ -1287,7 +1287,7 @@ set_multicast_list(struct net_device *dev) struct eepro_local *lp = netdev_priv(dev); short ioaddr = dev->base_addr; unsigned short mode; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int mc_count = netdev_mc_count(dev); if (dev->flags&(IFF_ALLMULTI|IFF_PROMISC) || mc_count > 63) @@ -1332,8 +1332,8 @@ set_multicast_list(struct net_device *dev) outw(0, ioaddr + IO_PORT); outw(6 * (mc_count + 1), ioaddr + IO_PORT); - netdev_for_each_mc_addr(dmi, dev) { - eaddrs = (unsigned short *) dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + eaddrs = (unsigned short *) ha->addr; outw(*eaddrs++, ioaddr + IO_PORT); outw(*eaddrs++, ioaddr + IO_PORT); outw(*eaddrs++, ioaddr + IO_PORT); diff --git a/drivers/net/eexpress.c b/drivers/net/eexpress.c index 7013dc8a6cb..b3882fd8db6 100644 --- a/drivers/net/eexpress.c +++ b/drivers/net/eexpress.c @@ -1576,7 +1576,7 @@ static void eexp_hw_init586(struct net_device *dev) static void eexp_setup_filter(struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned short ioaddr = dev->base_addr; int count = netdev_mc_count(dev); int i; @@ -1589,8 +1589,8 @@ static void eexp_setup_filter(struct net_device *dev) outw(CONF_NR_MULTICAST & ~31, ioaddr+SM_PTR); outw(6*count, ioaddr+SHADOW(CONF_NR_MULTICAST)); i = 0; - netdev_for_each_mc_addr(dmi, dev) { - unsigned short *data = (unsigned short *) dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + unsigned short *data = (unsigned short *) ha->addr; if (i == count) break; diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c index b004eaba3d7..b97411aaa77 100644 --- a/drivers/net/ehea/ehea_main.c +++ b/drivers/net/ehea/ehea_main.c @@ -1966,7 +1966,7 @@ static void ehea_add_multicast_entry(struct ehea_port *port, u8 *mc_mac_addr) static void ehea_set_multicast_list(struct net_device *dev) { struct ehea_port *port = netdev_priv(dev); - struct dev_mc_list *k_mcl_entry; + struct netdev_hw_addr *ha; int ret; if (dev->flags & IFF_PROMISC) { @@ -1997,8 +1997,8 @@ static void ehea_set_multicast_list(struct net_device *dev) goto out; } - netdev_for_each_mc_addr(k_mcl_entry, dev) - ehea_add_multicast_entry(port, k_mcl_entry->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + ehea_add_multicast_entry(port, ha->addr); } out: diff --git a/drivers/net/enic/enic_main.c b/drivers/net/enic/enic_main.c index 6d70c349c95..1232887c243 100644 --- a/drivers/net/enic/enic_main.c +++ b/drivers/net/enic/enic_main.c @@ -822,7 +822,7 @@ static int enic_set_mac_addr(struct net_device *netdev, char *addr) static void enic_set_multicast_list(struct net_device *netdev) { struct enic *enic = netdev_priv(netdev); - struct dev_mc_list *list; + struct netdev_hw_addr *ha; int directed = 1; int multicast = (netdev->flags & IFF_MULTICAST) ? 1 : 0; int broadcast = (netdev->flags & IFF_BROADCAST) ? 1 : 0; @@ -852,10 +852,10 @@ static void enic_set_multicast_list(struct net_device *netdev) */ i = 0; - netdev_for_each_mc_addr(list, netdev) { + netdev_for_each_mc_addr(ha, netdev) { if (i == mc_count) break; - memcpy(mc_addr[i++], list->dmi_addr, ETH_ALEN); + memcpy(mc_addr[i++], ha->addr, ETH_ALEN); } for (i = 0; i < enic->mc_count; i++) { diff --git a/drivers/net/epic100.c b/drivers/net/epic100.c index 39c271b6be4..f6584a1ad3b 100644 --- a/drivers/net/epic100.c +++ b/drivers/net/epic100.c @@ -1400,12 +1400,12 @@ static void set_rx_mode(struct net_device *dev) outl(0x0004, ioaddr + RxCtrl); return; } else { /* Never executed, for now. */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { unsigned int bit_nr = - ether_crc_le(ETH_ALEN, mclist->dmi_addr) & 0x3f; + ether_crc_le(ETH_ALEN, ha->addr) & 0x3f; mc_filter[bit_nr >> 3] |= (1 << bit_nr); } } diff --git a/drivers/net/ethoc.c b/drivers/net/ethoc.c index 209742304e2..f6be5aeaf94 100644 --- a/drivers/net/ethoc.c +++ b/drivers/net/ethoc.c @@ -755,7 +755,7 @@ static void ethoc_set_multicast_list(struct net_device *dev) { struct ethoc *priv = netdev_priv(dev); u32 mode = ethoc_read(priv, MODER); - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; u32 hash[2] = { 0, 0 }; /* set loopback mode if requested */ @@ -783,8 +783,8 @@ static void ethoc_set_multicast_list(struct net_device *dev) hash[0] = 0xffffffff; hash[1] = 0xffffffff; } else { - netdev_for_each_mc_addr(mc, dev) { - u32 crc = ether_crc(ETH_ALEN, mc->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + u32 crc = ether_crc(ETH_ALEN, ha->addr); int bit = (crc >> 26) & 0x3f; hash[bit >> 5] |= 1 << (bit & 0x1f); } diff --git a/drivers/net/ewrk3.c b/drivers/net/ewrk3.c index a2bade58688..11ba70f4997 100644 --- a/drivers/net/ewrk3.c +++ b/drivers/net/ewrk3.c @@ -1169,7 +1169,7 @@ static void set_multicast_list(struct net_device *dev) static void SetMulticastFilter(struct net_device *dev) { struct ewrk3_private *lp = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u_long iobase = dev->base_addr; int i; char *addrs, bit, byte; @@ -1213,8 +1213,8 @@ static void SetMulticastFilter(struct net_device *dev) } /* Update table */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if ((*addrs & 0x01) == 1) { /* multicast address? */ crc = ether_crc_le(ETH_ALEN, addrs); hashcode = crc & ((1 << 9) - 1); /* hashcode is 9 LSb of CRC */ diff --git a/drivers/net/fealnx.c b/drivers/net/fealnx.c index 9d5ad08a119..e8a2705237b 100644 --- a/drivers/net/fealnx.c +++ b/drivers/net/fealnx.c @@ -1792,12 +1792,12 @@ static void __set_rx_mode(struct net_device *dev) memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = CR_W_AB | CR_W_AM; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { unsigned int bit; - bit = (ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26) ^ 0x3F; + bit = (ether_crc(ETH_ALEN, ha->addr) >> 26) ^ 0x3F; mc_filter[bit >> 5] |= (1 << bit); } rx_mode = CR_W_AB | CR_W_AM; diff --git a/drivers/net/fec.c b/drivers/net/fec.c index 848eb1968ab..2b1651aee13 100644 --- a/drivers/net/fec.c +++ b/drivers/net/fec.c @@ -954,7 +954,7 @@ fec_enet_close(struct net_device *dev) static void set_multicast_list(struct net_device *dev) { struct fec_enet_private *fep = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned int i, bit, data, crc, tmp; unsigned char hash; @@ -984,16 +984,16 @@ static void set_multicast_list(struct net_device *dev) writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH); writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW); - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { /* Only support group multicast for now */ - if (!(dmi->dmi_addr[0] & 1)) + if (!(ha->addr[0] & 1)) continue; /* calculate crc32 value of mac address */ crc = 0xffffffff; - for (i = 0; i < dmi->dmi_addrlen; i++) { - data = dmi->dmi_addr[i]; + for (i = 0; i < dev->addr_len; i++) { + data = ha->addr[i]; for (bit = 0; bit < 8; bit++, data >>= 1) { crc = (crc >> 1) ^ (((crc ^ data) & 1) ? CRC32_POLY : 0); diff --git a/drivers/net/fec_mpc52xx.c b/drivers/net/fec_mpc52xx.c index 704155e2bdd..667ba1391b9 100644 --- a/drivers/net/fec_mpc52xx.c +++ b/drivers/net/fec_mpc52xx.c @@ -574,12 +574,12 @@ static void mpc52xx_fec_set_multicast_list(struct net_device *dev) out_be32(&fec->gaddr2, 0xffffffff); } else { u32 crc; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u32 gaddr1 = 0x00000000; u32 gaddr2 = 0x00000000; - netdev_for_each_mc_addr(dmi, dev) { - crc = ether_crc_le(6, dmi->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(6, ha->addr) >> 26; if (crc >= 32) gaddr1 |= 1 << (crc-32); else diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index ca05e566202..6a2b64f0a7d 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -3103,12 +3103,14 @@ static void nv_set_multicast(struct net_device *dev) if (dev->flags & IFF_ALLMULTI) { alwaysOn[0] = alwaysOn[1] = alwaysOff[0] = alwaysOff[1] = 0; } else { - struct dev_mc_list *walk; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(walk, dev) { + netdev_for_each_mc_addr(ha, dev) { + unsigned char *addr = ha->addr; u32 a, b; - a = le32_to_cpu(*(__le32 *) walk->dmi_addr); - b = le16_to_cpu(*(__le16 *) (&walk->dmi_addr[4])); + + a = le32_to_cpu(*(__le32 *) addr); + b = le16_to_cpu(*(__le16 *) (&addr[4])); alwaysOn[0] &= a; alwaysOff[0] &= ~a; alwaysOn[1] &= b; diff --git a/drivers/net/fs_enet/mac-fcc.c b/drivers/net/fs_enet/mac-fcc.c index cf4f674f9e2..b3bad7c15d0 100644 --- a/drivers/net/fs_enet/mac-fcc.c +++ b/drivers/net/fs_enet/mac-fcc.c @@ -231,12 +231,12 @@ static void set_multicast_finish(struct net_device *dev) static void set_multicast_list(struct net_device *dev) { - struct dev_mc_list *pmc; + struct netdev_hw_addr *ha; if ((dev->flags & IFF_PROMISC) == 0) { set_multicast_start(dev); - netdev_for_each_mc_addr(pmc, dev) - set_multicast_one(dev, pmc->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + set_multicast_one(dev, ha->addr); set_multicast_finish(dev); } else set_promiscuous_mode(dev); diff --git a/drivers/net/fs_enet/mac-fec.c b/drivers/net/fs_enet/mac-fec.c index cd2c6cca5f2..75974c6d201 100644 --- a/drivers/net/fs_enet/mac-fec.c +++ b/drivers/net/fs_enet/mac-fec.c @@ -232,12 +232,12 @@ static void set_multicast_finish(struct net_device *dev) static void set_multicast_list(struct net_device *dev) { - struct dev_mc_list *pmc; + struct netdev_hw_addr *ha; if ((dev->flags & IFF_PROMISC) == 0) { set_multicast_start(dev); - netdev_for_each_mc_addr(pmc, dev) - set_multicast_one(dev, pmc->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + set_multicast_one(dev, ha->addr); set_multicast_finish(dev); } else set_promiscuous_mode(dev); diff --git a/drivers/net/fs_enet/mac-scc.c b/drivers/net/fs_enet/mac-scc.c index c490a466cae..0ab6a346a19 100644 --- a/drivers/net/fs_enet/mac-scc.c +++ b/drivers/net/fs_enet/mac-scc.c @@ -224,12 +224,12 @@ static void set_multicast_finish(struct net_device *dev) static void set_multicast_list(struct net_device *dev) { - struct dev_mc_list *pmc; + struct netdev_hw_addr *ha; if ((dev->flags & IFF_PROMISC) == 0) { set_multicast_start(dev); - netdev_for_each_mc_addr(pmc, dev) - set_multicast_one(dev, pmc->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + set_multicast_one(dev, ha->addr); set_multicast_finish(dev); } else set_promiscuous_mode(dev); diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index b6715553cf1..fdd26c2b1a2 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -2797,7 +2797,7 @@ static void adjust_link(struct net_device *dev) * whenever dev->flags is changed */ static void gfar_set_multi(struct net_device *dev) { - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; struct gfar_private *priv = netdev_priv(dev); struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; @@ -2870,13 +2870,12 @@ static void gfar_set_multi(struct net_device *dev) return; /* Parse the list, and set the appropriate bits */ - netdev_for_each_mc_addr(mc_ptr, dev) { + netdev_for_each_mc_addr(ha, dev) { if (idx < em_num) { - gfar_set_mac_for_addr(dev, idx, - mc_ptr->dmi_addr); + gfar_set_mac_for_addr(dev, idx, ha->addr); idx++; } else - gfar_set_hash_for_addr(dev, mc_ptr->dmi_addr); + gfar_set_hash_for_addr(dev, ha->addr); } } diff --git a/drivers/net/greth.c b/drivers/net/greth.c index c5e0d28a6de..fbe6ab6b919 100644 --- a/drivers/net/greth.c +++ b/drivers/net/greth.c @@ -988,7 +988,7 @@ static u32 greth_hash_get_index(__u8 *addr) static void greth_set_hash_filter(struct net_device *dev) { - struct dev_mc_list *curr; + struct netdev_hw_addr *ha; struct greth_private *greth = netdev_priv(dev); struct greth_regs *regs = (struct greth_regs *) greth->regs; u32 mc_filter[2]; @@ -996,8 +996,8 @@ static void greth_set_hash_filter(struct net_device *dev) mc_filter[0] = mc_filter[1] = 0; - netdev_for_each_mc_addr(curr, dev) { - bitnr = greth_hash_get_index(curr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + bitnr = greth_hash_get_index(ha->addr); mc_filter[bitnr >> 5] |= 1 << (bitnr & 31); } diff --git a/drivers/net/hamachi.c b/drivers/net/hamachi.c index 373546dd083..2bfcca6d180 100644 --- a/drivers/net/hamachi.c +++ b/drivers/net/hamachi.c @@ -1858,12 +1858,12 @@ static void set_rx_mode(struct net_device *dev) /* Too many to match, or accept all multicasts. */ writew(0x000B, ioaddr + AddrMode); } else if (!netdev_mc_empty(dev)) { /* Must use the CAM filter. */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i = 0; - netdev_for_each_mc_addr(mclist, dev) { - writel(*(u32*)(mclist->dmi_addr), ioaddr + 0x100 + i*8); - writel(0x20000 | (*(u16*)&mclist->dmi_addr[4]), + netdev_for_each_mc_addr(ha, dev) { + writel(*(u32 *)(ha->addr), ioaddr + 0x100 + i*8); + writel(0x20000 | (*(u16 *)&ha->addr[4]), ioaddr + 0x104 + i*8); i++; } diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index b766a69bf0c..86b2b433234 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -2100,15 +2100,15 @@ static void hp100_set_multicast_list(struct net_device *dev) } else { int i, idx; u_char *addrs; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; memset(&lp->hash_bytes, 0x00, 8); #ifdef HP100_DEBUG printk("hp100: %s: computing hash filter - mc_count = %i\n", dev->name, netdev_mc_count(dev)); #endif - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if ((*addrs & 0x01) == 0x01) { /* multicast address? */ #ifdef HP100_DEBUG printk("hp100: %s: multicast = %pM, ", diff --git a/drivers/net/ibm_newemac/core.c b/drivers/net/ibm_newemac/core.c index d8533a4ef82..40c78507ef1 100644 --- a/drivers/net/ibm_newemac/core.c +++ b/drivers/net/ibm_newemac/core.c @@ -388,18 +388,19 @@ static void emac_hash_mc(struct emac_instance *dev) const int regs = EMAC_XAHT_REGS(dev); u32 *gaht_base = emac_gaht_base(dev); u32 gaht_temp[regs]; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i; DBG(dev, "hash_mc %d" NL, netdev_mc_count(dev->ndev)); memset(gaht_temp, 0, sizeof (gaht_temp)); - netdev_for_each_mc_addr(dmi, dev->ndev) { + netdev_for_each_mc_addr(ha, dev->ndev) { int slot, reg, mask; - DBG2(dev, "mc %pM" NL, dmi->dmi_addr); + DBG2(dev, "mc %pM" NL, ha->addr); - slot = EMAC_XAHT_CRC_TO_SLOT(dev, ether_crc(ETH_ALEN, dmi->dmi_addr)); + slot = EMAC_XAHT_CRC_TO_SLOT(dev, + ether_crc(ETH_ALEN, ha->addr)); reg = EMAC_XAHT_SLOT_TO_REG(dev, slot); mask = EMAC_XAHT_SLOT_TO_MASK(dev, slot); @@ -1176,7 +1177,7 @@ static int emac_open(struct net_device *ndev) netif_carrier_on(dev->ndev); /* Required for Pause packet support in EMAC */ - dev_mc_add(ndev, default_mcast_addr, sizeof(default_mcast_addr), 1); + dev_mc_add_global(ndev, default_mcast_addr); emac_configure(dev); mal_poll_add(dev->mal, &dev->commac); diff --git a/drivers/net/ibmlana.c b/drivers/net/ibmlana.c index b5d0f4e973f..76949e08ee8 100644 --- a/drivers/net/ibmlana.c +++ b/drivers/net/ibmlana.c @@ -385,7 +385,7 @@ static void InitBoard(struct net_device *dev) int camcnt; camentry_t cams[16]; u32 cammask; - struct dev_mc_list *mcptr; + struct netdev_hw_addr *ha; u16 rcrval; /* reset the SONIC */ @@ -420,8 +420,8 @@ static void InitBoard(struct net_device *dev) /* start putting the multicast addresses into the CAM list. Stop if it is full. */ - netdev_for_each_mc_addr(mcptr, dev) { - putcam(cams, &camcnt, mcptr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + putcam(cams, &camcnt, ha->addr); if (camcnt == 16) break; } @@ -479,7 +479,7 @@ static void InitBoard(struct net_device *dev) /* if still multicast addresses left or ALLMULTI is set, set the multicast enable bit */ - if ((dev->flags & IFF_ALLMULTI) || (mcptr != NULL)) + if ((dev->flags & IFF_ALLMULTI) || netdev_mc_count(dev) > camcnt) rcrval |= RCREG_AMC; /* promiscous mode ? */ diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 0bc777bac9b..f468590ed45 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -1072,7 +1072,7 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) ibmveth_error_printk("h_multicast_ctrl rc=%ld when entering promisc mode\n", lpar_rc); } } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; /* clear the filter table & disable filtering */ lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastEnableRecv | @@ -1083,10 +1083,10 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) ibmveth_error_printk("h_multicast_ctrl rc=%ld when attempting to clear filter table\n", lpar_rc); } /* add the addresses to the filter table */ - netdev_for_each_mc_addr(mclist, netdev) { + netdev_for_each_mc_addr(ha, netdev) { // add the multicast address to the filter table unsigned long mcast_addr = 0; - memcpy(((char *)&mcast_addr)+2, mclist->dmi_addr, 6); + memcpy(((char *)&mcast_addr)+2, ha->addr, 6); lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastAddFilter, mcast_addr); diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index ea875709f05..78cc742e233 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -2864,7 +2864,7 @@ static int igb_write_mc_addr_list(struct net_device *netdev) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 *mta_list; int i; @@ -2881,8 +2881,8 @@ static int igb_write_mc_addr_list(struct net_device *netdev) /* The shared function expects a packed array of only addresses. */ i = 0; - netdev_for_each_mc_addr(mc_ptr, netdev) - memcpy(mta_list + (i++ * ETH_ALEN), mc_ptr->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, netdev) + memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); igb_update_mc_addr_list(hw, mta_list, i); kfree(mta_list); diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c index a77afd8a14b..ea8abf5c1ef 100644 --- a/drivers/net/igbvf/netdev.c +++ b/drivers/net/igbvf/netdev.c @@ -1399,7 +1399,7 @@ static void igbvf_set_multi(struct net_device *netdev) { struct igbvf_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 *mta_list = NULL; int i; @@ -1414,8 +1414,8 @@ static void igbvf_set_multi(struct net_device *netdev) /* prepare a packed array of only addresses. */ i = 0; - netdev_for_each_mc_addr(mc_ptr, netdev) - memcpy(mta_list + (i++ * ETH_ALEN), mc_ptr->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, netdev) + memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); hw->mac.ops.update_mc_addr_list(hw, mta_list, i, 0, 0); kfree(mta_list); diff --git a/drivers/net/ioc3-eth.c b/drivers/net/ioc3-eth.c index 70871b9b045..57d873da978 100644 --- a/drivers/net/ioc3-eth.c +++ b/drivers/net/ioc3-eth.c @@ -1664,7 +1664,7 @@ static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static void ioc3_set_multicast_list(struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; struct ioc3_private *ip = netdev_priv(dev); struct ioc3 *ioc3 = ip->regs; u64 ehar = 0; @@ -1688,8 +1688,8 @@ static void ioc3_set_multicast_list(struct net_device *dev) ip->ehar_h = 0xffffffff; ip->ehar_l = 0xffffffff; } else { - netdev_for_each_mc_addr(dmi, dev) { - char *addr = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + char *addr = ha->addr; if (!(*addr & 1)) continue; diff --git a/drivers/net/ipg.c b/drivers/net/ipg.c index 0d7ad3f2d0f..67cfc7d9d89 100644 --- a/drivers/net/ipg.c +++ b/drivers/net/ipg.c @@ -569,7 +569,7 @@ static int ipg_config_autoneg(struct net_device *dev) static void ipg_nic_set_multicast_list(struct net_device *dev) { void __iomem *ioaddr = ipg_ioaddr(dev); - struct dev_mc_list *mc_list_ptr; + struct netdev_hw_addr *ha; unsigned int hashindex; u32 hashtable[2]; u8 receivemode; @@ -608,9 +608,9 @@ static void ipg_nic_set_multicast_list(struct net_device *dev) hashtable[1] = 0x00000000; /* Cycle through all multicast addresses to filter. */ - netdev_for_each_mc_addr(mc_list_ptr, dev) { + netdev_for_each_mc_addr(ha, dev) { /* Calculate CRC result for each multicast address. */ - hashindex = crc32_le(0xffffffff, mc_list_ptr->dmi_addr, + hashindex = crc32_le(0xffffffff, ha->addr, ETH_ALEN); /* Use only the least significant 6 bits. */ diff --git a/drivers/net/iseries_veth.c b/drivers/net/iseries_veth.c index e6e972d9b7c..cd65b8629bc 100644 --- a/drivers/net/iseries_veth.c +++ b/drivers/net/iseries_veth.c @@ -961,15 +961,15 @@ static void veth_set_multicast_list(struct net_device *dev) (netdev_mc_count(dev) > VETH_MAX_MCAST)) { port->promiscuous = 1; } else { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; port->promiscuous = 0; /* Update table */ port->num_mcast = 0; - netdev_for_each_mc_addr(dmi, dev) { - u8 *addr = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + u8 *addr = ha->addr; u64 xaddr = 0; if (addr[0] & 0x01) {/* multicast address? */ diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index c9fef65cb98..912dd1d5772 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1058,7 +1058,7 @@ ixgb_set_multi(struct net_device *netdev) { struct ixgb_adapter *adapter = netdev_priv(netdev); struct ixgb_hw *hw = &adapter->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u32 rctl; int i; @@ -1089,9 +1089,9 @@ ixgb_set_multi(struct net_device *netdev) IXGB_WRITE_REG(hw, RCTL, rctl); i = 0; - netdev_for_each_mc_addr(mc_ptr, netdev) + netdev_for_each_mc_addr(ha, netdev) memcpy(&mta[i++ * IXGB_ETH_LENGTH_OF_ADDRESS], - mc_ptr->dmi_addr, IXGB_ETH_LENGTH_OF_ADDRESS); + ha->addr, IXGB_ETH_LENGTH_OF_ADDRESS); ixgb_mc_addr_list_update(hw, mta, netdev_mc_count(netdev), 0); } diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c index 4d1c3a42945..6eb5814ca7d 100644 --- a/drivers/net/ixgbe/ixgbe_common.c +++ b/drivers/net/ixgbe/ixgbe_common.c @@ -1494,7 +1494,7 @@ static void ixgbe_set_mta(struct ixgbe_hw *hw, u8 *mc_addr) s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, struct net_device *netdev) { - struct dev_addr_list *dmi; + struct netdev_hw_addr *ha; u32 i; /* @@ -1510,9 +1510,9 @@ s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_MTA(i), 0); /* Add the new addresses */ - netdev_for_each_mc_addr(dmi, netdev) { + netdev_for_each_mc_addr(ha, netdev) { hw_dbg(hw, " Adding the multicast addresses:\n"); - ixgbe_set_mta(hw, dmi->dmi_addr); + ixgbe_set_mta(hw, ha->addr); } /* Enable mta */ diff --git a/drivers/net/ixgbevf/vf.c b/drivers/net/ixgbevf/vf.c index f457c52b5ed..852e9c4fd93 100644 --- a/drivers/net/ixgbevf/vf.c +++ b/drivers/net/ixgbevf/vf.c @@ -259,7 +259,7 @@ static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr, static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, struct net_device *netdev) { - struct dev_addr_list *dmi; + struct netdev_hw_addr *ha; struct ixgbe_mbx_info *mbx = &hw->mbx; u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; u16 *vector_list = (u16 *)&msgbuf[1]; @@ -281,10 +281,10 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, msgbuf[0] |= cnt << IXGBE_VT_MSGINFO_SHIFT; i = 0; - netdev_for_each_mc_addr(dmi, netdev) { + netdev_for_each_mc_addr(ha, netdev) { if (i == cnt) break; - vector_list[i++] = ixgbevf_mta_vector(hw, dmi->dmi_addr); + vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr); } mbx->ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE); diff --git a/drivers/net/jme.c b/drivers/net/jme.c index c0b59a55538..10e816d2caf 100644 --- a/drivers/net/jme.c +++ b/drivers/net/jme.c @@ -2009,12 +2009,12 @@ jme_set_multi(struct net_device *netdev) } else if (netdev->flags & IFF_ALLMULTI) { jme->reg_rxmcs |= RXMCS_ALLMULFRAME; } else if (netdev->flags & IFF_MULTICAST) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int bit_nr; jme->reg_rxmcs |= RXMCS_MULFRAME | RXMCS_MULFILTERED; - netdev_for_each_mc_addr(mclist, netdev) { - bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) & 0x3F; + netdev_for_each_mc_addr(ha, netdev) { + bit_nr = ether_crc(ETH_ALEN, ha->addr) & 0x3F; mc_hash[bit_nr >> 5] |= 1 << (bit_nr & 0x1F); } diff --git a/drivers/net/korina.c b/drivers/net/korina.c index edaedc7aa03..26bf1b76b99 100644 --- a/drivers/net/korina.c +++ b/drivers/net/korina.c @@ -482,7 +482,7 @@ static void korina_multicast_list(struct net_device *dev) { struct korina_private *lp = netdev_priv(dev); unsigned long flags; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u32 recognise = ETH_ARC_AB; /* always accept broadcasts */ int i; @@ -502,8 +502,8 @@ static void korina_multicast_list(struct net_device *dev) for (i = 0; i < 4; i++) hash_table[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - char *addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + char *addrs = ha->addr; if (!(*addrs & 1)) continue; diff --git a/drivers/net/ks8851.c b/drivers/net/ks8851.c index 66be4e449f0..4dcd61f81ec 100644 --- a/drivers/net/ks8851.c +++ b/drivers/net/ks8851.c @@ -956,13 +956,13 @@ static void ks8851_set_rx_mode(struct net_device *dev) rxctrl.rxcr1 = (RXCR1_RXME | RXCR1_RXAE | RXCR1_RXPAFMA | RXCR1_RXMAFMA); } else if (dev->flags & IFF_MULTICAST && !netdev_mc_empty(dev)) { - struct dev_mc_list *mcptr; + struct netdev_hw_addr *ha; u32 crc; /* accept some multicast */ - netdev_for_each_mc_addr(mcptr, dev) { - crc = ether_crc(ETH_ALEN, mcptr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc(ETH_ALEN, ha->addr); crc >>= (32 - 6); /* get top six bits */ rxctrl.mchash[crc >> 4] |= (1 << (crc & 0xf)); diff --git a/drivers/net/ks8851_mll.c b/drivers/net/ks8851_mll.c index ee3fe30b2ad..70a3d98f4bd 100644 --- a/drivers/net/ks8851_mll.c +++ b/drivers/net/ks8851_mll.c @@ -362,7 +362,6 @@ static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 }; #define MAX_MCAST_LST 32 #define HW_MCAST_SIZE 8 -#define MAC_ADDR_LEN 6 /** * union ks_tx_hdr - tx header data @@ -450,7 +449,7 @@ struct ks_net { u16 promiscuous; u16 all_mcast; u16 mcast_lst_size; - u8 mcast_lst[MAX_MCAST_LST][MAC_ADDR_LEN]; + u8 mcast_lst[MAX_MCAST_LST][ETH_ALEN]; u8 mcast_bits[HW_MCAST_SIZE]; u8 mac_addr[6]; u8 fid; @@ -1170,7 +1169,7 @@ static void ks_set_mcast(struct ks_net *ks, u16 mcast) static void ks_set_rx_mode(struct net_device *netdev) { struct ks_net *ks = netdev_priv(netdev); - struct dev_mc_list *ptr; + struct netdev_hw_addr *ha; /* Turn on/off promiscuous mode. */ if ((netdev->flags & IFF_PROMISC) == IFF_PROMISC) @@ -1187,13 +1186,12 @@ static void ks_set_rx_mode(struct net_device *netdev) if (netdev_mc_count(netdev) <= MAX_MCAST_LST) { int i = 0; - netdev_for_each_mc_addr(ptr, netdev) { - if (!(*ptr->dmi_addr & 1)) + netdev_for_each_mc_addr(ha, netdev) { + if (!(*ha->addr & 1)) continue; if (i >= MAX_MCAST_LST) break; - memcpy(ks->mcast_lst[i++], ptr->dmi_addr, - MAC_ADDR_LEN); + memcpy(ks->mcast_lst[i++], ha->addr, ETH_ALEN); } ks->mcast_lst_size = (u8)i; ks_set_grpaddr(ks); diff --git a/drivers/net/ksz884x.c b/drivers/net/ksz884x.c index b843bf7d8c1..34876952161 100644 --- a/drivers/net/ksz884x.c +++ b/drivers/net/ksz884x.c @@ -5763,7 +5763,7 @@ static void netdev_set_rx_mode(struct net_device *dev) struct dev_priv *priv = netdev_priv(dev); struct dev_info *hw_priv = priv->adapter; struct ksz_hw *hw = &hw_priv->hw; - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; int multicast = (dev->flags & IFF_ALLMULTI); dev_set_promiscuous(dev, priv, hw, (dev->flags & IFF_PROMISC)); @@ -5780,7 +5780,7 @@ static void netdev_set_rx_mode(struct net_device *dev) int i = 0; /* List too big to support so turn on all multicast mode. */ - if (dev->mc_count > MAX_MULTICAST_LIST) { + if (netdev_mc_count(dev) > MAX_MULTICAST_LIST) { if (MAX_MULTICAST_LIST != hw->multi_list_size) { hw->multi_list_size = MAX_MULTICAST_LIST; ++hw->all_multi; @@ -5789,13 +5789,12 @@ static void netdev_set_rx_mode(struct net_device *dev) return; } - netdev_for_each_mc_addr(mc_ptr, dev) { - if (!(*mc_ptr->dmi_addr & 1)) + netdev_for_each_mc_addr(ha, dev) { + if (!(*ha->addr & 1)) continue; if (i >= MAX_MULTICAST_LIST) break; - memcpy(hw->multi_list[i++], mc_ptr->dmi_addr, - MAC_ADDR_LEN); + memcpy(hw->multi_list[i++], ha->addr, MAC_ADDR_LEN); } hw->multi_list_size = (u8) i; hw_set_grp_addr(hw); diff --git a/drivers/net/lib82596.c b/drivers/net/lib82596.c index 443c39a3732..fddaf921885 100644 --- a/drivers/net/lib82596.c +++ b/drivers/net/lib82596.c @@ -1388,7 +1388,7 @@ static void set_multicast_list(struct net_device *dev) } if (!netdev_mc_empty(dev)) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char *cp; struct mc_cmd *cmd; @@ -1396,10 +1396,10 @@ static void set_multicast_list(struct net_device *dev) cmd->cmd.command = SWAP16(CmdMulticastList); cmd->mc_cnt = SWAP16(netdev_mc_count(dev) * 6); cp = cmd->mc_addrs; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if (!cnt--) break; - memcpy(cp, dmi->dmi_addr, 6); + memcpy(cp, ha->addr, 6); if (i596_debug > 1) DEB(DEB_MULTI, printk(KERN_DEBUG diff --git a/drivers/net/lib8390.c b/drivers/net/lib8390.c index 56f66f48540..526dc9cbc3c 100644 --- a/drivers/net/lib8390.c +++ b/drivers/net/lib8390.c @@ -905,10 +905,10 @@ static struct net_device_stats *__ei_get_stats(struct net_device *dev) static inline void make_mc_bits(u8 *bits, struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(dmi, dev) { - u32 crc = ether_crc(ETH_ALEN, dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + u32 crc = ether_crc(ETH_ALEN, ha->addr); /* * The 8390 uses the 6 most significant bits of the * CRC to index the multicast table. diff --git a/drivers/net/ll_temac_main.c b/drivers/net/ll_temac_main.c index a18e3485476..30474d6b15c 100644 --- a/drivers/net/ll_temac_main.c +++ b/drivers/net/ll_temac_main.c @@ -250,20 +250,20 @@ static void temac_set_multicast_list(struct net_device *ndev) temac_indirect_out32(lp, XTE_AFM_OFFSET, XTE_AFM_EPPRM_MASK); dev_info(&ndev->dev, "Promiscuous mode enabled.\n"); } else if (!netdev_mc_empty(ndev)) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; i = 0; - netdev_for_each_mc_addr(mclist, ndev) { + netdev_for_each_mc_addr(ha, ndev) { if (i >= MULTICAST_CAM_TABLE_NUM) break; - multi_addr_msw = ((mclist->dmi_addr[3] << 24) | - (mclist->dmi_addr[2] << 16) | - (mclist->dmi_addr[1] << 8) | - (mclist->dmi_addr[0])); + multi_addr_msw = ((ha->addr[3] << 24) | + (ha->addr[2] << 16) | + (ha->addr[1] << 8) | + (ha->addr[0])); temac_indirect_out32(lp, XTE_MAW0_OFFSET, multi_addr_msw); - multi_addr_lsw = ((mclist->dmi_addr[5] << 8) | - (mclist->dmi_addr[4]) | (i << 16)); + multi_addr_lsw = ((ha->addr[5] << 8) | + (ha->addr[4]) | (i << 16)); temac_indirect_out32(lp, XTE_MAW1_OFFSET, multi_addr_lsw); i++; diff --git a/drivers/net/lp486e.c b/drivers/net/lp486e.c index 3e3cc04defd..72379c5439d 100644 --- a/drivers/net/lp486e.c +++ b/drivers/net/lp486e.c @@ -1256,7 +1256,7 @@ static void set_multicast_list(struct net_device *dev) { dev->name, netdev_mc_count(dev)); if (!netdev_mc_empty(dev)) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *cp; cmd = kmalloc(sizeof(struct i596_cmd) + 2 + netdev_mc_count(dev) * 6, GFP_ATOMIC); @@ -1267,8 +1267,8 @@ static void set_multicast_list(struct net_device *dev) { cmd->command = CmdMulticastList; *((unsigned short *) (cmd + 1)) = netdev_mc_count(dev) * 6; cp = ((char *)(cmd + 1))+2; - netdev_for_each_mc_addr(dmi, dev) { - memcpy(cp, dmi->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) { + memcpy(cp, ha->addr, 6); cp += 6; } if (i596_debug & LOG_SRCDST) diff --git a/drivers/net/macb.c b/drivers/net/macb.c index c8a18a6203c..eab121945d7 100644 --- a/drivers/net/macb.c +++ b/drivers/net/macb.c @@ -882,15 +882,15 @@ static int hash_get_index(__u8 *addr) */ static void macb_sethashtable(struct net_device *dev) { - struct dev_mc_list *curr; + struct netdev_hw_addr *ha; unsigned long mc_filter[2]; unsigned int bitnr; struct macb *bp = netdev_priv(dev); mc_filter[0] = mc_filter[1] = 0; - netdev_for_each_mc_addr(curr, dev) { - bitnr = hash_get_index(curr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + bitnr = hash_get_index(ha->addr); mc_filter[bitnr >> 5] |= 1 << (bitnr & 31); } diff --git a/drivers/net/mace.c b/drivers/net/mace.c index ab5f0bf6d1a..2328a7399dc 100644 --- a/drivers/net/mace.c +++ b/drivers/net/mace.c @@ -598,7 +598,7 @@ static void mace_set_multicast(struct net_device *dev) mp->maccc |= PROM; } else { unsigned char multicast_filter[8]; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; if (dev->flags & IFF_ALLMULTI) { for (i = 0; i < 8; i++) @@ -606,8 +606,8 @@ static void mace_set_multicast(struct net_device *dev) } else { for (i = 0; i < 8; i++) multicast_filter[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - crc = ether_crc_le(6, dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(6, ha->addr); i = crc >> 26; /* bit number in multicast_filter */ multicast_filter[i >> 3] |= 1 << (i & 7); } diff --git a/drivers/net/macmace.c b/drivers/net/macmace.c index 13ba8f4afb7..8a50c67e592 100644 --- a/drivers/net/macmace.c +++ b/drivers/net/macmace.c @@ -508,7 +508,7 @@ static void mace_set_multicast(struct net_device *dev) mb->maccc |= PROM; } else { unsigned char multicast_filter[8]; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; if (dev->flags & IFF_ALLMULTI) { for (i = 0; i < 8; i++) { @@ -517,8 +517,8 @@ static void mace_set_multicast(struct net_device *dev) } else { for (i = 0; i < 8; i++) multicast_filter[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - crc = ether_crc_le(6, dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(6, ha->addr); /* bit number in multicast_filter */ i = crc >> 26; multicast_filter[i >> 3] |= 1 << (i & 7); diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c index 5eb96fe6ec5..455464223b4 100644 --- a/drivers/net/mlx4/en_netdev.c +++ b/drivers/net/mlx4/en_netdev.c @@ -168,7 +168,7 @@ static void mlx4_en_clear_list(struct net_device *dev) static void mlx4_en_cache_mclist(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; char *mc_addrs; int mc_addrs_cnt = netdev_mc_count(dev); int i; @@ -179,8 +179,8 @@ static void mlx4_en_cache_mclist(struct net_device *dev) return; } i = 0; - netdev_for_each_mc_addr(mclist, dev) - memcpy(mc_addrs + i++ * ETH_ALEN, mclist->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) + memcpy(mc_addrs + i++ * ETH_ALEN, ha->addr, ETH_ALEN); priv->mc_addrs = mc_addrs; priv->mc_addrs_cnt = mc_addrs_cnt; } diff --git a/drivers/net/mv643xx_eth.c b/drivers/net/mv643xx_eth.c index c97b6e4365a..d5ebe43b0e6 100644 --- a/drivers/net/mv643xx_eth.c +++ b/drivers/net/mv643xx_eth.c @@ -1769,7 +1769,7 @@ static void mv643xx_eth_program_multicast_filter(struct net_device *dev) struct mv643xx_eth_private *mp = netdev_priv(dev); u32 *mc_spec; u32 *mc_other; - struct dev_addr_list *addr; + struct netdev_hw_addr *ha; int i; if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { @@ -1794,8 +1794,8 @@ oom: memset(mc_spec, 0, 0x100); memset(mc_other, 0, 0x100); - netdev_for_each_mc_addr(addr, dev) { - u8 *a = addr->da_addr; + netdev_for_each_mc_addr(ha, dev) { + u8 *a = ha->addr; u32 *table; int entry; diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index e84dd3ee9c5..6d33adf988d 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -3001,7 +3001,7 @@ static void myri10ge_set_multicast_list(struct net_device *dev) { struct myri10ge_priv *mgp = netdev_priv(dev); struct myri10ge_cmd cmd; - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; __be32 data[2] = { 0, 0 }; int err; @@ -3038,8 +3038,8 @@ static void myri10ge_set_multicast_list(struct net_device *dev) } /* Walk the multicast list, and add each address */ - netdev_for_each_mc_addr(mc_list, dev) { - memcpy(data, &mc_list->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) { + memcpy(data, &ha->addr, 6); cmd.data0 = ntohl(data[0]); cmd.data1 = ntohl(data[1]); err = myri10ge_send_cmd(mgp, MXGEFW_JOIN_MULTICAST_GROUP, @@ -3047,7 +3047,7 @@ static void myri10ge_set_multicast_list(struct net_device *dev) if (err != 0) { netdev_err(dev, "Failed MXGEFW_JOIN_MULTICAST_GROUP, error status:%d %pM\n", - err, mc_list->dmi_addr); + err, ha->addr); goto abort; } } diff --git a/drivers/net/natsemi.c b/drivers/net/natsemi.c index e5203878324..9250bf6573e 100644 --- a/drivers/net/natsemi.c +++ b/drivers/net/natsemi.c @@ -2493,12 +2493,12 @@ static void __set_rx_mode(struct net_device *dev) rx_mode = RxFilterEnable | AcceptBroadcast | AcceptAllMulticast | AcceptMyPhys; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int b = (ether_crc(ETH_ALEN, mclist->dmi_addr) >> 23) & 0x1ff; + netdev_for_each_mc_addr(ha, dev) { + int b = (ether_crc(ETH_ALEN, ha->addr) >> 23) & 0x1ff; mc_filter[b/8] |= (1 << (b & 0x07)); } rx_mode = RxFilterEnable | AcceptBroadcast diff --git a/drivers/net/netxen/netxen_nic_hw.c b/drivers/net/netxen/netxen_nic_hw.c index a945591298a..781ca893ee0 100644 --- a/drivers/net/netxen/netxen_nic_hw.c +++ b/drivers/net/netxen/netxen_nic_hw.c @@ -537,7 +537,7 @@ netxen_nic_set_mcast_addr(struct netxen_adapter *adapter, void netxen_p2_nic_set_multi(struct net_device *netdev) { struct netxen_adapter *adapter = netdev_priv(netdev); - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 null_addr[6]; int i; @@ -571,8 +571,8 @@ void netxen_p2_nic_set_multi(struct net_device *netdev) netxen_nic_enable_mcast_filter(adapter); i = 0; - netdev_for_each_mc_addr(mc_ptr, netdev) - netxen_nic_set_mcast_addr(adapter, i++, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) + netxen_nic_set_mcast_addr(adapter, i++, ha->addr); /* Clear out remaining addresses */ while (i < adapter->max_mc_count) @@ -680,7 +680,7 @@ static int nx_p3_nic_add_mac(struct netxen_adapter *adapter, void netxen_p3_nic_set_multi(struct net_device *netdev) { struct netxen_adapter *adapter = netdev_priv(netdev); - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 bcast_addr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; u32 mode = VPORT_MISS_MODE_DROP; LIST_HEAD(del_list); @@ -707,8 +707,8 @@ void netxen_p3_nic_set_multi(struct net_device *netdev) } if (!netdev_mc_empty(netdev)) { - netdev_for_each_mc_addr(mc_ptr, netdev) - nx_p3_nic_add_mac(adapter, mc_ptr->dmi_addr, &del_list); + netdev_for_each_mc_addr(ha, netdev) + nx_p3_nic_add_mac(adapter, ha->addr, &del_list); } send_fw_cmd: diff --git a/drivers/net/ni52.c b/drivers/net/ni52.c index 05c29c2cef2..a76fabe2629 100644 --- a/drivers/net/ni52.c +++ b/drivers/net/ni52.c @@ -596,7 +596,7 @@ static int init586(struct net_device *dev) struct iasetup_cmd_struct __iomem *ias_cmd; struct tdr_cmd_struct __iomem *tdr_cmd; struct mcsetup_cmd_struct __iomem *mc_cmd; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int num_addrs = netdev_mc_count(dev); ptr = p->scb + 1; @@ -725,8 +725,8 @@ static int init586(struct net_device *dev) writew(num_addrs * 6, &mc_cmd->mc_cnt); i = 0; - netdev_for_each_mc_addr(dmi, dev) - memcpy_toio(mc_cmd->mc_list[i++], dmi->dmi_addr, 6); + netdev_for_each_mc_addr(ha, dev) + memcpy_toio(mc_cmd->mc_list[i++], ha->addr, 6); writew(make16(mc_cmd), &p->scb->cbl_offset); writeb(CUC_START, &p->scb->cmd_cuc); diff --git a/drivers/net/niu.c b/drivers/net/niu.c index 0678f3106cb..7b52c466cf4 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -6313,7 +6313,6 @@ static void niu_set_rx_mode(struct net_device *dev) { struct niu *np = netdev_priv(dev); int i, alt_cnt, err; - struct dev_addr_list *addr; struct netdev_hw_addr *ha; unsigned long flags; u16 hash[16] = { 0, }; @@ -6365,8 +6364,8 @@ static void niu_set_rx_mode(struct net_device *dev) for (i = 0; i < 16; i++) hash[i] = 0xffff; } else if (!netdev_mc_empty(dev)) { - netdev_for_each_mc_addr(addr, dev) { - u32 crc = ether_crc_le(ETH_ALEN, addr->da_addr); + netdev_for_each_mc_addr(ha, dev) { + u32 crc = ether_crc_le(ETH_ALEN, ha->addr); crc >>= 24; hash[crc >> 4] |= (1 << (15 - (crc & 0xf))); diff --git a/drivers/net/octeon/octeon_mgmt.c b/drivers/net/octeon/octeon_mgmt.c index be368e5cbf7..ee894ed35f7 100644 --- a/drivers/net/octeon/octeon_mgmt.c +++ b/drivers/net/octeon/octeon_mgmt.c @@ -474,7 +474,7 @@ static void octeon_mgmt_set_rx_filtering(struct net_device *netdev) unsigned int cam_mode = 1; /* 1 - Accept on CAM match */ unsigned int multicast_mode = 1; /* 1 - Reject all multicast. */ struct octeon_mgmt_cam_state cam_state; - struct dev_addr_list *list; + struct netdev_hw_addr *ha; struct list_head *pos; int available_cam_entries; @@ -510,8 +510,8 @@ static void octeon_mgmt_set_rx_filtering(struct net_device *netdev) } } if (multicast_mode == 0) { - netdev_for_each_mc_addr(list, netdev) - octeon_mgmt_cam_state_add(&cam_state, list->da_addr); + netdev_for_each_mc_addr(ha, netdev) + octeon_mgmt_cam_state_add(&cam_state, ha->addr); } diff --git a/drivers/net/pci-skeleton.c b/drivers/net/pci-skeleton.c index 36785853a14..dc3b4c7914f 100644 --- a/drivers/net/pci-skeleton.c +++ b/drivers/net/pci-skeleton.c @@ -1813,12 +1813,12 @@ static void netdrv_set_rx_mode(struct net_device *dev) rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); } diff --git a/drivers/net/pcmcia/axnet_cs.c b/drivers/net/pcmcia/axnet_cs.c index 09291e60d30..333cb3344d5 100644 --- a/drivers/net/pcmcia/axnet_cs.c +++ b/drivers/net/pcmcia/axnet_cs.c @@ -1623,11 +1623,11 @@ static struct net_device_stats *get_stats(struct net_device *dev) static inline void make_mc_bits(u8 *bits, struct net_device *dev) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u32 crc; - netdev_for_each_mc_addr(dmi, dev) { - crc = ether_crc(ETH_ALEN, dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc(ETH_ALEN, ha->addr); /* * The 8390 uses the 6 most significant bits of the * CRC to index the multicast table. diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index b9dc80b9d04..6734f7d6da9 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -1196,11 +1196,11 @@ static void set_rx_mode(struct net_device *dev) memset(mc_filter, 0x00, sizeof(mc_filter)); outb(1, ioaddr + RX_MODE); /* Ignore almost all multicasts. */ } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - unsigned int bit = ether_crc_le(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + unsigned int bit = ether_crc_le(ETH_ALEN, ha->addr) >> 26; mc_filter[bit >> 3] |= (1 << (bit & 7)); } outb(2, ioaddr + RX_MODE); /* Use normal mode. */ diff --git a/drivers/net/pcmcia/nmclan_cs.c b/drivers/net/pcmcia/nmclan_cs.c index c717b143f11..c516c199635 100644 --- a/drivers/net/pcmcia/nmclan_cs.c +++ b/drivers/net/pcmcia/nmclan_cs.c @@ -1475,7 +1475,7 @@ static void set_multicast_list(struct net_device *dev) { mace_private *lp = netdev_priv(dev); int adr[ETHER_ADDR_LEN] = {0}; /* Ethernet address */ - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; #ifdef PCMCIA_DEBUG { @@ -1495,8 +1495,8 @@ static void set_multicast_list(struct net_device *dev) if (num_addrs > 0) { /* Calculate multicast logical address filter */ memset(lp->multicast_ladrf, 0, MACE_LADRF_LEN); - netdev_for_each_mc_addr(dmi, dev) { - memcpy(adr, dmi->dmi_addr, ETHER_ADDR_LEN); + netdev_for_each_mc_addr(ha, dev) { + memcpy(adr, ha->addr, ETHER_ADDR_LEN); BuildLAF(lp->multicast_ladrf, adr); } } diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c index 5adc662c4bf..f45c626003a 100644 --- a/drivers/net/pcmcia/smc91c92_cs.c +++ b/drivers/net/pcmcia/smc91c92_cs.c @@ -1616,12 +1616,12 @@ static void set_rx_mode(struct net_device *dev) rx_cfg_setting = RxStripCRC | RxEnable | RxAllMulti; else { if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mc_addr; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(mc_addr, dev) { - u_int position = ether_crc(6, mc_addr->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + u_int position = ether_crc(6, ha->addr); #ifndef final_version /* Verify multicast address. */ - if ((mc_addr->dmi_addr[0] & 1) == 0) + if ((ha->addr[0] & 1) == 0) continue; #endif multicast_table[position >> 29] |= 1 << ((position >> 26) & 7); diff --git a/drivers/net/pcmcia/xirc2ps_cs.c b/drivers/net/pcmcia/xirc2ps_cs.c index 4d1802e457b..656be931207 100644 --- a/drivers/net/pcmcia/xirc2ps_cs.c +++ b/drivers/net/pcmcia/xirc2ps_cs.c @@ -1398,7 +1398,7 @@ static void set_addresses(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; local_info_t *lp = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; struct set_address_info sa_info; int i; @@ -1413,10 +1413,10 @@ static void set_addresses(struct net_device *dev) set_address(&sa_info, dev->dev_addr); i = 0; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if (i++ == 9) break; - set_address(&sa_info, dmi->dmi_addr); + set_address(&sa_info, ha->addr); } while (i++ < 9) set_address(&sa_info, dev->dev_addr); diff --git a/drivers/net/pcnet32.c b/drivers/net/pcnet32.c index 084d78dd163..a2254f749a9 100644 --- a/drivers/net/pcnet32.c +++ b/drivers/net/pcnet32.c @@ -2590,7 +2590,7 @@ static void pcnet32_load_multicast(struct net_device *dev) struct pcnet32_private *lp = netdev_priv(dev); volatile struct pcnet32_init_block *ib = lp->init_block; volatile __le16 *mcast_table = (__le16 *)ib->filter; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned long ioaddr = dev->base_addr; char *addrs; int i; @@ -2611,8 +2611,8 @@ static void pcnet32_load_multicast(struct net_device *dev) ib->filter[1] = 0; /* Add addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* multicast address? */ if (!(*addrs & 1)) diff --git a/drivers/net/ps3_gelic_net.c b/drivers/net/ps3_gelic_net.c index a602da6418c..fed5df9c5ea 100644 --- a/drivers/net/ps3_gelic_net.c +++ b/drivers/net/ps3_gelic_net.c @@ -546,7 +546,7 @@ out: void gelic_net_set_multi(struct net_device *netdev) { struct gelic_card *card = netdev_card(netdev); - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; unsigned int i; uint8_t *p; u64 addr; @@ -580,9 +580,9 @@ void gelic_net_set_multi(struct net_device *netdev) } /* set multicast addresses */ - netdev_for_each_mc_addr(mc, netdev) { + netdev_for_each_mc_addr(ha, netdev) { addr = 0; - p = mc->dmi_addr; + p = ha->addr; for (i = 0; i < ETH_ALEN; i++) { addr <<= 8; addr |= *p++; diff --git a/drivers/net/qlcnic/qlcnic_hw.c b/drivers/net/qlcnic/qlcnic_hw.c index 14c999ab422..9a1daa4ebe2 100644 --- a/drivers/net/qlcnic/qlcnic_hw.c +++ b/drivers/net/qlcnic/qlcnic_hw.c @@ -415,7 +415,7 @@ static int qlcnic_nic_add_mac(struct qlcnic_adapter *adapter, u8 *addr) void qlcnic_set_multi(struct net_device *netdev) { struct qlcnic_adapter *adapter = netdev_priv(netdev); - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; u8 bcast_addr[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }; u32 mode = VPORT_MISS_MODE_DROP; @@ -434,8 +434,8 @@ void qlcnic_set_multi(struct net_device *netdev) } if (!netdev_mc_empty(netdev)) { - netdev_for_each_mc_addr(mc_ptr, netdev) { - qlcnic_nic_add_mac(adapter, mc_ptr->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + qlcnic_nic_add_mac(adapter, ha->addr); } } diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c index fd34f266c0a..76df96813a7 100644 --- a/drivers/net/qlge/qlge_main.c +++ b/drivers/net/qlge/qlge_main.c @@ -4207,7 +4207,7 @@ static struct net_device_stats *qlge_get_stats(struct net_device static void qlge_set_multicast_list(struct net_device *ndev) { struct ql_adapter *qdev = (struct ql_adapter *)netdev_priv(ndev); - struct dev_mc_list *mc_ptr; + struct netdev_hw_addr *ha; int i, status; status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); @@ -4271,8 +4271,8 @@ static void qlge_set_multicast_list(struct net_device *ndev) if (status) goto exit; i = 0; - netdev_for_each_mc_addr(mc_ptr, ndev) { - if (ql_set_mac_addr_reg(qdev, (u8 *) mc_ptr->dmi_addr, + netdev_for_each_mc_addr(ha, ndev) { + if (ql_set_mac_addr_reg(qdev, (u8 *) ha->addr, MAC_ADDR_TYPE_MULTI_MAC, i)) { netif_err(qdev, hw, qdev->ndev, "Failed to loadmulticast address.\n"); diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 15d5373dc8f..f5a0e963e68 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -938,7 +938,7 @@ static void r6040_multicast_list(struct net_device *dev) u16 *adrp; u16 reg; unsigned long flags; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i; /* MAC Address */ @@ -973,8 +973,8 @@ static void r6040_multicast_list(struct net_device *dev) for (i = 0; i < 4; i++) hash_table[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - char *addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + char *addrs = ha->addr; if (!(*addrs & 1)) continue; @@ -994,9 +994,9 @@ static void r6040_multicast_list(struct net_device *dev) } /* Multicast Address 1~4 case */ i = 0; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if (i < MCAST_MAX) { - adrp = (u16 *) dmi->dmi_addr; + adrp = (u16 *) ha->addr; iowrite16(adrp[0], ioaddr + MID_1L + 8 * i); iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index f7ffa5d8ffe..64cd250f642 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -4785,12 +4785,12 @@ static void rtl_set_rx_mode(struct net_device *dev) rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); rx_mode |= AcceptMulticast; } diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index 2eb7f8a0d92..ad5a6a873b2 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -4964,7 +4964,7 @@ static struct net_device_stats *s2io_get_stats(struct net_device *dev) static void s2io_set_multicast(struct net_device *dev) { int i, j, prev_cnt; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct s2io_nic *sp = netdev_priv(dev); struct XENA_dev_config __iomem *bar0 = sp->bar0; u64 val64 = 0, multi_mac = 0x010203040506ULL, mask = @@ -5093,12 +5093,12 @@ static void s2io_set_multicast(struct net_device *dev) /* Create the new Rx filter list and update the same in H/W. */ i = 0; - netdev_for_each_mc_addr(mclist, dev) { - memcpy(sp->usr_addrs[i].addr, mclist->dmi_addr, + netdev_for_each_mc_addr(ha, dev) { + memcpy(sp->usr_addrs[i].addr, ha->addr, ETH_ALEN); mac_addr = 0; for (j = 0; j < ETH_ALEN; j++) { - mac_addr |= mclist->dmi_addr[j]; + mac_addr |= ha->addr[j]; mac_addr <<= 8; } mac_addr >>= 8; diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c index 9944e5d662c..f7de960ca06 100644 --- a/drivers/net/sb1250-mac.c +++ b/drivers/net/sb1250-mac.c @@ -2112,7 +2112,7 @@ static void sbmac_setmulti(struct sbmac_softc *sc) uint64_t reg; void __iomem *port; int idx; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct net_device *dev = sc->sbm_dev; /* @@ -2161,10 +2161,10 @@ static void sbmac_setmulti(struct sbmac_softc *sc) * XXX if the table overflows */ idx = 1; /* skip station address */ - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { if (idx == MAC_ADDR_COUNT) break; - reg = sbmac_addr2reg(mclist->dmi_addr); + reg = sbmac_addr2reg(ha->addr); port = sc->sbm_base + R_MAC_ADDR_BASE+(idx * sizeof(uint64_t)); __raw_writeq(reg, port); idx++; diff --git a/drivers/net/sc92031.c b/drivers/net/sc92031.c index d87c4787fff..1b326058893 100644 --- a/drivers/net/sc92031.c +++ b/drivers/net/sc92031.c @@ -433,13 +433,13 @@ static void _sc92031_set_mar(struct net_device *dev) (dev->flags & IFF_ALLMULTI)) mar0 = mar1 = 0xffffffff; else if (dev->flags & IFF_MULTICAST) { - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(mc_list, dev) { + netdev_for_each_mc_addr(ha, dev) { u32 crc; unsigned bit = 0; - crc = ~ether_crc(ETH_ALEN, mc_list->dmi_addr); + crc = ~ether_crc(ETH_ALEN, ha->addr); crc >>= 24; if (crc & 0x01) bit |= 0x02; diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index 88f2fb193ab..e07b82b266d 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -1602,7 +1602,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) static void efx_set_multicast_list(struct net_device *net_dev) { struct efx_nic *efx = netdev_priv(net_dev); - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; union efx_multicast_hash *mc_hash = &efx->multicast_hash; u32 crc; int bit; @@ -1614,8 +1614,8 @@ static void efx_set_multicast_list(struct net_device *net_dev) memset(mc_hash, 0xff, sizeof(*mc_hash)); } else { memset(mc_hash, 0x00, sizeof(*mc_hash)); - netdev_for_each_mc_addr(mc_list, net_dev) { - crc = ether_crc_le(ETH_ALEN, mc_list->dmi_addr); + netdev_for_each_mc_addr(ha, net_dev) { + crc = ether_crc_le(ETH_ALEN, ha->addr); bit = crc & (EFX_MCAST_HASH_ENTRIES - 1); set_bit_le(bit, mc_hash->byte); } diff --git a/drivers/net/sis190.c b/drivers/net/sis190.c index 760d9e83a46..6a05b93ae6c 100644 --- a/drivers/net/sis190.c +++ b/drivers/net/sis190.c @@ -848,13 +848,13 @@ static void sis190_set_rx_mode(struct net_device *dev) rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0xffffffff; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { int bit_nr = - ether_crc(ETH_ALEN, mclist->dmi_addr) & 0x3f; + ether_crc(ETH_ALEN, ha->addr) & 0x3f; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); rx_mode |= AcceptMulticast; } diff --git a/drivers/net/sis900.c b/drivers/net/sis900.c index bc7ff411aad..6293592635b 100644 --- a/drivers/net/sis900.c +++ b/drivers/net/sis900.c @@ -2298,12 +2298,14 @@ static void set_rx_mode(struct net_device *net_dev) /* Accept Broadcast packet, destination address matchs our * MAC address, use Receive Filter to reject unwanted MCAST * packets */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; rx_mode = RFAAB; - netdev_for_each_mc_addr(mclist, net_dev) { - unsigned int bit_nr = - sis900_mcast_bitnr(mclist->dmi_addr, sis_priv->chipset_rev); + netdev_for_each_mc_addr(ha, net_dev) { + unsigned int bit_nr; + + bit_nr = sis900_mcast_bitnr(ha->addr, + sis_priv->chipset_rev); mc_filter[bit_nr >> 4] |= (1 << (bit_nr & 0xf)); } } diff --git a/drivers/net/skfp/skfddi.c b/drivers/net/skfp/skfddi.c index 1921a54ea99..7e5b9f310fb 100644 --- a/drivers/net/skfp/skfddi.c +++ b/drivers/net/skfp/skfddi.c @@ -852,7 +852,7 @@ static void skfp_ctl_set_multicast_list(struct net_device *dev) static void skfp_ctl_set_multicast_list_wo_lock(struct net_device *dev) { struct s_smc *smc = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; /* Enable promiscuous mode, if necessary */ if (dev->flags & IFF_PROMISC) { @@ -876,13 +876,13 @@ static void skfp_ctl_set_multicast_list_wo_lock(struct net_device *dev) /* use exact filtering */ // point to first multicast addr - netdev_for_each_mc_addr(dmi, dev) { - mac_add_multicast(smc, - (struct fddi_addr *)dmi->dmi_addr, - 1); + netdev_for_each_mc_addr(ha, dev) { + mac_add_multicast(smc, + (struct fddi_addr *)ha->addr, + 1); pr_debug(KERN_INFO "ENABLE MC ADDRESS: %pMF\n", - dmi->dmi_addr); + ha->addr); } } else { // more MC addresses than HW supports diff --git a/drivers/net/skge.c b/drivers/net/skge.c index bd8c5e8413b..de5ef3877ba 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -2917,7 +2917,7 @@ static void genesis_set_multicast(struct net_device *dev) struct skge_port *skge = netdev_priv(dev); struct skge_hw *hw = skge->hw; int port = skge->port; - struct dev_mc_list *list; + struct netdev_hw_addr *ha; u32 mode; u8 filter[8]; @@ -2937,8 +2937,8 @@ static void genesis_set_multicast(struct net_device *dev) skge->flow_status == FLOW_STAT_SYMMETRIC) genesis_add_filter(filter, pause_mc_addr); - netdev_for_each_mc_addr(list, dev) - genesis_add_filter(filter, list->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + genesis_add_filter(filter, ha->addr); } xm_write32(hw, port, XM_MODE, mode); @@ -2956,7 +2956,7 @@ static void yukon_set_multicast(struct net_device *dev) struct skge_port *skge = netdev_priv(dev); struct skge_hw *hw = skge->hw; int port = skge->port; - struct dev_mc_list *list; + struct netdev_hw_addr *ha; int rx_pause = (skge->flow_status == FLOW_STAT_REM_SEND || skge->flow_status == FLOW_STAT_SYMMETRIC); u16 reg; @@ -2979,8 +2979,8 @@ static void yukon_set_multicast(struct net_device *dev) if (rx_pause) yukon_add_filter(filter, pause_mc_addr); - netdev_for_each_mc_addr(list, dev) - yukon_add_filter(filter, list->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + yukon_add_filter(filter, ha->addr); } diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index f1c0ec308bf..5b97edb7a35 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -3627,7 +3627,7 @@ static void sky2_set_multicast(struct net_device *dev) struct sky2_port *sky2 = netdev_priv(dev); struct sky2_hw *hw = sky2->hw; unsigned port = sky2->port; - struct dev_mc_list *list; + struct netdev_hw_addr *ha; u16 reg; u8 filter[8]; int rx_pause; @@ -3651,8 +3651,8 @@ static void sky2_set_multicast(struct net_device *dev) if (rx_pause) sky2_add_filter(filter, pause_mc_addr); - netdev_for_each_mc_addr(list, dev) - sky2_add_filter(filter, list->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + sky2_add_filter(filter, ha->addr); } gma_write16(hw, port, GM_MC_ADDR_H1, diff --git a/drivers/net/smc911x.c b/drivers/net/smc911x.c index 0f97b5af91e..6278734c735 100644 --- a/drivers/net/smc911x.c +++ b/drivers/net/smc911x.c @@ -1341,7 +1341,7 @@ static void smc911x_set_multicast_list(struct net_device *dev) * within that register. */ else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *cur_addr; + struct netdev_hw_addr *ha; /* Set the Hash perfec mode */ mcr |= MAC_CR_HPFILT_; @@ -1349,19 +1349,16 @@ static void smc911x_set_multicast_list(struct net_device *dev) /* start with a table of all zeros: reject all */ memset(multicast_table, 0, sizeof(multicast_table)); - netdev_for_each_mc_addr(cur_addr, dev) { + netdev_for_each_mc_addr(ha, dev) { u32 position; - /* do we have a pointer here? */ - if (!cur_addr) - break; /* make sure this is a multicast address - shouldn't this be a given if we have it here ? */ - if (!(*cur_addr->dmi_addr & 1)) - continue; + if (!(*ha->addr & 1)) + continue; /* upper 6 bits are used as hash index */ - position = ether_crc(ETH_ALEN, cur_addr->dmi_addr)>>26; + position = ether_crc(ETH_ALEN, ha->addr)>>26; multicast_table[position>>5] |= 1 << (position&0x1f); } diff --git a/drivers/net/smc9194.c b/drivers/net/smc9194.c index ee1487791d5..9e5e9e792e8 100644 --- a/drivers/net/smc9194.c +++ b/drivers/net/smc9194.c @@ -417,7 +417,7 @@ static void smc_shutdown( int ioaddr ) /* - . Function: smc_setmulticast( int ioaddr, int count, dev_mc_list * adds ) + . Function: smc_setmulticast( int ioaddr, struct net_device *dev ) . Purpose: . This sets the internal hardware table to filter out unwanted multicast . packets before they take up memory. @@ -438,26 +438,23 @@ static void smc_setmulticast(int ioaddr, struct net_device *dev) { int i; unsigned char multicast_table[ 8 ]; - struct dev_mc_list *cur_addr; + struct netdev_hw_addr *ha; /* table for flipping the order of 3 bits */ unsigned char invert3[] = { 0, 4, 2, 6, 1, 5, 3, 7 }; /* start with a table of all zeros: reject all */ memset( multicast_table, 0, sizeof( multicast_table ) ); - netdev_for_each_mc_addr(cur_addr, dev) { + netdev_for_each_mc_addr(ha, dev) { int position; - /* do we have a pointer here? */ - if ( !cur_addr ) - break; /* make sure this is a multicast address - shouldn't this be a given if we have it here ? */ - if ( !( *cur_addr->dmi_addr & 1 ) ) + if (!(*ha->addr & 1)) continue; /* only use the low order bits */ - position = ether_crc_le(6, cur_addr->dmi_addr) & 0x3f; + position = ether_crc_le(6, ha->addr) & 0x3f; /* do some messy swapping to put the bit in the right spot */ multicast_table[invert3[position&7]] |= diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index 2e8133809dc..20c75657763 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -1413,7 +1413,7 @@ static void smc_set_multicast_list(struct net_device *dev) * within that register. */ else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *cur_addr; + struct netdev_hw_addr *ha; /* table for flipping the order of 3 bits */ static const unsigned char invert3[] = {0, 4, 2, 6, 1, 5, 3, 7}; @@ -1421,16 +1421,16 @@ static void smc_set_multicast_list(struct net_device *dev) /* start with a table of all zeros: reject all */ memset(multicast_table, 0, sizeof(multicast_table)); - netdev_for_each_mc_addr(cur_addr, dev) { + netdev_for_each_mc_addr(ha, dev) { int position; /* make sure this is a multicast address - shouldn't this be a given if we have it here ? */ - if (!(*cur_addr->dmi_addr & 1)) + if (!(*ha->addr & 1)) continue; /* only use the low order bits */ - position = crc32_le(~0, cur_addr->dmi_addr, 6) & 0x3f; + position = crc32_le(~0, ha->addr, 6) & 0x3f; /* do some messy swapping to put the bit in the right spot */ multicast_table[invert3[position&7]] |= diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index 4fd1d8b3878..d6e3a12d65d 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -1383,13 +1383,13 @@ static void smsc911x_set_multicast_list(struct net_device *dev) /* Enabling specific multicast addresses */ unsigned int hash_high = 0; unsigned int hash_low = 0; - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; pdata->set_bits_mask = MAC_CR_HPFILT_; pdata->clear_bits_mask = (MAC_CR_PRMS_ | MAC_CR_MCPAS_); - netdev_for_each_mc_addr(mc_list, dev) { - unsigned int bitnum = smsc911x_hash(mc_list->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + unsigned int bitnum = smsc911x_hash(ha->addr); unsigned int mask = 0x01 << (bitnum & 0x1F); if (bitnum & 0x20) diff --git a/drivers/net/smsc9420.c b/drivers/net/smsc9420.c index 34fa10d8ad4..5409ec1a5fd 100644 --- a/drivers/net/smsc9420.c +++ b/drivers/net/smsc9420.c @@ -1063,12 +1063,12 @@ static void smsc9420_set_multicast_list(struct net_device *dev) mac_cr |= MAC_CR_MCPAS_; mac_cr &= (~MAC_CR_HPFILT_); } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; u32 hash_lo = 0, hash_hi = 0; smsc_dbg(HW, "Multicast filter enabled"); - netdev_for_each_mc_addr(mc_list, dev) { - u32 bit_num = smsc9420_hash(mc_list->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + u32 bit_num = smsc9420_hash(ha->addr); u32 mask = 1 << (bit_num & 0x1F); if (bit_num & 0x20) diff --git a/drivers/net/sonic.c b/drivers/net/sonic.c index 287c251075e..e5d67327d70 100644 --- a/drivers/net/sonic.c +++ b/drivers/net/sonic.c @@ -531,7 +531,7 @@ static void sonic_multicast_list(struct net_device *dev) { struct sonic_local *lp = netdev_priv(dev); unsigned int rcr; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char *addr; int i; @@ -550,8 +550,8 @@ static void sonic_multicast_list(struct net_device *dev) netdev_mc_count(dev)); sonic_set_cam_enable(dev, 1); /* always enable our own address */ i = 1; - netdev_for_each_mc_addr(dmi, dev) { - addr = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addr = ha->addr; sonic_cda_put(dev, i, SONIC_CD_CAP0, addr[1] << 8 | addr[0]); sonic_cda_put(dev, i, SONIC_CD_CAP1, addr[3] << 8 | addr[2]); sonic_cda_put(dev, i, SONIC_CD_CAP2, addr[5] << 8 | addr[4]); diff --git a/drivers/net/spider_net.c b/drivers/net/spider_net.c index 5ba9d989f8f..c04c8f9a2d9 100644 --- a/drivers/net/spider_net.c +++ b/drivers/net/spider_net.c @@ -625,7 +625,7 @@ spider_net_get_multicast_hash(struct net_device *netdev, __u8 *addr) static void spider_net_set_multi(struct net_device *netdev) { - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; u8 hash; int i; u32 reg; @@ -646,8 +646,8 @@ spider_net_set_multi(struct net_device *netdev) hash = spider_net_get_multicast_hash(netdev, netdev->broadcast); */ set_bit(0xfd, bitmask); - netdev_for_each_mc_addr(mc, netdev) { - hash = spider_net_get_multicast_hash(netdev, mc->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + hash = spider_net_get_multicast_hash(netdev, ha->addr); set_bit(hash, bitmask); } diff --git a/drivers/net/starfire.c b/drivers/net/starfire.c index 6dfa6989901..8a6d27cdc0b 100644 --- a/drivers/net/starfire.c +++ b/drivers/net/starfire.c @@ -1766,7 +1766,7 @@ static void set_rx_mode(struct net_device *dev) struct netdev_private *np = netdev_priv(dev); void __iomem *ioaddr = np->base; u32 rx_mode = MinVLANPrio; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i; #ifdef VLAN_SUPPORT @@ -1804,8 +1804,8 @@ static void set_rx_mode(struct net_device *dev) /* Use the 16 element perfect filter, skip first two entries. */ void __iomem *filter_addr = ioaddr + PerfFilterTable + 2 * 16; __be16 *eaddrs; - netdev_for_each_mc_addr(mclist, dev) { - eaddrs = (__be16 *)mclist->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + eaddrs = (__be16 *) ha->addr; writew(be16_to_cpu(eaddrs[2]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 8; @@ -1825,10 +1825,10 @@ static void set_rx_mode(struct net_device *dev) __le16 mc_filter[32] __attribute__ ((aligned(sizeof(long)))); /* Multicast hash filter */ memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { /* The chip uses the upper 9 CRC bits as index into the hash table */ - int bit_nr = ether_crc_le(ETH_ALEN, mclist->dmi_addr) >> 23; + int bit_nr = ether_crc_le(ETH_ALEN, ha->addr) >> 23; __le32 *fptr = (__le32 *) &mc_filter[(bit_nr >> 4) & ~1]; *fptr |= cpu_to_le32(1 << (bit_nr & 31)); diff --git a/drivers/net/stmmac/dwmac100.c b/drivers/net/stmmac/dwmac100.c index a183de29c39..c0a1c9df3ac 100644 --- a/drivers/net/stmmac/dwmac100.c +++ b/drivers/net/stmmac/dwmac100.c @@ -316,7 +316,7 @@ static void dwmac100_set_filter(struct net_device *dev) MAC_CONTROL_HO | MAC_CONTROL_HP); } else { u32 mc_filter[2]; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; /* Perfect filter mode for physical address and Hash filter for multicast */ @@ -325,11 +325,11 @@ static void dwmac100_set_filter(struct net_device *dev) MAC_CONTROL_IF | MAC_CONTROL_HO); memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { /* The upper 6 bits of the calculated CRC are used to * index the contens of the hash table */ int bit_nr = - ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + ether_crc(ETH_ALEN, ha->addr) >> 26; /* The most significant bit determines the register to * use (H/L) while the other 5 bits determine the bit * within the register. */ diff --git a/drivers/net/stmmac/dwmac1000_core.c b/drivers/net/stmmac/dwmac1000_core.c index a6538ae4694..bf73fda6adf 100644 --- a/drivers/net/stmmac/dwmac1000_core.c +++ b/drivers/net/stmmac/dwmac1000_core.c @@ -94,17 +94,17 @@ static void dwmac1000_set_filter(struct net_device *dev) writel(0xffffffff, ioaddr + GMAC_HASH_LOW); } else if (!netdev_mc_empty(dev)) { u32 mc_filter[2]; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; /* Hash filter for multicast */ value = GMAC_FRAME_FILTER_HMC; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { /* The upper 6 bits of the calculated CRC are used to index the contens of the hash table */ int bit_nr = - bitrev32(~crc32_le(~0, mclist->dmi_addr, 6)) >> 26; + bitrev32(~crc32_le(~0, ha->addr, 6)) >> 26; /* The most significant bit determines the register to * use (H/L) while the other 5 bits determine the bit * within the register. */ diff --git a/drivers/net/sun3_82586.c b/drivers/net/sun3_82586.c index 2f6a760e5f2..2cfa065c39c 100644 --- a/drivers/net/sun3_82586.c +++ b/drivers/net/sun3_82586.c @@ -413,7 +413,7 @@ static int init586(struct net_device *dev) volatile struct iasetup_cmd_struct *ias_cmd; volatile struct tdr_cmd_struct *tdr_cmd; volatile struct mcsetup_cmd_struct *mc_cmd; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int num_addrs=netdev_mc_count(dev); ptr = (void *) ((char *)p->scb + sizeof(struct scb_struct)); @@ -537,9 +537,9 @@ static int init586(struct net_device *dev) mc_cmd->mc_cnt = swab16(num_addrs * 6); i = 0; - netdev_for_each_mc_addr(dmi, dev) + netdev_for_each_mc_addr(ha, dev) memcpy((char *) mc_cmd->mc_list[i++], - dmi->dmi_addr, ETH_ALEN); + ha->addr, ETH_ALEN); p->scb->cbl_offset = make16(mc_cmd); p->scb->cmd_cuc = CUC_START; diff --git a/drivers/net/sunbmac.c b/drivers/net/sunbmac.c index a0bd361d5ec..4dd159b4116 100644 --- a/drivers/net/sunbmac.c +++ b/drivers/net/sunbmac.c @@ -999,7 +999,7 @@ static void bigmac_set_multicast(struct net_device *dev) { struct bigmac *bp = netdev_priv(dev); void __iomem *bregs = bp->bregs; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; int i; u32 tmp, crc; @@ -1028,8 +1028,8 @@ static void bigmac_set_multicast(struct net_device *dev) for (i = 0; i < 4; i++) hash_table[i] = 0; - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if (!(*addrs & 1)) continue; diff --git a/drivers/net/sundance.c b/drivers/net/sundance.c index a855934dfc3..47e8cce10d1 100644 --- a/drivers/net/sundance.c +++ b/drivers/net/sundance.c @@ -1523,13 +1523,13 @@ static void set_rx_mode(struct net_device *dev) memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int bit; int index; int crc; memset (mc_filter, 0, sizeof (mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - crc = ether_crc_le (ETH_ALEN, mclist->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(ETH_ALEN, ha->addr); for (index=0, bit=0; bit < 6; bit++, crc <<= 1) if (crc & 0x80000000) index |= 1 << bit; mc_filter[index/16] |= (1 << (index % 16)); diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 70196bc5fe6..58a27541ae3 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -1846,12 +1846,12 @@ static u32 gem_setup_multicast(struct gem *gp) } else { u16 hash_table[16]; u32 crc; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(dmi, gp->dev) { - char *addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, gp->dev) { + char *addrs = ha->addr; if (!(*addrs & 1)) continue; diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c index b17dbb11bd6..20deb14e98f 100644 --- a/drivers/net/sunhme.c +++ b/drivers/net/sunhme.c @@ -1523,13 +1523,13 @@ static int happy_meal_init(struct happy_meal *hp) hme_write32(hp, bregs + BMAC_HTABLE3, 0xffff); } else if ((hp->dev->flags & IFF_PROMISC) == 0) { u16 hash_table[4]; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(dmi, hp->dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, hp->dev) { + addrs = ha->addr; if (!(*addrs & 1)) continue; @@ -2362,7 +2362,7 @@ static void happy_meal_set_multicast(struct net_device *dev) { struct happy_meal *hp = netdev_priv(dev); void __iomem *bregs = hp->bigmacregs; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; @@ -2380,8 +2380,8 @@ static void happy_meal_set_multicast(struct net_device *dev) u16 hash_table[4]; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if (!(*addrs & 1)) continue; diff --git a/drivers/net/sunlance.c b/drivers/net/sunlance.c index d7c73f478ef..674570584bd 100644 --- a/drivers/net/sunlance.c +++ b/drivers/net/sunlance.c @@ -1170,7 +1170,7 @@ static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev) static void lance_load_multicast(struct net_device *dev) { struct lance_private *lp = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; char *addrs; u32 crc; u32 val; @@ -1195,8 +1195,8 @@ static void lance_load_multicast(struct net_device *dev) return; /* Add addresses */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; /* multicast address? */ if (!(*addrs & 1)) diff --git a/drivers/net/sunqe.c b/drivers/net/sunqe.c index be637dce944..239f0977219 100644 --- a/drivers/net/sunqe.c +++ b/drivers/net/sunqe.c @@ -627,7 +627,7 @@ static int qe_start_xmit(struct sk_buff *skb, struct net_device *dev) static void qe_set_multicast(struct net_device *dev) { struct sunqe *qep = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u8 new_mconfig = qep->mconfig; char *addrs; int i; @@ -651,8 +651,8 @@ static void qe_set_multicast(struct net_device *dev) u8 *hbytes = (unsigned char *) &hash_table[0]; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if (!(*addrs & 1)) continue; diff --git a/drivers/net/sunvnet.c b/drivers/net/sunvnet.c index 6b1b7cea7f6..6cf8b06be5c 100644 --- a/drivers/net/sunvnet.c +++ b/drivers/net/sunvnet.c @@ -763,12 +763,12 @@ static struct vnet_mcast_entry *__vnet_mc_find(struct vnet *vp, u8 *addr) static void __update_mc_list(struct vnet *vp, struct net_device *dev) { - struct dev_addr_list *p; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(p, dev) { + netdev_for_each_mc_addr(ha, dev) { struct vnet_mcast_entry *m; - m = __vnet_mc_find(vp, p->dmi_addr); + m = __vnet_mc_find(vp, ha->addr); if (m) { m->hit = 1; continue; @@ -778,7 +778,7 @@ static void __update_mc_list(struct vnet *vp, struct net_device *dev) m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) continue; - memcpy(m->addr, p->dmi_addr, ETH_ALEN); + memcpy(m->addr, ha->addr, ETH_ALEN); m->hit = 1; m->next = vp->mcast_list; diff --git a/drivers/net/tc35815.c b/drivers/net/tc35815.c index 49bd84c0d58..36149ddace4 100644 --- a/drivers/net/tc35815.c +++ b/drivers/net/tc35815.c @@ -1954,16 +1954,16 @@ tc35815_set_multicast_list(struct net_device *dev) /* Disable promiscuous mode, use normal mode. */ tc_writel(CAM_CompEn | CAM_BroadAcc | CAM_GroupAcc, &tr->CAM_Ctl); } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *cur_addr; + struct netdev_hw_addr *ha; int i; int ena_bits = CAM_Ena_Bit(CAM_ENTRY_SOURCE); tc_writel(0, &tr->CAM_Ctl); /* Walk the address list, and load the filter */ i = 0; - netdev_for_each_mc_addr(cur_addr, dev) { + netdev_for_each_mc_addr(ha, dev) { /* entry 0,1 is reserved. */ - tc35815_set_cam_entry(dev, i + 2, cur_addr->dmi_addr); + tc35815_set_cam_entry(dev, i + 2, ha->addr); ena_bits |= CAM_Ena_Bit(i + 2); i++; } diff --git a/drivers/net/tehuti.c b/drivers/net/tehuti.c index 068a47174fc..a38aede5c8d 100644 --- a/drivers/net/tehuti.c +++ b/drivers/net/tehuti.c @@ -808,7 +808,7 @@ static void bdx_setmulti(struct net_device *ndev) WRITE_REG(priv, regRX_MCST_HASH0 + i * 4, ~0); } else if (!netdev_mc_empty(ndev)) { u8 hash; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u32 reg, val; /* set IMF to deny all multicast frames */ @@ -825,10 +825,10 @@ static void bdx_setmulti(struct net_device *ndev) * into RX_MAC_MCST regs. we skip this phase now and accept ALL * multicast frames throu IMF */ /* accept the rest of addresses throu IMF */ - netdev_for_each_mc_addr(mclist, ndev) { + netdev_for_each_mc_addr(ha, ndev) { hash = 0; for (i = 0; i < ETH_ALEN; i++) - hash ^= mclist->dmi_addr[i]; + hash ^= ha->addr[i]; reg = regRX_MCST_HASH0 + ((hash >> 5) << 2); val = READ_REG(priv, reg); val |= (1 << (hash % 32)); diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 22cf1c446de..aff11f84f52 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -9457,14 +9457,14 @@ static void __tg3_set_rx_mode(struct net_device *dev) tg3_set_multi (tp, 0); } else { /* Accept one or more multicast(s). */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u32 mc_filter[4] = { 0, }; u32 regidx; u32 bit; u32 crc; - netdev_for_each_mc_addr(mclist, dev) { - crc = calc_crc (mclist->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) { + crc = calc_crc(ha->addr, ETH_ALEN); bit = ~crc & 0x7f; regidx = (bit & 0x60) >> 5; bit &= 0x1f; diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c index 05ea30a94e8..8ffec22b74b 100644 --- a/drivers/net/tlan.c +++ b/drivers/net/tlan.c @@ -1314,7 +1314,7 @@ static struct net_device_stats *TLan_GetStats( struct net_device *dev ) static void TLan_SetMulticastList( struct net_device *dev ) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u32 hash1 = 0; u32 hash2 = 0; int i; @@ -1336,12 +1336,12 @@ static void TLan_SetMulticastList( struct net_device *dev ) TLan_DioWrite32( dev->base_addr, TLAN_HASH_2, 0xFFFFFFFF ); } else { i = 0; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if ( i < 3 ) { TLan_SetMac( dev, i + 1, - (char *) &dmi->dmi_addr ); + (char *) &ha->addr); } else { - offset = TLan_HashFunc( (u8 *) &dmi->dmi_addr ); + offset = TLan_HashFunc((u8 *)&ha->addr); if ( offset < 32 ) hash1 |= ( 1 << offset ); else diff --git a/drivers/net/tokenring/3c359.c b/drivers/net/tokenring/3c359.c index 8c54d89e60d..4673e38c52a 100644 --- a/drivers/net/tokenring/3c359.c +++ b/drivers/net/tokenring/3c359.c @@ -1390,7 +1390,7 @@ static int xl_close(struct net_device *dev) static void xl_set_rx_mode(struct net_device *dev) { struct xl_private *xl_priv = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char dev_mc_address[4] ; u16 options ; @@ -1407,11 +1407,11 @@ static void xl_set_rx_mode(struct net_device *dev) dev_mc_address[0] = dev_mc_address[1] = dev_mc_address[2] = dev_mc_address[3] = 0 ; - netdev_for_each_mc_addr(dmi, dev) { - dev_mc_address[0] |= dmi->dmi_addr[2] ; - dev_mc_address[1] |= dmi->dmi_addr[3] ; - dev_mc_address[2] |= dmi->dmi_addr[4] ; - dev_mc_address[3] |= dmi->dmi_addr[5] ; + netdev_for_each_mc_addr(ha, dev) { + dev_mc_address[0] |= ha->addr[2]; + dev_mc_address[1] |= ha->addr[3]; + dev_mc_address[2] |= ha->addr[4]; + dev_mc_address[3] |= ha->addr[5]; } if (memcmp(xl_priv->xl_functional_addr,dev_mc_address,4) != 0) { /* Options have changed, run the command */ diff --git a/drivers/net/tokenring/ibmtr.c b/drivers/net/tokenring/ibmtr.c index 1a0967246e2..eebdaae2432 100644 --- a/drivers/net/tokenring/ibmtr.c +++ b/drivers/net/tokenring/ibmtr.c @@ -986,7 +986,7 @@ static void open_sap(unsigned char type, struct net_device *dev) static void tok_set_multicast_list(struct net_device *dev) { struct tok_info *ti = netdev_priv(dev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; unsigned char address[4]; int i; @@ -995,11 +995,11 @@ static void tok_set_multicast_list(struct net_device *dev) /*BMS ifconfig tr down or hot unplug a PCMCIA card ??hownowbrowncow*/ if (/*BMSHELPdev->start == 0 ||*/ ti->open_status != OPEN) return; address[0] = address[1] = address[2] = address[3] = 0; - netdev_for_each_mc_addr(mclist, dev) { - address[0] |= mclist->dmi_addr[2]; - address[1] |= mclist->dmi_addr[3]; - address[2] |= mclist->dmi_addr[4]; - address[3] |= mclist->dmi_addr[5]; + netdev_for_each_mc_addr(ha, dev) { + address[0] |= ha->addr[2]; + address[1] |= ha->addr[3]; + address[2] |= ha->addr[4]; + address[3] |= ha->addr[5]; } SET_PAGE(ti->srb_page); for (i = 0; i < sizeof(struct srb_set_funct_addr); i++) diff --git a/drivers/net/tokenring/lanstreamer.c b/drivers/net/tokenring/lanstreamer.c index 01c780f25e9..88c893100c2 100644 --- a/drivers/net/tokenring/lanstreamer.c +++ b/drivers/net/tokenring/lanstreamer.c @@ -1266,7 +1266,7 @@ static void streamer_set_rx_mode(struct net_device *dev) netdev_priv(dev); __u8 __iomem *streamer_mmio = streamer_priv->streamer_mmio; __u8 options = 0; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char dev_mc_address[5]; writel(streamer_priv->srb, streamer_mmio + LAPA); @@ -1302,11 +1302,11 @@ static void streamer_set_rx_mode(struct net_device *dev) writel(streamer_priv->srb,streamer_mmio+LAPA); dev_mc_address[0] = dev_mc_address[1] = dev_mc_address[2] = dev_mc_address[3] = 0 ; - netdev_for_each_mc_addr(dmi, dev) { - dev_mc_address[0] |= dmi->dmi_addr[2] ; - dev_mc_address[1] |= dmi->dmi_addr[3] ; - dev_mc_address[2] |= dmi->dmi_addr[4] ; - dev_mc_address[3] |= dmi->dmi_addr[5] ; + netdev_for_each_mc_addr(ha, dev) { + dev_mc_address[0] |= ha->addr[2]; + dev_mc_address[1] |= ha->addr[3]; + dev_mc_address[2] |= ha->addr[4]; + dev_mc_address[3] |= ha->addr[5]; } writew(htons(SRB_SET_FUNC_ADDRESS << 8),streamer_mmio+LAPDINC); diff --git a/drivers/net/tokenring/olympic.c b/drivers/net/tokenring/olympic.c index 3decaf4b6cf..3d2fbe60b46 100644 --- a/drivers/net/tokenring/olympic.c +++ b/drivers/net/tokenring/olympic.c @@ -1139,7 +1139,7 @@ static void olympic_set_rx_mode(struct net_device *dev) u8 __iomem *olympic_mmio = olympic_priv->olympic_mmio ; u8 options = 0; u8 __iomem *srb; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; unsigned char dev_mc_address[4] ; writel(olympic_priv->srb,olympic_mmio+LAPA); @@ -1177,11 +1177,11 @@ static void olympic_set_rx_mode(struct net_device *dev) dev_mc_address[0] = dev_mc_address[1] = dev_mc_address[2] = dev_mc_address[3] = 0 ; - netdev_for_each_mc_addr(dmi, dev) { - dev_mc_address[0] |= dmi->dmi_addr[2] ; - dev_mc_address[1] |= dmi->dmi_addr[3] ; - dev_mc_address[2] |= dmi->dmi_addr[4] ; - dev_mc_address[3] |= dmi->dmi_addr[5] ; + netdev_for_each_mc_addr(ha, dev) { + dev_mc_address[0] |= ha->addr[2]; + dev_mc_address[1] |= ha->addr[3]; + dev_mc_address[2] |= ha->addr[4]; + dev_mc_address[3] |= ha->addr[5]; } writeb(SRB_SET_FUNC_ADDRESS,srb+0); diff --git a/drivers/net/tokenring/tms380tr.c b/drivers/net/tokenring/tms380tr.c index b545e20d289..9fa2c36ff90 100644 --- a/drivers/net/tokenring/tms380tr.c +++ b/drivers/net/tokenring/tms380tr.c @@ -1212,17 +1212,17 @@ static void tms380tr_set_multicast_list(struct net_device *dev) } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { ((char *)(&tp->ocpl.FunctAddr))[0] |= - mclist->dmi_addr[2]; + ha->addr[2]; ((char *)(&tp->ocpl.FunctAddr))[1] |= - mclist->dmi_addr[3]; + ha->addr[3]; ((char *)(&tp->ocpl.FunctAddr))[2] |= - mclist->dmi_addr[4]; + ha->addr[4]; ((char *)(&tp->ocpl.FunctAddr))[3] |= - mclist->dmi_addr[5]; + ha->addr[5]; } } tms380tr_exec_cmd(dev, OC_SET_FUNCT_ADDR); diff --git a/drivers/net/tsi108_eth.c b/drivers/net/tsi108_eth.c index 80333a4d328..1366541c30a 100644 --- a/drivers/net/tsi108_eth.c +++ b/drivers/net/tsi108_eth.c @@ -1186,15 +1186,15 @@ static void tsi108_set_rx_mode(struct net_device *dev) if (dev->flags & IFF_ALLMULTI || !netdev_mc_empty(dev)) { int i; - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; rxcfg |= TSI108_EC_RXCFG_MFE | TSI108_EC_RXCFG_MC_HASH; memset(data->mc_hash, 0, sizeof(data->mc_hash)); - netdev_for_each_mc_addr(mc, dev) { + netdev_for_each_mc_addr(ha, dev) { u32 hash, crc; - crc = ether_crc(6, mc->dmi_addr); + crc = ether_crc(6, ha->addr); hash = crc >> 23; __set_bit(hash, &data->mc_hash[0]); } diff --git a/drivers/net/tulip/de2104x.c b/drivers/net/tulip/de2104x.c index cb429723b2c..a68b9176462 100644 --- a/drivers/net/tulip/de2104x.c +++ b/drivers/net/tulip/de2104x.c @@ -670,15 +670,15 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) { struct de_private *de = netdev_priv(dev); u16 hash_table[32]; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i; u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); set_bit_le(255, hash_table); /* Broadcast entry */ /* This should work on big-endian machines as well. */ - netdev_for_each_mc_addr(mclist, dev) { - int index = ether_crc_le(ETH_ALEN, mclist->dmi_addr) & 0x1ff; + netdev_for_each_mc_addr(ha, dev) { + int index = ether_crc_le(ETH_ALEN, ha->addr) & 0x1ff; set_bit_le(index, hash_table); } @@ -699,13 +699,13 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct de_private *de = netdev_priv(dev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ - netdev_for_each_mc_addr(mclist, dev) { - eaddrs = (u16 *)mclist->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + eaddrs = (u16 *) ha->addr; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c index 55ade8949a6..cac4bcc8318 100644 --- a/drivers/net/tulip/de4x5.c +++ b/drivers/net/tulip/de4x5.c @@ -1951,7 +1951,7 @@ static void SetMulticastFilter(struct net_device *dev) { struct de4x5_private *lp = netdev_priv(dev); - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; u_long iobase = dev->base_addr; int i, bit, byte; u16 hashcode; @@ -1966,8 +1966,8 @@ SetMulticastFilter(struct net_device *dev) if ((dev->flags & IFF_ALLMULTI) || (netdev_mc_count(dev) > 14)) { omr |= OMR_PM; /* Pass all multicasts */ } else if (lp->setup_f == HASH_PERF) { /* Hash Filtering */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; if ((*addrs & 0x01) == 1) { /* multicast address? */ crc = ether_crc_le(ETH_ALEN, addrs); hashcode = crc & HASH_BITS; /* hashcode is 9 LSb of CRC */ @@ -1983,8 +1983,8 @@ SetMulticastFilter(struct net_device *dev) } } } else { /* Perfect filtering */ - netdev_for_each_mc_addr(dmi, dev) { - addrs = dmi->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrs = ha->addr; for (i=0; ibase_addr+0xc0; /* ID Table */ u32 hash_val; @@ -1478,8 +1478,8 @@ static void dm9132_id_table(struct DEVICE *dev) hash_table[3] = 0x8000; /* the multicast address in Hash Table : 64 bits */ - netdev_for_each_mc_addr(mcptr, dev) { - hash_val = cal_CRC((char *) mcptr->dmi_addr, 6, 0) & 0x3f; + netdev_for_each_mc_addr(ha, dev) { + hash_val = cal_CRC((char *) ha->addr, 6, 0) & 0x3f; hash_table[hash_val / 16] |= (u16) 1 << (hash_val % 16); } @@ -1497,7 +1497,7 @@ static void dm9132_id_table(struct DEVICE *dev) static void send_filter_frame(struct DEVICE *dev) { struct dmfe_board_info *db = netdev_priv(dev); - struct dev_mc_list *mcptr; + struct netdev_hw_addr *ha; struct tx_desc *txptr; u16 * addrptr; u32 * suptr; @@ -1520,8 +1520,8 @@ static void send_filter_frame(struct DEVICE *dev) *suptr++ = 0xffff; /* fit the multicast address */ - netdev_for_each_mc_addr(mcptr, dev) { - addrptr = (u16 *) mcptr->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrptr = (u16 *) ha->addr; *suptr++ = addrptr[0]; *suptr++ = addrptr[1]; *suptr++ = addrptr[2]; diff --git a/drivers/net/tulip/tulip_core.c b/drivers/net/tulip/tulip_core.c index 7f544ef2f5f..c4b7cd726b6 100644 --- a/drivers/net/tulip/tulip_core.c +++ b/drivers/net/tulip/tulip_core.c @@ -990,15 +990,15 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) { struct tulip_private *tp = netdev_priv(dev); u16 hash_table[32]; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i; u16 *eaddrs; memset(hash_table, 0, sizeof(hash_table)); set_bit_le(255, hash_table); /* Broadcast entry */ /* This should work on big-endian machines as well. */ - netdev_for_each_mc_addr(mclist, dev) { - int index = ether_crc_le(ETH_ALEN, mclist->dmi_addr) & 0x1ff; + netdev_for_each_mc_addr(ha, dev) { + int index = ether_crc_le(ETH_ALEN, ha->addr) & 0x1ff; set_bit_le(index, hash_table); } @@ -1018,13 +1018,13 @@ static void build_setup_frame_hash(u16 *setup_frm, struct net_device *dev) static void build_setup_frame_perfect(u16 *setup_frm, struct net_device *dev) { struct tulip_private *tp = netdev_priv(dev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u16 *eaddrs; /* We have <= 14 addresses so we can use the wonderful 16 address perfect filtering of the Tulip. */ - netdev_for_each_mc_addr(mclist, dev) { - eaddrs = (u16 *)mclist->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + eaddrs = (u16 *) ha->addr; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; *setup_frm++ = *eaddrs; *setup_frm++ = *eaddrs++; @@ -1061,7 +1061,7 @@ static void set_rx_mode(struct net_device *dev) } else if (tp->flags & MC_HASH_ONLY) { /* Some work-alikes have only a 64-entry hash filter table. */ /* Should verify correctness on big-endian/__powerpc__ */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; if (netdev_mc_count(dev) > 64) { /* Arbitrary non-effective limit. */ tp->csr6 |= AcceptAllMulticast; @@ -1069,18 +1069,21 @@ static void set_rx_mode(struct net_device *dev) } else { u32 mc_filter[2] = {0, 0}; /* Multicast hash filter */ int filterbit; - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { if (tp->flags & COMET_MAC_ADDR) - filterbit = ether_crc_le(ETH_ALEN, mclist->dmi_addr); + filterbit = ether_crc_le(ETH_ALEN, + ha->addr); else - filterbit = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + filterbit = ether_crc(ETH_ALEN, + ha->addr) >> 26; filterbit &= 0x3f; mc_filter[filterbit >> 5] |= 1 << (filterbit & 31); if (tulip_debug > 2) dev_info(&dev->dev, "Added filter for %pM %08x bit %d\n", - mclist->dmi_addr, - ether_crc(ETH_ALEN, mclist->dmi_addr), filterbit); + ha->addr, + ether_crc(ETH_ALEN, ha->addr), + filterbit); } if (mc_filter[0] == tp->mc_filter[0] && mc_filter[1] == tp->mc_filter[1]) diff --git a/drivers/net/tulip/uli526x.c b/drivers/net/tulip/uli526x.c index 0ab05af237e..b79d908fe34 100644 --- a/drivers/net/tulip/uli526x.c +++ b/drivers/net/tulip/uli526x.c @@ -1392,7 +1392,7 @@ static void update_cr6(u32 cr6_data, unsigned long ioaddr) static void send_filter_frame(struct net_device *dev, int mc_cnt) { struct uli526x_board_info *db = netdev_priv(dev); - struct dev_mc_list *mcptr; + struct netdev_hw_addr *ha; struct tx_desc *txptr; u16 * addrptr; u32 * suptr; @@ -1415,8 +1415,8 @@ static void send_filter_frame(struct net_device *dev, int mc_cnt) *suptr++ = 0xffff << FLT_SHIFT; /* fit the multicast address */ - netdev_for_each_mc_addr(mcptr, dev) { - addrptr = (u16 *) mcptr->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addrptr = (u16 *) ha->addr; *suptr++ = addrptr[0] << FLT_SHIFT; *suptr++ = addrptr[1] << FLT_SHIFT; *suptr++ = addrptr[2] << FLT_SHIFT; diff --git a/drivers/net/tulip/winbond-840.c b/drivers/net/tulip/winbond-840.c index 304f43866c4..3e3822c98a0 100644 --- a/drivers/net/tulip/winbond-840.c +++ b/drivers/net/tulip/winbond-840.c @@ -1367,13 +1367,15 @@ static u32 __set_rx_mode(struct net_device *dev) memset(mc_filter, 0xff, sizeof(mc_filter)); rx_mode = RxAcceptBroadcast | AcceptMulticast | AcceptMyPhys; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int filterbit = (ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26) ^ 0x3F; - filterbit &= 0x3f; - mc_filter[filterbit >> 5] |= 1 << (filterbit & 31); + netdev_for_each_mc_addr(ha, dev) { + int filbit; + + filbit = (ether_crc(ETH_ALEN, ha->addr) >> 26) ^ 0x3F; + filbit &= 0x3f; + mc_filter[filbit >> 5] |= 1 << (filbit & 31); } rx_mode = RxAcceptBroadcast | AcceptMulticast | AcceptMyPhys; } diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index cd24e5f2b2a..3053f85aa06 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -921,11 +921,11 @@ typhoon_set_rx_mode(struct net_device *dev) /* Too many to match, or accept all multicasts. */ filter |= TYPHOON_RX_FILTER_ALL_MCAST; } else if (!netdev_mc_empty(dev)) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int bit = ether_crc(ETH_ALEN, mclist->dmi_addr) & 0x3f; + netdev_for_each_mc_addr(ha, dev) { + int bit = ether_crc(ETH_ALEN, ha->addr) & 0x3f; mc_filter[bit >> 5] |= 1 << (bit & 0x1f); } diff --git a/drivers/net/ucc_geth.c b/drivers/net/ucc_geth.c index 75743a76bbe..081f76bff34 100644 --- a/drivers/net/ucc_geth.c +++ b/drivers/net/ucc_geth.c @@ -1999,7 +1999,7 @@ static void ucc_geth_memclean(struct ucc_geth_private *ugeth) static void ucc_geth_set_multi(struct net_device *dev) { struct ucc_geth_private *ugeth; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; struct ucc_fast __iomem *uf_regs; struct ucc_geth_82xx_address_filtering_pram __iomem *p_82xx_addr_filt; @@ -2028,16 +2028,16 @@ static void ucc_geth_set_multi(struct net_device *dev) out_be32(&p_82xx_addr_filt->gaddr_h, 0x0); out_be32(&p_82xx_addr_filt->gaddr_l, 0x0); - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { /* Only support group multicast for now. */ - if (!(dmi->dmi_addr[0] & 1)) + if (!(ha->addr[0] & 1)) continue; /* Ask CPM to run CRC and set bit in * filter mask. */ - hw_add_addr_in_hash(ugeth, dmi->dmi_addr); + hw_add_addr_in_hash(ugeth, ha->addr); } } } diff --git a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c index 9e05639435f..763364f0972 100644 --- a/drivers/net/usb/asix.c +++ b/drivers/net/usb/asix.c @@ -557,16 +557,14 @@ static void asix_set_multicast(struct net_device *net) * for our 8 byte filter buffer * to avoid allocating memory that * is tricky to free later */ - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; u32 crc_bits; memset(data->multi_filter, 0, AX_MCAST_FILTER_SIZE); /* Build the multicast hash filter. */ - netdev_for_each_mc_addr(mc_list, net) { - crc_bits = - ether_crc(ETH_ALEN, - mc_list->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, net) { + crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; data->multi_filter[crc_bits >> 3] |= 1 << (crc_bits & 7); } @@ -793,16 +791,14 @@ static void ax88172_set_multicast(struct net_device *net) * for our 8 byte filter buffer * to avoid allocating memory that * is tricky to free later */ - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; u32 crc_bits; memset(data->multi_filter, 0, AX_MCAST_FILTER_SIZE); /* Build the multicast hash filter. */ - netdev_for_each_mc_addr(mc_list, net) { - crc_bits = - ether_crc(ETH_ALEN, - mc_list->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, net) { + crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; data->multi_filter[crc_bits >> 3] |= 1 << (crc_bits & 7); } diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 96f1ebe0d34..0c48ff97f47 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -629,7 +629,7 @@ static void catc_multicast(unsigned char *addr, u8 *multicast) static void catc_set_multicast_list(struct net_device *netdev) { struct catc *catc = netdev_priv(netdev); - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; u8 broadcast[6]; u8 rx = RxEnable | RxPolarity | RxMultiCast; @@ -647,8 +647,8 @@ static void catc_set_multicast_list(struct net_device *netdev) if (netdev->flags & IFF_ALLMULTI) { memset(catc->multicast, 0xff, 64); } else { - netdev_for_each_mc_addr(mc, netdev) { - u32 crc = ether_crc_le(6, mc->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + u32 crc = ether_crc_le(6, ha->addr); if (!catc->is_f5u011) { catc->multicast[(crc >> 3) & 0x3f] |= 1 << (crc & 7); } else { diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index 269339769f4..4eb1fb31ff0 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -386,10 +386,10 @@ static void dm9601_set_multicast(struct net_device *net) netdev_mc_count(net) > DM_MAX_MCAST) { rx_ctl |= 0x04; } else if (!netdev_mc_empty(net)) { - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; - netdev_for_each_mc_addr(mc_list, net) { - u32 crc = ether_crc(ETH_ALEN, mc_list->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, net) { + u32 crc = ether_crc(ETH_ALEN, ha->addr) >> 26; hashes[crc >> 3] |= 1 << (crc & 0x7); } } diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index 70978219e98..0dc92c8ba4b 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -452,12 +452,12 @@ static void mcs7830_data_set_multicast(struct net_device *net) * for our 8 byte filter buffer * to avoid allocating memory that * is tricky to free later */ - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; u32 crc_bits; /* Build the multicast hash filter. */ - netdev_for_each_mc_addr(mc_list, net) { - crc_bits = ether_crc(ETH_ALEN, mc_list->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, net) { + crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26; data->multi_filter[crc_bits >> 3] |= 1 << (crc_bits & 7); } } diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 300e3e764fa..b8b00d06ea7 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -444,14 +444,14 @@ static void smsc75xx_set_multicast(struct net_device *netdev) netif_dbg(dev, drv, dev->net, "receive all multicast enabled"); pdata->rfe_ctl |= RFE_CTL_AM | RFE_CTL_DPF; } else if (!netdev_mc_empty(dev->net)) { - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; netif_dbg(dev, drv, dev->net, "receive multicast hash filter"); pdata->rfe_ctl |= RFE_CTL_MHF | RFE_CTL_DPF; - netdev_for_each_mc_addr(mc_list, netdev) { - u32 bitnum = smsc75xx_hash(mc_list->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + u32 bitnum = smsc75xx_hash(ha->addr); pdata->multicast_hash_table[bitnum / 32] |= (1 << (bitnum % 32)); } diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 73f9a31cf94..ccd55ca3a06 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -384,13 +384,13 @@ static void smsc95xx_set_multicast(struct net_device *netdev) pdata->mac_cr |= MAC_CR_MCPAS_; pdata->mac_cr &= ~(MAC_CR_PRMS_ | MAC_CR_HPFILT_); } else if (!netdev_mc_empty(dev->net)) { - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; pdata->mac_cr |= MAC_CR_HPFILT_; pdata->mac_cr &= ~(MAC_CR_PRMS_ | MAC_CR_MCPAS_); - netdev_for_each_mc_addr(mc_list, netdev) { - u32 bitnum = smsc95xx_hash(mc_list->dmi_addr); + netdev_for_each_mc_addr(ha, netdev) { + u32 bitnum = smsc95xx_hash(ha->addr); u32 mask = 0x01 << (bitnum & 0x1F); if (bitnum & 0x20) hash_hi |= mask; diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index 50f881aa393..d9133c62a2f 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -1704,11 +1704,11 @@ static void rhine_set_rx_mode(struct net_device *dev) iowrite32(0xffffffff, ioaddr + MulticastFilter1); rx_mode = 0x0C; } else { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); } diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index 3a486f3bad3..91f3b841288 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -1126,7 +1126,7 @@ static void velocity_set_multi(struct net_device *dev) struct mac_regs __iomem *regs = vptr->mac_regs; u8 rx_mode; int i; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ writel(0xffffffff, ®s->MARCAM[0]); @@ -1142,8 +1142,8 @@ static void velocity_set_multi(struct net_device *dev) mac_get_cam_mask(regs, vptr->mCAMmask); i = 0; - netdev_for_each_mc_addr(mclist, dev) { - mac_set_cam(regs, i + offset, mclist->dmi_addr); + netdev_for_each_mc_addr(ha, dev) { + mac_set_cam(regs, i + offset, ha->addr); vptr->mCAMmask[(offset + i) / 8] |= 1 << ((offset + i) & 7); i++; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3f5be35dea2..ecec9a8527f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -721,7 +721,6 @@ static void virtnet_set_rx_mode(struct net_device *dev) struct scatterlist sg[2]; u8 promisc, allmulti; struct virtio_net_ctrl_mac *mac_data; - struct dev_addr_list *addr; struct netdev_hw_addr *ha; int uc_count; int mc_count; @@ -778,8 +777,8 @@ static void virtnet_set_rx_mode(struct net_device *dev) mac_data->entries = mc_count; i = 0; - netdev_for_each_mc_addr(addr, dev) - memcpy(&mac_data->macs[i++][0], addr->da_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) + memcpy(&mac_data->macs[i++][0], ha->addr, ETH_ALEN); sg_set_buf(&sg[1], mac_data, sizeof(mac_data->entries) + (mc_count * ETH_ALEN)); diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index cff3485d967..58dfa367bf8 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1675,11 +1675,11 @@ vmxnet3_copy_mc(struct net_device *netdev) /* We may be called with BH disabled */ buf = kmalloc(sz, GFP_ATOMIC); if (buf) { - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; int i = 0; - netdev_for_each_mc_addr(mc, netdev) - memcpy(buf + i++ * ETH_ALEN, mc->dmi_addr, + netdev_for_each_mc_addr(ha, netdev) + memcpy(buf + i++ * ETH_ALEN, ha->addr, ETH_ALEN); } } diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index e5f2d3ee0df..37836a10d09 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -1117,7 +1117,7 @@ vxge_tx_term(void *dtrh, enum vxge_hw_txdl_state state, void *userdata) */ static void vxge_set_multicast(struct net_device *dev) { - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct vxgedev *vdev; int i, mcast_cnt = 0; struct __vxge_hw_device *hldev; @@ -1217,8 +1217,8 @@ static void vxge_set_multicast(struct net_device *dev) } /* Add new ones */ - netdev_for_each_mc_addr(mclist, dev) { - memcpy(mac_info.macaddr, mclist->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) { + memcpy(mac_info.macaddr, ha->addr, ETH_ALEN); for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) { mac_info.vpath_no = vpath_idx; diff --git a/drivers/net/wireless/adm8211.c b/drivers/net/wireless/adm8211.c index 547912e6843..2277998b726 100644 --- a/drivers/net/wireless/adm8211.c +++ b/drivers/net/wireless/adm8211.c @@ -1317,21 +1317,19 @@ static void adm8211_bss_info_changed(struct ieee80211_hw *dev, } static u64 adm8211_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { - unsigned int bit_nr, i; + unsigned int bit_nr; u32 mc_filter[2]; + struct netdev_hw_addr *ha; mc_filter[1] = mc_filter[0] = 0; - for (i = 0; i < mc_count; i++) { - if (!mclist) - break; - bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_hw_addr_list_for_each(ha, mc_list) { + bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; bit_nr &= 0x3F; mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); - mclist = mclist->next; } return mc_filter[0] | ((u64)(mc_filter[1]) << 32); diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c index 257c734733d..b43d4b006d7 100644 --- a/drivers/net/wireless/ath/ar9170/main.c +++ b/drivers/net/wireless/ath/ar9170/main.c @@ -2045,21 +2045,17 @@ out: return err; } -static u64 ar9170_op_prepare_multicast(struct ieee80211_hw *hw, int mc_count, - struct dev_addr_list *mclist) +static u64 ar9170_op_prepare_multicast(struct ieee80211_hw *hw, + struct netdev_hw_addr_list *mc_list) { u64 mchash; - int i; + struct netdev_hw_addr *ha; /* always get broadcast frames */ mchash = 1ULL << (0xff >> 2); - for (i = 0; i < mc_count; i++) { - if (WARN_ON(!mclist)) - break; - mchash |= 1ULL << (mclist->dmi_addr[5] >> 2); - mclist = mclist->next; - } + netdev_hw_addr_list_for_each(ha, mc_list) + mchash |= 1ULL << (ha->addr[5] >> 2); return mchash; } diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index b142a78ed1e..53a2340f52b 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -230,7 +230,7 @@ static void ath5k_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif); static int ath5k_config(struct ieee80211_hw *hw, u32 changed); static u64 ath5k_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mc_list); + struct netdev_hw_addr_list *mc_list); static void ath5k_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *new_flags, @@ -2999,22 +2999,20 @@ unlock: } static u64 ath5k_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { u32 mfilt[2], val; - int i; u8 pos; + struct netdev_hw_addr *ha; mfilt[0] = 0; mfilt[1] = 1; - for (i = 0; i < mc_count; i++) { - if (!mclist) - break; + netdev_hw_addr_list_for_each(ha, mc_list) { /* calculate XOR of eight 6-bit values */ - val = get_unaligned_le32(mclist->dmi_addr + 0); + val = get_unaligned_le32(ha->addr + 0); pos = (val >> 18) ^ (val >> 12) ^ (val >> 6) ^ val; - val = get_unaligned_le32(mclist->dmi_addr + 3); + val = get_unaligned_le32(ha->addr + 3); pos ^= (val >> 18) ^ (val >> 12) ^ (val >> 6) ^ val; pos &= 0x3f; mfilt[pos / 32] |= (1 << (pos % 32)); @@ -3022,8 +3020,7 @@ static u64 ath5k_prepare_multicast(struct ieee80211_hw *hw, * but not sure, needs testing, if we do use this we'd * neet to inform below to not reset the mcast */ /* ath5k_hw_set_mcast_filterindex(ah, - * mclist->dmi_addr[5]); */ - mclist = mclist->next; + * ha->addr[5]); */ } return ((u64)(mfilt[1]) << 32) | mfilt[0]; diff --git a/drivers/net/wireless/libertas/main.c b/drivers/net/wireless/libertas/main.c index 3c889f43d90..ff7b0d0cca5 100644 --- a/drivers/net/wireless/libertas/main.c +++ b/drivers/net/wireless/libertas/main.c @@ -318,7 +318,7 @@ static int lbs_add_mcast_addrs(struct cmd_ds_mac_multicast_adr *cmd, struct net_device *dev, int nr_addrs) { int i = nr_addrs; - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; int cnt; if ((dev->flags & (IFF_UP|IFF_MULTICAST)) != (IFF_UP|IFF_MULTICAST)) @@ -326,19 +326,19 @@ static int lbs_add_mcast_addrs(struct cmd_ds_mac_multicast_adr *cmd, netif_addr_lock_bh(dev); cnt = netdev_mc_count(dev); - netdev_for_each_mc_addr(mc_list, dev) { - if (mac_in_list(cmd->maclist, nr_addrs, mc_list->dmi_addr)) { + netdev_for_each_mc_addr(ha, dev) { + if (mac_in_list(cmd->maclist, nr_addrs, ha->addr)) { lbs_deb_net("mcast address %s:%pM skipped\n", dev->name, - mc_list->dmi_addr); + ha->addr); cnt--; continue; } if (i == MRVDRV_MAX_MULTICAST_LIST_SIZE) break; - memcpy(&cmd->maclist[6*i], mc_list->dmi_addr, ETH_ALEN); + memcpy(&cmd->maclist[6*i], ha->addr, ETH_ALEN); lbs_deb_net("mcast address %s:%pM added to filter\n", dev->name, - mc_list->dmi_addr); + ha->addr); i++; cnt--; } diff --git a/drivers/net/wireless/libertas_tf/main.c b/drivers/net/wireless/libertas_tf/main.c index 6ab30033c26..c20eef6b95c 100644 --- a/drivers/net/wireless/libertas_tf/main.c +++ b/drivers/net/wireless/libertas_tf/main.c @@ -367,22 +367,20 @@ static int lbtf_op_config(struct ieee80211_hw *hw, u32 changed) } static u64 lbtf_op_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { struct lbtf_private *priv = hw->priv; int i; + struct netdev_hw_addr *ha; + int mc_count = netdev_hw_addr_list_count(mc_list); if (!mc_count || mc_count > MRVDRV_MAX_MULTICAST_LIST_SIZE) return mc_count; priv->nr_of_multicastmacaddr = mc_count; - for (i = 0; i < mc_count; i++) { - if (!mclist) - break; - memcpy(&priv->multicastlist[i], mclist->da_addr, - ETH_ALEN); - mclist = mclist->next; - } + i = 0; + netdev_hw_addr_list_for_each(ha, mc_list) + memcpy(&priv->multicastlist[i++], ha->addr, ETH_ALEN); return mc_count; } diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index ac65e13eb0d..6599fd15e67 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -1938,11 +1938,15 @@ struct mwl8k_cmd_mac_multicast_adr { static struct mwl8k_cmd_pkt * __mwl8k_cmd_mac_multicast_adr(struct ieee80211_hw *hw, int allmulti, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { struct mwl8k_priv *priv = hw->priv; struct mwl8k_cmd_mac_multicast_adr *cmd; int size; + int mc_count = 0; + + if (mc_list) + mc_count = netdev_hw_addr_list_count(mc_list); if (allmulti || mc_count > priv->num_mcaddrs) { allmulti = 1; @@ -1963,17 +1967,13 @@ __mwl8k_cmd_mac_multicast_adr(struct ieee80211_hw *hw, int allmulti, if (allmulti) { cmd->action |= cpu_to_le16(MWL8K_ENABLE_RX_ALL_MULTICAST); } else if (mc_count) { - int i; + struct netdev_hw_addr *ha; + int i = 0; cmd->action |= cpu_to_le16(MWL8K_ENABLE_RX_MULTICAST); cmd->numaddr = cpu_to_le16(mc_count); - for (i = 0; i < mc_count && mclist; i++) { - if (mclist->da_addrlen != ETH_ALEN) { - kfree(cmd); - return NULL; - } - memcpy(cmd->addr[i], mclist->da_addr, ETH_ALEN); - mclist = mclist->next; + netdev_hw_addr_list_for_each(ha, mc_list) { + memcpy(cmd->addr[i], ha->addr, ETH_ALEN); } } @@ -3552,7 +3552,7 @@ mwl8k_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } static u64 mwl8k_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { struct mwl8k_cmd_pkt *cmd; @@ -3563,7 +3563,7 @@ static u64 mwl8k_prepare_multicast(struct ieee80211_hw *hw, * we'll end up throwing this packet away and creating a new * one in mwl8k_configure_filter(). */ - cmd = __mwl8k_cmd_mac_multicast_adr(hw, 0, mc_count, mclist); + cmd = __mwl8k_cmd_mac_multicast_adr(hw, 0, mc_list); return (unsigned long)cmd; } @@ -3686,7 +3686,7 @@ static void mwl8k_configure_filter(struct ieee80211_hw *hw, */ if (*total_flags & FIF_ALLMULTI) { kfree(cmd); - cmd = __mwl8k_cmd_mac_multicast_adr(hw, 1, 0, NULL); + cmd = __mwl8k_cmd_mac_multicast_adr(hw, 1, NULL); } if (cmd != NULL) { diff --git a/drivers/net/wireless/orinoco/hw.c b/drivers/net/wireless/orinoco/hw.c index 883b8f86862..9f657afaa3e 100644 --- a/drivers/net/wireless/orinoco/hw.c +++ b/drivers/net/wireless/orinoco/hw.c @@ -1056,14 +1056,14 @@ int __orinoco_hw_set_multicast_list(struct orinoco_private *priv, * group address if either we want to multicast, or if we were * multicasting and want to stop */ if (!promisc && (mc_count || priv->mc_count)) { - struct dev_mc_list *p; + struct netdev_hw_addr *ha; struct hermes_multicast mclist; int i = 0; - netdev_for_each_mc_addr(p, dev) { + netdev_for_each_mc_addr(ha, dev) { if (i == mc_count) break; - memcpy(mclist.addr[i++], p->dmi_addr, ETH_ALEN); + memcpy(mclist.addr[i++], ha->addr, ETH_ALEN); } err = hermes_write_ltv(hw, USER_BAP, diff --git a/drivers/net/wireless/orinoco/hw.h b/drivers/net/wireless/orinoco/hw.h index 9799a1d14a6..97af71e7995 100644 --- a/drivers/net/wireless/orinoco/hw.h +++ b/drivers/net/wireless/orinoco/hw.h @@ -22,7 +22,6 @@ /* Forward declarations */ struct orinoco_private; -struct dev_addr_list; int determine_fw_capabilities(struct orinoco_private *priv, char *fw_name, size_t fw_name_len, u32 *hw_ver); diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 4f5bdb528ef..54680a3a5ac 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -1875,17 +1875,17 @@ static void ray_update_multi_list(struct net_device *dev, int all) writeb(0xff, &pccs->var); local->num_multi = 0xff; } else { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i = 0; /* Copy the kernel's list of MC addresses to card */ - netdev_for_each_mc_addr(dmi, dev) { - memcpy_toio(p, dmi->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) { + memcpy_toio(p, ha->addr, ETH_ALEN); dev_dbg(&link->dev, "ray_update_multi add addr %02x%02x%02x%02x%02x%02x\n", - dmi->dmi_addr[0], dmi->dmi_addr[1], - dmi->dmi_addr[2], dmi->dmi_addr[3], - dmi->dmi_addr[4], dmi->dmi_addr[5]); + ha->addr[0], ha->addr[1], + ha->addr[2], ha->addr[3], + ha->addr[4], ha->addr[5]); p += ETH_ALEN; i++; } diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index aceb95ef727..8ab9f094747 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -1545,7 +1545,7 @@ static int remove_key(struct usbnet *usbdev, int index, const u8 *bssid) static void set_multicast_list(struct usbnet *usbdev) { struct rndis_wlan_private *priv = get_rndis_wlan_priv(usbdev); - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; __le32 filter, basefilter; int ret; char *mc_addrs = NULL; @@ -1584,9 +1584,9 @@ static void set_multicast_list(struct usbnet *usbdev) return; } - netdev_for_each_mc_addr(mclist, usbdev->net) + netdev_for_each_mc_addr(ha, usbdev->net) memcpy(mc_addrs + i++ * ETH_ALEN, - mclist->dmi_addr, ETH_ALEN); + ha->addr, ETH_ALEN); } netif_addr_unlock_bh(usbdev->net); diff --git a/drivers/net/wireless/rtl818x/rtl8180_dev.c b/drivers/net/wireless/rtl818x/rtl8180_dev.c index 2b928ecf47b..fb8a62f2b9b 100644 --- a/drivers/net/wireless/rtl818x/rtl8180_dev.c +++ b/drivers/net/wireless/rtl818x/rtl8180_dev.c @@ -723,10 +723,10 @@ static void rtl8180_bss_info_changed(struct ieee80211_hw *dev, priv->rf->conf_erp(dev, info); } -static u64 rtl8180_prepare_multicast(struct ieee80211_hw *dev, int mc_count, - struct dev_addr_list *mc_list) +static u64 rtl8180_prepare_multicast(struct ieee80211_hw *dev, + struct netdev_hw_addr_list *mc_list) { - return mc_count; + return netdev_hw_addr_list_count(mc_list); } static void rtl8180_configure_filter(struct ieee80211_hw *dev, diff --git a/drivers/net/wireless/rtl818x/rtl8187_dev.c b/drivers/net/wireless/rtl818x/rtl8187_dev.c index 0fb850e0c65..441d817ed48 100644 --- a/drivers/net/wireless/rtl818x/rtl8187_dev.c +++ b/drivers/net/wireless/rtl818x/rtl8187_dev.c @@ -1193,9 +1193,9 @@ static void rtl8187_bss_info_changed(struct ieee80211_hw *dev, } static u64 rtl8187_prepare_multicast(struct ieee80211_hw *dev, - int mc_count, struct dev_addr_list *mc_list) + struct netdev_hw_addr_list *mc_list) { - return mc_count; + return netdev_hw_addr_list_count(mc_list); } static void rtl8187_configure_filter(struct ieee80211_hw *dev, diff --git a/drivers/net/wireless/wl12xx/wl1271_main.c b/drivers/net/wireless/wl12xx/wl1271_main.c index 3daba6c0c77..6036d0206fe 100644 --- a/drivers/net/wireless/wl12xx/wl1271_main.c +++ b/drivers/net/wireless/wl12xx/wl1271_main.c @@ -1266,11 +1266,11 @@ struct wl1271_filter_params { u8 mc_list[ACX_MC_ADDRESS_GROUP_MAX][ETH_ALEN]; }; -static u64 wl1271_op_prepare_multicast(struct ieee80211_hw *hw, int mc_count, - struct dev_addr_list *mc_list) +static u64 wl1271_op_prepare_multicast(struct ieee80211_hw *hw, + struct netdev_hw_addr_list *mc_list) { struct wl1271_filter_params *fp; - int i; + struct netdev_hw_addr *ha; fp = kzalloc(sizeof(*fp), GFP_ATOMIC); if (!fp) { @@ -1279,21 +1279,16 @@ static u64 wl1271_op_prepare_multicast(struct ieee80211_hw *hw, int mc_count, } /* update multicast filtering parameters */ - fp->enabled = true; - if (mc_count > ACX_MC_ADDRESS_GROUP_MAX) { - mc_count = 0; - fp->enabled = false; - } - fp->mc_list_length = 0; - for (i = 0; i < mc_count; i++) { - if (mc_list->da_addrlen == ETH_ALEN) { + if (netdev_hw_addr_list_count(mc_list) > ACX_MC_ADDRESS_GROUP_MAX) { + fp->enabled = false; + } else { + fp->enabled = true; + netdev_hw_addr_list_for_each(ha, mc_list) { memcpy(fp->mc_list[fp->mc_list_length], - mc_list->da_addr, ETH_ALEN); + ha->addr, ETH_ALEN); fp->mc_list_length++; - } else - wl1271_warning("Unknown mc address length."); - mc_list = mc_list->next; + } } return (u64)(unsigned long)fp; diff --git a/drivers/net/wireless/zd1201.c b/drivers/net/wireless/zd1201.c index 6917286edca..74530b2d672 100644 --- a/drivers/net/wireless/zd1201.c +++ b/drivers/net/wireless/zd1201.c @@ -875,7 +875,7 @@ static struct iw_statistics *zd1201_get_wireless_stats(struct net_device *dev) static void zd1201_set_multicast(struct net_device *dev) { struct zd1201 *zd = netdev_priv(dev); - struct dev_mc_list *mc; + struct netdev_hw_addr *ha; unsigned char reqbuf[ETH_ALEN*ZD1201_MAXMULTI]; int i; @@ -883,8 +883,8 @@ static void zd1201_set_multicast(struct net_device *dev) return; i = 0; - netdev_for_each_mc_addr(mc, dev) - memcpy(reqbuf + i++ * ETH_ALEN, mc->dmi_addr, ETH_ALEN); + netdev_for_each_mc_addr(ha, dev) + memcpy(reqbuf + i++ * ETH_ALEN, ha->addr, ETH_ALEN); zd1201_setconfig(zd, ZD1201_RID_CNFGROUPADDRESS, reqbuf, netdev_mc_count(dev) * ETH_ALEN, 0); } diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index 00e09e26c82..6d95e4d74d7 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -947,20 +947,17 @@ static void set_rx_filter_handler(struct work_struct *work) } static u64 zd_op_prepare_multicast(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mclist) + struct netdev_hw_addr_list *mc_list) { struct zd_mac *mac = zd_hw_mac(hw); struct zd_mc_hash hash; - int i; + struct netdev_hw_addr *ha; zd_mc_clear(&hash); - for (i = 0; i < mc_count; i++) { - if (!mclist) - break; - dev_dbg_f(zd_mac_dev(mac), "mc addr %pM\n", mclist->dmi_addr); - zd_mc_add_addr(&hash, mclist->dmi_addr); - mclist = mclist->next; + netdev_hw_addr_list_for_each(ha, mc_list) { + dev_dbg_f(zd_mac_dev(mac), "mc addr %pM\n", ha->addr); + zd_mc_add_addr(&hash, ha->addr); } return hash.low | ((u64)hash.high << 32); diff --git a/drivers/net/yellowfin.c b/drivers/net/yellowfin.c index 7d4107f5eeb..34c91cf5d83 100644 --- a/drivers/net/yellowfin.c +++ b/drivers/net/yellowfin.c @@ -1300,25 +1300,25 @@ static void set_rx_mode(struct net_device *dev) /* Too many to filter well, or accept all multicasts. */ iowrite16(0x000B, ioaddr + AddrMode); } else if (!netdev_mc_empty(dev)) { /* Must use the multicast hash table. */ - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; u16 hash_table[4]; int i; memset(hash_table, 0, sizeof(hash_table)); - netdev_for_each_mc_addr(mclist, dev) { + netdev_for_each_mc_addr(ha, dev) { unsigned int bit; /* Due to a bug in the early chip versions, multiple filter slots must be set for each address. */ if (yp->drv_flags & HasMulticastBug) { - bit = (ether_crc_le(3, mclist->dmi_addr) >> 3) & 0x3f; + bit = (ether_crc_le(3, ha->addr) >> 3) & 0x3f; hash_table[bit >> 4] |= (1 << bit); - bit = (ether_crc_le(4, mclist->dmi_addr) >> 3) & 0x3f; + bit = (ether_crc_le(4, ha->addr) >> 3) & 0x3f; hash_table[bit >> 4] |= (1 << bit); - bit = (ether_crc_le(5, mclist->dmi_addr) >> 3) & 0x3f; + bit = (ether_crc_le(5, ha->addr) >> 3) & 0x3f; hash_table[bit >> 4] |= (1 << bit); } - bit = (ether_crc_le(6, mclist->dmi_addr) >> 3) & 0x3f; + bit = (ether_crc_le(6, ha->addr) >> 3) & 0x3f; hash_table[bit >> 4] |= (1 << bit); } /* Copy the hash table to the chip. */ diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 7576ad5a833..945f3e0a9f0 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -607,7 +607,6 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) static void qeth_l2_set_multicast_list(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; - struct dev_addr_list *dm; struct netdev_hw_addr *ha; if (card->info.type == QETH_CARD_TYPE_OSN) @@ -619,8 +618,8 @@ static void qeth_l2_set_multicast_list(struct net_device *dev) return; qeth_l2_del_all_mc(card); spin_lock_bh(&card->mclock); - netdev_for_each_mc_addr(dm, dev) - qeth_l2_add_mc(card, dm->da_addr, 0); + netdev_for_each_mc_addr(ha, dev) + qeth_l2_add_mc(card, ha->addr, 0); netdev_for_each_uc_addr(ha, dev) qeth_l2_add_mc(card, ha->addr, 1); diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index de33e38a405..37de40e0168 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -311,7 +311,7 @@ static int fcoe_interface_setup(struct fcoe_interface *fcoe, dev_uc_add(netdev, flogi_maddr); if (fip->spma) dev_uc_add(netdev, fip->ctl_src_addr); - dev_mc_add(netdev, FIP_ALL_ENODE_MACS, ETH_ALEN, 0); + dev_mc_add(netdev, FIP_ALL_ENODE_MACS); /* * setup the receive function from ethernet driver @@ -397,7 +397,7 @@ void fcoe_interface_cleanup(struct fcoe_interface *fcoe) dev_uc_del(netdev, flogi_maddr); if (fip->spma) dev_uc_del(netdev, fip->ctl_src_addr); - dev_mc_delete(netdev, FIP_ALL_ENODE_MACS, ETH_ALEN, 0); + dev_mc_del(netdev, FIP_ALL_ENODE_MACS); /* Tell the LLD we are done w/ FCoE */ ops = netdev->netdev_ops; diff --git a/drivers/staging/arlan/arlan-main.c b/drivers/staging/arlan/arlan-main.c index 88fdd53cf5d..80284522c42 100644 --- a/drivers/staging/arlan/arlan-main.c +++ b/drivers/staging/arlan/arlan-main.c @@ -1458,7 +1458,7 @@ static void arlan_rx_interrupt(struct net_device *dev, u_char rxStatus, u_short !netdev_mc_empty(dev)) { char hw_dst_addr[6]; - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i; memcpy_fromio(hw_dst_addr, arlan->ultimateDestAddress, 6); @@ -1469,12 +1469,13 @@ static void arlan_rx_interrupt(struct net_device *dev, u_char rxStatus, u_short printk(KERN_ERR "%s mcast 0x0100 \n", dev->name); else if (hw_dst_addr[1] == 0x40) printk(KERN_ERR "%s m/bcast 0x0140 \n", dev->name); - netdev_for_each_mc_entry(dmi, dev) { + netdev_for_each_mc_entry(ha, dev) { if (arlan_debug & ARLAN_DEBUG_HEADER_DUMP) printk(KERN_ERR "%s mcl %pM\n", - dev->name, dmi->dmi_addr); + dev->name, + ha->addr); for (i = 0; i < 6; i++) - if (dmi->dmi_addr[i] != hw_dst_addr[i]) + if (ha->addr[i] != hw_dst_addr[i]) break; if (i == 6) break; diff --git a/drivers/staging/et131x/et131x_netdev.c b/drivers/staging/et131x/et131x_netdev.c index 40f8954dde4..2fb89cddef1 100644 --- a/drivers/staging/et131x/et131x_netdev.c +++ b/drivers/staging/et131x/et131x_netdev.c @@ -405,7 +405,7 @@ void et131x_multicast(struct net_device *netdev) struct et131x_adapter *adapter = netdev_priv(netdev); uint32_t PacketFilter = 0; unsigned long flags; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; int i; spin_lock_irqsave(&adapter->Lock, flags); @@ -450,10 +450,10 @@ void et131x_multicast(struct net_device *netdev) /* Set values in the private adapter struct */ i = 0; - netdev_for_each_mc_addr(mclist, netdev) { + netdev_for_each_mc_addr(ha, netdev) { if (i == NIC_MAX_MCAST_LIST) break; - memcpy(adapter->MCList[i++], mclist->dmi_addr, ETH_ALEN); + memcpy(adapter->MCList[i++], ha->addr, ETH_ALEN); } adapter->MCAddressCount = i; diff --git a/drivers/staging/slicoss/slicoss.c b/drivers/staging/slicoss/slicoss.c index 7daeced317c..bebf0fd2af8 100644 --- a/drivers/staging/slicoss/slicoss.c +++ b/drivers/staging/slicoss/slicoss.c @@ -1367,12 +1367,12 @@ static void slic_mcast_set_list(struct net_device *dev) struct adapter *adapter = netdev_priv(dev); int status = STATUS_SUCCESS; char *addresses; - struct dev_mc_list *mc_list; + struct netdev_hw_addr *ha; ASSERT(adapter); - netdev_for_each_mc_addr(mc_list, dev) { - addresses = (char *) &mc_list->dmi_addr; + netdev_for_each_mc_addr(ha, dev) { + addresses = (char *) &ha->addr; status = slic_mcast_add_list(adapter, addresses); if (status != STATUS_SUCCESS) break; diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c index 1d643653a7e..b698de40a60 100644 --- a/drivers/staging/vt6655/device_main.c +++ b/drivers/staging/vt6655/device_main.c @@ -3079,7 +3079,7 @@ static void device_set_multi(struct net_device *dev) { PSMgmtObject pMgmt = pDevice->pMgmt; u32 mc_filter[2]; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; VNSvInPortB(pDevice->PortOffset + MAC_REG_RCR, &(pDevice->byRxMode)); @@ -3099,8 +3099,8 @@ static void device_set_multi(struct net_device *dev) { } else { memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= cpu_to_le32(1 << (bit_nr & 31)); } MACvSelectPage1(pDevice->PortOffset); diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c index a8e1adbc959..49270db98fb 100644 --- a/drivers/staging/vt6656/main_usb.c +++ b/drivers/staging/vt6656/main_usb.c @@ -1596,7 +1596,7 @@ static void device_set_multi(struct net_device *dev) { PSMgmtObject pMgmt = &(pDevice->sMgmtObj); u32 mc_filter[2]; int ii; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; BYTE pbyData[8] = {0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff}; BYTE byTmpMode = 0; int rc; @@ -1632,8 +1632,8 @@ static void device_set_multi(struct net_device *dev) { } else { memset(mc_filter, 0, sizeof(mc_filter)); - netdev_for_each_mc_addr(mclist, dev) { - int bit_nr = ether_crc(ETH_ALEN, mclist->dmi_addr) >> 26; + netdev_for_each_mc_addr(ha, dev) { + int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; mc_filter[bit_nr >> 5] |= cpu_to_le32(1 << (bit_nr & 31)); } for (ii = 0; ii < 4; ii++) { diff --git a/drivers/staging/wavelan/wavelan.c b/drivers/staging/wavelan/wavelan.c index 54ca63196fd..f44ef351647 100644 --- a/drivers/staging/wavelan/wavelan.c +++ b/drivers/staging/wavelan/wavelan.c @@ -3419,7 +3419,7 @@ static void wv_82586_config(struct net_device * dev) ac_cfg_t cfg; /* Configure action */ ac_ias_t ias; /* IA-setup action */ ac_mcs_t mcs; /* Multicast setup */ - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; #ifdef DEBUG_CONFIG_TRACE printk(KERN_DEBUG "%s: ->wv_82586_config()\n", dev->name); @@ -3531,16 +3531,16 @@ static void wv_82586_config(struct net_device * dev) /* Any address to set? */ if (lp->mc_count) { - netdev_for_each_mc_addr(dmi, dev) - outsw(PIOP1(ioaddr), (u16 *) dmi->dmi_addr, + netdev_for_each_mc_addr(ha, dev) + outsw(PIOP1(ioaddr), (u16 *) ha->addr, WAVELAN_ADDR_SIZE >> 1); #ifdef DEBUG_CONFIG_INFO printk(KERN_DEBUG "%s: wv_82586_config(): set %d multicast addresses:\n", dev->name, lp->mc_count); - netdev_for_each_mc_addr(dmi, dev) - printk(KERN_DEBUG " %pM\n", dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + printk(KERN_DEBUG " %pM\n", ha->addr); #endif } diff --git a/drivers/staging/wavelan/wavelan_cs.c b/drivers/staging/wavelan/wavelan_cs.c index 04f691d127b..a90132a204e 100644 --- a/drivers/staging/wavelan/wavelan_cs.c +++ b/drivers/staging/wavelan/wavelan_cs.c @@ -3591,20 +3591,20 @@ wv_82593_config(struct net_device * dev) /* If roaming is enabled, join the "Beacon Request" multicast group... */ /* But only if it's not in there already! */ if(do_roaming) - dev_mc_add(dev,WAVELAN_BEACON_ADDRESS, WAVELAN_ADDR_SIZE, 1); + dev_mc_add(dev, WAVELAN_BEACON_ADDRESS); #endif /* WAVELAN_ROAMING */ /* If any multicast address to set */ if(lp->mc_count) { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int addrs_len = WAVELAN_ADDR_SIZE * lp->mc_count; #ifdef DEBUG_CONFIG_INFO printk(KERN_DEBUG "%s: wv_hw_config(): set %d multicast addresses:\n", dev->name, lp->mc_count); - netdev_for_each_mc_addr(dmi, dev) - printk(KERN_DEBUG " %pM\n", dmi->dmi_addr); + netdev_for_each_mc_addr(ha, dev) + printk(KERN_DEBUG " %pM\n", ha->addr); #endif /* Initialize adapter's ethernet multicast addresses */ @@ -3612,8 +3612,8 @@ wv_82593_config(struct net_device * dev) outb(((TX_BASE >> 8) & PIORH_MASK) | PIORH_SEL_TX, PIORH(base)); outb(addrs_len & 0xff, PIOP(base)); /* byte count lsb */ outb((addrs_len >> 8), PIOP(base)); /* byte count msb */ - netdev_for_each_mc_addr(dmi, dev) - outsb(PIOP(base), dmi->dmi_addr, dmi->dmi_addrlen); + netdev_for_each_mc_addr(ha, dev) + outsb(PIOP(base), ha->addr, dev->addr_len); /* reset transmit DMA pointer */ hacr_write_slow(base, HACR_PWR_STAT | HACR_TX_DMA_RESET); diff --git a/drivers/staging/winbond/wbusb.c b/drivers/staging/winbond/wbusb.c index 3482eec1865..5d9499bba9c 100644 --- a/drivers/staging/winbond/wbusb.c +++ b/drivers/staging/winbond/wbusb.c @@ -92,10 +92,10 @@ static int wbsoft_get_stats(struct ieee80211_hw *hw, return 0; } -static u64 wbsoft_prepare_multicast(struct ieee80211_hw *hw, int mc_count, - struct dev_addr_list *mc_list) +static u64 wbsoft_prepare_multicast(struct ieee80211_hw *hw, + struct netdev_hw_addr_list *mc_list) { - return mc_count; + return netdev_hw_addr_list_count(mc_list); } static void wbsoft_configure_filter(struct ieee80211_hw *dev, diff --git a/drivers/staging/wlags49_h2/wl_netdev.c b/drivers/staging/wlags49_h2/wl_netdev.c index fa082d90fca..d7532e89f5f 100644 --- a/drivers/staging/wlags49_h2/wl_netdev.c +++ b/drivers/staging/wlags49_h2/wl_netdev.c @@ -1049,7 +1049,7 @@ void wl_multicast( struct net_device *dev ) //;?seems reasonable that even an AP-only driver could afford this small additional footprint int x; - struct dev_mc_list *mclist; + struct netdev_hw_addr *ha; struct wl_private *lp = wl_priv(dev); unsigned long flags; /*------------------------------------------------------------------------*/ @@ -1072,9 +1072,9 @@ void wl_multicast( struct net_device *dev ) DBG_PRINT( " mc_count: %d\n", netdev_mc_count(dev)); - netdev_for_each_mc_addr(mclist, dev) - DBG_PRINT( " %s (%d)\n", DbgHwAddr(mclist->dmi_addr), - mclist->dmi_addrlen ); + netdev_for_each_mc_addr(ha, dev) + DBG_PRINT(" %s (%d)\n", DbgHwAddr(ha->addr), + dev->addr_len); } #endif /* DBG */ @@ -1119,9 +1119,9 @@ void wl_multicast( struct net_device *dev ) lp->ltvRecord.typ = CFG_GROUP_ADDR; x = 0; - netdev_for_each_mc_addr(mclist, dev) + netdev_for_each_mc_addr(ha, dev) memcpy(&(lp->ltvRecord.u.u8[x++ * ETH_ALEN]), - mclist->dmi_addr, ETH_ALEN); + ha->addr, ETH_ALEN); DBG_PRINT( "Setting multicast list\n" ); hcf_put_info( &( lp->hcfCtx ), (LTVP)&( lp->ltvRecord )); } else { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 60f0c83192f..a343a21ba8b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -228,25 +228,6 @@ struct netif_rx_stats { DECLARE_PER_CPU(struct netif_rx_stats, netdev_rx_stat); -struct dev_addr_list { - struct dev_addr_list *next; - u8 da_addr[MAX_ADDR_LEN]; - u8 da_addrlen; - u8 da_synced; - int da_users; - int da_gusers; -}; - -/* - * We tag multicasts with these structures. - */ - -#define dev_mc_list dev_addr_list -#define dmi_addr da_addr -#define dmi_addrlen da_addrlen -#define dmi_users da_users -#define dmi_gusers da_gusers - struct netdev_hw_addr { struct list_head list; unsigned char addr[MAX_ADDR_LEN]; @@ -255,8 +236,10 @@ struct netdev_hw_addr { #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_SLAVE 3 #define NETDEV_HW_ADDR_T_UNICAST 4 +#define NETDEV_HW_ADDR_T_MULTICAST 5 int refcount; bool synced; + bool global_use; struct rcu_head rcu_head; }; @@ -265,16 +248,20 @@ struct netdev_hw_addr_list { int count; }; -#define netdev_uc_count(dev) ((dev)->uc.count) -#define netdev_uc_empty(dev) ((dev)->uc.count == 0) -#define netdev_for_each_uc_addr(ha, dev) \ - list_for_each_entry(ha, &dev->uc.list, list) +#define netdev_hw_addr_list_count(l) ((l)->count) +#define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) +#define netdev_hw_addr_list_for_each(ha, l) \ + list_for_each_entry(ha, &(l)->list, list) -#define netdev_mc_count(dev) ((dev)->mc_count) -#define netdev_mc_empty(dev) (netdev_mc_count(dev) == 0) +#define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) +#define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) +#define netdev_for_each_uc_addr(ha, dev) \ + netdev_hw_addr_list_for_each(ha, &(dev)->uc) +#define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) +#define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(mclist, dev) \ - for (mclist = dev->mc_list; mclist; mclist = mclist->next) + netdev_hw_addr_list_for_each(ha, &(dev)->mc) struct hh_cache { struct hh_cache *hh_next; /* Next entry */ @@ -862,12 +849,10 @@ struct net_device { unsigned char addr_len; /* hardware address length */ unsigned short dev_id; /* for shared network cards */ - struct netdev_hw_addr_list uc; /* Secondary unicast - mac addresses */ - int uc_promisc; spinlock_t addr_list_lock; - struct dev_addr_list *mc_list; /* Multicast mac addresses */ - int mc_count; /* Number of installed mcasts */ + struct netdev_hw_addr_list uc; /* Unicast mac addresses */ + struct netdev_hw_addr_list mc; /* Multicast mac addresses */ + int uc_promisc; unsigned int promiscuity; unsigned int allmulti; @@ -1980,6 +1965,22 @@ extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, extern int register_netdev(struct net_device *dev); extern void unregister_netdev(struct net_device *dev); +/* General hardware address lists handling functions */ +extern int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type); +extern void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type); +extern int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); +extern void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len); +extern void __hw_addr_flush(struct netdev_hw_addr_list *list); +extern void __hw_addr_init(struct netdev_hw_addr_list *list); + /* Functions used for device addresses handling */ extern int dev_addr_add(struct net_device *dev, unsigned char *addr, unsigned char addr_type); @@ -2002,18 +2003,19 @@ extern void dev_uc_unsync(struct net_device *to, struct net_device *from); extern void dev_uc_flush(struct net_device *dev); extern void dev_uc_init(struct net_device *dev); +/* Functions used for multicast addresses handling */ +extern int dev_mc_add(struct net_device *dev, unsigned char *addr); +extern int dev_mc_add_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_del(struct net_device *dev, unsigned char *addr); +extern int dev_mc_del_global(struct net_device *dev, unsigned char *addr); +extern int dev_mc_sync(struct net_device *to, struct net_device *from); +extern void dev_mc_unsync(struct net_device *to, struct net_device *from); +extern void dev_mc_flush(struct net_device *dev); +extern void dev_mc_init(struct net_device *dev); + /* Functions used for secondary unicast and multicast support */ extern void dev_set_rx_mode(struct net_device *dev); extern void __dev_set_rx_mode(struct net_device *dev); -extern int dev_mc_delete(struct net_device *dev, void *addr, int alen, int all); -extern int dev_mc_add(struct net_device *dev, void *addr, int alen, int newonly); -extern int dev_mc_sync(struct net_device *to, struct net_device *from); -extern void dev_mc_unsync(struct net_device *to, struct net_device *from); -extern void dev_addr_discard(struct net_device *dev); -extern int __dev_addr_delete(struct dev_addr_list **list, int *count, void *addr, int alen, int all); -extern int __dev_addr_add(struct dev_addr_list **list, int *count, void *addr, int alen, int newonly); -extern int __dev_addr_sync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count); -extern void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count); extern int dev_set_promiscuity(struct net_device *dev, int inc); extern int dev_set_allmulti(struct net_device *dev, int inc); extern void netdev_state_change(struct net_device *dev); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 1a8f50af49a..20823d04e03 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1626,7 +1626,7 @@ struct ieee80211_ops { struct ieee80211_bss_conf *info, u32 changed); u64 (*prepare_multicast)(struct ieee80211_hw *hw, - int mc_count, struct dev_addr_list *mc_list); + struct netdev_hw_addr_list *mc_list); void (*configure_filter)(struct ieee80211_hw *hw, unsigned int changed_flags, unsigned int *total_flags, diff --git a/net/802/garp.c b/net/802/garp.c index 1dcb0660c49..78cff9ec2cb 100644 --- a/net/802/garp.c +++ b/net/802/garp.c @@ -575,7 +575,7 @@ int garp_init_applicant(struct net_device *dev, struct garp_application *appl) if (!app) goto err2; - err = dev_mc_add(dev, appl->proto.group_address, ETH_ALEN, 0); + err = dev_mc_add(dev, appl->proto.group_address); if (err < 0) goto err3; @@ -615,7 +615,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl garp_pdu_queue(app); garp_queue_xmit(app); - dev_mc_delete(dev, appl->proto.group_address, ETH_ALEN, 0); + dev_mc_del(dev, appl->proto.group_address); kfree(app); garp_release_port(dev); } diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 9fc4da56fb1..1d15a60b23a 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -781,7 +781,7 @@ static int atif_ioctl(int cmd, void __user *arg) atrtr_create(&rtdef, dev); } } - dev_mc_add(dev, aarp_mcast, 6, 1); + dev_mc_add_global(dev, aarp_mcast); return 0; case SIOCGIFADDR: diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index 326ab453edb..260a9507e54 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -87,7 +87,7 @@ static void bnep_net_set_mc_list(struct net_device *dev) memcpy(__skb_put(skb, ETH_ALEN), dev->broadcast, ETH_ALEN); r->len = htons(ETH_ALEN * 2); } else { - struct dev_mc_list *dmi; + struct netdev_hw_addr *ha; int i, len = skb->len; if (dev->flags & IFF_BROADCAST) { @@ -98,11 +98,11 @@ static void bnep_net_set_mc_list(struct net_device *dev) /* FIXME: We should group addresses here. */ i = 0; - netdev_for_each_mc_addr(dmi, dev) { + netdev_for_each_mc_addr(ha, dev) { if (i == BNEP_MAX_MULTICAST_FILTERS) break; - memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN); - memcpy(__skb_put(skb, ETH_ALEN), dmi->dmi_addr, ETH_ALEN); + memcpy(__skb_put(skb, ETH_ALEN), ha->addr, ETH_ALEN); + memcpy(__skb_put(skb, ETH_ALEN), ha->addr, ETH_ALEN); } r->len = htons(skb->len - len); } diff --git a/net/core/Makefile b/net/core/Makefile index 0a899f1aadb..51c3eec850e 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -7,9 +7,8 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ - neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ - dev_addr_lists.o +obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ + neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o obj-y += net-sysfs.o diff --git a/net/core/dev.c b/net/core/dev.c index 949c62dba71..2a9b7dd0bb6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3968,140 +3968,6 @@ void dev_set_rx_mode(struct net_device *dev) netif_addr_unlock_bh(dev); } -/* multicast addresses handling functions */ - -int __dev_addr_delete(struct dev_addr_list **list, int *count, - void *addr, int alen, int glbl) -{ - struct dev_addr_list *da; - - for (; (da = *list) != NULL; list = &da->next) { - if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && - alen == da->da_addrlen) { - if (glbl) { - int old_glbl = da->da_gusers; - da->da_gusers = 0; - if (old_glbl == 0) - break; - } - if (--da->da_users) - return 0; - - *list = da->next; - kfree(da); - (*count)--; - return 0; - } - } - return -ENOENT; -} - -int __dev_addr_add(struct dev_addr_list **list, int *count, - void *addr, int alen, int glbl) -{ - struct dev_addr_list *da; - - for (da = *list; da != NULL; da = da->next) { - if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && - da->da_addrlen == alen) { - if (glbl) { - int old_glbl = da->da_gusers; - da->da_gusers = 1; - if (old_glbl) - return 0; - } - da->da_users++; - return 0; - } - } - - da = kzalloc(sizeof(*da), GFP_ATOMIC); - if (da == NULL) - return -ENOMEM; - memcpy(da->da_addr, addr, alen); - da->da_addrlen = alen; - da->da_users = 1; - da->da_gusers = glbl ? 1 : 0; - da->next = *list; - *list = da; - (*count)++; - return 0; -} - - -int __dev_addr_sync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - int err = 0; - - da = *from; - while (da != NULL) { - next = da->next; - if (!da->da_synced) { - err = __dev_addr_add(to, to_count, - da->da_addr, da->da_addrlen, 0); - if (err < 0) - break; - da->da_synced = 1; - da->da_users++; - } else if (da->da_users == 1) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } - return err; -} -EXPORT_SYMBOL_GPL(__dev_addr_sync); - -void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - - da = *from; - while (da != NULL) { - next = da->next; - if (da->da_synced) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - da->da_synced = 0; - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } -} -EXPORT_SYMBOL_GPL(__dev_addr_unsync); - -static void __dev_addr_discard(struct dev_addr_list **list) -{ - struct dev_addr_list *tmp; - - while (*list != NULL) { - tmp = *list; - *list = tmp->next; - if (tmp->da_users > tmp->da_gusers) - printk("__dev_addr_discard: address leakage! " - "da_users=%d\n", tmp->da_users); - kfree(tmp); - } -} - -void dev_addr_discard(struct net_device *dev) -{ - netif_addr_lock_bh(dev); - - __dev_addr_discard(&dev->mc_list); - netdev_mc_count(dev) = 0; - - netif_addr_unlock_bh(dev); -} -EXPORT_SYMBOL(dev_addr_discard); - /** * dev_get_flags - get flags reported to userspace * @dev: device @@ -4412,8 +4278,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); case SIOCDELMULTI: if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || @@ -4421,8 +4286,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); case SIOCSIFTXQLEN: if (ifr->ifr_qlen < 0) @@ -4730,7 +4594,7 @@ static void rollback_registered_many(struct list_head *head) * Flush the unicast and multicast chains */ dev_uc_flush(dev); - dev_addr_discard(dev); + dev_mc_flush(dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -5310,6 +5174,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, if (dev_addr_init(dev)) goto free_rx; + dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); @@ -5545,7 +5410,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * Flush the unicast and multicast chains */ dev_uc_flush(dev); - dev_addr_discard(dev); + dev_mc_flush(dev); netdev_unregister_kobject(dev); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 7e52b6d18ad..37d5975e18a 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -19,8 +19,9 @@ * General list handling functions */ -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; int alloc_size; @@ -31,6 +32,13 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, list_for_each_entry(ha, &list->list, list) { if (!memcmp(ha->addr, addr, addr_len) && ha->type == addr_type) { + if (global) { + /* check if addr is already used as global */ + if (ha->global_use) + return 0; + else + ha->global_use = true; + } ha->refcount++; return 0; } @@ -46,12 +54,19 @@ static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, memcpy(ha->addr, addr, addr_len); ha->type = addr_type; ha->refcount = 1; + ha->global_use = global; ha->synced = false; list_add_tail_rcu(&ha->list, &list->list); list->count++; return 0; } +static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); +} + static void ha_rcu_free(struct rcu_head *head) { struct netdev_hw_addr *ha; @@ -60,14 +75,21 @@ static void ha_rcu_free(struct rcu_head *head) kfree(ha); } -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) { struct netdev_hw_addr *ha; list_for_each_entry(ha, &list->list, list) { if (!memcmp(ha->addr, addr, addr_len) && (ha->type == addr_type || !addr_type)) { + if (global) { + if (!ha->global_use) + break; + else + ha->global_use = false; + } if (--ha->refcount) return 0; list_del_rcu(&ha->list); @@ -79,10 +101,15 @@ static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, return -ENOENT; } -static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) +static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); +} + +int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type) { int err; struct netdev_hw_addr *ha, *ha2; @@ -105,11 +132,11 @@ unroll: } return err; } +EXPORT_SYMBOL(__hw_addr_add_multiple); -static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) +void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type) { struct netdev_hw_addr *ha; unsigned char type; @@ -119,10 +146,11 @@ static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, __hw_addr_del(to_list, ha->addr, addr_len, addr_type); } } +EXPORT_SYMBOL(__hw_addr_del_multiple); -static int __hw_addr_sync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) +int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) { int err = 0; struct netdev_hw_addr *ha, *tmp; @@ -142,10 +170,11 @@ static int __hw_addr_sync(struct netdev_hw_addr_list *to_list, } return err; } +EXPORT_SYMBOL(__hw_addr_sync); -static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) +void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) { struct netdev_hw_addr *ha, *tmp; @@ -159,8 +188,9 @@ static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, } } } +EXPORT_SYMBOL(__hw_addr_unsync); -static void __hw_addr_flush(struct netdev_hw_addr_list *list) +void __hw_addr_flush(struct netdev_hw_addr_list *list) { struct netdev_hw_addr *ha, *tmp; @@ -170,12 +200,14 @@ static void __hw_addr_flush(struct netdev_hw_addr_list *list) } list->count = 0; } +EXPORT_SYMBOL(__hw_addr_flush); -static void __hw_addr_init(struct netdev_hw_addr_list *list) +void __hw_addr_init(struct netdev_hw_addr_list *list) { INIT_LIST_HEAD(&list->list); list->count = 0; } +EXPORT_SYMBOL(__hw_addr_init); /* * Device addresses handling functions @@ -475,4 +507,235 @@ EXPORT_SYMBOL(dev_uc_init); * Multicast list handling functions */ -/* To be filled here */ +static int __dev_mc_add(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +/** + * dev_mc_add - Add a multicast address + * @dev: device + * @addr: address to add + * + * Add a multicast address to the device or increase + * the reference count if it already exists. + */ +int dev_mc_add(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_add); + +/** + * dev_mc_add_global - Add a global multicast address + * @dev: device + * @addr: address to add + * + * Add a global multicast address to the device. + */ +int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_add_global); + +static int __dev_mc_del(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} + +/** + * dev_mc_del - Delete a multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_del); + +/** + * dev_mc_del_global - Delete a global multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_del_global); + +/** + * dev_mc_sync - Synchronize device's unicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. + * + * This function is intended to be called from the dev->set_multicast_list + * or dev->set_rx_mode function of layered software devices. + */ +int dev_mc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_bh(to); + err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync); + +/** + * dev_mc_unsync - Remove synchronized addresses from the destination device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_mc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_mc_unsync(struct net_device *to, struct net_device *from) +{ + if (to->addr_len != from->addr_len) + return; + + netif_addr_lock_bh(from); + netif_addr_lock(to); + __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_mc_unsync); + +/** + * dev_mc_flush - Flush multicast addresses + * @dev: device + * + * Flush multicast addresses. + */ +void dev_mc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->mc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_mc_flush); + +/** + * dev_mc_flush - Init multicast address list + * @dev: device + * + * Init multicast address list. + */ +void dev_mc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->mc); +} +EXPORT_SYMBOL(dev_mc_init); + +#ifdef CONFIG_PROC_FS +#include +#include + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +#endif + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + proc_net_remove(net, "dev_mcast"); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +void __init dev_mcast_init(void) +{ + register_pernet_subsys(&dev_mc_net_ops); +} + diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c deleted file mode 100644 index 3dc295beb48..00000000000 --- a/net/core/dev_mcast.c +++ /dev/null @@ -1,232 +0,0 @@ -/* - * Linux NET3: Multicast List maintenance. - * - * Authors: - * Tim Kordas - * Richard Underwood - * - * Stir fried together from the IP multicast and CAP patches above - * Alan Cox - * - * Fixes: - * Alan Cox : Update the device on a real delete - * rather than any time but... - * Alan Cox : IFF_ALLMULTI support. - * Alan Cox : New format set_multicast_list() calls. - * Gleb Natapov : Remove dev_mc_lock. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - - -/* - * Device multicast list maintenance. - * - * This is used both by IP and by the user level maintenance functions. - * Unlike BSD we maintain a usage count on a given multicast address so - * that a casual user application can add/delete multicasts used by - * protocols without doing damage to the protocols when it deletes the - * entries. It also helps IP as it tracks overlapping maps. - * - * Device mc lists are changed by bh at least if IPv6 is enabled, - * so that it must be bh protected. - * - * We block accesses to device mc filters with netif_tx_lock. - */ - -/* - * Delete a device level multicast - */ - -int dev_mc_delete(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - err = __dev_addr_delete(&dev->mc_list, &dev->mc_count, - addr, alen, glbl); - if (!err) { - /* - * We have altered the list, so the card - * loaded filter is now wrong. Fix it - */ - - __dev_set_rx_mode(dev); - } - netif_addr_unlock_bh(dev); - return err; -} - -/* - * Add a device level multicast - */ - -int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - if (alen != dev->addr_len) - err = -EINVAL; - else - err = __dev_addr_add(&dev->mc_list, &dev->mc_count, addr, alen, glbl); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); - return err; -} - -/** - * dev_mc_sync - Synchronize device's multicast list to another device - * @to: destination device - * @from: source device - * - * Add newly added addresses to the destination device and release - * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. - * - * This function is intended to be called from the dev->set_multicast_list - * or dev->set_rx_mode function of layered software devices. - */ -int dev_mc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0; - - netif_addr_lock_bh(to); - err = __dev_addr_sync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - if (!err) - __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); - - return err; -} -EXPORT_SYMBOL(dev_mc_sync); - - -/** - * dev_mc_unsync - Remove synchronized addresses from the destination - * device - * @to: destination device - * @from: source device - * - * Remove all addresses that were added to the destination device by - * dev_mc_sync(). This function is intended to be called from the - * dev->stop function of layered software devices. - */ -void dev_mc_unsync(struct net_device *to, struct net_device *from) -{ - netif_addr_lock_bh(from); - netif_addr_lock(to); - - __dev_addr_unsync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - __dev_set_rx_mode(to); - - netif_addr_unlock(to); - netif_addr_unlock_bh(from); -} -EXPORT_SYMBOL(dev_mc_unsync); - -#ifdef CONFIG_PROC_FS -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct dev_addr_list *m; - struct net_device *dev = v; - - if (v == SEQ_START_TOKEN) - return 0; - - netif_addr_lock_bh(dev); - for (m = dev->mc_list; m; m = m->next) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, m->dmi_users, m->dmi_gusers); - - for (i = 0; i < m->dmi_addrlen; i++) - seq_printf(seq, "%02x", m->dmi_addr[i]); - - seq_putc(seq, '\n'); - } - netif_addr_unlock_bh(dev); - return 0; -} - -static const struct seq_operations dev_mc_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -#endif - -static int __net_init dev_mc_net_init(struct net *net) -{ - if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) - return -ENOMEM; - return 0; -} - -static void __net_exit dev_mc_net_exit(struct net *net) -{ - proc_net_remove(net, "dev_mcast"); -} - -static struct pernet_operations __net_initdata dev_mc_net_ops = { - .init = dev_mc_net_init, - .exit = dev_mc_net_exit, -}; - -void __init dev_mcast_init(void) -{ - register_pernet_subsys(&dev_mc_net_ops); -} - -EXPORT_SYMBOL(dev_mc_add); -EXPORT_SYMBOL(dev_mc_delete); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 238af093495..f3e4734d207 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -349,7 +349,7 @@ static void dn_dev_del_ifa(struct dn_dev *dn_db, struct dn_ifaddr **ifap, int de if (dn_db->dev->type == ARPHRD_ETHER) { if (ifa1->ifa_local != dn_eth2dn(dev->dev_addr)) { dn_dn2eth(mac_addr, ifa1->ifa_local); - dev_mc_delete(dev, mac_addr, ETH_ALEN, 0); + dev_mc_del(dev, mac_addr); } } @@ -380,7 +380,7 @@ static int dn_dev_insert_ifa(struct dn_dev *dn_db, struct dn_ifaddr *ifa) if (dev->type == ARPHRD_ETHER) { if (ifa->ifa_local != dn_eth2dn(dev->dev_addr)) { dn_dn2eth(mac_addr, ifa->ifa_local); - dev_mc_add(dev, mac_addr, ETH_ALEN, 0); + dev_mc_add(dev, mac_addr); } } @@ -1000,9 +1000,9 @@ static int dn_eth_up(struct net_device *dev) struct dn_dev *dn_db = dev->dn_ptr; if (dn_db->parms.forwarding == 0) - dev_mc_add(dev, dn_rt_all_end_mcast, ETH_ALEN, 0); + dev_mc_add(dev, dn_rt_all_end_mcast); else - dev_mc_add(dev, dn_rt_all_rt_mcast, ETH_ALEN, 0); + dev_mc_add(dev, dn_rt_all_rt_mcast); dn_db->use_long = 1; @@ -1014,9 +1014,9 @@ static void dn_eth_down(struct net_device *dev) struct dn_dev *dn_db = dev->dn_ptr; if (dn_db->parms.forwarding == 0) - dev_mc_delete(dev, dn_rt_all_end_mcast, ETH_ALEN, 0); + dev_mc_del(dev, dn_rt_all_end_mcast); else - dev_mc_delete(dev, dn_rt_all_rt_mcast, ETH_ALEN, 0); + dev_mc_del(dev, dn_rt_all_rt_mcast); } static void dn_dev_set_timer(struct net_device *dev); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 63bf298ca10..51824c42b77 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -997,7 +997,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_add(dev, buf, dev->addr_len, 0); + dev_mc_add(dev, buf); } /* @@ -1010,7 +1010,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_delete(dev, buf, dev->addr_len, 0); + dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 0886f96c736..a2208b7b313 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -87,7 +87,7 @@ clusterip_config_entry_put(struct clusterip_config *c) list_del(&c->list); write_unlock_bh(&clusterip_lock); - dev_mc_delete(c->dev, c->clustermac, ETH_ALEN, 0); + dev_mc_del(c->dev, c->clustermac); dev_put(c->dev); /* In case anyone still accesses the file, the open/close @@ -396,7 +396,7 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) dev_put(dev); return false; } - dev_mc_add(config->dev,config->clustermac, ETH_ALEN, 0); + dev_mc_add(config->dev, config->clustermac); } } cipinfo->config = config; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index bcd97191596..37d1868c006 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -714,7 +714,7 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) if (!(mc->mca_flags&MAF_LOADED)) { mc->mca_flags |= MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_add(dev, buf, dev->addr_len, 0); + dev_mc_add(dev, buf); } spin_unlock_bh(&mc->mca_lock); @@ -740,7 +740,7 @@ static void igmp6_group_dropped(struct ifmcaddr6 *mc) if (mc->mca_flags&MAF_LOADED) { mc->mca_flags &= ~MAF_LOADED; if (ndisc_mc_map(&mc->mca_addr, buf, dev, 0) == 0) - dev_mc_delete(dev, buf, dev->addr_len, 0); + dev_mc_del(dev, buf); } if (mc->mca_flags & MAF_NOREPORT) diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index c3d844093a2..9179196da26 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -84,16 +84,14 @@ static inline void drv_bss_info_changed(struct ieee80211_local *local, } static inline u64 drv_prepare_multicast(struct ieee80211_local *local, - int mc_count, - struct dev_addr_list *mc_list) + struct netdev_hw_addr_list *mc_list) { u64 ret = 0; if (local->ops->prepare_multicast) - ret = local->ops->prepare_multicast(&local->hw, mc_count, - mc_list); + ret = local->ops->prepare_multicast(&local->hw, mc_list); - trace_drv_prepare_multicast(local, mc_count, ret); + trace_drv_prepare_multicast(local, mc_list->count, ret); return ret; } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index ab369e2a528..7fdacf9408b 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -646,8 +646,7 @@ struct ieee80211_local { struct work_struct recalc_smps; /* aggregated multicast list */ - struct dev_addr_list *mc_list; - int mc_count; + struct netdev_hw_addr_list mc_list; bool tim_in_locked_section; /* see ieee80211_beacon_get() */ diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index b4ec59a8dc0..00f3a93c6b0 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -412,8 +412,7 @@ static int ieee80211_stop(struct net_device *dev) netif_addr_lock_bh(dev); spin_lock_bh(&local->filter_lock); - __dev_addr_unsync(&local->mc_list, &local->mc_count, - &dev->mc_list, &dev->mc_count); + __hw_addr_unsync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); netif_addr_unlock_bh(dev); @@ -596,8 +595,7 @@ static void ieee80211_set_multicast_list(struct net_device *dev) sdata->flags ^= IEEE80211_SDATA_PROMISC; } spin_lock_bh(&local->filter_lock); - __dev_addr_sync(&local->mc_list, &local->mc_count, - &dev->mc_list, &dev->mc_count); + __hw_addr_sync(&local->mc_list, &dev->mc, dev->addr_len); spin_unlock_bh(&local->filter_lock); ieee80211_queue_work(&local->hw, &local->reconfig_filter); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 06c33b68d8e..84ad249a4e2 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -71,7 +71,7 @@ void ieee80211_configure_filter(struct ieee80211_local *local) spin_lock_bh(&local->filter_lock); changed_flags = local->filter_flags ^ new_flags; - mc = drv_prepare_multicast(local, local->mc_count, local->mc_list); + mc = drv_prepare_multicast(local, &local->mc_list); spin_unlock_bh(&local->filter_lock); /* be a bit nasty */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 48c1e0ae565..b0f037cc899 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1691,9 +1691,9 @@ static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) - return dev_mc_add(dev, i->addr, i->alen, 0); + return dev_mc_add(dev, i->addr); else - return dev_mc_delete(dev, i->addr, i->alen, 0); + return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); -- cgit v1.2.3-70-g09d2 From fe1a5f031e76bd8761a7803d75b95ee96e84a574 Mon Sep 17 00:00:00 2001 From: Timo Teräs Date: Wed, 7 Apr 2010 00:30:04 +0000 Subject: flow: virtualize flow cache entry methods This allows to validate the cached object before returning it. It also allows to destruct object properly, if the last reference was held in flow cache. This is also a prepartion for caching bundles in the flow cache. In return for virtualizing the methods, we save on: - not having to regenerate the whole flow cache on policy removal: each flow matching a killed policy gets refreshed as the getter function notices it smartly. - we do not have to call flow_cache_flush from policy gc, since the flow cache now properly deletes the object if it had any references Signed-off-by: Timo Teras Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/flow.h | 23 +++++++-- include/net/xfrm.h | 2 + net/core/flow.c | 128 ++++++++++++++++++++++++++----------------------- net/xfrm/xfrm_policy.c | 112 ++++++++++++++++++++++++++++--------------- 4 files changed, 163 insertions(+), 102 deletions(-) (limited to 'include/net') diff --git a/include/net/flow.h b/include/net/flow.h index 809970b7dfe..bb08692a20b 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -86,11 +86,26 @@ struct flowi { struct net; struct sock; -typedef int (*flow_resolve_t)(struct net *net, struct flowi *key, u16 family, - u8 dir, void **objp, atomic_t **obj_refp); +struct flow_cache_ops; + +struct flow_cache_object { + const struct flow_cache_ops *ops; +}; + +struct flow_cache_ops { + struct flow_cache_object *(*get)(struct flow_cache_object *); + int (*check)(struct flow_cache_object *); + void (*delete)(struct flow_cache_object *); +}; + +typedef struct flow_cache_object *(*flow_resolve_t)( + struct net *net, struct flowi *key, u16 family, + u8 dir, struct flow_cache_object *oldobj, void *ctx); + +extern struct flow_cache_object *flow_cache_lookup( + struct net *net, struct flowi *key, u16 family, + u8 dir, flow_resolve_t resolver, void *ctx); -extern void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, - u8 dir, flow_resolve_t resolver); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d74e080ba6c..35396e2dd1d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -19,6 +19,7 @@ #include #include #include +#include #include @@ -481,6 +482,7 @@ struct xfrm_policy { atomic_t refcnt; struct timer_list timer; + struct flow_cache_object flo; u32 priority; u32 index; struct xfrm_mark mark; diff --git a/net/core/flow.c b/net/core/flow.c index 1d27ca6b421..521df52a77d 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -26,17 +26,16 @@ #include struct flow_cache_entry { - struct flow_cache_entry *next; - u16 family; - u8 dir; - u32 genid; - struct flowi key; - void *object; - atomic_t *object_ref; + struct flow_cache_entry *next; + u16 family; + u8 dir; + u32 genid; + struct flowi key; + struct flow_cache_object *object; }; struct flow_cache_percpu { - struct flow_cache_entry ** hash_table; + struct flow_cache_entry **hash_table; int hash_count; u32 hash_rnd; int hash_rnd_recalc; @@ -44,7 +43,7 @@ struct flow_cache_percpu { }; struct flow_flush_info { - struct flow_cache * cache; + struct flow_cache *cache; atomic_t cpuleft; struct completion completion; }; @@ -52,7 +51,7 @@ struct flow_flush_info { struct flow_cache { u32 hash_shift; unsigned long order; - struct flow_cache_percpu * percpu; + struct flow_cache_percpu *percpu; struct notifier_block hotcpu_notifier; int low_watermark; int high_watermark; @@ -78,12 +77,21 @@ static void flow_cache_new_hashrnd(unsigned long arg) add_timer(&fc->rnd_timer); } +static int flow_entry_valid(struct flow_cache_entry *fle) +{ + if (atomic_read(&flow_cache_genid) != fle->genid) + return 0; + if (fle->object && !fle->object->ops->check(fle->object)) + return 0; + return 1; +} + static void flow_entry_kill(struct flow_cache *fc, struct flow_cache_percpu *fcp, struct flow_cache_entry *fle) { if (fle->object) - atomic_dec(fle->object_ref); + fle->object->ops->delete(fle->object); kmem_cache_free(flow_cachep, fle); fcp->hash_count--; } @@ -96,16 +104,18 @@ static void __flow_cache_shrink(struct flow_cache *fc, int i; for (i = 0; i < flow_cache_hash_size(fc); i++) { - int k = 0; + int saved = 0; flp = &fcp->hash_table[i]; - while ((fle = *flp) != NULL && k < shrink_to) { - k++; - flp = &fle->next; - } while ((fle = *flp) != NULL) { - *flp = fle->next; - flow_entry_kill(fc, fcp, fle); + if (saved < shrink_to && + flow_entry_valid(fle)) { + saved++; + flp = &fle->next; + } else { + *flp = fle->next; + flow_entry_kill(fc, fcp, fle); + } } } } @@ -166,18 +176,21 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, - flow_resolve_t resolver) +struct flow_cache_object * +flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, + flow_resolve_t resolver, void *ctx) { struct flow_cache *fc = &flow_cache_global; struct flow_cache_percpu *fcp; struct flow_cache_entry *fle, **head; + struct flow_cache_object *flo; unsigned int hash; local_bh_disable(); fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); fle = NULL; + flo = NULL; /* Packet really early in init? Making flow_cache_init a * pre-smp initcall would solve this. --RR */ if (!fcp->hash_table) @@ -185,27 +198,17 @@ void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, if (fcp->hash_rnd_recalc) flow_new_hash_rnd(fc, fcp); - hash = flow_hash_code(fc, fcp, key); + hash = flow_hash_code(fc, fcp, key); head = &fcp->hash_table[hash]; for (fle = *head; fle; fle = fle->next) { if (fle->family == family && fle->dir == dir && - flow_key_compare(key, &fle->key) == 0) { - if (fle->genid == atomic_read(&flow_cache_genid)) { - void *ret = fle->object; - - if (ret) - atomic_inc(fle->object_ref); - local_bh_enable(); - - return ret; - } + flow_key_compare(key, &fle->key) == 0) break; - } } - if (!fle) { + if (unlikely(!fle)) { if (fcp->hash_count > fc->high_watermark) flow_cache_shrink(fc, fcp); @@ -219,33 +222,39 @@ void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, fle->object = NULL; fcp->hash_count++; } + } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + flo = fle->object; + if (!flo) + goto ret_object; + flo = flo->ops->get(flo); + if (flo) + goto ret_object; + } else if (fle->object) { + flo = fle->object; + flo->ops->delete(flo); + fle->object = NULL; } nocache: - { - int err; - void *obj; - atomic_t *obj_ref; - - err = resolver(net, key, family, dir, &obj, &obj_ref); - - if (fle && !err) { - fle->genid = atomic_read(&flow_cache_genid); - - if (fle->object) - atomic_dec(fle->object_ref); - - fle->object = obj; - fle->object_ref = obj_ref; - if (obj) - atomic_inc(fle->object_ref); - } - local_bh_enable(); - - if (err) - obj = ERR_PTR(err); - return obj; + flo = NULL; + if (fle) { + flo = fle->object; + fle->object = NULL; + } + flo = resolver(net, key, family, dir, flo, ctx); + if (fle) { + fle->genid = atomic_read(&flow_cache_genid); + if (!IS_ERR(flo)) + fle->object = flo; + else + fle->genid--; + } else { + if (flo && !IS_ERR(flo)) + flo->ops->delete(flo); } +ret_object: + local_bh_enable(); + return flo; } static void flow_cache_flush_tasklet(unsigned long data) @@ -261,13 +270,12 @@ static void flow_cache_flush_tasklet(unsigned long data) fle = fcp->hash_table[i]; for (; fle; fle = fle->next) { - unsigned genid = atomic_read(&flow_cache_genid); - - if (!fle->object || fle->genid == genid) + if (flow_entry_valid(fle)) continue; + if (fle->object) + fle->object->ops->delete(fle->object); fle->object = NULL; - atomic_dec(fle->object_ref); } } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 82789cf1c63..7722baeb140 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -216,6 +216,35 @@ expired: xfrm_pol_put(xp); } +static struct flow_cache_object *xfrm_policy_flo_get(struct flow_cache_object *flo) +{ + struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo); + + if (unlikely(pol->walk.dead)) + flo = NULL; + else + xfrm_pol_hold(pol); + + return flo; +} + +static int xfrm_policy_flo_check(struct flow_cache_object *flo) +{ + struct xfrm_policy *pol = container_of(flo, struct xfrm_policy, flo); + + return !pol->walk.dead; +} + +static void xfrm_policy_flo_delete(struct flow_cache_object *flo) +{ + xfrm_pol_put(container_of(flo, struct xfrm_policy, flo)); +} + +static const struct flow_cache_ops xfrm_policy_fc_ops = { + .get = xfrm_policy_flo_get, + .check = xfrm_policy_flo_check, + .delete = xfrm_policy_flo_delete, +}; /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2 * SPD calls. @@ -236,6 +265,7 @@ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) atomic_set(&policy->refcnt, 1); setup_timer(&policy->timer, xfrm_policy_timer, (unsigned long)policy); + policy->flo.ops = &xfrm_policy_fc_ops; } return policy; } @@ -269,9 +299,6 @@ static void xfrm_policy_gc_kill(struct xfrm_policy *policy) if (del_timer(&policy->timer)) atomic_dec(&policy->refcnt); - if (atomic_read(&policy->refcnt) > 1) - flow_cache_flush(); - xfrm_pol_put(policy); } @@ -661,10 +688,8 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type, } write_unlock_bh(&xfrm_policy_lock); - if (ret && delete) { - atomic_inc(&flow_cache_genid); + if (ret && delete) xfrm_policy_kill(ret); - } return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); @@ -703,10 +728,8 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type, } write_unlock_bh(&xfrm_policy_lock); - if (ret && delete) { - atomic_inc(&flow_cache_genid); + if (ret && delete) xfrm_policy_kill(ret); - } return ret; } EXPORT_SYMBOL(xfrm_policy_byid); @@ -822,7 +845,6 @@ int xfrm_policy_flush(struct net *net, u8 type, struct xfrm_audit *audit_info) } if (!cnt) err = -ESRCH; - atomic_inc(&flow_cache_genid); out: write_unlock_bh(&xfrm_policy_lock); return err; @@ -976,32 +998,35 @@ fail: return ret; } -static int xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, - u8 dir, void **objp, atomic_t **obj_refp) +static struct flow_cache_object * +xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, + u8 dir, struct flow_cache_object *old_obj, void *ctx) { struct xfrm_policy *pol; - int err = 0; + + if (old_obj) + xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo)); #ifdef CONFIG_XFRM_SUB_POLICY pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); - pol = NULL; - } - if (pol || err) - goto end; + if (IS_ERR(pol)) + return ERR_CAST(pol); + if (pol) + goto found; #endif pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); - if (IS_ERR(pol)) { - err = PTR_ERR(pol); - pol = NULL; - } -#ifdef CONFIG_XFRM_SUB_POLICY -end: -#endif - if ((*objp = (void *) pol) != NULL) - *obj_refp = &pol->refcnt; - return err; + if (IS_ERR(pol)) + return ERR_CAST(pol); + if (pol) + goto found; + return NULL; + +found: + /* Resolver returns two references: + * one for cache and one for caller of flow_cache_lookup() */ + xfrm_pol_hold(pol); + + return &pol->flo; } static inline int policy_to_flow_dir(int dir) @@ -1091,8 +1116,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir) pol = __xfrm_policy_unlink(pol, dir); write_unlock_bh(&xfrm_policy_lock); if (pol) { - if (dir < XFRM_POLICY_MAX) - atomic_inc(&flow_cache_genid); xfrm_policy_kill(pol); return 0; } @@ -1578,18 +1601,24 @@ restart: } if (!policy) { + struct flow_cache_object *flo; + /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - policy = flow_cache_lookup(net, fl, dst_orig->ops->family, - dir, xfrm_policy_lookup); - err = PTR_ERR(policy); - if (IS_ERR(policy)) { + flo = flow_cache_lookup(net, fl, dst_orig->ops->family, + dir, xfrm_policy_lookup, NULL); + err = PTR_ERR(flo); + if (IS_ERR(flo)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); goto dropdst; } + if (flo) + policy = container_of(flo, struct xfrm_policy, flo); + else + policy = NULL; } if (!policy) @@ -1939,9 +1968,16 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, } } - if (!pol) - pol = flow_cache_lookup(net, &fl, family, fl_dir, - xfrm_policy_lookup); + if (!pol) { + struct flow_cache_object *flo; + + flo = flow_cache_lookup(net, &fl, family, fl_dir, + xfrm_policy_lookup, NULL); + if (IS_ERR_OR_NULL(flo)) + pol = ERR_CAST(flo); + else + pol = container_of(flo, struct xfrm_policy, flo); + } if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); -- cgit v1.2.3-70-g09d2 From 80c802f3073e84c956846e921e8a0b02dfa3755f Mon Sep 17 00:00:00 2001 From: Timo Teräs Date: Wed, 7 Apr 2010 00:30:05 +0000 Subject: xfrm: cache bundles instead of policies for outgoing flows __xfrm_lookup() is called for each packet transmitted out of system. The xfrm_find_bundle() does a linear search which can kill system performance depending on how many bundles are required per policy. This modifies __xfrm_lookup() to store bundles directly in the flow cache. If we did not get a hit, we just create a new bundle instead of doing slow search. This means that we can now get multiple xfrm_dst's for same flow (on per-cpu basis). Signed-off-by: Timo Teras Signed-off-by: David S. Miller --- include/net/xfrm.h | 10 +- net/ipv4/xfrm4_policy.c | 22 -- net/ipv6/xfrm6_policy.c | 31 --- net/xfrm/xfrm_policy.c | 711 +++++++++++++++++++++++++----------------------- 4 files changed, 383 insertions(+), 391 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 35396e2dd1d..625dd61ccbb 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -267,7 +267,6 @@ struct xfrm_policy_afinfo { xfrm_address_t *saddr, xfrm_address_t *daddr); int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr); - struct dst_entry *(*find_bundle)(struct flowi *fl, struct xfrm_policy *policy); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); @@ -483,13 +482,13 @@ struct xfrm_policy { struct timer_list timer; struct flow_cache_object flo; + atomic_t genid; u32 priority; u32 index; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; - struct dst_entry *bundles; struct xfrm_policy_walk_entry walk; u8 type; u8 action; @@ -879,11 +878,15 @@ struct xfrm_dst { struct rt6_info rt6; } u; struct dst_entry *route; + struct flow_cache_object flo; + struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; + int num_pols, num_xfrms; #ifdef CONFIG_XFRM_SUB_POLICY struct flowi *origin; struct xfrm_selector *partner; #endif - u32 genid; + u32 xfrm_genid; + u32 policy_genid; u32 route_mtu_cached; u32 child_mtu_cached; u32 route_cookie; @@ -893,6 +896,7 @@ struct xfrm_dst { #ifdef CONFIG_XFRM static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { + xfrm_pols_put(xdst->pols, xdst->num_pols); dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index e4a1483fba7..1705476670e 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -59,27 +59,6 @@ static int xfrm4_get_saddr(struct net *net, return 0; } -static struct dst_entry * -__xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) -{ - struct dst_entry *dst; - - read_lock_bh(&policy->lock); - for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/ - xdst->u.rt.fl.fl4_dst == fl->fl4_dst && - xdst->u.rt.fl.fl4_src == fl->fl4_src && - xdst->u.rt.fl.fl4_tos == fl->fl4_tos && - xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) { - dst_clone(dst); - break; - } - } - read_unlock_bh(&policy->lock); - return dst; -} - static int xfrm4_get_tos(struct flowi *fl) { return fl->fl4_tos; @@ -259,7 +238,6 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, - .find_bundle = __xfrm4_find_bundle, .decode_session = _decode_session4, .get_tos = xfrm4_get_tos, .init_path = xfrm4_init_path, diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index ae181651c75..8c452fd5cea 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -67,36 +67,6 @@ static int xfrm6_get_saddr(struct net *net, return 0; } -static struct dst_entry * -__xfrm6_find_bundle(struct flowi *fl, struct xfrm_policy *policy) -{ - struct dst_entry *dst; - - /* Still not clear if we should set fl->fl6_{src,dst}... */ - read_lock_bh(&policy->lock); - for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; - struct in6_addr fl_dst_prefix, fl_src_prefix; - - ipv6_addr_prefix(&fl_dst_prefix, - &fl->fl6_dst, - xdst->u.rt6.rt6i_dst.plen); - ipv6_addr_prefix(&fl_src_prefix, - &fl->fl6_src, - xdst->u.rt6.rt6i_src.plen); - if (ipv6_addr_equal(&xdst->u.rt6.rt6i_dst.addr, &fl_dst_prefix) && - ipv6_addr_equal(&xdst->u.rt6.rt6i_src.addr, &fl_src_prefix) && - xfrm_bundle_ok(policy, xdst, fl, AF_INET6, - (xdst->u.rt6.rt6i_dst.plen != 128 || - xdst->u.rt6.rt6i_src.plen != 128))) { - dst_clone(dst); - break; - } - } - read_unlock_bh(&policy->lock); - return dst; -} - static int xfrm6_get_tos(struct flowi *fl) { return 0; @@ -291,7 +261,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .dst_ops = &xfrm6_dst_ops, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, - .find_bundle = __xfrm6_find_bundle, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, .init_path = xfrm6_init_path, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7722baeb140..06ccc71c871 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -37,6 +37,8 @@ DEFINE_MUTEX(xfrm_cfg_mutex); EXPORT_SYMBOL(xfrm_cfg_mutex); +static DEFINE_SPINLOCK(xfrm_policy_sk_bundle_lock); +static struct dst_entry *xfrm_policy_sk_bundles; static DEFINE_RWLOCK(xfrm_policy_lock); static DEFINE_RWLOCK(xfrm_policy_afinfo_lock); @@ -50,6 +52,7 @@ static DEFINE_SPINLOCK(xfrm_policy_gc_lock); static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); +static int stale_bundle(struct dst_entry *dst); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); @@ -277,8 +280,6 @@ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); - BUG_ON(policy->bundles); - if (del_timer(&policy->timer)) BUG(); @@ -289,12 +290,7 @@ EXPORT_SYMBOL(xfrm_policy_destroy); static void xfrm_policy_gc_kill(struct xfrm_policy *policy) { - struct dst_entry *dst; - - while ((dst = policy->bundles) != NULL) { - policy->bundles = dst->next; - dst_free(dst); - } + atomic_inc(&policy->genid); if (del_timer(&policy->timer)) atomic_dec(&policy->refcnt); @@ -572,7 +568,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) struct xfrm_policy *delpol; struct hlist_head *chain; struct hlist_node *entry, *newpos; - struct dst_entry *gc_list; u32 mark = policy->mark.v & policy->mark.m; write_lock_bh(&xfrm_policy_lock); @@ -622,34 +617,6 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) else if (xfrm_bydst_should_resize(net, dir, NULL)) schedule_work(&net->xfrm.policy_hash_work); - read_lock_bh(&xfrm_policy_lock); - gc_list = NULL; - entry = &policy->bydst; - hlist_for_each_entry_continue(policy, entry, bydst) { - struct dst_entry *dst; - - write_lock(&policy->lock); - dst = policy->bundles; - if (dst) { - struct dst_entry *tail = dst; - while (tail->next) - tail = tail->next; - tail->next = gc_list; - gc_list = dst; - - policy->bundles = NULL; - } - write_unlock(&policy->lock); - } - read_unlock_bh(&xfrm_policy_lock); - - while (gc_list) { - struct dst_entry *dst = gc_list; - - gc_list = dst->next; - dst_free(dst); - } - return 0; } EXPORT_SYMBOL(xfrm_policy_insert); @@ -998,6 +965,19 @@ fail: return ret; } +static struct xfrm_policy * +__xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir) +{ +#ifdef CONFIG_XFRM_SUB_POLICY + struct xfrm_policy *pol; + + pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); + if (pol != NULL) + return pol; +#endif + return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); +} + static struct flow_cache_object * xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *old_obj, void *ctx) @@ -1007,21 +987,10 @@ xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, if (old_obj) xfrm_pol_put(container_of(old_obj, struct xfrm_policy, flo)); -#ifdef CONFIG_XFRM_SUB_POLICY - pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir); - if (IS_ERR(pol)) + pol = __xfrm_policy_lookup(net, fl, family, dir); + if (IS_ERR_OR_NULL(pol)) return ERR_CAST(pol); - if (pol) - goto found; -#endif - pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir); - if (IS_ERR(pol)) - return ERR_CAST(pol); - if (pol) - goto found; - return NULL; -found: /* Resolver returns two references: * one for cache and one for caller of flow_cache_lookup() */ xfrm_pol_hold(pol); @@ -1313,18 +1282,6 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, * still valid. */ -static struct dst_entry * -xfrm_find_bundle(struct flowi *fl, struct xfrm_policy *policy, unsigned short family) -{ - struct dst_entry *x; - struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); - if (unlikely(afinfo == NULL)) - return ERR_PTR(-EINVAL); - x = afinfo->find_bundle(fl, policy); - xfrm_policy_put_afinfo(afinfo); - return x; -} - static inline int xfrm_get_tos(struct flowi *fl, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); @@ -1340,6 +1297,54 @@ static inline int xfrm_get_tos(struct flowi *fl, int family) return tos; } +static struct flow_cache_object *xfrm_bundle_flo_get(struct flow_cache_object *flo) +{ + struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo); + struct dst_entry *dst = &xdst->u.dst; + + if (xdst->route == NULL) { + /* Dummy bundle - if it has xfrms we were not + * able to build bundle as template resolution failed. + * It means we need to try again resolving. */ + if (xdst->num_xfrms > 0) + return NULL; + } else { + /* Real bundle */ + if (stale_bundle(dst)) + return NULL; + } + + dst_hold(dst); + return flo; +} + +static int xfrm_bundle_flo_check(struct flow_cache_object *flo) +{ + struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo); + struct dst_entry *dst = &xdst->u.dst; + + if (!xdst->route) + return 0; + if (stale_bundle(dst)) + return 0; + + return 1; +} + +static void xfrm_bundle_flo_delete(struct flow_cache_object *flo) +{ + struct xfrm_dst *xdst = container_of(flo, struct xfrm_dst, flo); + struct dst_entry *dst = &xdst->u.dst; + + dst_free(dst); +} + +static const struct flow_cache_ops xfrm_bundle_fc_ops = { + .get = xfrm_bundle_flo_get, + .check = xfrm_bundle_flo_check, + .delete = xfrm_bundle_flo_delete, +}; + static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); @@ -1362,9 +1367,10 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) BUG(); } xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS); - xfrm_policy_put_afinfo(afinfo); + xdst->flo.ops = &xfrm_bundle_fc_ops; + return xdst; } @@ -1402,6 +1408,7 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, return err; } + /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ @@ -1465,7 +1472,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_hold(dst); dst1->xfrm = xfrm[i]; - xdst->genid = xfrm[i]->genid; + xdst->xfrm_genid = xfrm[i]->genid; dst1->obsolete = -1; dst1->flags |= DST_HOST; @@ -1558,7 +1565,186 @@ xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl) #endif } -static int stale_bundle(struct dst_entry *dst); +static int xfrm_expand_policies(struct flowi *fl, u16 family, + struct xfrm_policy **pols, + int *num_pols, int *num_xfrms) +{ + int i; + + if (*num_pols == 0 || !pols[0]) { + *num_pols = 0; + *num_xfrms = 0; + return 0; + } + if (IS_ERR(pols[0])) + return PTR_ERR(pols[0]); + + *num_xfrms = pols[0]->xfrm_nr; + +#ifdef CONFIG_XFRM_SUB_POLICY + if (pols[0] && pols[0]->action == XFRM_POLICY_ALLOW && + pols[0]->type != XFRM_POLICY_TYPE_MAIN) { + pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), + XFRM_POLICY_TYPE_MAIN, + fl, family, + XFRM_POLICY_OUT); + if (pols[1]) { + if (IS_ERR(pols[1])) { + xfrm_pols_put(pols, *num_pols); + return PTR_ERR(pols[1]); + } + (*num_pols) ++; + (*num_xfrms) += pols[1]->xfrm_nr; + } + } +#endif + for (i = 0; i < *num_pols; i++) { + if (pols[i]->action != XFRM_POLICY_ALLOW) { + *num_xfrms = -1; + break; + } + } + + return 0; + +} + +static struct xfrm_dst * +xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, + struct flowi *fl, u16 family, + struct dst_entry *dst_orig) +{ + struct net *net = xp_net(pols[0]); + struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; + struct dst_entry *dst; + struct xfrm_dst *xdst; + int err; + + /* Try to instantiate a bundle */ + err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); + if (err < 0) { + if (err != -EAGAIN) + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); + return ERR_PTR(err); + } + + dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig); + if (IS_ERR(dst)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); + return ERR_CAST(dst); + } + + xdst = (struct xfrm_dst *)dst; + xdst->num_xfrms = err; + if (num_pols > 1) + err = xfrm_dst_update_parent(dst, &pols[1]->selector); + else + err = xfrm_dst_update_origin(dst, fl); + if (unlikely(err)) { + dst_free(dst); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); + return ERR_PTR(err); + } + + xdst->num_pols = num_pols; + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + xdst->policy_genid = atomic_read(&pols[0]->genid); + + return xdst; +} + +static struct flow_cache_object * +xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir, + struct flow_cache_object *oldflo, void *ctx) +{ + struct dst_entry *dst_orig = (struct dst_entry *)ctx; + struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; + struct xfrm_dst *xdst, *new_xdst; + int num_pols = 0, num_xfrms = 0, i, err, pol_dead; + + /* Check if the policies from old bundle are usable */ + xdst = NULL; + if (oldflo) { + xdst = container_of(oldflo, struct xfrm_dst, flo); + num_pols = xdst->num_pols; + num_xfrms = xdst->num_xfrms; + pol_dead = 0; + for (i = 0; i < num_pols; i++) { + pols[i] = xdst->pols[i]; + pol_dead |= pols[i]->walk.dead; + } + if (pol_dead) { + dst_free(&xdst->u.dst); + xdst = NULL; + num_pols = 0; + num_xfrms = 0; + oldflo = NULL; + } + } + + /* Resolve policies to use if we couldn't get them from + * previous cache entry */ + if (xdst == NULL) { + num_pols = 1; + pols[0] = __xfrm_policy_lookup(net, fl, family, dir); + err = xfrm_expand_policies(fl, family, pols, + &num_pols, &num_xfrms); + if (err < 0) + goto inc_error; + if (num_pols == 0) + return NULL; + if (num_xfrms <= 0) + goto make_dummy_bundle; + } + + new_xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, dst_orig); + if (IS_ERR(new_xdst)) { + err = PTR_ERR(new_xdst); + if (err != -EAGAIN) + goto error; + if (oldflo == NULL) + goto make_dummy_bundle; + dst_hold(&xdst->u.dst); + return oldflo; + } + + /* Kill the previous bundle */ + if (xdst) { + /* The policies were stolen for newly generated bundle */ + xdst->num_pols = 0; + dst_free(&xdst->u.dst); + } + + /* Flow cache does not have reference, it dst_free()'s, + * but we do need to return one reference for original caller */ + dst_hold(&new_xdst->u.dst); + return &new_xdst->flo; + +make_dummy_bundle: + /* We found policies, but there's no bundles to instantiate: + * either because the policy blocks, has no transformations or + * we could not build template (no xfrm_states).*/ + xdst = xfrm_alloc_dst(net, family); + if (IS_ERR(xdst)) { + xfrm_pols_put(pols, num_pols); + return ERR_CAST(xdst); + } + xdst->num_pols = num_pols; + xdst->num_xfrms = num_xfrms; + memcpy(xdst->pols, pols, sizeof(struct xfrm_policy*) * num_pols); + + dst_hold(&xdst->u.dst); + return &xdst->flo; + +inc_error: + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); +error: + if (xdst != NULL) + dst_free(&xdst->u.dst); + else + xfrm_pols_put(pols, num_pols); + return ERR_PTR(err); +} /* Main function: finds/creates a bundle for given flow. * @@ -1568,248 +1754,152 @@ static int stale_bundle(struct dst_entry *dst); int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, struct sock *sk, int flags) { - struct xfrm_policy *policy; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; - int npols; - int pol_dead; - int xfrm_nr; - int pi; - struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; - struct dst_entry *dst, *dst_orig = *dst_p; - int nx = 0; - int err; - u32 genid; - u16 family; + struct flow_cache_object *flo; + struct xfrm_dst *xdst; + struct dst_entry *dst, *dst_orig = *dst_p, *route; + u16 family = dst_orig->ops->family; u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT); + int i, err, num_pols, num_xfrms, drop_pols = 0; restart: - genid = atomic_read(&flow_cache_genid); - policy = NULL; - for (pi = 0; pi < ARRAY_SIZE(pols); pi++) - pols[pi] = NULL; - npols = 0; - pol_dead = 0; - xfrm_nr = 0; + dst = NULL; + xdst = NULL; + route = NULL; if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { - policy = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); - err = PTR_ERR(policy); - if (IS_ERR(policy)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); + num_pols = 1; + pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl); + err = xfrm_expand_policies(fl, family, pols, + &num_pols, &num_xfrms); + if (err < 0) goto dropdst; + + if (num_pols) { + if (num_xfrms <= 0) { + drop_pols = num_pols; + goto no_transform; + } + + xdst = xfrm_resolve_and_create_bundle( + pols, num_pols, fl, + family, dst_orig); + if (IS_ERR(xdst)) { + xfrm_pols_put(pols, num_pols); + err = PTR_ERR(xdst); + goto dropdst; + } + + spin_lock_bh(&xfrm_policy_sk_bundle_lock); + xdst->u.dst.next = xfrm_policy_sk_bundles; + xfrm_policy_sk_bundles = &xdst->u.dst; + spin_unlock_bh(&xfrm_policy_sk_bundle_lock); + + route = xdst->route; } } - if (!policy) { - struct flow_cache_object *flo; - + if (xdst == NULL) { /* To accelerate a bit... */ if ((dst_orig->flags & DST_NOXFRM) || !net->xfrm.policy_count[XFRM_POLICY_OUT]) goto nopol; - flo = flow_cache_lookup(net, fl, dst_orig->ops->family, - dir, xfrm_policy_lookup, NULL); - err = PTR_ERR(flo); + flo = flow_cache_lookup(net, fl, family, dir, + xfrm_bundle_lookup, dst_orig); + if (flo == NULL) + goto nopol; if (IS_ERR(flo)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); + err = PTR_ERR(flo); goto dropdst; } - if (flo) - policy = container_of(flo, struct xfrm_policy, flo); - else - policy = NULL; + xdst = container_of(flo, struct xfrm_dst, flo); + + num_pols = xdst->num_pols; + num_xfrms = xdst->num_xfrms; + memcpy(pols, xdst->pols, sizeof(struct xfrm_policy*) * num_pols); + route = xdst->route; + } + + dst = &xdst->u.dst; + if (route == NULL && num_xfrms > 0) { + /* The only case when xfrm_bundle_lookup() returns a + * bundle with null route, is when the template could + * not be resolved. It means policies are there, but + * bundle could not be created, since we don't yet + * have the xfrm_state's. We need to wait for KM to + * negotiate new SA's or bail out with error.*/ + if (net->xfrm.sysctl_larval_drop) { + /* EREMOTE tells the caller to generate + * a one-shot blackhole route. */ + dst_release(dst); + xfrm_pols_put(pols, num_pols); + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); + return -EREMOTE; + } + if (flags & XFRM_LOOKUP_WAIT) { + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue(&net->xfrm.km_waitq, &wait); + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + set_current_state(TASK_RUNNING); + remove_wait_queue(&net->xfrm.km_waitq, &wait); + + if (!signal_pending(current)) { + dst_release(dst); + goto restart; + } + + err = -ERESTART; + } else + err = -EAGAIN; + + XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); + goto error; } - if (!policy) +no_transform: + if (num_pols == 0) goto nopol; - family = dst_orig->ops->family; - pols[0] = policy; - npols ++; - xfrm_nr += pols[0]->xfrm_nr; - - err = -ENOENT; - if ((flags & XFRM_LOOKUP_ICMP) && !(policy->flags & XFRM_POLICY_ICMP)) + if ((flags & XFRM_LOOKUP_ICMP) && + !(pols[0]->flags & XFRM_POLICY_ICMP)) { + err = -ENOENT; goto error; + } - policy->curlft.use_time = get_seconds(); + for (i = 0; i < num_pols; i++) + pols[i]->curlft.use_time = get_seconds(); - switch (policy->action) { - default: - case XFRM_POLICY_BLOCK: + if (num_xfrms < 0) { /* Prohibit the flow */ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; - - case XFRM_POLICY_ALLOW: -#ifndef CONFIG_XFRM_SUB_POLICY - if (policy->xfrm_nr == 0) { - /* Flow passes not transformed. */ - xfrm_pol_put(policy); - return 0; - } -#endif - - /* Try to find matching bundle. - * - * LATER: help from flow cache. It is optional, this - * is required only for output policy. - */ - dst = xfrm_find_bundle(fl, policy, family); - if (IS_ERR(dst)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - err = PTR_ERR(dst); - goto error; - } - - if (dst) - break; - -#ifdef CONFIG_XFRM_SUB_POLICY - if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { - pols[1] = xfrm_policy_lookup_bytype(net, - XFRM_POLICY_TYPE_MAIN, - fl, family, - XFRM_POLICY_OUT); - if (pols[1]) { - if (IS_ERR(pols[1])) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); - err = PTR_ERR(pols[1]); - goto error; - } - if (pols[1]->action == XFRM_POLICY_BLOCK) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); - err = -EPERM; - goto error; - } - npols ++; - xfrm_nr += pols[1]->xfrm_nr; - } - } - - /* - * Because neither flowi nor bundle information knows about - * transformation template size. On more than one policy usage - * we can realize whether all of them is bypass or not after - * they are searched. See above not-transformed bypass - * is surrounded by non-sub policy configuration, too. - */ - if (xfrm_nr == 0) { - /* Flow passes not transformed. */ - xfrm_pols_put(pols, npols); - return 0; - } - -#endif - nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); - - if (unlikely(nx<0)) { - err = nx; - if (err == -EAGAIN && net->xfrm.sysctl_larval_drop) { - /* EREMOTE tells the caller to generate - * a one-shot blackhole route. - */ - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - xfrm_pol_put(policy); - return -EREMOTE; - } - if (err == -EAGAIN && (flags & XFRM_LOOKUP_WAIT)) { - DECLARE_WAITQUEUE(wait, current); - - add_wait_queue(&net->xfrm.km_waitq, &wait); - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - set_current_state(TASK_RUNNING); - remove_wait_queue(&net->xfrm.km_waitq, &wait); - - nx = xfrm_tmpl_resolve(pols, npols, fl, xfrm, family); - - if (nx == -EAGAIN && signal_pending(current)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - err = -ERESTART; - goto error; - } - if (nx == -EAGAIN || - genid != atomic_read(&flow_cache_genid)) { - xfrm_pols_put(pols, npols); - goto restart; - } - err = nx; - } - if (err < 0) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); - goto error; - } - } - if (nx == 0) { - /* Flow passes not transformed. */ - xfrm_pols_put(pols, npols); - return 0; - } - - dst = xfrm_bundle_create(policy, xfrm, nx, fl, dst_orig); - err = PTR_ERR(dst); - if (IS_ERR(dst)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); - goto error; - } - - for (pi = 0; pi < npols; pi++) - pol_dead |= pols[pi]->walk.dead; - - write_lock_bh(&policy->lock); - if (unlikely(pol_dead || stale_bundle(dst))) { - /* Wow! While we worked on resolving, this - * policy has gone. Retry. It is not paranoia, - * we just cannot enlist new bundle to dead object. - * We can't enlist stable bundles either. - */ - write_unlock_bh(&policy->lock); - dst_free(dst); - - if (pol_dead) - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLDEAD); - else - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - err = -EHOSTUNREACH; - goto error; - } - - if (npols > 1) - err = xfrm_dst_update_parent(dst, &pols[1]->selector); - else - err = xfrm_dst_update_origin(dst, fl); - if (unlikely(err)) { - write_unlock_bh(&policy->lock); - dst_free(dst); - XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLECHECKERROR); - goto error; - } - - dst->next = policy->bundles; - policy->bundles = dst; - dst_hold(dst); - write_unlock_bh(&policy->lock); + } else if (num_xfrms > 0) { + /* Flow transformed */ + *dst_p = dst; + dst_release(dst_orig); + } else { + /* Flow passes untransformed */ + dst_release(dst); } - *dst_p = dst; - dst_release(dst_orig); - xfrm_pols_put(pols, npols); +ok: + xfrm_pols_put(pols, drop_pols); return 0; +nopol: + if (!(flags & XFRM_LOOKUP_ICMP)) + goto ok; + err = -ENOENT; error: - xfrm_pols_put(pols, npols); + dst_release(dst); dropdst: dst_release(dst_orig); *dst_p = NULL; + xfrm_pols_put(pols, drop_pols); return err; - -nopol: - err = -ENOENT; - if (flags & XFRM_LOOKUP_ICMP) - goto dropdst; - return 0; } EXPORT_SYMBOL(__xfrm_lookup); @@ -2161,71 +2251,24 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) return dst; } -static void prune_one_bundle(struct xfrm_policy *pol, int (*func)(struct dst_entry *), struct dst_entry **gc_list_p) -{ - struct dst_entry *dst, **dstp; - - write_lock(&pol->lock); - dstp = &pol->bundles; - while ((dst=*dstp) != NULL) { - if (func(dst)) { - *dstp = dst->next; - dst->next = *gc_list_p; - *gc_list_p = dst; - } else { - dstp = &dst->next; - } - } - write_unlock(&pol->lock); -} - -static void xfrm_prune_bundles(struct net *net, int (*func)(struct dst_entry *)) +static void __xfrm_garbage_collect(struct net *net) { - struct dst_entry *gc_list = NULL; - int dir; + struct dst_entry *head, *next; - read_lock_bh(&xfrm_policy_lock); - for (dir = 0; dir < XFRM_POLICY_MAX * 2; dir++) { - struct xfrm_policy *pol; - struct hlist_node *entry; - struct hlist_head *table; - int i; + flow_cache_flush(); - hlist_for_each_entry(pol, entry, - &net->xfrm.policy_inexact[dir], bydst) - prune_one_bundle(pol, func, &gc_list); + spin_lock_bh(&xfrm_policy_sk_bundle_lock); + head = xfrm_policy_sk_bundles; + xfrm_policy_sk_bundles = NULL; + spin_unlock_bh(&xfrm_policy_sk_bundle_lock); - table = net->xfrm.policy_bydst[dir].table; - for (i = net->xfrm.policy_bydst[dir].hmask; i >= 0; i--) { - hlist_for_each_entry(pol, entry, table + i, bydst) - prune_one_bundle(pol, func, &gc_list); - } - } - read_unlock_bh(&xfrm_policy_lock); - - while (gc_list) { - struct dst_entry *dst = gc_list; - gc_list = dst->next; - dst_free(dst); + while (head) { + next = head->next; + dst_free(head); + head = next; } } -static int unused_bundle(struct dst_entry *dst) -{ - return !atomic_read(&dst->__refcnt); -} - -static void __xfrm_garbage_collect(struct net *net) -{ - xfrm_prune_bundles(net, unused_bundle); -} - -static int xfrm_flush_bundles(struct net *net) -{ - xfrm_prune_bundles(net, stale_bundle); - return 0; -} - static void xfrm_init_pmtu(struct dst_entry *dst) { do { @@ -2283,7 +2326,9 @@ int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, return 0; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; - if (xdst->genid != dst->xfrm->genid) + if (xdst->xfrm_genid != dst->xfrm->genid) + return 0; + if (xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; if (strict && fl && @@ -2448,7 +2493,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void switch (event) { case NETDEV_DOWN: - xfrm_flush_bundles(dev_net(dev)); + __xfrm_garbage_collect(dev_net(dev)); } return NOTIFY_DONE; } @@ -2780,7 +2825,6 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, struct xfrm_migrate *m, int num_migrate) { struct xfrm_migrate *mp; - struct dst_entry *dst; int i, j, n = 0; write_lock_bh(&pol->lock); @@ -2805,10 +2849,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, sizeof(pol->xfrm_vec[i].saddr)); pol->xfrm_vec[i].encap_family = mp->new_family; /* flush bundles */ - while ((dst = pol->bundles) != NULL) { - pol->bundles = dst->next; - dst_free(dst); - } + atomic_inc(&pol->genid); } } -- cgit v1.2.3-70-g09d2 From d5cdfacb35ed886271d1ccfffbded98d3447da17 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sun, 4 Apr 2010 09:37:19 +0300 Subject: cfg80211: Add local-state-change-only auth/deauth/disassoc cfg80211 is quite strict on allowing authentication and association commands only in certain states. In order to meet these requirements, user space applications may need to clear authentication or association state in some cases. Currently, this can be done with deauth/disassoc command, but that ends up sending out Deauthentication or Disassociation frame unnecessarily. Add a new nl80211 attribute to allow this sending of the frame be skipped, but with all other deauth/disassoc operations being completed. Similar state change is also needed for IEEE 802.11r FT protocol in the FT-over-DS case which does not use Authentication frame exchange in a transition to another BSS. For this to work with cfg80211, an authentication entry needs to be created for the target BSS without sending out an Authentication frame. The nl80211 authentication command can be used for this purpose, too, with the new attribute to indicate that the command is only for changing local state. This enables wpa_supplicant to complete FT-over-DS transition successfully. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- include/linux/nl80211.h | 8 ++++++++ include/net/cfg80211.h | 11 +++++++++++ net/mac80211/mlme.c | 23 +++++++++++++++-------- net/wireless/core.h | 15 ++++++++++----- net/wireless/mlme.c | 39 ++++++++++++++++++++++++++++----------- net/wireless/nl80211.c | 19 ++++++++++++++++--- net/wireless/sme.c | 15 +++++++++------ 7 files changed, 97 insertions(+), 33 deletions(-) (limited to 'include/net') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index daf6a3432b9..2ea3edeee7a 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -703,6 +703,12 @@ enum nl80211_commands { * @NL80211_ATTR_CQM: connection quality monitor configuration in a * nested attribute with %NL80211_ATTR_CQM_* sub-attributes. * + * @NL80211_ATTR_LOCAL_STATE_CHANGE: Flag attribute to indicate that a command + * is requesting a local authentication/association state change without + * invoking actual management frame exchange. This can be used with + * NL80211_CMD_AUTHENTICATE, NL80211_CMD_DEAUTHENTICATE, + * NL80211_CMD_DISASSOCIATE. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -856,6 +862,8 @@ enum nl80211_attrs { NL80211_ATTR_CQM, + NL80211_ATTR_LOCAL_STATE_CHANGE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 868cfd3b972..37cebd3aa0f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -704,6 +704,10 @@ struct cfg80211_crypto_settings { * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication + * @local_state_change: This is a request for a local state only, i.e., no + * Authentication frame is to be transmitted and authentication state is + * to be changed without having to wait for a response from the peer STA + * (AP). */ struct cfg80211_auth_request { struct cfg80211_bss *bss; @@ -712,6 +716,7 @@ struct cfg80211_auth_request { enum nl80211_auth_type auth_type; const u8 *key; u8 key_len, key_idx; + bool local_state_change; }; /** @@ -744,12 +749,15 @@ struct cfg80211_assoc_request { * @ie: Extra IEs to add to Deauthentication frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the deauthentication + * @local_state_change: This is a request for a local state only, i.e., no + * Deauthentication frame is to be transmitted. */ struct cfg80211_deauth_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; u16 reason_code; + bool local_state_change; }; /** @@ -762,12 +770,15 @@ struct cfg80211_deauth_request { * @ie: Extra IEs to add to Disassociation frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the disassociation + * @local_state_change: This is a request for a local state only, i.e., no + * Disassociation frame is to be transmitted. */ struct cfg80211_disassoc_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; u16 reason_code; + bool local_state_change; }; /** diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 57a3c62139e..4c189d0be4a 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -210,7 +210,7 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, const u8 *bssid, u16 stype, u16 reason, - void *cookie) + void *cookie, bool send_frame) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -247,7 +247,11 @@ static void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata, cfg80211_send_disassoc(sdata->dev, (u8 *)mgmt, skb->len); if (!(ifmgd->flags & IEEE80211_STA_MFP_ENABLED)) IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; - ieee80211_tx_skb(sdata, skb); + + if (send_frame) + ieee80211_tx_skb(sdata, skb); + else + kfree_skb(skb); } void ieee80211_send_pspoll(struct ieee80211_local *local, @@ -980,7 +984,7 @@ static void __ieee80211_connection_loss(struct ieee80211_sub_if_data *sdata) ieee80211_send_deauth_disassoc(sdata, bssid, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, - NULL); + NULL, true); } void ieee80211_beacon_connection_loss_work(struct work_struct *work) @@ -1724,7 +1728,7 @@ static void ieee80211_sta_work(struct work_struct *work) ieee80211_send_deauth_disassoc(sdata, bssid, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, - NULL); + NULL, true); mutex_lock(&ifmgd->mtx); } } @@ -1908,6 +1912,9 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, struct ieee80211_work *wk; u16 auth_alg; + if (req->local_state_change) + return 0; /* no need to update mac80211 state */ + switch (req->auth_type) { case NL80211_AUTHTYPE_OPEN_SYSTEM: auth_alg = WLAN_AUTH_OPEN; @@ -2163,9 +2170,9 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata, printk(KERN_DEBUG "%s: deauthenticating from %pM by local choice (reason=%d)\n", sdata->name, bssid, req->reason_code); - ieee80211_send_deauth_disassoc(sdata, bssid, - IEEE80211_STYPE_DEAUTH, req->reason_code, - cookie); + ieee80211_send_deauth_disassoc(sdata, bssid, IEEE80211_STYPE_DEAUTH, + req->reason_code, cookie, + !req->local_state_change); ieee80211_recalc_idle(sdata->local); @@ -2202,7 +2209,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_send_deauth_disassoc(sdata, req->bss->bssid, IEEE80211_STYPE_DISASSOC, req->reason_code, - cookie); + cookie, !req->local_state_change); sta_info_destroy_addr(sdata, bssid); ieee80211_recalc_idle(sdata->local); diff --git a/net/wireless/core.h b/net/wireless/core.h index d52da913145..b2234b436ea 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -293,13 +293,15 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx); + const u8 *key, int key_len, int key_idx, + bool local_state_change); int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_auth_type auth_type, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx); + const u8 *key, int key_len, int key_idx, + bool local_state_change); int __cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct net_device *dev, struct ieee80211_channel *chan, @@ -315,13 +317,16 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, struct cfg80211_crypto_settings *crypt); int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason); + const u8 *ie, int ie_len, u16 reason, + bool local_state_change); int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason); + const u8 *ie, int ie_len, u16 reason, + bool local_state_change); int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason); + const u8 *ie, int ie_len, u16 reason, + bool local_state_change); void cfg80211_mlme_down(struct cfg80211_registered_device *rdev, struct net_device *dev); void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid, diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 0855f0d3234..387dd2a27d2 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -377,7 +377,8 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx) + const u8 *key, int key_len, int key_idx, + bool local_state_change) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_auth_request req; @@ -407,6 +408,7 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, memset(&req, 0, sizeof(req)); + req.local_state_change = local_state_change; req.ie = ie; req.ie_len = ie_len; req.auth_type = auth_type; @@ -433,12 +435,18 @@ int __cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, goto out; } - wdev->authtry_bsses[slot] = bss; + if (local_state_change) + wdev->auth_bsses[slot] = bss; + else + wdev->authtry_bsses[slot] = bss; cfg80211_hold_bss(bss); err = rdev->ops->auth(&rdev->wiphy, dev, &req); if (err) { - wdev->authtry_bsses[slot] = NULL; + if (local_state_change) + wdev->auth_bsses[slot] = NULL; + else + wdev->authtry_bsses[slot] = NULL; cfg80211_unhold_bss(bss); } @@ -453,14 +461,15 @@ int cfg80211_mlme_auth(struct cfg80211_registered_device *rdev, enum nl80211_auth_type auth_type, const u8 *bssid, const u8 *ssid, int ssid_len, const u8 *ie, int ie_len, - const u8 *key, int key_len, int key_idx) + const u8 *key, int key_len, int key_idx, + bool local_state_change) { int err; wdev_lock(dev->ieee80211_ptr); err = __cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, - key, key_len, key_idx); + key, key_len, key_idx, local_state_change); wdev_unlock(dev->ieee80211_ptr); return err; @@ -554,7 +563,8 @@ int cfg80211_mlme_assoc(struct cfg80211_registered_device *rdev, int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason) + const u8 *ie, int ie_len, u16 reason, + bool local_state_change) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_deauth_request req; @@ -564,6 +574,7 @@ int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, memset(&req, 0, sizeof(req)); req.reason_code = reason; + req.local_state_change = local_state_change; req.ie = ie; req.ie_len = ie_len; if (wdev->current_bss && @@ -590,13 +601,15 @@ int __cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason) + const u8 *ie, int ie_len, u16 reason, + bool local_state_change) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); - err = __cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason); + err = __cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason, + local_state_change); wdev_unlock(wdev); return err; @@ -604,7 +617,8 @@ int cfg80211_mlme_deauth(struct cfg80211_registered_device *rdev, static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason) + const u8 *ie, int ie_len, u16 reason, + bool local_state_change) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_disassoc_request req; @@ -619,6 +633,7 @@ static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, memset(&req, 0, sizeof(req)); req.reason_code = reason; + req.local_state_change = local_state_change; req.ie = ie; req.ie_len = ie_len; if (memcmp(wdev->current_bss->pub.bssid, bssid, ETH_ALEN) == 0) @@ -631,13 +646,15 @@ static int __cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, int cfg80211_mlme_disassoc(struct cfg80211_registered_device *rdev, struct net_device *dev, const u8 *bssid, - const u8 *ie, int ie_len, u16 reason) + const u8 *ie, int ie_len, u16 reason, + bool local_state_change) { struct wireless_dev *wdev = dev->ieee80211_ptr; int err; wdev_lock(wdev); - err = __cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason); + err = __cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason, + local_state_change); wdev_unlock(wdev); return err; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 95149f30340..df5505b3930 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -150,6 +150,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_FRAME_MATCH] = { .type = NLA_BINARY, }, [NL80211_ATTR_PS_STATE] = { .type = NLA_U32 }, [NL80211_ATTR_CQM] = { .type = NLA_NESTED, }, + [NL80211_ATTR_LOCAL_STATE_CHANGE] = { .type = NLA_FLAG }, }; /* policy for the attributes */ @@ -3393,6 +3394,7 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) int err, ssid_len, ie_len = 0; enum nl80211_auth_type auth_type; struct key_parse key; + bool local_state_change; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -3471,9 +3473,12 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info) goto out; } + local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; + err = cfg80211_mlme_auth(rdev, dev, chan, auth_type, bssid, ssid, ssid_len, ie, ie_len, - key.p.key, key.p.key_len, key.idx); + key.p.key, key.p.key_len, key.idx, + local_state_change); out: cfg80211_unlock_rdev(rdev); @@ -3650,6 +3655,7 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) const u8 *ie = NULL, *bssid; int err, ie_len = 0; u16 reason_code; + bool local_state_change; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -3695,7 +3701,10 @@ static int nl80211_deauthenticate(struct sk_buff *skb, struct genl_info *info) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - err = cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason_code); + local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; + + err = cfg80211_mlme_deauth(rdev, dev, bssid, ie, ie_len, reason_code, + local_state_change); out: cfg80211_unlock_rdev(rdev); @@ -3712,6 +3721,7 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) const u8 *ie = NULL, *bssid; int err, ie_len = 0; u16 reason_code; + bool local_state_change; if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; @@ -3757,7 +3767,10 @@ static int nl80211_disassociate(struct sk_buff *skb, struct genl_info *info) ie_len = nla_len(info->attrs[NL80211_ATTR_IE]); } - err = cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason_code); + local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE]; + + err = cfg80211_mlme_disassoc(rdev, dev, bssid, ie, ie_len, reason_code, + local_state_change); out: cfg80211_unlock_rdev(rdev); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 17fde0da1b0..17465777eb4 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -170,7 +170,7 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) params->ssid, params->ssid_len, NULL, 0, params->key, params->key_len, - params->key_idx); + params->key_idx, false); case CFG80211_CONN_ASSOCIATE_NEXT: BUG_ON(!rdev->ops->assoc); wdev->conn->state = CFG80211_CONN_ASSOCIATING; @@ -185,12 +185,13 @@ static int cfg80211_conn_do_work(struct wireless_dev *wdev) if (err) __cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, - WLAN_REASON_DEAUTH_LEAVING); + WLAN_REASON_DEAUTH_LEAVING, + false); return err; case CFG80211_CONN_DEAUTH_ASSOC_FAIL: __cfg80211_mlme_deauth(rdev, wdev->netdev, params->bssid, NULL, 0, - WLAN_REASON_DEAUTH_LEAVING); + WLAN_REASON_DEAUTH_LEAVING, false); /* return an error so that we call __cfg80211_connect_result() */ return -EINVAL; default: @@ -675,7 +676,8 @@ void __cfg80211_disconnected(struct net_device *dev, const u8 *ie, continue; bssid = wdev->auth_bsses[i]->pub.bssid; ret = __cfg80211_mlme_deauth(rdev, dev, bssid, NULL, 0, - WLAN_REASON_DEAUTH_LEAVING); + WLAN_REASON_DEAUTH_LEAVING, + false); WARN(ret, "deauth failed: %d\n", ret); } } @@ -934,7 +936,7 @@ int __cfg80211_disconnect(struct cfg80211_registered_device *rdev, /* wdev->conn->params.bssid must be set if > SCANNING */ err = __cfg80211_mlme_deauth(rdev, dev, wdev->conn->params.bssid, - NULL, 0, reason); + NULL, 0, reason, false); if (err) return err; } else { @@ -990,7 +992,8 @@ void cfg80211_sme_disassoc(struct net_device *dev, int idx) memcpy(bssid, wdev->auth_bsses[idx]->pub.bssid, ETH_ALEN); if (__cfg80211_mlme_deauth(rdev, dev, bssid, - NULL, 0, WLAN_REASON_DEAUTH_LEAVING)) { + NULL, 0, WLAN_REASON_DEAUTH_LEAVING, + false)) { /* whatever -- assume gone anyway */ cfg80211_unhold_bss(wdev->auth_bsses[idx]); cfg80211_put_bss(&wdev->auth_bsses[idx]->pub); -- cgit v1.2.3-70-g09d2 From e4077e018b5ead3de9951fc01d8bf12eeeeeefed Mon Sep 17 00:00:00 2001 From: Timo Teräs Date: Thu, 8 Apr 2010 11:27:42 -0700 Subject: xfrm: Fix crashes in xfrm_lookup() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit From: Timo Teräs Happens because CONFIG_XFRM_SUB_POLICY is not enabled, and one of the helper functions I used did unexpected things in that case. Signed-off-by: David S. Miller --- include/net/xfrm.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 625dd61ccbb..cccb049991a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -735,19 +735,12 @@ static inline void xfrm_pol_put(struct xfrm_policy *policy) xfrm_policy_destroy(policy); } -#ifdef CONFIG_XFRM_SUB_POLICY static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) { int i; for (i = npols - 1; i >= 0; --i) xfrm_pol_put(pols[i]); } -#else -static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) -{ - xfrm_pol_put(pols[0]); -} -#endif extern void __xfrm_state_destroy(struct xfrm_state *); -- cgit v1.2.3-70-g09d2 From bb29624614c2afe2873ee8ee97cf09df42701694 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Sun, 11 Apr 2010 02:15:55 +0000 Subject: inet: Remove unused send_check length argument inet: Remove unused send_check length argument This patch removes the unused length argument from the send_check function in struct inet_connection_sock_af_ops. Signed-off-by: Herbert Xu Tested-by: Yinghai Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 3 +-- include/net/tcp.h | 2 +- net/dccp/dccp.h | 2 +- net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 3 +-- net/dccp/output.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- 9 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 696d6e4ce68..52c8b8b8a0b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -37,8 +37,7 @@ struct tcp_congestion_ops; */ struct inet_connection_sock_af_ops { int (*queue_xmit)(struct sk_buff *skb, int ipfragok); - void (*send_check)(struct sock *sk, int len, - struct sk_buff *skb); + void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); int (*conn_request)(struct sock *sk, struct sk_buff *skb); struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/tcp.h b/include/net/tcp.h index 75be5a28815..70c5159f4b3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -423,7 +423,7 @@ extern u8 *tcp_parse_md5sig_option(struct tcphdr *th); * TCP v4 functions exported for the inet6 API */ -extern void tcp_v4_send_check(struct sock *sk, int len, +extern void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); extern int tcp_v4_conn_request(struct sock *sk, diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 53f8e12d0c1..a10a61a1ded 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -223,7 +223,7 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb) skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0); } -extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); +extern void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); extern int dccp_retransmit_skb(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 52ffa1cde15..d9b11ef8694 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -349,7 +349,7 @@ static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb, return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum); } -void dccp_v4_send_check(struct sock *sk, int unused, struct sk_buff *skb) +void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 3b11e41a292..ab1ab95946d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -60,8 +60,7 @@ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } -static inline void dccp_v6_send_check(struct sock *sk, int unused_value, - struct sk_buff *skb) +static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); diff --git a/net/dccp/output.c b/net/dccp/output.c index fc3f436440b..b8d98e3c052 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -129,7 +129,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - icsk->icsk_af_ops->send_check(sk, 0, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (set_ack) dccp_event_ack_sent(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index aebfd28c508..a24995cdc4b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -537,7 +537,7 @@ static void __tcp_v4_send_check(struct sk_buff *skb, } /* This routine computes an IPv4 TCP checksum. */ -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0dda86e72ad..0ae7ce7a71a 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } #endif - icsk->icsk_af_ops->send_check(sk, skb->len, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->flags & TCPCB_FLAG_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f84c506c588..b429dfdd69d 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -933,7 +933,7 @@ static void __tcp_v6_send_check(struct sk_buff *skb, } } -static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) +static void tcp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); -- cgit v1.2.3-70-g09d2 From b6c6712a42ca3f9fa7f4a3d7c40e3a9dd1fd9e03 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 8 Apr 2010 23:03:29 +0000 Subject: net: sk_dst_cache RCUification With latest CONFIG_PROVE_RCU stuff, I felt more comfortable to make this work. sk->sk_dst_cache is currently protected by a rwlock (sk_dst_lock) This rwlock is readlocked for a very small amount of time, and dst entries are already freed after RCU grace period. This calls for RCU again :) This patch converts sk_dst_lock to a spinlock, and use RCU for readers. __sk_dst_get() is supposed to be called with rcu_read_lock() or if socket locked by user, so use appropriate rcu_dereference_check() condition (rcu_read_lock_held() || sock_owned_by_user(sk)) This patch avoids two atomic ops per tx packet on UDP connected sockets, for example, and permits sk_dst_lock to be much less dirtied. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 15 --------------- include/net/ip6_route.h | 4 ++-- include/net/sock.h | 47 ++++++++++++++++++++++++++++++----------------- net/core/dev.c | 2 +- net/core/sock.c | 8 ++++---- net/dccp/timer.c | 4 ++-- net/decnet/af_decnet.c | 6 +++--- net/ipv4/af_inet.c | 2 +- net/ipv4/tcp_input.c | 4 ++-- net/ipv4/tcp_timer.c | 4 ++-- net/ipv6/ipv6_sockglue.c | 25 +++++++++++++------------ 11 files changed, 60 insertions(+), 61 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index ce078cda6b7..aac5a5fcfda 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -225,21 +225,6 @@ static inline void dst_confirm(struct dst_entry *dst) neigh_confirm(dst->neighbour); } -static inline void dst_negative_advice(struct dst_entry **dst_p, - struct sock *sk) -{ - struct dst_entry * dst = *dst_p; - if (dst && dst->ops->negative_advice) { - *dst_p = dst->ops->negative_advice(dst); - - if (dst != *dst_p) { - extern void sk_reset_txq(struct sock *sk); - - sk_reset_txq(sk); - } - } -} - static inline void dst_link_failure(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 68f67836e14..278312c95f9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -152,9 +152,9 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, struct in6_addr *daddr, struct in6_addr *saddr) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __ip6_dst_store(sk, dst, daddr, saddr); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline int ipv6_unicast_destination(struct sk_buff *skb) diff --git a/include/net/sock.h b/include/net/sock.h index b4603cd54fc..56df440a950 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -262,7 +262,7 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; #endif - rwlock_t sk_dst_lock; + spinlock_t sk_dst_lock; atomic_t sk_rmem_alloc; atomic_t sk_wmem_alloc; atomic_t sk_omem_alloc; @@ -1192,7 +1192,8 @@ extern unsigned long sock_i_ino(struct sock *sk); static inline struct dst_entry * __sk_dst_get(struct sock *sk) { - return sk->sk_dst_cache; + return rcu_dereference_check(sk->sk_dst_cache, rcu_read_lock_held() || + sock_owned_by_user(sk)); } static inline struct dst_entry * @@ -1200,50 +1201,62 @@ sk_dst_get(struct sock *sk) { struct dst_entry *dst; - read_lock(&sk->sk_dst_lock); - dst = sk->sk_dst_cache; + rcu_read_lock(); + dst = rcu_dereference(sk->sk_dst_cache); if (dst) dst_hold(dst); - read_unlock(&sk->sk_dst_lock); + rcu_read_unlock(); return dst; } +extern void sk_reset_txq(struct sock *sk); + +static inline void dst_negative_advice(struct sock *sk) +{ + struct dst_entry *ndst, *dst = __sk_dst_get(sk); + + if (dst && dst->ops->negative_advice) { + ndst = dst->ops->negative_advice(dst); + + if (ndst != dst) { + rcu_assign_pointer(sk->sk_dst_cache, ndst); + sk_reset_txq(sk); + } + } +} + static inline void __sk_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old_dst; sk_tx_queue_clear(sk); - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = dst; + old_dst = rcu_dereference_check(sk->sk_dst_cache, + lockdep_is_held(&sk->sk_dst_lock)); + rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } static inline void sk_dst_set(struct sock *sk, struct dst_entry *dst) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_set(sk, dst); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline void __sk_dst_reset(struct sock *sk) { - struct dst_entry *old_dst; - - sk_tx_queue_clear(sk); - old_dst = sk->sk_dst_cache; - sk->sk_dst_cache = NULL; - dst_release(old_dst); + __sk_dst_set(sk, NULL); } static inline void sk_dst_reset(struct sock *sk) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __sk_dst_reset(sk); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie); diff --git a/net/core/dev.c b/net/core/dev.c index 0eb79e35671..ca4cdef74a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2015,7 +2015,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); - if (sk && sk->sk_dst_cache) + if (sk && rcu_dereference_check(sk->sk_dst_cache, 1)) sk_tx_queue_set(sk, queue_index); } } diff --git a/net/core/sock.c b/net/core/sock.c index c5812bbc2cc..7effa1e689d 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -364,11 +364,11 @@ EXPORT_SYMBOL(sk_reset_txq); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst = sk->sk_dst_cache; + struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_cache = NULL; + rcu_assign_pointer(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -1157,7 +1157,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) skb_queue_head_init(&newsk->sk_async_wait_queue); #endif - rwlock_init(&newsk->sk_dst_lock); + spin_lock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); lockdep_set_class_and_name(&newsk->sk_callback_lock, af_callback_keys + newsk->sk_family, @@ -1898,7 +1898,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) } else sk->sk_sleep = NULL; - rwlock_init(&sk->sk_dst_lock); + spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, diff --git a/net/dccp/timer.c b/net/dccp/timer.c index bbfeb5eae46..1a9aa05d4dc 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -38,7 +38,7 @@ static int dccp_write_timeout(struct sock *sk) if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) { if (icsk->icsk_retransmits != 0) - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_dccp_request_retries; } else { @@ -63,7 +63,7 @@ static int dccp_write_timeout(struct sock *sk) Golden words :-). */ - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); } retry_until = sysctl_dccp_retries2; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 2b494fac946..55e3b6b0061 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -446,7 +446,7 @@ static void dn_destruct(struct sock *sk) skb_queue_purge(&scp->other_xmit_queue); skb_queue_purge(&scp->other_receive_queue); - dst_release(xchg(&sk->sk_dst_cache, NULL)); + dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); } static int dn_memory_pressure; @@ -1105,7 +1105,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) release_sock(sk); dst = skb_dst(skb); - dst_release(xchg(&newsk->sk_dst_cache, dst)); + sk_dst_set(newsk, dst); skb_dst_set(skb, NULL); DN_SK(newsk)->state = DN_CR; @@ -1956,7 +1956,7 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock, } if ((flags & MSG_TRYHARD) && sk->sk_dst_cache) - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); mss = scp->segsize_rem; fctype = scp->services_rem & NSP_FC_MASK; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a0beb32beaa..193dcd6ed64 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -154,7 +154,7 @@ void inet_sock_destruct(struct sock *sk) WARN_ON(sk->sk_forward_alloc); kfree(inet->opt); - dst_release(sk->sk_dst_cache); + dst_release(rcu_dereference_check(sk->sk_dst_cache, 1)); sk_refcnt_debug_dec(sk); } EXPORT_SYMBOL(inet_sock_destruct); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4000b10610b..ae3ec15fb63 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3710,7 +3710,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) } if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) - dst_confirm(sk->sk_dst_cache); + dst_confirm(__sk_dst_get(sk)); return 1; @@ -5833,7 +5833,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tp->snd_una == tp->write_seq) { tcp_set_state(sk, TCP_FIN_WAIT2); sk->sk_shutdown |= SEND_SHUTDOWN; - dst_confirm(sk->sk_dst_cache); + dst_confirm(__sk_dst_get(sk)); if (!sock_flag(sk, SOCK_DEAD)) /* Wake up lingering close() */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 8a0ab2977f1..c732be00606 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -172,14 +172,14 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(&sk->sk_dst_cache, sk); + dst_negative_advice(sk); } retry_until = sysctl_tcp_retries2; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 33f60fca7aa..1160400e9db 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -114,9 +114,9 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, } opt = xchg(&inet6_sk(sk)->opt, opt); } else { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); opt = xchg(&inet6_sk(sk)->opt, opt); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } sk_dst_reset(sk); @@ -971,14 +971,13 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, case IPV6_MTU: { struct dst_entry *dst; + val = 0; - lock_sock(sk); - dst = sk_dst_get(sk); - if (dst) { + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) val = dst_mtu(dst); - dst_release(dst); - } - release_sock(sk); + rcu_read_unlock(); if (!val) return -ENOTCONN; break; @@ -1066,12 +1065,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, else val = np->mcast_hops; - dst = sk_dst_get(sk); - if (dst) { - if (val < 0) + if (val < 0) { + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (dst) val = ip6_dst_hoplimit(dst); - dst_release(dst); + rcu_read_unlock(); } + if (val < 0) val = sock_net(sk)->ipv6.devconf_all->hop_limit; break; -- cgit v1.2.3-70-g09d2 From d8a566beaa75c6ad5e38cdccf0ea5294323e7866 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:15 +0000 Subject: net: fib_rules: consolidate IPv4 and DECnet ->default_pref() functions. Both functions are equivalent, consolidate them since a following patch needs a third implementation for multicast routing. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/fib_rules.h | 1 + net/core/fib_rules.c | 18 ++++++++++++++++++ net/decnet/dn_rules.c | 19 +------------------ net/ipv4/fib_rules.c | 19 +------------------ 4 files changed, 21 insertions(+), 36 deletions(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index c49086d2bc7..52bd9e6c914 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -114,4 +114,5 @@ extern int fib_rules_lookup(struct fib_rules_ops *, extern int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); +extern u32 fib_default_rule_pref(struct fib_rules_ops *ops); #endif diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 05cce4ec84d..1eb32276be7 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -39,6 +39,24 @@ int fib_default_rule_add(struct fib_rules_ops *ops, } EXPORT_SYMBOL(fib_default_rule_add); +u32 fib_default_rule_pref(struct fib_rules_ops *ops) +{ + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&ops->rules_list)) { + pos = ops->rules_list.next; + if (pos->next != &ops->rules_list) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } + } + + return 0; +} +EXPORT_SYMBOL(fib_default_rule_pref); + static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 7466c546f28..2d14093a2c3 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -212,23 +212,6 @@ nla_put_failure: return -ENOBUFS; } -static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops) -{ - struct list_head *pos; - struct fib_rule *rule; - - if (!list_empty(&dn_fib_rules_ops->rules_list)) { - pos = dn_fib_rules_ops->rules_list.next; - if (pos->next != &dn_fib_rules_ops->rules_list) { - rule = list_entry(pos->next, struct fib_rule, list); - if (rule->pref) - return rule->pref - 1; - } - } - - return 0; -} - static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) { dn_rt_cache_flush(-1); @@ -243,7 +226,7 @@ static struct fib_rules_ops dn_fib_rules_ops_template = { .configure = dn_fib_rule_configure, .compare = dn_fib_rule_compare, .fill = dn_fib_rule_fill, - .default_pref = dn_fib_rule_default_pref, + .default_pref = fib_default_rule_pref, .flush_cache = dn_fib_rule_flush_cache, .nlgroup = RTNLGRP_DECnet_RULE, .policy = dn_fib_rule_policy, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index ca2d07b1c70..73b67849c5b 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -234,23 +234,6 @@ nla_put_failure: return -ENOBUFS; } -static u32 fib4_rule_default_pref(struct fib_rules_ops *ops) -{ - struct list_head *pos; - struct fib_rule *rule; - - if (!list_empty(&ops->rules_list)) { - pos = ops->rules_list.next; - if (pos->next != &ops->rules_list) { - rule = list_entry(pos->next, struct fib_rule, list); - if (rule->pref) - return rule->pref - 1; - } - } - - return 0; -} - static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) { return nla_total_size(4) /* dst */ @@ -272,7 +255,7 @@ static struct fib_rules_ops fib4_rules_ops_template = { .configure = fib4_rule_configure, .compare = fib4_rule_compare, .fill = fib4_rule_fill, - .default_pref = fib4_rule_default_pref, + .default_pref = fib_default_rule_pref, .nlmsg_payload = fib4_rule_nlmsg_payload, .flush_cache = fib4_rule_flush_cache, .nlgroup = RTNLGRP_IPV4_RULE, -- cgit v1.2.3-70-g09d2 From f74e49b5613206fb18468bdc9509a1db746aa01b Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:18 +0000 Subject: ipv4: raw: move struct raw_sock and raw_sk() to include/net/raw.h A following patch will use struct raw_sock to store state for ipmr, so having the definitions in icmp.h doesn't fit very well anymore. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/icmp.h | 11 ----------- include/net/raw.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/icmp.h b/include/net/icmp.h index 15b3dfe9fce..6e991e0d0d6 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -48,15 +48,4 @@ extern void icmp_out_count(struct net *net, unsigned char type); /* Move into dst.h ? */ extern int xrlim_allow(struct dst_entry *dst, int timeout); -struct raw_sock { - /* inet_sock has to be the first member */ - struct inet_sock inet; - struct icmp_filter filter; -}; - -static inline struct raw_sock *raw_sk(const struct sock *sk) -{ - return (struct raw_sock *)sk; -} - #endif /* _ICMP_H */ diff --git a/include/net/raw.h b/include/net/raw.h index 6c14a656357..67cc6436943 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -19,6 +19,7 @@ #include +#include extern struct proto raw_prot; @@ -56,4 +57,15 @@ int raw_seq_open(struct inode *ino, struct file *file, void raw_hash_sk(struct sock *sk); void raw_unhash_sk(struct sock *sk); +struct raw_sock { + /* inet_sock has to be the first member */ + struct inet_sock inet; + struct icmp_filter filter; +}; + +static inline struct raw_sock *raw_sk(const struct sock *sk) +{ + return (struct raw_sock *)sk; +} + #endif /* _RAW_H */ -- cgit v1.2.3-70-g09d2 From e258beb22f4d3ea3dc88586ffc9c990d0eb03380 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:19 +0000 Subject: ipv4: ipmr: move unres_queue and timer to per-namespace data The unres_queue is currently shared between all namespaces. Following patches will additionally allow to create multiple multicast routing tables in each namespace. Having a single shared queue for all these users seems to excessive, move the queue and the cleanup timer to the per-namespace data to unshare it. As a side-effect, this fixes a bug in the seq file iteration functions: the first entry returned is always from the current namespace, entries returned after that may belong to any namespace. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 2 ++ net/ipv4/ipmr.c | 70 ++++++++++++++++++++---------------------------- 2 files changed, 31 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2764994c913..b15e518f952 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -60,6 +60,8 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE struct sock *mroute_sk; + struct timer_list ipmr_expire_timer; + struct mfc_cache *mfc_unres_queue; struct mfc_cache **mfc_cache_array; struct vif_device *vif_table; int maxvif; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9d4f6d1340a..d6aa65e2b08 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -80,8 +80,6 @@ static DEFINE_RWLOCK(mrt_lock); #define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL) -static struct mfc_cache *mfc_unres_queue; /* Queue of unresolved entries */ - /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -100,8 +98,6 @@ static int ipmr_cache_report(struct net *net, struct sk_buff *pkt, vifi_t vifi, int assert); static int ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); -static struct timer_list ipmr_expire_timer; - /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) @@ -364,25 +360,26 @@ static void ipmr_destroy_unres(struct mfc_cache *c) } -/* Single timer process for all the unresolved queue. */ +/* Timer process for the unresolved queue. */ -static void ipmr_expire_process(unsigned long dummy) +static void ipmr_expire_process(unsigned long arg) { + struct net *net = (struct net *)arg; unsigned long now; unsigned long expires; struct mfc_cache *c, **cp; if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&ipmr_expire_timer, jiffies+HZ/10); + mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10); return; } - if (mfc_unres_queue == NULL) + if (net->ipv4.mfc_unres_queue == NULL) goto out; now = jiffies; expires = 10*HZ; - cp = &mfc_unres_queue; + cp = &net->ipv4.mfc_unres_queue; while ((c=*cp) != NULL) { if (time_after(c->mfc_un.unres.expires, now)) { @@ -398,8 +395,8 @@ static void ipmr_expire_process(unsigned long dummy) ipmr_destroy_unres(c); } - if (mfc_unres_queue != NULL) - mod_timer(&ipmr_expire_timer, jiffies + expires); + if (net->ipv4.mfc_unres_queue != NULL) + mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); @@ -708,9 +705,8 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); spin_lock_bh(&mfc_unres_lock); - for (c=mfc_unres_queue; c; c=c->next) { - if (net_eq(mfc_net(c), net) && - c->mfc_mcastgrp == iph->daddr && + for (c=net->ipv4.mfc_unres_queue; c; c=c->next) { + if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) break; } @@ -751,10 +747,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) } atomic_inc(&net->ipv4.cache_resolve_queue_len); - c->next = mfc_unres_queue; - mfc_unres_queue = c; + c->next = net->ipv4.mfc_unres_queue; + net->ipv4.mfc_unres_queue = c; - mod_timer(&ipmr_expire_timer, c->mfc_un.unres.expires); + mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires); } /* @@ -849,18 +845,17 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) * need to send on the frames and tidy up. */ spin_lock_bh(&mfc_unres_lock); - for (cp = &mfc_unres_queue; (uc=*cp) != NULL; + for (cp = &net->ipv4.mfc_unres_queue; (uc=*cp) != NULL; cp = &uc->next) { - if (net_eq(mfc_net(uc), net) && - uc->mfc_origin == c->mfc_origin && + if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { *cp = uc->next; atomic_dec(&net->ipv4.cache_resolve_queue_len); break; } } - if (mfc_unres_queue == NULL) - del_timer(&ipmr_expire_timer); + if (net->ipv4.mfc_unres_queue == NULL) + del_timer(&net->ipv4.ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (uc) { @@ -912,14 +907,9 @@ static void mroute_clean_tables(struct net *net) struct mfc_cache *c, **cp; spin_lock_bh(&mfc_unres_lock); - cp = &mfc_unres_queue; + cp = &net->ipv4.mfc_unres_queue; while ((c = *cp) != NULL) { - if (!net_eq(mfc_net(c), net)) { - cp = &c->next; - continue; - } *cp = c->next; - ipmr_destroy_unres(c); } spin_unlock_bh(&mfc_unres_lock); @@ -1819,11 +1809,10 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, return mfc; read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &net->ipv4.mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (net_eq(mfc_net(mfc), net) && - pos-- == 0) + for (mfc = net->ipv4.mfc_unres_queue; mfc; mfc = mfc->next) + if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -1857,7 +1846,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (mfc->next) return mfc->next; - if (it->cache == &mfc_unres_queue) + if (it->cache == &net->ipv4.mfc_unres_queue) goto end_of_list; BUG_ON(it->cache != net->ipv4.mfc_cache_array); @@ -1870,13 +1859,11 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &net->ipv4.mfc_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; - while (mfc && !net_eq(mfc_net(mfc), net)) - mfc = mfc->next; + mfc = net->ipv4.mfc_unres_queue; if (mfc) return mfc; @@ -1892,7 +1879,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - if (it->cache == &mfc_unres_queue) + if (it->cache == &net->ipv4.mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); else if (it->cache == net->ipv4.mfc_cache_array) read_unlock(&mrt_lock); @@ -1915,7 +1902,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) (unsigned long) mfc->mfc_origin, mfc->mfc_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &net->ipv4.mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, @@ -1992,6 +1979,9 @@ static int __net_init ipmr_net_init(struct net *net) goto fail_mfc_cache; } + setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process, + (unsigned long)net); + #ifdef CONFIG_IP_PIMSM net->ipv4.mroute_reg_vif_num = -1; #endif @@ -2047,7 +2037,6 @@ int __init ip_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip_mr_notifier); if (err) goto reg_notif_fail; @@ -2065,7 +2054,6 @@ add_proto_fail: unregister_netdevice_notifier(&ip_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ipmr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); -- cgit v1.2.3-70-g09d2 From 862465f2e7e90975e7bf0ecfbb171dd3adedd950 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:21 +0000 Subject: ipv4: ipmr: convert struct mfc_cache to struct list_head Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/mroute.h | 2 +- include/net/netns/ipv4.h | 4 +- net/ipv4/ipmr.c | 125 +++++++++++++++++++++++------------------------ 3 files changed, 64 insertions(+), 67 deletions(-) (limited to 'include/net') diff --git a/include/linux/mroute.h b/include/linux/mroute.h index de7780a6dd3..7ff6c77d600 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -191,7 +191,7 @@ struct vif_device { #define VIFF_STATIC 0x8000 struct mfc_cache { - struct mfc_cache *next; /* Next entry on cache line */ + struct list_head list; __be32 mfc_mcastgrp; /* Group the entry belongs to */ __be32 mfc_origin; /* Source of packet */ vifi_t mfc_parent; /* Source interface */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index b15e518f952..5d06429968d 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -61,8 +61,8 @@ struct netns_ipv4 { #ifdef CONFIG_IP_MROUTE struct sock *mroute_sk; struct timer_list ipmr_expire_timer; - struct mfc_cache *mfc_unres_queue; - struct mfc_cache **mfc_cache_array; + struct list_head mfc_unres_queue; + struct list_head *mfc_cache_array; struct vif_device *vif_table; int maxvif; atomic_t cache_resolve_queue_len; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index f8e25c8ba07..21b5edc2f34 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -367,35 +367,32 @@ static void ipmr_expire_process(unsigned long arg) struct net *net = (struct net *)arg; unsigned long now; unsigned long expires; - struct mfc_cache *c, **cp; + struct mfc_cache *c, *next; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10); return; } - if (net->ipv4.mfc_unres_queue == NULL) + if (list_empty(&net->ipv4.mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; - cp = &net->ipv4.mfc_unres_queue; - while ((c=*cp) != NULL) { + list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; - cp = &c->next; continue; } - *cp = c->next; - + list_del(&c->list); ipmr_destroy_unres(net, c); } - if (net->ipv4.mfc_unres_queue != NULL) + if (!list_empty(&net->ipv4.mfc_unres_queue)) mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires); out: @@ -537,11 +534,11 @@ static struct mfc_cache *ipmr_cache_find(struct net *net, int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; - for (c = net->ipv4.mfc_cache_array[line]; c; c = c->next) { - if (c->mfc_origin==origin && c->mfc_mcastgrp==mcastgrp) - break; + list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) { + if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp) + return c; } - return c; + return NULL; } /* @@ -699,18 +696,21 @@ static int ipmr_cache_report(struct net *net, static int ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) { + bool found = false; int err; struct mfc_cache *c; const struct iphdr *iph = ip_hdr(skb); spin_lock_bh(&mfc_unres_lock); - for (c=net->ipv4.mfc_unres_queue; c; c=c->next) { + list_for_each_entry(c, &net->ipv4.mfc_unres_queue, list) { if (c->mfc_mcastgrp == iph->daddr && - c->mfc_origin == iph->saddr) + c->mfc_origin == iph->saddr) { + found = true; break; + } } - if (c == NULL) { + if (!found) { /* * Create a new entry if allowable */ @@ -746,8 +746,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) } atomic_inc(&net->ipv4.cache_resolve_queue_len); - c->next = net->ipv4.mfc_unres_queue; - net->ipv4.mfc_unres_queue = c; + list_add(&c->list, &net->ipv4.mfc_unres_queue); mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires); } @@ -774,16 +773,15 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) { int line; - struct mfc_cache *c, **cp; + struct mfc_cache *c, *next; line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - for (cp = &net->ipv4.mfc_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ipmr_cache_free(c); @@ -795,22 +793,24 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) { + bool found = false; int line; - struct mfc_cache *uc, *c, **cp; + struct mfc_cache *uc, *c; if (mfc->mfcc_parent >= MAXVIFS) return -ENFILE; line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - for (cp = &net->ipv4.mfc_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && - c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) + c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { + found = true; break; + } } - if (c != NULL) { + if (found) { write_lock_bh(&mrt_lock); c->mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(net, c, mfc->mfcc_ttls); @@ -835,8 +835,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = net->ipv4.mfc_cache_array[line]; - net->ipv4.mfc_cache_array[line] = c; + list_add(&c->list, &net->ipv4.mfc_cache_array[line]); write_unlock_bh(&mrt_lock); /* @@ -844,16 +843,15 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) * need to send on the frames and tidy up. */ spin_lock_bh(&mfc_unres_lock); - for (cp = &net->ipv4.mfc_unres_queue; (uc=*cp) != NULL; - cp = &uc->next) { + list_for_each_entry(uc, &net->ipv4.mfc_unres_queue, list) { if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { - *cp = uc->next; + list_del(&uc->list); atomic_dec(&net->ipv4.cache_resolve_queue_len); break; } } - if (net->ipv4.mfc_unres_queue == NULL) + if (list_empty(&net->ipv4.mfc_unres_queue)) del_timer(&net->ipv4.ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); @@ -872,6 +870,7 @@ static void mroute_clean_tables(struct net *net) { int i; LIST_HEAD(list); + struct mfc_cache *c, *next; /* * Shut down all active vif entries @@ -885,17 +884,12 @@ static void mroute_clean_tables(struct net *net) /* * Wipe the cache */ - for (i=0; iipv4.mfc_cache_array[i]; - while ((c = *cp) != NULL) { - if (c->mfc_flags&MFC_STATIC) { - cp = &c->next; + for (i = 0; i < MFC_LINES; i++) { + list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[i], list) { + if (c->mfc_flags&MFC_STATIC) continue; - } write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ipmr_cache_free(c); @@ -903,12 +897,9 @@ static void mroute_clean_tables(struct net *net) } if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) { - struct mfc_cache *c, **cp; - spin_lock_bh(&mfc_unres_lock); - cp = &net->ipv4.mfc_unres_queue; - while ((c = *cp) != NULL) { - *cp = c->next; + list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) { + list_del(&c->list); ipmr_destroy_unres(net, c); } spin_unlock_bh(&mfc_unres_lock); @@ -1789,7 +1780,7 @@ static const struct file_operations ipmr_vif_fops = { struct ipmr_mfc_iter { struct seq_net_private p; - struct mfc_cache **cache; + struct list_head *cache; int ct; }; @@ -1799,18 +1790,18 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, { struct mfc_cache *mfc; - it->cache = net->ipv4.mfc_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC_LINES; it->ct++) - for (mfc = net->ipv4.mfc_cache_array[it->ct]; - mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC_LINES; it->ct++) { + it->cache = &net->ipv4.mfc_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; + } read_unlock(&mrt_lock); - it->cache = &net->ipv4.mfc_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = net->ipv4.mfc_unres_queue; mfc; mfc = mfc->next) + it->cache = &net->ipv4.mfc_unres_queue; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -1842,18 +1833,19 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (v == SEQ_START_TOKEN) return ipmr_mfc_seq_idx(net, seq->private, 0); - if (mfc->next) - return mfc->next; + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc_cache, list); if (it->cache == &net->ipv4.mfc_unres_queue) goto end_of_list; - BUG_ON(it->cache != net->ipv4.mfc_cache_array); + BUG_ON(it->cache != &net->ipv4.mfc_cache_array[it->ct]); while (++it->ct < MFC_LINES) { - mfc = net->ipv4.mfc_cache_array[it->ct]; - if (mfc) - return mfc; + it->cache = &net->ipv4.mfc_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc_cache, list); } /* exhausted cache_array, show unresolved */ @@ -1862,9 +1854,8 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = net->ipv4.mfc_unres_queue; - if (mfc) - return mfc; + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc_cache, list); end_of_list: spin_unlock_bh(&mfc_unres_lock); @@ -1880,7 +1871,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &net->ipv4.mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == net->ipv4.mfc_cache_array) + else if (it->cache == &net->ipv4.mfc_cache_array[it->ct]) read_unlock(&mrt_lock); } @@ -1960,6 +1951,7 @@ static const struct net_protocol pim_protocol = { */ static int __net_init ipmr_net_init(struct net *net) { + unsigned int i; int err = 0; net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device), @@ -1971,13 +1963,18 @@ static int __net_init ipmr_net_init(struct net *net) /* Forwarding cache */ net->ipv4.mfc_cache_array = kcalloc(MFC_LINES, - sizeof(struct mfc_cache *), + sizeof(struct list_head), GFP_KERNEL); if (!net->ipv4.mfc_cache_array) { err = -ENOMEM; goto fail_mfc_cache; } + for (i = 0; i < MFC_LINES; i++) + INIT_LIST_HEAD(&net->ipv4.mfc_cache_array[i]); + + INIT_LIST_HEAD(&net->ipv4.mfc_unres_queue); + setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process, (unsigned long)net); -- cgit v1.2.3-70-g09d2 From 0c12295a741d3186987f96f518cfbdaf01abb087 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:22 +0000 Subject: ipv4: ipmr: move mroute data into seperate structure Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 13 +- net/ipv4/ipmr.c | 369 +++++++++++++++++++++++++---------------------- 2 files changed, 200 insertions(+), 182 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 5d06429968d..72e762ab3e5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -59,18 +59,7 @@ struct netns_ipv4 { atomic_t rt_genid; #ifdef CONFIG_IP_MROUTE - struct sock *mroute_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc_unres_queue; - struct list_head *mfc_cache_array; - struct vif_device *vif_table; - int maxvif; - atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; -#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) - int mroute_reg_vif_num; -#endif + struct mr_table *mrt; #endif }; #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 21b5edc2f34..498f4e907d5 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -68,6 +68,21 @@ #define CONFIG_IP_PIMSM 1 #endif +struct mr_table { + struct sock *mroute_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc_unres_queue; + struct list_head mfc_cache_array[MFC_LINES]; + struct vif_device vif_table[MAXVIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + int mroute_do_assert; + int mroute_do_pim; +#if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) + int mroute_reg_vif_num; +#endif +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -78,7 +93,7 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -#define VIF_EXISTS(_net, _idx) ((_net)->ipv4.vif_table[_idx].dev != NULL) +#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL) /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -93,11 +108,12 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static int ip_mr_forward(struct net *net, struct sk_buff *skb, - struct mfc_cache *cache, int local); -static int ipmr_cache_report(struct net *net, +static int ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local); +static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); -static int ipmr_fill_mroute(struct net *net, struct sk_buff *skb, +static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ @@ -199,12 +215,12 @@ failure: static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); + struct mr_table *mrt = net->ipv4.mrt; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ipmr_cache_report(net, skb, net->ipv4.mroute_reg_vif_num, - IGMPMSG_WHOLEPKT); + ipmr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, IGMPMSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; @@ -274,17 +290,17 @@ failure: * @notify: Set to 1, if the caller is a notifier_call */ -static int vif_delete(struct net *net, int vifi, int notify, +static int vif_delete(struct mr_table *mrt, int vifi, int notify, struct list_head *head) { struct vif_device *v; struct net_device *dev; struct in_device *in_dev; - if (vifi < 0 || vifi >= net->ipv4.maxvif) + if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &net->ipv4.vif_table[vifi]; + v = &mrt->vif_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -296,17 +312,17 @@ static int vif_delete(struct net *net, int vifi, int notify, } #ifdef CONFIG_IP_PIMSM - if (vifi == net->ipv4.mroute_reg_vif_num) - net->ipv4.mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; #endif - if (vifi+1 == net->ipv4.maxvif) { + if (vifi+1 == mrt->maxvif) { int tmp; for (tmp=vifi-1; tmp>=0; tmp--) { - if (VIF_EXISTS(net, tmp)) + if (VIF_EXISTS(mrt, tmp)) break; } - net->ipv4.maxvif = tmp+1; + mrt->maxvif = tmp+1; } write_unlock_bh(&mrt_lock); @@ -334,12 +350,13 @@ static inline void ipmr_cache_free(struct mfc_cache *c) and reporting error to netlink readers. */ -static void ipmr_destroy_unres(struct net *net, struct mfc_cache *c) +static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) { + struct net *net = NULL; //mrt->net; struct sk_buff *skb; struct nlmsgerr *e; - atomic_dec(&net->ipv4.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { @@ -364,23 +381,23 @@ static void ipmr_destroy_unres(struct net *net, struct mfc_cache *c) static void ipmr_expire_process(unsigned long arg) { - struct net *net = (struct net *)arg; + struct mr_table *mrt = (struct mr_table *)arg; unsigned long now; unsigned long expires; struct mfc_cache *c, *next; if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&net->ipv4.ipmr_expire_timer, jiffies+HZ/10); + mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); return; } - if (list_empty(&net->ipv4.mfc_unres_queue)) + if (list_empty(&mrt->mfc_unres_queue)) goto out; now = jiffies; expires = 10*HZ; - list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) @@ -389,11 +406,11 @@ static void ipmr_expire_process(unsigned long arg) } list_del(&c->list); - ipmr_destroy_unres(net, c); + ipmr_destroy_unres(mrt, c); } - if (!list_empty(&net->ipv4.mfc_unres_queue)) - mod_timer(&net->ipv4.ipmr_expire_timer, jiffies + expires); + if (!list_empty(&mrt->mfc_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); out: spin_unlock(&mfc_unres_lock); @@ -401,7 +418,7 @@ out: /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache, +static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache, unsigned char *ttls) { int vifi; @@ -410,8 +427,8 @@ static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache, cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXVIFS); - for (vifi = 0; vifi < net->ipv4.maxvif; vifi++) { - if (VIF_EXISTS(net, vifi) && + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (VIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -422,16 +439,17 @@ static void ipmr_update_thresholds(struct net *net, struct mfc_cache *cache, } } -static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) +static int vif_add(struct net *net, struct mr_table *mrt, + struct vifctl *vifc, int mrtsock) { int vifi = vifc->vifc_vifi; - struct vif_device *v = &net->ipv4.vif_table[vifi]; + struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; int err; /* Is vif busy ? */ - if (VIF_EXISTS(net, vifi)) + if (VIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->vifc_flags) { @@ -441,7 +459,7 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (net->ipv4.mroute_reg_vif_num >= 0) + if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ipmr_reg_vif(net); if (!dev) @@ -519,22 +537,22 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IP_PIMSM if (v->flags&VIFF_REGISTER) - net->ipv4.mroute_reg_vif_num = vifi; + mrt->mroute_reg_vif_num = vifi; #endif - if (vifi+1 > net->ipv4.maxvif) - net->ipv4.maxvif = vifi+1; + if (vifi+1 > mrt->maxvif) + mrt->maxvif = vifi+1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc_cache *ipmr_cache_find(struct net *net, +static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) { int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; - list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) { + list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp) return c; } @@ -567,8 +585,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void) * A cache entry has gone into a resolved state from queued */ -static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc, - struct mfc_cache *c) +static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, + struct mfc_cache *uc, struct mfc_cache *c) { struct sk_buff *skb; struct nlmsgerr *e; @@ -581,7 +599,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc, if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); - if (ipmr_fill_mroute(net, skb, c, NLMSG_DATA(nlh)) > 0) { + if (ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { nlh->nlmsg_len = (skb_tail_pointer(skb) - (u8 *)nlh); } else { @@ -595,7 +613,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc, rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else - ip_mr_forward(net, skb, c, 0); + ip_mr_forward(net, mrt, skb, c, 0); } } @@ -606,7 +624,7 @@ static void ipmr_cache_resolve(struct net *net, struct mfc_cache *uc, * Called under mrt_lock. */ -static int ipmr_cache_report(struct net *net, +static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert) { struct sk_buff *skb; @@ -639,7 +657,7 @@ static int ipmr_cache_report(struct net *net, memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr)); msg->im_msgtype = IGMPMSG_WHOLEPKT; msg->im_mbz = 0; - msg->im_vif = net->ipv4.mroute_reg_vif_num; + msg->im_vif = mrt->mroute_reg_vif_num; ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2; ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) + sizeof(struct iphdr)); @@ -671,7 +689,7 @@ static int ipmr_cache_report(struct net *net, skb->transport_header = skb->network_header; } - if (net->ipv4.mroute_sk == NULL) { + if (mrt->mroute_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -679,7 +697,7 @@ static int ipmr_cache_report(struct net *net, /* * Deliver to mrouted */ - ret = sock_queue_rcv_skb(net->ipv4.mroute_sk, skb); + ret = sock_queue_rcv_skb(mrt->mroute_sk, skb); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); @@ -694,7 +712,7 @@ static int ipmr_cache_report(struct net *net, */ static int -ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) +ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) { bool found = false; int err; @@ -702,7 +720,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &net->ipv4.mfc_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc_unres_queue, list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; @@ -715,7 +733,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) * Create a new entry if allowable */ - if (atomic_read(&net->ipv4.cache_resolve_queue_len) >= 10 || + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || (c = ipmr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); @@ -733,7 +751,7 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) /* * Reflect first query at mrouted. */ - err = ipmr_cache_report(net, skb, vifi, IGMPMSG_NOCACHE); + err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -745,10 +763,10 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) return err; } - atomic_inc(&net->ipv4.cache_resolve_queue_len); - list_add(&c->list, &net->ipv4.mfc_unres_queue); + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc_unres_queue); - mod_timer(&net->ipv4.ipmr_expire_timer, c->mfc_un.unres.expires); + mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } /* @@ -770,14 +788,14 @@ ipmr_cache_unresolved(struct net *net, vifi_t vifi, struct sk_buff *skb) * MFC cache manipulation by user space mroute daemon */ -static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) +static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) { int line; struct mfc_cache *c, *next; line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[line], list) { + list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { write_lock_bh(&mrt_lock); @@ -791,7 +809,8 @@ static int ipmr_mfc_delete(struct net *net, struct mfcctl *mfc) return -ENOENT; } -static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) +static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, + struct mfcctl *mfc, int mrtsock) { bool found = false; int line; @@ -802,7 +821,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); - list_for_each_entry(c, &net->ipv4.mfc_cache_array[line], list) { + list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { found = true; @@ -813,7 +832,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) if (found) { write_lock_bh(&mrt_lock); c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(net, c, mfc->mfcc_ttls); + ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); @@ -830,12 +849,12 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(net, c, mfc->mfcc_ttls); + ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - list_add(&c->list, &net->ipv4.mfc_cache_array[line]); + list_add(&c->list, &mrt->mfc_cache_array[line]); write_unlock_bh(&mrt_lock); /* @@ -843,20 +862,20 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) * need to send on the frames and tidy up. */ spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &net->ipv4.mfc_unres_queue, list) { + list_for_each_entry(uc, &mrt->mfc_unres_queue, list) { if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { list_del(&uc->list); - atomic_dec(&net->ipv4.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); break; } } - if (list_empty(&net->ipv4.mfc_unres_queue)) - del_timer(&net->ipv4.ipmr_expire_timer); + if (list_empty(&mrt->mfc_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (uc) { - ipmr_cache_resolve(net, uc, c); + ipmr_cache_resolve(net, mrt, uc, c); ipmr_cache_free(uc); } return 0; @@ -866,7 +885,7 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct net *net) +static void mroute_clean_tables(struct mr_table *mrt) { int i; LIST_HEAD(list); @@ -875,9 +894,9 @@ static void mroute_clean_tables(struct net *net) /* * Shut down all active vif entries */ - for (i = 0; i < net->ipv4.maxvif; i++) { - if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC)) - vif_delete(net, i, 0, &list); + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif_table[i].flags&VIFF_STATIC)) + vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); @@ -885,7 +904,7 @@ static void mroute_clean_tables(struct net *net) * Wipe the cache */ for (i = 0; i < MFC_LINES; i++) { - list_for_each_entry_safe(c, next, &net->ipv4.mfc_cache_array[i], list) { + list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { if (c->mfc_flags&MFC_STATIC) continue; write_lock_bh(&mrt_lock); @@ -896,11 +915,11 @@ static void mroute_clean_tables(struct net *net) } } - if (atomic_read(&net->ipv4.cache_resolve_queue_len) != 0) { + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - list_for_each_entry_safe(c, next, &net->ipv4.mfc_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) { list_del(&c->list); - ipmr_destroy_unres(net, c); + ipmr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); } @@ -909,16 +928,17 @@ static void mroute_clean_tables(struct net *net) static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); + struct mr_table *mrt = net->ipv4.mrt; rtnl_lock(); - if (sk == net->ipv4.mroute_sk) { + if (sk == mrt->mroute_sk) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; write_lock_bh(&mrt_lock); - net->ipv4.mroute_sk = NULL; + mrt->mroute_sk = NULL; write_unlock_bh(&mrt_lock); - mroute_clean_tables(net); + mroute_clean_tables(mrt); } rtnl_unlock(); } @@ -936,9 +956,10 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); + struct mr_table *mrt = net->ipv4.mrt; if (optname != MRT_INIT) { - if (sk != net->ipv4.mroute_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -951,7 +972,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOPROTOOPT; rtnl_lock(); - if (net->ipv4.mroute_sk) { + if (mrt->mroute_sk) { rtnl_unlock(); return -EADDRINUSE; } @@ -959,7 +980,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { write_lock_bh(&mrt_lock); - net->ipv4.mroute_sk = sk; + mrt->mroute_sk = sk; write_unlock_bh(&mrt_lock); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; @@ -967,7 +988,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi rtnl_unlock(); return ret; case MRT_DONE: - if (sk != net->ipv4.mroute_sk) + if (sk != mrt->mroute_sk) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: @@ -980,9 +1001,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENFILE; rtnl_lock(); if (optname == MRT_ADD_VIF) { - ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk); + ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk); } else { - ret = vif_delete(net, vif.vifc_vifi, 0, NULL); + ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } rtnl_unlock(); return ret; @@ -999,9 +1020,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EFAULT; rtnl_lock(); if (optname == MRT_DEL_MFC) - ret = ipmr_mfc_delete(net, &mfc); + ret = ipmr_mfc_delete(mrt, &mfc); else - ret = ipmr_mfc_add(net, &mfc, sk == net->ipv4.mroute_sk); + ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk); rtnl_unlock(); return ret; /* @@ -1012,7 +1033,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi int v; if (get_user(v,(int __user *)optval)) return -EFAULT; - net->ipv4.mroute_do_assert = (v) ? 1 : 0; + mrt->mroute_do_assert = (v) ? 1 : 0; return 0; } #ifdef CONFIG_IP_PIMSM @@ -1026,9 +1047,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi rtnl_lock(); ret = 0; - if (v != net->ipv4.mroute_do_pim) { - net->ipv4.mroute_do_pim = v; - net->ipv4.mroute_do_assert = v; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; } rtnl_unlock(); return ret; @@ -1052,6 +1073,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int int olr; int val; struct net *net = sock_net(sk); + struct mr_table *mrt = net->ipv4.mrt; if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM @@ -1073,10 +1095,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int val = 0x0305; #ifdef CONFIG_IP_PIMSM else if (optname == MRT_PIM) - val = net->ipv4.mroute_do_pim; + val = mrt->mroute_do_pim; #endif else - val = net->ipv4.mroute_do_assert; + val = mrt->mroute_do_assert; if (copy_to_user(optval, &val, olr)) return -EFAULT; return 0; @@ -1093,16 +1115,17 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); + struct mr_table *mrt = net->ipv4.mrt; switch (cmd) { case SIOCGETVIFCNT: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.vifi >= net->ipv4.maxvif) + if (vr.vifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &net->ipv4.vif_table[vr.vifi]; - if (VIF_EXISTS(net, vr.vifi)) { + vif = &mrt->vif_table[vr.vifi]; + if (VIF_EXISTS(mrt, vr.vifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1120,7 +1143,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ipmr_cache_find(net, sr.src.s_addr, sr.grp.s_addr); + c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1143,16 +1166,17 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct mr_table *mrt = net->ipv4.mrt; struct vif_device *v; int ct; LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &net->ipv4.vif_table[0]; - for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) { + v = &mrt->vif_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - vif_delete(net, ct, 1, &list); + vif_delete(mrt, ct, 1, &list); } unregister_netdevice_many(&list); return NOTIFY_DONE; @@ -1211,11 +1235,11 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) * Processing handlers for ipmr_forward */ -static void ipmr_queue_xmit(struct net *net, struct sk_buff *skb, - struct mfc_cache *c, int vifi) +static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *c, int vifi) { const struct iphdr *iph = ip_hdr(skb); - struct vif_device *vif = &net->ipv4.vif_table[vifi]; + struct vif_device *vif = &mrt->vif_table[vifi]; struct net_device *dev; struct rtable *rt; int encap = 0; @@ -1229,7 +1253,7 @@ static void ipmr_queue_xmit(struct net *net, struct sk_buff *skb, vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ipmr_cache_report(net, skb, vifi, IGMPMSG_WHOLEPKT); + ipmr_cache_report(mrt, skb, vifi, IGMPMSG_WHOLEPKT); goto out_free; } #endif @@ -1312,12 +1336,12 @@ out_free: return; } -static int ipmr_find_vif(struct net_device *dev) +static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) { - struct net *net = dev_net(dev); int ct; - for (ct = net->ipv4.maxvif-1; ct >= 0; ct--) { - if (net->ipv4.vif_table[ct].dev == dev) + + for (ct = mrt->maxvif-1; ct >= 0; ct--) { + if (mrt->vif_table[ct].dev == dev) break; } return ct; @@ -1325,8 +1349,9 @@ static int ipmr_find_vif(struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ -static int ip_mr_forward(struct net *net, struct sk_buff *skb, - struct mfc_cache *cache, int local) +static int ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local) { int psend = -1; int vif, ct; @@ -1338,7 +1363,7 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb, /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (net->ipv4.vif_table[vif].dev != skb->dev) { + if (mrt->vif_table[vif].dev != skb->dev) { int true_vifi; if (skb_rtable(skb)->fl.iif == 0) { @@ -1357,26 +1382,26 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb, } cache->mfc_un.res.wrong_if++; - true_vifi = ipmr_find_vif(skb->dev); + true_vifi = ipmr_find_vif(mrt, skb->dev); - if (true_vifi >= 0 && net->ipv4.mroute_do_assert && + if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (net->ipv4.mroute_do_pim || + (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ipmr_cache_report(net, skb, true_vifi, IGMPMSG_WRONGVIF); + ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); } goto dont_forward; } - net->ipv4.vif_table[vif].pkt_in++; - net->ipv4.vif_table[vif].bytes_in += skb->len; + mrt->vif_table[vif].pkt_in++; + mrt->vif_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1386,7 +1411,8 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb, if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, skb2, cache, psend); + ipmr_queue_xmit(net, mrt, skb2, cache, + psend); } psend = ct; } @@ -1395,9 +1421,9 @@ static int ip_mr_forward(struct net *net, struct sk_buff *skb, if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ipmr_queue_xmit(net, skb2, cache, psend); + ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { - ipmr_queue_xmit(net, skb, cache, psend); + ipmr_queue_xmit(net, mrt, skb, cache, psend); return 0; } } @@ -1417,6 +1443,7 @@ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); + struct mr_table *mrt = net->ipv4.mrt; int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; /* Packet is looped back after forward, it should not be @@ -1437,9 +1464,9 @@ int ip_mr_input(struct sk_buff *skb) that we can forward NO IGMP messages. */ read_lock(&mrt_lock); - if (net->ipv4.mroute_sk) { + if (mrt->mroute_sk) { nf_reset(skb); - raw_rcv(net->ipv4.mroute_sk, skb); + raw_rcv(mrt->mroute_sk, skb); read_unlock(&mrt_lock); return 0; } @@ -1448,7 +1475,7 @@ int ip_mr_input(struct sk_buff *skb) } read_lock(&mrt_lock); - cache = ipmr_cache_find(net, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); + cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); /* * No usable cache entry @@ -1466,9 +1493,9 @@ int ip_mr_input(struct sk_buff *skb) skb = skb2; } - vif = ipmr_find_vif(skb->dev); + vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ipmr_cache_unresolved(net, vif, skb); + int err = ipmr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); return err; @@ -1478,7 +1505,7 @@ int ip_mr_input(struct sk_buff *skb) return -ENODEV; } - ip_mr_forward(net, skb, cache, local); + ip_mr_forward(net, mrt, skb, cache, local); read_unlock(&mrt_lock); @@ -1500,6 +1527,7 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) struct net_device *reg_dev = NULL; struct iphdr *encap; struct net *net = dev_net(skb->dev); + struct mr_table *mrt = net->ipv4.mrt; encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* @@ -1514,8 +1542,8 @@ static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) return 1; read_lock(&mrt_lock); - if (net->ipv4.mroute_reg_vif_num >= 0) - reg_dev = net->ipv4.vif_table[net->ipv4.mroute_reg_vif_num].dev; + if (mrt->mroute_reg_vif_num >= 0) + reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -1550,13 +1578,14 @@ int pim_rcv_v1(struct sk_buff * skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); + struct mr_table *mrt = net->ipv4.mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); - if (!net->ipv4.mroute_do_pim || + if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; @@ -1592,7 +1621,7 @@ drop: #endif static int -ipmr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc_cache *c, +ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm) { int ct; @@ -1604,19 +1633,19 @@ ipmr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc_cache *c, if (c->mfc_parent > MAXVIFS) return -ENOENT; - if (VIF_EXISTS(net, c->mfc_parent)) - RTA_PUT(skb, RTA_IIF, 4, &net->ipv4.vif_table[c->mfc_parent].dev->ifindex); + if (VIF_EXISTS(mrt, c->mfc_parent)) + RTA_PUT(skb, RTA_IIF, 4, &mrt->vif_table[c->mfc_parent].dev->ifindex); mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (VIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) { + if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = net->ipv4.vif_table[ct].dev->ifindex; + nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1634,11 +1663,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; + struct mr_table *mrt = net->ipv4.mrt; struct mfc_cache *cache; struct rtable *rt = skb_rtable(skb); read_lock(&mrt_lock); - cache = ipmr_cache_find(net, rt->rt_src, rt->rt_dst); + cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); if (cache == NULL) { struct sk_buff *skb2; @@ -1652,7 +1682,7 @@ int ipmr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ipmr_find_vif(dev)) < 0) { + if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -1669,14 +1699,14 @@ int ipmr_get_route(struct net *net, iph->saddr = rt->rt_src; iph->daddr = rt->rt_dst; iph->version = 0; - err = ipmr_cache_unresolved(net, vif, skb2); + err = ipmr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); return err; } if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; - err = ipmr_fill_mroute(net, skb, cache, rtm); + err = ipmr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); return err; } @@ -1694,11 +1724,13 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < net->ipv4.maxvif; ++iter->ct) { - if (!VIF_EXISTS(net, iter->ct)) + struct mr_table *mrt = net->ipv4.mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!VIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) - return &net->ipv4.vif_table[iter->ct]; + return &mrt->vif_table[iter->ct]; } return NULL; } @@ -1717,15 +1749,16 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt = net->ipv4.mrt; ++*pos; if (v == SEQ_START_TOKEN) return ipmr_vif_seq_idx(net, iter, 0); - while (++iter->ct < net->ipv4.maxvif) { - if (!VIF_EXISTS(net, iter->ct)) + while (++iter->ct < mrt->maxvif) { + if (!VIF_EXISTS(mrt, iter->ct)) continue; - return &net->ipv4.vif_table[iter->ct]; + return &mrt->vif_table[iter->ct]; } return NULL; } @@ -1739,6 +1772,7 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); + struct mr_table *mrt = net->ipv4.mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1749,7 +1783,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2Zd %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", - vif - net->ipv4.vif_table, + vif - mrt->vif_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags, vif->local, vif->remote); @@ -1788,11 +1822,12 @@ struct ipmr_mfc_iter { static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { + struct mr_table *mrt = net->ipv4.mrt; struct mfc_cache *mfc; read_lock(&mrt_lock); for (it->ct = 0; it->ct < MFC_LINES; it->ct++) { - it->cache = &net->ipv4.mfc_cache_array[it->ct]; + it->cache = &mrt->mfc_cache_array[it->ct]; list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; @@ -1800,7 +1835,7 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, read_unlock(&mrt_lock); spin_lock_bh(&mfc_unres_lock); - it->cache = &net->ipv4.mfc_unres_queue; + it->cache = &mrt->mfc_unres_queue; list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; @@ -1827,6 +1862,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt = net->ipv4.mrt; ++*pos; @@ -1836,13 +1872,13 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (mfc->list.next != it->cache) return list_entry(mfc->list.next, struct mfc_cache, list); - if (it->cache == &net->ipv4.mfc_unres_queue) + if (it->cache == &mrt->mfc_unres_queue) goto end_of_list; - BUG_ON(it->cache != &net->ipv4.mfc_cache_array[it->ct]); + BUG_ON(it->cache != &mrt->mfc_cache_array[it->ct]); while (++it->ct < MFC_LINES) { - it->cache = &net->ipv4.mfc_cache_array[it->ct]; + it->cache = &mrt->mfc_cache_array[it->ct]; if (list_empty(it->cache)) continue; return list_first_entry(it->cache, struct mfc_cache, list); @@ -1850,7 +1886,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &net->ipv4.mfc_unres_queue; + it->cache = &mrt->mfc_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); @@ -1868,10 +1904,11 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt = net->ipv4.mrt; - if (it->cache == &net->ipv4.mfc_unres_queue) + if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == &net->ipv4.mfc_cache_array[it->ct]) + else if (it->cache == &mrt->mfc_cache_array[it->ct]) read_unlock(&mrt_lock); } @@ -1879,6 +1916,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; struct net *net = seq_file_net(seq); + struct mr_table *mrt = net->ipv4.mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1892,14 +1930,14 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) (unsigned long) mfc->mfc_origin, mfc->mfc_parent); - if (it->cache != &net->ipv4.mfc_unres_queue) { + if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++ ) { - if (VIF_EXISTS(net, n) && + if (VIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", @@ -1951,35 +1989,27 @@ static const struct net_protocol pim_protocol = { */ static int __net_init ipmr_net_init(struct net *net) { + struct mr_table *mrt; unsigned int i; int err = 0; - net->ipv4.vif_table = kcalloc(MAXVIFS, sizeof(struct vif_device), - GFP_KERNEL); - if (!net->ipv4.vif_table) { + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) { err = -ENOMEM; goto fail; } /* Forwarding cache */ - net->ipv4.mfc_cache_array = kcalloc(MFC_LINES, - sizeof(struct list_head), - GFP_KERNEL); - if (!net->ipv4.mfc_cache_array) { - err = -ENOMEM; - goto fail_mfc_cache; - } - for (i = 0; i < MFC_LINES; i++) - INIT_LIST_HEAD(&net->ipv4.mfc_cache_array[i]); + INIT_LIST_HEAD(&mrt->mfc_cache_array[i]); - INIT_LIST_HEAD(&net->ipv4.mfc_unres_queue); + INIT_LIST_HEAD(&mrt->mfc_unres_queue); - setup_timer(&net->ipv4.ipmr_expire_timer, ipmr_expire_process, + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, (unsigned long)net); #ifdef CONFIG_IP_PIMSM - net->ipv4.mroute_reg_vif_num = -1; + mrt->mroute_reg_vif_num = -1; #endif #ifdef CONFIG_PROC_FS @@ -1989,16 +2019,16 @@ static int __net_init ipmr_net_init(struct net *net) if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops)) goto proc_cache_fail; #endif + + net->ipv4.mrt = mrt; return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip_mr_vif"); proc_vif_fail: - kfree(net->ipv4.mfc_cache_array); + kfree(mrt); #endif -fail_mfc_cache: - kfree(net->ipv4.vif_table); fail: return err; } @@ -2009,8 +2039,7 @@ static void __net_exit ipmr_net_exit(struct net *net) proc_net_remove(net, "ip_mr_cache"); proc_net_remove(net, "ip_mr_vif"); #endif - kfree(net->ipv4.mfc_cache_array); - kfree(net->ipv4.vif_table); + kfree(net->ipv4.mrt); } static struct pernet_operations ipmr_net_ops = { -- cgit v1.2.3-70-g09d2 From f0ad0860d01e47a3ffd220564c5c653b3afbe962 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:23 +0000 Subject: ipv4: ipmr: support multiple tables This patch adds support for multiple independant multicast routing instances, named "tables". Userspace multicast routing daemons can bind to a specific table instance by issuing a setsockopt call using a new option MRT_TABLE. The table number is stored in the raw socket data and affects all following ipmr setsockopt(), getsockopt() and ioctl() calls. By default, a single table (RT_TABLE_DEFAULT) is created with a default routing rule pointing to it. Newly created pimreg devices have the table number appended ("pimregX"), with the exception of devices created in the default table, which are named just "pimreg" for compatibility reasons. Packets are directed to a specific table instance using routing rules, similar to how regular routing rules work. Currently iif, oif and mark are supported as keys, source and destination addresses could be supported additionally. Example usage: - bind pimd/xorp/... to a specific table: uint32_t table = 123; setsockopt(fd, IPPROTO_IP, MRT_TABLE, &table, sizeof(table)); - create routing rules directing packets to the new table: # ip mrule add iif eth0 lookup 123 # ip mrule add oif eth0 lookup 123 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 1 + include/linux/mroute.h | 3 +- include/net/netns/ipv4.h | 5 + include/net/raw.h | 1 + net/ipv4/Kconfig | 14 ++ net/ipv4/ipmr.c | 399 +++++++++++++++++++++++++++++++++++++++------- 6 files changed, 361 insertions(+), 62 deletions(-) (limited to 'include/net') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 405e41139a4..04a397619eb 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -21,6 +21,7 @@ #define FIB_RULES_IPV4 AF_INET #define FIB_RULES_IPV6 AF_INET6 #define FIB_RULES_DECNET AF_DECnet +#define FIB_RULES_IPMR 128 struct fib_rule_hdr { __u8 family; diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 7ff6c77d600..fa04b246c9a 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -27,7 +27,8 @@ #define MRT_DEL_MFC (MRT_BASE+5) /* Delete a multicast forwarding entry */ #define MRT_VERSION (MRT_BASE+6) /* Get the kernel multicast version */ #define MRT_ASSERT (MRT_BASE+7) /* Activate PIM assert mode */ -#define MRT_PIM (MRT_BASE+8) /* enable PIM code */ +#define MRT_PIM (MRT_BASE+8) /* enable PIM code */ +#define MRT_TABLE (MRT_BASE+9) /* Specify mroute table ID */ #define SIOCGETVIFCNT SIOCPROTOPRIVATE /* IP protocol privates */ #define SIOCGETSGCNT (SIOCPROTOPRIVATE+1) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 72e762ab3e5..ae07feec644 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -59,7 +59,12 @@ struct netns_ipv4 { atomic_t rt_genid; #ifdef CONFIG_IP_MROUTE +#ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES struct mr_table *mrt; +#else + struct list_head mr_tables; + struct fib_rules_ops *mr_rules_ops; +#endif #endif }; #endif diff --git a/include/net/raw.h b/include/net/raw.h index 67cc6436943..43c57502659 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -61,6 +61,7 @@ struct raw_sock { /* inet_sock has to be the first member */ struct inet_sock inet; struct icmp_filter filter; + u32 ipmr_table; }; static inline struct raw_sock *raw_sk(const struct sock *sk) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index c9a1c68767f..be597749c38 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -250,6 +250,20 @@ config IP_MROUTE . If you haven't heard about it, you don't need it. +config IP_MROUTE_MULTIPLE_TABLES + bool "IP: multicast policy routing" + depends on IP_ADVANCED_ROUTER + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + config IP_PIMSM_V1 bool "IP: PIM-SM version 1 support" depends on IP_MROUTE diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 498f4e907d5..5df5fd74c6d 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -63,12 +63,15 @@ #include #include #include +#include #if defined(CONFIG_IP_PIMSM_V1) || defined(CONFIG_IP_PIMSM_V2) #define CONFIG_IP_PIMSM 1 #endif struct mr_table { + struct list_head list; + u32 id; struct sock *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; @@ -83,6 +86,14 @@ struct mr_table { #endif }; +struct ipmr_rule { + struct fib_rule common; +}; + +struct ipmr_result { + struct mr_table *mrt; +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -108,6 +119,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; +static struct mr_table *ipmr_new_table(struct net *net, u32 id); static int ip_mr_forward(struct net *net, struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *cache, int local); @@ -115,6 +127,206 @@ static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) + +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + + ipmr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ipmr_fib_lookup(struct net *net, struct flowi *flp, + struct mr_table **mrt) +{ + struct ipmr_result res; + struct fib_lookup_arg arg = { .result = &res, }; + int err; + + err = fib_rules_lookup(net->ipv4.mr_rules_ops, flp, 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ipmr_result *res = arg->result; + struct mr_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ipmr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ipmr_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + return 1; +} + +static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ipmr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static struct fib_rules_ops ipmr_rules_ops_template = { + .family = FIB_RULES_IPMR, + .rule_size = sizeof(struct ipmr_rule), + .addr_size = sizeof(u32), + .action = ipmr_rule_action, + .match = ipmr_rule_match, + .configure = ipmr_rule_configure, + .compare = ipmr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ipmr_rule_fill, + .nlgroup = RTNLGRP_IPV4_RULE, + .policy = ipmr_rule_policy, + .owner = THIS_MODULE, +}; + +static int __net_init ipmr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr_table *mrt; + int err; + + ops = fib_rules_register(&ipmr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv4.mr_tables); + + mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + + err = fib_default_rule_add(ops, 0x7fff, RT_TABLE_DEFAULT, 0); + if (err < 0) + goto err2; + + net->ipv4.mr_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ipmr_rules_exit(struct net *net) +{ + struct mr_table *mrt, *next; + + list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) + kfree(mrt); + fib_rules_unregister(net->ipv4.mr_rules_ops); +} +#else +#define ipmr_for_each_table(mrt, net) \ + for (mrt = net->ipv4.mrt; mrt; mrt = NULL) + +static struct mr_table *ipmr_get_table(struct net *net, u32 id) +{ + return net->ipv4.mrt; +} + +static int ipmr_fib_lookup(struct net *net, struct flowi *flp, + struct mr_table **mrt) +{ + *mrt = net->ipv4.mrt; + return 0; +} + +static int __net_init ipmr_rules_init(struct net *net) +{ + net->ipv4.mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); + return net->ipv4.mrt ? 0 : -ENOMEM; +} + +static void __net_exit ipmr_rules_exit(struct net *net) +{ + kfree(net->ipv4.mrt); +} +#endif + +static struct mr_table *ipmr_new_table(struct net *net, u32 id) +{ + struct mr_table *mrt; + unsigned int i; + + mrt = ipmr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + mrt->id = id; + + /* Forwarding cache */ + for (i = 0; i < MFC_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc_unres_queue); + + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IP_PIMSM + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); +#endif + return mrt; +} /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */ @@ -215,7 +427,17 @@ failure: static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; + struct flowi fl = { + .oif = dev->ifindex, + .iif = skb->skb_iif, + .mark = skb->mark, + }; + int err; + + err = ipmr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; @@ -240,12 +462,18 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ipmr_reg_vif(struct net *net) +static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) { struct net_device *dev; struct in_device *in_dev; + char name[IFNAMSIZ]; + + if (mrt->id == RT_TABLE_DEFAULT) + sprintf(name, "pimreg"); + else + sprintf(name, "pimreg%u", mrt->id); - dev = alloc_netdev(0, "pimreg", reg_vif_setup); + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -461,7 +689,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ipmr_reg_vif(net); + dev = ipmr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -928,17 +1156,19 @@ static void mroute_clean_tables(struct mr_table *mrt) static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; rtnl_lock(); - if (sk == mrt->mroute_sk) { - IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; + ipmr_for_each_table(mrt, net) { + if (sk == mrt->mroute_sk) { + IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - write_lock_bh(&mrt_lock); - mrt->mroute_sk = NULL; - write_unlock_bh(&mrt_lock); + write_lock_bh(&mrt_lock); + mrt->mroute_sk = NULL; + write_unlock_bh(&mrt_lock); - mroute_clean_tables(mrt); + mroute_clean_tables(mrt); + } } rtnl_unlock(); } @@ -956,7 +1186,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi struct vifctl vif; struct mfcctl mfc; struct net *net = sock_net(sk); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT_INIT) { if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN)) @@ -1054,6 +1288,27 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi rtnl_unlock(); return ret; } +#endif +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + case MRT_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + if (sk == mrt->mroute_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ipmr_new_table(net, v)) + ret = -ENOMEM; + raw_sk(sk)->ipmr_table = v; + rtnl_unlock(); + return ret; + } #endif /* * Spurious command, or MRT_VERSION which you cannot @@ -1073,7 +1328,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int int olr; int val; struct net *net = sock_net(sk); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM @@ -1115,7 +1374,11 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; + + mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; switch (cmd) { case SIOCGETVIFCNT: @@ -1166,17 +1429,20 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v { struct net_device *dev = ptr; struct net *net = dev_net(dev); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; struct vif_device *v; int ct; LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &mrt->vif_table[0]; - for (ct = 0; ct < mrt->maxvif; ct++, v++) { - if (v->dev == dev) - vif_delete(mrt, ct, 1, &list); + + ipmr_for_each_table(mrt, net) { + v = &mrt->vif_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + vif_delete(mrt, ct, 1, &list); + } } unregister_netdevice_many(&list); return NOTIFY_DONE; @@ -1443,8 +1709,9 @@ int ip_mr_input(struct sk_buff *skb) { struct mfc_cache *cache; struct net *net = dev_net(skb->dev); - struct mr_table *mrt = net->ipv4.mrt; int local = skb_rtable(skb)->rt_flags & RTCF_LOCAL; + struct mr_table *mrt; + int err; /* Packet is looped back after forward, it should not be forwarded second time, but still can be delivered locally. @@ -1452,6 +1719,10 @@ int ip_mr_input(struct sk_buff *skb) if (IPCB(skb)->flags&IPSKB_FORWARDED) goto dont_forward; + err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt); + if (err < 0) + return err; + if (!local) { if (IPCB(skb)->opt.router_alert) { if (ip_call_ra_chain(skb)) @@ -1522,12 +1793,11 @@ dont_forward: } #ifdef CONFIG_IP_PIMSM -static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) +static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, + unsigned int pimlen) { struct net_device *reg_dev = NULL; struct iphdr *encap; - struct net *net = dev_net(skb->dev); - struct mr_table *mrt = net->ipv4.mrt; encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* @@ -1578,18 +1848,21 @@ int pim_rcv_v1(struct sk_buff * skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = igmp_hdr(skb); + if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0) + goto drop; + if (!mrt->mroute_do_pim || pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; - if (__pim_rcv(skb, sizeof(*pim))) { + if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } @@ -1601,6 +1874,8 @@ drop: static int pim_rcv(struct sk_buff * skb) { struct pimreghdr *pim; + struct net *net = dev_net(skb->dev); + struct mr_table *mrt; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; @@ -1612,7 +1887,10 @@ static int pim_rcv(struct sk_buff * skb) csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; - if (__pim_rcv(skb, sizeof(*pim))) { + if (ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt) < 0) + goto drop; + + if (__pim_rcv(mrt, skb, sizeof(*pim))) { drop: kfree_skb(skb); } @@ -1663,10 +1941,14 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt; struct mfc_cache *cache; struct rtable *rt = skb_rtable(skb); + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return -ENOENT; + read_lock(&mrt_lock); cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); @@ -1717,6 +1999,7 @@ int ipmr_get_route(struct net *net, */ struct ipmr_vif_iter { struct seq_net_private p; + struct mr_table *mrt; int ct; }; @@ -1724,7 +2007,7 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt = iter->mrt; for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { if (!VIF_EXISTS(mrt, iter->ct)) @@ -1738,7 +2021,15 @@ static struct vif_device *ipmr_vif_seq_idx(struct net *net, static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; read_lock(&mrt_lock); return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1) @@ -1749,7 +2040,7 @@ static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) @@ -1771,8 +2062,8 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { - struct net *net = seq_file_net(seq); - struct mr_table *mrt = net->ipv4.mrt; + struct ipmr_vif_iter *iter = seq->private; + struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1814,6 +2105,7 @@ static const struct file_operations ipmr_vif_fops = { struct ipmr_mfc_iter { struct seq_net_private p; + struct mr_table *mrt; struct list_head *cache; int ct; }; @@ -1822,7 +2114,7 @@ struct ipmr_mfc_iter { static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt = it->mrt; struct mfc_cache *mfc; read_lock(&mrt_lock); @@ -1850,7 +2142,13 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr_table *mrt; + + mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + it->mrt = mrt; it->cache = NULL; it->ct = 0; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) @@ -1862,7 +2160,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt = it->mrt; ++*pos; @@ -1903,8 +2201,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = net->ipv4.mrt; + struct mr_table *mrt = it->mrt; if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); @@ -1915,8 +2212,6 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = net->ipv4.mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -1924,6 +2219,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) } else { const struct mfc_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; + const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08lX %08lX %-3hd", (unsigned long) mfc->mfc_mcastgrp, @@ -1989,28 +2285,11 @@ static const struct net_protocol pim_protocol = { */ static int __net_init ipmr_net_init(struct net *net) { - struct mr_table *mrt; - unsigned int i; - int err = 0; + int err; - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (mrt == NULL) { - err = -ENOMEM; + err = ipmr_rules_init(net); + if (err < 0) goto fail; - } - - /* Forwarding cache */ - for (i = 0; i < MFC_LINES; i++) - INIT_LIST_HEAD(&mrt->mfc_cache_array[i]); - - INIT_LIST_HEAD(&mrt->mfc_unres_queue); - - setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, - (unsigned long)net); - -#ifdef CONFIG_IP_PIMSM - mrt->mroute_reg_vif_num = -1; -#endif #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -2019,15 +2298,13 @@ static int __net_init ipmr_net_init(struct net *net) if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops)) goto proc_cache_fail; #endif - - net->ipv4.mrt = mrt; return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip_mr_vif"); proc_vif_fail: - kfree(mrt); + ipmr_rules_exit(net); #endif fail: return err; @@ -2039,7 +2316,7 @@ static void __net_exit ipmr_net_exit(struct net *net) proc_net_remove(net, "ip_mr_cache"); proc_net_remove(net, "ip_mr_vif"); #endif - kfree(net->ipv4.mrt); + ipmr_rules_exit(net); } static struct pernet_operations ipmr_net_ops = { -- cgit v1.2.3-70-g09d2 From e179e6322ac334e21a3c6d669d95bc967e5d0a80 Mon Sep 17 00:00:00 2001 From: Bart De Schuymer Date: Thu, 15 Apr 2010 12:26:39 +0200 Subject: netfilter: bridge-netfilter: Fix MAC header handling with IP DNAT - fix IP DNAT on vlan- or pppoe-encapsulated traffic: The functions neigh_hh_output() or dst->neighbour->output() overwrite the complete Ethernet header, although we only need the destination MAC address. For encapsulated packets, they ended up overwriting the encapsulating header. The new code copies the Ethernet source MAC address and protocol number before calling dst->neighbour->output(). The Ethernet source MAC and protocol number are copied back in place in br_nf_pre_routing_finish_bridge_slow(). This also makes the IP DNAT more transparent because in the old scheme the source MAC of the bridge was copied into the source address in the Ethernet header. We also let skb->protocol equal ETH_P_IP resp. ETH_P_IPV6 during the execution of the PF_INET resp. PF_INET6 hooks. - Speed up IP DNAT by calling neigh_hh_bridge() instead of neigh_hh_output(): if dst->hh is available, we already know the MAC address so we can just copy it. Signed-off-by: Bart De Schuymer Signed-off-by: Patrick McHardy --- include/linux/netfilter_bridge.h | 5 ++- include/net/neighbour.h | 14 +++++++ net/bridge/br_netfilter.c | 90 +++++++++++++++++++++++++++++----------- 3 files changed, 83 insertions(+), 26 deletions(-) (limited to 'include/net') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index ffab6c423a5..ea0e44b9043 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -43,7 +43,8 @@ enum nf_br_hook_priorities { #define BRNF_BRIDGED_DNAT 0x02 #define BRNF_BRIDGED 0x04 #define BRNF_NF_BRIDGE_PREROUTING 0x08 - +#define BRNF_8021Q 0x10 +#define BRNF_PPPoE 0x20 /* Only used in br_forward.c */ extern int nf_bridge_copy_header(struct sk_buff *skb); @@ -75,6 +76,8 @@ static inline int br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb_pull(skb, ETH_HLEN); nf_bridge->mask ^= BRNF_BRIDGED_DNAT; + skb_copy_to_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), + skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); skb->dev = nf_bridge->physindev; return br_handle_frame_finish(skb); } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index da1d58be31b..eb21340a573 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -299,6 +299,20 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) return 0; } +#ifdef CONFIG_BRIDGE_NETFILTER +static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) +{ + unsigned seq, hh_alen; + + do { + seq = read_seqbegin(&hh->hh_lock); + hh_alen = HH_DATA_ALIGN(ETH_HLEN); + memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); + } while (read_seqretry(&hh->hh_lock, seq)); + return 0; +} +#endif + static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) { unsigned seq; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 05dc6304992..b7e405dc9d1 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -196,15 +196,24 @@ static inline void nf_bridge_save_header(struct sk_buff *skb) skb->nf_bridge->data, header_size); } -/* - * When forwarding bridge frames, we save a copy of the original - * header before processing. +static inline void nf_bridge_update_protocol(struct sk_buff *skb) +{ + if (skb->nf_bridge->mask & BRNF_8021Q) + skb->protocol = htons(ETH_P_8021Q); + else if (skb->nf_bridge->mask & BRNF_PPPoE) + skb->protocol = htons(ETH_P_PPP_SES); +} + +/* Fill in the header for fragmented IP packets handled by + * the IPv4 connection tracking code. */ int nf_bridge_copy_header(struct sk_buff *skb) { int err; - int header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); + unsigned int header_size; + nf_bridge_update_protocol(skb); + header_size = ETH_HLEN + nf_bridge_encap_header_len(skb); err = skb_cow_head(skb, header_size); if (err) return err; @@ -238,6 +247,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) skb_dst_set(skb, &rt->u.dst); skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); @@ -245,6 +255,38 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) return 0; } +/* Obtain the correct destination MAC address, while preserving the original + * source MAC address. If we already know this address, we just copy it. If we + * don't, we use the neighbour framework to find out. In both cases, we make + * sure that br_handle_frame_finish() is called afterwards. + */ +static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) +{ + struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct dst_entry *dst; + + skb->dev = bridge_parent(skb->dev); + if (!skb->dev) + goto free_skb; + dst = skb_dst(skb); + if (dst->hh) { + neigh_hh_bridge(dst->hh, skb); + skb->dev = nf_bridge->physindev; + return br_handle_frame_finish(skb); + } else if (dst->neighbour) { + /* the neighbour function below overwrites the complete + * MAC header, so we save the Ethernet source address and + * protocol number. */ + skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); + /* tell br_dev_xmit to continue with forwarding */ + nf_bridge->mask |= BRNF_BRIDGED_DNAT; + return dst->neighbour->output(skb); + } +free_skb: + kfree_skb(skb); + return 0; +} + /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. * @@ -283,25 +325,6 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ - -static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) -{ - skb->dev = bridge_parent(skb->dev); - if (skb->dev) { - struct dst_entry *dst = skb_dst(skb); - - nf_bridge_pull_encap_header(skb); - skb->nf_bridge->mask |= BRNF_BRIDGED_DNAT; - - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); - } - kfree_skb(skb); - return 0; -} - static int br_nf_pre_routing_finish(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -354,6 +377,7 @@ free_skb: if (skb_dst(skb)->dev == dev) { bridged_dnat: skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, @@ -376,6 +400,7 @@ bridged_dnat: } skb->dev = nf_bridge->physindev; + nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, skb, skb->dev, NULL, br_handle_frame_finish, 1); @@ -396,6 +421,10 @@ static struct net_device *setup_pre_routing(struct sk_buff *skb) nf_bridge->mask |= BRNF_NF_BRIDGE_PREROUTING; nf_bridge->physindev = skb->dev; skb->dev = bridge_parent(skb->dev); + if (skb->protocol == htons(ETH_P_8021Q)) + nf_bridge->mask |= BRNF_8021Q; + else if (skb->protocol == htons(ETH_P_PPP_SES)) + nf_bridge->mask |= BRNF_PPPoE; return skb->dev; } @@ -494,6 +523,7 @@ static unsigned int br_nf_pre_routing_ipv6(unsigned int hook, if (!setup_pre_routing(skb)) return NF_DROP; + skb->protocol = htons(ETH_P_IPV6); NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); @@ -566,6 +596,7 @@ static unsigned int br_nf_pre_routing(unsigned int hook, struct sk_buff *skb, if (!setup_pre_routing(skb)) return NF_DROP; store_orig_dstaddr(skb); + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, skb->dev, NULL, br_nf_pre_routing_finish); @@ -614,7 +645,9 @@ static int br_nf_forward_finish(struct sk_buff *skb) } else { in = *((struct net_device **)(skb->cb)); } + nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, in, skb->dev, br_forward_finish, 1); return 0; @@ -666,6 +699,10 @@ static unsigned int br_nf_forward_ip(unsigned int hook, struct sk_buff *skb, /* The physdev module checks on this */ nf_bridge->mask |= BRNF_BRIDGED; nf_bridge->physoutdev = skb->dev; + if (pf == PF_INET) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_FORWARD, skb, bridge_parent(in), parent, br_nf_forward_finish); @@ -706,8 +743,7 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb, #if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE) static int br_nf_dev_queue_xmit(struct sk_buff *skb) { - if (skb->nfct != NULL && - (skb->protocol == htons(ETH_P_IP) || IS_VLAN_IP(skb)) && + if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) && skb->len > skb->dev->mtu && !skb_is_gso(skb)) return ip_fragment(skb, br_dev_queue_push_xmit); @@ -755,6 +791,10 @@ static unsigned int br_nf_post_routing(unsigned int hook, struct sk_buff *skb, nf_bridge_pull_encap_header(skb); nf_bridge_save_header(skb); + if (pf == PF_INET) + skb->protocol = htons(ETH_P_IP); + else + skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_POST_ROUTING, skb, NULL, realoutdev, br_nf_dev_queue_xmit); -- cgit v1.2.3-70-g09d2 From 4e15ed4d930297c127d280ca1d0c785be870def4 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Thu, 15 Apr 2010 16:43:08 +0000 Subject: net: replace ipfragok with skb->local_df As Herbert Xu said: we should be able to simply replace ipfragok with skb->local_df. commit f88037(sctp: Drop ipfargok in sctp_xmit function) has droped ipfragok and set local_df value properly. The patch kills the ipfragok parameter of .queue_xmit(). Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 2 +- include/net/inet_connection_sock.h | 2 +- include/net/ip.h | 2 +- include/net/ipv6.h | 3 +-- net/dccp/ipv6.c | 4 ++-- net/dccp/output.c | 2 +- net/ipv4/ip_output.c | 4 ++-- net/ipv4/tcp_output.c | 2 +- net/ipv6/inet6_connection_sock.c | 4 ++-- net/ipv6/ip6_output.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- net/l2tp/l2tp_core.c | 3 ++- net/l2tp/l2tp_ip.c | 2 +- net/sctp/ipv6.c | 2 +- net/sctp/protocol.c | 2 +- 15 files changed, 20 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index f13ddc2543b..aae08f68663 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -38,5 +38,5 @@ extern void inet6_csk_reqsk_queue_hash_add(struct sock *sk, extern void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); -extern int inet6_csk_xmit(struct sk_buff *skb, int ipfragok); +extern int inet6_csk_xmit(struct sk_buff *skb); #endif /* _INET6_CONNECTION_SOCK_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 52c8b8b8a0b..b6d3b55da19 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -36,7 +36,7 @@ struct tcp_congestion_ops; * (i.e. things that depend on the address family) */ struct inet_connection_sock_af_ops { - int (*queue_xmit)(struct sk_buff *skb, int ipfragok); + int (*queue_xmit)(struct sk_buff *skb); void (*send_check)(struct sock *sk, struct sk_buff *skb); int (*rebuild_header)(struct sock *sk); int (*conn_request)(struct sock *sk, struct sk_buff *skb); diff --git a/include/net/ip.h b/include/net/ip.h index 503994a38ed..a84ceb69268 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ extern int ip_do_nat(struct sk_buff *skb); extern void ip_send_check(struct iphdr *ip); extern int __ip_local_out(struct sk_buff *skb); extern int ip_local_out(struct sk_buff *skb); -extern int ip_queue_xmit(struct sk_buff *skb, int ipfragok); +extern int ip_queue_xmit(struct sk_buff *skb); extern void ip_init(void); extern int ip_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 033ddd4652a..b1d8db90b21 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -482,8 +482,7 @@ extern int ip6_rcv_finish(struct sk_buff *skb); extern int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct ipv6_txoptions *opt, - int ipfragok); + struct ipv6_txoptions *opt); extern int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index ab1ab95946d..09169889959 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -292,7 +292,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, &ireq6->loc_addr, &ireq6->rmt_addr); ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + err = ip6_xmit(sk, skb, &fl, opt); err = net_xmit_eval(err); } @@ -347,7 +347,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { skb_dst_set(skb, dst); - ip6_xmit(ctl_sk, skb, &fl, NULL, 0); + ip6_xmit(ctl_sk, skb, &fl, NULL); DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); return; diff --git a/net/dccp/output.c b/net/dccp/output.c index b8d98e3c052..e98b65e9569 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -136,7 +136,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(skb); return net_xmit_eval(err); } return -ENOBUFS; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c65f18e0936..512af81b750 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -311,7 +311,7 @@ int ip_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } -int ip_queue_xmit(struct sk_buff *skb, int ipfragok) +int ip_queue_xmit(struct sk_buff *skb) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -370,7 +370,7 @@ packet_routed: skb_reset_network_header(skb); iph = ip_hdr(skb); *((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff)); - if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok) + if (ip_dont_fragment(sk, &rt->u.dst) && !skb->local_df) iph->frag_off = htons(IP_DF); else iph->frag_off = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e46849989a5..2b7d71fb843 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -890,7 +890,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(skb); if (likely(err <= 0)) return err; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 628db24bcf2..0c5e3c3b7fd 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -178,7 +178,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) return dst; } -int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) +int inet6_csk_xmit(struct sk_buff *skb) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -234,7 +234,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) /* Restore final destination back after routing done */ ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - return ip6_xmit(sk, skb, &fl, np->opt, 0); + return ip6_xmit(sk, skb, &fl, np->opt); } EXPORT_SYMBOL_GPL(inet6_csk_xmit); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index f3a847e3ec8..141819f0c6f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -185,7 +185,7 @@ int ip6_output(struct sk_buff *skb) */ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, - struct ipv6_txoptions *opt, int ipfragok) + struct ipv6_txoptions *opt) { struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b429dfdd69d..bd5ef7b6e48 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -509,7 +509,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + err = ip6_xmit(sk, skb, &fl, opt); err = net_xmit_eval(err); } @@ -1071,7 +1071,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, if (!ip6_dst_lookup(ctl_sk, &dst, &fl)) { if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { skb_dst_set(buff, dst); - ip6_xmit(ctl_sk, buff, &fl, NULL, 0); + ip6_xmit(ctl_sk, buff, &fl, NULL); TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 98dfcce1a5f..ecc7aea9efe 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -954,7 +954,8 @@ int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t dat } /* Queue the packet to IP for output */ - error = ip_queue_xmit(skb, 1); + skb->local_df = 1; + error = ip_queue_xmit(skb); /* Update stats */ if (error >= 0) { diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 75bf784ba18..0852512d392 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -501,7 +501,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m skb_dst_set(skb, dst_clone(&rt->u.dst)); /* Queue the packet to IP for output */ - rc = ip_queue_xmit(skb, 0); + rc = ip_queue_xmit(skb); error: /* Update stats */ diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 14db5689fb8..732689140fb 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -232,7 +232,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) if (!(transport->param_flags & SPP_PMTUD_ENABLE)) skb->local_df = 1; - return ip6_xmit(sk, skb, &fl, np->opt, 0); + return ip6_xmit(sk, skb, &fl, np->opt); } /* Returns the dst cache entry for the given source and destination ip diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index a56f98e82f9..704298f4b28 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -854,7 +854,7 @@ static inline int sctp_v4_xmit(struct sk_buff *skb, IP_PMTUDISC_DO : IP_PMTUDISC_DONT; SCTP_INC_STATS(SCTP_MIB_OUTSCTPPACKS); - return ip_queue_xmit(skb, 0); + return ip_queue_xmit(skb); } static struct sctp_af sctp_af_inet; -- cgit v1.2.3-70-g09d2 From 0a56bd0ae3f84dbd63535205b18b1a736abaa920 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Thu, 15 Apr 2010 17:39:37 -0400 Subject: mac80211: add LDPC control flag LDPC will be enabled through the rate control algorithm for each buffer the the tx_info flags. Signed-off-by: Luis R. Rodriguez Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dcf3c5f23c9..75056dde381 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -274,6 +274,7 @@ struct ieee80211_bss_conf { * @IEEE80211_TX_INTFL_NL80211_FRAME_TX: Frame was requested through nl80211 * MLME command (internal to mac80211 to figure out whether to send TX * status to user space) + * @IEEE80211_TX_CTL_LDPC: tells the driver to use LDPC for this frame */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -297,6 +298,7 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTFL_RETRANSMISSION = BIT(19), IEEE80211_TX_INTFL_HAS_RADIOTAP = BIT(20), IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), + IEEE80211_TX_CTL_LDPC = BIT(22), }; /** -- cgit v1.2.3-70-g09d2 From fec5e652e58fa6017b2c9e06466cb2a6538de5b4 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Fri, 16 Apr 2010 16:01:27 -0700 Subject: rfs: Receive Flow Steering This patch implements receive flow steering (RFS). RFS steers received packets for layer 3 and 4 processing to the CPU where the application for the corresponding flow is running. RFS is an extension of Receive Packet Steering (RPS). The basic idea of RFS is that when an application calls recvmsg (or sendmsg) the application's running CPU is stored in a hash table that is indexed by the connection's rxhash which is stored in the socket structure. The rxhash is passed in skb's received on the connection from netif_receive_skb. For each received packet, the associated rxhash is used to look up the CPU in the hash table, if a valid CPU is set then the packet is steered to that CPU using the RPS mechanisms. The convolution of the simple approach is that it would potentially allow OOO packets. If threads are thrashing around CPUs or multiple threads are trying to read from the same sockets, a quickly changing CPU value in the hash table could cause rampant OOO packets-- we consider this a non-starter. To avoid OOO packets, this solution implements two types of hash tables: rps_sock_flow_table and rps_dev_flow_table. rps_sock_table is a global hash table. Each entry is just a CPU number and it is populated in recvmsg and sendmsg as described above. This table contains the "desired" CPUs for flows. rps_dev_flow_table is specific to each device queue. Each entry contains a CPU and a tail queue counter. The CPU is the "current" CPU for a matching flow. The tail queue counter holds the value of a tail queue counter for the associated CPU's backlog queue at the time of last enqueue for a flow matching the entry. Each backlog queue has a queue head counter which is incremented on dequeue, and so a queue tail counter is computed as queue head count + queue length. When a packet is enqueued on a backlog queue, the current value of the queue tail counter is saved in the hash entry of the rps_dev_flow_table. And now the trick: when selecting the CPU for RPS (get_rps_cpu) the rps_sock_flow table and the rps_dev_flow table for the RX queue are consulted. When the desired CPU for the flow (found in the rps_sock_flow table) does not match the current CPU (found in the rps_dev_flow table), the current CPU is changed to the desired CPU if one of the following is true: - The current CPU is unset (equal to RPS_NO_CPU) - Current CPU is offline - The current CPU's queue head counter >= queue tail counter in the rps_dev_flow table. This checks if the queue tail has advanced beyond the last packet that was enqueued using this table entry. This guarantees that all packets queued using this entry have been dequeued, thus preserving in order delivery. Making each queue have its own rps_dev_flow table has two advantages: 1) the tail queue counters will be written on each receive, so keeping the table local to interrupting CPU s good for locality. 2) this allows lockless access to the table-- the CPU number and queue tail counter need to be accessed together under mutual exclusion from netif_receive_skb, we assume that this is only called from device napi_poll which is non-reentrant. This patch implements RFS for TCP and connected UDP sockets. It should be usable for other flow oriented protocols. There are two configuration parameters for RFS. The "rps_flow_entries" kernel init parameter sets the number of entries in the rps_sock_flow_table, the per rxqueue sysfs entry "rps_flow_cnt" contains the number of entries in the rps_dev_flow table for the rxqueue. Both are rounded to power of two. The obvious benefit of RFS (over just RPS) is that it achieves CPU locality between the receive processing for a flow and the applications processing; this can result in increased performance (higher pps, lower latency). The benefits of RFS are dependent on cache hierarchy, application load, and other factors. On simple benchmarks, we don't necessarily see improvement and sometimes see degradation. However, for more complex benchmarks and for applications where cache pressure is much higher this technique seems to perform very well. Below are some benchmark results which show the potential benfit of this patch. The netperf test has 500 instances of netperf TCP_RR test with 1 byte req. and resp. The RPC test is an request/response test similar in structure to netperf RR test ith 100 threads on each host, but does more work in userspace that netperf. e1000e on 8 core Intel No RFS or RPS 104K tps at 30% CPU No RFS (best RPS config): 290K tps at 63% CPU RFS 303K tps at 61% CPU RPC test tps CPU% 50/90/99% usec latency Latency StdDev No RFS/RPS 103K 48% 757/900/3185 4472.35 RPS only: 174K 73% 415/993/2468 491.66 RFS 223K 73% 379/651/1382 315.61 Signed-off-by: Tom Herbert Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 69 +++++++++++++++++++++++++++- include/net/inet_sock.h | 38 ++++++++++++++++ net/core/dev.c | 111 +++++++++++++++++++++++++++++++++++++-------- net/core/net-sysfs.c | 94 ++++++++++++++++++++++++++++++++++++-- net/core/sysctl_net_core.c | 68 +++++++++++++++++++++++++++ net/ipv4/af_inet.c | 29 ++++++++++-- net/ipv4/tcp_ipv4.c | 2 + net/ipv4/udp.c | 7 ++- 8 files changed, 389 insertions(+), 29 deletions(-) (limited to 'include/net') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 55c2086e1f0..649a0252686 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -530,14 +530,73 @@ struct rps_map { }; #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU and the + * tail pointer for that CPU's input queue at the time of last enqueue. + */ +struct rps_dev_flow { + u16 cpu; + u16 fill; + unsigned int last_qtail; +}; + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct work_struct free_work; + struct rps_dev_flow flows[0]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + (_num * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + */ +struct rps_sock_flow_table { + unsigned int mask; + u16 ents[0]; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_sock_flow_table) + \ + (_num * sizeof(u16))) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) { + unsigned int cpu, index = hash & table->mask; + + /* We only give a hint, preemption can change cpu under us */ + cpu = raw_smp_processor_id(); + + if (table->ents[index] != cpu) + table->ents[index] = cpu; + } +} + +static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + if (table && hash) + table->ents[hash & table->mask] = RPS_NO_CPU; +} + +extern struct rps_sock_flow_table *rps_sock_flow_table; + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map *rps_map; + struct rps_dev_flow_table *rps_flow_table; struct kobject kobj; struct netdev_rx_queue *first; atomic_t count; } ____cacheline_aligned_in_smp; -#endif +#endif /* CONFIG_RPS */ /* * This structure defines the management hooks for network devices. @@ -1333,11 +1392,19 @@ struct softnet_data { /* Elements below can be accessed between CPUs for RPS */ #ifdef CONFIG_RPS struct call_single_data csd ____cacheline_aligned_in_smp; + unsigned int input_queue_head; #endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; }; +static inline void incr_input_queue_head(struct softnet_data *queue) +{ +#ifdef CONFIG_RPS + queue->input_queue_head++; +#endif +} + DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); #define HAVE_NETIF_QUEUE diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 83fd34437cf..b487bc1b99a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -21,6 +21,7 @@ #include #include #include +#include #include #include @@ -101,6 +102,7 @@ struct rtable; * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts + * @rxhash - flow hash received from netif layer * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -124,6 +126,9 @@ struct inet_sock { __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; +#ifdef CONFIG_RPS + __u32 rxhash; +#endif struct ip_options *opt; __u8 tos; @@ -219,4 +224,37 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; } +static inline void inet_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); + rcu_read_unlock(); +#endif +} + +static inline void inet_rps_save_rxhash(const struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(inet_sk(sk)->rxhash != rxhash)) { + inet_rps_reset_flow(sk); + inet_sk(sk)->rxhash = rxhash; + } +#endif +} #endif /* _INET_SOCK_H */ diff --git a/net/core/dev.c b/net/core/dev.c index e8041eb76ac..d7107ac835f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2203,19 +2203,28 @@ int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; #ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table *rps_sock_flow_table; +EXPORT_SYMBOL(rps_sock_flow_table); + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ -static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) { struct ipv6hdr *ip6; struct iphdr *ip; struct netdev_rx_queue *rxqueue; struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u8 ip_proto; + u16 tcpu; u32 addr1, addr2, ports, ihl; if (skb_rx_queue_recorded(skb)) { @@ -2232,7 +2241,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) } else rxqueue = dev->_rx; - if (!rxqueue->rps_map) + if (!rxqueue->rps_map && !rxqueue->rps_flow_table) goto done; if (skb->rxhash) @@ -2284,9 +2293,48 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) skb->rxhash = 1; got_hash: + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[skb->rxhash & + sock_flow_table->mask]; + + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) + rflow->last_qtail = per_cpu(softnet_data, + tcpu).input_queue_head; + } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + map = rcu_dereference(rxqueue->rps_map); if (map) { - u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -2320,13 +2368,14 @@ static void trigger_softirq(void *data) __napi_schedule(&queue->backlog); __get_cpu_var(netdev_rx_stat).received_rps++; } -#endif /* CONFIG_SMP */ +#endif /* CONFIG_RPS */ /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ -static int enqueue_to_backlog(struct sk_buff *skb, int cpu) +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) { struct softnet_data *queue; unsigned long flags; @@ -2341,6 +2390,10 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu) if (queue->input_pkt_queue.qlen) { enqueue: __skb_queue_tail(&queue->input_pkt_queue, skb); +#ifdef CONFIG_RPS + *qtail = queue->input_queue_head + + queue->input_pkt_queue.qlen; +#endif rps_unlock(queue); local_irq_restore(flags); return NET_RX_SUCCESS; @@ -2355,11 +2408,10 @@ enqueue: cpu_set(cpu, rcpus->mask[rcpus->select]); __raise_softirq_irqoff(NET_RX_SOFTIRQ); - } else - __napi_schedule(&queue->backlog); -#else - __napi_schedule(&queue->backlog); + goto enqueue; + } #endif + __napi_schedule(&queue->backlog); } goto enqueue; } @@ -2401,18 +2453,25 @@ int netif_rx(struct sk_buff *skb) #ifdef CONFIG_RPS { + struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); - ret = enqueue_to_backlog(skb, cpu); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); } #else - ret = enqueue_to_backlog(skb, get_cpu()); - put_cpu(); + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } #endif return ret; } @@ -2830,14 +2889,22 @@ out: int netif_receive_skb(struct sk_buff *skb) { #ifdef CONFIG_RPS - int cpu; + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + cpu = get_rps_cpu(skb->dev, skb, &rflow); - if (cpu < 0) - return __netif_receive_skb(skb); - else - return enqueue_to_backlog(skb, cpu); + if (cpu >= 0) { + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + ret = __netif_receive_skb(skb); + } + + return ret; #else return __netif_receive_skb(skb); #endif @@ -2856,6 +2923,7 @@ static void flush_backlog(void *arg) if (skb->dev == dev) { __skb_unlink(skb, &queue->input_pkt_queue); kfree_skb(skb); + incr_input_queue_head(queue); } rps_unlock(queue); } @@ -3179,6 +3247,7 @@ static int process_backlog(struct napi_struct *napi, int quota) local_irq_enable(); break; } + incr_input_queue_head(queue); rps_unlock(queue); local_irq_enable(); @@ -5542,8 +5611,10 @@ static int dev_cpu_callback(struct notifier_block *nfb, local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); + incr_input_queue_head(oldsd); + } return NOTIFY_OK; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 96ed6905b82..143052a22b9 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include "net-sysfs.h" @@ -601,22 +602,109 @@ ssize_t store_rps_map(struct netdev_rx_queue *queue, return len; } +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned int val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%u\n", val); +} + +static void rps_dev_flow_table_release_work(struct work_struct *work) +{ + struct rps_dev_flow_table *table = container_of(work, + struct rps_dev_flow_table, free_work); + + vfree(table); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + + INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); + schedule_work(&table->free_work); +} + +ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned int count; + char *endp; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + count = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (count) { + int i; + + if (count > 1<<30) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } + count = roundup_pow_of_two(count); + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); + if (!table) + return -ENOMEM; + + table->mask = count - 1; + for (i = 0; i < count; i++) + table->flows[i].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = queue->rps_flow_table; + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + static struct rx_queue_attribute rps_cpus_attribute = __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); + static struct attribute *rx_queue_default_attrs[] = { &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct rps_map *map = queue->rps_map; struct netdev_rx_queue *first = queue->first; - if (map) - call_rcu(&map->rcu, rps_map_release); + if (queue->rps_map) + call_rcu(&queue->rps_map->rcu, rps_map_release); + + if (queue->rps_flow_table) + call_rcu(&queue->rps_flow_table->rcu, + rps_dev_flow_table_release); if (atomic_dec_and_test(&first->count)) kfree(first); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b7b6b8208f7..dcc7d25996a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,12 +11,72 @@ #include #include #include +#include #include #include #include #include +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rps_sock_flow_table; + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -82,6 +142,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_RPS + { + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 193dcd6ed64..c5376c72550 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -419,6 +419,8 @@ int inet_release(struct socket *sock) if (sk) { long timeout; + inet_rps_reset_flow(sk); + /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -720,6 +722,8 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -728,12 +732,13 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, } EXPORT_SYMBOL(inet_sendmsg); - static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { struct sock *sk = sock->sk; + inet_rps_record_flow(sk); + /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; @@ -743,6 +748,22 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, return sock_no_sendpage(sock, page, offset, size, flags); } +int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, + size_t size, int flags) +{ + struct sock *sk = sock->sk; + int addr_len = 0; + int err; + + inet_rps_record_flow(sk); + + err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, + flags & ~MSG_DONTWAIT, &addr_len); + if (err >= 0) + msg->msg_namelen = addr_len; + return err; +} +EXPORT_SYMBOL(inet_recvmsg); int inet_shutdown(struct socket *sock, int how) { @@ -872,7 +893,7 @@ const struct proto_ops inet_stream_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = tcp_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = tcp_sendpage, .splice_read = tcp_splice_read, @@ -899,7 +920,7 @@ const struct proto_ops inet_dgram_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT @@ -929,7 +950,7 @@ static const struct proto_ops inet_sockraw_ops = { .setsockopt = sock_common_setsockopt, .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, - .recvmsg = sock_common_recvmsg, + .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a24995cdc4b..ad08392a738 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1672,6 +1672,8 @@ process: skb->dev = NULL; + inet_rps_save_rxhash(sk, skb->rxhash); + bh_lock_sock_nested(sk); ret = 0; if (!sock_owned_by_user(sk)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8fef859db35..666b963496f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1217,6 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; + inet_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1258,8 +1259,12 @@ EXPORT_SYMBOL(udp_lib_unhash); static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int rc = sock_queue_rcv_skb(sk, skb); + int rc; + + if (inet_sk(sk)->inet_daddr) + inet_rps_save_rxhash(sk, skb->rxhash); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); -- cgit v1.2.3-70-g09d2 From 93d95b12b3ba06e0e1f3e43a370ee61539d8cb90 Mon Sep 17 00:00:00 2001 From: Daniel Halperin Date: Sun, 18 Apr 2010 09:28:18 -0700 Subject: mac80211: fix typo in comments The flag is called IEEE80211_TX_STAT_AMPDU rather than using the whole word STATUS. Signed-off-by: Daniel Halperin Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 75056dde381..c49e6adcd8f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -397,11 +397,11 @@ struct ieee80211_tx_rate { * @status: union for status data * @driver_data: array of driver_data pointers * @ampdu_ack_len: number of acked aggregated frames. - * relevant only if IEEE80211_TX_STATUS_AMPDU was set. + * relevant only if IEEE80211_TX_STAT_AMPDU was set. * @ampdu_ack_map: block ack bit map for the aggregation. - * relevant only if IEEE80211_TX_STATUS_AMPDU was set. + * relevant only if IEEE80211_TX_STAT_AMPDU was set. * @ampdu_len: number of aggregated frames. - * relevant only if IEEE80211_TX_STATUS_AMPDU was set. + * relevant only if IEEE80211_TX_STAT_AMPDU was set. * @ack_signal: signal strength of the ACK frame */ struct ieee80211_tx_info { -- cgit v1.2.3-70-g09d2 From 03ceedea972a82d343fa5c2528b3952fa9e615d5 Mon Sep 17 00:00:00 2001 From: Daniel Yingqiang Ma Date: Tue, 13 Apr 2010 15:12:07 +0800 Subject: ath9k: Group Key fix for VAPs When I set up multiple VAPs with ath9k, I encountered an issue that the traffic may be lost after a while. The detailed phenomenon is 1. After a while the clients connected to one of these VAPs will get into a state that no broadcast/multicast packets can be transfered successfully while the unicast packets can be transfered normally. 2. Minutes latter the unitcast packets transfer will fail as well, because the ARP entry is expired and it can't be freshed due to the broadcast trouble. It's caused by the group key overwritten and someone discussed this issue in ath9k-devel maillist before, but haven't work out a fix yet. I referred the method in madwifi, and made a patch for ath9k. The method is to set the high bit of the sender(AP)'s address, and associated that mac and the group key. It requires the hardware supports multicast frame key search. It seems true for AR9160. Not sure whether it's the correct way to fix this issue. But it seems to work in my test. The patch is attached, feel free to revise it. Signed-off-by: Daniel Yingqiang ma Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ath9k/main.c | 28 +++++++++++++++++++++++++--- include/net/mac80211.h | 1 + net/mac80211/key.c | 1 + 3 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index 1f4ea74bf4c..40136cf63fa 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -751,6 +751,7 @@ static int ath_key_config(struct ath_common *common, struct ath_hw *ah = common->ah; struct ath9k_keyval hk; const u8 *mac = NULL; + u8 gmac[ETH_ALEN]; int ret = 0; int idx; @@ -774,9 +775,30 @@ static int ath_key_config(struct ath_common *common, memcpy(hk.kv_val, key->key, key->keylen); if (!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) { - /* For now, use the default keys for broadcast keys. This may - * need to change with virtual interfaces. */ - idx = key->keyidx; + + if (key->ap_addr) { + /* + * Group keys on hardware that supports multicast frame + * key search use a mac that is the sender's address with + * the high bit set instead of the app-specified address. + */ + memcpy(gmac, key->ap_addr, ETH_ALEN); + gmac[0] |= 0x80; + mac = gmac; + + if (key->alg == ALG_TKIP) + idx = ath_reserve_key_cache_slot_tkip(common); + else + idx = ath_reserve_key_cache_slot(common); + if (idx < 0) + mac = NULL; /* no free key cache entries */ + } + + if (!mac) { + /* For now, use the default keys for broadcast keys. This may + * need to change with virtual interfaces. */ + idx = key->keyidx; + } } else if (key->keyidx) { if (WARN_ON(!sta)) return -EOPNOTSUPP; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c49e6adcd8f..63e9d37e3e7 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -793,6 +793,7 @@ struct ieee80211_key_conf { u8 iv_len; u8 hw_key_idx; u8 flags; + u8 *ap_addr; s8 keyidx; u8 keylen; u8 key[0]; diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 8160d9c5372..75705bd4195 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -139,6 +139,7 @@ static void ieee80211_key_enable_hw_accel(struct ieee80211_key *key) struct ieee80211_sub_if_data, u.ap); + key->conf.ap_addr = sdata->dev->dev_addr; ret = drv_set_key(key->local, SET_KEY, sdata, sta, &key->conf); if (!ret) { -- cgit v1.2.3-70-g09d2 From 1289723ef238908ca8d95ff48a46ee0de970f882 Mon Sep 17 00:00:00 2001 From: Holger Schurig Date: Mon, 19 Apr 2010 10:23:57 +0200 Subject: mac80211: sample survey implementation for mac80211 & hwsim This adds the survey function to both mac80211 itself and to mac80211_hwsim. For the latter driver, we simply invent some noise level.A real driver which cannot determine the real channel noise MUST NOT report any noise, especially not a magically conjured one :-) Signed-off-by: Holger Schurig Signed-off-by: John W. Linville --- drivers/net/wireless/mac80211_hwsim.c | 28 ++++++++++++++++++++++++++++ include/net/mac80211.h | 3 ++- net/mac80211/cfg.c | 12 ++++++++++++ net/mac80211/driver-ops.h | 9 +++++++++ 4 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index ec8b0829179..79bb8833ddb 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -829,6 +829,33 @@ static int mac80211_hwsim_conf_tx( return 0; } +static int mac80211_hwsim_get_survey( + struct ieee80211_hw *hw, int idx, + struct survey_info *survey) +{ + struct ieee80211_conf *conf = &hw->conf; + + printk(KERN_DEBUG "%s:%s (idx=%d)\n", + wiphy_name(hw->wiphy), __func__, idx); + + if (idx != 0) + return -ENOENT; + + /* Current channel */ + survey->channel = conf->channel; + + /* + * Magically conjured noise level --- this is only ok for simulated hardware. + * + * A real driver which cannot determine the real channel noise MUST NOT + * report any noise, especially not a magically conjured one :-) + */ + survey->filled = SURVEY_INFO_NOISE_DBM; + survey->noise = -92; + + return 0; +} + #ifdef CONFIG_NL80211_TESTMODE /* * This section contains example code for using netlink @@ -1012,6 +1039,7 @@ static struct ieee80211_ops mac80211_hwsim_ops = .sta_notify = mac80211_hwsim_sta_notify, .set_tim = mac80211_hwsim_set_tim, .conf_tx = mac80211_hwsim_conf_tx, + .get_survey = mac80211_hwsim_get_survey, CFG80211_TESTMODE_CMD(mac80211_hwsim_testmode_cmd) .ampdu_action = mac80211_hwsim_ampdu_action, .sw_scan_start = mac80211_hwsim_sw_scan, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 63e9d37e3e7..cd9915686dd 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1674,7 +1674,8 @@ struct ieee80211_ops { struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, u16 *ssn); - + int (*get_survey)(struct ieee80211_hw *hw, int idx, + struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); void (*set_coverage_class)(struct ieee80211_hw *hw, u8 coverage_class); #ifdef CONFIG_NL80211_TESTMODE diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4edd73cbf05..f97dda735cb 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -410,6 +410,17 @@ static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, return ret; } +static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev, + int idx, struct survey_info *survey) +{ + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + + if (!local->ops->get_survey) + return -EOPNOTSUPP; + + return drv_get_survey(local, idx, survey); +} + static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, u8 *mac, struct station_info *sinfo) { @@ -1507,6 +1518,7 @@ struct cfg80211_ops mac80211_config_ops = { .change_station = ieee80211_change_station, .get_station = ieee80211_get_station, .dump_station = ieee80211_dump_station, + .dump_survey = ieee80211_dump_survey, #ifdef CONFIG_MAC80211_MESH .add_mpath = ieee80211_add_mpath, .del_mpath = ieee80211_del_mpath, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index c3d844093a2..d1f8a7c2225 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -346,6 +346,15 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, return ret; } +static inline int drv_get_survey(struct ieee80211_local *local, int idx, + struct survey_info *survey) +{ + int ret = -EOPNOTSUPP; + if (local->ops->conf_tx) + ret = local->ops->get_survey(&local->hw, idx, survey); + /* trace_drv_get_survey(local, idx, survey, ret); */ + return ret; +} static inline void drv_rfkill_poll(struct ieee80211_local *local) { -- cgit v1.2.3-70-g09d2 From 80725f454e58937ad546103e6a141c46b0d65a1b Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Tue, 20 Apr 2010 08:16:37 +0200 Subject: mac80211: document IEEE80211_CONF_CHANGE_QOS Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville --- include/net/mac80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index cd9915686dd..0e2a1a9b2b6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -612,6 +612,7 @@ enum ieee80211_conf_flags { * @IEEE80211_CONF_CHANGE_RETRY_LIMITS: retry limits changed * @IEEE80211_CONF_CHANGE_IDLE: Idle flag changed * @IEEE80211_CONF_CHANGE_SMPS: Spatial multiplexing powersave mode changed + * @IEEE80211_CONF_CHANGE_QOS: Quality of service was enabled or disabled */ enum ieee80211_conf_changed { IEEE80211_CONF_CHANGE_SMPS = BIT(1), -- cgit v1.2.3-70-g09d2 From f79d9bad37cb1e7ef23d60b1dd0b7859957ced9e Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Mon, 19 Apr 2010 19:57:35 +0200 Subject: mac80211: add flags for STBC (Space-Time Block Coding) Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/linux/ieee80211.h | 1 + include/net/mac80211.h | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 1252ba1fbff..97b2eae6a22 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -876,6 +876,7 @@ struct ieee80211_ht_cap { #define IEEE80211_HT_CAP_SGI_40 0x0040 #define IEEE80211_HT_CAP_TX_STBC 0x0080 #define IEEE80211_HT_CAP_RX_STBC 0x0300 +#define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 #define IEEE80211_HT_CAP_DELAY_BA 0x0400 #define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 #define IEEE80211_HT_CAP_DSSSCCK40 0x1000 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0e2a1a9b2b6..7dc5a679039 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -275,6 +275,8 @@ struct ieee80211_bss_conf { * MLME command (internal to mac80211 to figure out whether to send TX * status to user space) * @IEEE80211_TX_CTL_LDPC: tells the driver to use LDPC for this frame + * @IEEE80211_TX_CTL_STBC: Enables Space-Time Block Coding (STBC) for this + * frame and selects the maximum number of streams that it can use. */ enum mac80211_tx_control_flags { IEEE80211_TX_CTL_REQ_TX_STATUS = BIT(0), @@ -299,6 +301,8 @@ enum mac80211_tx_control_flags { IEEE80211_TX_INTFL_HAS_RADIOTAP = BIT(20), IEEE80211_TX_INTFL_NL80211_FRAME_TX = BIT(21), IEEE80211_TX_CTL_LDPC = BIT(22), + IEEE80211_TX_CTL_STBC = BIT(23) | BIT(24), +#define IEEE80211_TX_CTL_STBC_SHIFT 23 }; /** -- cgit v1.2.3-70-g09d2 From aa395145165cb06a0d0885221bbe0ce4a564391d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Apr 2010 13:03:51 +0000 Subject: net: sk_sleep() helper Define a new function to return the waitqueue of a "struct sock". static inline wait_queue_head_t *sk_sleep(struct sock *sk) { return sk->sk_sleep; } Change all read occurrences of sk_sleep by a call to this function. Needed for a future RCU conversion. sk_sleep wont be a field directly available. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/atm/atmtcp.c | 6 ++-- drivers/net/macvtap.c | 4 +-- drivers/net/tun.c | 4 +-- drivers/scsi/iscsi_tcp.c | 4 +-- include/net/sock.h | 10 +++++-- include/net/tcp.h | 2 +- net/atm/common.c | 12 ++++---- net/atm/signaling.c | 2 +- net/atm/svc.c | 62 ++++++++++++++++++++--------------------- net/ax25/af_ax25.c | 8 +++--- net/bluetooth/af_bluetooth.c | 6 ++-- net/bluetooth/bnep/core.c | 8 +++--- net/bluetooth/bnep/netdev.c | 6 ++-- net/bluetooth/cmtp/cmtp.h | 2 +- net/bluetooth/cmtp/core.c | 4 +-- net/bluetooth/hidp/core.c | 10 +++---- net/bluetooth/hidp/hidp.h | 4 +-- net/bluetooth/l2cap.c | 4 +-- net/bluetooth/rfcomm/sock.c | 8 +++--- net/bluetooth/sco.c | 4 +-- net/caif/caif_socket.c | 2 +- net/core/datagram.c | 6 ++-- net/core/sock.c | 16 +++++------ net/core/stream.c | 16 +++++------ net/dccp/output.c | 6 ++-- net/dccp/proto.c | 2 +- net/decnet/af_decnet.c | 26 ++++++++--------- net/ipv4/af_inet.c | 6 ++-- net/ipv4/inet_connection_sock.c | 4 +-- net/ipv4/tcp.c | 2 +- net/irda/af_irda.c | 14 +++++----- net/iucv/af_iucv.c | 12 ++++---- net/llc/af_llc.c | 12 ++++---- net/netfilter/ipvs/ip_vs_sync.c | 2 +- net/netrom/af_netrom.c | 8 +++--- net/rds/af_rds.c | 2 +- net/rds/rds.h | 2 +- net/rds/recv.c | 2 +- net/rds/send.c | 2 +- net/rose/af_rose.c | 8 +++--- net/rxrpc/af_rxrpc.c | 4 +-- net/sctp/socket.c | 20 ++++++------- net/sunrpc/svcsock.c | 24 ++++++++-------- net/tipc/socket.c | 26 ++++++++--------- net/unix/af_unix.c | 10 +++---- net/x25/af_x25.c | 8 +++--- 46 files changed, 208 insertions(+), 204 deletions(-) (limited to 'include/net') diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index b86712167eb..b9101818b47 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -68,7 +68,7 @@ static int atmtcp_send_control(struct atm_vcc *vcc,int type, *(struct atm_vcc **) &new_msg->vcc = vcc; old_test = test_bit(flag,&vcc->flags); out_vcc->push(out_vcc,skb); - add_wait_queue(sk_atm(vcc)->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk_atm(vcc)), &wait); while (test_bit(flag,&vcc->flags) == old_test) { mb(); out_vcc = PRIV(vcc->dev) ? PRIV(vcc->dev)->vcc : NULL; @@ -80,7 +80,7 @@ static int atmtcp_send_control(struct atm_vcc *vcc,int type, schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(sk_atm(vcc)->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk_atm(vcc)), &wait); return error; } @@ -105,7 +105,7 @@ static int atmtcp_recv_control(const struct atmtcp_control *msg) msg->type); return -EINVAL; } - wake_up(sk_atm(vcc)->sk_sleep); + wake_up(sk_sleep(sk_atm(vcc))); return 0; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index abba3cc81f1..85d6420f840 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -246,8 +246,8 @@ static void macvtap_sock_write_space(struct sock *sk) !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 43265207d46..20a17938c62 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -868,8 +868,8 @@ static void tun_sock_write_space(struct sock *sk) if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); tun = tun_sk(sk)->tun; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 0ee725ced51..9eae04afa9a 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -599,9 +599,9 @@ static void iscsi_sw_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); write_unlock_bh(&tcp_sw_conn->sock->sk->sk_callback_lock); - if (sock->sk->sk_sleep && waitqueue_active(sock->sk->sk_sleep)) { + if (sk_sleep(sock->sk) && waitqueue_active(sk_sleep(sock->sk))) { sock->sk->sk_err = EIO; - wake_up_interruptible(sock->sk->sk_sleep); + wake_up_interruptible(sk_sleep(sock->sk)); } iscsi_conn_stop(cls_conn, flag); diff --git a/include/net/sock.h b/include/net/sock.h index 56df440a950..8ab05146a44 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1160,6 +1160,10 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) sk->sk_socket = sock; } +static inline wait_queue_head_t *sk_sleep(struct sock *sk) +{ + return sk->sk_sleep; +} /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, @@ -1346,8 +1350,8 @@ static inline int sk_has_allocations(const struct sock *sk) * tp->rcv_nxt check sock_def_readable * ... { * schedule ... - * if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - * wake_up_interruptible(sk->sk_sleep) + * if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + * wake_up_interruptible(sk_sleep(sk)) * ... * } * @@ -1368,7 +1372,7 @@ static inline int sk_has_sleeper(struct sock *sk) * This memory barrier is paired in the sock_poll_wait. */ smp_mb__after_lock(); - return sk->sk_sleep && waitqueue_active(sk->sk_sleep); + return sk_sleep(sk) && waitqueue_active(sk_sleep(sk)); } /** diff --git a/include/net/tcp.h b/include/net/tcp.h index 70c5159f4b3..b7d83d204a9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -939,7 +939,7 @@ static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb) tp->ucopy.memory = 0; } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { - wake_up_interruptible_sync_poll(sk->sk_sleep, + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | POLLRDNORM | POLLRDBAND); if (!inet_csk_ack_scheduled(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, diff --git a/net/atm/common.c b/net/atm/common.c index 97ed94aa0cb..e3e10e6f862 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -92,7 +92,7 @@ static void vcc_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up(sk->sk_sleep); + wake_up(sk_sleep(sk)); read_unlock(&sk->sk_callback_lock); } @@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk) if (vcc_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -549,7 +549,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, } eff = (size+3) & ~3; /* align to word boundary */ - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); error = 0; while (!(skb = alloc_tx(vcc, eff))) { if (m->msg_flags & MSG_DONTWAIT) { @@ -568,9 +568,9 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, send_sig(SIGPIPE, current, 0); break; } - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (error) goto out; skb->dev = NULL; /* for paths shared with net_device interfaces */ @@ -595,7 +595,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait) struct atm_vcc *vcc; unsigned int mask; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; vcc = ATM_SD(sock); diff --git a/net/atm/signaling.c b/net/atm/signaling.c index 6ba6e466ee5..509c8ac02b6 100644 --- a/net/atm/signaling.c +++ b/net/atm/signaling.c @@ -131,7 +131,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb) } sk->sk_ack_backlog++; skb_queue_tail(&sk->sk_receive_queue, skb); - pr_debug("waking sk->sk_sleep 0x%p\n", sk->sk_sleep); + pr_debug("waking sk_sleep(sk) 0x%p\n", sk_sleep(sk)); sk->sk_state_change(sk); as_indicate_complete: release_sock(sk); diff --git a/net/atm/svc.c b/net/atm/svc.c index 3ba9a45a51a..754ee4791d9 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -49,14 +49,14 @@ static void svc_disconnect(struct atm_vcc *vcc) pr_debug("%p\n", vcc); if (test_bit(ATM_VF_REGIS, &vcc->flags)) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); sigd_enq(vcc, as_close, NULL, NULL, NULL); while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } /* beware - socket is still in use by atmsigd until the last as_indicate has been answered */ @@ -125,13 +125,13 @@ static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, } vcc->local = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */ if (!sigd) { error = -EUNATCH; @@ -201,10 +201,10 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, } vcc->remote = *addr; set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote); if (flags & O_NONBLOCK) { - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); sock->state = SS_CONNECTING; error = -EINPROGRESS; goto out; @@ -213,7 +213,7 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); if (!signal_pending(current)) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); continue; } @@ -232,14 +232,14 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, */ sigd_enq(vcc, as_close, NULL, NULL, NULL); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } if (!sk->sk_err) while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); schedule(); } @@ -250,7 +250,7 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, error = -EINTR; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!sigd) { @@ -302,13 +302,13 @@ static int svc_listen(struct socket *sock, int backlog) goto out; } set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; @@ -343,7 +343,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) while (1) { DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (!(skb = skb_dequeue(&sk->sk_receive_queue)) && sigd) { if (test_bit(ATM_VF_RELEASED, &old_vcc->flags)) @@ -363,10 +363,10 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) error = -ERESTARTSYS; break; } - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (error) goto out; if (!skb) { @@ -392,17 +392,17 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags) } /* wait should be short, so we ignore the non-blocking flag */ set_bit(ATM_VF_WAITING, &new_vcc->flags); - prepare_to_wait(sk_atm(new_vcc)->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait, TASK_UNINTERRUPTIBLE); sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL); while (test_bit(ATM_VF_WAITING, &new_vcc->flags) && sigd) { release_sock(sk); schedule(); lock_sock(sk); - prepare_to_wait(sk_atm(new_vcc)->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait, TASK_UNINTERRUPTIBLE); } - finish_wait(sk_atm(new_vcc)->sk_sleep, &wait); + finish_wait(sk_sleep(sk_atm(new_vcc)), &wait); if (!sigd) { error = -EUNATCH; goto out; @@ -438,14 +438,14 @@ int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos) DEFINE_WAIT(wait); set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0); while (test_bit(ATM_VF_WAITING, &vcc->flags) && !test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (!sigd) return -EUNATCH; return -sk->sk_err; @@ -534,20 +534,20 @@ static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr, lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sigd_enq(vcc, as_addparty, NULL, NULL, (struct sockaddr_atmsvc *) sockaddr); if (flags & O_NONBLOCK) { - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); error = -EINPROGRESS; goto out; } pr_debug("added wait queue\n"); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); error = xchg(&sk->sk_err_soft, 0); out: release_sock(sk); @@ -563,13 +563,13 @@ static int svc_dropparty(struct socket *sock, int ep_ref) lock_sock(sk); set_bit(ATM_VF_WAITING, &vcc->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref); while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) { schedule(); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (!sigd) { error = -EUNATCH; goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 65c5801261f..cfdfd7e2a17 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1281,7 +1281,7 @@ static int __must_check ax25_connect(struct socket *sock, DEFINE_WAIT(wait); for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_state != TCP_SYN_SENT) break; @@ -1294,7 +1294,7 @@ static int __must_check ax25_connect(struct socket *sock, err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; @@ -1346,7 +1346,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) * hooked into the SABM we saved */ for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); skb = skb_dequeue(&sk->sk_receive_queue); if (skb) break; @@ -1364,7 +1364,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags) err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 404a8500fd0..421c45bd1b9 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -288,7 +288,7 @@ unsigned int bt_sock_poll(struct file * file, struct socket *sock, poll_table *w BT_DBG("sock %p, sk %p", sock, sk); - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); @@ -378,7 +378,7 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) BT_DBG("sk %p", sk); - add_wait_queue(sk->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk), &wait); while (sk->sk_state != state) { set_current_state(TASK_INTERRUPTIBLE); @@ -401,7 +401,7 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) break; } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_state); diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 8062dad6d10..f10b41fb05a 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -474,7 +474,7 @@ static int bnep_session(void *arg) set_user_nice(current, -15); init_waitqueue_entry(&wait, current); - add_wait_queue(sk->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk), &wait); while (!atomic_read(&s->killed)) { set_current_state(TASK_INTERRUPTIBLE); @@ -496,7 +496,7 @@ static int bnep_session(void *arg) schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); /* Cleanup session */ down_write(&bnep_session_sem); @@ -507,7 +507,7 @@ static int bnep_session(void *arg) /* Wakeup user-space polling for socket errors */ s->sock->sk->sk_err = EUNATCH; - wake_up_interruptible(s->sock->sk->sk_sleep); + wake_up_interruptible(sk_sleep(s->sock->sk)); /* Release the socket */ fput(s->sock->file); @@ -638,7 +638,7 @@ int bnep_del_connection(struct bnep_conndel_req *req) /* Kill session thread */ atomic_inc(&s->killed); - wake_up_interruptible(s->sock->sk->sk_sleep); + wake_up_interruptible(sk_sleep(s->sock->sk)); } else err = -ENOENT; diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c index d48b33f4d4b..0faad5ce6dc 100644 --- a/net/bluetooth/bnep/netdev.c +++ b/net/bluetooth/bnep/netdev.c @@ -109,7 +109,7 @@ static void bnep_net_set_mc_list(struct net_device *dev) } skb_queue_tail(&sk->sk_write_queue, skb); - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); #endif } @@ -193,11 +193,11 @@ static netdev_tx_t bnep_net_xmit(struct sk_buff *skb, /* * We cannot send L2CAP packets from here as we are potentially in a bh. * So we have to queue them and wake up session thread which is sleeping - * on the sk->sk_sleep. + * on the sk_sleep(sk). */ dev->trans_start = jiffies; skb_queue_tail(&sk->sk_write_queue, skb); - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); if (skb_queue_len(&sk->sk_write_queue) >= BNEP_TX_QUEUE_LEN) { BT_DBG("tx queue is full"); diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h index e4663aa14d2..785e79e953c 100644 --- a/net/bluetooth/cmtp/cmtp.h +++ b/net/bluetooth/cmtp/cmtp.h @@ -125,7 +125,7 @@ static inline void cmtp_schedule(struct cmtp_session *session) { struct sock *sk = session->sock->sk; - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); } /* CMTP init defines */ diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 0073ec8495d..d4c6af082d4 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -284,7 +284,7 @@ static int cmtp_session(void *arg) set_user_nice(current, -15); init_waitqueue_entry(&wait, current); - add_wait_queue(sk->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk), &wait); while (!atomic_read(&session->terminate)) { set_current_state(TASK_INTERRUPTIBLE); @@ -301,7 +301,7 @@ static int cmtp_session(void *arg) schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); down_write(&cmtp_session_sem); diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 280529ad927..bfe641b7dfa 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -561,8 +561,8 @@ static int hidp_session(void *arg) init_waitqueue_entry(&ctrl_wait, current); init_waitqueue_entry(&intr_wait, current); - add_wait_queue(ctrl_sk->sk_sleep, &ctrl_wait); - add_wait_queue(intr_sk->sk_sleep, &intr_wait); + add_wait_queue(sk_sleep(ctrl_sk), &ctrl_wait); + add_wait_queue(sk_sleep(intr_sk), &intr_wait); while (!atomic_read(&session->terminate)) { set_current_state(TASK_INTERRUPTIBLE); @@ -584,8 +584,8 @@ static int hidp_session(void *arg) schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(intr_sk->sk_sleep, &intr_wait); - remove_wait_queue(ctrl_sk->sk_sleep, &ctrl_wait); + remove_wait_queue(sk_sleep(intr_sk), &intr_wait); + remove_wait_queue(sk_sleep(ctrl_sk), &ctrl_wait); down_write(&hidp_session_sem); @@ -609,7 +609,7 @@ static int hidp_session(void *arg) fput(session->intr_sock->file); - wait_event_timeout(*(ctrl_sk->sk_sleep), + wait_event_timeout(*(sk_sleep(ctrl_sk)), (ctrl_sk->sk_state == BT_CLOSED), msecs_to_jiffies(500)); fput(session->ctrl_sock->file); diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index a4e215d50c1..8d934a19da0 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -164,8 +164,8 @@ static inline void hidp_schedule(struct hidp_session *session) struct sock *ctrl_sk = session->ctrl_sock->sk; struct sock *intr_sk = session->intr_sock->sk; - wake_up_interruptible(ctrl_sk->sk_sleep); - wake_up_interruptible(intr_sk->sk_sleep); + wake_up_interruptible(sk_sleep(ctrl_sk)); + wake_up_interruptible(sk_sleep(intr_sk)); } /* HIDP init defines */ diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 99d68c34e4f..c1e60eed5a9 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1147,7 +1147,7 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(nsk = bt_accept_dequeue(sk, newsock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { @@ -1170,7 +1170,7 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl } } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 8ed3c37684f..43fbf6b4b4b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -503,7 +503,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(nsk = bt_accept_dequeue(sk, newsock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { @@ -526,7 +526,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f } } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; @@ -621,7 +621,7 @@ static long rfcomm_sock_data_wait(struct sock *sk, long timeo) { DECLARE_WAITQUEUE(wait, current); - add_wait_queue(sk->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk), &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); @@ -640,7 +640,7 @@ static long rfcomm_sock_data_wait(struct sock *sk, long timeo) } __set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); return timeo; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index ca6b2ad1c3f..b406d3eff53 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -567,7 +567,7 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(ch = bt_accept_dequeue(sk, newsock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { @@ -590,7 +590,7 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag } } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index cdf62b9fefa..90317e7d10b 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -689,7 +689,7 @@ static unsigned int caif_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; struct caifsock *cf_sk = container_of(sk, struct caifsock, sk); u32 mask = 0; - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); lock_sock(&(cf_sk->sk)); if (!STATE_IS_OPEN(cf_sk)) { if (!STATE_IS_PENDING(cf_sk)) diff --git a/net/core/datagram.c b/net/core/datagram.c index 2dccd4ee591..5574a5ddf90 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -86,7 +86,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) int error; DEFINE_WAIT_FUNC(wait, receiver_wake_function); - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); @@ -115,7 +115,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p) error = 0; *timeo_p = schedule_timeout(*timeo_p); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return error; interrupted: error = sock_intr_errno(*timeo_p); @@ -726,7 +726,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* exceptional events? */ diff --git a/net/core/sock.c b/net/core/sock.c index 7effa1e689d..58ebd146ce5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1395,7 +1395,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) if (signal_pending(current)) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) break; if (sk->sk_shutdown & SEND_SHUTDOWN) @@ -1404,7 +1404,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; timeo = schedule_timeout(timeo); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } @@ -1570,11 +1570,11 @@ int sk_wait_data(struct sock *sk, long *timeo) int rc; DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } EXPORT_SYMBOL(sk_wait_data); @@ -1798,7 +1798,7 @@ static void sock_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk->sk_sleep); + wake_up_interruptible_all(sk_sleep(sk)); read_unlock(&sk->sk_callback_lock); } @@ -1806,7 +1806,7 @@ static void sock_def_error_report(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible_poll(sk->sk_sleep, POLLERR); + wake_up_interruptible_poll(sk_sleep(sk), POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); read_unlock(&sk->sk_callback_lock); } @@ -1815,7 +1815,7 @@ static void sock_def_readable(struct sock *sk, int len) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN | + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); read_unlock(&sk->sk_callback_lock); @@ -1830,7 +1830,7 @@ static void sock_def_write_space(struct sock *sk) */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ diff --git a/net/core/stream.c b/net/core/stream.c index a37debfeb1b..7b3c3f30b10 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -32,8 +32,8 @@ void sk_stream_write_space(struct sock *sk) if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); @@ -66,13 +66,13 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) if (signal_pending(tsk)) return sock_intr_errno(*timeo_p); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, !sk->sk_err && !((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); return 0; @@ -96,13 +96,13 @@ void sk_stream_wait_close(struct sock *sk, long timeout) DEFINE_WAIT(wait); do { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk))) break; } while (!signal_pending(current) && timeout); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } } @@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) while (1) { set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; @@ -157,7 +157,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) *timeo_p = current_timeo; } out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; do_error: diff --git a/net/dccp/output.c b/net/dccp/output.c index e98b65e9569..2d3dcb39851 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -198,7 +198,7 @@ void dccp_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); @@ -225,7 +225,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay) dccp_pr_debug("delayed send by %d msec\n", delay); jiffdelay = msecs_to_jiffies(delay); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); sk->sk_write_pending++; release_sock(sk); @@ -241,7 +241,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay) rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); } while ((delay = rc) > 0); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; do_error: diff --git a/net/dccp/proto.c b/net/dccp/proto.c index a0e38d8018f..b03ecf6b2bb 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -312,7 +312,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 55e3b6b0061..d6b93d19790 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -832,7 +832,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) scp->segsize_loc = dst_metric(__sk_dst_get(sk), RTAX_ADVMSS); dn_send_conn_conf(sk, allocation); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); for(;;) { release_sock(sk); if (scp->state == DN_CC) @@ -850,9 +850,9 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err == 0) { sk->sk_socket->state = SS_CONNECTED; } else if (scp->state != DN_CC) { @@ -873,7 +873,7 @@ static int dn_wait_run(struct sock *sk, long *timeo) if (!*timeo) return -EALREADY; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); for(;;) { release_sock(sk); if (scp->state == DN_CI || scp->state == DN_CC) @@ -891,9 +891,9 @@ static int dn_wait_run(struct sock *sk, long *timeo) err = -ETIMEDOUT; if (!*timeo) break; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); out: if (err == 0) { sk->sk_socket->state = SS_CONNECTED; @@ -1040,7 +1040,7 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) struct sk_buff *skb = NULL; int err = 0; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); for(;;) { release_sock(sk); skb = skb_dequeue(&sk->sk_receive_queue); @@ -1060,9 +1060,9 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo) err = -EAGAIN; if (!*timeo) break; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return skb == NULL ? ERR_PTR(err) : skb; } @@ -1746,11 +1746,11 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock, goto out; } - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } skb_queue_walk_safe(queue, skb, n) { @@ -2003,12 +2003,12 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock, goto out; } - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); sk_wait_event(sk, &timeo, !dn_queue_too_long(scp, queue, flags)); clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); continue; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c5376c72550..5ca7290c2e6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -548,7 +548,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) { DEFINE_WAIT(wait); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -561,9 +561,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo) lock_sock(sk); if (signal_pending(current) || !timeo) break; - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeo; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8da6429269d..e0a3e3537b1 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -234,7 +234,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) * having to remove and re-insert us on the wait queue. */ for (;;) { - prepare_to_wait_exclusive(sk->sk_sleep, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); if (reqsk_queue_empty(&icsk->icsk_accept_queue)) @@ -253,7 +253,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) if (!timeo) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0f8caf64caa..77208334a61 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -378,7 +378,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sock *sk = sock->sk; struct tcp_sock *tp = tcp_sk(sk); - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == TCP_LISTEN) return inet_csk_listen_poll(sk); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 2a4efcea342..79986a674f6 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -347,7 +347,7 @@ static void irda_flow_indication(void *instance, void *sap, LOCAL_FLOW flow) self->tx_flow = flow; IRDA_DEBUG(1, "%s(), IrTTP wants us to start again\n", __func__); - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); break; default: IRDA_DEBUG(0, "%s(), Unknown flow command!\n", __func__); @@ -900,7 +900,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) if (flags & O_NONBLOCK) goto out; - err = wait_event_interruptible(*(sk->sk_sleep), + err = wait_event_interruptible(*(sk_sleep(sk)), skb_peek(&sk->sk_receive_queue)); if (err) goto out; @@ -1066,7 +1066,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, goto out; err = -ERESTARTSYS; - if (wait_event_interruptible(*(sk->sk_sleep), + if (wait_event_interruptible(*(sk_sleep(sk)), (sk->sk_state != TCP_SYN_SENT))) goto out; @@ -1318,7 +1318,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock, /* Check if IrTTP is wants us to slow down */ - if (wait_event_interruptible(*(sk->sk_sleep), + if (wait_event_interruptible(*(sk_sleep(sk)), (self->tx_flow != FLOW_STOP || sk->sk_state != TCP_ESTABLISHED))) { err = -ERESTARTSYS; goto out; @@ -1477,7 +1477,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, if (copied >= target) break; - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* * POSIX 1003.1g mandates this order. @@ -1497,7 +1497,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock, /* Wait process until data arrives */ schedule(); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out; @@ -1787,7 +1787,7 @@ static unsigned int irda_poll(struct file * file, struct socket *sock, IRDA_DEBUG(4, "%s()\n", __func__); lock_kernel(); - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); mask = 0; /* Exceptional events? */ diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index c18286a2167..9636b7d27b4 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -59,7 +59,7 @@ do { \ DEFINE_WAIT(__wait); \ long __timeo = timeo; \ ret = 0; \ - prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \ + prepare_to_wait(sk_sleep(sk), &__wait, TASK_INTERRUPTIBLE); \ while (!(condition)) { \ if (!__timeo) { \ ret = -EAGAIN; \ @@ -76,7 +76,7 @@ do { \ if (ret) \ break; \ } \ - finish_wait(sk->sk_sleep, &__wait); \ + finish_wait(sk_sleep(sk), &__wait); \ } while (0) #define iucv_sock_wait(sk, condition, timeo) \ @@ -307,7 +307,7 @@ static void iucv_sock_wake_msglim(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk->sk_sleep); + wake_up_interruptible_all(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); read_unlock(&sk->sk_callback_lock); } @@ -795,7 +795,7 @@ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* Wait for an incoming connection */ - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); while (!(nsk = iucv_accept_dequeue(sk, newsock))) { set_current_state(TASK_INTERRUPTIBLE); if (!timeo) { @@ -819,7 +819,7 @@ static int iucv_sock_accept(struct socket *sock, struct socket *newsock, } set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; @@ -1269,7 +1269,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; unsigned int mask = 0; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == IUCV_LISTEN) return iucv_accept_poll(sk); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2db6a9f7591..023ba820236 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -536,7 +536,7 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) int rc = 0; while (1) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE)) break; rc = -ERESTARTSYS; @@ -547,7 +547,7 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout) break; rc = 0; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } @@ -556,13 +556,13 @@ static int llc_ui_wait_for_conn(struct sock *sk, long timeout) DEFINE_WAIT(wait); while (1) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT)) break; if (signal_pending(current) || !timeout) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return timeout; } @@ -573,7 +573,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) int rc; while (1) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); rc = 0; if (sk_wait_event(sk, &timeout, (sk->sk_shutdown & RCV_SHUTDOWN) || @@ -588,7 +588,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout) if (!timeout) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return rc; } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 8fb0ae61676..7ba06939829 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -802,7 +802,7 @@ static int sync_thread_backup(void *data) ip_vs_backup_mcast_ifn, ip_vs_backup_syncid); while (!kthread_should_stop()) { - wait_event_interruptible(*tinfo->sock->sk->sk_sleep, + wait_event_interruptible(*sk_sleep(tinfo->sock->sk), !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) || kthread_should_stop()); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index fa07f044b59..06cb02796a0 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -739,7 +739,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, DEFINE_WAIT(wait); for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_state != TCP_SYN_SENT) break; @@ -752,7 +752,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; } @@ -798,7 +798,7 @@ static int nr_accept(struct socket *sock, struct socket *newsock, int flags) * hooked into the SABM we saved */ for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); skb = skb_dequeue(&sk->sk_receive_queue); if (skb) break; @@ -816,7 +816,7 @@ static int nr_accept(struct socket *sock, struct socket *newsock, int flags) err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 7919a9edb8e..aebfecbdb84 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -158,7 +158,7 @@ static unsigned int rds_poll(struct file *file, struct socket *sock, unsigned int mask = 0; unsigned long flags; - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); if (rs->rs_seen_congestion) poll_wait(file, &rds_poll_waitq, wait); diff --git a/net/rds/rds.h b/net/rds/rds.h index 4bec6e2ed49..c224b5bb3ba 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -492,7 +492,7 @@ void rds_sock_put(struct rds_sock *rs); void rds_wake_sk_sleep(struct rds_sock *rs); static inline void __rds_wake_sk_sleep(struct sock *sk) { - wait_queue_head_t *waitq = sk->sk_sleep; + wait_queue_head_t *waitq = sk_sleep(sk); if (!sock_flag(sk, SOCK_DEAD) && waitq) wake_up(waitq); diff --git a/net/rds/recv.c b/net/rds/recv.c index e2a2b9344f7..795a00b7f2c 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -432,7 +432,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, break; } - timeo = wait_event_interruptible_timeout(*sk->sk_sleep, + timeo = wait_event_interruptible_timeout(*sk_sleep(sk), (!list_empty(&rs->rs_notify_queue) || rs->rs_cong_notify || rds_next_incoming(rs, &inc)), timeo); diff --git a/net/rds/send.c b/net/rds/send.c index 53d6795ac9d..9c1c6bcaa6c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -915,7 +915,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, goto out; } - timeo = wait_event_interruptible_timeout(*sk->sk_sleep, + timeo = wait_event_interruptible_timeout(*sk_sleep(sk), rds_send_queue_rm(rs, conn, rm, rs->rs_bound_port, dport, diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 4fb711a035f..8e45e76a95f 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -845,7 +845,7 @@ rose_try_next_neigh: DEFINE_WAIT(wait); for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (sk->sk_state != TCP_SYN_SENT) break; @@ -858,7 +858,7 @@ rose_try_next_neigh: err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; @@ -911,7 +911,7 @@ static int rose_accept(struct socket *sock, struct socket *newsock, int flags) * hooked into the SABM we saved */ for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); skb = skb_dequeue(&sk->sk_receive_queue); if (skb) @@ -930,7 +930,7 @@ static int rose_accept(struct socket *sock, struct socket *newsock, int flags) err = -ERESTARTSYS; break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); if (err) goto out_release; diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index c060095b27c..c432d76f415 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -65,7 +65,7 @@ static void rxrpc_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (rxrpc_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } read_unlock(&sk->sk_callback_lock); @@ -589,7 +589,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* the socket is readable if there are any messages waiting on the Rx diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c1941276f6e..f34adcca8a8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5702,7 +5702,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) struct sctp_sock *sp = sctp_sk(sk); unsigned int mask; - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); /* A TCP-style listening socket becomes readable when the accept queue * is not empty. @@ -5943,7 +5943,7 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) int error; DEFINE_WAIT(wait); - prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); /* Socket errors? */ error = sock_error(sk); @@ -5980,14 +5980,14 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p) sctp_lock_sock(sk); ready: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return 0; interrupted: error = sock_intr_errno(*timeo_p); out: - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); *err = error; return error; } @@ -6061,8 +6061,8 @@ static void __sctp_write_space(struct sctp_association *asoc) wake_up_interruptible(&asoc->wait); if (sctp_writeable(sk)) { - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); /* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. @@ -6296,7 +6296,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) for (;;) { - prepare_to_wait_exclusive(sk->sk_sleep, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&ep->asocs)) { @@ -6322,7 +6322,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo) break; } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); return err; } @@ -6332,7 +6332,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) DEFINE_WAIT(wait); do { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (list_empty(&sctp_sk(sk)->ep->asocs)) break; sctp_release_sock(sk); @@ -6340,7 +6340,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout) sctp_lock_sock(sk); } while (!signal_pending(current) && timeout); - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); } static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index a29f259204e..ce0d5b35c2a 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -419,8 +419,8 @@ static void svc_udp_data_ready(struct sock *sk, int count) set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); } - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); } /* @@ -436,10 +436,10 @@ static void svc_write_space(struct sock *sk) svc_xprt_enqueue(&svsk->sk_xprt); } - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) { + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) { dprintk("RPC svc_write_space: someone sleeping on %p\n", svsk); - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); } } @@ -757,8 +757,8 @@ static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused) printk("svc: socket %p: no user data\n", sk); } - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_all(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_all(sk_sleep(sk)); } /* @@ -777,8 +777,8 @@ static void svc_tcp_state_change(struct sock *sk) set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); } - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_all(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_all(sk_sleep(sk)); } static void svc_tcp_data_ready(struct sock *sk, int count) @@ -791,8 +791,8 @@ static void svc_tcp_data_ready(struct sock *sk, int count) set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); } - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); } /* @@ -1494,8 +1494,8 @@ static void svc_sock_detach(struct svc_xprt *xprt) sk->sk_data_ready = svsk->sk_odata; sk->sk_write_space = svsk->sk_owspace; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); } /* diff --git a/net/tipc/socket.c b/net/tipc/socket.c index cfb20b80b3a..66e889ba48f 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -446,7 +446,7 @@ static unsigned int poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; u32 mask; - poll_wait(file, sk->sk_sleep, wait); + poll_wait(file, sk_sleep(sk), wait); if (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state == SS_UNCONNECTED) || @@ -591,7 +591,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock, break; } release_sock(sk); - res = wait_event_interruptible(*sk->sk_sleep, + res = wait_event_interruptible(*sk_sleep(sk), !tport->congested); lock_sock(sk); if (res) @@ -650,7 +650,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock, break; } release_sock(sk); - res = wait_event_interruptible(*sk->sk_sleep, + res = wait_event_interruptible(*sk_sleep(sk), (!tport->congested || !tport->connected)); lock_sock(sk); if (res) @@ -931,7 +931,7 @@ restart: goto exit; } release_sock(sk); - res = wait_event_interruptible(*sk->sk_sleep, + res = wait_event_interruptible(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state == SS_DISCONNECTING))); lock_sock(sk); @@ -1064,7 +1064,7 @@ restart: goto exit; } release_sock(sk); - res = wait_event_interruptible(*sk->sk_sleep, + res = wait_event_interruptible(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state == SS_DISCONNECTING))); lock_sock(sk); @@ -1271,8 +1271,8 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf) tipc_disconnect_port(tipc_sk_port(sk)); } - if (waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); return TIPC_OK; } @@ -1343,8 +1343,8 @@ static void wakeupdispatch(struct tipc_port *tport) { struct sock *sk = (struct sock *)tport->usr_handle; - if (waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); } /** @@ -1426,7 +1426,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen, /* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */ release_sock(sk); - res = wait_event_interruptible_timeout(*sk->sk_sleep, + res = wait_event_interruptible_timeout(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue) || (sock->state != SS_CONNECTING)), sk->sk_rcvtimeo); @@ -1521,7 +1521,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags) goto exit; } release_sock(sk); - res = wait_event_interruptible(*sk->sk_sleep, + res = wait_event_interruptible(*sk_sleep(sk), (!skb_queue_empty(&sk->sk_receive_queue))); lock_sock(sk); if (res) @@ -1632,8 +1632,8 @@ restart: /* Discard any unreceived messages; wake up sleeping tasks */ discard_rx_queue(sk); - if (waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + if (waitqueue_active(sk_sleep(sk))) + wake_up_interruptible(sk_sleep(sk)); res = 0; break; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3d9122e78f4..87c0360eaa2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,7 +316,7 @@ static void unix_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (unix_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } read_unlock(&sk->sk_callback_lock); @@ -1736,7 +1736,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo) unix_state_lock(sk); for (;;) { - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (!skb_queue_empty(&sk->sk_receive_queue) || sk->sk_err || @@ -1752,7 +1752,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo) clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags); } - finish_wait(sk->sk_sleep, &wait); + finish_wait(sk_sleep(sk), &wait); unix_state_unlock(sk); return timeo; } @@ -1991,7 +1991,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table struct sock *sk = sock->sk; unsigned int mask; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* exceptional events? */ @@ -2028,7 +2028,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk, *other; unsigned int mask, writable; - sock_poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; /* exceptional events? */ diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index cbddd0cb83f..6cffbc4da02 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -718,7 +718,7 @@ static int x25_wait_for_connection_establishment(struct sock *sk) DECLARE_WAITQUEUE(wait, current); int rc; - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); for (;;) { __set_current_state(TASK_INTERRUPTIBLE); rc = -ERESTARTSYS; @@ -738,7 +738,7 @@ static int x25_wait_for_connection_establishment(struct sock *sk) break; } __set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); return rc; } @@ -838,7 +838,7 @@ static int x25_wait_for_data(struct sock *sk, long timeout) DECLARE_WAITQUEUE(wait, current); int rc = 0; - add_wait_queue_exclusive(sk->sk_sleep, &wait); + add_wait_queue_exclusive(sk_sleep(sk), &wait); for (;;) { __set_current_state(TASK_INTERRUPTIBLE); if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -858,7 +858,7 @@ static int x25_wait_for_data(struct sock *sk, long timeout) break; } __set_current_state(TASK_RUNNING); - remove_wait_queue(sk->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk), &wait); return rc; } -- cgit v1.2.3-70-g09d2 From 672724403b42da1d276c6cf811e8e34d15efd964 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 21 Apr 2010 10:25:36 +0200 Subject: radiotap parser: fix endian annotation When I updated this from the corresponding userspace library, an annotation error crept in -- this variable needs to be annotated as little endian. No effect on code generation. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/cfg80211.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 37cebd3aa0f..5a4efe54cff 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1643,7 +1643,7 @@ struct ieee80211_radiotap_iterator { const struct ieee80211_radiotap_namespace *current_namespace; unsigned char *_arg, *_next_ns_data; - uint32_t *_next_bitmap; + __le32 *_next_bitmap; unsigned char *this_arg; int this_arg_index; -- cgit v1.2.3-70-g09d2 From aa2ea0586d9dbe56a334d835a43b45e8c2104e77 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Thu, 22 Apr 2010 07:00:24 +0000 Subject: tcp: fix outsegs stat for TSO segments Account for TSO segments of an skb in TCP_MIB_OUTSEGS counter. Without doing this, the counter can be off by orders of magnitude from the actual number of segments sent. Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/net/snmp.h | 2 ++ include/net/tcp.h | 1 + net/ipv4/tcp_output.c | 5 +++-- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/snmp.h b/include/net/snmp.h index 884fdbb74b2..92456f1035f 100644 --- a/include/net/snmp.h +++ b/include/net/snmp.h @@ -133,6 +133,8 @@ struct linux_xfrm_mib { __this_cpu_add(mib[0]->mibs[field], addend) #define SNMP_ADD_STATS_USER(mib, field, addend) \ this_cpu_add(mib[1]->mibs[field], addend) +#define SNMP_ADD_STATS(mib, field, addend) \ + this_cpu_add(mib[0]->mibs[field], addend) /* * Use "__typeof__(*mib[0]) *ptr" instead of "__typeof__(mib[0]) ptr" * to make @ptr a non-percpu pointer. diff --git a/include/net/tcp.h b/include/net/tcp.h index b7d83d204a9..3f87fd87bc9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -294,6 +294,7 @@ extern struct proto tcp_prot; #define TCP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field) #define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field) #define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val) +#define TCP_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.tcp_statistics, field, val) extern void tcp_v4_err(struct sk_buff *skb, u32); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 429ad9286ef..5db3a2c6cb3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -888,7 +888,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, tcp_event_data_sent(tp, skb, sk); if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) - TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, + tcp_skb_pcount(skb)); err = icsk->icsk_af_ops->queue_xmit(skb); if (likely(err <= 0)) @@ -2503,7 +2504,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, th->window = htons(min(req->rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); - TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); + TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ -- cgit v1.2.3-70-g09d2 From f68c224fedff2157f3fad7f7da674cbc96567c84 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 22 Apr 2010 16:06:59 -0700 Subject: dst: rcu check refinement __sk_dst_get() might be called from softirq, with socket lock held. [ 159.026180] include/net/sock.h:1200 invoked rcu_dereference_check() without protection! [ 159.026261] [ 159.026261] other info that might help us debug this: [ 159.026263] [ 159.026425] [ 159.026426] rcu_scheduler_active = 1, debug_locks = 0 [ 159.026552] 2 locks held by swapper/0: [ 159.026609] #0: (&icsk->icsk_retransmit_timer){+.-...}, at: [] run_timer_softirq+0x105/0x350 [ 159.026839] #1: (slock-AF_INET){+.-...}, at: [] tcp_write_timer+0x2f/0x1e0 [ 159.027063] [ 159.027064] stack backtrace: [ 159.027172] Pid: 0, comm: swapper Not tainted 2.6.34-rc5-03707-gde498c8-dirty #36 [ 159.027252] Call Trace: [ 159.027306] [] lockdep_rcu_dereference +0xaf/0xc0 [ 159.027411] [] tcp_current_mss+0xa7/0xb0 [ 159.027537] [] tcp_write_wakeup+0x89/0x190 [ 159.027600] [] tcp_send_probe0+0x16/0x100 [ 159.027726] [] tcp_write_timer+0x179/0x1e0 [ 159.027790] [] run_timer_softirq+0x191/0x350 [ 159.027980] [] __do_softirq+0xcd/0x200 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 8ab05146a44..86a8ca177a2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1197,7 +1197,8 @@ static inline struct dst_entry * __sk_dst_get(struct sock *sk) { return rcu_dereference_check(sk->sk_dst_cache, rcu_read_lock_held() || - sock_owned_by_user(sk)); + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); } static inline struct dst_entry * -- cgit v1.2.3-70-g09d2 From 5ebfbc06aae941484326c9e7e9c4d85330f63591 Mon Sep 17 00:00:00 2001 From: Andrew Hendry Date: Thu, 22 Apr 2010 16:12:36 -0700 Subject: X25: Add if_x25.h and x25 to device identifiers V2 Feedback from John Hughes. - Add header for userspace implementations such as xot/xoe to use - Use explicit values for interface stability - No changes to driver patches V1 - Use identifiers instead of magic numbers for X25 layer 3 to device interface. - Also fixed checkpatch notes on updated code. [ Add new user header to include/linux/Kbuild -DaveM ] Signed-off-by: Andrew Hendry Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/if_x25.h | 26 ++++++++++++++++++++++++++ include/net/x25device.h | 1 + net/x25/x25_dev.c | 36 ++++++++++++++++++++---------------- 4 files changed, 48 insertions(+), 16 deletions(-) create mode 100644 include/linux/if_x25.h (limited to 'include/net') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index e2ea0b2159c..2fc8e14cc24 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -94,6 +94,7 @@ header-y += if_ppp.h header-y += if_slip.h header-y += if_strip.h header-y += if_tun.h +header-y += if_x25.h header-y += in_route.h header-y += ioctl.h header-y += ip6_tunnel.h diff --git a/include/linux/if_x25.h b/include/linux/if_x25.h new file mode 100644 index 00000000000..897765f5feb --- /dev/null +++ b/include/linux/if_x25.h @@ -0,0 +1,26 @@ +/* + * Linux X.25 packet to device interface + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef _IF_X25_H +#define _IF_X25_H + +#include + +/* Documentation/networking/x25-iface.txt */ +#define X25_IFACE_DATA 0x00 +#define X25_IFACE_CONNECT 0x01 +#define X25_IFACE_DISCONNECT 0x02 +#define X25_IFACE_PARAMS 0x03 + +#endif /* _IF_X25_H */ diff --git a/include/net/x25device.h b/include/net/x25device.h index 1415bcf9398..1fa08b49f1c 100644 --- a/include/net/x25device.h +++ b/include/net/x25device.h @@ -3,6 +3,7 @@ #include #include +#include #include static inline __be16 x25_type_trans(struct sk_buff *skb, struct net_device *dev) diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index b9ef682230a..9005f6daeab 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -24,6 +24,7 @@ #include #include #include +#include static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) { @@ -115,19 +116,22 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, } switch (skb->data[0]) { - case 0x00: - skb_pull(skb, 1); - if (x25_receive_data(skb, nb)) { - x25_neigh_put(nb); - goto out; - } - break; - case 0x01: - x25_link_established(nb); - break; - case 0x02: - x25_link_terminated(nb); - break; + + case X25_IFACE_DATA: + skb_pull(skb, 1); + if (x25_receive_data(skb, nb)) { + x25_neigh_put(nb); + goto out; + } + break; + + case X25_IFACE_CONNECT: + x25_link_established(nb); + break; + + case X25_IFACE_DISCONNECT: + x25_link_terminated(nb); + break; } x25_neigh_put(nb); drop: @@ -148,7 +152,7 @@ void x25_establish_link(struct x25_neigh *nb) return; } ptr = skb_put(skb, 1); - *ptr = 0x01; + *ptr = X25_IFACE_CONNECT; break; #if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE) @@ -184,7 +188,7 @@ void x25_terminate_link(struct x25_neigh *nb) } ptr = skb_put(skb, 1); - *ptr = 0x02; + *ptr = X25_IFACE_DISCONNECT; skb->protocol = htons(ETH_P_X25); skb->dev = nb->dev; @@ -200,7 +204,7 @@ void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb) switch (nb->dev->type) { case ARPHRD_X25: dptr = skb_push(skb, 1); - *dptr = 0x00; + *dptr = X25_IFACE_DATA; break; #if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE) -- cgit v1.2.3-70-g09d2 From 6e7cb8370760ec17e10098399822292def8d84f3 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Sun, 18 Apr 2010 12:42:05 +0900 Subject: ipv6 mcast: Introduce include/net/mld.h for MLD definitions. Signed-off-by: YOSHIFUJI Hideaki --- include/net/mld.h | 75 ++++++++++++++++++++++++++++++ net/ipv6/mcast.c | 135 ++++++++++++++++-------------------------------------- 2 files changed, 115 insertions(+), 95 deletions(-) create mode 100644 include/net/mld.h (limited to 'include/net') diff --git a/include/net/mld.h b/include/net/mld.h new file mode 100644 index 00000000000..467143cd4e2 --- /dev/null +++ b/include/net/mld.h @@ -0,0 +1,75 @@ +#ifndef LINUX_MLD_H +#define LINUX_MLD_H + +#include +#include + +/* MLDv1 Query/Report/Done */ +struct mld_msg { + struct icmp6hdr mld_hdr; + struct in6_addr mld_mca; +}; + +#define mld_type mld_hdr.icmp6_type +#define mld_code mld_hdr.icmp6_code +#define mld_cksum mld_hdr.icmp6_cksum +#define mld_maxdelay mld_hdr.icmp6_maxdelay +#define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] + +/* Multicast Listener Discovery version 2 headers */ +/* MLDv2 Report */ +struct mld2_grec { + __u8 grec_type; + __u8 grec_auxwords; + __be16 grec_nsrcs; + struct in6_addr grec_mca; + struct in6_addr grec_src[0]; +}; + +struct mld2_report { + struct icmp6hdr mld2r_hdr; + struct mld2_grec mld2r_grec[0]; +}; + +#define mld2r_type mld2r_hdr.icmp6_type +#define mld2r_resv1 mld2r_hdr.icmp6_code +#define mld2r_cksum mld2r_hdr.icmp6_cksum +#define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] +#define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] + +/* MLDv2 Query */ +struct mld2_query { + struct icmp6hdr mld2q_hdr; + struct in6_addr mld2q_mca; +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 mld2q_qrv:3, + mld2q_suppress:1, + mld2q_resv2:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 mld2q_resv2:4, + mld2q_suppress:1, + mld2q_qrv:3; +#else +#error "Please fix " +#endif + __u8 mld2q_qqic; + __be16 mld2q_nsrcs; + struct in6_addr mld2q_srcs[0]; +}; + +#define mld2q_type mld2q_hdr.icmp6_type +#define mld2q_code mld2q_hdr.icmp6_code +#define mld2q_cksum mld2q_hdr.icmp6_cksum +#define mld2q_mrc mld2q_hdr.icmp6_maxdelay +#define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] + +/* Max Response Code */ +#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) +#define MLDV2_EXP(thresh, nbmant, nbexp, value) \ + ((value) < (thresh) ? (value) : \ + ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \ + (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp)))) + +#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value) + +#endif diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 62ed08213d9..006aee683a0 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include @@ -71,54 +72,11 @@ #define MDBG(x) #endif -/* - * These header formats should be in a separate include file, but icmpv6.h - * doesn't have in6_addr defined in all cases, there is no __u128, and no - * other files reference these. - * - * +-DLS 4/14/03 - */ - -/* Multicast Listener Discovery version 2 headers */ - -struct mld2_grec { - __u8 grec_type; - __u8 grec_auxwords; - __be16 grec_nsrcs; - struct in6_addr grec_mca; - struct in6_addr grec_src[0]; -}; - -struct mld2_report { - __u8 type; - __u8 resv1; - __sum16 csum; - __be16 resv2; - __be16 ngrec; - struct mld2_grec grec[0]; -}; - -struct mld2_query { - __u8 type; - __u8 code; - __sum16 csum; - __be16 mrc; - __be16 resv1; - struct in6_addr mca; -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 qrv:3, - suppress:1, - resv2:4; -#elif defined(__BIG_ENDIAN_BITFIELD) - __u8 resv2:4, - suppress:1, - qrv:3; -#else -#error "Please fix " -#endif - __u8 qqic; - __be16 nsrcs; - struct in6_addr srcs[0]; +/* Ensure that we have struct in6_addr aligned on 32bit word. */ +static void *__mld2_query_bugs[] __attribute__((__unused__)) = { + BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4), + BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4) }; static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT; @@ -157,14 +115,6 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, ((idev)->mc_v1_seen && \ time_before(jiffies, (idev)->mc_v1_seen))) -#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value)) -#define MLDV2_EXP(thresh, nbmant, nbexp, value) \ - ((value) < (thresh) ? (value) : \ - ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \ - (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp)))) - -#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value) - #define IPV6_MLD_MAX_MSF 64 int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF; @@ -1161,7 +1111,7 @@ int igmp6_event_query(struct sk_buff *skb) struct in6_addr *group; unsigned long max_delay; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int group_type; int mark = 0; int len; @@ -1182,8 +1132,8 @@ int igmp6_event_query(struct sk_buff *skb) if (idev == NULL) return 0; - hdr = icmp6_hdr(skb); - group = (struct in6_addr *) (hdr + 1); + mld = (struct mld_msg *)icmp6_hdr(skb); + group = &mld->mld_mca; group_type = ipv6_addr_type(group); if (group_type != IPV6_ADDR_ANY && @@ -1197,7 +1147,7 @@ int igmp6_event_query(struct sk_buff *skb) /* MLDv1 router present */ /* Translate milliseconds to jiffies */ - max_delay = (ntohs(hdr->icmp6_maxdelay)*HZ)/1000; + max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000; switchback = (idev->mc_qrv + 1) * max_delay; idev->mc_v1_seen = jiffies + switchback; @@ -1216,14 +1166,14 @@ int igmp6_event_query(struct sk_buff *skb) return -EINVAL; } mlh2 = (struct mld2_query *)skb_transport_header(skb); - max_delay = (MLDV2_MRC(ntohs(mlh2->mrc))*HZ)/1000; + max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000; if (!max_delay) max_delay = 1; idev->mc_maxdelay = max_delay; - if (mlh2->qrv) - idev->mc_qrv = mlh2->qrv; + if (mlh2->mld2q_qrv) + idev->mc_qrv = mlh2->mld2q_qrv; if (group_type == IPV6_ADDR_ANY) { /* general query */ - if (mlh2->nsrcs) { + if (mlh2->mld2q_nsrcs) { in6_dev_put(idev); return -EINVAL; /* no sources allowed */ } @@ -1232,9 +1182,9 @@ int igmp6_event_query(struct sk_buff *skb) return 0; } /* mark sources to include, if group & source-specific */ - if (mlh2->nsrcs != 0) { + if (mlh2->mld2q_nsrcs != 0) { if (!pskb_may_pull(skb, srcs_offset + - ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) { + ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) { in6_dev_put(idev); return -EINVAL; } @@ -1270,7 +1220,7 @@ int igmp6_event_query(struct sk_buff *skb) ma->mca_flags &= ~MAF_GSQUERY; } if (!(ma->mca_flags & MAF_GSQUERY) || - mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs)) + mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs)) igmp6_group_queried(ma, max_delay); spin_unlock_bh(&ma->mca_lock); break; @@ -1286,9 +1236,8 @@ int igmp6_event_query(struct sk_buff *skb) int igmp6_event_report(struct sk_buff *skb) { struct ifmcaddr6 *ma; - struct in6_addr *addrp; struct inet6_dev *idev; - struct icmp6hdr *hdr; + struct mld_msg *mld; int addr_type; /* Our own report looped back. Ignore it. */ @@ -1300,10 +1249,10 @@ int igmp6_event_report(struct sk_buff *skb) skb->pkt_type != PACKET_BROADCAST) return 0; - if (!pskb_may_pull(skb, sizeof(struct in6_addr))) + if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr))) return -EINVAL; - hdr = icmp6_hdr(skb); + mld = (struct mld_msg *)icmp6_hdr(skb); /* Drop reports with not link local source */ addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr); @@ -1311,8 +1260,6 @@ int igmp6_event_report(struct sk_buff *skb) !(addr_type&IPV6_ADDR_LINKLOCAL)) return -EINVAL; - addrp = (struct in6_addr *) (hdr + 1); - idev = in6_dev_get(skb->dev); if (idev == NULL) return -ENODEV; @@ -1323,7 +1270,7 @@ int igmp6_event_report(struct sk_buff *skb) read_lock_bh(&idev->lock); for (ma = idev->mc_list; ma; ma=ma->next) { - if (ipv6_addr_equal(&ma->mca_addr, addrp)) { + if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) { spin_lock(&ma->mca_lock); if (del_timer(&ma->mca_timer)) atomic_dec(&ma->mca_refcnt); @@ -1432,11 +1379,11 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); skb_put(skb, sizeof(*pmr)); pmr = (struct mld2_report *)skb_transport_header(skb); - pmr->type = ICMPV6_MLD2_REPORT; - pmr->resv1 = 0; - pmr->csum = 0; - pmr->resv2 = 0; - pmr->ngrec = 0; + pmr->mld2r_type = ICMPV6_MLD2_REPORT; + pmr->mld2r_resv1 = 0; + pmr->mld2r_cksum = 0; + pmr->mld2r_resv2 = 0; + pmr->mld2r_ngrec = 0; return skb; } @@ -1458,9 +1405,10 @@ static void mld_sendpack(struct sk_buff *skb) mldlen = skb->tail - skb->transport_header; pip6->payload_len = htons(payload_len); - pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, - IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb), - mldlen, 0)); + pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen, + IPPROTO_ICMPV6, + csum_partial(skb_transport_header(skb), + mldlen, 0)); dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr); @@ -1521,7 +1469,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc, pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->mca_addr; /* structure copy */ pmr = (struct mld2_report *)skb_transport_header(skb); - pmr->ngrec = htons(ntohs(pmr->ngrec)+1); + pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1); *ppgr = pgr; return skb; } @@ -1557,7 +1505,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { - if (pmr && pmr->ngrec && + if (pmr && pmr->mld2r_ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) mld_sendpack(skb); @@ -1770,9 +1718,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) struct sock *sk = net->ipv6.igmp_sk; struct inet6_dev *idev; struct sk_buff *skb; - struct icmp6hdr *hdr; + struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; - struct in6_addr *addrp; struct in6_addr addr_buf; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, @@ -1820,16 +1767,14 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra)); - hdr = (struct icmp6hdr *) skb_put(skb, sizeof(struct icmp6hdr)); - memset(hdr, 0, sizeof(struct icmp6hdr)); - hdr->icmp6_type = type; + hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); + memset(hdr, 0, sizeof(struct mld_msg)); + hdr->mld_type = type; + ipv6_addr_copy(&hdr->mld_mca, addr); - addrp = (struct in6_addr *) skb_put(skb, sizeof(struct in6_addr)); - ipv6_addr_copy(addrp, addr); - - hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len, - IPPROTO_ICMPV6, - csum_partial(hdr, len, 0)); + hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, + IPPROTO_ICMPV6, + csum_partial(hdr, len, 0)); idev = in6_dev_get(skb->dev); -- cgit v1.2.3-70-g09d2 From 13b52cd44670e3359055e9918d0e766d89836425 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Fri, 23 Apr 2010 11:26:08 +0000 Subject: IPv6: Add dontfrag argument to relevant functions Add dontfrag argument to relevant functions for IPV6_DONTFRAG support, as well as allowing the value to be passed-in via ancillary cmsg data. Signed-off-by: Brian Haley Signed-off-by: David S. Miller --- include/net/ipv6.h | 3 ++- include/net/transp_v6.h | 3 ++- net/ipv6/datagram.c | 21 ++++++++++++++++++++- net/ipv6/icmp.c | 5 +++-- net/ipv6/ip6_flowlabel.c | 3 ++- net/ipv6/ip6_output.c | 2 +- net/ipv6/ipv6_sockglue.c | 3 ++- net/ipv6/raw.c | 9 +++++++-- net/ipv6/udp.c | 9 +++++++-- 9 files changed, 46 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b1d8db90b21..7ab6323e631 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -503,7 +503,8 @@ extern int ip6_append_data(struct sock *sk, struct ipv6_txoptions *opt, struct flowi *fl, struct rt6_info *rt, - unsigned int flags); + unsigned int flags, + int dontfrag); extern int ip6_push_pending_frames(struct sock *sk); diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h index d65381cad0f..42a0eb68b7b 100644 --- a/include/net/transp_v6.h +++ b/include/net/transp_v6.h @@ -44,7 +44,8 @@ extern int datagram_send_ctl(struct net *net, struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, - int *hlimit, int *tclass); + int *hlimit, int *tclass, + int *dontfrag); #define LOOPBACK4_IPV6 cpu_to_be32(0x7f000006) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 622dc7939a1..f5076d349b1 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -497,7 +497,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) int datagram_send_ctl(struct net *net, struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, - int *hlimit, int *tclass) + int *hlimit, int *tclass, int *dontfrag) { struct in6_pktinfo *src_info; struct cmsghdr *cmsg; @@ -735,6 +735,25 @@ int datagram_send_ctl(struct net *net, err = 0; *tclass = tc; + break; + } + + case IPV6_DONTFRAG: + { + int df; + + err = -EINVAL; + if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) { + goto exit_f; + } + + df = *(int *)CMSG_DATA(cmsg); + if (df < 0 || df > 1) + goto exit_f; + + err = 0; + *dontfrag = df; + break; } default: diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 12d2fa42657..ce799298255 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -481,7 +481,7 @@ route_done: len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, (struct rt6_info*)dst, - MSG_DONTWAIT); + MSG_DONTWAIT, np->dontfrag); if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); ip6_flush_pending_frames(sk); @@ -561,7 +561,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb) err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl, - (struct rt6_info*)dst, MSG_DONTWAIT); + (struct rt6_info*)dst, MSG_DONTWAIT, + np->dontfrag); if (err) { ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 14e23216eb2..13654686aea 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -360,7 +360,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, + &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 263d4cf5a8d..54d43dd1f08 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1105,7 +1105,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl, - struct rt6_info *rt, unsigned int flags) + struct rt6_info *rt, unsigned int flags, int dontfrag) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 2bf9eda7278..bd43f0152c2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -458,7 +458,8 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk, + &junk); if (retv) goto done; update: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8763b1a0814..44a84ea9b3e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -733,6 +733,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, int addr_len = msg->msg_namelen; int hlimit = -1; int tclass = -1; + int dontfrag = -1; u16 proto; int err; @@ -811,7 +812,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -880,6 +882,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (tclass < 0) tclass = np->tclass; + if (dontfrag < 0) + dontfrag = np->dontfrag; + if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; @@ -890,7 +895,7 @@ back_from_confirm: lock_sock(sk); err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst, - msg->msg_flags); + msg->msg_flags, dontfrag); if (err) ip6_flush_pending_frames(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 92bf9033e24..39e3665d946 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -919,6 +919,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, int ulen = len; int hlimit = -1; int tclass = -1; + int dontfrag = -1; int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int err; int connected = 0; @@ -1049,7 +1050,8 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, + &tclass, &dontfrag); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1120,6 +1122,9 @@ do_udp_sendmsg: if (tclass < 0) tclass = np->tclass; + if (dontfrag < 0) + dontfrag = np->dontfrag; + if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: @@ -1143,7 +1148,7 @@ do_append_data: err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl, (struct rt6_info*)dst, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); if (err) udp_v6_flush_pending_frames(sk); else if (!corkreq) -- cgit v1.2.3-70-g09d2 From 4b340ae20d0e2366792abe70f46629e576adaf5e Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Fri, 23 Apr 2010 11:26:09 +0000 Subject: IPv6: Complete IPV6_DONTFRAG support Finally add support to detect a local IPV6_DONTFRAG event and return the relevant data to the user if they've enabled IPV6_RECVPATHMTU on the socket. The next recvmsg() will return no data, but have an IPV6_PATHMTU as ancillary data. Signed-off-by: Brian Haley Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/net/ipv6.h | 2 ++ net/ipv6/af_inet6.c | 3 ++ net/ipv6/datagram.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/ip6_output.c | 24 +++++++++----- net/ipv6/raw.c | 3 ++ net/ipv6/udp.c | 3 ++ 7 files changed, 116 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 1976942cf6f..2ab5509f6d4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -257,6 +257,7 @@ struct inet6_skb_parm { }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) +#define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb)) static inline int inet6_iif(const struct sk_buff *skb) { @@ -366,6 +367,7 @@ struct ipv6_pinfo { struct ipv6_txoptions *opt; struct sk_buff *pktoptions; + struct sk_buff *rxpmtu; struct { struct ipv6_txoptions *opt; u8 hop_limit; diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 7ab6323e631..eba5cc00325 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -578,9 +578,11 @@ extern int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len); +extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len); extern void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); extern void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info); +extern void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu); extern int inet6_release(struct socket *sock); extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3192aa02ba5..d2df3144429 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -417,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk) if ((skb = xchg(&np->pktoptions, NULL)) != NULL) kfree_skb(skb); + if ((skb = xchg(&np->rxpmtu, NULL)) != NULL) + kfree_skb(skb); + /* Free flowlabels */ fl6_free_socklist(sk); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index f5076d349b1..5959230bc6c 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -278,6 +278,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info) kfree_skb(skb); } +void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6hdr *iph; + struct sk_buff *skb; + struct ip6_mtuinfo *mtu_info; + + if (!np->rxopt.bits.rxpmtu) + return; + + skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); + if (!skb) + return; + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + iph = ipv6_hdr(skb); + ipv6_addr_copy(&iph->daddr, &fl->fl6_dst); + + mtu_info = IP6CBMTU(skb); + if (!mtu_info) { + kfree_skb(skb); + return; + } + + mtu_info->ip6m_mtu = mtu; + mtu_info->ip6m_addr.sin6_family = AF_INET6; + mtu_info->ip6m_addr.sin6_port = 0; + mtu_info->ip6m_addr.sin6_flowinfo = 0; + mtu_info->ip6m_addr.sin6_scope_id = fl->oif; + ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr); + + __skb_pull(skb, skb_tail_pointer(skb) - skb->data); + skb_reset_transport_header(skb); + + skb = xchg(&np->rxpmtu, skb); + kfree_skb(skb); +} + /* * Handle MSG_ERRQUEUE */ @@ -381,6 +420,54 @@ out: return err; } +/* + * Handle IPV6_RECVPATHMTU + */ +int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *skb; + struct sockaddr_in6 *sin; + struct ip6_mtuinfo mtu_info; + int err; + int copied; + + err = -EAGAIN; + skb = xchg(&np->rxpmtu, NULL); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info)); + + sin = (struct sockaddr_in6 *)msg->msg_name; + if (sin) { + sin->sin6_family = AF_INET6; + sin->sin6_flowinfo = 0; + sin->sin6_port = 0; + sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; + ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr); + } + + put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); + + err = copied; + +out_free_skb: + kfree_skb(skb); +out: + return err; +} int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 54d43dd1f08..61e2bef5609 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1219,15 +1219,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, */ inet->cork.length += length; - if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) && - (rt->u.dst.dev->features & NETIF_F_UFO)) { + if (length > mtu) { + int proto = sk->sk_protocol; + if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){ + ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen); + return -EMSGSIZE; + } - err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, - fragheaderlen, transhdrlen, mtu, - flags); - if (err) - goto error; - return 0; + if (proto == IPPROTO_UDP && + (rt->u.dst.dev->features & NETIF_F_UFO)) { + + err = ip6_ufo_append_data(sk, getfrag, from, length, + hh_len, fragheaderlen, + transhdrlen, mtu, flags); + if (err) + goto error; + return 0; + } } if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 44a84ea9b3e..85627386cb0 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -461,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len); + skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 39e3665d946..2850e35cee3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -335,6 +335,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len); + if (np->rxpmtu && np->rxopt.bits.rxpmtu) + return ipv6_recv_rxpmtu(sk, msg, len); + try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), &peeked, &err); -- cgit v1.2.3-70-g09d2 From 3d0c9c4eb2dbdcc461be4084abd87a9a9e70f713 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 26 Apr 2010 16:02:04 +0200 Subject: net: fib_rules: mark arguments to fib_rules_register const and __net_initdata fib_rules_register() duplicates the template passed to it without modification, mark the argument as const. Additionally the templates are only needed when instantiating a new namespace, so mark them as __net_initdata, which means they can be discarded when CONFIG_NET_NS=n. Signed-off-by: Patrick McHardy --- include/net/fib_rules.h | 2 +- net/core/fib_rules.c | 2 +- net/decnet/dn_rules.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv6/fib6_rules.c | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index 52bd9e6c914..e8923bc20f9 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -104,7 +104,7 @@ static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) return frh->table; } -extern struct fib_rules_ops *fib_rules_register(struct fib_rules_ops *, struct net *); +extern struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *, struct net *); extern void fib_rules_unregister(struct fib_rules_ops *); extern void fib_rules_cleanup_ops(struct fib_rules_ops *); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 1bc66592453..42e84e08a1b 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -122,7 +122,7 @@ errout: } struct fib_rules_ops * -fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) { struct fib_rules_ops *ops; int err; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index af28dcc2184..1226bcad776 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -216,7 +216,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) dn_rt_cache_flush(-1); } -static struct fib_rules_ops dn_fib_rules_ops_template = { +static const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = { .family = FIB_RULES_DECNET, .rule_size = sizeof(struct dn_fib_rule), .addr_size = sizeof(u16), diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 3ec84fea5b7..8ab62a56701 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -245,7 +245,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) rt_cache_flush(ops->fro_net, -1); } -static struct fib_rules_ops fib4_rules_ops_template = { +static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { .family = FIB_RULES_IPV4, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a2df5012a1d..7d3e382aed6 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -216,7 +216,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, return 0; } -static struct fib_rules_ops ipmr_rules_ops_template = { +static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = { .family = FIB_RULES_IPMR, .rule_size = sizeof(struct ipmr_rule), .addr_size = sizeof(u32), diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 8124f16f2ac..35f6949446f 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -237,7 +237,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } -static struct fib_rules_ops fib6_rules_ops_template = { +static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = { .family = FIB_RULES_IPV6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), -- cgit v1.2.3-70-g09d2 From 7ec75c582e639d956ce3afd499f67febe6f902a4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 27 Apr 2010 06:22:01 +0000 Subject: net: suppress RCU lockdep false positive in twsk_net() Calls to twsk_net() are in some cases protected by reference counting as an alternative to RCU protection. Cases covered by reference counts include __inet_twsk_kill(), inet_twsk_free(), inet_twdr_do_twkill_work(), inet_twdr_twcal_tick(), and tcp_timewait_state_process(). RCU is used by inet_twsk_purge(). Locking is used by established_get_first() and established_get_next(). Finally, __inet_twsk_hashdance() is an initialization case. It appears to be non-trivial to locate the appropriate locks and reference counts from within twsk_net(), so used rcu_dereference_raw(). Signed-off-by: Paul E. McKenney Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_timewait_sock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 79f67eae8a7..a066fdd50da 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -224,7 +224,9 @@ static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { #ifdef CONFIG_NET_NS - return rcu_dereference(twsk->tw_net); + return rcu_dereference_raw(twsk->tw_net); /* protected by locking, */ + /* reference counting, */ + /* initialization, or RCU. */ #else return &init_net; #endif -- cgit v1.2.3-70-g09d2 From 6c37e5de456987f5bc80879afde05aa120784095 Mon Sep 17 00:00:00 2001 From: Flavio Leitner Date: Mon, 26 Apr 2010 18:33:27 +0000 Subject: TCP: avoid to send keepalive probes if receiving data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit RFC 1122 says the following: ... Keep-alive packets MUST only be sent when no data or acknowledgement packets have been received for the connection within an interval. ... The acknowledgement packet is reseting the keepalive timer but the data packet isn't. This patch fixes it by checking the timestamp of the last received data packet too when the keepalive timer expires. Signed-off-by: Flavio Leitner Signed-off-by: Eric Dumazet Acked-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 8 ++++++++ net/ipv4/tcp.c | 2 +- net/ipv4/tcp_timer.c | 4 ++-- 3 files changed, 11 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/tcp.h b/include/net/tcp.h index 3f87fd87bc9..fb5c66b2ab8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1033,6 +1033,14 @@ static inline int keepalive_probes(const struct tcp_sock *tp) return tp->keepalive_probes ? : sysctl_tcp_keepalive_probes; } +static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) +{ + const struct inet_connection_sock *icsk = &tp->inet_conn; + + return min_t(u32, tcp_time_stamp - icsk->icsk_ack.lrcvtime, + tcp_time_stamp - tp->rcv_tstamp); +} + static inline int tcp_fin_time(const struct sock *sk) { int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6689c61cab4..8ce29747ad9 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2298,7 +2298,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { - __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp; + u32 elapsed = keepalive_time_elapsed(tp); if (tp->keepalive_time > elapsed) elapsed = tp->keepalive_time - elapsed; else diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c732be00606..440a5c6004f 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -517,7 +517,7 @@ static void tcp_keepalive_timer (unsigned long data) struct sock *sk = (struct sock *) data; struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - __u32 elapsed; + u32 elapsed; /* Only process if socket is not in use. */ bh_lock_sock(sk); @@ -554,7 +554,7 @@ static void tcp_keepalive_timer (unsigned long data) if (tp->packets_out || tcp_send_head(sk)) goto resched; - elapsed = tcp_time_stamp - tp->rcv_tstamp; + elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { if (icsk->icsk_probes_out >= keepalive_probes(tp)) { -- cgit v1.2.3-70-g09d2 From 18f9f1365dad1237072d360bc487d8c7a1cae532 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Apr 2010 02:42:51 +0000 Subject: rps: inet_rps_save_rxhash() argument is not const const qualifier on sock argument is misleading, since we can modify rxhash. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index b487bc1b99a..c1d42957b86 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -248,7 +248,7 @@ static inline void inet_rps_reset_flow(const struct sock *sk) #endif } -static inline void inet_rps_save_rxhash(const struct sock *sk, u32 rxhash) +static inline void inet_rps_save_rxhash(struct sock *sk, u32 rxhash) { #ifdef CONFIG_RPS if (unlikely(inet_sk(sk)->rxhash != rxhash)) { -- cgit v1.2.3-70-g09d2 From 0b53ff2eadb1db6818894435f85989fb05d7e718 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 26 Apr 2010 20:40:43 +0000 Subject: net: fix a lockdep rcu warning in __sk_dst_set() __sk_dst_set() might be called while no state can be integrated in a rcu_dereference_check() condition. So use rcu_dereference_raw() to shutup lockdep warnings (if CONFIG_PROVE_RCU is set) Signed-off-by: Eric Dumazet Acked-by: Paul E. McKenney Signed-off-by: David S. Miller --- include/net/sock.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 86a8ca177a2..4081db86a35 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1236,8 +1236,11 @@ __sk_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old_dst; sk_tx_queue_clear(sk); - old_dst = rcu_dereference_check(sk->sk_dst_cache, - lockdep_is_held(&sk->sk_dst_lock)); + /* + * This can be called while sk is owned by the caller only, + * with no state that can be checked in a rcu_dereference_check() cond + */ + old_dst = rcu_dereference_raw(sk->sk_dst_cache); rcu_assign_pointer(sk->sk_dst_cache, dst); dst_release(old_dst); } -- cgit v1.2.3-70-g09d2 From fd8aaaf3519f3fd3c82594e90bc6808072b94d54 Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Tue, 27 Apr 2010 01:23:35 +0200 Subject: cfg80211: add ap isolation support This is used to configure APs to not bridge traffic between connected stations. Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville --- include/linux/nl80211.h | 5 +++++ include/net/cfg80211.h | 2 ++ net/wireless/nl80211.c | 4 ++++ 3 files changed, 11 insertions(+) (limited to 'include/net') diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index 2ea3edeee7a..f8750f9a65b 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -709,6 +709,9 @@ enum nl80211_commands { * NL80211_CMD_AUTHENTICATE, NL80211_CMD_DEAUTHENTICATE, * NL80211_CMD_DISASSOCIATE. * + * @NL80211_ATTR_AP_ISOLATE: (AP mode) Do not forward traffic between stations + * connected to this BSS. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -864,6 +867,8 @@ enum nl80211_attrs { NL80211_ATTR_LOCAL_STATE_CHANGE, + NL80211_ATTR_AP_ISOLATE, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5a4efe54cff..f6b29bf925d 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -511,6 +511,7 @@ struct mpath_info { * @basic_rates: basic rates in IEEE 802.11 format * (or NULL for no change) * @basic_rates_len: number of basic rates + * @ap_isolate: do not forward packets between connected stations */ struct bss_parameters { int use_cts_prot; @@ -518,6 +519,7 @@ struct bss_parameters { int use_short_slot_time; u8 *basic_rates; u8 basic_rates_len; + int ap_isolate; }; struct mesh_config { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index df5505b3930..c27bef8e0c1 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -151,6 +151,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_PS_STATE] = { .type = NLA_U32 }, [NL80211_ATTR_CQM] = { .type = NLA_NESTED, }, [NL80211_ATTR_LOCAL_STATE_CHANGE] = { .type = NLA_FLAG }, + [NL80211_ATTR_AP_ISOLATE] = { .type = NLA_U8 }, }; /* policy for the attributes */ @@ -2441,6 +2442,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) params.use_cts_prot = -1; params.use_short_preamble = -1; params.use_short_slot_time = -1; + params.ap_isolate = -1; if (info->attrs[NL80211_ATTR_BSS_CTS_PROT]) params.use_cts_prot = @@ -2457,6 +2459,8 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info) params.basic_rates_len = nla_len(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]); } + if (info->attrs[NL80211_ATTR_AP_ISOLATE]) + params.ap_isolate = !!nla_get_u8(info->attrs[NL80211_ATTR_AP_ISOLATE]); rtnl_lock(); -- cgit v1.2.3-70-g09d2 From 195e294d21e88af879da4f88db2ceeb4ec28a755 Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 27 Apr 2010 12:47:40 +0300 Subject: mac80211: Determine dynamic PS timeout based on ps-qos network latency Determine the dynamic PS timeout based on the configured ps-qos network latency. For backwards wext compatibility, allow the dynamic PS timeout configured by the cfg80211 to overrule the automatically determined value. Signed-off-by: Juuso Oikarinen Signed-off-by: John W. Linville --- include/net/mac80211.h | 5 ++++- net/mac80211/cfg.c | 4 ++-- net/mac80211/main.c | 2 ++ net/mac80211/mlme.c | 21 +++++++++++++++++++++ 4 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 7dc5a679039..c26de6cb12f 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -668,6 +668,9 @@ enum ieee80211_smps_mode { * @dynamic_ps_timeout: The dynamic powersave timeout (in ms), see the * powersave documentation below. This variable is valid only when * the CONF_PS flag is set. + * @dynamic_ps_forced_timeout: The dynamic powersave timeout (in ms) configured + * by cfg80211 (essentially, wext) If set, this value overrules the value + * chosen by mac80211 based on ps qos network latency. * * @power_level: requested transmit power (in dBm) * @@ -687,7 +690,7 @@ enum ieee80211_smps_mode { */ struct ieee80211_conf { u32 flags; - int power_level, dynamic_ps_timeout; + int power_level, dynamic_ps_timeout, dynamic_ps_forced_timeout; int max_sleep_period; u16 listen_interval; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index e13fb3a6223..b575a506621 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1404,11 +1404,11 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, return -EOPNOTSUPP; if (enabled == sdata->u.mgd.powersave && - timeout == conf->dynamic_ps_timeout) + timeout == conf->dynamic_ps_forced_timeout) return 0; sdata->u.mgd.powersave = enabled; - conf->dynamic_ps_timeout = timeout; + conf->dynamic_ps_forced_timeout = timeout; /* no change, but if automatic follow powersave */ mutex_lock(&sdata->u.mgd.mtx); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4afe851cf8d..ebcca0eaf1d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -569,6 +569,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.conf.listen_interval = local->hw.max_listen_interval; + local->hw.conf.dynamic_ps_forced_timeout = -1; + result = sta_info_start(local); if (result < 0) goto fail_sta_info; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d811e3fa1d7..2d1a2bef366 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -475,6 +475,7 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) { struct ieee80211_sub_if_data *sdata, *found = NULL; int count = 0; + int timeout; if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) { local->ps_sdata = NULL; @@ -508,6 +509,26 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency) beaconint_us = ieee80211_tu_to_usec( found->vif.bss_conf.beacon_int); + timeout = local->hw.conf.dynamic_ps_forced_timeout; + if (timeout < 0) { + /* + * The 2 second value is there for compatibility until + * the PM_QOS_NETWORK_LATENCY is configured with real + * values. + */ + if (latency == 2000000000) + timeout = 100; + else if (latency <= 50000) + timeout = 300; + else if (latency <= 100000) + timeout = 100; + else if (latency <= 500000) + timeout = 50; + else + timeout = 0; + } + local->hw.conf.dynamic_ps_timeout = timeout; + if (beaconint_us > latency) { local->ps_sdata = NULL; } else { -- cgit v1.2.3-70-g09d2 From 9043f3b89abebfbfe4b8d64c7b71b9ac0b9eaa0b Mon Sep 17 00:00:00 2001 From: Juuso Oikarinen Date: Tue, 27 Apr 2010 12:47:41 +0300 Subject: cfg80211: Remove default dynamic PS timeout value Now that the mac80211 is choosing dynamic ps timeouts based on the ps-qos network latency configuration, configure a default value of -1 as the dynamic ps timeout in cfg80211. This value allows the mac80211 to determine the value to be used. Signed-off-by: Juuso Oikarinen Signed-off-by: John W. Linville --- include/net/cfg80211.h | 2 ++ net/wireless/core.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index f6b29bf925d..7d10c0182f5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1020,6 +1020,8 @@ struct cfg80211_pmksa { * RSN IE. It allows for faster roaming between WPA2 BSSIDs. * @del_pmksa: Delete a cached PMKID. * @flush_pmksa: Flush all cached PMKIDs. + * @set_power_mgmt: Configure WLAN power management. A timeout value of -1 + * allows the driver to adjust the dynamic ps timeout value. * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. * */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 7fdb9409ad2..40cbbbfbccb 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -704,7 +704,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, wdev->ps = true; else wdev->ps = false; - wdev->ps_timeout = 100; + /* allow mac80211 to determine the timeout */ + wdev->ps_timeout = -1; if (rdev->ops->set_power_mgmt) if (rdev->ops->set_power_mgmt(wdev->wiphy, dev, wdev->ps, -- cgit v1.2.3-70-g09d2 From a060bbfe4ee95d115e8f9705a66894ac34e2c475 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 27 Apr 2010 11:59:34 +0200 Subject: mac80211: give virtual interface to hw_scan When scanning, it is somewhat important to scan on the correct virtual interface. All drivers that currently implement hw_scan only support a single virtual interface, but that may change and then we'd want to be ready. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/at76c50x-usb.c | 1 + drivers/net/wireless/iwlwifi/iwl-core.h | 4 +++- drivers/net/wireless/iwlwifi/iwl-scan.c | 3 ++- drivers/net/wireless/mac80211_hwsim.c | 1 + drivers/net/wireless/wl12xx/wl1251_main.c | 1 + drivers/net/wireless/wl12xx/wl1271_main.c | 1 + include/net/mac80211.h | 2 +- net/mac80211/driver-ops.h | 5 +++-- net/mac80211/driver-trace.h | 9 ++++++--- net/mac80211/scan.c | 4 ++-- 10 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/at76c50x-usb.c b/drivers/net/wireless/at76c50x-usb.c index 0fb419936df..7a626d4e100 100644 --- a/drivers/net/wireless/at76c50x-usb.c +++ b/drivers/net/wireless/at76c50x-usb.c @@ -1889,6 +1889,7 @@ static void at76_dwork_hw_scan(struct work_struct *work) } static int at76_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, struct cfg80211_scan_request *req) { struct at76_priv *priv = hw->priv; diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h index a0cc11ecbe9..72736094485 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.h +++ b/drivers/net/wireless/iwlwifi/iwl-core.h @@ -512,7 +512,9 @@ static inline __le32 iwl_hw_set_rate_n_flags(u8 rate, u32 flags) void iwl_init_scan_params(struct iwl_priv *priv); int iwl_scan_cancel(struct iwl_priv *priv); int iwl_scan_cancel_timeout(struct iwl_priv *priv, unsigned long ms); -int iwl_mac_hw_scan(struct ieee80211_hw *hw, struct cfg80211_scan_request *req); +int iwl_mac_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct cfg80211_scan_request *req); void iwl_internal_short_hw_scan(struct iwl_priv *priv); int iwl_force_reset(struct iwl_priv *priv, int mode); u16 iwl_fill_probe_req(struct iwl_priv *priv, struct ieee80211_mgmt *frame, diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c index 1bc1d29f2a0..447c3018296 100644 --- a/drivers/net/wireless/iwlwifi/iwl-scan.c +++ b/drivers/net/wireless/iwlwifi/iwl-scan.c @@ -312,7 +312,8 @@ static int iwl_scan_initiate(struct iwl_priv *priv) } int iwl_mac_hw_scan(struct ieee80211_hw *hw, - struct cfg80211_scan_request *req) + struct ieee80211_vif *vif, + struct cfg80211_scan_request *req) { struct iwl_priv *priv = hw->priv; int ret; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 79bb8833ddb..d016933d757 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -973,6 +973,7 @@ static void hw_scan_done(struct work_struct *work) } static int mac80211_hwsim_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, struct cfg80211_scan_request *req) { struct hw_scan_done *hsd = kzalloc(sizeof(*hsd), GFP_KERNEL); diff --git a/drivers/net/wireless/wl12xx/wl1251_main.c b/drivers/net/wireless/wl12xx/wl1251_main.c index 390cee7e61a..4d3be80c220 100644 --- a/drivers/net/wireless/wl12xx/wl1251_main.c +++ b/drivers/net/wireless/wl12xx/wl1251_main.c @@ -856,6 +856,7 @@ out: } static int wl1251_op_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, struct cfg80211_scan_request *req) { struct wl1251 *wl = hw->priv; diff --git a/drivers/net/wireless/wl12xx/wl1271_main.c b/drivers/net/wireless/wl12xx/wl1271_main.c index 283d5dade1a..08ff6447dcd 100644 --- a/drivers/net/wireless/wl12xx/wl1271_main.c +++ b/drivers/net/wireless/wl12xx/wl1271_main.c @@ -1523,6 +1523,7 @@ out: } static int wl1271_op_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, struct cfg80211_scan_request *req) { struct wl1271 *wl = hw->priv; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index c26de6cb12f..a36e0df5a17 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1657,7 +1657,7 @@ struct ieee80211_ops { struct ieee80211_key_conf *conf, struct ieee80211_sta *sta, u32 iv32, u16 *phase1key); - int (*hw_scan)(struct ieee80211_hw *hw, + int (*hw_scan)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct cfg80211_scan_request *req); void (*sw_scan_start)(struct ieee80211_hw *hw); void (*sw_scan_complete)(struct ieee80211_hw *hw); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index d1f8a7c2225..997008e236f 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -154,14 +154,15 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local, } static inline int drv_hw_scan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req) { int ret; might_sleep(); - ret = local->ops->hw_scan(&local->hw, req); - trace_drv_hw_scan(local, req, ret); + ret = local->ops->hw_scan(&local->hw, &sdata->vif, req); + trace_drv_hw_scan(local, sdata, req, ret); return ret; } diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index e209cb82ff2..ce734b58d07 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -363,23 +363,26 @@ TRACE_EVENT(drv_update_tkip_key, TRACE_EVENT(drv_hw_scan, TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, struct cfg80211_scan_request *req, int ret), - TP_ARGS(local, req, ret), + TP_ARGS(local, sdata, req, ret), TP_STRUCT__entry( LOCAL_ENTRY + VIF_ENTRY __field(int, ret) ), TP_fast_assign( LOCAL_ASSIGN; + VIF_ASSIGN; __entry->ret = ret; ), TP_printk( - LOCAL_PR_FMT " ret:%d", - LOCAL_PR_ARG, __entry->ret + LOCAL_PR_FMT VIF_PR_FMT " ret:%d", + LOCAL_PR_ARG,VIF_PR_ARG, __entry->ret ) ); diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index eb86a5f6e64..2b1f1f3d6a5 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -410,7 +410,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, if (local->ops->hw_scan) { WARN_ON(!ieee80211_prep_hw_scan(local)); - rc = drv_hw_scan(local, local->hw_scan_req); + rc = drv_hw_scan(local, sdata, local->hw_scan_req); } else rc = ieee80211_start_sw_scan(local); @@ -654,7 +654,7 @@ void ieee80211_scan_work(struct work_struct *work) } if (local->hw_scan_req) { - int rc = drv_hw_scan(local, local->hw_scan_req); + int rc = drv_hw_scan(local, sdata, local->hw_scan_req); mutex_unlock(&local->scan_mtx); if (rc) ieee80211_scan_completed(&local->hw, true); -- cgit v1.2.3-70-g09d2 From c58dc01babfd58ec9e71a6ce080150dc27755d88 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 27 Apr 2010 15:05:31 -0700 Subject: net: Make RFS socket operations not be inet specific. Idea from Eric Dumazet. As for placement inside of struct sock, I tried to choose a place that otherwise has a 32-bit hole on 64-bit systems. Signed-off-by: David S. Miller Acked-by: Eric Dumazet --- include/net/inet_sock.h | 37 ------------------------------------- include/net/sock.h | 38 ++++++++++++++++++++++++++++++++++++++ net/ipv4/af_inet.c | 8 ++++---- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 4 ++-- 5 files changed, 45 insertions(+), 44 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c1d42957b86..1653de515ce 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -102,7 +102,6 @@ struct rtable; * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts - * @rxhash - flow hash received from netif layer * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? @@ -126,9 +125,6 @@ struct inet_sock { __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; -#ifdef CONFIG_RPS - __u32 rxhash; -#endif struct ip_options *opt; __u8 tos; @@ -224,37 +220,4 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk) return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; } -static inline void inet_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); - rcu_read_unlock(); -#endif -} - -static inline void inet_rps_reset_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash); - rcu_read_unlock(); -#endif -} - -static inline void inet_rps_save_rxhash(struct sock *sk, u32 rxhash) -{ -#ifdef CONFIG_RPS - if (unlikely(inet_sk(sk)->rxhash != rxhash)) { - inet_rps_reset_flow(sk); - inet_sk(sk)->rxhash = rxhash; - } -#endif -} #endif /* _INET_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 4081db86a35..07822280d95 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -198,6 +198,7 @@ struct sock_common { * @sk_rcvlowat: %SO_RCVLOWAT setting * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting + * @sk_rxhash: flow hash received from netif layer * @sk_filter: socket filtering instructions * @sk_protinfo: private area, net family specific, when not using slab * @sk_timer: sock cleanup timer @@ -279,6 +280,9 @@ struct sock { int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; +#ifdef CONFIG_RPS + __u32 sk_rxhash; +#endif unsigned long sk_flags; unsigned long sk_lingertime; struct sk_buff_head sk_error_queue; @@ -620,6 +624,40 @@ static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) return sk->sk_backlog_rcv(sk, skb); } +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_record_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_reset_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + rcu_read_lock(); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + rps_reset_sock_flow(sock_flow_table, sk->sk_rxhash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_save_rxhash(struct sock *sk, u32 rxhash) +{ +#ifdef CONFIG_RPS + if (unlikely(sk->sk_rxhash != rxhash)) { + sock_rps_reset_flow(sk); + sk->sk_rxhash = rxhash; + } +#endif +} + #define sk_wait_event(__sk, __timeo, __condition) \ ({ int __rc; \ release_sock(__sk); \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9f52880fae1..c6c43bcd1c6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -419,7 +419,7 @@ int inet_release(struct socket *sock) if (sk) { long timeout; - inet_rps_reset_flow(sk); + sock_rps_reset_flow(sk); /* Applications forget to leave groups before exiting */ ip_mc_drop_socket(sk); @@ -722,7 +722,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) @@ -737,7 +737,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, { struct sock *sk = sock->sk; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); /* We may need to bind the socket. */ if (!inet_sk(sk)->inet_num && inet_autobind(sk)) @@ -755,7 +755,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, int addr_len = 0; int err; - inet_rps_record_flow(sk); + sock_rps_record_flow(sk); err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT, flags & ~MSG_DONTWAIT, &addr_len); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 4d6717d1e61..771f8146a2e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1672,7 +1672,7 @@ process: skb->dev = NULL; - inet_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb->rxhash); bh_lock_sock_nested(sk); ret = 0; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1e18f9cc924..fa3d2874db4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1217,7 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags) sk->sk_state = TCP_CLOSE; inet->inet_daddr = 0; inet->inet_dport = 0; - inet_rps_save_rxhash(sk, 0); + sock_rps_save_rxhash(sk, 0); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -1262,7 +1262,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) int rc; if (inet_sk(sk)->inet_daddr) - inet_rps_save_rxhash(sk, skb->rxhash); + sock_rps_save_rxhash(sk, skb->rxhash); rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { -- cgit v1.2.3-70-g09d2 From c377411f2494a931ff7facdbb3a6839b1266bcf6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 27 Apr 2010 15:13:20 -0700 Subject: net: sk_add_backlog() take rmem_alloc into account Current socket backlog limit is not enough to really stop DDOS attacks, because user thread spend many time to process a full backlog each round, and user might crazy spin on socket lock. We should add backlog size and receive_queue size (aka rmem_alloc) to pace writers, and let user run without being slow down too much. Introduce a sk_rcvqueues_full() helper, to avoid taking socket lock in stress situations. Under huge stress from a multiqueue/RPS enabled NIC, a single flow udp receiver can now process ~200.000 pps (instead of ~100 pps before the patch) on a 8 core machine. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 13 +++++++++++-- net/core/sock.c | 5 ++++- net/ipv4/udp.c | 4 ++++ net/ipv6/udp.c | 8 ++++++++ net/sctp/socket.c | 3 --- 5 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 07822280d95..cf12b1e61fa 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -256,7 +256,6 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; int len; - int limit; } sk_backlog; wait_queue_head_t *sk_sleep; struct dst_entry *sk_dst_cache; @@ -608,10 +607,20 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb->next = NULL; } +/* + * Take into account size of receive queue and backlog queue + */ +static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb) +{ + unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); + + return qsize + skb->truesize > sk->sk_rcvbuf; +} + /* The per-socket spinlock must be held here. */ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *skb) { - if (sk->sk_backlog.len >= max(sk->sk_backlog.limit, sk->sk_rcvbuf << 1)) + if (sk_rcvqueues_full(sk, skb)) return -ENOBUFS; __sk_add_backlog(sk, skb); diff --git a/net/core/sock.c b/net/core/sock.c index 58ebd146ce5..51041759517 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -327,6 +327,10 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested) skb->dev = NULL; + if (sk_rcvqueues_full(sk, skb)) { + atomic_inc(&sk->sk_drops); + goto discard_and_relse; + } if (nested) bh_lock_sock_nested(sk); else @@ -1885,7 +1889,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_allocation = GFP_KERNEL; sk->sk_rcvbuf = sysctl_rmem_default; sk->sk_sndbuf = sysctl_wmem_default; - sk->sk_backlog.limit = sk->sk_rcvbuf << 1; sk->sk_state = TCP_CLOSE; sk_set_socket(sk, sock); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index fa3d2874db4..63eb56b2d87 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1372,6 +1372,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; } + + if (sk_rcvqueues_full(sk, skb)) + goto drop; + rc = 0; bh_lock_sock(sk); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2850e35cee3..3ead20ad9d0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -584,6 +584,10 @@ static void flush_stack(struct sock **stack, unsigned int count, sk = stack[i]; if (skb1) { + if (sk_rcvqueues_full(sk, skb)) { + kfree_skb(skb1); + goto drop; + } bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb1); @@ -759,6 +763,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* deliver */ + if (sk_rcvqueues_full(sk, skb)) { + sock_put(sk); + goto discard; + } bh_lock_sock(sk); if (!sock_owned_by_user(sk)) udpv6_queue_rcv_skb(sk, skb); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f34adcca8a8..13d8229f3a9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3721,9 +3721,6 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) SCTP_DBG_OBJCNT_INC(sock); percpu_counter_inc(&sctp_sockets_allocated); - /* Set socket backlog limit. */ - sk->sk_backlog.limit = sysctl_sctp_rmem[1]; - local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); local_bh_enable(); -- cgit v1.2.3-70-g09d2 From 05fceb4ad7e8bf809a2a97061d6273d27d1a8449 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 23 Apr 2010 01:40:47 +0000 Subject: net: disallow to use net_assign_generic externally Now there's no need to use this fuction directly because it's handled by register_pernet_device. So to make this simple and easy to understand, make this static to do not tempt potentional users. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/netns/generic.h | 9 +---- net/core/net_namespace.c | 91 ++++++++++++++++++++++----------------------- 2 files changed, 47 insertions(+), 53 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/generic.h b/include/net/netns/generic.h index ff4982ab84b..81a31c0db3e 100644 --- a/include/net/netns/generic.h +++ b/include/net/netns/generic.h @@ -14,11 +14,8 @@ * The rules are simple: * 1. set pernet_operations->id. After register_pernet_device you * will have the id of your private pointer. - * 2. Either set pernet_operations->size (to have the code allocate and - * free a private structure pointed to from struct net ) or - * call net_assign_generic() to put the private data on the struct - * net (most preferably this should be done in the ->init callback - * of the ops registered); + * 2. set pernet_operations->size to have the code allocate and free + * a private structure pointed to from struct net. * 3. do not change this pointer while the net is alive; * 4. do not try to have any private reference on the net_generic object. * @@ -46,6 +43,4 @@ static inline void *net_generic(struct net *net, int id) return ptr; } - -extern int net_assign_generic(struct net *net, int id, void *data); #endif diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 69a20bfc527..c988e685433 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,6 +27,51 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static void net_generic_release(struct rcu_head *rcu) +{ + struct net_generic *ng; + + ng = container_of(rcu, struct net_generic, rcu); + kfree(ng); +} + +static int net_assign_generic(struct net *net, int id, void *data) +{ + struct net_generic *ng, *old_ng; + + BUG_ON(!mutex_is_locked(&net_mutex)); + BUG_ON(id == 0); + + ng = old_ng = net->gen; + if (old_ng->len >= id) + goto assign; + + ng = kzalloc(sizeof(struct net_generic) + + id * sizeof(void *), GFP_KERNEL); + if (ng == NULL) + return -ENOMEM; + + /* + * Some synchronisation notes: + * + * The net_generic explores the net->gen array inside rcu + * read section. Besides once set the net->gen->ptr[x] + * pointer never changes (see rules in netns/generic.h). + * + * That said, we simply duplicate this array and schedule + * the old copy for kfree after a grace period. + */ + + ng->len = id; + memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); + + rcu_assign_pointer(net->gen, ng); + call_rcu(&old_ng->rcu, net_generic_release); +assign: + ng->ptr[id - 1] = data; + return 0; +} + static int ops_init(const struct pernet_operations *ops, struct net *net) { int err; @@ -526,49 +571,3 @@ void unregister_pernet_device(struct pernet_operations *ops) mutex_unlock(&net_mutex); } EXPORT_SYMBOL_GPL(unregister_pernet_device); - -static void net_generic_release(struct rcu_head *rcu) -{ - struct net_generic *ng; - - ng = container_of(rcu, struct net_generic, rcu); - kfree(ng); -} - -int net_assign_generic(struct net *net, int id, void *data) -{ - struct net_generic *ng, *old_ng; - - BUG_ON(!mutex_is_locked(&net_mutex)); - BUG_ON(id == 0); - - ng = old_ng = net->gen; - if (old_ng->len >= id) - goto assign; - - ng = kzalloc(sizeof(struct net_generic) + - id * sizeof(void *), GFP_KERNEL); - if (ng == NULL) - return -ENOMEM; - - /* - * Some synchronisation notes: - * - * The net_generic explores the net->gen array inside rcu - * read section. Besides once set the net->gen->ptr[x] - * pointer never changes (see rules in netns/generic.h). - * - * That said, we simply duplicate this array and schedule - * the old copy for kfree after a grace period. - */ - - ng->len = id; - memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*)); - - rcu_assign_pointer(net->gen, ng); - call_rcu(&old_ng->rcu, net_generic_release); -assign: - ng->ptr[id - 1] = data; - return 0; -} -EXPORT_SYMBOL_GPL(net_assign_generic); -- cgit v1.2.3-70-g09d2 From e539d83cc8a4fa581cbf8ed288fdadb19a692cb0 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Wed, 28 Apr 2010 08:54:35 +0000 Subject: caif: Rename functions in cfcnfg and caif_dev Changes: o Renamed cfcnfg_del_adapt_layer to cfcnfg_disconn_adapt_layer o Fixed typo cfcfg to cfcnfg o Renamed linkid to channel_id o Updated documentation in caif_dev.h o Minor formatting changes Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_dev.h | 6 ++++-- include/net/caif/cfcnfg.h | 10 ++++----- net/caif/caif_dev.c | 15 +++++++------ net/caif/cfcnfg.c | 51 ++++++++++++++++++++++----------------------- 4 files changed, 41 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h index 42a7c786784..3aa1ff64232 100644 --- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -23,17 +23,19 @@ struct caif_param { }; /** - * caif_connect_request - Request data for CAIF channel setup. + * struct caif_connect_request - Request data for CAIF channel setup. + * @protocol: Type of CAIF protocol to use (at, datagram etc) * @sockaddr: Socket address to connect. * @priority: Priority of the connection. * @link_selector: Link selector (high bandwidth or low latency) * @link_name: Name of the CAIF Link Layer to use. + * @param: Connect Request parameters (CAIF_SO_REQ_PARAM). * * This struct is used when connecting a CAIF channel. * It contains all CAIF channel configuration options. */ struct caif_connect_request { - int protocol; + enum caif_protocol_type protocol; struct sockaddr_caif sockaddr; enum caif_channel_priority priority; enum caif_link_selector link_selector; diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h index 366082c5d43..f16b875acc4 100644 --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -87,13 +87,14 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type, int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer); /** - * cfcnfg_del_adapt_layer - Deletes an adaptation layer from the CAIF stack. + * cfcnfg_disconn_adapt_layer - Disconnects an adaptation layer. * * @cnfg: Pointer to a CAIF configuration object, created by * cfcnfg_create(). * @adap_layer: Adaptation layer to be removed. */ -int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer); +int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, + struct cflayer *adap_layer); /** * cfcnfg_add_adaptation_layer - Add an adaptation layer to the CAIF stack. @@ -102,14 +103,13 @@ int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer); * driver functionality is implemented. * * @cnfg: Pointer to a CAIF configuration object, created by - * cfcnfg_create(). + * cfcnfg_create(). * @param: Link setup parameters. * @adap_layer: Specify the adaptation layer; the receive and * flow-control functions MUST be set in the structure. * */ -int -cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, +int cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, struct cfctrl_link_param *param, struct cflayer *adap_layer); diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e84837e1bc8..be1f674a3b6 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -330,20 +330,19 @@ int caif_connect_client(struct caif_connect_request *conn_req, struct cflayer *client_layer) { struct cfctrl_link_param param; - if (connect_req_to_link_param(get_caif_conf(), conn_req, ¶m) == 0) - /* Hook up the adaptation layer. */ - return cfcnfg_add_adaptation_layer(get_caif_conf(), + int ret; + ret = connect_req_to_link_param(get_caif_conf(), conn_req, ¶m); + if (ret) + return ret; + /* Hook up the adaptation layer. */ + return cfcnfg_add_adaptation_layer(get_caif_conf(), ¶m, client_layer); - - return -EINVAL; - - caif_assert(0); } EXPORT_SYMBOL(caif_connect_client); int caif_disconnect_client(struct cflayer *adap_layer) { - return cfcnfg_del_adapt_layer(get_caif_conf(), adap_layer); + return cfcnfg_disconn_adapt_layer(get_caif_conf(), adap_layer); } EXPORT_SYMBOL(caif_disconnect_client); diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index c873e3d4387..d52f2566916 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -51,12 +51,12 @@ struct cfcnfg { struct cfcnfg_phyinfo phy_layers[MAX_PHY_LAYERS]; }; -static void cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, +static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer); -static void cncfg_linkdestroy_rsp(struct cflayer *layer, u8 linkid, +static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *client_layer); -static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid, +static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer); static void cfctrl_resp_func(void); static void cfctrl_enum_resp(void); @@ -82,13 +82,13 @@ struct cfcnfg *cfcnfg_create(void) resp = cfctrl_get_respfuncs(this->ctrl); resp->enum_rsp = cfctrl_enum_resp; resp->linkerror_ind = cfctrl_resp_func; - resp->linkdestroy_rsp = cncfg_linkdestroy_rsp; + resp->linkdestroy_rsp = cfcnfg_linkdestroy_rsp; resp->sleep_rsp = cfctrl_resp_func; resp->wake_rsp = cfctrl_resp_func; resp->restart_rsp = cfctrl_resp_func; resp->radioset_rsp = cfctrl_resp_func; - resp->linksetup_rsp = cncfg_linkup_rsp; - resp->reject_rsp = cncfg_reject_rsp; + resp->linksetup_rsp = cfcnfg_linkup_rsp; + resp->reject_rsp = cfcnfg_reject_rsp; this->last_phyid = 1; @@ -191,8 +191,7 @@ int cfcnfg_get_named(struct cfcnfg *cnfg, char *name) * 4) Link-Error - (no response) * Not handled, but this should be a CAIF PROTOCOL ERROR */ - -int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) +int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) { u8 channel_id = 0; int ret = 0; @@ -246,9 +245,9 @@ end: return ret; } -EXPORT_SYMBOL(cfcnfg_del_adapt_layer); +EXPORT_SYMBOL(cfcnfg_disconn_adapt_layer); -static void cncfg_linkdestroy_rsp(struct cflayer *layer, u8 linkid, +static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *client_layer) { struct cfcnfg *cnfg = container_obj(layer); @@ -258,20 +257,20 @@ static void cncfg_linkdestroy_rsp(struct cflayer *layer, u8 linkid, * 1) Remove service from the MUX layer. The MUX must * guarante that no more payload sent "upwards" (receive) */ - servl = cfmuxl_remove_uplayer(cnfg->mux, linkid); + servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id); if (servl == NULL) { pr_err("CAIF: %s(): PROTOCOL ERROR " - "- Error removing service_layer Linkid(%d)", - __func__, linkid); + "- Error removing service_layer Channel_Id(%d)", + __func__, channel_id); return; } - caif_assert(linkid == servl->id); + caif_assert(channel_id == servl->id); if (servl != client_layer && servl->up != client_layer) { pr_err("CAIF: %s(): Error removing service_layer " - "Linkid(%d) %p %p", - __func__, linkid, (void *) servl, + "Channel_Id(%d) %p %p", + __func__, channel_id, (void *) servl, (void *) client_layer); return; } @@ -345,7 +344,7 @@ cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, } EXPORT_SYMBOL(cfcnfg_add_adaptation_layer); -static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid, +static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer) { if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL) @@ -354,7 +353,7 @@ static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid, } static void -cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv, +cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer) { struct cfcnfg *cnfg = container_obj(layer); @@ -383,26 +382,26 @@ cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv, _CAIF_MODEMCMD_PHYIF_USEFULL); } - adapt_layer->id = linkid; + adapt_layer->id = channel_id; switch (serv) { case CFCTRL_SRV_VEI: - servicel = cfvei_create(linkid, &phyinfo->dev_info); + servicel = cfvei_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DATAGRAM: - servicel = cfdgml_create(linkid, &phyinfo->dev_info); + servicel = cfdgml_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_RFM: - servicel = cfrfml_create(linkid, &phyinfo->dev_info); + servicel = cfrfml_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_UTIL: - servicel = cfutill_create(linkid, &phyinfo->dev_info); + servicel = cfutill_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_VIDEO: - servicel = cfvidl_create(linkid, &phyinfo->dev_info); + servicel = cfvidl_create(channel_id, &phyinfo->dev_info); break; case CFCTRL_SRV_DBG: - servicel = cfdbgl_create(linkid, &phyinfo->dev_info); + servicel = cfdbgl_create(channel_id, &phyinfo->dev_info); break; default: pr_err("CAIF: %s(): Protocol error. " @@ -415,7 +414,7 @@ cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv, return; } layer_set_dn(servicel, cnfg->mux); - cfmuxl_set_uplayer(cnfg->mux, servicel, linkid); + cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); layer_set_dn(adapt_layer, servicel); servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0); -- cgit v1.2.3-70-g09d2 From 5b2086567503f9b55136642031ec0067319f58e0 Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Wed, 28 Apr 2010 08:54:36 +0000 Subject: caif: Add reference counting to service layer Changes: o Added functions cfsrvl_get and cfsrvl_put. o Added support release_client to use by socket and net device. o Increase reference counting for in-flight packets from cfmuxl Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/caif_dev.h | 11 +++++++++++ include/net/caif/cfcnfg.h | 7 +++++++ include/net/caif/cfsrvl.h | 22 ++++++++++++++++++++++ net/caif/caif_dev.c | 6 ++++++ net/caif/cfcnfg.c | 7 +++++++ net/caif/cfmuxl.c | 7 ++++++- net/caif/cfsrvl.c | 7 +++++++ 7 files changed, 66 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h index 3aa1ff64232..318ab9478a4 100644 --- a/include/net/caif/caif_dev.h +++ b/include/net/caif/caif_dev.h @@ -69,6 +69,17 @@ int caif_connect_client(struct caif_connect_request *config, */ int caif_disconnect_client(struct cflayer *client_layer); +/** + * caif_release_client - Release adaptation layer reference to client. + * + * @client_layer: Client layer. + * + * Releases a client/adaptation layer use of the caif stack. + * This function must be used after caif_disconnect_client to + * decrease the reference count of the service layer. + */ +void caif_release_client(struct cflayer *client_layer); + /** * connect_req_to_link_param - Translate configuration parameters * from socket format to internal format. diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h index f16b875acc4..9fc2fc20b88 100644 --- a/include/net/caif/cfcnfg.h +++ b/include/net/caif/cfcnfg.h @@ -96,6 +96,13 @@ int cfcnfg_del_phy_layer(struct cfcnfg *cnfg, struct cflayer *phy_layer); int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer); +/** + * cfcnfg_release_adap_layer - Used by client to release the adaptation layer. + * + * @adap_layer: Adaptation layer. + */ +void cfcnfg_release_adap_layer(struct cflayer *adap_layer); + /** * cfcnfg_add_adaptation_layer - Add an adaptation layer to the CAIF stack. * diff --git a/include/net/caif/cfsrvl.h b/include/net/caif/cfsrvl.h index b2a12db20cd..2dc9eb193ec 100644 --- a/include/net/caif/cfsrvl.h +++ b/include/net/caif/cfsrvl.h @@ -9,14 +9,18 @@ #include #include #include +#include + struct cfsrvl { struct cflayer layer; bool open; bool phy_flow_on; bool modem_flow_on; struct dev_info dev_info; + struct kref ref; }; +void cfsrvl_release(struct kref *kref); struct cflayer *cfvei_create(u8 linkid, struct dev_info *dev_info); struct cflayer *cfdgml_create(u8 linkid, struct dev_info *dev_info); struct cflayer *cfutill_create(u8 linkid, struct dev_info *dev_info); @@ -31,4 +35,22 @@ void cfsrvl_init(struct cfsrvl *service, bool cfsrvl_ready(struct cfsrvl *service, int *err); u8 cfsrvl_getphyid(struct cflayer *layer); +static inline void cfsrvl_get(struct cflayer *layr) +{ + struct cfsrvl *s; + if (layr == NULL) + return; + s = container_of(layr, struct cfsrvl, layer); + kref_get(&s->ref); +} + +static inline void cfsrvl_put(struct cflayer *layr) +{ + struct cfsrvl *s; + if (layr == NULL) + return; + s = container_of(layr, struct cfsrvl, layer); + kref_put(&s->ref, cfsrvl_release); +} + #endif /* CFSRVL_H_ */ diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index be1f674a3b6..0145bae0274 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -346,6 +346,12 @@ int caif_disconnect_client(struct cflayer *adap_layer) } EXPORT_SYMBOL(caif_disconnect_client); +void caif_release_client(struct cflayer *adap_layer) +{ + cfcnfg_release_adap_layer(adap_layer); +} +EXPORT_SYMBOL(caif_release_client); + /* Per-namespace Caif devices handling */ static int caif_init_net(struct net *net) { diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index d52f2566916..f94f3dfe85c 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -247,6 +247,13 @@ end: } EXPORT_SYMBOL(cfcnfg_disconn_adapt_layer); +void cfcnfg_release_adap_layer(struct cflayer *adap_layer) +{ + if (adap_layer->dn) + cfsrvl_put(adap_layer->dn); +} +EXPORT_SYMBOL(cfcnfg_release_adap_layer); + static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *client_layer) { diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 6fb9f9e96cf..7372f27f1d3 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -62,6 +62,7 @@ int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid) { struct cfmuxl *muxl = container_obj(layr); spin_lock(&muxl->receive_lock); + cfsrvl_get(up); list_add(&up->node, &muxl->srvl_list); spin_unlock(&muxl->receive_lock); return 0; @@ -172,8 +173,11 @@ struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id) struct cfmuxl *muxl = container_obj(layr); spin_lock(&muxl->receive_lock); up = get_up(muxl, id); + if (up == NULL) + return NULL; memset(muxl->up_cache, 0, sizeof(muxl->up_cache)); list_del(&up->node); + cfsrvl_put(up); spin_unlock(&muxl->receive_lock); return up; } @@ -203,8 +207,9 @@ static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt) */ return /* CFGLU_EPROT; */ 0; } - + cfsrvl_get(up); ret = up->receive(up, pkt); + cfsrvl_put(up); return ret; } diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c index d470c51c643..aff31f34528 100644 --- a/net/caif/cfsrvl.c +++ b/net/caif/cfsrvl.c @@ -158,6 +158,13 @@ void cfsrvl_init(struct cfsrvl *service, service->layer.ctrlcmd = cfservl_ctrlcmd; service->layer.modemcmd = cfservl_modemcmd; service->dev_info = *dev_info; + kref_init(&service->ref); +} + +void cfsrvl_release(struct kref *kref) +{ + struct cfsrvl *service = container_of(kref, struct cfsrvl, ref); + kfree(service); } bool cfsrvl_ready(struct cfsrvl *service, int *err) -- cgit v1.2.3-70-g09d2 From 8d545c8f958f5f433c50a00762ce1f231ed56eee Mon Sep 17 00:00:00 2001 From: Sjur Braendeland Date: Wed, 28 Apr 2010 08:54:37 +0000 Subject: caif: Disconnect without waiting for response Changes: o Function cfcnfg_disconn_adapt_layer is changed to do asynchronous disconnect, not waiting for any response from the modem. Due to this the function cfcnfg_linkdestroy_rsp does nothing anymore. o Because disconnect may take down a connection before a connect response is received the function cfcnfg_linkup_rsp is checking if the client is still waiting for the response, if not a disconnect request is sent to the modem. o cfctrl is no longer keeping track of pending disconnect requests. o Added function cfctrl_cancel_req, which is used for deleting a pending connect request if disconnect is done before connect response is received. o Removed unused function cfctrl_insert_req2 o Added better handling of connect reject from modem. Signed-off-by: Sjur Braendeland Signed-off-by: David S. Miller --- include/net/caif/cfctrl.h | 7 ++- net/caif/cfcnfg.c | 155 ++++++++++++++-------------------------------- net/caif/cfctrl.c | 95 ++++++++++++++++++---------- 3 files changed, 111 insertions(+), 146 deletions(-) (limited to 'include/net') diff --git a/include/net/caif/cfctrl.h b/include/net/caif/cfctrl.h index dee25b86caa..997603f2bf4 100644 --- a/include/net/caif/cfctrl.h +++ b/include/net/caif/cfctrl.h @@ -43,8 +43,7 @@ struct cfctrl_rsp { void (*linksetup_rsp)(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer); - void (*linkdestroy_rsp)(struct cflayer *layer, u8 linkid, - struct cflayer *client_layer); + void (*linkdestroy_rsp)(struct cflayer *layer, u8 linkid); void (*linkerror_ind)(void); void (*enum_rsp)(void); void (*sleep_rsp)(void); @@ -117,7 +116,7 @@ struct cfctrl { }; void cfctrl_enum_req(struct cflayer *cfctrl, u8 physlinkid); -void cfctrl_linkup_request(struct cflayer *cfctrl, +int cfctrl_linkup_request(struct cflayer *cfctrl, struct cfctrl_link_param *param, struct cflayer *user_layer); int cfctrl_linkdown_req(struct cflayer *cfctrl, u8 linkid, @@ -135,4 +134,6 @@ void cfctrl_insert_req(struct cfctrl *ctrl, struct cfctrl_request_info *req); struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, struct cfctrl_request_info *req); +void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer); + #endif /* CFCTRL_H_ */ diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index f94f3dfe85c..471c62939fa 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -54,8 +54,7 @@ struct cfcnfg { static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, u8 phyid, struct cflayer *adapt_layer); -static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id, - struct cflayer *client_layer); +static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id); static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id, struct cflayer *adapt_layer); static void cfctrl_resp_func(void); @@ -175,73 +174,65 @@ int cfcnfg_get_named(struct cfcnfg *cnfg, char *name) return 0; } -/* - * NOTE: What happens on destroy failure: - * 1a) No response - Too early - * This will not happen because enumerate has already - * completed. - * 1b) No response - FATAL - * Not handled, but this should be a CAIF PROTOCOL ERROR - * Modem error, response is really expected - this - * case is not really handled. - * 2) O/E-bit indicate error - * Ignored - this link is destroyed anyway. - * 3) Not able to match on request - * Not handled, but this should be a CAIF PROTOCOL ERROR - * 4) Link-Error - (no response) - * Not handled, but this should be a CAIF PROTOCOL ERROR - */ int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer) { u8 channel_id = 0; int ret = 0; + struct cflayer *servl = NULL; struct cfcnfg_phyinfo *phyinfo = NULL; u8 phyid = 0; - caif_assert(adap_layer != NULL); channel_id = adap_layer->id; - if (channel_id == 0) { + if (adap_layer->dn == NULL || channel_id == 0) { pr_err("CAIF: %s():adap_layer->id is 0\n", __func__); ret = -ENOTCONN; goto end; } - - if (adap_layer->dn == NULL) { - pr_err("CAIF: %s():adap_layer->dn is NULL\n", __func__); - ret = -ENODEV; - goto end; - } - - if (adap_layer->dn != NULL) - phyid = cfsrvl_getphyid(adap_layer->dn); - - phyinfo = cfcnfg_get_phyinfo(cnfg, phyid); - if (phyinfo == NULL) { - pr_warning("CAIF: %s(): No interface to send disconnect to\n", - __func__); - ret = -ENODEV; + servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id); + if (servl == NULL) goto end; - } - - if (phyinfo->id != phyid - || phyinfo->phy_layer->id != phyid - || phyinfo->frm_layer->id != phyid) { - - pr_err("CAIF: %s(): Inconsistency in phy registration\n", - __func__); + layer_set_up(servl, NULL); + ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer); + if (servl == NULL) { + pr_err("CAIF: %s(): PROTOCOL ERROR " + "- Error removing service_layer Channel_Id(%d)", + __func__, channel_id); ret = -EINVAL; goto end; } + caif_assert(channel_id == servl->id); + if (adap_layer->dn != NULL) { + phyid = cfsrvl_getphyid(adap_layer->dn); - ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer); - -end: + phyinfo = cfcnfg_get_phyinfo(cnfg, phyid); + if (phyinfo == NULL) { + pr_warning("CAIF: %s(): " + "No interface to send disconnect to\n", + __func__); + ret = -ENODEV; + goto end; + } + if (phyinfo->id != phyid || + phyinfo->phy_layer->id != phyid || + phyinfo->frm_layer->id != phyid) { + pr_err("CAIF: %s(): " + "Inconsistency in phy registration\n", + __func__); + ret = -EINVAL; + goto end; + } + } if (phyinfo != NULL && --phyinfo->phy_ref_count == 0 && phyinfo->phy_layer != NULL && phyinfo->phy_layer->modemcmd != NULL) { phyinfo->phy_layer->modemcmd(phyinfo->phy_layer, _CAIF_MODEMCMD_PHYIF_USELESS); } +end: + cfsrvl_put(servl); + cfctrl_cancel_req(cnfg->ctrl, adap_layer); + if (adap_layer->ctrlcmd != NULL) + adap_layer->ctrlcmd(adap_layer, CAIF_CTRLCMD_DEINIT_RSP, 0); return ret; } @@ -254,69 +245,11 @@ void cfcnfg_release_adap_layer(struct cflayer *adap_layer) } EXPORT_SYMBOL(cfcnfg_release_adap_layer); -static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id, - struct cflayer *client_layer) +static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id) { - struct cfcnfg *cnfg = container_obj(layer); - struct cflayer *servl; - - /* - * 1) Remove service from the MUX layer. The MUX must - * guarante that no more payload sent "upwards" (receive) - */ - servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id); - - if (servl == NULL) { - pr_err("CAIF: %s(): PROTOCOL ERROR " - "- Error removing service_layer Channel_Id(%d)", - __func__, channel_id); - return; - } - caif_assert(channel_id == servl->id); - - if (servl != client_layer && servl->up != client_layer) { - pr_err("CAIF: %s(): Error removing service_layer " - "Channel_Id(%d) %p %p", - __func__, channel_id, (void *) servl, - (void *) client_layer); - return; - } - - /* - * 2) DEINIT_RSP must guarantee that no more packets are transmitted - * from client (adap_layer) when it returns. - */ - - if (servl->ctrlcmd == NULL) { - pr_err("CAIF: %s(): Error servl->ctrlcmd == NULL", __func__); - return; - } - - servl->ctrlcmd(servl, CAIF_CTRLCMD_DEINIT_RSP, 0); - - /* 3) It is now safe to destroy the service layer. */ - cfservl_destroy(servl); } -/* - * NOTE: What happens on linksetup failure: - * 1a) No response - Too early - * This will not happen because enumerate is secured - * before using interface. - * 1b) No response - FATAL - * Not handled, but this should be a CAIF PROTOCOL ERROR - * Modem error, response is really expected - this case is - * not really handled. - * 2) O/E-bit indicate error - * Handled in cnfg_reject_rsp - * 3) Not able to match on request - * Not handled, but this should be a CAIF PROTOCOL ERROR - * 4) Link-Error - (no response) - * Not handled, but this should be a CAIF PROTOCOL ERROR - */ - -int -cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, +int cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, struct cfctrl_link_param *param, struct cflayer *adap_layer) { @@ -346,8 +279,7 @@ cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg, param->phyid); /* FIXME: ENUMERATE INITIALLY WHEN ACTIVATING PHYSICAL INTERFACE */ cfctrl_enum_req(cnfg->ctrl, param->phyid); - cfctrl_linkup_request(cnfg->ctrl, param, adap_layer); - return 0; + return cfctrl_linkup_request(cnfg->ctrl, param, adap_layer); } EXPORT_SYMBOL(cfcnfg_add_adaptation_layer); @@ -367,8 +299,10 @@ cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, struct cflayer *servicel = NULL; struct cfcnfg_phyinfo *phyinfo; if (adapt_layer == NULL) { - pr_err("CAIF: %s(): PROTOCOL ERROR " - "- LinkUp Request/Response did not match\n", __func__); + pr_debug("CAIF: %s(): link setup response " + "but no client exist, send linkdown back\n", + __func__); + cfctrl_linkdown_req(cnfg->ctrl, channel_id, NULL); return; } @@ -424,6 +358,7 @@ cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv, cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id); layer_set_up(servicel, adapt_layer); layer_set_dn(adapt_layer, servicel); + cfsrvl_get(servicel); servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0); } diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c index 11f80140f3c..a521d32cfe5 100644 --- a/net/caif/cfctrl.c +++ b/net/caif/cfctrl.c @@ -32,6 +32,7 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, struct cflayer *cfctrl_create(void) { + struct dev_info dev_info; struct cfctrl *this = kmalloc(sizeof(struct cfctrl), GFP_ATOMIC); if (!this) { @@ -39,12 +40,13 @@ struct cflayer *cfctrl_create(void) return NULL; } caif_assert(offsetof(struct cfctrl, serv.layer) == 0); + memset(&dev_info, 0, sizeof(dev_info)); + dev_info.id = 0xff; memset(this, 0, sizeof(*this)); + cfsrvl_init(&this->serv, 0, &dev_info); spin_lock_init(&this->info_list_lock); atomic_set(&this->req_seq_no, 1); atomic_set(&this->rsp_seq_no, 1); - this->serv.dev_info.id = 0xff; - this->serv.layer.id = 0; this->serv.layer.receive = cfctrl_recv; sprintf(this->serv.layer.name, "ctrl"); this->serv.layer.ctrlcmd = cfctrl_ctrlcmd; @@ -127,20 +129,6 @@ void cfctrl_insert_req(struct cfctrl *ctrl, spin_unlock(&ctrl->info_list_lock); } -static void cfctrl_insert_req2(struct cfctrl *ctrl, enum cfctrl_cmd cmd, - u8 linkid, struct cflayer *user_layer) -{ - struct cfctrl_request_info *req = kmalloc(sizeof(*req), GFP_KERNEL); - if (!req) { - pr_warning("CAIF: %s(): Out of memory\n", __func__); - return; - } - req->client_layer = user_layer; - req->cmd = cmd; - req->channel_id = linkid; - cfctrl_insert_req(ctrl, req); -} - /* Compare and remove request */ struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl, struct cfctrl_request_info *req) @@ -234,7 +222,7 @@ void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid) } } -void cfctrl_linkup_request(struct cflayer *layer, +int cfctrl_linkup_request(struct cflayer *layer, struct cfctrl_link_param *param, struct cflayer *user_layer) { @@ -248,7 +236,7 @@ void cfctrl_linkup_request(struct cflayer *layer, struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN); if (!pkt) { pr_warning("CAIF: %s(): Out of memory\n", __func__); - return; + return -ENOMEM; } cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_SETUP); cfpkt_addbdy(pkt, (param->chtype << 4) + param->linktype); @@ -294,11 +282,12 @@ void cfctrl_linkup_request(struct cflayer *layer, default: pr_warning("CAIF: %s():Request setup of bad link type = %d\n", __func__, param->linktype); + return -EINVAL; } req = kmalloc(sizeof(*req), GFP_KERNEL); if (!req) { pr_warning("CAIF: %s(): Out of memory\n", __func__); - return; + return -ENOMEM; } memset(req, 0, sizeof(*req)); req->client_layer = user_layer; @@ -306,6 +295,11 @@ void cfctrl_linkup_request(struct cflayer *layer, req->param = *param; cfctrl_insert_req(cfctrl, req); init_info(cfpkt_info(pkt), cfctrl); + /* + * NOTE:Always send linkup and linkdown request on the same + * device as the payload. Otherwise old queued up payload + * might arrive with the newly allocated channel ID. + */ cfpkt_info(pkt)->dev_info->id = param->phyid; ret = cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt); @@ -313,7 +307,9 @@ void cfctrl_linkup_request(struct cflayer *layer, pr_err("CAIF: %s(): Could not transmit linksetup request\n", __func__); cfpkt_destroy(pkt); + return -ENODEV; } + return 0; } int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, @@ -326,7 +322,6 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid, pr_warning("CAIF: %s(): Out of memory\n", __func__); return -ENOMEM; } - cfctrl_insert_req2(cfctrl, CFCTRL_CMD_LINK_DESTROY, channelid, client); cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY); cfpkt_addbdy(pkt, channelid); init_info(cfpkt_info(pkt), cfctrl); @@ -392,6 +387,38 @@ void cfctrl_getstartreason_req(struct cflayer *layer) } +void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer) +{ + struct cfctrl_request_info *p, *req; + struct cfctrl *ctrl = container_obj(layr); + spin_lock(&ctrl->info_list_lock); + + if (ctrl->first_req == NULL) { + spin_unlock(&ctrl->info_list_lock); + return; + } + + if (ctrl->first_req->client_layer == adap_layer) { + + req = ctrl->first_req; + ctrl->first_req = ctrl->first_req->next; + kfree(req); + } + + p = ctrl->first_req; + while (p != NULL && p->next != NULL) { + if (p->next->client_layer == adap_layer) { + + req = p->next; + p->next = p->next->next; + kfree(p->next); + } + p = p->next; + } + + spin_unlock(&ctrl->info_list_lock); +} + static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) { u8 cmdrsp; @@ -409,11 +436,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) cmd = cmdrsp & CFCTRL_CMD_MASK; if (cmd != CFCTRL_CMD_LINK_ERR && CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp)) { - if (handle_loop(cfctrl, cmd, pkt) == CAIF_FAILURE) { - pr_info("CAIF: %s() CAIF Protocol error:" - "Response bit not set\n", __func__); - goto error; - } + if (handle_loop(cfctrl, cmd, pkt) == CAIF_FAILURE) + cmdrsp |= CFCTRL_ERR_BIT; } switch (cmd) { @@ -451,12 +475,16 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) switch (serv) { case CFCTRL_SRV_VEI: case CFCTRL_SRV_DBG: + if (CFCTRL_ERR_BIT & cmdrsp) + break; /* Link ID */ cfpkt_extr_head(pkt, &linkid, 1); break; case CFCTRL_SRV_VIDEO: cfpkt_extr_head(pkt, &tmp, 1); linkparam.u.video.connid = tmp; + if (CFCTRL_ERR_BIT & cmdrsp) + break; /* Link ID */ cfpkt_extr_head(pkt, &linkid, 1); break; @@ -465,6 +493,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) cfpkt_extr_head(pkt, &tmp32, 4); linkparam.u.datagram.connid = le32_to_cpu(tmp32); + if (CFCTRL_ERR_BIT & cmdrsp) + break; /* Link ID */ cfpkt_extr_head(pkt, &linkid, 1); break; @@ -483,6 +513,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) *cp++ = tmp; *cp = '\0'; + if (CFCTRL_ERR_BIT & cmdrsp) + break; /* Link ID */ cfpkt_extr_head(pkt, &linkid, 1); @@ -519,6 +551,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) cfpkt_extr_head(pkt, &tmp, 1); *cp++ = tmp; } + if (CFCTRL_ERR_BIT & cmdrsp) + break; /* Link ID */ cfpkt_extr_head(pkt, &linkid, 1); /* Length */ @@ -560,13 +594,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt) break; case CFCTRL_CMD_LINK_DESTROY: cfpkt_extr_head(pkt, &linkid, 1); - rsp.cmd = cmd; - rsp.channel_id = linkid; - req = cfctrl_remove_req(cfctrl, &rsp); - cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid, - req ? req->client_layer : NULL); - if (req != NULL) - kfree(req); + cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid); break; case CFCTRL_CMD_LINK_ERR: pr_err("CAIF: %s(): Frame Error Indication received\n", @@ -608,7 +636,7 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, case CAIF_CTRLCMD_FLOW_OFF_IND: spin_lock(&this->info_list_lock); if (this->first_req != NULL) { - pr_warning("CAIF: %s(): Received flow off in " + pr_debug("CAIF: %s(): Received flow off in " "control layer", __func__); } spin_unlock(&this->info_list_lock); @@ -633,6 +661,7 @@ static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt) if (!ctrl->loop_linkused[linkid]) goto found; spin_unlock(&ctrl->loop_linkid_lock); + pr_err("CAIF: %s(): Out of link-ids\n", __func__); return -EINVAL; found: if (!ctrl->loop_linkused[linkid]) -- cgit v1.2.3-70-g09d2 From 8fc214ba958648ab111a173f2db7b0e1dfed5b11 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 28 Apr 2010 17:40:43 +0200 Subject: mac80211: notify driver about IBSS status Some drivers (e.g. iwlwifi) need to know and try to figure it out based on other things, but making it explicit is definitely better. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 6 +++++- net/mac80211/ibss.c | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a36e0df5a17..2879c8ef557 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -145,6 +145,7 @@ struct ieee80211_low_level_stats { * @BSS_CHANGED_BEACON_ENABLED: Beaconing should be * enabled/disabled (beaconing modes) * @BSS_CHANGED_CQM: Connection quality monitor config changed + * @BSS_CHANGED_IBSS: IBSS join status changed */ enum ieee80211_bss_change { BSS_CHANGED_ASSOC = 1<<0, @@ -158,6 +159,7 @@ enum ieee80211_bss_change { BSS_CHANGED_BEACON = 1<<8, BSS_CHANGED_BEACON_ENABLED = 1<<9, BSS_CHANGED_CQM = 1<<10, + BSS_CHANGED_IBSS = 1<<11, }; /** @@ -167,6 +169,8 @@ enum ieee80211_bss_change { * to that BSS) that can change during the lifetime of the BSS. * * @assoc: association status + * @ibss_joined: indicates whether this station is part of an IBSS + * or not * @aid: association ID number, valid only when @assoc is true * @use_cts_prot: use CTS protection * @use_short_preamble: use 802.11b short preamble; @@ -194,7 +198,7 @@ enum ieee80211_bss_change { struct ieee80211_bss_conf { const u8 *bssid; /* association related data */ - bool assoc; + bool assoc, ibss_joined; u16 aid; /* erp related data */ bool use_cts_prot; diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 01974c2510a..a87e309e3b9 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -170,6 +170,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, bss_change |= BSS_CHANGED_BSSID; bss_change |= BSS_CHANGED_BEACON; bss_change |= BSS_CHANGED_BEACON_ENABLED; + bss_change |= BSS_CHANGED_IBSS; + sdata->vif.bss_conf.ibss_joined = true; ieee80211_bss_info_change_notify(sdata, bss_change); ieee80211_sta_def_wmm_params(sdata, sband->n_bitrates, supp_rates); @@ -950,7 +952,9 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) kfree(sdata->u.ibss.ie); skb = sdata->u.ibss.presp; rcu_assign_pointer(sdata->u.ibss.presp, NULL); - ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + sdata->vif.bss_conf.ibss_joined = false; + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED | + BSS_CHANGED_IBSS); synchronize_rcu(); kfree_skb(skb); -- cgit v1.2.3-70-g09d2 From 4b0b72f7dd617b13abd1b04c947e15873e011a24 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 28 Apr 2010 14:35:48 -0700 Subject: net: speedup udp receive path Since commit 95766fff ([UDP]: Add memory accounting.), each received packet needs one extra sock_lock()/sock_release() pair. This added latency because of possible backlog handling. Then later, ticket spinlocks added yet another latency source in case of DDOS. This patch introduces lock_sock_bh() and unlock_sock_bh() synchronization primitives, avoiding one atomic operation and backlog processing. skb_free_datagram_locked() uses them instead of full blown lock_sock()/release_sock(). skb is orphaned inside locked section for proper socket memory reclaim, and finally freed outside of it. UDP receive path now take the socket spinlock only once. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 10 ++++++++++ net/core/datagram.c | 10 +++++++--- net/ipv4/udp.c | 12 ++++++------ net/ipv6/udp.c | 4 ++-- 4 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index cf12b1e61fa..d361c7769fe 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1021,6 +1021,16 @@ extern void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) +static inline void lock_sock_bh(struct sock *sk) +{ + spin_lock_bh(&sk->sk_lock.slock); +} + +static inline void unlock_sock_bh(struct sock *sk) +{ + spin_unlock_bh(&sk->sk_lock.slock); +} + extern struct sock *sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot); diff --git a/net/core/datagram.c b/net/core/datagram.c index 5574a5ddf90..95b851f3d71 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -229,9 +229,13 @@ EXPORT_SYMBOL(skb_free_datagram); void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) { - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + lock_sock_bh(sk); + skb_orphan(skb); + sk_mem_reclaim_partial(sk); + unlock_sock_bh(sk); + + /* skb is now orphaned, might be freed outside of locked section */ + consume_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 63eb56b2d87..1f86965ba7d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1062,10 +1062,10 @@ static unsigned int first_packet_length(struct sock *sk) spin_unlock_bh(&rcvq->lock); if (!skb_queue_empty(&list_kill)) { - lock_sock(sk); + lock_sock_bh(sk); __skb_queue_purge(&list_kill); sk_mem_reclaim_partial(sk); - release_sock(sk); + unlock_sock_bh(sk); } return res; } @@ -1196,10 +1196,10 @@ out: return err; csum_copy_err: - lock_sock(sk); + lock_sock_bh(sk); if (!skb_kill_datagram(sk, skb, flags)) UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - release_sock(sk); + unlock_sock_bh(sk); if (noblock) return -EAGAIN; @@ -1624,9 +1624,9 @@ int udp_rcv(struct sk_buff *skb) void udp_destroy_sock(struct sock *sk) { - lock_sock(sk); + lock_sock_bh(sk); udp_flush_pending_frames(sk); - release_sock(sk); + unlock_sock_bh(sk); } /* diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3ead20ad9d0..91c60f0090a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -424,7 +424,7 @@ out: return err; csum_copy_err: - lock_sock(sk); + lock_sock_bh(sk); if (!skb_kill_datagram(sk, skb, flags)) { if (is_udp4) UDP_INC_STATS_USER(sock_net(sk), @@ -433,7 +433,7 @@ csum_copy_err: UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - release_sock(sk); + unlock_sock_bh(sk); if (flags & MSG_DONTWAIT) return -EAGAIN; -- cgit v1.2.3-70-g09d2 From f84af32cbca70a3c6d30463dc08c7984af11c277 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 28 Apr 2010 15:31:51 -0700 Subject: net: ip_queue_rcv_skb() helper When queueing a skb to socket, we can immediately release its dst if target socket do not use IP_CMSG_PKTINFO. tcp_data_queue() can drop dst too. This to benefit from a hot cache line and avoid the receiver, possibly on another cpu, to dirty this cache line himself. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ip.h | 1 + net/ipv4/ip_sockglue.c | 16 ++++++++++++++++ net/ipv4/raw.c | 2 +- net/ipv4/tcp_input.c | 1 + net/ipv4/udp.c | 2 +- net/ipv6/raw.c | 2 +- net/ipv6/udp.c | 2 +- 7 files changed, 22 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/ip.h b/include/net/ip.h index a84ceb69268..8149b77cea9 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -393,6 +393,7 @@ extern int ip_options_rcv_srr(struct sk_buff *skb); * Functions provided by ip_sockglue.c */ +extern int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); extern void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb); extern int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b0aa0546a3b..ce231780a2b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -954,6 +954,22 @@ e_inval: return -EINVAL; } +/** + * ip_queue_rcv_skb - Queue an skb into sock receive queue + * @sk: socket + * @skb: buffer + * + * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option + * is not set, we drop skb dst entry now, while dst cache line is hot. + */ +int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO)) + skb_dst_drop(skb); + return sock_queue_rcv_skb(sk, skb); +} +EXPORT_SYMBOL(ip_queue_rcv_skb); + int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index cc6f097fbd5..52ef5af78a4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -290,7 +290,7 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) { /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk, skb) < 0) { + if (ip_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ae3ec15fb63..e82162c211b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4367,6 +4367,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) goto drop; + skb_dst_drop(skb); __skb_pull(skb, th->doff * 4); TCP_ECN_accept_cwr(tp, skb); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1f86965ba7d..4560b291180 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1264,7 +1264,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (inet_sk(sk)->inet_daddr) sock_rps_save_rxhash(sk, skb->rxhash); - rc = sock_queue_rcv_skb(sk, skb); + rc = ip_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 85627386cb0..0e3d2dd9207 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -381,7 +381,7 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) } /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk, skb) < 0) { + if (ip_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 91c60f0090a..79359c8380b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -514,7 +514,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } - if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { + if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), -- cgit v1.2.3-70-g09d2 From f5c044e53a6b319776c7140b22fee9be3bc1f758 Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Fri, 30 Apr 2010 15:37:00 -0400 Subject: mac80211: remove deprecated noise field from ieee80211_rx_status Also remove associated IEEE80211_HW_NOISE_DBM from ieee80211_hw_flags. Signed-off-by: John W. Linville --- drivers/net/wireless/ath/ar9170/main.c | 3 +-- drivers/net/wireless/ath/ath5k/base.c | 3 +-- drivers/net/wireless/b43/main.c | 3 +-- drivers/net/wireless/b43legacy/main.c | 3 +-- drivers/net/wireless/iwlwifi/iwl-agn.c | 1 - drivers/net/wireless/iwlwifi/iwl3945-base.c | 1 - drivers/net/wireless/mwl8k.c | 4 ++-- drivers/net/wireless/p54/main.c | 3 +-- drivers/net/wireless/wl12xx/wl1251_main.c | 1 - drivers/net/wireless/wl12xx/wl1271_main.c | 1 - include/net/mac80211.h | 8 +------- net/mac80211/rx.c | 2 -- 12 files changed, 8 insertions(+), 25 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c index cfc6a35a2c6..dfcc055a827 100644 --- a/drivers/net/wireless/ath/ar9170/main.c +++ b/drivers/net/wireless/ath/ar9170/main.c @@ -2550,8 +2550,7 @@ void *ar9170_alloc(size_t priv_size) BIT(NL80211_IFTYPE_ADHOC); ar->hw->flags |= IEEE80211_HW_RX_INCLUDES_FCS | IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING | - IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM; + IEEE80211_HW_SIGNAL_DBM; if (modparam_ht) { ar->hw->flags |= IEEE80211_HW_AMPDU_AGGREGATION; diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 1f3e5b0986c..feb7b9ea80a 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -547,8 +547,7 @@ ath5k_pci_probe(struct pci_dev *pdev, SET_IEEE80211_DEV(hw, &pdev->dev); hw->flags = IEEE80211_HW_RX_INCLUDES_FCS | IEEE80211_HW_HOST_BROADCAST_PS_BUFFERING | - IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM; + IEEE80211_HW_SIGNAL_DBM; hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_AP) | diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index 14cf3bd7ea5..e0575591828 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -4904,8 +4904,7 @@ static int b43_wireless_init(struct ssb_device *dev) /* fill hw info */ hw->flags = IEEE80211_HW_RX_INCLUDES_FCS | - IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM; + IEEE80211_HW_SIGNAL_DBM; hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_AP) | diff --git a/drivers/net/wireless/b43legacy/main.c b/drivers/net/wireless/b43legacy/main.c index 1d070be5a67..b2df432d3c6 100644 --- a/drivers/net/wireless/b43legacy/main.c +++ b/drivers/net/wireless/b43legacy/main.c @@ -3768,8 +3768,7 @@ static int b43legacy_wireless_init(struct ssb_device *dev) /* fill hw info */ hw->flags = IEEE80211_HW_RX_INCLUDES_FCS | - IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM; + IEEE80211_HW_SIGNAL_DBM; hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_AP) | BIT(NL80211_IFTYPE_STATION) | diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index c22d3d8c440..0cd33863159 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -2653,7 +2653,6 @@ static int iwl_mac_setup_register(struct iwl_priv *priv) /* Tell mac80211 our characteristics */ hw->flags = IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM | IEEE80211_HW_AMPDU_AGGREGATION | IEEE80211_HW_SPECTRUM_MGMT; diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index e7263ed693c..c9da39d7c41 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -3872,7 +3872,6 @@ static int iwl3945_setup_mac(struct iwl_priv *priv) /* Tell mac80211 our characteristics */ hw->flags = IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM | IEEE80211_HW_SPECTRUM_MGMT; if (!priv->cfg->broken_powersave) diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 9af6c945460..a90bb6d2e26 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -3981,8 +3981,8 @@ static int __devinit mwl8k_probe(struct pci_dev *pdev, hw->queues = MWL8K_TX_QUEUES; - /* Set rssi and noise values to dBm */ - hw->flags |= IEEE80211_HW_SIGNAL_DBM | IEEE80211_HW_NOISE_DBM; + /* Set rssi values to dBm */ + hw->flags |= IEEE80211_HW_SIGNAL_DBM; hw->vif_data_size = sizeof(struct mwl8k_vif); hw->sta_data_size = sizeof(struct mwl8k_sta); diff --git a/drivers/net/wireless/p54/main.c b/drivers/net/wireless/p54/main.c index 36f4c820ad0..10a4b16f31c 100644 --- a/drivers/net/wireless/p54/main.c +++ b/drivers/net/wireless/p54/main.c @@ -545,8 +545,7 @@ struct ieee80211_hw *p54_init_common(size_t priv_data_len) IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_PS_NULLFUNC_STACK | IEEE80211_HW_BEACON_FILTER | - IEEE80211_HW_REPORTS_TX_ACK_STATUS | - IEEE80211_HW_NOISE_DBM; + IEEE80211_HW_REPORTS_TX_ACK_STATUS; dev->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_ADHOC) | diff --git a/drivers/net/wireless/wl12xx/wl1251_main.c b/drivers/net/wireless/wl12xx/wl1251_main.c index 4d3be80c220..b70621f63cd 100644 --- a/drivers/net/wireless/wl12xx/wl1251_main.c +++ b/drivers/net/wireless/wl12xx/wl1251_main.c @@ -1291,7 +1291,6 @@ int wl1251_init_ieee80211(struct wl1251 *wl) wl->hw->channel_change_time = 10000; wl->hw->flags = IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM | IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_BEACON_FILTER | IEEE80211_HW_SUPPORTS_UAPSD; diff --git a/drivers/net/wireless/wl12xx/wl1271_main.c b/drivers/net/wireless/wl12xx/wl1271_main.c index a794d5ed8c6..b0837255de6 100644 --- a/drivers/net/wireless/wl12xx/wl1271_main.c +++ b/drivers/net/wireless/wl12xx/wl1271_main.c @@ -2275,7 +2275,6 @@ int wl1271_init_ieee80211(struct wl1271 *wl) wl->hw->max_listen_interval = wl->conf.conn.max_listen_interval; wl->hw->flags = IEEE80211_HW_SIGNAL_DBM | - IEEE80211_HW_NOISE_DBM | IEEE80211_HW_BEACON_FILTER | IEEE80211_HW_SUPPORTS_PS | IEEE80211_HW_SUPPORTS_UAPSD | diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 2879c8ef557..00502b1a9e3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -560,7 +560,6 @@ enum mac80211_rx_flags { * @signal: signal strength when receiving this frame, either in dBm, in dB or * unspecified depending on the hardware capabilities flags * @IEEE80211_HW_SIGNAL_* - * @noise: noise when receiving this frame, in dBm (DEPRECATED). * @antenna: antenna used * @rate_idx: index of data rate into band's supported rates or MCS index if * HT rates are use (RX_FLAG_HT) @@ -571,7 +570,6 @@ struct ieee80211_rx_status { enum ieee80211_band band; int freq; int signal; - int noise __deprecated; int antenna; int rate_idx; int flag; @@ -934,10 +932,6 @@ enum ieee80211_tkip_key_type { * one milliwatt. This is the preferred method since it is standardized * between different devices. @max_signal does not need to be set. * - * @IEEE80211_HW_NOISE_DBM: - * Hardware can provide noise (radio interference) values in units dBm, - * decibel difference from one milliwatt. - * * @IEEE80211_HW_SPECTRUM_MGMT: * Hardware supports spectrum management defined in 802.11h * Measurement, Channel Switch, Quieting, TPC @@ -1001,7 +995,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_2GHZ_SHORT_PREAMBLE_INCAPABLE = 1<<4, IEEE80211_HW_SIGNAL_UNSPEC = 1<<5, IEEE80211_HW_SIGNAL_DBM = 1<<6, - IEEE80211_HW_NOISE_DBM = 1<<7, + /* use this hole */ IEEE80211_HW_SPECTRUM_MGMT = 1<<8, IEEE80211_HW_AMPDU_AGGREGATION = 1<<9, IEEE80211_HW_SUPPORTS_PS = 1<<10, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 8ee7db19326..e4f325f68fd 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -80,8 +80,6 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local, len += 8; if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM) len += 1; - if (local->hw.flags & IEEE80211_HW_NOISE_DBM) - len += 1; if (len & 1) /* padding for RX_FLAGS if necessary */ len++; -- cgit v1.2.3-70-g09d2 From 767dd03369ac18af58efdef0383d6eb986eab426 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 28 Apr 2010 19:14:43 +0000 Subject: net: speedup sock_recv_ts_and_drops() sock_recv_ts_and_drops() is fat and slow (~ 4% of cpu time on some profiles) We can test all socket flags at once to make fast path fast again. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 19 ++++++++++++++++++- net/socket.c | 4 ++-- 2 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index d361c7769fe..e1777db5b9a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1635,7 +1635,24 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) sk->sk_stamp = kt; } -extern void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); +extern void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb); + +static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb) +{ +#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL) | \ + (1UL << SOCK_RCVTSTAMP) | \ + (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE) | \ + (1UL << SOCK_TIMESTAMPING_SOFTWARE) | \ + (1UL << SOCK_TIMESTAMPING_RAW_HARDWARE) | \ + (1UL << SOCK_TIMESTAMPING_SYS_HARDWARE)) + + if (sk->sk_flags & FLAGS_TS_OR_DROPS) + __sock_recv_ts_and_drops(msg, sk, skb); + else + sk->sk_stamp = skb->tstamp; +} /** * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped diff --git a/net/socket.c b/net/socket.c index 9822081eab3..cb7c1f6c0d6 100644 --- a/net/socket.c +++ b/net/socket.c @@ -655,13 +655,13 @@ inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff sizeof(__u32), &skb->dropcount); } -void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, +void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); } -EXPORT_SYMBOL_GPL(sock_recv_ts_and_drops); +EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t size, int flags) -- cgit v1.2.3-70-g09d2 From 52688d6ec977e69b164e0bd3de51d43cf6d4b7b3 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Fri, 30 Apr 2010 21:42:44 -0400 Subject: sctp: discard ABORT chunk with zero verification tag in COOKIE-WAIT state In current implementation if ABORT chunk is received with T flag is set and zero verification tag in COOKIE-WAIT state, the ABORT chunk will be always accepted. This is because in COOKIE-WAIT state, the endpoint does not know the peer's verification tag, and it's zero in the endpoint. Signed-off-by: Wei Yongjun Signed-off-by: Vlad Yasevich --- include/net/sctp/sm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 851c813adb3..273a8bb683e 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -437,7 +437,7 @@ sctp_vtag_verify_either(const struct sctp_chunk *chunk, */ if ((!sctp_test_T_bit(chunk) && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag)) || - (sctp_test_T_bit(chunk) && + (sctp_test_T_bit(chunk) && asoc->c.peer_vtag && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.peer_vtag))) { return 1; } -- cgit v1.2.3-70-g09d2 From ae19c54866450f6c6f79223ca7d37965859a54e1 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 30 Apr 2010 22:41:09 -0400 Subject: sctp: remove 'resent' bit from the chunk The 'resent' bit is used to make sure that we don't update rto estimate based on retransmitted chunks. However, we already have the 'rto_pending' bit that we test when need to update rto, so 'resent' bit is just extra. Additionally, we currently have a bug in that we always set a 'resent' bit and thus rto estimate is only updated by Heartbeats. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 3 +-- net/sctp/output.c | 25 +++++++++---------------- net/sctp/outqueue.c | 1 - net/sctp/sm_make_chunk.c | 1 - 4 files changed, 10 insertions(+), 20 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index ff301774471..03deffb1886 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -757,7 +757,6 @@ struct sctp_chunk { #define SCTP_NEED_FRTX 0x1 #define SCTP_DONT_FRTX 0x2 __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ - resent:1, /* Has this chunk ever been resent. */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ singleton:1, /* Only chunk in the packet? */ @@ -1065,7 +1064,7 @@ void sctp_transport_route(struct sctp_transport *, union sctp_addr *, struct sctp_sock *); void sctp_transport_pmtu(struct sctp_transport *); void sctp_transport_free(struct sctp_transport *); -void sctp_transport_reset_timers(struct sctp_transport *, int); +void sctp_transport_reset_timers(struct sctp_transport *); void sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); diff --git a/net/sctp/output.c b/net/sctp/output.c index fad261d41ec..35e49b9df4e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -429,24 +429,17 @@ int sctp_packet_transmit(struct sctp_packet *packet) list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) { list_del_init(&chunk->list); if (sctp_chunk_is_data(chunk)) { + /* 6.3.1 C4) When data is in flight and when allowed + * by rule C5, a new RTT measurement MUST be made each + * round trip. Furthermore, new RTT measurements + * SHOULD be made no more than once per round-trip + * for a given destination transport address. + */ - if (!chunk->resent) { - - /* 6.3.1 C4) When data is in flight and when allowed - * by rule C5, a new RTT measurement MUST be made each - * round trip. Furthermore, new RTT measurements - * SHOULD be made no more than once per round-trip - * for a given destination transport address. - */ - - if (!tp->rto_pending) { - chunk->rtt_in_progress = 1; - tp->rto_pending = 1; - } + if (!tp->rto_pending) { + chunk->rtt_in_progress = 1; + tp->rto_pending = 1; } - - chunk->resent = 1; - has_data = 1; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index a4fe7dee76e..4e551ba8998 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1405,7 +1405,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, * instance). */ if (!tchunk->tsn_gap_acked && - !tchunk->resent && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 33aed1c6cbd..24effdf471e 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1205,7 +1205,6 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, INIT_LIST_HEAD(&retval->list); retval->skb = skb; retval->asoc = (struct sctp_association *)asoc; - retval->resent = 0; retval->has_tsn = 0; retval->has_ssn = 0; retval->rtt_in_progress = 0; -- cgit v1.2.3-70-g09d2 From c0058a35aacc79406e867ec33c5cb75624fd5860 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 30 Apr 2010 22:41:09 -0400 Subject: sctp: Save some room in the sctp_transport by using bitfields Saves some room in the sctp_transport structure. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 49 +++++++++++++++++++++++++--------------------- 1 file changed, 27 insertions(+), 22 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 03deffb1886..9072dd67d8a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -877,7 +877,33 @@ struct sctp_transport { /* Reference counting. */ atomic_t refcnt; - int dead; + int dead:1, + /* RTO-Pending : A flag used to track if one of the DATA + * chunks sent to this address is currently being + * used to compute a RTT. If this flag is 0, + * the next DATA chunk sent to this destination + * should be used to compute a RTT and this flag + * should be set. Every time the RTT + * calculation completes (i.e. the DATA chunk + * is SACK'd) clear this flag. + */ + rto_pending:1, + + /* + * hb_sent : a flag that signals that we have a pending + * heartbeat. + */ + hb_sent:1, + + /* Flag to track the current fast recovery state */ + fast_recovery:1, + + /* Is the Path MTU update pending on this tranport */ + pmtu_pending:1, + + /* Is this structure kfree()able? */ + malloced:1; + /* This is the peer's IP address and port. */ union sctp_addr ipaddr; @@ -907,22 +933,6 @@ struct sctp_transport { /* SRTT : The current smoothed round trip time. */ __u32 srtt; - /* RTO-Pending : A flag used to track if one of the DATA - * chunks sent to this address is currently being - * used to compute a RTT. If this flag is 0, - * the next DATA chunk sent to this destination - * should be used to compute a RTT and this flag - * should be set. Every time the RTT - * calculation completes (i.e. the DATA chunk - * is SACK'd) clear this flag. - * hb_sent : a flag that signals that we have a pending heartbeat. - */ - __u8 rto_pending; - __u8 hb_sent; - - /* Flag to track the current fast recovery state */ - __u8 fast_recovery; - /* * These are the congestion stats. */ @@ -975,9 +985,6 @@ struct sctp_transport { */ __u16 pathmaxrxt; - /* is the Path MTU update pending on this tranport */ - __u8 pmtu_pending; - /* PMTU : The current known path MTU. */ __u32 pathmtu; @@ -1021,8 +1028,6 @@ struct sctp_transport { /* This is the list of transports that have chunks to send. */ struct list_head send_ready; - int malloced; /* Is this structure kfree()able? */ - /* State information saved for SFR_CACC algorithm. The key * idea in SFR_CACC is to maintain state at the sender on a * per-destination basis when a changeover happens. -- cgit v1.2.3-70-g09d2 From b2cf9b6bd93af1cc047d3356f1c6cc9367fe3731 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 30 Apr 2010 22:41:10 -0400 Subject: sctp: update transport initializations Right now, sctp transports are not fully initialized and when adding any new fields, they have to be explicitely initialized. This is prone to mistakes. So we switch to calling kzalloc() which makes things much simpler. Signed-off-by: Vlad Yasevich --- include/net/sctp/sctp.h | 2 +- net/sctp/associola.c | 3 --- net/sctp/endpointola.c | 2 -- net/sctp/transport.c | 25 ------------------------- 4 files changed, 1 insertion(+), 31 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 59151557406..289241d31cc 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -546,7 +546,7 @@ for (pos = chunk->subh.fwdtsn_hdr->skip;\ #define WORD_ROUND(s) (((s)+3)&~3) /* Make a new instance of type. */ -#define t_new(type, flags) (type *)kmalloc(sizeof(type), flags) +#define t_new(type, flags) (type *)kzalloc(sizeof(type), flags) /* Compare two timevals. */ #define tv_lt(s, t) \ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index fab9cb2783a..37753cd48be 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -87,9 +87,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a /* Retrieve the SCTP per socket area. */ sp = sctp_sk((struct sock *)sk); - /* Init all variables to a known value. */ - memset(asoc, 0, sizeof(struct sctp_association)); - /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; sctp_endpoint_hold(asoc->ep); diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 905fda582b9..2f8763bae9e 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -70,8 +70,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, struct sctp_shared_key *null_key; int err; - memset(ep, 0, sizeof(struct sctp_endpoint)); - ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp); if (!ep->digest) return NULL; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 0ebb97fc98e..854228bf3f3 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -64,9 +64,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, /* Copy in the address. */ peer->ipaddr = *addr; peer->af_specific = sctp_get_af_specific(addr->sa.sa_family); - peer->asoc = NULL; - - peer->dst = NULL; memset(&peer->saddr, 0, sizeof(union sctp_addr)); /* From 6.3.1 RTO Calculation: @@ -76,34 +73,21 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, * parameter 'RTO.Initial'. */ peer->rto = msecs_to_jiffies(sctp_rto_initial); - peer->rtt = 0; - peer->rttvar = 0; - peer->srtt = 0; - peer->rto_pending = 0; - peer->hb_sent = 0; - peer->fast_recovery = 0; peer->last_time_heard = jiffies; peer->last_time_ecne_reduced = jiffies; - peer->init_sent_count = 0; - peer->param_flags = SPP_HB_DISABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; - peer->hbinterval = 0; /* Initialize the default path max_retrans. */ peer->pathmaxrxt = sctp_max_retrans_path; - peer->error_count = 0; INIT_LIST_HEAD(&peer->transmitted); INIT_LIST_HEAD(&peer->send_ready); INIT_LIST_HEAD(&peer->transports); - peer->T3_rtx_timer.expires = 0; - peer->hb_timer.expires = 0; - setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event, (unsigned long)peer); setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event, @@ -113,15 +97,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce)); atomic_set(&peer->refcnt, 1); - peer->dead = 0; - - peer->malloced = 0; - - /* Initialize the state information for SFR-CACC */ - peer->cacc.changeover_active = 0; - peer->cacc.cycling_changeover = 0; - peer->cacc.next_tsn_at_change = 0; - peer->cacc.cacc_saw_newack = 0; return peer; } -- cgit v1.2.3-70-g09d2 From cf9b4812e18aab6f86ff998bd7425a9e823269c3 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 30 Apr 2010 22:41:10 -0400 Subject: sctp: fast recovery algorithm is per association. SCTP fast recovery algorithm really applies per association and impacts all transports. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 12 ++++++------ net/sctp/transport.c | 32 +++++++++++++++++--------------- 2 files changed, 23 insertions(+), 21 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 9072dd67d8a..d463296d9f7 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -895,9 +895,6 @@ struct sctp_transport { */ hb_sent:1, - /* Flag to track the current fast recovery state */ - fast_recovery:1, - /* Is the Path MTU update pending on this tranport */ pmtu_pending:1, @@ -952,9 +949,6 @@ struct sctp_transport { __u32 burst_limited; /* Holds old cwnd when max.burst is applied */ - /* TSN marking the fast recovery exit point */ - __u32 fast_recovery_exit; - /* Destination */ struct dst_entry *dst; /* Source address. */ @@ -1723,6 +1717,12 @@ struct sctp_association { /* Highest TSN that is acknowledged by incoming SACKs. */ __u32 highest_sacked; + /* TSN marking the fast recovery exit point */ + __u32 fast_recovery_exit; + + /* Flag to track the current fast recovery state */ + __u8 fast_recovery; + /* The number of unacknowledged data chunks. Reported through * the SCTP_STATUS sockopt. */ diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 854228bf3f3..fccf4947aff 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -378,15 +378,16 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt) void sctp_transport_raise_cwnd(struct sctp_transport *transport, __u32 sack_ctsn, __u32 bytes_acked) { + struct sctp_association *asoc = transport->asoc; __u32 cwnd, ssthresh, flight_size, pba, pmtu; cwnd = transport->cwnd; flight_size = transport->flight_size; /* See if we need to exit Fast Recovery first */ - if (transport->fast_recovery && - TSN_lte(transport->fast_recovery_exit, sack_ctsn)) - transport->fast_recovery = 0; + if (asoc->fast_recovery && + TSN_lte(asoc->fast_recovery_exit, sack_ctsn)) + asoc->fast_recovery = 0; /* The appropriate cwnd increase algorithm is performed if, and only * if the cumulative TSN whould advanced and the congestion window is @@ -415,7 +416,7 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, * 2) the destination's path MTU. This upper bound protects * against the ACK-Splitting attack outlined in [SAVAGE99]. */ - if (transport->fast_recovery) + if (asoc->fast_recovery) return; if (bytes_acked > pmtu) @@ -466,6 +467,8 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, void sctp_transport_lower_cwnd(struct sctp_transport *transport, sctp_lower_cwnd_t reason) { + struct sctp_association *asoc = transport->asoc; + switch (reason) { case SCTP_LOWER_CWND_T3_RTX: /* RFC 2960 Section 7.2.3, sctpimpguide @@ -476,11 +479,11 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * partial_bytes_acked = 0 */ transport->ssthresh = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); - transport->cwnd = transport->asoc->pathmtu; + 4*asoc->pathmtu); + transport->cwnd = asoc->pathmtu; - /* T3-rtx also clears fast recovery on the transport */ - transport->fast_recovery = 0; + /* T3-rtx also clears fast recovery */ + asoc->fast_recovery = 0; break; case SCTP_LOWER_CWND_FAST_RTX: @@ -496,15 +499,15 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * cwnd = ssthresh * partial_bytes_acked = 0 */ - if (transport->fast_recovery) + if (asoc->fast_recovery) return; /* Mark Fast recovery */ - transport->fast_recovery = 1; - transport->fast_recovery_exit = transport->asoc->next_tsn - 1; + asoc->fast_recovery = 1; + asoc->fast_recovery_exit = asoc->next_tsn - 1; transport->ssthresh = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); + 4*asoc->pathmtu); transport->cwnd = transport->ssthresh; break; @@ -524,7 +527,7 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, if (time_after(jiffies, transport->last_time_ecne_reduced + transport->rtt)) { transport->ssthresh = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); + 4*asoc->pathmtu); transport->cwnd = transport->ssthresh; transport->last_time_ecne_reduced = jiffies; } @@ -540,7 +543,7 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * interval. */ transport->cwnd = max(transport->cwnd/2, - 4*transport->asoc->pathmtu); + 4*asoc->pathmtu); break; } @@ -625,7 +628,6 @@ void sctp_transport_reset(struct sctp_transport *t) t->error_count = 0; t->rto_pending = 0; t->hb_sent = 0; - t->fast_recovery = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; -- cgit v1.2.3-70-g09d2 From 0e3aef8d09a8c11e3fb83cdcb24b5bc7421b3726 Mon Sep 17 00:00:00 2001 From: Vlad Yasevich Date: Fri, 30 Apr 2010 22:41:10 -0400 Subject: sctp: Tag messages that can be Nagle delayed at creation. When we create the sctp_datamsg and fragment the user data, we know exactly if we are sending full segments or not and how they might be bundled. During this time, we can mark messages a Nagle capable or not. This makes the check at transmit time much simpler. Signed-off-by: Vlad Yasevich --- include/net/sctp/structs.h | 8 +++----- net/sctp/chunk.c | 4 ++-- net/sctp/output.c | 2 +- 3 files changed, 6 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d463296d9f7..9d44aef365d 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -643,17 +643,15 @@ struct sctp_pf { struct sctp_datamsg { /* Chunks waiting to be submitted to lower layer. */ struct list_head chunks; - /* Chunks that have been transmitted. */ - size_t msg_size; /* Reference counting. */ atomic_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; /* Did the messenge fail to send? */ int send_error; - char send_failed; - /* Control whether chunks from this message can be abandoned. */ - char can_abandon; + u8 send_failed:1, + can_abandon:1, /* can chunks from this message can be abandoned. */ + can_delay; /* should this message be Nagle delayed */ }; struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 3eab6db59a3..476caaf100e 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -58,9 +58,9 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg) msg->send_failed = 0; msg->send_error = 0; msg->can_abandon = 0; + msg->can_delay = 1; msg->expires_at = 0; INIT_LIST_HEAD(&msg->chunks); - msg->msg_size = 0; } /* Allocate and initialize datamsg. */ @@ -157,7 +157,6 @@ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chu { sctp_datamsg_hold(msg); chunk->msg = msg; - msg->msg_size += chunk->skb->len; } @@ -247,6 +246,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (msg_len >= first_len) { msg_len -= first_len; whole = 1; + msg->can_delay = 0; } /* How many full sized? How many bytes leftover? */ diff --git a/net/sctp/output.c b/net/sctp/output.c index 35e49b9df4e..a646681f5ac 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -674,7 +674,7 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet, * Don't delay large message writes that may have been * fragmeneted into small peices. */ - if ((len < max) && (chunk->msg->msg_size < max)) { + if ((len < max) && chunk->msg->can_delay) { retval = SCTP_XMIT_NAGLE_DELAY; goto finish; } -- cgit v1.2.3-70-g09d2 From 43815482370c510c569fd18edb57afcb0fa8cab6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 Apr 2010 11:01:49 +0000 Subject: net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 13 +++++++++---- drivers/net/tun.c | 21 ++++++++++++--------- include/linux/net.h | 14 +++++++++----- include/net/af_unix.h | 20 +++++++++++--------- include/net/sock.h | 38 +++++++++++++++++++------------------- net/atm/common.c | 22 ++++++++++++++-------- net/core/sock.c | 50 +++++++++++++++++++++++++++++++------------------- net/core/stream.c | 10 +++++++--- net/dccp/output.c | 10 ++++++---- net/iucv/af_iucv.c | 11 +++++++---- net/phonet/pep.c | 8 ++++---- net/phonet/socket.c | 2 +- net/rxrpc/af_rxrpc.c | 10 ++++++---- net/sctp/socket.c | 2 +- net/socket.c | 47 ++++++++++++++++++++++++++++++++++++----------- net/unix/af_unix.c | 17 ++++++++--------- 16 files changed, 181 insertions(+), 114 deletions(-) (limited to 'include/net') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index d97e1fd234b..1c4110df343 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -37,6 +37,7 @@ struct macvtap_queue { struct sock sk; struct socket sock; + struct socket_wq wq; struct macvlan_dev *vlan; struct file *file; unsigned int flags; @@ -242,12 +243,15 @@ static struct rtnl_link_ops macvtap_link_ops __read_mostly = { static void macvtap_sock_write_space(struct sock *sk) { + wait_queue_head_t *wqueue; + if (!sock_writeable(sk) || !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); + wqueue = sk_sleep(sk); + if (wqueue && waitqueue_active(wqueue)) + wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) @@ -272,7 +276,8 @@ static int macvtap_open(struct inode *inode, struct file *file) if (!q) goto out; - init_waitqueue_head(&q->sock.wait); + q->sock.wq = &q->wq; + init_waitqueue_head(&q->wq.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; q->sock.file = file; @@ -308,7 +313,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) goto out; mask = 0; - poll_wait(file, &q->sock.wait, wait); + poll_wait(file, &q->wq.wait, wait); if (!skb_queue_empty(&q->sk.sk_receive_queue)) mask |= POLLIN | POLLRDNORM; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 20a17938c62..e525a6cf558 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -109,7 +109,7 @@ struct tun_struct { struct tap_filter txflt; struct socket socket; - + struct socket_wq wq; #ifdef TUN_DEBUG int debug; #endif @@ -323,7 +323,7 @@ static void tun_net_uninit(struct net_device *dev) /* Inform the methods they need to stop using the dev. */ if (tfile) { - wake_up_all(&tun->socket.wait); + wake_up_all(&tun->wq.wait); if (atomic_dec_and_test(&tfile->count)) __tun_detach(tun); } @@ -398,7 +398,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) /* Notify and wake up reader process */ if (tun->flags & TUN_FASYNC) kill_fasync(&tun->fasync, SIGIO, POLL_IN); - wake_up_interruptible_poll(&tun->socket.wait, POLLIN | + wake_up_interruptible_poll(&tun->wq.wait, POLLIN | POLLRDNORM | POLLRDBAND); return NETDEV_TX_OK; @@ -498,7 +498,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait) DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name); - poll_wait(file, &tun->socket.wait, wait); + poll_wait(file, &tun->wq.wait, wait); if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; @@ -773,7 +773,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name); - add_wait_queue(&tun->socket.wait, &wait); + add_wait_queue(&tun->wq.wait, &wait); while (len) { current->state = TASK_INTERRUPTIBLE; @@ -804,7 +804,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, } current->state = TASK_RUNNING; - remove_wait_queue(&tun->socket.wait, &wait); + remove_wait_queue(&tun->wq.wait, &wait); return ret; } @@ -861,6 +861,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = { static void tun_sock_write_space(struct sock *sk) { struct tun_struct *tun; + wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; @@ -868,8 +869,9 @@ static void tun_sock_write_space(struct sock *sk) if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | + wqueue = sk_sleep(sk); + if (wqueue && waitqueue_active(wqueue)) + wake_up_interruptible_sync_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); tun = tun_sk(sk)->tun; @@ -1039,7 +1041,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!sk) goto err_free_dev; - init_waitqueue_head(&tun->socket.wait); + tun->socket.wq = &tun->wq; + init_waitqueue_head(&tun->wq.wait); tun->socket.ops = &tun_socket_ops; sock_init_data(&tun->socket, sk); sk->sk_write_space = tun_sock_write_space; diff --git a/include/linux/net.h b/include/linux/net.h index 4157b5d42bd..2b4deeeb864 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -59,6 +59,7 @@ typedef enum { #include #include /* For O_CLOEXEC and O_NONBLOCK */ #include +#include struct poll_table_struct; struct pipe_inode_info; @@ -116,6 +117,12 @@ enum sock_shutdown_cmd { SHUT_RDWR = 2, }; +struct socket_wq { + wait_queue_head_t wait; + struct fasync_struct *fasync_list; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) @@ -135,11 +142,8 @@ struct socket { kmemcheck_bitfield_end(type); unsigned long flags; - /* - * Please keep fasync_list & wait fields in the same cache line - */ - struct fasync_struct *fasync_list; - wait_queue_head_t wait; + + struct socket_wq *wq; struct file *file; struct sock *sk; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 1614d78c60e..20725e213ae 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -30,7 +30,7 @@ struct unix_skb_parms { #endif }; -#define UNIXCB(skb) (*(struct unix_skb_parms*)&((skb)->cb)) +#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) #define UNIXCREDS(skb) (&UNIXCB((skb)).creds) #define UNIXSID(skb) (&UNIXCB((skb)).secid) @@ -45,21 +45,23 @@ struct unix_skb_parms { struct unix_sock { /* WARNING: sk has to be the first member */ struct sock sk; - struct unix_address *addr; - struct dentry *dentry; - struct vfsmount *mnt; + struct unix_address *addr; + struct dentry *dentry; + struct vfsmount *mnt; struct mutex readlock; - struct sock *peer; - struct sock *other; + struct sock *peer; + struct sock *other; struct list_head link; - atomic_long_t inflight; - spinlock_t lock; + atomic_long_t inflight; + spinlock_t lock; unsigned int gc_candidate : 1; unsigned int gc_maybe_cycle : 1; - wait_queue_head_t peer_wait; + struct socket_wq peer_wq; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) +#define peer_wait peer_wq.wait + #ifdef CONFIG_SYSCTL extern int unix_sysctl_register(struct net *net); extern void unix_sysctl_unregister(struct net *net); diff --git a/include/net/sock.h b/include/net/sock.h index e1777db5b9a..cc7f91ec972 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -159,7 +159,7 @@ struct sock_common { * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_rcvbuf: size of receive buffer in bytes - * @sk_sleep: sock wait queue + * @sk_wq: sock wait queue and async head * @sk_dst_cache: destination cache * @sk_dst_lock: destination cache lock * @sk_policy: flow policy @@ -257,7 +257,7 @@ struct sock { struct sk_buff *tail; int len; } sk_backlog; - wait_queue_head_t *sk_sleep; + struct socket_wq *sk_wq; struct dst_entry *sk_dst_cache; #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; @@ -1219,7 +1219,7 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) static inline wait_queue_head_t *sk_sleep(struct sock *sk) { - return sk->sk_sleep; + return &sk->sk_wq->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. @@ -1233,14 +1233,14 @@ static inline void sock_orphan(struct sock *sk) write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); - sk->sk_sleep = NULL; + sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - sk->sk_sleep = &parent->wait; + rcu_assign_pointer(sk->sk_wq, parent->wq); parent->sk = sk; sk_set_socket(sk, parent); security_sock_graft(sk, parent); @@ -1392,12 +1392,12 @@ static inline int sk_has_allocations(const struct sock *sk) } /** - * sk_has_sleeper - check if there are any waiting processes - * @sk: socket + * wq_has_sleeper - check if there are any waiting processes + * @sk: struct socket_wq * - * Returns true if socket has waiting processes + * Returns true if socket_wq has waiting processes * - * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory + * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths: @@ -1410,9 +1410,10 @@ static inline int sk_has_allocations(const struct sock *sk) * ... ... * tp->rcv_nxt check sock_def_readable * ... { - * schedule ... - * if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - * wake_up_interruptible(sk_sleep(sk)) + * schedule rcu_read_lock(); + * wq = rcu_dereference(sk->sk_wq); + * if (wq && waitqueue_active(&wq->wait)) + * wake_up_interruptible(&wq->wait) * ... * } * @@ -1421,19 +1422,18 @@ static inline int sk_has_allocations(const struct sock *sk) * could then endup calling schedule and sleep forever if there are no more * data on the socket. * - * The sk_has_sleeper is always called right after a call to read_lock, so we - * can use smp_mb__after_lock barrier. */ -static inline int sk_has_sleeper(struct sock *sk) +static inline bool wq_has_sleeper(struct socket_wq *wq) { + /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier is paired in the sock_poll_wait. */ - smp_mb__after_lock(); - return sk_sleep(sk) && waitqueue_active(sk_sleep(sk)); + smp_mb(); + return wq && waitqueue_active(&wq->wait); } /** @@ -1442,7 +1442,7 @@ static inline int sk_has_sleeper(struct sock *sk) * @wait_address: socket wait queue * @p: poll_table * - * See the comments in the sk_has_sleeper function. + * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) @@ -1453,7 +1453,7 @@ static inline void sock_poll_wait(struct file *filp, * We need to be sure we are in sync with the * socket flags modification. * - * This memory barrier is paired in the sk_has_sleeper. + * This memory barrier is paired in the wq_has_sleeper. */ smp_mb(); } diff --git a/net/atm/common.c b/net/atm/common.c index e3e10e6f862..b43feb1a399 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -90,10 +90,13 @@ static void vcc_sock_destruct(struct sock *sk) static void vcc_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up(sk_sleep(sk)); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up(&wq->wait); + rcu_read_unlock(); } static inline int vcc_writable(struct sock *sk) @@ -106,16 +109,19 @@ static inline int vcc_writable(struct sock *sk) static void vcc_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); if (vcc_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static struct proto vcc_proto = { diff --git a/net/core/sock.c b/net/core/sock.c index 51041759517..94c4affdda9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1211,7 +1211,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); - newsk->sk_sleep = NULL; + newsk->sk_wq = NULL; if (newsk->sk_prot->sockets_allocated) percpu_counter_inc(newsk->sk_prot->sockets_allocated); @@ -1800,41 +1800,53 @@ EXPORT_SYMBOL(sock_no_sendpage); static void sock_def_wakeup(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk_sleep(sk)); - read_unlock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); + rcu_read_unlock(); } static void sock_def_error_report(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_poll(sk_sleep(sk), POLLERR); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_readable(struct sock *sk, int len) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ @@ -1842,7 +1854,7 @@ static void sock_def_write_space(struct sock *sk) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } static void sock_def_destruct(struct sock *sk) @@ -1896,10 +1908,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) if (sock) { sk->sk_type = sock->type; - sk->sk_sleep = &sock->wait; + sk->sk_wq = sock->wq; sock->sk = sk; } else - sk->sk_sleep = NULL; + sk->sk_wq = NULL; spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); diff --git a/net/core/stream.c b/net/core/stream.c index 7b3c3f30b10..cc196f42b8d 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -28,15 +28,19 @@ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; + struct socket_wq *wq; if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_poll(&wq->wait, POLLOUT | POLLWRNORM | POLLWRBAND); - if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) + if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); + rcu_read_unlock(); } } diff --git a/net/dccp/output.c b/net/dccp/output.c index 2d3dcb39851..aadbdb58758 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -195,15 +195,17 @@ EXPORT_SYMBOL_GPL(dccp_sync_mss); void dccp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /** diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 9636b7d27b4..8be324fe08b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -305,11 +305,14 @@ static inline int iucv_below_msglim(struct sock *sk) */ static void iucv_sock_wake_msglim(struct sock *sk) { - read_lock(&sk->sk_callback_lock); - if (sk_has_sleeper(sk)) - wake_up_interruptible_all(sk_sleep(sk)); + struct socket_wq *wq; + + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_all(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* Timers */ diff --git a/net/phonet/pep.c b/net/phonet/pep.c index e2a95762abd..af4d38bc3b2 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -664,12 +664,12 @@ static int pep_wait_connreq(struct sock *sk, int noblock) if (signal_pending(tsk)) return sock_intr_errno(timeo); - prepare_to_wait_exclusive(&sk->sk_socket->wait, &wait, + prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); - finish_wait(&sk->sk_socket->wait, &wait); + finish_wait(sk_sleep(sk), &wait); } return 0; @@ -910,10 +910,10 @@ disabled: goto out; } - prepare_to_wait(&sk->sk_socket->wait, &wait, + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits)); - finish_wait(&sk->sk_socket->wait, &wait); + finish_wait(sk_sleep(sk), &wait); if (sk->sk_state != TCP_ESTABLISHED) goto disabled; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index c785bfd0744..6e9848bf037 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -265,7 +265,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock, struct pep_sock *pn = pep_sk(sk); unsigned int mask = 0; - poll_wait(file, &sock->wait, wait); + poll_wait(file, sk_sleep(sk), wait); switch (sk->sk_state) { case TCP_LISTEN: diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index c432d76f415..0b9bb2085ce 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -62,13 +62,15 @@ static inline int rxrpc_writable(struct sock *sk) static void rxrpc_write_space(struct sock *sk) { _enter("%p", sk); - read_lock(&sk->sk_callback_lock); + rcu_read_lock(); if (rxrpc_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible(sk_sleep(sk)); + struct socket_wq *wq = rcu_dereference(sk->sk_wq); + + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13d8229f3a9..d54700af927 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6065,7 +6065,7 @@ static void __sctp_write_space(struct sctp_association *asoc) * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ - if (sock->fasync_list && + if (sock->wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); diff --git a/net/socket.c b/net/socket.c index cb7c1f6c0d6..dae8c6b84a0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -252,9 +252,14 @@ static struct inode *sock_alloc_inode(struct super_block *sb) ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; - init_waitqueue_head(&ei->socket.wait); + ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL); + if (!ei->socket.wq) { + kmem_cache_free(sock_inode_cachep, ei); + return NULL; + } + init_waitqueue_head(&ei->socket.wq->wait); + ei->socket.wq->fasync_list = NULL; - ei->socket.fasync_list = NULL; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; @@ -264,10 +269,21 @@ static struct inode *sock_alloc_inode(struct super_block *sb) return &ei->vfs_inode; } + +static void wq_free_rcu(struct rcu_head *head) +{ + struct socket_wq *wq = container_of(head, struct socket_wq, rcu); + + kfree(wq); +} + static void sock_destroy_inode(struct inode *inode) { - kmem_cache_free(sock_inode_cachep, - container_of(inode, struct socket_alloc, vfs_inode)); + struct socket_alloc *ei; + + ei = container_of(inode, struct socket_alloc, vfs_inode); + call_rcu(&ei->socket.wq->rcu, wq_free_rcu); + kmem_cache_free(sock_inode_cachep, ei); } static void init_once(void *foo) @@ -513,7 +529,7 @@ void sock_release(struct socket *sock) module_put(owner); } - if (sock->fasync_list) + if (sock->wq->fasync_list) printk(KERN_ERR "sock_release: fasync list not empty!\n"); percpu_sub(sockets_in_use, 1); @@ -1080,9 +1096,9 @@ static int sock_fasync(int fd, struct file *filp, int on) lock_sock(sk); - fasync_helper(fd, filp, on, &sock->fasync_list); + fasync_helper(fd, filp, on, &sock->wq->fasync_list); - if (!sock->fasync_list) + if (!sock->wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); @@ -1091,12 +1107,20 @@ static int sock_fasync(int fd, struct file *filp, int on) return 0; } -/* This function may be called only under socket lock or callback_lock */ +/* This function may be called only under socket lock or callback_lock or rcu_lock */ int sock_wake_async(struct socket *sock, int how, int band) { - if (!sock || !sock->fasync_list) + struct socket_wq *wq; + + if (!sock) return -1; + rcu_read_lock(); + wq = rcu_dereference(sock->wq); + if (!wq || !wq->fasync_list) { + rcu_read_unlock(); + return -1; + } switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags)) @@ -1108,11 +1132,12 @@ int sock_wake_async(struct socket *sock, int how, int band) /* fall through */ case SOCK_WAKE_IO: call_kill: - kill_fasync(&sock->fasync_list, SIGIO, band); + kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: - kill_fasync(&sock->fasync_list, SIGURG, band); + kill_fasync(&wq->fasync_list, SIGURG, band); } + rcu_read_unlock(); return 0; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 87c0360eaa2..fef2cc5e9d2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -313,13 +313,16 @@ static inline int unix_writable(struct sock *sk) static void unix_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; + + rcu_read_lock(); if (unix_writable(sk)) { - if (sk_has_sleeper(sk)) - wake_up_interruptible_sync(sk_sleep(sk)); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible_sync(&wq->wait); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /* When dgram socket disconnects (or changes its peer), we clear its receive @@ -406,9 +409,7 @@ static int unix_release_sock(struct sock *sk, int embrion) skpair->sk_err = ECONNRESET; unix_state_unlock(skpair); skpair->sk_state_change(skpair); - read_lock(&skpair->sk_callback_lock); sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP); - read_unlock(&skpair->sk_callback_lock); } sock_put(skpair); /* It may now die */ unix_peer(sk) = NULL; @@ -1142,7 +1143,7 @@ restart: newsk->sk_peercred.pid = task_tgid_vnr(current); current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid); newu = unix_sk(newsk); - newsk->sk_sleep = &newu->peer_wait; + newsk->sk_wq = &newu->peer_wq; otheru = unix_sk(other); /* copy address information from listening to new sock*/ @@ -1931,12 +1932,10 @@ static int unix_shutdown(struct socket *sock, int mode) other->sk_shutdown |= peer_mode; unix_state_unlock(other); other->sk_state_change(other); - read_lock(&other->sk_callback_lock); if (peer_mode == SHUTDOWN_MASK) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); else if (peer_mode & RCV_SHUTDOWN) sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); - read_unlock(&other->sk_callback_lock); } if (other) sock_put(other); -- cgit v1.2.3-70-g09d2 From ac8dd506e40ee2c7fcc61654a44c32555a0a8d6c Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 May 2010 09:44:02 +0200 Subject: mac80211: fix BSS info reconfiguration When reconfiguring an interface due to a previous hardware restart, mac80211 will currently include the new IBSS flag on non-IBSS interfaces which may confuse drivers. Instead of doing the ~0 trick, simply spell out which things are going to be reconfigured. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 2 ++ net/mac80211/util.c | 25 ++++++++++++++++++++----- 2 files changed, 22 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 00502b1a9e3..0528615ac82 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -160,6 +160,8 @@ enum ieee80211_bss_change { BSS_CHANGED_BEACON_ENABLED = 1<<9, BSS_CHANGED_CQM = 1<<10, BSS_CHANGED_IBSS = 1<<11, + + /* when adding here, make sure to change ieee80211_reconfig */ }; /** diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 2b75b4fb68f..5b79d552780 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1160,18 +1160,33 @@ int ieee80211_reconfig(struct ieee80211_local *local) /* Finally also reconfigure all the BSS information */ list_for_each_entry(sdata, &local->interfaces, list) { - u32 changed = ~0; + u32 changed; + if (!ieee80211_sdata_running(sdata)) continue; + + /* common change flags for all interface types */ + changed = BSS_CHANGED_ERP_CTS_PROT | + BSS_CHANGED_ERP_PREAMBLE | + BSS_CHANGED_ERP_SLOT | + BSS_CHANGED_HT | + BSS_CHANGED_BASIC_RATES | + BSS_CHANGED_BEACON_INT | + BSS_CHANGED_BSSID | + BSS_CHANGED_CQM; + switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: - /* disable beacon change bits */ - changed &= ~(BSS_CHANGED_BEACON | - BSS_CHANGED_BEACON_ENABLED); - /* fall through */ + changed |= BSS_CHANGED_ASSOC; + ieee80211_bss_info_change_notify(sdata, changed); + break; case NL80211_IFTYPE_ADHOC: + changed |= BSS_CHANGED_IBSS; + /* fall through */ case NL80211_IFTYPE_AP: case NL80211_IFTYPE_MESH_POINT: + changed |= BSS_CHANGED_BEACON | + BSS_CHANGED_BEACON_ENABLED; ieee80211_bss_info_change_notify(sdata, changed); break; case NL80211_IFTYPE_WDS: -- cgit v1.2.3-70-g09d2 From f444de05d20e27cdd960c13fcbcfca3099f03143 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 May 2010 15:25:02 +0200 Subject: cfg80211/mac80211: better channel handling Currently (all tested with hwsim) you can do stupid things like setting up an AP on a certain channel, then adding another virtual interface and making that associate on another channel -- this will make the beaconing to move channel but obviously without the necessary IEs data update. In order to improve this situation, first make the configuration APIs (cfg80211 and nl80211) aware of multi-channel operation -- we'll eventually need that in the future anyway. There's one userland API change and one API addition. The API change is that now SET_WIPHY must be called with virtual interface index rather than only wiphy index in order to take effect for that interface -- luckily all current users (hostapd) do that. For monitor interfaces, the old setting is preserved, but monitors are always slaved to other devices anyway so no guarantees. The second userland API change is the introduction of a per virtual interface SET_CHANNEL command, that hostapd should use going forward to make it easier to understand what's going on (it can automatically detect a kernel with this command). Other than mac80211, no existing cfg80211 drivers are affected by this change because they only allow a single virtual interface. mac80211, however, now needs to be aware that the channel settings are per interface now, and needs to disallow (for now) real multi-channel operation, which is another important part of this patch. One of the immediate benefits is that you can now start hostapd to operate on a hardware that already has a connection on another virtual interface, as long as you specify the same channel. Note that two things are left unhandled (this is an improvement -- not a complete fix): * different HT/no-HT modes currently you could start an HT AP and then connect to a non-HT network on the same channel which would configure the hardware for no HT; that can be fixed fairly easily * CSA An AP we're connected to on a virtual interface might indicate switching channels, and in that case we would follow it, regardless of how many other interfaces are operating; this requires more effort to fix but is pretty rare after all Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/libertas/cfg.c | 1 + drivers/net/wireless/orinoco/cfg.c | 1 + drivers/net/wireless/rndis_wlan.c | 4 +- include/linux/nl80211.h | 13 +++ include/net/cfg80211.h | 11 ++- net/mac80211/Makefile | 3 +- net/mac80211/cfg.c | 41 +++++++++ net/mac80211/chan.c | 57 ++++++++++++ net/mac80211/ieee80211_i.h | 11 +++ net/wireless/chan.c | 56 ++++-------- net/wireless/core.h | 12 +-- net/wireless/ibss.c | 5 -- net/wireless/nl80211.c | 171 ++++++++++++++++++++++++++++-------- net/wireless/sme.c | 5 -- net/wireless/wext-compat.c | 15 ++-- net/wireless/wext-sme.c | 2 +- 16 files changed, 300 insertions(+), 108 deletions(-) create mode 100644 net/mac80211/chan.c (limited to 'include/net') diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index 82ebe1461a7..ea9d0b2ea0d 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -78,6 +78,7 @@ static const u32 cipher_suites[] = { static int lbs_cfg_set_channel(struct wiphy *wiphy, + struct net_device *netdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type) { diff --git a/drivers/net/wireless/orinoco/cfg.c b/drivers/net/wireless/orinoco/cfg.c index 81d228de9e5..8c4169c227a 100644 --- a/drivers/net/wireless/orinoco/cfg.c +++ b/drivers/net/wireless/orinoco/cfg.c @@ -159,6 +159,7 @@ static int orinoco_scan(struct wiphy *wiphy, struct net_device *dev, } static int orinoco_set_channel(struct wiphy *wiphy, + struct net_device *netdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type) { diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index aceb95ef727..99d4f0de77c 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -534,7 +534,7 @@ static int rndis_join_ibss(struct wiphy *wiphy, struct net_device *dev, static int rndis_leave_ibss(struct wiphy *wiphy, struct net_device *dev); -static int rndis_set_channel(struct wiphy *wiphy, +static int rndis_set_channel(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type); static int rndis_add_key(struct wiphy *wiphy, struct net_device *netdev, @@ -2290,7 +2290,7 @@ static int rndis_leave_ibss(struct wiphy *wiphy, struct net_device *dev) return deauthenticate(usbdev); } -static int rndis_set_channel(struct wiphy *wiphy, +static int rndis_set_channel(struct wiphy *wiphy, struct net_device *netdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type) { struct rndis_wlan_private *priv = wiphy_priv(wiphy); diff --git a/include/linux/nl80211.h b/include/linux/nl80211.h index f8750f9a65b..b7c77f9712f 100644 --- a/include/linux/nl80211.h +++ b/include/linux/nl80211.h @@ -52,6 +52,8 @@ * %NL80211_ATTR_WIPHY_CHANNEL_TYPE, %NL80211_ATTR_WIPHY_RETRY_SHORT, * %NL80211_ATTR_WIPHY_RETRY_LONG, %NL80211_ATTR_WIPHY_FRAG_THRESHOLD, * and/or %NL80211_ATTR_WIPHY_RTS_THRESHOLD. + * However, for setting the channel, see %NL80211_CMD_SET_CHANNEL + * instead, the support here is for backward compatibility only. * @NL80211_CMD_NEW_WIPHY: Newly created wiphy, response to get request * or rename notification. Has attributes %NL80211_ATTR_WIPHY and * %NL80211_ATTR_WIPHY_NAME. @@ -329,6 +331,15 @@ * @NL80211_CMD_NOTIFY_CQM: Connection quality monitor notification. This * command is used as an event to indicate the that a trigger level was * reached. + * @NL80211_CMD_SET_CHANNEL: Set the channel (using %NL80211_ATTR_WIPHY_FREQ + * and %NL80211_ATTR_WIPHY_CHANNEL_TYPE) the given interface (identifed + * by %NL80211_ATTR_IFINDEX) shall operate on. + * In case multiple channels are supported by the device, the mechanism + * with which it switches channels is implementation-defined. + * When a monitor interface is given, it can only switch channel while + * no other interfaces are operating to avoid disturbing the operation + * of any other interfaces, and other interfaces will again take + * precedence when they are used. * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use @@ -428,6 +439,8 @@ enum nl80211_commands { NL80211_CMD_SET_CQM, NL80211_CMD_NOTIFY_CQM, + NL80211_CMD_SET_CHANNEL, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7d10c0182f5..b44a2e5321a 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -966,7 +966,11 @@ struct cfg80211_pmksa { * * @set_txq_params: Set TX queue parameters * - * @set_channel: Set channel + * @set_channel: Set channel for a given wireless interface. Some devices + * may support multi-channel operation (by channel hopping) so cfg80211 + * doesn't verify much. Note, however, that the passed netdev may be + * %NULL as well if the user requested changing the channel for the + * device itself, or for a monitor interface. * * @scan: Request to do a scan. If returning zero, the scan request is given * the driver, and will be valid until passed to cfg80211_scan_done(). @@ -1095,7 +1099,7 @@ struct cfg80211_ops { int (*set_txq_params)(struct wiphy *wiphy, struct ieee80211_txq_params *params); - int (*set_channel)(struct wiphy *wiphy, + int (*set_channel)(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type); @@ -1461,6 +1465,8 @@ struct cfg80211_cached_keys; * @list: (private) Used to collect the interfaces * @netdev: (private) Used to reference back to the netdev * @current_bss: (private) Used by the internal configuration code + * @channel: (private) Used by the internal configuration code to track + * user-set AP, monitor and WDS channels for wireless extensions * @bssid: (private) Used by the internal configuration code * @ssid: (private) Used by the internal configuration code * @ssid_len: (private) Used by the internal configuration code @@ -1507,6 +1513,7 @@ struct wireless_dev { struct cfg80211_internal_bss *authtry_bsses[MAX_AUTH_BSSES]; struct cfg80211_internal_bss *auth_bsses[MAX_AUTH_BSSES]; struct cfg80211_internal_bss *current_bss; /* associated / joined */ + struct ieee80211_channel *channel; bool ps; int ps_timeout; diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile index 04420291e7a..84b48ba8a77 100644 --- a/net/mac80211/Makefile +++ b/net/mac80211/Makefile @@ -23,7 +23,8 @@ mac80211-y := \ key.o \ util.o \ wme.o \ - event.o + event.o \ + chan.o mac80211-$(CONFIG_MAC80211_LEDS) += led.o mac80211-$(CONFIG_MAC80211_DEBUGFS) += \ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index b575a506621..414b7dd7d7f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1161,11 +1161,24 @@ static int ieee80211_set_txq_params(struct wiphy *wiphy, } static int ieee80211_set_channel(struct wiphy *wiphy, + struct net_device *netdev, struct ieee80211_channel *chan, enum nl80211_channel_type channel_type) { struct ieee80211_local *local = wiphy_priv(wiphy); + switch (ieee80211_get_channel_mode(local, NULL)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (local->oper_channel == chan && + local->oper_channel_type == channel_type) + return 0; + return -EBUSY; + case CHAN_MODE_UNDEFINED: + break; + } + local->oper_channel = chan; local->oper_channel_type = channel_type; @@ -1213,6 +1226,20 @@ static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + switch (ieee80211_get_channel_mode(local, sdata)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (local->oper_channel == req->bss->channel) + break; + return -EBUSY; + case CHAN_MODE_UNDEFINED: + break; + } + return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } @@ -1235,8 +1262,22 @@ static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { + struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + switch (ieee80211_get_channel_mode(local, sdata)) { + case CHAN_MODE_HOPPING: + return -EBUSY; + case CHAN_MODE_FIXED: + if (!params->channel_fixed) + return -EBUSY; + if (local->oper_channel == params->channel) + break; + return -EBUSY; + case CHAN_MODE_UNDEFINED: + break; + } + return ieee80211_ibss_join(sdata, params); } diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c new file mode 100644 index 00000000000..08f3832661a --- /dev/null +++ b/net/mac80211/chan.c @@ -0,0 +1,57 @@ +/* + * mac80211 - channel management + */ + +#include "ieee80211_i.h" + +enum ieee80211_chan_mode +__ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore) +{ + struct ieee80211_sub_if_data *sdata; + + WARN_ON(!mutex_is_locked(&local->iflist_mtx)); + + list_for_each_entry(sdata, &local->interfaces, list) { + if (sdata == ignore) + continue; + + if (!ieee80211_sdata_running(sdata)) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_MONITOR) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !sdata->u.mgd.associated) + continue; + + if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { + if (!sdata->u.ibss.ssid_len) + continue; + if (!sdata->u.ibss.fixed_channel) + return CHAN_MODE_HOPPING; + } + + if (sdata->vif.type == NL80211_IFTYPE_AP && + !sdata->u.ap.beacon) + continue; + + return CHAN_MODE_FIXED; + } + + return CHAN_MODE_UNDEFINED; +} + +enum ieee80211_chan_mode +ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore) +{ + enum ieee80211_chan_mode mode; + + mutex_lock(&local->iflist_mtx); + mode = __ieee80211_get_channel_mode(local, ignore); + mutex_unlock(&local->iflist_mtx); + + return mode; +} diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c8077a3647c..359edff3147 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1229,6 +1229,17 @@ int ieee80211_wk_remain_on_channel(struct ieee80211_sub_if_data *sdata, int ieee80211_wk_cancel_remain_on_channel( struct ieee80211_sub_if_data *sdata, u64 cookie); +/* channel management */ +enum ieee80211_chan_mode { + CHAN_MODE_UNDEFINED, + CHAN_MODE_HOPPING, + CHAN_MODE_FIXED, +}; + +enum ieee80211_chan_mode +ieee80211_get_channel_mode(struct ieee80211_local *local, + struct ieee80211_sub_if_data *ignore); + #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline #else diff --git a/net/wireless/chan.c b/net/wireless/chan.c index bf1737fc9a7..d92d088026b 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -9,38 +9,6 @@ #include #include "core.h" -struct ieee80211_channel * -rdev_fixed_channel(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev) -{ - struct wireless_dev *wdev; - struct ieee80211_channel *result = NULL; - - WARN_ON(!mutex_is_locked(&rdev->devlist_mtx)); - - list_for_each_entry(wdev, &rdev->netdev_list, list) { - if (wdev == for_wdev) - continue; - - /* - * Lock manually to tell lockdep about allowed - * nesting here if for_wdev->mtx is held already. - * This is ok as it's all under the rdev devlist - * mutex and as such can only be done once at any - * given time. - */ - mutex_lock_nested(&wdev->mtx, SINGLE_DEPTH_NESTING); - if (wdev->current_bss) - result = wdev->current_bss->pub.channel; - wdev_unlock(wdev); - - if (result) - break; - } - - return result; -} - struct ieee80211_channel * rdev_freq_to_chan(struct cfg80211_registered_device *rdev, int freq, enum nl80211_channel_type channel_type) @@ -75,15 +43,22 @@ rdev_freq_to_chan(struct cfg80211_registered_device *rdev, return chan; } -int rdev_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev, - int freq, enum nl80211_channel_type channel_type) +int cfg80211_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type) { struct ieee80211_channel *chan; int result; - if (rdev_fixed_channel(rdev, for_wdev)) - return -EBUSY; + if (wdev->iftype == NL80211_IFTYPE_MONITOR) + wdev = NULL; + + if (wdev) { + ASSERT_WDEV_LOCK(wdev); + + if (!netif_running(wdev->netdev)) + return -ENETDOWN; + } if (!rdev->ops->set_channel) return -EOPNOTSUPP; @@ -92,11 +67,14 @@ int rdev_set_freq(struct cfg80211_registered_device *rdev, if (!chan) return -EINVAL; - result = rdev->ops->set_channel(&rdev->wiphy, chan, channel_type); + result = rdev->ops->set_channel(&rdev->wiphy, + wdev ? wdev->netdev : NULL, + chan, channel_type); if (result) return result; - rdev->channel = chan; + if (wdev) + wdev->channel = chan; return 0; } diff --git a/net/wireless/core.h b/net/wireless/core.h index b2234b436ea..ae930acf75e 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -70,9 +70,6 @@ struct cfg80211_registered_device { struct work_struct conn_work; struct work_struct event_work; - /* current channel */ - struct ieee80211_channel *channel; - /* must be last because of the way we do wiphy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wiphy wiphy __attribute__((__aligned__(NETDEV_ALIGN))); @@ -387,15 +384,12 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, u32 *flags, struct vif_params *params); void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev); -struct ieee80211_channel * -rdev_fixed_channel(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev); struct ieee80211_channel * rdev_freq_to_chan(struct cfg80211_registered_device *rdev, int freq, enum nl80211_channel_type channel_type); -int rdev_set_freq(struct cfg80211_registered_device *rdev, - struct wireless_dev *for_wdev, - int freq, enum nl80211_channel_type channel_type); +int cfg80211_set_freq(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, int freq, + enum nl80211_channel_type channel_type); u16 cfg80211_calculate_bitrate(struct rate_info *rate); diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index 6ef5a491fb4..9825317e653 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -80,15 +80,10 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, struct cfg80211_cached_keys *connkeys) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct ieee80211_channel *chan; int err; ASSERT_WDEV_LOCK(wdev); - chan = rdev_fixed_channel(rdev, wdev); - if (chan && chan != params->channel) - return -EBUSY; - if (wdev->ssid_len) return -EALREADY; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c27bef8e0c1..ec1b4a896c6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -588,6 +588,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, i++; NLA_PUT_U32(msg, i, NL80211_CMD_SET_WIPHY_NETNS); } + CMD(set_channel, SET_CHANNEL); #undef CMD @@ -688,10 +689,90 @@ static int parse_txq_params(struct nlattr *tb[], return 0; } +static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev) +{ + /* + * You can only set the channel explicitly for AP, mesh + * and WDS type interfaces; all others have their channel + * managed via their respective "establish a connection" + * command (connect, join, ...) + * + * Monitors are special as they are normally slaved to + * whatever else is going on, so they behave as though + * you tried setting the wiphy channel itself. + */ + return !wdev || + wdev->iftype == NL80211_IFTYPE_AP || + wdev->iftype == NL80211_IFTYPE_WDS || + wdev->iftype == NL80211_IFTYPE_MESH_POINT || + wdev->iftype == NL80211_IFTYPE_MONITOR; +} + +static int __nl80211_set_channel(struct cfg80211_registered_device *rdev, + struct wireless_dev *wdev, + struct genl_info *info) +{ + enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; + u32 freq; + int result; + + if (!info->attrs[NL80211_ATTR_WIPHY_FREQ]) + return -EINVAL; + + if (!nl80211_can_set_dev_channel(wdev)) + return -EOPNOTSUPP; + + if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { + channel_type = nla_get_u32(info->attrs[ + NL80211_ATTR_WIPHY_CHANNEL_TYPE]); + if (channel_type != NL80211_CHAN_NO_HT && + channel_type != NL80211_CHAN_HT20 && + channel_type != NL80211_CHAN_HT40PLUS && + channel_type != NL80211_CHAN_HT40MINUS) + return -EINVAL; + } + + freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); + + mutex_lock(&rdev->devlist_mtx); + if (wdev) { + wdev_lock(wdev); + result = cfg80211_set_freq(rdev, wdev, freq, channel_type); + wdev_unlock(wdev); + } else { + result = cfg80211_set_freq(rdev, NULL, freq, channel_type); + } + mutex_unlock(&rdev->devlist_mtx); + + return result; +} + +static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev; + struct net_device *netdev; + int result; + + rtnl_lock(); + + result = get_rdev_dev_by_info_ifindex(info, &rdev, &netdev); + if (result) + goto unlock; + + result = __nl80211_set_channel(rdev, netdev->ieee80211_ptr, info); + + unlock: + rtnl_unlock(); + + return result; +} + static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; - int result = 0, rem_txq_params = 0; + struct net_device *netdev = NULL; + struct wireless_dev *wdev; + int result, rem_txq_params = 0; struct nlattr *nl_txq_params; u32 changed; u8 retry_short = 0, retry_long = 0; @@ -700,16 +781,50 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); + /* + * Try to find the wiphy and netdev. Normally this + * function shouldn't need the netdev, but this is + * done for backward compatibility -- previously + * setting the channel was done per wiphy, but now + * it is per netdev. Previous userland like hostapd + * also passed a netdev to set_wiphy, so that it is + * possible to let that go to the right netdev! + */ mutex_lock(&cfg80211_mutex); - rdev = __cfg80211_rdev_from_info(info); - if (IS_ERR(rdev)) { - mutex_unlock(&cfg80211_mutex); - result = PTR_ERR(rdev); - goto unlock; + if (info->attrs[NL80211_ATTR_IFINDEX]) { + int ifindex = nla_get_u32(info->attrs[NL80211_ATTR_IFINDEX]); + + netdev = dev_get_by_index(genl_info_net(info), ifindex); + if (netdev && netdev->ieee80211_ptr) { + rdev = wiphy_to_dev(netdev->ieee80211_ptr->wiphy); + mutex_lock(&rdev->mtx); + } else + netdev = NULL; } - mutex_lock(&rdev->mtx); + if (!netdev) { + rdev = __cfg80211_rdev_from_info(info); + if (IS_ERR(rdev)) { + mutex_unlock(&cfg80211_mutex); + result = PTR_ERR(rdev); + goto unlock; + } + wdev = NULL; + netdev = NULL; + result = 0; + + mutex_lock(&rdev->mtx); + } else if (netif_running(netdev) && + nl80211_can_set_dev_channel(netdev->ieee80211_ptr)) + wdev = netdev->ieee80211_ptr; + else + wdev = NULL; + + /* + * end workaround code, by now the rdev is available + * and locked, and wdev may or may not be NULL. + */ if (info->attrs[NL80211_ATTR_WIPHY_NAME]) result = cfg80211_dev_rename( @@ -748,26 +863,7 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) } if (info->attrs[NL80211_ATTR_WIPHY_FREQ]) { - enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; - u32 freq; - - result = -EINVAL; - - if (info->attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { - channel_type = nla_get_u32(info->attrs[ - NL80211_ATTR_WIPHY_CHANNEL_TYPE]); - if (channel_type != NL80211_CHAN_NO_HT && - channel_type != NL80211_CHAN_HT20 && - channel_type != NL80211_CHAN_HT40PLUS && - channel_type != NL80211_CHAN_HT40MINUS) - goto bad_res; - } - - freq = nla_get_u32(info->attrs[NL80211_ATTR_WIPHY_FREQ]); - - mutex_lock(&rdev->devlist_mtx); - result = rdev_set_freq(rdev, NULL, freq, channel_type); - mutex_unlock(&rdev->devlist_mtx); + result = __nl80211_set_channel(rdev, wdev, info); if (result) goto bad_res; } @@ -864,6 +960,8 @@ static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info) bad_res: mutex_unlock(&rdev->mtx); + if (netdev) + dev_put(netdev); unlock: rtnl_unlock(); return result; @@ -3561,9 +3659,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev; struct net_device *dev; - struct wireless_dev *wdev; struct cfg80211_crypto_settings crypto; - struct ieee80211_channel *chan, *fixedchan; + struct ieee80211_channel *chan; const u8 *bssid, *ssid, *ie = NULL, *prev_bssid = NULL; int err, ssid_len, ie_len = 0; bool use_mfp = false; @@ -3606,16 +3703,6 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info) goto out; } - mutex_lock(&rdev->devlist_mtx); - wdev = dev->ieee80211_ptr; - fixedchan = rdev_fixed_channel(rdev, wdev); - if (fixedchan && chan != fixedchan) { - err = -EBUSY; - mutex_unlock(&rdev->devlist_mtx); - goto out; - } - mutex_unlock(&rdev->devlist_mtx); - ssid = nla_data(info->attrs[NL80211_ATTR_SSID]); ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); @@ -5185,6 +5272,12 @@ static struct genl_ops nl80211_ops[] = { .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, }, + { + .cmd = NL80211_CMD_SET_CHANNEL, + .doit = nl80211_set_channel, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { diff --git a/net/wireless/sme.c b/net/wireless/sme.c index dcd7685242f..14cf8163912 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -740,7 +740,6 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, const u8 *prev_bssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct ieee80211_channel *chan; struct cfg80211_bss *bss = NULL; int err; @@ -749,10 +748,6 @@ int __cfg80211_connect(struct cfg80211_registered_device *rdev, if (wdev->sme_state != CFG80211_SME_IDLE) return -EALREADY; - chan = rdev_fixed_channel(rdev, wdev); - if (chan && chan != connect->channel) - return -EBUSY; - if (WARN_ON(wdev->connect_keys)) { kfree(wdev->connect_keys); wdev->connect_keys = NULL; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 9ab51838849..75848c6cb22 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -781,16 +781,22 @@ int cfg80211_wext_siwfreq(struct net_device *dev, return cfg80211_mgd_wext_siwfreq(dev, info, wextfreq, extra); case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_siwfreq(dev, info, wextfreq, extra); - default: + case NL80211_IFTYPE_MONITOR: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wdev->wiphy, wextfreq); if (freq < 0) return freq; if (freq == 0) return -EINVAL; + wdev_lock(wdev); mutex_lock(&rdev->devlist_mtx); - err = rdev_set_freq(rdev, NULL, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); mutex_unlock(&rdev->devlist_mtx); + wdev_unlock(wdev); return err; + default: + return -EOPNOTSUPP; } } EXPORT_SYMBOL_GPL(cfg80211_wext_siwfreq); @@ -800,7 +806,6 @@ int cfg80211_wext_giwfreq(struct net_device *dev, struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; - struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_STATION: @@ -808,9 +813,9 @@ int cfg80211_wext_giwfreq(struct net_device *dev, case NL80211_IFTYPE_ADHOC: return cfg80211_ibss_wext_giwfreq(dev, info, freq, extra); default: - if (!rdev->channel) + if (!wdev->channel) return -EINVAL; - freq->m = rdev->channel->center_freq; + freq->m = wdev->channel->center_freq; freq->e = 6; return 0; } diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index 5615a880253..8e5ab4f4e9c 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -107,7 +107,7 @@ int cfg80211_mgd_wext_siwfreq(struct net_device *dev, /* SSID is not set, we just want to switch channel */ if (chan && !wdev->wext.connect.ssid_len) { - err = rdev_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); + err = cfg80211_set_freq(rdev, wdev, freq, NL80211_CHAN_NO_HT); goto out; } -- cgit v1.2.3-70-g09d2 From 0aaffa9b9699894aab3266195a529baf9f96ac29 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 5 May 2010 15:28:27 +0200 Subject: mac80211: improve HT channel handling Currently, when one interface switches HT mode, all others will follow along. This is clearly undesirable, since the new one might switch to no-HT while another one is operating in HT. Address this issue by keeping track of the HT mode per interface, and allowing only changes that are compatible, i.e. switching into HT40+ is not possible when another interface is in HT40-, in that case the second one needs to fall back to HT20. Also, to allow drivers to know what's going on, store the per-interface HT mode (channel type) in the virtual interface's bss_conf. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- drivers/net/wireless/mac80211_hwsim.c | 19 +++++----- include/net/mac80211.h | 4 ++ net/mac80211/cfg.c | 23 +++++++++--- net/mac80211/chan.c | 70 +++++++++++++++++++++++++++++++++++ net/mac80211/ibss.c | 5 ++- net/mac80211/ieee80211_i.h | 5 ++- net/mac80211/main.c | 2 +- net/mac80211/mlme.c | 44 +++++++++++----------- 8 files changed, 132 insertions(+), 40 deletions(-) (limited to 'include/net') diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 62a739f6c37..bdce71a4ba2 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -651,17 +651,17 @@ static void mac80211_hwsim_beacon(unsigned long arg) add_timer(&data->beacon_timer); } +static const char *hwsim_chantypes[] = { + [NL80211_CHAN_NO_HT] = "noht", + [NL80211_CHAN_HT20] = "ht20", + [NL80211_CHAN_HT40MINUS] = "ht40-", + [NL80211_CHAN_HT40PLUS] = "ht40+", +}; static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) { struct mac80211_hwsim_data *data = hw->priv; struct ieee80211_conf *conf = &hw->conf; - static const char *chantypes[4] = { - [NL80211_CHAN_NO_HT] = "noht", - [NL80211_CHAN_HT20] = "ht20", - [NL80211_CHAN_HT40MINUS] = "ht40-", - [NL80211_CHAN_HT40PLUS] = "ht40+", - }; static const char *smps_modes[IEEE80211_SMPS_NUM_MODES] = { [IEEE80211_SMPS_AUTOMATIC] = "auto", [IEEE80211_SMPS_OFF] = "off", @@ -672,7 +672,7 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) printk(KERN_DEBUG "%s:%s (freq=%d/%s idle=%d ps=%d smps=%s)\n", wiphy_name(hw->wiphy), __func__, conf->channel->center_freq, - chantypes[conf->channel_type], + hwsim_chantypes[conf->channel_type], !!(conf->flags & IEEE80211_CONF_IDLE), !!(conf->flags & IEEE80211_CONF_PS), smps_modes[conf->smps_mode]); @@ -760,9 +760,10 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, } if (changed & BSS_CHANGED_HT) { - printk(KERN_DEBUG " %s: HT: op_mode=0x%x\n", + printk(KERN_DEBUG " %s: HT: op_mode=0x%x, chantype=%s\n", wiphy_name(hw->wiphy), - info->ht_operation_mode); + info->ht_operation_mode, + hwsim_chantypes[info->channel_type]); } if (changed & BSS_CHANGED_BASIC_RATES) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0528615ac82..9448a5b1bb1 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -191,6 +191,9 @@ enum ieee80211_bss_change { * the current band. * @bssid: The BSSID for this BSS * @enable_beacon: whether beaconing should be enabled or not + * @channel_type: Channel type for this BSS -- the hardware might be + * configured for HT40+ while this BSS only uses no-HT, for + * example. * @ht_operation_mode: HT operation mode (like in &struct ieee80211_ht_info). * This field is only valid when the channel type is one of the HT types. * @cqm_rssi_thold: Connection quality monitor RSSI threshold, a zero value @@ -215,6 +218,7 @@ struct ieee80211_bss_conf { u16 ht_operation_mode; s32 cqm_rssi_thold; u32 cqm_rssi_hyst; + enum nl80211_channel_type channel_type; }; /** diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 414b7dd7d7f..ab166c6d939 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1166,23 +1166,34 @@ static int ieee80211_set_channel(struct wiphy *wiphy, enum nl80211_channel_type channel_type) { struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = NULL; + + if (netdev) + sdata = IEEE80211_DEV_TO_SUB_IF(netdev); switch (ieee80211_get_channel_mode(local, NULL)) { case CHAN_MODE_HOPPING: return -EBUSY; case CHAN_MODE_FIXED: - if (local->oper_channel == chan && - local->oper_channel_type == channel_type) + if (local->oper_channel != chan) + return -EBUSY; + if (!sdata && local->_oper_channel_type == channel_type) return 0; - return -EBUSY; + break; case CHAN_MODE_UNDEFINED: break; } local->oper_channel = chan; - local->oper_channel_type = channel_type; - return ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (!ieee80211_set_channel_type(local, sdata, channel_type)) + return -EBUSY; + + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); + if (sdata && sdata->vif.type != NL80211_IFTYPE_MONITOR) + ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_HT); + + return 0; } #ifdef CONFIG_PM @@ -1406,7 +1417,7 @@ int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, * association, there's no need to send an action frame. */ if (!sdata->u.mgd.associated || - sdata->local->oper_channel_type == NL80211_CHAN_NO_HT) { + sdata->vif.bss_conf.channel_type == NL80211_CHAN_NO_HT) { mutex_lock(&sdata->local->iflist_mtx); ieee80211_recalc_smps(sdata->local, sdata); mutex_unlock(&sdata->local->iflist_mtx); diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 08f3832661a..5d218c530a4 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -2,6 +2,7 @@ * mac80211 - channel management */ +#include #include "ieee80211_i.h" enum ieee80211_chan_mode @@ -55,3 +56,72 @@ ieee80211_get_channel_mode(struct ieee80211_local *local, return mode; } + +bool ieee80211_set_channel_type(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum nl80211_channel_type chantype) +{ + struct ieee80211_sub_if_data *tmp; + enum nl80211_channel_type superchan = NL80211_CHAN_NO_HT; + bool result; + + mutex_lock(&local->iflist_mtx); + + list_for_each_entry(tmp, &local->interfaces, list) { + if (tmp == sdata) + continue; + + if (!ieee80211_sdata_running(tmp)) + continue; + + switch (tmp->vif.bss_conf.channel_type) { + case NL80211_CHAN_NO_HT: + case NL80211_CHAN_HT20: + superchan = tmp->vif.bss_conf.channel_type; + break; + case NL80211_CHAN_HT40PLUS: + WARN_ON(superchan == NL80211_CHAN_HT40MINUS); + superchan = NL80211_CHAN_HT40PLUS; + break; + case NL80211_CHAN_HT40MINUS: + WARN_ON(superchan == NL80211_CHAN_HT40PLUS); + superchan = NL80211_CHAN_HT40MINUS; + break; + } + } + + switch (superchan) { + case NL80211_CHAN_NO_HT: + case NL80211_CHAN_HT20: + /* + * allow any change that doesn't go to no-HT + * (if it already is no-HT no change is needed) + */ + if (chantype == NL80211_CHAN_NO_HT) + break; + superchan = chantype; + break; + case NL80211_CHAN_HT40PLUS: + case NL80211_CHAN_HT40MINUS: + /* allow smaller bandwidth and same */ + if (chantype == NL80211_CHAN_NO_HT) + break; + if (chantype == NL80211_CHAN_HT20) + break; + if (superchan == chantype) + break; + result = false; + goto out; + } + + local->_oper_channel_type = superchan; + + if (sdata) + sdata->vif.bss_conf.channel_type = chantype; + + result = true; + out: + mutex_unlock(&local->iflist_mtx); + + return result; +} diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index d5855ae387e..36745f494f6 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -102,7 +102,7 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata, sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; local->oper_channel = chan; - local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(local, sdata, NL80211_CHAN_NO_HT)); ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); sband = local->hw.wiphy->bands[chan->band]; @@ -910,7 +910,8 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata, /* fix ourselves to that channel now already */ if (params->channel_fixed) { sdata->local->oper_channel = params->channel; - sdata->local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(sdata->local, sdata, + NL80211_CHAN_NO_HT)); } if (params->ie) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 359edff3147..69e7f4131f4 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -768,7 +768,7 @@ struct ieee80211_local { enum mac80211_scan_state next_scan_state; struct delayed_work scan_work; struct ieee80211_sub_if_data *scan_sdata; - enum nl80211_channel_type oper_channel_type; + enum nl80211_channel_type _oper_channel_type; struct ieee80211_channel *oper_channel, *csa_channel; /* Temporary remain-on-channel for off-channel operations */ @@ -1239,6 +1239,9 @@ enum ieee80211_chan_mode { enum ieee80211_chan_mode ieee80211_get_channel_mode(struct ieee80211_local *local, struct ieee80211_sub_if_data *ignore); +bool ieee80211_set_channel_type(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + enum nl80211_channel_type chantype); #ifdef CONFIG_MAC80211_NOINLINE #define debug_noinline noinline diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 353b6b42d9c..d763d76e809 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -111,7 +111,7 @@ int ieee80211_hw_config(struct ieee80211_local *local, u32 changed) channel_type = local->tmp_channel_type; } else { chan = local->oper_channel; - channel_type = local->oper_channel_type; + channel_type = local->_oper_channel_type; } if (chan != local->hw.conf.channel || diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 17cb8ae912b..6e149b49d4f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -136,11 +136,14 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; u32 changed = 0; u16 ht_opmode; - bool enable_ht = true, ht_changed; + bool enable_ht = true; + enum nl80211_channel_type prev_chantype; enum nl80211_channel_type channel_type = NL80211_CHAN_NO_HT; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; + prev_chantype = sdata->vif.bss_conf.channel_type; + /* HT is not supported */ if (!sband->ht_cap.ht_supported) enable_ht = false; @@ -171,38 +174,37 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, } } - ht_changed = conf_is_ht(&local->hw.conf) != enable_ht || - channel_type != local->hw.conf.channel_type; - if (local->tmp_channel) local->tmp_channel_type = channel_type; - local->oper_channel_type = channel_type; - if (ht_changed) { - /* channel_type change automatically detected */ - ieee80211_hw_config(local, 0); + if (!ieee80211_set_channel_type(local, sdata, channel_type)) { + /* can only fail due to HT40+/- mismatch */ + channel_type = NL80211_CHAN_HT20; + WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); + } + /* channel_type change automatically detected */ + ieee80211_hw_config(local, 0); + + if (prev_chantype != channel_type) { rcu_read_lock(); sta = sta_info_get(sdata, bssid); if (sta) rate_control_rate_update(local, sband, sta, IEEE80211_RC_HT_CHANGED, - local->oper_channel_type); + channel_type); rcu_read_unlock(); - } - - /* disable HT */ - if (!enable_ht) - return 0; + } ht_opmode = le16_to_cpu(hti->operation_mode); /* if bss configuration changed store the new one */ - if (!sdata->ht_opmode_valid || - sdata->vif.bss_conf.ht_operation_mode != ht_opmode) { + if (sdata->ht_opmode_valid != enable_ht || + sdata->vif.bss_conf.ht_operation_mode != ht_opmode || + prev_chantype != channel_type) { changed |= BSS_CHANGED_HT; sdata->vif.bss_conf.ht_operation_mode = ht_opmode; - sdata->ht_opmode_valid = true; + sdata->ht_opmode_valid = enable_ht; } return changed; @@ -865,7 +867,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_set_wmm_default(sdata); /* channel(_type) changes are handled by ieee80211_hw_config */ - local->oper_channel_type = NL80211_CHAN_NO_HT; + WARN_ON(!ieee80211_set_channel_type(local, sdata, NL80211_CHAN_NO_HT)); /* on the next assoc, re-program HT parameters */ sdata->ht_opmode_valid = false; @@ -882,8 +884,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, ieee80211_hw_config(local, config_changed); - /* And the BSSID changed -- not very interesting here */ - changed |= BSS_CHANGED_BSSID; + /* The BSSID (not really interesting) and HT changed */ + changed |= BSS_CHANGED_BSSID | BSS_CHANGED_HT; ieee80211_bss_info_change_notify(sdata, changed); if (remove_sta) @@ -2265,7 +2267,7 @@ int ieee80211_mgd_action(struct ieee80211_sub_if_data *sdata, if ((chan != local->tmp_channel || channel_type != local->tmp_channel_type) && (chan != local->oper_channel || - channel_type != local->oper_channel_type)) + channel_type != local->_oper_channel_type)) return -EBUSY; skb = dev_alloc_skb(local->hw.extra_tx_headroom + len); -- cgit v1.2.3-70-g09d2 From 3ee943728fff536edaf8f59faa58aaa1aa7366e3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Sat, 8 May 2010 01:57:52 -0700 Subject: ipv4: remove ip_rt_secret timer (v4) A while back there was a discussion regarding the rt_secret_interval timer. Given that we've had the ability to do emergency route cache rebuilds for awhile now, based on a statistical analysis of the various hash chain lengths in the cache, the use of the flush timer is somewhat redundant. This patch removes the rt_secret_interval sysctl, allowing us to rely solely on the statistical analysis mechanism to determine the need for route cache flushes. Signed-off-by: Neil Horman Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/netns/ipv4.h | 1 - kernel/sysctl_binary.c | 1 - net/ipv4/route.c | 108 ++++------------------------------------------- 3 files changed, 8 insertions(+), 102 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index ae07feec644..d68c3f12177 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -55,7 +55,6 @@ struct netns_ipv4 { int sysctl_rt_cache_rebuild_count; int current_rt_cache_rebuild_count; - struct timer_list rt_secret_timer; atomic_t rt_genid; #ifdef CONFIG_IP_MROUTE diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 59030570f5c..937d31dc856 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -224,7 +224,6 @@ static const struct bin_table bin_net_ipv4_route_table[] = { { CTL_INT, NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires" }, { CTL_INT, NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu" }, { CTL_INT, NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss" }, - { CTL_INT, NET_IPV4_ROUTE_SECRET_INTERVAL, "secret_interval" }, {} }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a947428ef0a..dea3f926425 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; -static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ; static int rt_chain_length_max __read_mostly = 20; static struct delayed_work expires_work; @@ -918,32 +917,11 @@ void rt_cache_flush_batch(void) rt_do_flush(!in_softirq()); } -/* - * We change rt_genid and let gc do the cleanup - */ -static void rt_secret_rebuild(unsigned long __net) -{ - struct net *net = (struct net *)__net; - rt_cache_invalidate(net); - mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); -} - -static void rt_secret_rebuild_oneshot(struct net *net) -{ - del_timer_sync(&net->ipv4.rt_secret_timer); - rt_cache_invalidate(net); - if (ip_rt_secret_interval) - mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); -} - static void rt_emergency_hash_rebuild(struct net *net) { - if (net_ratelimit()) { + if (net_ratelimit()) printk(KERN_WARNING "Route hash chain too long!\n"); - printk(KERN_WARNING "Adjust your secret_interval!\n"); - } - - rt_secret_rebuild_oneshot(net); + rt_cache_invalidate(net); } /* @@ -3101,48 +3079,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, return -EINVAL; } -static void rt_secret_reschedule(int old) -{ - struct net *net; - int new = ip_rt_secret_interval; - int diff = new - old; - - if (!diff) - return; - - rtnl_lock(); - for_each_net(net) { - int deleted = del_timer_sync(&net->ipv4.rt_secret_timer); - long time; - - if (!new) - continue; - - if (deleted) { - time = net->ipv4.rt_secret_timer.expires - jiffies; - - if (time <= 0 || (time += diff) <= 0) - time = 0; - } else - time = new; - - mod_timer(&net->ipv4.rt_secret_timer, jiffies + time); - } - rtnl_unlock(); -} - -static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int old = ip_rt_secret_interval; - int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); - - rt_secret_reschedule(old); - - return ret; -} - static ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", @@ -3251,13 +3187,6 @@ static ctl_table ipv4_route_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "secret_interval", - .data = &ip_rt_secret_interval, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = ipv4_sysctl_rt_secret_interval, - }, { } }; @@ -3336,34 +3265,15 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { }; #endif - -static __net_init int rt_secret_timer_init(struct net *net) +static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->ipv4.rt_genid, - (int) ((num_physpages ^ (num_physpages>>8)) ^ - (jiffies ^ (jiffies >> 7)))); - - net->ipv4.rt_secret_timer.function = rt_secret_rebuild; - net->ipv4.rt_secret_timer.data = (unsigned long)net; - init_timer_deferrable(&net->ipv4.rt_secret_timer); - - if (ip_rt_secret_interval) { - net->ipv4.rt_secret_timer.expires = - jiffies + net_random() % ip_rt_secret_interval + - ip_rt_secret_interval; - add_timer(&net->ipv4.rt_secret_timer); - } + get_random_bytes(&net->ipv4.rt_genid, + sizeof(net->ipv4.rt_genid)); return 0; } -static __net_exit void rt_secret_timer_exit(struct net *net) -{ - del_timer_sync(&net->ipv4.rt_secret_timer); -} - -static __net_initdata struct pernet_operations rt_secret_timer_ops = { - .init = rt_secret_timer_init, - .exit = rt_secret_timer_exit, +static __net_initdata struct pernet_operations rt_genid_ops = { + .init = rt_genid_init, }; @@ -3424,9 +3334,6 @@ int __init ip_rt_init(void) schedule_delayed_work(&expires_work, net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - if (register_pernet_subsys(&rt_secret_timer_ops)) - printk(KERN_ERR "Unable to setup rt_secret_timer\n"); - if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM @@ -3438,6 +3345,7 @@ int __init ip_rt_init(void) #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif + register_pernet_subsys(&rt_genid_ops); return rc; } -- cgit v1.2.3-70-g09d2 From 0d861d8b8edd139a9b291cb262d08dec8dc3922d Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:35 -0300 Subject: Bluetooth: Make hci_send_sco() void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It also removes an unneeded check for the MTU. The check is done before on sco_send_frame() Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_core.c | 9 +-------- net/bluetooth/sco.c | 3 +-- 3 files changed, 3 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index ce3c99e5fa2..9830a88f487 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -637,7 +637,7 @@ int hci_unregister_notifier(struct notifier_block *nb); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags); -int hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); +void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4ad23192c7a..1c9aef97f51 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1308,18 +1308,13 @@ int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) EXPORT_SYMBOL(hci_send_acl); /* Send SCO data */ -int hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) +void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) { struct hci_dev *hdev = conn->hdev; struct hci_sco_hdr hdr; BT_DBG("%s len %d", hdev->name, skb->len); - if (skb->len > hdev->sco_mtu) { - kfree_skb(skb); - return -EINVAL; - } - hdr.handle = cpu_to_le16(conn->handle); hdr.dlen = skb->len; @@ -1332,8 +1327,6 @@ int hci_send_sco(struct hci_conn *conn, struct sk_buff *skb) skb_queue_tail(&conn->data_q, skb); tasklet_schedule(&hdev->tx_task); - - return 0; } EXPORT_SYMBOL(hci_send_sco); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index b406d3eff53..541b26efb72 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -249,8 +249,7 @@ static inline int sco_send_frame(struct sock *sk, struct msghdr *msg, int len) goto fail; } - if ((err = hci_send_sco(conn->hcon, skb)) < 0) - return err; + hci_send_sco(conn->hcon, skb); return count; -- cgit v1.2.3-70-g09d2 From d5392c8f1e9faef089bb7cb66c3314da8bddd1fe Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:36 -0300 Subject: Bluetooth: Implement 'Send IorRRorRNR' event MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After receive a RR with P bit set ERTM shall use this funcion to choose what type of frame to reply with F bit = 1. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 20 +++++++++++--------- net/bluetooth/l2cap.c | 43 +++++++++++++++++++++++++++++++++++++++---- 2 files changed, 50 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 17a689f27a6..d9c20c3d6f3 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -320,7 +320,7 @@ struct l2cap_pinfo { __u8 conf_req[64]; __u8 conf_len; __u8 conf_state; - __u8 conn_state; + __u16 conn_state; __u8 next_tx_seq; __u8 expected_ack_seq; @@ -328,6 +328,7 @@ struct l2cap_pinfo { __u8 buffer_seq; __u8 buffer_seq_srej; __u8 srej_save_reqseq; + __u8 frames_sent; __u8 unacked_frames; __u8 retry_count; __u8 num_to_ack; @@ -367,14 +368,15 @@ struct l2cap_pinfo { #define L2CAP_CONF_MAX_CONF_REQ 2 #define L2CAP_CONF_MAX_CONF_RSP 2 -#define L2CAP_CONN_SAR_SDU 0x01 -#define L2CAP_CONN_SREJ_SENT 0x02 -#define L2CAP_CONN_WAIT_F 0x04 -#define L2CAP_CONN_SREJ_ACT 0x08 -#define L2CAP_CONN_SEND_PBIT 0x10 -#define L2CAP_CONN_REMOTE_BUSY 0x20 -#define L2CAP_CONN_LOCAL_BUSY 0x40 -#define L2CAP_CONN_REJ_ACT 0x80 +#define L2CAP_CONN_SAR_SDU 0x0001 +#define L2CAP_CONN_SREJ_SENT 0x0002 +#define L2CAP_CONN_WAIT_F 0x0004 +#define L2CAP_CONN_SREJ_ACT 0x0008 +#define L2CAP_CONN_SEND_PBIT 0x0010 +#define L2CAP_CONN_REMOTE_BUSY 0x0020 +#define L2CAP_CONN_LOCAL_BUSY 0x0040 +#define L2CAP_CONN_REJ_ACT 0x0080 +#define L2CAP_CONN_SEND_FBIT 0x0100 #define __mod_retrans_timer() mod_timer(&l2cap_pi(sk)->retrans_timer, \ jiffies + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index a9c152a09f0..06687e26470 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1383,6 +1383,10 @@ static int l2cap_ertm_send(struct sock *sk) bt_cb(skb)->retries++; control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); + if (pi->conn_state & L2CAP_CONN_SEND_FBIT) { + control |= L2CAP_CTRL_FINAL; + pi->conn_state &= ~L2CAP_CONN_SEND_FBIT; + } control |= (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (pi->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1404,6 +1408,7 @@ static int l2cap_ertm_send(struct sock *sk) pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; pi->unacked_frames++; + pi->frames_sent++; if (skb_queue_is_last(TX_QUEUE(sk), skb)) sk->sk_send_head = NULL; @@ -2191,6 +2196,7 @@ static inline void l2cap_ertm_init(struct sock *sk) l2cap_pi(sk)->unacked_frames = 0; l2cap_pi(sk)->buffer_seq = 0; l2cap_pi(sk)->num_to_ack = 0; + l2cap_pi(sk)->frames_sent = 0; setup_timer(&l2cap_pi(sk)->retrans_timer, l2cap_retrans_timeout, (unsigned long) sk); @@ -3148,6 +3154,38 @@ static int l2cap_check_fcs(struct l2cap_pinfo *pi, struct sk_buff *skb) return 0; } +static inline void l2cap_send_i_or_rr_or_rnr(struct sock *sk) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + u16 control = 0; + + pi->frames_sent = 0; + pi->conn_state |= L2CAP_CONN_SEND_FBIT; + + control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + + if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { + control |= L2CAP_SUPER_RCV_NOT_READY | L2CAP_CTRL_FINAL; + l2cap_send_sframe(pi, control); + pi->conn_state &= ~L2CAP_CONN_SEND_FBIT; + } + + if (pi->conn_state & L2CAP_CONN_REMOTE_BUSY && pi->unacked_frames > 0) + __mod_retrans_timer(); + + l2cap_ertm_send(sk); + + if (!(pi->conn_state & L2CAP_CONN_LOCAL_BUSY) && + pi->frames_sent == 0) { + control |= L2CAP_SUPER_RCV_READY; + if (pi->conn_state & L2CAP_CONN_SEND_FBIT) { + control |= L2CAP_CTRL_FINAL; + pi->conn_state &= ~L2CAP_CONN_SEND_FBIT; + } + l2cap_send_sframe(pi, control); + } +} + static void l2cap_add_to_srej_queue(struct sock *sk, struct sk_buff *skb, u8 tx_seq, u8 sar) { struct sk_buff *next_skb; @@ -3418,10 +3456,7 @@ static inline int l2cap_data_channel_sframe(struct sock *sk, u16 rx_control, str switch (rx_control & L2CAP_CTRL_SUPERVISE) { case L2CAP_SUPER_RCV_READY: if (rx_control & L2CAP_CTRL_POLL) { - u16 control = L2CAP_CTRL_FINAL; - control |= L2CAP_SUPER_RCV_READY | - (pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT); - l2cap_send_sframe(l2cap_pi(sk), control); + l2cap_send_i_or_rr_or_rnr(sk); pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; } else if (rx_control & L2CAP_CTRL_FINAL) { -- cgit v1.2.3-70-g09d2 From c1b4f43be01c2a363be021485dd18cca33cfab8a Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:39 -0300 Subject: Bluetooth: Add timer to Acknowledge I-frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We ack I-frames on each txWindow/5 I-frames received, but if the sender stop to send I-frames and it's not a txWindow multiple we can leave some frames unacked. So I added a timer to ack I-frames on this case. The timer expires in 200ms. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 4 ++++ net/bluetooth/l2cap.c | 15 +++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index d9c20c3d6f3..48f10f46c73 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -35,6 +35,7 @@ #define L2CAP_DEFAULT_RETRANS_TO 1000 /* 1 second */ #define L2CAP_DEFAULT_MONITOR_TO 12000 /* 12 seconds */ #define L2CAP_DEFAULT_MAX_PDU_SIZE 672 +#define L2CAP_DEFAULT_ACK_TO 200 #define L2CAP_CONN_TIMEOUT (40000) /* 40 seconds */ #define L2CAP_INFO_TIMEOUT (4000) /* 4 seconds */ @@ -348,6 +349,7 @@ struct l2cap_pinfo { struct timer_list retrans_timer; struct timer_list monitor_timer; + struct timer_list ack_timer; struct sk_buff_head tx_queue; struct sk_buff_head srej_queue; struct srej_list srej_l; @@ -382,6 +384,8 @@ struct l2cap_pinfo { jiffies + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); #define __mod_monitor_timer() mod_timer(&l2cap_pi(sk)->monitor_timer, \ jiffies + msecs_to_jiffies(L2CAP_DEFAULT_MONITOR_TO)); +#define __mod_ack_timer() mod_timer(&l2cap_pi(sk)->ack_timer, \ + jiffies + msecs_to_jiffies(L2CAP_DEFAULT_ACK_TO)); static inline int l2cap_tx_window_full(struct sock *sk) { diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index f3869857ee9..03006568f8a 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -2235,6 +2235,15 @@ static void l2cap_add_conf_opt(void **ptr, u8 type, u8 len, unsigned long val) *ptr += L2CAP_CONF_OPT_SIZE + len; } +static void l2cap_ack_timeout(unsigned long arg) +{ + struct sock *sk = (void *) arg; + + bh_lock_sock(sk); + l2cap_send_ack(l2cap_pi(sk)); + bh_unlock_sock(sk); +} + static inline void l2cap_ertm_init(struct sock *sk) { l2cap_pi(sk)->expected_ack_seq = 0; @@ -2247,6 +2256,8 @@ static inline void l2cap_ertm_init(struct sock *sk) l2cap_retrans_timeout, (unsigned long) sk); setup_timer(&l2cap_pi(sk)->monitor_timer, l2cap_monitor_timeout, (unsigned long) sk); + setup_timer(&l2cap_pi(sk)->ack_timer, + l2cap_ack_timeout, (unsigned long) sk); __skb_queue_head_init(SREJ_QUEUE(sk)); } @@ -2975,6 +2986,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd skb_queue_purge(SREJ_QUEUE(sk)); del_timer(&l2cap_pi(sk)->retrans_timer); del_timer(&l2cap_pi(sk)->monitor_timer); + del_timer(&l2cap_pi(sk)->ack_timer); } l2cap_chan_del(sk, ECONNRESET); @@ -3005,6 +3017,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd skb_queue_purge(SREJ_QUEUE(sk)); del_timer(&l2cap_pi(sk)->retrans_timer); del_timer(&l2cap_pi(sk)->monitor_timer); + del_timer(&l2cap_pi(sk)->ack_timer); } l2cap_chan_del(sk, 0); @@ -3484,6 +3497,8 @@ expected: if (err < 0) return err; + __mod_ack_timer(); + pi->num_to_ack = (pi->num_to_ack + 1) % L2CAP_DEFAULT_NUM_TO_ACK; if (pi->num_to_ack == L2CAP_DEFAULT_NUM_TO_ACK - 1) l2cap_send_ack(pi); -- cgit v1.2.3-70-g09d2 From 1c7621596d11b9c3e19eb88a818758dee4901c95 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:40 -0300 Subject: Bluetooth: Fix configuration of the MPS value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We were accepting values bigger than we can accept. This was leading ERTM to drop packets because of wrong FCS checks. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 3 ++- net/bluetooth/l2cap.c | 36 ++++++++++++++++++++---------------- 2 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 48f10f46c73..0f4e4234c5f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -343,7 +343,8 @@ struct l2cap_pinfo { __u8 remote_max_tx; __u16 retrans_timeout; __u16 monitor_timeout; - __u16 max_pdu_size; + __u16 remote_mps; + __u16 mps; __le16 sport; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c50c05738fb..94be5dbb256 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1606,21 +1606,21 @@ static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, siz __skb_queue_head_init(&sar_queue); control = L2CAP_SDU_START; - skb = l2cap_create_iframe_pdu(sk, msg, pi->max_pdu_size, control, len); + skb = l2cap_create_iframe_pdu(sk, msg, pi->remote_mps, control, len); if (IS_ERR(skb)) return PTR_ERR(skb); __skb_queue_tail(&sar_queue, skb); - len -= pi->max_pdu_size; - size +=pi->max_pdu_size; + len -= pi->remote_mps; + size += pi->remote_mps; control = 0; while (len > 0) { size_t buflen; - if (len > pi->max_pdu_size) { + if (len > pi->remote_mps) { control |= L2CAP_SDU_CONTINUE; - buflen = pi->max_pdu_size; + buflen = pi->remote_mps; } else { control |= L2CAP_SDU_END; buflen = len; @@ -1701,7 +1701,7 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms case L2CAP_MODE_ERTM: case L2CAP_MODE_STREAMING: /* Entire SDU fits into one PDU */ - if (len <= pi->max_pdu_size) { + if (len <= pi->remote_mps) { control = L2CAP_SDU_UNSEGMENTED; skb = l2cap_create_iframe_pdu(sk, msg, len, control, 0); if (IS_ERR(skb)) { @@ -2330,7 +2330,7 @@ done: rfc.monitor_timeout = 0; rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); if (L2CAP_DEFAULT_MAX_PDU_SIZE > pi->conn->mtu - 10) - rfc.max_pdu_size = pi->conn->mtu - 10; + rfc.max_pdu_size = cpu_to_le16(pi->conn->mtu - 10); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc); @@ -2353,7 +2353,7 @@ done: rfc.monitor_timeout = 0; rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); if (L2CAP_DEFAULT_MAX_PDU_SIZE > pi->conn->mtu - 10) - rfc.max_pdu_size = pi->conn->mtu - 10; + rfc.max_pdu_size = cpu_to_le16(pi->conn->mtu - 10); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc); @@ -2482,7 +2482,10 @@ done: case L2CAP_MODE_ERTM: pi->remote_tx_win = rfc.txwin_size; pi->remote_max_tx = rfc.max_transmit; - pi->max_pdu_size = rfc.max_pdu_size; + if (rfc.max_pdu_size > pi->conn->mtu - 10) + rfc.max_pdu_size = le16_to_cpu(pi->conn->mtu - 10); + + pi->remote_mps = le16_to_cpu(rfc.max_pdu_size); rfc.retrans_timeout = L2CAP_DEFAULT_RETRANS_TO; rfc.monitor_timeout = L2CAP_DEFAULT_MONITOR_TO; @@ -2495,7 +2498,10 @@ done: break; case L2CAP_MODE_STREAMING: - pi->max_pdu_size = rfc.max_pdu_size; + if (rfc.max_pdu_size > pi->conn->mtu - 10) + rfc.max_pdu_size = le16_to_cpu(pi->conn->mtu - 10); + + pi->remote_mps = le16_to_cpu(rfc.max_pdu_size); pi->conf_state |= L2CAP_CONF_MODE_DONE; @@ -2574,11 +2580,10 @@ static int l2cap_parse_conf_rsp(struct sock *sk, void *rsp, int len, void *data, pi->remote_tx_win = rfc.txwin_size; pi->retrans_timeout = rfc.retrans_timeout; pi->monitor_timeout = rfc.monitor_timeout; - pi->max_pdu_size = le16_to_cpu(rfc.max_pdu_size); + pi->mps = le16_to_cpu(rfc.max_pdu_size); break; case L2CAP_MODE_STREAMING: - pi->max_pdu_size = le16_to_cpu(rfc.max_pdu_size); - break; + pi->mps = le16_to_cpu(rfc.max_pdu_size); } } @@ -3753,7 +3758,7 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk * Receiver will miss it and start proper recovery * procedures and ask retransmission. */ - if (len > L2CAP_DEFAULT_MAX_PDU_SIZE) + if (len > pi->mps) goto drop; if (l2cap_check_fcs(pi, skb)) @@ -3784,8 +3789,7 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk if (pi->fcs == L2CAP_FCS_CRC16) len -= 2; - if (len > L2CAP_DEFAULT_MAX_PDU_SIZE || len < 4 - || __is_sframe(control)) + if (len > pi->mps || len < 4 || __is_sframe(control)) goto drop; if (l2cap_check_fcs(pi, skb)) -- cgit v1.2.3-70-g09d2 From 14b5aa71ec506f4e38ca6a1dc02ecd668ecfd902 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:40 -0300 Subject: Bluetooth: Add sockopt configuration for txWindow on L2CAP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now we can set/get Transmission Window size via sockopt. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 2 ++ net/bluetooth/l2cap.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 0f4e4234c5f..07ae4ccfffb 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -56,6 +56,7 @@ struct l2cap_options { __u16 flush_to; __u8 mode; __u8 fcs; + __u16 txwin_size; }; #define L2CAP_CONNINFO 0x02 @@ -339,6 +340,7 @@ struct l2cap_pinfo { __u8 ident; + __u8 tx_win; __u8 remote_tx_win; __u8 remote_max_tx; __u16 retrans_timeout; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index c6bc1b9ed65..530079649b4 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -782,6 +782,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->omtu = l2cap_pi(parent)->omtu; pi->mode = l2cap_pi(parent)->mode; pi->fcs = l2cap_pi(parent)->fcs; + pi->tx_win = l2cap_pi(parent)->tx_win; pi->sec_level = l2cap_pi(parent)->sec_level; pi->role_switch = l2cap_pi(parent)->role_switch; pi->force_reliable = l2cap_pi(parent)->force_reliable; @@ -790,6 +791,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->omtu = 0; pi->mode = L2CAP_MODE_BASIC; pi->fcs = L2CAP_FCS_CRC16; + pi->tx_win = L2CAP_DEFAULT_TX_WINDOW; pi->sec_level = BT_SECURITY_LOW; pi->role_switch = 0; pi->force_reliable = 0; @@ -1782,6 +1784,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us opts.flush_to = l2cap_pi(sk)->flush_to; opts.mode = l2cap_pi(sk)->mode; opts.fcs = l2cap_pi(sk)->fcs; + opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win; len = min_t(unsigned int, sizeof(opts), optlen); if (copy_from_user((char *) &opts, optval, len)) { @@ -1793,6 +1796,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us l2cap_pi(sk)->omtu = opts.omtu; l2cap_pi(sk)->mode = opts.mode; l2cap_pi(sk)->fcs = opts.fcs; + l2cap_pi(sk)->tx_win = (__u8)opts.txwin_size; break; case L2CAP_LM: @@ -1907,6 +1911,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us opts.flush_to = l2cap_pi(sk)->flush_to; opts.mode = l2cap_pi(sk)->mode; opts.fcs = l2cap_pi(sk)->fcs; + opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win; len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) @@ -2324,7 +2329,7 @@ done: case L2CAP_MODE_ERTM: rfc.mode = L2CAP_MODE_ERTM; - rfc.txwin_size = L2CAP_DEFAULT_TX_WINDOW; + rfc.txwin_size = pi->tx_win; rfc.max_transmit = max_transmit; rfc.retrans_timeout = 0; rfc.monitor_timeout = 0; -- cgit v1.2.3-70-g09d2 From 803020c6fa63aa738cfda3329c9675b42023e9d2 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:41 -0300 Subject: Bluetooth: Change acknowledgement to use the value of txWindow MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that we can set the txWindow we need to change the acknowledgement procedure to ack after each (pi->txWindow/6 + 1). The plus 1 is to avoid the zero value. It also renames pi->num_to_ack to a better name: pi->num_acked. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 3 +-- net/bluetooth/l2cap.c | 7 ++++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 07ae4ccfffb..059260bed4e 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -30,7 +30,6 @@ #define L2CAP_DEFAULT_MIN_MTU 48 #define L2CAP_DEFAULT_FLUSH_TO 0xffff #define L2CAP_DEFAULT_TX_WINDOW 63 -#define L2CAP_DEFAULT_NUM_TO_ACK (L2CAP_DEFAULT_TX_WINDOW/5) #define L2CAP_DEFAULT_MAX_TX 3 #define L2CAP_DEFAULT_RETRANS_TO 1000 /* 1 second */ #define L2CAP_DEFAULT_MONITOR_TO 12000 /* 12 seconds */ @@ -333,7 +332,7 @@ struct l2cap_pinfo { __u8 frames_sent; __u8 unacked_frames; __u8 retry_count; - __u8 num_to_ack; + __u8 num_acked; __u16 sdu_len; __u16 partial_sdu_len; struct sk_buff *sdu; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 530079649b4..0b0b237bb78 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -2254,7 +2254,7 @@ static inline void l2cap_ertm_init(struct sock *sk) l2cap_pi(sk)->expected_ack_seq = 0; l2cap_pi(sk)->unacked_frames = 0; l2cap_pi(sk)->buffer_seq = 0; - l2cap_pi(sk)->num_to_ack = 0; + l2cap_pi(sk)->num_acked = 0; l2cap_pi(sk)->frames_sent = 0; setup_timer(&l2cap_pi(sk)->retrans_timer, @@ -3466,6 +3466,7 @@ static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, str u8 tx_seq = __get_txseq(rx_control); u8 req_seq = __get_reqseq(rx_control); u8 sar = rx_control >> L2CAP_CTRL_SAR_SHIFT; + int num_to_ack = (pi->tx_win/6) + 1; int err = 0; BT_DBG("sk %p rx_control 0x%4.4x len %d", sk, rx_control, skb->len); @@ -3553,8 +3554,8 @@ expected: __mod_ack_timer(); - pi->num_to_ack = (pi->num_to_ack + 1) % L2CAP_DEFAULT_NUM_TO_ACK; - if (pi->num_to_ack == L2CAP_DEFAULT_NUM_TO_ACK - 1) + pi->num_acked = (pi->num_acked + 1) % num_to_ack; + if (pi->num_acked == num_to_ack - 1) l2cap_send_ack(pi); return 0; -- cgit v1.2.3-70-g09d2 From 68d7f0ce911e41e463c45911be031cdf6a096fe8 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:41 -0300 Subject: Bluetooth: Enable option to configure Max Transmission value via sockopt MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the sockopt extension we can set a per-channel MaxTx value. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 2 ++ net/bluetooth/l2cap.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 059260bed4e..8942c2ffc58 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -55,6 +55,7 @@ struct l2cap_options { __u16 flush_to; __u8 mode; __u8 fcs; + __u8 max_tx; __u16 txwin_size; }; @@ -340,6 +341,7 @@ struct l2cap_pinfo { __u8 ident; __u8 tx_win; + __u8 max_tx; __u8 remote_tx_win; __u8 remote_max_tx; __u16 retrans_timeout; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index ff1466b2158..f9e4da2677a 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -783,6 +783,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->omtu = l2cap_pi(parent)->omtu; pi->mode = l2cap_pi(parent)->mode; pi->fcs = l2cap_pi(parent)->fcs; + pi->max_tx = l2cap_pi(parent)->max_tx; pi->tx_win = l2cap_pi(parent)->tx_win; pi->sec_level = l2cap_pi(parent)->sec_level; pi->role_switch = l2cap_pi(parent)->role_switch; @@ -791,6 +792,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->imtu = L2CAP_DEFAULT_MTU; pi->omtu = 0; pi->mode = L2CAP_MODE_BASIC; + pi->max_tx = max_transmit; pi->fcs = L2CAP_FCS_CRC16; pi->tx_win = tx_window; pi->sec_level = BT_SECURITY_LOW; @@ -1785,6 +1787,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us opts.flush_to = l2cap_pi(sk)->flush_to; opts.mode = l2cap_pi(sk)->mode; opts.fcs = l2cap_pi(sk)->fcs; + opts.max_tx = l2cap_pi(sk)->max_tx; opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win; len = min_t(unsigned int, sizeof(opts), optlen); @@ -1797,6 +1800,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us l2cap_pi(sk)->omtu = opts.omtu; l2cap_pi(sk)->mode = opts.mode; l2cap_pi(sk)->fcs = opts.fcs; + l2cap_pi(sk)->max_tx = opts.max_tx; l2cap_pi(sk)->tx_win = (__u8)opts.txwin_size; break; @@ -1912,6 +1916,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us opts.flush_to = l2cap_pi(sk)->flush_to; opts.mode = l2cap_pi(sk)->mode; opts.fcs = l2cap_pi(sk)->fcs; + opts.max_tx = l2cap_pi(sk)->max_tx; opts.txwin_size = (__u16)l2cap_pi(sk)->tx_win; len = min_t(unsigned int, len, sizeof(opts)); @@ -2331,7 +2336,7 @@ done: case L2CAP_MODE_ERTM: rfc.mode = L2CAP_MODE_ERTM; rfc.txwin_size = pi->tx_win; - rfc.max_transmit = max_transmit; + rfc.max_transmit = pi->max_tx; rfc.retrans_timeout = 0; rfc.monitor_timeout = 0; rfc.max_pdu_size = cpu_to_le16(L2CAP_DEFAULT_MAX_PDU_SIZE); -- cgit v1.2.3-70-g09d2 From 9a9c6a34416b3743c09c00f3d6708d9df3c21629 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:43 -0300 Subject: Bluetooth: Make hci_send_acl() void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit hci_send_acl can't fail, so we can make it void. This patch changes that and all the funcions that use hci_send_acl(). That change exposed a bug on sending connectionless data. We were not reporting the lenght send back to the user space. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 +- net/bluetooth/hci_core.c | 4 +-- net/bluetooth/l2cap.c | 73 +++++++++++++++------------------------- 3 files changed, 30 insertions(+), 49 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9830a88f487..4511df2a0d7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -636,7 +636,7 @@ int hci_register_notifier(struct notifier_block *nb); int hci_unregister_notifier(struct notifier_block *nb); int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen, void *param); -int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags); +void hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags); void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 1c9aef97f51..904f1e8a7a3 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1260,7 +1260,7 @@ static void hci_add_acl_hdr(struct sk_buff *skb, __u16 handle, __u16 flags) hdr->dlen = cpu_to_le16(len); } -int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) +void hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) { struct hci_dev *hdev = conn->hdev; struct sk_buff *list; @@ -1303,7 +1303,7 @@ int hci_send_acl(struct hci_conn *conn, struct sk_buff *skb, __u16 flags) tasklet_schedule(&hdev->tx_task); - return 0; + return; } EXPORT_SYMBOL(hci_send_acl); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 6b08f4d7c87..7e74d5be16e 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -330,19 +330,19 @@ static inline u8 l2cap_get_ident(struct l2cap_conn *conn) return id; } -static inline int l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) +static inline void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) { struct sk_buff *skb = l2cap_build_cmd(conn, code, ident, len, data); BT_DBG("code 0x%2.2x", code); if (!skb) - return -ENOMEM; + return; - return hci_send_acl(conn->hcon, skb, 0); + hci_send_acl(conn->hcon, skb, 0); } -static inline int l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) +static inline void l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) { struct sk_buff *skb; struct l2cap_hdr *lh; @@ -369,7 +369,7 @@ static inline int l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) skb = bt_skb_alloc(count, GFP_ATOMIC); if (!skb) - return -ENOMEM; + return; lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); lh->len = cpu_to_le16(hlen - L2CAP_HDR_SIZE); @@ -381,10 +381,10 @@ static inline int l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) put_unaligned_le16(fcs, skb_put(skb, 2)); } - return hci_send_acl(pi->conn->hcon, skb, 0); + hci_send_acl(pi->conn->hcon, skb, 0); } -static inline int l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) +static inline void l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) { if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) control |= L2CAP_SUPER_RCV_NOT_READY; @@ -393,7 +393,7 @@ static inline int l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; - return l2cap_send_sframe(pi, control); + l2cap_send_sframe(pi, control); } static void l2cap_do_start(struct sock *sk) @@ -1289,18 +1289,13 @@ static void l2cap_drop_acked_frames(struct sock *sk) return; } -static inline int l2cap_do_send(struct sock *sk, struct sk_buff *skb) +static inline void l2cap_do_send(struct sock *sk, struct sk_buff *skb) { struct l2cap_pinfo *pi = l2cap_pi(sk); - int err; BT_DBG("sk %p, skb %p len %d", sk, skb, skb->len); - err = hci_send_acl(pi->conn->hcon, skb, 0); - if (err < 0) - kfree_skb(skb); - - return err; + hci_send_acl(pi->conn->hcon, skb, 0); } static int l2cap_streaming_send(struct sock *sk) @@ -1308,7 +1303,6 @@ static int l2cap_streaming_send(struct sock *sk) struct sk_buff *skb, *tx_skb; struct l2cap_pinfo *pi = l2cap_pi(sk); u16 control, fcs; - int err; while ((skb = sk->sk_send_head)) { tx_skb = skb_clone(skb, GFP_ATOMIC); @@ -1322,11 +1316,7 @@ static int l2cap_streaming_send(struct sock *sk) put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2); } - err = l2cap_do_send(sk, tx_skb); - if (err < 0) { - l2cap_send_disconn_req(pi->conn, sk); - return err; - } + l2cap_do_send(sk, tx_skb); pi->next_tx_seq = (pi->next_tx_seq + 1) % 64; @@ -1346,7 +1336,6 @@ static int l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) struct l2cap_pinfo *pi = l2cap_pi(sk); struct sk_buff *skb, *tx_skb; u16 control, fcs; - int err; skb = skb_peek(TX_QUEUE(sk)); do { @@ -1375,11 +1364,7 @@ static int l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) put_unaligned_le16(fcs, tx_skb->data + tx_skb->len - 2); } - err = l2cap_do_send(sk, tx_skb); - if (err < 0) { - l2cap_send_disconn_req(pi->conn, sk); - return err; - } + l2cap_do_send(sk, tx_skb); break; } while(1); return 0; @@ -1390,7 +1375,7 @@ static int l2cap_ertm_send(struct sock *sk) struct sk_buff *skb, *tx_skb; struct l2cap_pinfo *pi = l2cap_pi(sk); u16 control, fcs; - int err, nsent = 0; + int nsent = 0; if (pi->conn_state & L2CAP_CONN_WAIT_F) return 0; @@ -1423,11 +1408,8 @@ static int l2cap_ertm_send(struct sock *sk) put_unaligned_le16(fcs, skb->data + tx_skb->len - 2); } - err = l2cap_do_send(sk, tx_skb); - if (err < 0) { - l2cap_send_disconn_req(pi->conn, sk); - return err; - } + l2cap_do_send(sk, tx_skb); + __mod_retrans_timer(); bt_cb(skb)->tx_seq = pi->next_tx_seq; @@ -1447,7 +1429,7 @@ static int l2cap_ertm_send(struct sock *sk) return nsent; } -static int l2cap_send_ack(struct l2cap_pinfo *pi) +static void l2cap_send_ack(struct l2cap_pinfo *pi) { struct sock *sk = (struct sock *)pi; u16 control = 0; @@ -1456,15 +1438,15 @@ static int l2cap_send_ack(struct l2cap_pinfo *pi) if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { control |= L2CAP_SUPER_RCV_NOT_READY; - return l2cap_send_sframe(pi, control); + l2cap_send_sframe(pi, control); + return; } else if (l2cap_ertm_send(sk) == 0) { control |= L2CAP_SUPER_RCV_READY; - return l2cap_send_sframe(pi, control); + l2cap_send_sframe(pi, control); } - return 0; } -static int l2cap_send_srejtail(struct sock *sk) +static void l2cap_send_srejtail(struct sock *sk) { struct srej_list *tail; u16 control; @@ -1476,8 +1458,6 @@ static int l2cap_send_srejtail(struct sock *sk) control |= tail->tx_seq << L2CAP_CTRL_REQSEQ_SHIFT; l2cap_send_sframe(l2cap_pi(sk), control); - - return 0; } static inline int l2cap_skbuff_fromiovec(struct sock *sk, struct msghdr *msg, int len, int count, struct sk_buff *skb) @@ -1687,10 +1667,12 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms /* Connectionless channel */ if (sk->sk_type == SOCK_DGRAM) { skb = l2cap_create_connless_pdu(sk, msg, len); - if (IS_ERR(skb)) + if (IS_ERR(skb)) { err = PTR_ERR(skb); - else - err = l2cap_do_send(sk, skb); + } else { + l2cap_do_send(sk, skb); + err = len; + } goto done; } @@ -1709,9 +1691,8 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms goto done; } - err = l2cap_do_send(sk, skb); - if (!err) - err = len; + l2cap_do_send(sk, skb); + err = len; break; case L2CAP_MODE_ERTM: -- cgit v1.2.3-70-g09d2 From 1890d36bb556a27684ad29654a9898ab9a5f57ee Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:44 -0300 Subject: Bluetooth: Implement Local Busy Condition handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Supports Local Busy condition handling through a waitqueue that wake ups each 200ms and try to push the packets to the upper layer. If it can push all the queue then it leaves the Local Busy state. The patch modifies the behaviour of l2cap_ertm_reassembly_sdu() to support retry of the push operation. Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 6 ++ net/bluetooth/l2cap.c | 187 +++++++++++++++++++++++++++++++++++++----- 2 files changed, 172 insertions(+), 21 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 8942c2ffc58..d0185cc04c1 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -35,6 +35,7 @@ #define L2CAP_DEFAULT_MONITOR_TO 12000 /* 12 seconds */ #define L2CAP_DEFAULT_MAX_PDU_SIZE 672 #define L2CAP_DEFAULT_ACK_TO 200 +#define L2CAP_LOCAL_BUSY_TRIES 12 #define L2CAP_CONN_TIMEOUT (40000) /* 40 seconds */ #define L2CAP_INFO_TIMEOUT (4000) /* 4 seconds */ @@ -294,6 +295,7 @@ struct l2cap_conn { #define l2cap_pi(sk) ((struct l2cap_pinfo *) sk) #define TX_QUEUE(sk) (&l2cap_pi(sk)->tx_queue) #define SREJ_QUEUE(sk) (&l2cap_pi(sk)->srej_queue) +#define BUSY_QUEUE(sk) (&l2cap_pi(sk)->busy_queue) #define SREJ_LIST(sk) (&l2cap_pi(sk)->srej_l.list) struct srej_list { @@ -356,6 +358,8 @@ struct l2cap_pinfo { struct timer_list ack_timer; struct sk_buff_head tx_queue; struct sk_buff_head srej_queue; + struct sk_buff_head busy_queue; + struct work_struct busy_work; struct srej_list srej_l; struct l2cap_conn *conn; struct sock *next_c; @@ -383,6 +387,8 @@ struct l2cap_pinfo { #define L2CAP_CONN_LOCAL_BUSY 0x0040 #define L2CAP_CONN_REJ_ACT 0x0080 #define L2CAP_CONN_SEND_FBIT 0x0100 +#define L2CAP_CONN_RNR_SENT 0x0200 +#define L2CAP_CONN_SAR_RETRY 0x0400 #define __mod_retrans_timer() mod_timer(&l2cap_pi(sk)->retrans_timer, \ jiffies + msecs_to_jiffies(L2CAP_DEFAULT_RETRANS_TO)); diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 481cec22ef9..103e4b54a86 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -68,10 +68,14 @@ static u8 l2cap_fixed_chan[8] = { 0x02, }; static const struct proto_ops l2cap_sock_ops; +static struct workqueue_struct *_busy_wq; + static struct bt_sock_list l2cap_sk_list = { .lock = __RW_LOCK_UNLOCKED(l2cap_sk_list.lock) }; +static void l2cap_busy_work(struct work_struct *work); + static void __l2cap_sock_close(struct sock *sk, int reason); static void l2cap_sock_close(struct sock *sk); static void l2cap_sock_kill(struct sock *sk); @@ -386,9 +390,10 @@ static inline void l2cap_send_sframe(struct l2cap_pinfo *pi, u16 control) static inline void l2cap_send_rr_or_rnr(struct l2cap_pinfo *pi, u16 control) { - if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) + if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { control |= L2CAP_SUPER_RCV_NOT_READY; - else + pi->conn_state |= L2CAP_CONN_RNR_SENT; + } else control |= L2CAP_SUPER_RCV_READY; control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; @@ -816,6 +821,7 @@ static void l2cap_sock_init(struct sock *sk, struct sock *parent) pi->flush_to = L2CAP_DEFAULT_FLUSH_TO; skb_queue_head_init(TX_QUEUE(sk)); skb_queue_head_init(SREJ_QUEUE(sk)); + skb_queue_head_init(BUSY_QUEUE(sk)); INIT_LIST_HEAD(SREJ_LIST(sk)); } @@ -1439,6 +1445,7 @@ static void l2cap_send_ack(struct l2cap_pinfo *pi) if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { control |= L2CAP_SUPER_RCV_NOT_READY; + pi->conn_state |= L2CAP_CONN_RNR_SENT; l2cap_send_sframe(pi, control); return; } else if (l2cap_ertm_send(sk) == 0) { @@ -2279,6 +2286,9 @@ static inline void l2cap_ertm_init(struct sock *sk) l2cap_ack_timeout, (unsigned long) sk); __skb_queue_head_init(SREJ_QUEUE(sk)); + __skb_queue_head_init(BUSY_QUEUE(sk)); + + INIT_WORK(&l2cap_pi(sk)->busy_work, l2cap_busy_work); } static int l2cap_mode_supported(__u8 mode, __u32 feat_mask) @@ -3046,6 +3056,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { skb_queue_purge(SREJ_QUEUE(sk)); + skb_queue_purge(BUSY_QUEUE(sk)); del_timer(&l2cap_pi(sk)->retrans_timer); del_timer(&l2cap_pi(sk)->monitor_timer); del_timer(&l2cap_pi(sk)->ack_timer); @@ -3077,6 +3088,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd if (l2cap_pi(sk)->mode == L2CAP_MODE_ERTM) { skb_queue_purge(SREJ_QUEUE(sk)); + skb_queue_purge(BUSY_QUEUE(sk)); del_timer(&l2cap_pi(sk)->retrans_timer); del_timer(&l2cap_pi(sk)->monitor_timer); del_timer(&l2cap_pi(sk)->ack_timer); @@ -3287,6 +3299,7 @@ static inline void l2cap_send_i_or_rr_or_rnr(struct sock *sk) if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { control |= L2CAP_SUPER_RCV_NOT_READY | L2CAP_CTRL_FINAL; l2cap_send_sframe(pi, control); + pi->conn_state |= L2CAP_CONN_RNR_SENT; pi->conn_state &= ~L2CAP_CONN_SEND_FBIT; } @@ -3338,7 +3351,7 @@ static int l2cap_ertm_reassembly_sdu(struct sock *sk, struct sk_buff *skb, u16 c { struct l2cap_pinfo *pi = l2cap_pi(sk); struct sk_buff *_skb; - int err = 0; + int err; switch (control & L2CAP_CTRL_SAR) { case L2CAP_SDU_UNSEGMENTED: @@ -3356,16 +3369,18 @@ static int l2cap_ertm_reassembly_sdu(struct sock *sk, struct sk_buff *skb, u16 c goto drop; pi->sdu_len = get_unaligned_le16(skb->data); - skb_pull(skb, 2); if (pi->sdu_len > pi->imtu) goto disconnect; pi->sdu = bt_skb_alloc(pi->sdu_len, GFP_ATOMIC); - if (!pi->sdu) { - err = -ENOMEM; - break; - } + if (!pi->sdu) + return -ENOMEM; + + /* pull sdu_len bytes only after alloc, because of Local Busy + * condition we have to be sure that this will be executed + * only once, i.e., when alloc does not fail */ + skb_pull(skb, 2); memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); @@ -3395,28 +3410,40 @@ static int l2cap_ertm_reassembly_sdu(struct sock *sk, struct sk_buff *skb, u16 c if (!pi->sdu) goto disconnect; - memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); + if (!(pi->conn_state & L2CAP_CONN_SAR_RETRY)) { + memcpy(skb_put(pi->sdu, skb->len), skb->data, skb->len); - pi->conn_state &= ~L2CAP_CONN_SAR_SDU; - pi->partial_sdu_len += skb->len; + pi->partial_sdu_len += skb->len; - if (pi->partial_sdu_len > pi->imtu) - goto drop; + if (pi->partial_sdu_len > pi->imtu) + goto drop; - if (pi->partial_sdu_len != pi->sdu_len) - goto drop; + if (pi->partial_sdu_len != pi->sdu_len) + goto drop; + } _skb = skb_clone(pi->sdu, GFP_ATOMIC); + if (!_skb) { + pi->conn_state |= L2CAP_CONN_SAR_RETRY; + return -ENOMEM; + } + err = sock_queue_rcv_skb(sk, _skb); - if (err < 0) + if (err < 0) { kfree_skb(_skb); + pi->conn_state |= L2CAP_CONN_SAR_RETRY; + return err; + } + + pi->conn_state &= ~L2CAP_CONN_SAR_RETRY; + pi->conn_state &= ~L2CAP_CONN_SAR_SDU; kfree_skb(pi->sdu); break; } kfree_skb(skb); - return err; + return 0; drop: kfree_skb(pi->sdu); @@ -3428,6 +3455,115 @@ disconnect: return 0; } +static void l2cap_busy_work(struct work_struct *work) +{ + DECLARE_WAITQUEUE(wait, current); + struct l2cap_pinfo *pi = + container_of(work, struct l2cap_pinfo, busy_work); + struct sock *sk = (struct sock *)pi; + int n_tries = 0, timeo = HZ/5, err; + struct sk_buff *skb; + u16 control; + + lock_sock(sk); + + add_wait_queue(sk->sk_sleep, &wait); + while ((skb = skb_peek(BUSY_QUEUE(sk)))) { + set_current_state(TASK_INTERRUPTIBLE); + + if (n_tries++ > L2CAP_LOCAL_BUSY_TRIES) { + err = -EBUSY; + l2cap_send_disconn_req(pi->conn, sk); + goto done; + } + + if (!timeo) + timeo = HZ/5; + + if (signal_pending(current)) { + err = sock_intr_errno(timeo); + goto done; + } + + release_sock(sk); + timeo = schedule_timeout(timeo); + lock_sock(sk); + + err = sock_error(sk); + if (err) + goto done; + + while ((skb = skb_dequeue(BUSY_QUEUE(sk)))) { + control = bt_cb(skb)->sar << L2CAP_CTRL_SAR_SHIFT; + err = l2cap_ertm_reassembly_sdu(sk, skb, control); + if (err < 0) { + skb_queue_head(BUSY_QUEUE(sk), skb); + break; + } + + pi->buffer_seq = (pi->buffer_seq + 1) % 64; + } + + if (!skb) + break; + } + + if (!(pi->conn_state & L2CAP_CONN_RNR_SENT)) + goto done; + + control = pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + control |= L2CAP_SUPER_RCV_READY | L2CAP_CTRL_POLL; + l2cap_send_sframe(pi, control); + l2cap_pi(sk)->retry_count = 1; + + del_timer(&pi->retrans_timer); + __mod_monitor_timer(); + + l2cap_pi(sk)->conn_state |= L2CAP_CONN_WAIT_F; + +done: + pi->conn_state &= ~L2CAP_CONN_LOCAL_BUSY; + pi->conn_state &= ~L2CAP_CONN_RNR_SENT; + + set_current_state(TASK_RUNNING); + remove_wait_queue(sk->sk_sleep, &wait); + + release_sock(sk); +} + +static int l2cap_push_rx_skb(struct sock *sk, struct sk_buff *skb, u16 control) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + int sctrl, err; + + if (pi->conn_state & L2CAP_CONN_LOCAL_BUSY) { + bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; + __skb_queue_tail(BUSY_QUEUE(sk), skb); + return -EBUSY; + } + + err = l2cap_ertm_reassembly_sdu(sk, skb, control); + if (err >= 0) { + pi->buffer_seq = (pi->buffer_seq + 1) % 64; + return err; + } + + /* Busy Condition */ + pi->conn_state |= L2CAP_CONN_LOCAL_BUSY; + bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; + __skb_queue_tail(BUSY_QUEUE(sk), skb); + + sctrl = pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + sctrl |= L2CAP_SUPER_RCV_NOT_READY; + l2cap_send_sframe(pi, sctrl); + + pi->conn_state |= L2CAP_CONN_RNR_SENT; + + queue_work(_busy_wq, &pi->busy_work); + + return err; +} + static int l2cap_streaming_reassembly_sdu(struct sock *sk, struct sk_buff *skb, u16 control) { struct l2cap_pinfo *pi = l2cap_pi(sk); @@ -3614,6 +3750,9 @@ static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, str goto drop; } + if (pi->conn_state == L2CAP_CONN_LOCAL_BUSY) + goto drop; + if (pi->conn_state & L2CAP_CONN_SREJ_SENT) { struct srej_list *first; @@ -3662,6 +3801,7 @@ static inline int l2cap_data_channel_iframe(struct sock *sk, u16 rx_control, str pi->buffer_seq_srej = pi->buffer_seq; __skb_queue_head_init(SREJ_QUEUE(sk)); + __skb_queue_head_init(BUSY_QUEUE(sk)); l2cap_add_to_srej_queue(sk, skb, tx_seq, sar); pi->conn_state |= L2CAP_CONN_SEND_PBIT; @@ -3691,11 +3831,9 @@ expected: } } - pi->buffer_seq = (pi->buffer_seq + 1) % 64; - - err = l2cap_ertm_reassembly_sdu(sk, skb, rx_control); + err = l2cap_push_rx_skb(sk, skb, rx_control); if (err < 0) - return err; + return 0; __mod_ack_timer(); @@ -4406,6 +4544,10 @@ static int __init l2cap_init(void) if (err < 0) return err; + _busy_wq = create_singlethread_workqueue("l2cap"); + if (!_busy_wq) + goto error; + err = bt_sock_register(BTPROTO_L2CAP, &l2cap_sock_family_ops); if (err < 0) { BT_ERR("L2CAP socket registration failed"); @@ -4440,6 +4582,9 @@ static void __exit l2cap_exit(void) { debugfs_remove(l2cap_debugfs); + flush_workqueue(_busy_wq); + destroy_workqueue(_busy_wq); + if (bt_sock_unregister(BTPROTO_L2CAP) < 0) BT_ERR("L2CAP socket unregistration failed"); -- cgit v1.2.3-70-g09d2 From dfc909befbfe967bd7f46ef33b6969c1b7f3cf42 Mon Sep 17 00:00:00 2001 From: "Gustavo F. Padovan" Date: Sat, 1 May 2010 16:15:45 -0300 Subject: Bluetooth: Fix race condition on l2cap_ertm_send() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit l2cap_ertm_send() can be called both from user context and bottom half context. The socket locks for that contexts are different, the user context uses a mutex(which can sleep) and the second one uses a spinlock_bh. That creates a race condition when we have interruptions on both contexts at the same time. The better way to solve this is to add a new spinlock to lock l2cap_ertm_send() and the vars it access. The other solution was to defer l2cap_ertm_send() with a workqueue, but we the sending process already has one defer on the hci layer. It's not a good idea add another one. The patch refactor the code to create l2cap_retransmit_frames(), then we encapulate the lock of l2cap_ertm_send() for some call. It also changes l2cap_retransmit_frame() to l2cap_retransmit_one_frame() to avoid confusion Signed-off-by: Gustavo F. Padovan Reviewed-by: João Paulo Rechi Vita Signed-off-by: Marcel Holtmann --- include/net/bluetooth/l2cap.h | 1 + net/bluetooth/l2cap.c | 99 ++++++++++++++++++++++++++++--------------- 2 files changed, 67 insertions(+), 33 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index d0185cc04c1..7c695bfd853 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -353,6 +353,7 @@ struct l2cap_pinfo { __le16 sport; + spinlock_t send_lock; struct timer_list retrans_timer; struct timer_list monitor_timer; struct timer_list ack_timer; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 9d514f9dbc0..fe663e9c668 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1368,7 +1368,7 @@ static int l2cap_streaming_send(struct sock *sk) return 0; } -static void l2cap_retransmit_frame(struct sock *sk, u8 tx_seq) +static void l2cap_retransmit_one_frame(struct sock *sk, u8 tx_seq) { struct l2cap_pinfo *pi = l2cap_pi(sk); struct sk_buff *skb, *tx_skb; @@ -1467,10 +1467,29 @@ static int l2cap_ertm_send(struct sock *sk) return nsent; } +static int l2cap_retransmit_frames(struct sock *sk) +{ + struct l2cap_pinfo *pi = l2cap_pi(sk); + int ret; + + spin_lock_bh(&pi->send_lock); + + if (!skb_queue_empty(TX_QUEUE(sk))) + sk->sk_send_head = TX_QUEUE(sk)->next; + + pi->next_tx_seq = pi->expected_ack_seq; + ret = l2cap_ertm_send(sk); + + spin_unlock_bh(&pi->send_lock); + + return ret; +} + static void l2cap_send_ack(struct l2cap_pinfo *pi) { struct sock *sk = (struct sock *)pi; u16 control = 0; + int nframes; control |= pi->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; @@ -1479,10 +1498,17 @@ static void l2cap_send_ack(struct l2cap_pinfo *pi) pi->conn_state |= L2CAP_CONN_RNR_SENT; l2cap_send_sframe(pi, control); return; - } else if (l2cap_ertm_send(sk) == 0) { - control |= L2CAP_SUPER_RCV_READY; - l2cap_send_sframe(pi, control); } + + spin_lock_bh(&pi->send_lock); + nframes = l2cap_ertm_send(sk); + spin_unlock_bh(&pi->send_lock); + + if (nframes > 0) + return; + + control |= L2CAP_SUPER_RCV_READY; + l2cap_send_sframe(pi, control); } static void l2cap_send_srejtail(struct sock *sk) @@ -1673,8 +1699,10 @@ static inline int l2cap_sar_segment_sdu(struct sock *sk, struct msghdr *msg, siz size += buflen; } skb_queue_splice_tail(&sar_queue, TX_QUEUE(sk)); + spin_lock_bh(&pi->send_lock); if (sk->sk_send_head == NULL) sk->sk_send_head = sar_queue.next; + spin_unlock_bh(&pi->send_lock); return size; } @@ -1745,8 +1773,15 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms goto done; } __skb_queue_tail(TX_QUEUE(sk), skb); + + if (pi->mode == L2CAP_MODE_ERTM) + spin_lock_bh(&pi->send_lock); + if (sk->sk_send_head == NULL) sk->sk_send_head = skb; + + if (pi->mode == L2CAP_MODE_ERTM) + spin_unlock_bh(&pi->send_lock); } else { /* Segment SDU into multiples PDUs */ err = l2cap_sar_segment_sdu(sk, msg, len); @@ -1754,10 +1789,13 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms goto done; } - if (pi->mode == L2CAP_MODE_STREAMING) + if (pi->mode == L2CAP_MODE_STREAMING) { err = l2cap_streaming_send(sk); - else + } else { + spin_lock_bh(&pi->send_lock); err = l2cap_ertm_send(sk); + spin_unlock_bh(&pi->send_lock); + } if (err >= 0) err = len; @@ -2321,6 +2359,7 @@ static inline void l2cap_ertm_init(struct sock *sk) __skb_queue_head_init(SREJ_QUEUE(sk)); __skb_queue_head_init(BUSY_QUEUE(sk)); + spin_lock_init(&l2cap_pi(sk)->send_lock); INIT_WORK(&l2cap_pi(sk)->busy_work, l2cap_busy_work); } @@ -3340,7 +3379,9 @@ static inline void l2cap_send_i_or_rr_or_rnr(struct sock *sk) if (pi->conn_state & L2CAP_CONN_REMOTE_BUSY && pi->unacked_frames > 0) __mod_retrans_timer(); + spin_lock_bh(&pi->send_lock); l2cap_ertm_send(sk); + spin_unlock_bh(&pi->send_lock); if (!(pi->conn_state & L2CAP_CONN_LOCAL_BUSY) && pi->frames_sent == 0) { @@ -3857,12 +3898,8 @@ expected: if (rx_control & L2CAP_CTRL_FINAL) { if (pi->conn_state & L2CAP_CONN_REJ_ACT) pi->conn_state &= ~L2CAP_CONN_REJ_ACT; - else { - if (!skb_queue_empty(TX_QUEUE(sk))) - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; - l2cap_ertm_send(sk); - } + else + l2cap_retransmit_frames(sk); } err = l2cap_push_rx_skb(sk, skb, rx_control); @@ -3907,12 +3944,8 @@ static inline void l2cap_data_channel_rrframe(struct sock *sk, u16 rx_control) if (pi->conn_state & L2CAP_CONN_REJ_ACT) pi->conn_state &= ~L2CAP_CONN_REJ_ACT; - else { - if (!skb_queue_empty(TX_QUEUE(sk))) - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; - l2cap_ertm_send(sk); - } + else + l2cap_retransmit_frames(sk); } else { if ((pi->conn_state & L2CAP_CONN_REMOTE_BUSY) && @@ -3920,10 +3953,13 @@ static inline void l2cap_data_channel_rrframe(struct sock *sk, u16 rx_control) __mod_retrans_timer(); pi->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; - if (pi->conn_state & L2CAP_CONN_SREJ_SENT) + if (pi->conn_state & L2CAP_CONN_SREJ_SENT) { l2cap_send_ack(pi); - else + } else { + spin_lock_bh(&pi->send_lock); l2cap_ertm_send(sk); + spin_unlock_bh(&pi->send_lock); + } } } @@ -3940,17 +3976,10 @@ static inline void l2cap_data_channel_rejframe(struct sock *sk, u16 rx_control) if (rx_control & L2CAP_CTRL_FINAL) { if (pi->conn_state & L2CAP_CONN_REJ_ACT) pi->conn_state &= ~L2CAP_CONN_REJ_ACT; - else { - if (!skb_queue_empty(TX_QUEUE(sk))) - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; - l2cap_ertm_send(sk); - } + else + l2cap_retransmit_frames(sk); } else { - if (!skb_queue_empty(TX_QUEUE(sk))) - sk->sk_send_head = TX_QUEUE(sk)->next; - pi->next_tx_seq = pi->expected_ack_seq; - l2cap_ertm_send(sk); + l2cap_retransmit_frames(sk); if (pi->conn_state & L2CAP_CONN_WAIT_F) pi->conn_state |= L2CAP_CONN_REJ_ACT; @@ -3966,8 +3995,12 @@ static inline void l2cap_data_channel_srejframe(struct sock *sk, u16 rx_control) if (rx_control & L2CAP_CTRL_POLL) { pi->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(sk); - l2cap_retransmit_frame(sk, tx_seq); + l2cap_retransmit_one_frame(sk, tx_seq); + + spin_lock_bh(&pi->send_lock); l2cap_ertm_send(sk); + spin_unlock_bh(&pi->send_lock); + if (pi->conn_state & L2CAP_CONN_WAIT_F) { pi->srej_save_reqseq = tx_seq; pi->conn_state |= L2CAP_CONN_SREJ_ACT; @@ -3977,9 +4010,9 @@ static inline void l2cap_data_channel_srejframe(struct sock *sk, u16 rx_control) pi->srej_save_reqseq == tx_seq) pi->conn_state &= ~L2CAP_CONN_SREJ_ACT; else - l2cap_retransmit_frame(sk, tx_seq); + l2cap_retransmit_one_frame(sk, tx_seq); } else { - l2cap_retransmit_frame(sk, tx_seq); + l2cap_retransmit_one_frame(sk, tx_seq); if (pi->conn_state & L2CAP_CONN_WAIT_F) { pi->srej_save_reqseq = tx_seq; pi->conn_state |= L2CAP_CONN_SREJ_ACT; -- cgit v1.2.3-70-g09d2 From f48fd9c8cd746fdb055a97249a209c77dca0f710 Mon Sep 17 00:00:00 2001 From: Marcel Holtmann Date: Sat, 20 Mar 2010 15:20:04 +0100 Subject: Bluetooth: Create per controller workqueue Instead of having a global workqueue for all controllers, it makes more sense to have a workqueue per controller. Signed-off-by: Marcel Holtmann --- include/net/bluetooth/hci_core.h | 2 ++ net/bluetooth/hci_core.c | 14 ++++++++++++++ net/bluetooth/hci_sysfs.c | 16 +++------------- 3 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include/net') diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 4511df2a0d7..e42f6ed5421 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -107,6 +107,8 @@ struct hci_dev { unsigned long acl_last_tx; unsigned long sco_last_tx; + struct workqueue_struct *workqueue; + struct tasklet_struct cmd_task; struct tasklet_struct rx_task; struct tasklet_struct tx_task; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 904f1e8a7a3..5e83f8e0877 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include @@ -928,6 +929,10 @@ int hci_register_dev(struct hci_dev *hdev) write_unlock_bh(&hci_dev_list_lock); + hdev->workqueue = create_singlethread_workqueue(hdev->name); + if (!hdev->workqueue) + goto nomem; + hci_register_sysfs(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, @@ -942,6 +947,13 @@ int hci_register_dev(struct hci_dev *hdev) hci_notify(hdev, HCI_DEV_REG); return id; + +nomem: + write_lock_bh(&hci_dev_list_lock); + list_del(&hdev->list); + write_unlock_bh(&hci_dev_list_lock); + + return -ENOMEM; } EXPORT_SYMBOL(hci_register_dev); @@ -970,6 +982,8 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_unregister_sysfs(hdev); + destroy_workqueue(hdev->workqueue); + __hci_dev_put(hdev); return 0; diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 0e8e1a59856..a978449ab04 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -14,8 +14,6 @@ static struct class *bt_class; struct dentry *bt_debugfs = NULL; EXPORT_SYMBOL_GPL(bt_debugfs); -static struct workqueue_struct *bt_workq; - static inline char *link_typetostr(int type) { switch (type) { @@ -161,14 +159,14 @@ void hci_conn_add_sysfs(struct hci_conn *conn) { BT_DBG("conn %p", conn); - queue_work(bt_workq, &conn->work_add); + queue_work(conn->hdev->workqueue, &conn->work_add); } void hci_conn_del_sysfs(struct hci_conn *conn) { BT_DBG("conn %p", conn); - queue_work(bt_workq, &conn->work_del); + queue_work(conn->hdev->workqueue, &conn->work_del); } static inline char *host_bustostr(int bus) @@ -487,17 +485,11 @@ void hci_unregister_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - bt_workq = create_singlethread_workqueue("bluetooth"); - if (!bt_workq) - return -ENOMEM; - bt_debugfs = debugfs_create_dir("bluetooth", NULL); bt_class = class_create(THIS_MODULE, "bluetooth"); - if (IS_ERR(bt_class)) { - destroy_workqueue(bt_workq); + if (IS_ERR(bt_class)) return PTR_ERR(bt_class); - } return 0; } @@ -507,6 +499,4 @@ void bt_sysfs_cleanup(void) class_destroy(bt_class); debugfs_remove_recursive(bt_debugfs); - - destroy_workqueue(bt_workq); } -- cgit v1.2.3-70-g09d2 From c476efbcde5ba58b81ac752f4a894d6db8e17d94 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 11 May 2010 14:40:48 +0200 Subject: ipv6: ip6mr: move unres_queue and timer to per-namespace data The unres_queue is currently shared between all namespaces. Following patches will additionally allow to create multiple multicast routing tables in each namespace. Having a single shared queue for all these users seems to excessive, move the queue and the cleanup timer to the per-namespace data to unshare it. As a side-effect, this fixes a bug in the seq file iteration functions: the first entry returned is always from the current namespace, entries returned after that may belong to any namespace. Signed-off-by: Patrick McHardy --- include/net/netns/ipv6.h | 2 ++ net/ipv6/ip6mr.c | 74 +++++++++++++++++++++--------------------------- 2 files changed, 35 insertions(+), 41 deletions(-) (limited to 'include/net') diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 1f11ebc2215..43d842ab004 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -60,6 +60,8 @@ struct netns_ipv6 { struct sock *igmp_sk; #ifdef CONFIG_IPV6_MROUTE struct sock *mroute6_sk; + struct timer_list ipmr_expire_timer; + struct mfc6_cache *mfc6_unres_queue; struct mfc6_cache **mfc6_cache_array; struct mif_device *vif6_table; int maxvif; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e0b530ca394..7236030e403 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -63,8 +63,6 @@ static DEFINE_RWLOCK(mrt_lock); #define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL) -static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */ - /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -84,8 +82,6 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); static void mroute_clean_tables(struct net *net); -static struct timer_list ipmr_expire_timer; - #ifdef CONFIG_PROC_FS @@ -110,11 +106,10 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, return mfc; read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &net->ipv6.mfc6_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) - if (net_eq(mfc6_net(mfc), net) && - pos-- == 0) + for (mfc = net->ipv6.mfc6_unres_queue; mfc; mfc = mfc->next) + if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -244,7 +239,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (mfc->next) return mfc->next; - if (it->cache == &mfc_unres_queue) + if (it->cache == &net->ipv6.mfc6_unres_queue) goto end_of_list; BUG_ON(it->cache != net->ipv6.mfc6_cache_array); @@ -257,11 +252,11 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &mfc_unres_queue; + it->cache = &net->ipv6.mfc6_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = mfc_unres_queue; + mfc = net->ipv6.mfc6_unres_queue; if (mfc) return mfc; @@ -277,7 +272,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - if (it->cache == &mfc_unres_queue) + if (it->cache == &net->ipv6.mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); else if (it->cache == net->ipv6.mfc6_cache_array) read_unlock(&mrt_lock); @@ -301,7 +296,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->mf6c_parent); - if (it->cache != &mfc_unres_queue) { + if (it->cache != &net->ipv6.mfc6_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, @@ -559,15 +554,15 @@ static void ip6mr_destroy_unres(struct mfc6_cache *c) } -/* Single timer process for all the unresolved queue. */ +/* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(unsigned long dummy) +static void ipmr_do_expire_process(struct net *net) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; struct mfc6_cache *c, **cp; - cp = &mfc_unres_queue; + cp = &net->ipv6.mfc6_unres_queue; while ((c = *cp) != NULL) { if (time_after(c->mfc_un.unres.expires, now)) { @@ -583,19 +578,21 @@ static void ipmr_do_expire_process(unsigned long dummy) ip6mr_destroy_unres(c); } - if (mfc_unres_queue != NULL) - mod_timer(&ipmr_expire_timer, jiffies + expires); + if (net->ipv6.mfc6_unres_queue != NULL) + mod_timer(&net->ipv6.ipmr_expire_timer, jiffies + expires); } -static void ipmr_expire_process(unsigned long dummy) +static void ipmr_expire_process(unsigned long arg) { + struct net *net = (struct net *)arg; + if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&ipmr_expire_timer, jiffies + 1); + mod_timer(&net->ipv6.ipmr_expire_timer, jiffies + 1); return; } - if (mfc_unres_queue != NULL) - ipmr_do_expire_process(dummy); + if (net->ipv6.mfc6_unres_queue != NULL) + ipmr_do_expire_process(net); spin_unlock(&mfc_unres_lock); } @@ -880,9 +877,8 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - for (c = mfc_unres_queue; c; c = c->next) { - if (net_eq(mfc6_net(c), net) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + for (c = net->ipv6.mfc6_unres_queue; c; c = c->next) { + if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) break; } @@ -923,10 +919,10 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) } atomic_inc(&net->ipv6.cache_resolve_queue_len); - c->next = mfc_unres_queue; - mfc_unres_queue = c; + c->next = net->ipv6.mfc6_unres_queue; + net->ipv6.mfc6_unres_queue = c; - ipmr_do_expire_process(1); + ipmr_do_expire_process(net); } /* @@ -1019,6 +1015,9 @@ static int __net_init ip6mr_net_init(struct net *net) goto fail_mfc6_cache; } + setup_timer(&net->ipv6.ipmr_expire_timer, ipmr_expire_process, + (unsigned long)net); + #ifdef CONFIG_IPV6_PIMSM_V2 net->ipv6.mroute_reg_vif_num = -1; #endif @@ -1050,6 +1049,7 @@ static void __net_exit ip6mr_net_exit(struct net *net) proc_net_remove(net, "ip6_mr_cache"); proc_net_remove(net, "ip6_mr_vif"); #endif + del_timer(&net->ipv6.ipmr_expire_timer); mroute_clean_tables(net); kfree(net->ipv6.mfc6_cache_array); kfree(net->ipv6.vif6_table); @@ -1075,7 +1075,6 @@ int __init ip6_mr_init(void) if (err) goto reg_pernet_fail; - setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); err = register_netdevice_notifier(&ip6_mr_notifier); if (err) goto reg_notif_fail; @@ -1092,7 +1091,6 @@ add_proto_fail: unregister_netdevice_notifier(&ip6_mr_notifier); #endif reg_notif_fail: - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); reg_pernet_fail: kmem_cache_destroy(mrt_cachep); @@ -1102,7 +1100,6 @@ reg_pernet_fail: void ip6_mr_cleanup(void) { unregister_netdevice_notifier(&ip6_mr_notifier); - del_timer(&ipmr_expire_timer); unregister_pernet_subsys(&ip6mr_net_ops); kmem_cache_destroy(mrt_cachep); } @@ -1167,18 +1164,17 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) * need to send on the frames and tidy up. */ spin_lock_bh(&mfc_unres_lock); - for (cp = &mfc_unres_queue; (uc = *cp) != NULL; + for (cp = &net->ipv6.mfc6_unres_queue; (uc = *cp) != NULL; cp = &uc->next) { - if (net_eq(mfc6_net(uc), net) && - ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { *cp = uc->next; atomic_dec(&net->ipv6.cache_resolve_queue_len); break; } } - if (mfc_unres_queue == NULL) - del_timer(&ipmr_expire_timer); + if (net->ipv6.mfc6_unres_queue == NULL) + del_timer(&net->ipv6.ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (uc) { @@ -1230,12 +1226,8 @@ static void mroute_clean_tables(struct net *net) struct mfc6_cache *c, **cp; spin_lock_bh(&mfc_unres_lock); - cp = &mfc_unres_queue; + cp = &net->ipv6.mfc6_unres_queue; while ((c = *cp) != NULL) { - if (!net_eq(mfc6_net(c), net)) { - cp = &c->next; - continue; - } *cp = c->next; ip6mr_destroy_unres(c); } -- cgit v1.2.3-70-g09d2 From f30a77842129b5656360cc1f5db48a3fcfb64528 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 11 May 2010 14:40:51 +0200 Subject: ipv6: ip6mr: convert struct mfc_cache to struct list_head Signed-off-by: Patrick McHardy --- include/linux/mroute6.h | 2 +- include/net/netns/ipv6.h | 4 +- net/ipv6/ip6mr.c | 127 +++++++++++++++++++++++------------------------ 3 files changed, 65 insertions(+), 68 deletions(-) (limited to 'include/net') diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 04e2e54d040..94a0cb521ca 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -182,7 +182,7 @@ struct mif_device { #define VIFF_STATIC 0x8000 struct mfc6_cache { - struct mfc6_cache *next; /* Next entry on cache line */ + struct list_head list; struct in6_addr mf6c_mcastgrp; /* Group the entry belongs to */ struct in6_addr mf6c_origin; /* Source of packet */ mifi_t mf6c_parent; /* Source interface */ diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 43d842ab004..9cb3b5f2cd7 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -61,8 +61,8 @@ struct netns_ipv6 { #ifdef CONFIG_IPV6_MROUTE struct sock *mroute6_sk; struct timer_list ipmr_expire_timer; - struct mfc6_cache *mfc6_unres_queue; - struct mfc6_cache **mfc6_cache_array; + struct list_head mfc6_unres_queue; + struct list_head *mfc6_cache_array; struct mif_device *vif6_table; int maxvif; atomic_t cache_resolve_queue_len; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index b3783a436bb..08e09042ad1 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -89,7 +89,7 @@ static void mroute_clean_tables(struct net *net); struct ipmr_mfc_iter { struct seq_net_private p; - struct mfc6_cache **cache; + struct list_head *cache; int ct; }; @@ -99,18 +99,18 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, { struct mfc6_cache *mfc; - it->cache = net->ipv6.mfc6_cache_array; read_lock(&mrt_lock); - for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) - for (mfc = net->ipv6.mfc6_cache_array[it->ct]; - mfc; mfc = mfc->next) + for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { + it->cache = &net->ipv6.mfc6_cache_array[it->ct]; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; + } read_unlock(&mrt_lock); - it->cache = &net->ipv6.mfc6_unres_queue; spin_lock_bh(&mfc_unres_lock); - for (mfc = net->ipv6.mfc6_unres_queue; mfc; mfc = mfc->next) + it->cache = &net->ipv6.mfc6_unres_queue; + list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; spin_unlock_bh(&mfc_unres_lock); @@ -119,9 +119,6 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, return NULL; } - - - /* * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif */ @@ -238,18 +235,19 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (v == SEQ_START_TOKEN) return ipmr_mfc_seq_idx(net, seq->private, 0); - if (mfc->next) - return mfc->next; + if (mfc->list.next != it->cache) + return list_entry(mfc->list.next, struct mfc6_cache, list); if (it->cache == &net->ipv6.mfc6_unres_queue) goto end_of_list; - BUG_ON(it->cache != net->ipv6.mfc6_cache_array); + BUG_ON(it->cache != &net->ipv6.mfc6_cache_array[it->ct]); while (++it->ct < MFC6_LINES) { - mfc = net->ipv6.mfc6_cache_array[it->ct]; - if (mfc) - return mfc; + it->cache = &net->ipv6.mfc6_cache_array[it->ct]; + if (list_empty(it->cache)) + continue; + return list_first_entry(it->cache, struct mfc6_cache, list); } /* exhausted cache_array, show unresolved */ @@ -258,9 +256,8 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) it->ct = 0; spin_lock_bh(&mfc_unres_lock); - mfc = net->ipv6.mfc6_unres_queue; - if (mfc) - return mfc; + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mfc6_cache, list); end_of_list: spin_unlock_bh(&mfc_unres_lock); @@ -560,25 +557,22 @@ static void ipmr_do_expire_process(struct net *net) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; - struct mfc6_cache *c, **cp; - - cp = &net->ipv6.mfc6_unres_queue; + struct mfc6_cache *c, *next; - while ((c = *cp) != NULL) { + list_for_each_entry_safe(c, next, &net->ipv6.mfc6_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; if (interval < expires) expires = interval; - cp = &c->next; continue; } - *cp = c->next; + list_del(&c->list); ip6mr_destroy_unres(net, c); } - if (net->ipv6.mfc6_unres_queue != NULL) + if (!list_empty(&net->ipv6.mfc6_unres_queue)) mod_timer(&net->ipv6.ipmr_expire_timer, jiffies + expires); } @@ -591,7 +585,7 @@ static void ipmr_expire_process(unsigned long arg) return; } - if (net->ipv6.mfc6_unres_queue != NULL) + if (!list_empty(&net->ipv6.mfc6_unres_queue)) ipmr_do_expire_process(net); spin_unlock(&mfc_unres_lock); @@ -706,12 +700,12 @@ static struct mfc6_cache *ip6mr_cache_find(struct net *net, int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; - for (c = net->ipv6.mfc6_cache_array[line]; c; c = c->next) { + list_for_each_entry(c, &net->ipv6.mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, origin) && ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) - break; + return c; } - return c; + return NULL; } /* @@ -872,17 +866,20 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, static int ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) { + bool found = false; int err; struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - for (c = net->ipv6.mfc6_unres_queue; c; c = c->next) { + list_for_each_entry(c, &net->ipv6.mfc6_unres_queue, list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && - ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) + ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { + found = true; break; + } } - if (c == NULL) { + if (!found) { /* * Create a new entry if allowable */ @@ -918,8 +915,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) } atomic_inc(&net->ipv6.cache_resolve_queue_len); - c->next = net->ipv6.mfc6_unres_queue; - net->ipv6.mfc6_unres_queue = c; + list_add(&c->list, &net->ipv6.mfc6_unres_queue); ipmr_do_expire_process(net); } @@ -946,16 +942,15 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc) { int line; - struct mfc6_cache *c, **cp; + struct mfc6_cache *c, *next; line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry_safe(c, next, &net->ipv6.mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); @@ -997,7 +992,9 @@ static struct notifier_block ip6_mr_notifier = { static int __net_init ip6mr_net_init(struct net *net) { + unsigned int i; int err = 0; + net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device), GFP_KERNEL); if (!net->ipv6.vif6_table) { @@ -1007,13 +1004,18 @@ static int __net_init ip6mr_net_init(struct net *net) /* Forwarding cache */ net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES, - sizeof(struct mfc6_cache *), + sizeof(struct list_head), GFP_KERNEL); if (!net->ipv6.mfc6_cache_array) { err = -ENOMEM; goto fail_mfc6_cache; } + for (i = 0; i < MFC6_LINES; i++) + INIT_LIST_HEAD(&net->ipv6.mfc6_cache_array[i]); + + INIT_LIST_HEAD(&net->ipv6.mfc6_unres_queue); + setup_timer(&net->ipv6.ipmr_expire_timer, ipmr_expire_process, (unsigned long)net); @@ -1105,8 +1107,9 @@ void ip6_mr_cleanup(void) static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) { + bool found = false; int line; - struct mfc6_cache *uc, *c, **cp; + struct mfc6_cache *uc, *c; unsigned char ttls[MAXMIFS]; int i; @@ -1122,14 +1125,15 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - for (cp = &net->ipv6.mfc6_cache_array[line]; - (c = *cp) != NULL; cp = &c->next) { + list_for_each_entry(c, &net->ipv6.mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && - ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) + ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + found = true; break; + } } - if (c != NULL) { + if (found) { write_lock_bh(&mrt_lock); c->mf6c_parent = mfc->mf6cc_parent; ip6mr_update_thresholds(net, c, ttls); @@ -1154,29 +1158,29 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - c->next = net->ipv6.mfc6_cache_array[line]; - net->ipv6.mfc6_cache_array[line] = c; + list_add(&c->list, &net->ipv6.mfc6_cache_array[line]); write_unlock_bh(&mrt_lock); /* * Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ + found = false; spin_lock_bh(&mfc_unres_lock); - for (cp = &net->ipv6.mfc6_unres_queue; (uc = *cp) != NULL; - cp = &uc->next) { + list_for_each_entry(uc, &net->ipv6.mfc6_unres_queue, list) { if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { - *cp = uc->next; + list_del(&uc->list); atomic_dec(&net->ipv6.cache_resolve_queue_len); + found = true; break; } } - if (net->ipv6.mfc6_unres_queue == NULL) + if (list_empty(&net->ipv6.mfc6_unres_queue)) del_timer(&net->ipv6.ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); - if (uc) { + if (found) { ip6mr_cache_resolve(net, uc, c); ip6mr_cache_free(uc); } @@ -1191,6 +1195,7 @@ static void mroute_clean_tables(struct net *net) { int i; LIST_HEAD(list); + struct mfc6_cache *c, *next; /* * Shut down all active vif entries @@ -1205,16 +1210,11 @@ static void mroute_clean_tables(struct net *net) * Wipe the cache */ for (i = 0; i < MFC6_LINES; i++) { - struct mfc6_cache *c, **cp; - - cp = &net->ipv6.mfc6_cache_array[i]; - while ((c = *cp) != NULL) { - if (c->mfc_flags & MFC_STATIC) { - cp = &c->next; + list_for_each_entry_safe(c, next, &net->ipv6.mfc6_cache_array[i], list) { + if (c->mfc_flags & MFC_STATIC) continue; - } write_lock_bh(&mrt_lock); - *cp = c->next; + list_del(&c->list); write_unlock_bh(&mrt_lock); ip6mr_cache_free(c); @@ -1222,12 +1222,9 @@ static void mroute_clean_tables(struct net *net) } if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) { - struct mfc6_cache *c, **cp; - spin_lock_bh(&mfc_unres_lock); - cp = &net->ipv6.mfc6_unres_queue; - while ((c = *cp) != NULL) { - *cp = c->next; + list_for_each_entry_safe(c, next, &net->ipv6.mfc6_unres_queue, list) { + list_del(&c->list); ip6mr_destroy_unres(net, c); } spin_unlock_bh(&mfc_unres_lock); -- cgit v1.2.3-70-g09d2 From 6bd521433942d85e80f7a731a88cc91a327f38e0 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 11 May 2010 14:40:53 +0200 Subject: ipv6: ip6mr: move mroute data into seperate structure Signed-off-by: Patrick McHardy --- include/linux/mroute6.h | 5 +- include/net/netns/ipv6.h | 13 +- net/ipv6/ip6mr.c | 390 ++++++++++++++++++++++++++--------------------- 3 files changed, 216 insertions(+), 192 deletions(-) (limited to 'include/net') diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 94a0cb521ca..0370dd4f238 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -229,10 +229,7 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait); #ifdef CONFIG_IPV6_MROUTE -static inline struct sock *mroute6_socket(struct net *net) -{ - return net->ipv6.mroute6_sk; -} +extern struct sock *mroute6_socket(struct net *net); extern int ip6mr_sk_done(struct sock *sk); #else static inline struct sock *mroute6_socket(struct net *net) { return NULL; } diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 9cb3b5f2cd7..4e2780e6d8b 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -59,18 +59,7 @@ struct netns_ipv6 { struct sock *tcp_sk; struct sock *igmp_sk; #ifdef CONFIG_IPV6_MROUTE - struct sock *mroute6_sk; - struct timer_list ipmr_expire_timer; - struct list_head mfc6_unres_queue; - struct list_head *mfc6_cache_array; - struct mif_device *vif6_table; - int maxvif; - atomic_t cache_resolve_queue_len; - int mroute_do_assert; - int mroute_do_pim; -#ifdef CONFIG_IPV6_PIMSM_V2 - int mroute_reg_vif_num; -#endif + struct mr6_table *mrt6; #endif }; #endif diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 08e09042ad1..9419fceeed4 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -51,6 +51,24 @@ #include #include +struct mr6_table { +#ifdef CONFIG_NET_NS + struct net *net; +#endif + struct sock *mroute6_sk; + struct timer_list ipmr_expire_timer; + struct list_head mfc6_unres_queue; + struct list_head mfc6_cache_array[MFC6_LINES]; + struct mif_device vif6_table[MAXMIFS]; + int maxvif; + atomic_t cache_resolve_queue_len; + int mroute_do_assert; + int mroute_do_pim; +#ifdef CONFIG_IPV6_PIMSM_V2 + int mroute_reg_vif_num; +#endif +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -61,7 +79,7 @@ static DEFINE_RWLOCK(mrt_lock); * Multicast router control variables */ -#define MIF_EXISTS(_net, _idx) ((_net)->ipv6.vif6_table[_idx].dev != NULL) +#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL) /* Special spinlock for queue of unresolved entries */ static DEFINE_SPINLOCK(mfc_unres_lock); @@ -76,13 +94,13 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; -static int ip6_mr_forward(struct net *net, struct sk_buff *skb, - struct mfc6_cache *cache); -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); -static int ip6mr_fill_mroute(struct net *net, struct sk_buff *skb, +static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); -static void mroute_clean_tables(struct net *net); +static void mroute_clean_tables(struct mr6_table *mrt); #ifdef CONFIG_PROC_FS @@ -97,11 +115,12 @@ struct ipmr_mfc_iter { static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { + struct mr6_table *mrt = net->ipv6.mrt6; struct mfc6_cache *mfc; read_lock(&mrt_lock); for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) { - it->cache = &net->ipv6.mfc6_cache_array[it->ct]; + it->cache = &mrt->mfc6_cache_array[it->ct]; list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; @@ -109,7 +128,7 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, read_unlock(&mrt_lock); spin_lock_bh(&mfc_unres_lock); - it->cache = &net->ipv6.mfc6_unres_queue; + it->cache = &mrt->mfc6_unres_queue; list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; @@ -132,11 +151,13 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - for (iter->ct = 0; iter->ct < net->ipv6.maxvif; ++iter->ct) { - if (!MIF_EXISTS(net, iter->ct)) + struct mr6_table *mrt = net->ipv6.mrt6; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -155,15 +176,16 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = net->ipv6.mrt6; ++*pos; if (v == SEQ_START_TOKEN) return ip6mr_vif_seq_idx(net, iter, 0); - while (++iter->ct < net->ipv6.maxvif) { - if (!MIF_EXISTS(net, iter->ct)) + while (++iter->ct < mrt->maxvif) { + if (!MIF_EXISTS(mrt, iter->ct)) continue; - return &net->ipv6.vif6_table[iter->ct]; + return &mrt->vif6_table[iter->ct]; } return NULL; } @@ -177,6 +199,7 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { struct net *net = seq_file_net(seq); + struct mr6_table *mrt = net->ipv6.mrt6; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -187,7 +210,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", - vif - net->ipv6.vif6_table, + vif - mrt->vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, vif->flags); @@ -229,6 +252,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc6_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = net->ipv6.mrt6; ++*pos; @@ -238,13 +262,13 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (mfc->list.next != it->cache) return list_entry(mfc->list.next, struct mfc6_cache, list); - if (it->cache == &net->ipv6.mfc6_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) goto end_of_list; - BUG_ON(it->cache != &net->ipv6.mfc6_cache_array[it->ct]); + BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]); while (++it->ct < MFC6_LINES) { - it->cache = &net->ipv6.mfc6_cache_array[it->ct]; + it->cache = &mrt->mfc6_cache_array[it->ct]; if (list_empty(it->cache)) continue; return list_first_entry(it->cache, struct mfc6_cache, list); @@ -252,7 +276,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) /* exhausted cache_array, show unresolved */ read_unlock(&mrt_lock); - it->cache = &net->ipv6.mfc6_unres_queue; + it->cache = &mrt->mfc6_unres_queue; it->ct = 0; spin_lock_bh(&mfc_unres_lock); @@ -270,10 +294,11 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = net->ipv6.mrt6; - if (it->cache == &net->ipv6.mfc6_unres_queue) + if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == net->ipv6.mfc6_cache_array) + else if (it->cache == mrt->mfc6_cache_array) read_unlock(&mrt_lock); } @@ -281,6 +306,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; struct net *net = seq_file_net(seq); + struct mr6_table *mrt = net->ipv6.mrt6; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -295,14 +321,14 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, mfc->mf6c_parent); - if (it->cache != &net->ipv6.mfc6_unres_queue) { + if (it->cache != &mrt->mfc6_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", mfc->mfc_un.res.pkt, mfc->mfc_un.res.bytes, mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++) { - if (MIF_EXISTS(net, n) && + if (MIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", @@ -349,7 +375,8 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - int reg_vif_num = net->ipv6.mroute_reg_vif_num; + struct mr6_table *mrt = net->ipv6.mrt6; + int reg_vif_num = mrt->mroute_reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; @@ -374,7 +401,7 @@ static int pim6_rcv(struct sk_buff *skb) read_lock(&mrt_lock); if (reg_vif_num >= 0) - reg_dev = net->ipv6.vif6_table[reg_vif_num].dev; + reg_dev = mrt->vif6_table[reg_vif_num].dev; if (reg_dev) dev_hold(reg_dev); read_unlock(&mrt_lock); @@ -411,12 +438,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); + struct mr6_table *mrt = net->ipv6.mrt6; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, net->ipv6.mroute_reg_vif_num, - MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT); read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; @@ -472,15 +499,16 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi, struct list_head *head) +static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; struct inet6_dev *in6_dev; - if (vifi < 0 || vifi >= net->ipv6.maxvif) + + if (vifi < 0 || vifi >= mrt->maxvif) return -EADDRNOTAVAIL; - v = &net->ipv6.vif6_table[vifi]; + v = &mrt->vif6_table[vifi]; write_lock_bh(&mrt_lock); dev = v->dev; @@ -492,17 +520,17 @@ static int mif6_delete(struct net *net, int vifi, struct list_head *head) } #ifdef CONFIG_IPV6_PIMSM_V2 - if (vifi == net->ipv6.mroute_reg_vif_num) - net->ipv6.mroute_reg_vif_num = -1; + if (vifi == mrt->mroute_reg_vif_num) + mrt->mroute_reg_vif_num = -1; #endif - if (vifi + 1 == net->ipv6.maxvif) { + if (vifi + 1 == mrt->maxvif) { int tmp; for (tmp = vifi - 1; tmp >= 0; tmp--) { - if (MIF_EXISTS(net, tmp)) + if (MIF_EXISTS(mrt, tmp)) break; } - net->ipv6.maxvif = tmp + 1; + mrt->maxvif = tmp + 1; } write_unlock_bh(&mrt_lock); @@ -529,11 +557,12 @@ static inline void ip6mr_cache_free(struct mfc6_cache *c) and reporting error to netlink readers. */ -static void ip6mr_destroy_unres(struct net *net, struct mfc6_cache *c) +static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) { + struct net *net = read_pnet(&mrt->net); struct sk_buff *skb; - atomic_dec(&net->ipv6.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { if (ipv6_hdr(skb)->version == 0) { @@ -553,13 +582,13 @@ static void ip6mr_destroy_unres(struct net *net, struct mfc6_cache *c) /* Timer process for all the unresolved queue. */ -static void ipmr_do_expire_process(struct net *net) +static void ipmr_do_expire_process(struct mr6_table *mrt) { unsigned long now = jiffies; unsigned long expires = 10 * HZ; struct mfc6_cache *c, *next; - list_for_each_entry_safe(c, next, &net->ipv6.mfc6_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { if (time_after(c->mfc_un.unres.expires, now)) { /* not yet... */ unsigned long interval = c->mfc_un.unres.expires - now; @@ -569,31 +598,31 @@ static void ipmr_do_expire_process(struct net *net) } list_del(&c->list); - ip6mr_destroy_unres(net, c); + ip6mr_destroy_unres(mrt, c); } - if (!list_empty(&net->ipv6.mfc6_unres_queue)) - mod_timer(&net->ipv6.ipmr_expire_timer, jiffies + expires); + if (!list_empty(&mrt->mfc6_unres_queue)) + mod_timer(&mrt->ipmr_expire_timer, jiffies + expires); } static void ipmr_expire_process(unsigned long arg) { - struct net *net = (struct net *)arg; + struct mr6_table *mrt = (struct mr6_table *)arg; if (!spin_trylock(&mfc_unres_lock)) { - mod_timer(&net->ipv6.ipmr_expire_timer, jiffies + 1); + mod_timer(&mrt->ipmr_expire_timer, jiffies + 1); return; } - if (!list_empty(&net->ipv6.mfc6_unres_queue)) - ipmr_do_expire_process(net); + if (!list_empty(&mrt->mfc6_unres_queue)) + ipmr_do_expire_process(mrt); spin_unlock(&mfc_unres_lock); } /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ip6mr_update_thresholds(struct net *net, struct mfc6_cache *cache, +static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache, unsigned char *ttls) { int vifi; @@ -602,8 +631,8 @@ static void ip6mr_update_thresholds(struct net *net, struct mfc6_cache *cache, cache->mfc_un.res.maxvif = 0; memset(cache->mfc_un.res.ttls, 255, MAXMIFS); - for (vifi = 0; vifi < net->ipv6.maxvif; vifi++) { - if (MIF_EXISTS(net, vifi) && + for (vifi = 0; vifi < mrt->maxvif; vifi++) { + if (MIF_EXISTS(mrt, vifi) && ttls[vifi] && ttls[vifi] < 255) { cache->mfc_un.res.ttls[vifi] = ttls[vifi]; if (cache->mfc_un.res.minvif > vifi) @@ -614,16 +643,17 @@ static void ip6mr_update_thresholds(struct net *net, struct mfc6_cache *cache, } } -static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) +static int mif6_add(struct net *net, struct mr6_table *mrt, + struct mif6ctl *vifc, int mrtsock) { int vifi = vifc->mif6c_mifi; - struct mif_device *v = &net->ipv6.vif6_table[vifi]; + struct mif_device *v = &mrt->vif6_table[vifi]; struct net_device *dev; struct inet6_dev *in6_dev; int err; /* Is vif busy ? */ - if (MIF_EXISTS(net, vifi)) + if (MIF_EXISTS(mrt, vifi)) return -EADDRINUSE; switch (vifc->mif6c_flags) { @@ -633,7 +663,7 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) * Special Purpose VIF in PIM * All the packets will be sent to the daemon */ - if (net->ipv6.mroute_reg_vif_num >= 0) + if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; dev = ip6mr_reg_vif(net); if (!dev) @@ -685,22 +715,22 @@ static int mif6_add(struct net *net, struct mif6ctl *vifc, int mrtsock) v->dev = dev; #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) - net->ipv6.mroute_reg_vif_num = vifi; + mrt->mroute_reg_vif_num = vifi; #endif - if (vifi + 1 > net->ipv6.maxvif) - net->ipv6.maxvif = vifi + 1; + if (vifi + 1 > mrt->maxvif) + mrt->maxvif = vifi + 1; write_unlock_bh(&mrt_lock); return 0; } -static struct mfc6_cache *ip6mr_cache_find(struct net *net, +static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt, struct in6_addr *origin, struct in6_addr *mcastgrp) { int line = MFC6_HASH(mcastgrp, origin); struct mfc6_cache *c; - list_for_each_entry(c, &net->ipv6.mfc6_cache_array[line], list) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, origin) && ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) return c; @@ -734,8 +764,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void) * A cache entry has gone into a resolved state from queued */ -static void ip6mr_cache_resolve(struct net *net, struct mfc6_cache *uc, - struct mfc6_cache *c) +static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, + struct mfc6_cache *uc, struct mfc6_cache *c) { struct sk_buff *skb; @@ -748,7 +778,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mfc6_cache *uc, int err; struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); - if (ip6mr_fill_mroute(net, skb, c, NLMSG_DATA(nlh)) > 0) { + if (ip6mr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; @@ -758,7 +788,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mfc6_cache *uc, } err = rtnl_unicast(skb, net, NETLINK_CB(skb).pid); } else - ip6_mr_forward(net, skb, c); + ip6_mr_forward(net, mrt, skb, c); } } @@ -769,8 +799,8 @@ static void ip6mr_cache_resolve(struct net *net, struct mfc6_cache *uc, * Called under mrt_lock. */ -static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, - int assert) +static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, + mifi_t mifi, int assert) { struct sk_buff *skb; struct mrt6msg *msg; @@ -806,7 +836,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, msg = (struct mrt6msg *)skb_transport_header(skb); msg->im6_mbz = 0; msg->im6_msgtype = MRT6MSG_WHOLEPKT; - msg->im6_mif = net->ipv6.mroute_reg_vif_num; + msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); @@ -841,7 +871,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, skb->ip_summed = CHECKSUM_UNNECESSARY; } - if (net->ipv6.mroute6_sk == NULL) { + if (mrt->mroute6_sk == NULL) { kfree_skb(skb); return -EINVAL; } @@ -849,7 +879,7 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, /* * Deliver to user space multicast routing algorithms */ - ret = sock_queue_rcv_skb(net->ipv6.mroute6_sk, skb); + ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); @@ -864,14 +894,14 @@ static int ip6mr_cache_report(struct net *net, struct sk_buff *pkt, mifi_t mifi, */ static int -ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) +ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb) { bool found = false; int err; struct mfc6_cache *c; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &net->ipv6.mfc6_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc6_unres_queue, list) { if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) { found = true; @@ -884,7 +914,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) * Create a new entry if allowable */ - if (atomic_read(&net->ipv6.cache_resolve_queue_len) >= 10 || + if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || (c = ip6mr_cache_alloc_unres()) == NULL) { spin_unlock_bh(&mfc_unres_lock); @@ -902,7 +932,7 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) /* * Reflect first query at pim6sd */ - err = ip6mr_cache_report(net, skb, mifi, MRT6MSG_NOCACHE); + err = ip6mr_cache_report(mrt, skb, mifi, MRT6MSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -914,10 +944,10 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) return err; } - atomic_inc(&net->ipv6.cache_resolve_queue_len); - list_add(&c->list, &net->ipv6.mfc6_unres_queue); + atomic_inc(&mrt->cache_resolve_queue_len); + list_add(&c->list, &mrt->mfc6_unres_queue); - ipmr_do_expire_process(net); + ipmr_do_expire_process(mrt); } /* @@ -939,14 +969,14 @@ ip6mr_cache_unresolved(struct net *net, mifi_t mifi, struct sk_buff *skb) * MFC6 cache manipulation by user space */ -static int ip6mr_mfc_delete(struct net *net, struct mf6cctl *mfc) +static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc) { int line; struct mfc6_cache *c, *next; line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - list_for_each_entry_safe(c, next, &net->ipv6.mfc6_cache_array[line], list) { + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { write_lock_bh(&mrt_lock); @@ -965,6 +995,7 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = ptr; struct net *net = dev_net(dev); + struct mr6_table *mrt = net->ipv6.mrt6; struct mif_device *v; int ct; LIST_HEAD(list); @@ -972,10 +1003,10 @@ static int ip6mr_device_event(struct notifier_block *this, if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &net->ipv6.vif6_table[0]; - for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { + v = &mrt->vif6_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(net, ct, &list); + mif6_delete(mrt, ct, &list); } unregister_netdevice_many(&list); @@ -992,35 +1023,28 @@ static struct notifier_block ip6_mr_notifier = { static int __net_init ip6mr_net_init(struct net *net) { + struct mr6_table *mrt; unsigned int i; int err = 0; - net->ipv6.vif6_table = kcalloc(MAXMIFS, sizeof(struct mif_device), - GFP_KERNEL); - if (!net->ipv6.vif6_table) { + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) { err = -ENOMEM; goto fail; } - /* Forwarding cache */ - net->ipv6.mfc6_cache_array = kcalloc(MFC6_LINES, - sizeof(struct list_head), - GFP_KERNEL); - if (!net->ipv6.mfc6_cache_array) { - err = -ENOMEM; - goto fail_mfc6_cache; - } + write_pnet(&mrt->net, net); for (i = 0; i < MFC6_LINES; i++) - INIT_LIST_HEAD(&net->ipv6.mfc6_cache_array[i]); + INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); - INIT_LIST_HEAD(&net->ipv6.mfc6_unres_queue); + INIT_LIST_HEAD(&mrt->mfc6_unres_queue); - setup_timer(&net->ipv6.ipmr_expire_timer, ipmr_expire_process, - (unsigned long)net); + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); #ifdef CONFIG_IPV6_PIMSM_V2 - net->ipv6.mroute_reg_vif_num = -1; + mrt->mroute_reg_vif_num = -1; #endif #ifdef CONFIG_PROC_FS @@ -1030,30 +1054,31 @@ static int __net_init ip6mr_net_init(struct net *net) if (!proc_net_fops_create(net, "ip6_mr_cache", 0, &ip6mr_mfc_fops)) goto proc_cache_fail; #endif + + net->ipv6.mrt6 = mrt; return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip6_mr_vif"); proc_vif_fail: - kfree(net->ipv6.mfc6_cache_array); + kfree(mrt); #endif -fail_mfc6_cache: - kfree(net->ipv6.vif6_table); fail: return err; } static void __net_exit ip6mr_net_exit(struct net *net) { + struct mr6_table *mrt = net->ipv6.mrt6; + #ifdef CONFIG_PROC_FS proc_net_remove(net, "ip6_mr_cache"); proc_net_remove(net, "ip6_mr_vif"); #endif - del_timer(&net->ipv6.ipmr_expire_timer); - mroute_clean_tables(net); - kfree(net->ipv6.mfc6_cache_array); - kfree(net->ipv6.vif6_table); + del_timer(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); } static struct pernet_operations ip6mr_net_ops = { @@ -1105,7 +1130,8 @@ void ip6_mr_cleanup(void) kmem_cache_destroy(mrt_cachep); } -static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) +static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt, + struct mf6cctl *mfc, int mrtsock) { bool found = false; int line; @@ -1125,7 +1151,7 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); - list_for_each_entry(c, &net->ipv6.mfc6_cache_array[line], list) { + list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) { if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { found = true; @@ -1136,7 +1162,7 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) if (found) { write_lock_bh(&mrt_lock); c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(net, c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); @@ -1153,12 +1179,12 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; c->mf6c_parent = mfc->mf6cc_parent; - ip6mr_update_thresholds(net, c, ttls); + ip6mr_update_thresholds(mrt, c, ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; write_lock_bh(&mrt_lock); - list_add(&c->list, &net->ipv6.mfc6_cache_array[line]); + list_add(&c->list, &mrt->mfc6_cache_array[line]); write_unlock_bh(&mrt_lock); /* @@ -1167,21 +1193,21 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) */ found = false; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &net->ipv6.mfc6_unres_queue, list) { + list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) { if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { list_del(&uc->list); - atomic_dec(&net->ipv6.cache_resolve_queue_len); + atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; } } - if (list_empty(&net->ipv6.mfc6_unres_queue)) - del_timer(&net->ipv6.ipmr_expire_timer); + if (list_empty(&mrt->mfc6_unres_queue)) + del_timer(&mrt->ipmr_expire_timer); spin_unlock_bh(&mfc_unres_lock); if (found) { - ip6mr_cache_resolve(net, uc, c); + ip6mr_cache_resolve(net, mrt, uc, c); ip6mr_cache_free(uc); } return 0; @@ -1191,7 +1217,7 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) * Close the multicast socket, and clear the vif tables etc */ -static void mroute_clean_tables(struct net *net) +static void mroute_clean_tables(struct mr6_table *mrt) { int i; LIST_HEAD(list); @@ -1200,9 +1226,9 @@ static void mroute_clean_tables(struct net *net) /* * Shut down all active vif entries */ - for (i = 0; i < net->ipv6.maxvif; i++) { - if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(net, i, &list); + for (i = 0; i < mrt->maxvif; i++) { + if (!(mrt->vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(mrt, i, &list); } unregister_netdevice_many(&list); @@ -1210,7 +1236,7 @@ static void mroute_clean_tables(struct net *net) * Wipe the cache */ for (i = 0; i < MFC6_LINES; i++) { - list_for_each_entry_safe(c, next, &net->ipv6.mfc6_cache_array[i], list) { + list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) { if (c->mfc_flags & MFC_STATIC) continue; write_lock_bh(&mrt_lock); @@ -1221,25 +1247,25 @@ static void mroute_clean_tables(struct net *net) } } - if (atomic_read(&net->ipv6.cache_resolve_queue_len) != 0) { + if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); - list_for_each_entry_safe(c, next, &net->ipv6.mfc6_unres_queue, list) { + list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) { list_del(&c->list); - ip6mr_destroy_unres(net, c); + ip6mr_destroy_unres(mrt, c); } spin_unlock_bh(&mfc_unres_lock); } } -static int ip6mr_sk_init(struct sock *sk) +static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) { int err = 0; struct net *net = sock_net(sk); rtnl_lock(); write_lock_bh(&mrt_lock); - if (likely(net->ipv6.mroute6_sk == NULL)) { - net->ipv6.mroute6_sk = sk; + if (likely(mrt->mroute6_sk == NULL)) { + mrt->mroute6_sk = sk; net->ipv6.devconf_all->mc_forwarding++; } else @@ -1255,15 +1281,16 @@ int ip6mr_sk_done(struct sock *sk) { int err = 0; struct net *net = sock_net(sk); + struct mr6_table *mrt = net->ipv6.mrt6; rtnl_lock(); - if (sk == net->ipv6.mroute6_sk) { + if (sk == mrt->mroute6_sk) { write_lock_bh(&mrt_lock); - net->ipv6.mroute6_sk = NULL; + mrt->mroute6_sk = NULL; net->ipv6.devconf_all->mc_forwarding--; write_unlock_bh(&mrt_lock); - mroute_clean_tables(net); + mroute_clean_tables(mrt); } else err = -EACCES; rtnl_unlock(); @@ -1271,6 +1298,13 @@ int ip6mr_sk_done(struct sock *sk) return err; } +struct sock *mroute6_socket(struct net *net) +{ + struct mr6_table *mrt = net->ipv6.mrt6; + + return mrt->mroute6_sk; +} + /* * Socket options and virtual interface manipulation. The whole * virtual interface system is a complete heap, but unfortunately @@ -1285,9 +1319,10 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); + struct mr6_table *mrt = net->ipv6.mrt6; if (optname != MRT6_INIT) { - if (sk != net->ipv6.mroute6_sk && !capable(CAP_NET_ADMIN)) + if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1299,7 +1334,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (optlen < sizeof(int)) return -EINVAL; - return ip6mr_sk_init(sk); + return ip6mr_sk_init(mrt, sk); case MRT6_DONE: return ip6mr_sk_done(sk); @@ -1312,7 +1347,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (vif.mif6c_mifi >= MAXMIFS) return -ENFILE; rtnl_lock(); - ret = mif6_add(net, &vif, sk == net->ipv6.mroute6_sk); + ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1322,7 +1357,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi, NULL); + ret = mif6_delete(mrt, mifi, NULL); rtnl_unlock(); return ret; @@ -1338,10 +1373,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return -EFAULT; rtnl_lock(); if (optname == MRT6_DEL_MFC) - ret = ip6mr_mfc_delete(net, &mfc); + ret = ip6mr_mfc_delete(mrt, &mfc); else - ret = ip6mr_mfc_add(net, &mfc, - sk == net->ipv6.mroute6_sk); + ret = ip6mr_mfc_add(net, mrt, &mfc, sk == mrt->mroute6_sk); rtnl_unlock(); return ret; @@ -1353,7 +1387,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns int v; if (get_user(v, (int __user *)optval)) return -EFAULT; - net->ipv6.mroute_do_assert = !!v; + mrt->mroute_do_assert = !!v; return 0; } @@ -1366,9 +1400,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns v = !!v; rtnl_lock(); ret = 0; - if (v != net->ipv6.mroute_do_pim) { - net->ipv6.mroute_do_pim = v; - net->ipv6.mroute_do_assert = v; + if (v != mrt->mroute_do_pim) { + mrt->mroute_do_pim = v; + mrt->mroute_do_assert = v; } rtnl_unlock(); return ret; @@ -1394,6 +1428,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); + struct mr6_table *mrt = net->ipv6.mrt6; switch (optname) { case MRT6_VERSION: @@ -1401,11 +1436,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, break; #ifdef CONFIG_IPV6_PIMSM_V2 case MRT6_PIM: - val = net->ipv6.mroute_do_pim; + val = mrt->mroute_do_pim; break; #endif case MRT6_ASSERT: - val = net->ipv6.mroute_do_assert; + val = mrt->mroute_do_assert; break; default: return -ENOPROTOOPT; @@ -1436,16 +1471,17 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); + struct mr6_table *mrt = net->ipv6.mrt6; switch (cmd) { case SIOCGETMIFCNT_IN6: if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.mifi >= net->ipv6.maxvif) + if (vr.mifi >= mrt->maxvif) return -EINVAL; read_lock(&mrt_lock); - vif = &net->ipv6.vif6_table[vr.mifi]; - if (MIF_EXISTS(net, vr.mifi)) { + vif = &mrt->vif6_table[vr.mifi]; + if (MIF_EXISTS(mrt, vr.mifi)) { vr.icount = vif->pkt_in; vr.ocount = vif->pkt_out; vr.ibytes = vif->bytes_in; @@ -1463,7 +1499,7 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) return -EFAULT; read_lock(&mrt_lock); - c = ip6mr_cache_find(net, &sr.src.sin6_addr, &sr.grp.sin6_addr); + c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; @@ -1493,11 +1529,11 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) * Processing handlers for ip6mr_forward */ -static int ip6mr_forward2(struct net *net, struct sk_buff *skb, - struct mfc6_cache *c, int vifi) +static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *c, int vifi) { struct ipv6hdr *ipv6h; - struct mif_device *vif = &net->ipv6.vif6_table[vifi]; + struct mif_device *vif = &mrt->vif6_table[vifi]; struct net_device *dev; struct dst_entry *dst; struct flowi fl; @@ -1511,7 +1547,7 @@ static int ip6mr_forward2(struct net *net, struct sk_buff *skb, vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; - ip6mr_cache_report(net, skb, vifi, MRT6MSG_WHOLEPKT); + ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT); goto out_free; } #endif @@ -1566,19 +1602,19 @@ out_free: return 0; } -static int ip6mr_find_vif(struct net_device *dev) +static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) { - struct net *net = dev_net(dev); int ct; - for (ct = net->ipv6.maxvif - 1; ct >= 0; ct--) { - if (net->ipv6.vif6_table[ct].dev == dev) + + for (ct = mrt->maxvif - 1; ct >= 0; ct--) { + if (mrt->vif6_table[ct].dev == dev) break; } return ct; } -static int ip6_mr_forward(struct net *net, struct sk_buff *skb, - struct mfc6_cache *cache) +static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; @@ -1590,30 +1626,30 @@ static int ip6_mr_forward(struct net *net, struct sk_buff *skb, /* * Wrong interface: drop packet and (maybe) send PIM assert. */ - if (net->ipv6.vif6_table[vif].dev != skb->dev) { + if (mrt->vif6_table[vif].dev != skb->dev) { int true_vifi; cache->mfc_un.res.wrong_if++; - true_vifi = ip6mr_find_vif(skb->dev); + true_vifi = ip6mr_find_vif(mrt, skb->dev); - if (true_vifi >= 0 && net->ipv6.mroute_do_assert && + if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, so that we cannot check that packet arrived on an oif. It is bad, but otherwise we would need to move pretty large chunk of pimd to kernel. Ough... --ANK */ - (net->ipv6.mroute_do_pim || + (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { cache->mfc_un.res.last_assert = jiffies; - ip6mr_cache_report(net, skb, true_vifi, MRT6MSG_WRONGMIF); + ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF); } goto dont_forward; } - net->ipv6.vif6_table[vif].pkt_in++; - net->ipv6.vif6_table[vif].bytes_in += skb->len; + mrt->vif6_table[vif].pkt_in++; + mrt->vif6_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1623,13 +1659,13 @@ static int ip6_mr_forward(struct net *net, struct sk_buff *skb, if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) - ip6mr_forward2(net, skb2, cache, psend); + ip6mr_forward2(net, mrt, skb2, cache, psend); } psend = ct; } } if (psend != -1) { - ip6mr_forward2(net, skb, cache, psend); + ip6mr_forward2(net, mrt, skb, cache, psend); return 0; } @@ -1647,9 +1683,10 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); + struct mr6_table *mrt = net->ipv6.mrt6; read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, + cache = ip6mr_cache_find(mrt, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); /* @@ -1658,9 +1695,9 @@ int ip6_mr_input(struct sk_buff *skb) if (cache == NULL) { int vif; - vif = ip6mr_find_vif(skb->dev); + vif = ip6mr_find_vif(mrt, skb->dev); if (vif >= 0) { - int err = ip6mr_cache_unresolved(net, vif, skb); + int err = ip6mr_cache_unresolved(mrt, vif, skb); read_unlock(&mrt_lock); return err; @@ -1670,7 +1707,7 @@ int ip6_mr_input(struct sk_buff *skb) return -ENODEV; } - ip6_mr_forward(net, skb, cache); + ip6_mr_forward(net, mrt, skb, cache); read_unlock(&mrt_lock); @@ -1679,8 +1716,8 @@ int ip6_mr_input(struct sk_buff *skb) static int -ip6mr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc6_cache *c, - struct rtmsg *rtm) +ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, + struct mfc6_cache *c, struct rtmsg *rtm) { int ct; struct rtnexthop *nhp; @@ -1691,19 +1728,19 @@ ip6mr_fill_mroute(struct net *net, struct sk_buff *skb, struct mfc6_cache *c, if (c->mf6c_parent > MAXMIFS) return -ENOENT; - if (MIF_EXISTS(net, c->mf6c_parent)) - RTA_PUT(skb, RTA_IIF, 4, &net->ipv6.vif6_table[c->mf6c_parent].dev->ifindex); + if (MIF_EXISTS(mrt, c->mf6c_parent)) + RTA_PUT(skb, RTA_IIF, 4, &mrt->vif6_table[c->mf6c_parent].dev->ifindex); mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (MIF_EXISTS(net, ct) && c->mfc_un.res.ttls[ct] < 255) { + if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = net->ipv6.vif6_table[ct].dev->ifindex; + nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex; nhp->rtnh_len = sizeof(*nhp); } } @@ -1721,11 +1758,12 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; + struct mr6_table *mrt = net->ipv6.mrt6; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); read_lock(&mrt_lock); - cache = ip6mr_cache_find(net, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); + cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); if (!cache) { struct sk_buff *skb2; @@ -1739,7 +1777,7 @@ int ip6mr_get_route(struct net *net, } dev = skb->dev; - if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) { + if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) { read_unlock(&mrt_lock); return -ENODEV; } @@ -1768,7 +1806,7 @@ int ip6mr_get_route(struct net *net, ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); - err = ip6mr_cache_unresolved(net, vif, skb2); + err = ip6mr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); return err; @@ -1777,7 +1815,7 @@ int ip6mr_get_route(struct net *net, if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; - err = ip6mr_fill_mroute(net, skb, cache, rtm); + err = ip6mr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); return err; } -- cgit v1.2.3-70-g09d2 From d1db275dd3f6e4182c4c4b4a1ac6287925d60569 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 11 May 2010 14:40:55 +0200 Subject: ipv6: ip6mr: support multiple tables This patch adds support for multiple independant multicast routing instances, named "tables". Userspace multicast routing daemons can bind to a specific table instance by issuing a setsockopt call using a new option MRT6_TABLE. The table number is stored in the raw socket data and affects all following ip6mr setsockopt(), getsockopt() and ioctl() calls. By default, a single table (RT6_TABLE_DFLT) is created with a default routing rule pointing to it. Newly created pim6reg devices have the table number appended ("pim6regX"), with the exception of devices created in the default table, which are named just "pim6reg" for compatibility reasons. Packets are directed to a specific table instance using routing rules, similar to how regular routing rules work. Currently iif, oif and mark are supported as keys, source and destination addresses could be supported additionally. Example usage: - bind pimd/xorp/... to a specific table: uint32_t table = 123; setsockopt(fd, SOL_IPV6, MRT6_TABLE, &table, sizeof(table)); - create routing rules directing packets to the new table: # ip -6 mrule add iif eth0 lookup 123 # ip -6 mrule add oif eth0 lookup 123 Signed-off-by: Patrick McHardy --- include/linux/ipv6.h | 1 + include/linux/mroute6.h | 15 +- include/linux/rtnetlink.h | 3 +- include/net/netns/ipv6.h | 5 + net/ipv6/Kconfig | 14 ++ net/ipv6/ip6_output.c | 2 +- net/ipv6/ip6mr.c | 428 +++++++++++++++++++++++++++++++++++++++------- 7 files changed, 396 insertions(+), 72 deletions(-) (limited to 'include/net') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0e269038bb3..99e1ab7e3ee 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -383,6 +383,7 @@ struct raw6_sock { __u32 checksum; /* perform checksum */ __u32 offset; /* checksum offset */ struct icmp6_filter filter; + __u32 ip6mr_table; /* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */ struct ipv6_pinfo inet6; }; diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 0370dd4f238..6091ab77f38 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -24,7 +24,8 @@ #define MRT6_DEL_MFC (MRT6_BASE+5) /* Delete a multicast forwarding entry */ #define MRT6_VERSION (MRT6_BASE+6) /* Get the kernel multicast version */ #define MRT6_ASSERT (MRT6_BASE+7) /* Activate PIM assert mode */ -#define MRT6_PIM (MRT6_BASE+8) /* enable PIM code */ +#define MRT6_PIM (MRT6_BASE+8) /* enable PIM code */ +#define MRT6_TABLE (MRT6_BASE+9) /* Specify mroute table ID */ #define SIOCGETMIFCNT_IN6 SIOCPROTOPRIVATE /* IP protocol privates */ #define SIOCGETSGCNT_IN6 (SIOCPROTOPRIVATE+1) @@ -229,11 +230,17 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait); #ifdef CONFIG_IPV6_MROUTE -extern struct sock *mroute6_socket(struct net *net); +extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb); extern int ip6mr_sk_done(struct sock *sk); #else -static inline struct sock *mroute6_socket(struct net *net) { return NULL; } -static inline int ip6mr_sk_done(struct sock *sk) { return 0; } +static inline struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) +{ + return NULL; +} +static inline int ip6mr_sk_done(struct sock *sk) +{ + return 0; +} #endif #endif diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 5a42c36cb6a..fbc8cb0d48c 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -11,7 +11,8 @@ * families, values above 128 may be used arbitrarily. */ #define RTNL_FAMILY_IPMR 128 -#define RTNL_FAMILY_MAX 128 +#define RTNL_FAMILY_IP6MR 129 +#define RTNL_FAMILY_MAX 129 /**** * Routing/neighbour discovery messages. diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 4e2780e6d8b..81abfcb2eb4 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -59,7 +59,12 @@ struct netns_ipv6 { struct sock *tcp_sk; struct sock *igmp_sk; #ifdef CONFIG_IPV6_MROUTE +#ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES struct mr6_table *mrt6; +#else + struct list_head mr6_tables; + struct fib_rules_ops *mr6_rules_ops; +#endif #endif }; #endif diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index a578096152a..36d7437ac05 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -229,6 +229,20 @@ config IPV6_MROUTE Experimental support for IPv6 multicast forwarding. If unsure, say N. +config IPV6_MROUTE_MULTIPLE_TABLES + bool "IPv6: multicast policy routing" + depends on IPV6_MROUTE + select FIB_RULES + help + Normally, a multicast router runs a userspace daemon and decides + what to do with a multicast packet based on the source and + destination addresses. If you say Y here, the multicast router + will also be able to take interfaces and packet marks into + account and run multiple instances of userspace daemons + simultaneously, each one handling a single table. + + If unsure, say N. + config IPV6_PIMSM_V2 bool "IPv6: PIM-SM version 2 support (EXPERIMENTAL)" depends on IPV6_MROUTE diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5173acaeb50..cd963f64e27 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -108,7 +108,7 @@ static int ip6_finish_output2(struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(skb->sk) && - ((mroute6_socket(dev_net(dev)) && + ((mroute6_socket(dev_net(dev), skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 9419fceeed4..c2920a1a6db 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -52,9 +53,11 @@ #include struct mr6_table { + struct list_head list; #ifdef CONFIG_NET_NS struct net *net; #endif + u32 id; struct sock *mroute6_sk; struct timer_list ipmr_expire_timer; struct list_head mfc6_unres_queue; @@ -69,6 +72,14 @@ struct mr6_table { #endif }; +struct ip6mr_rule { + struct fib_rule common; +}; + +struct ip6mr_result { + struct mr6_table *mrt; +}; + /* Big lock, protecting vif table, mrt cache and mroute socket state. Note that the changes are semaphored via rtnl_lock. */ @@ -94,6 +105,9 @@ static DEFINE_SPINLOCK(mfc_unres_lock); static struct kmem_cache *mrt_cachep __read_mostly; +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); +static void ip6mr_free_table(struct mr6_table *mrt); + static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, @@ -101,12 +115,220 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); static void mroute_clean_tables(struct mr6_table *mrt); +static void ipmr_expire_process(unsigned long arg); + +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES +#define ip6mr_for_each_table(mrt, met) \ + list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + ip6mr_for_each_table(mrt, net) { + if (mrt->id == id) + return mrt; + } + return NULL; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + struct ip6mr_result res; + struct fib_lookup_arg arg = { .result = &res, }; + int err; + + err = fib_rules_lookup(net->ipv6.mr6_rules_ops, flp, 0, &arg); + if (err < 0) + return err; + *mrt = res.mrt; + return 0; +} + +static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct ip6mr_result *res = arg->result; + struct mr6_table *mrt; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + return -ENETUNREACH; + case FR_ACT_PROHIBIT: + return -EACCES; + case FR_ACT_BLACKHOLE: + default: + return -EINVAL; + } + + mrt = ip6mr_get_table(rule->fr_net, rule->table); + if (mrt == NULL) + return -EAGAIN; + res->mrt = mrt; + return 0; +} + +static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags) +{ + return 1; +} + +static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { + FRA_GENERIC_POLICY, +}; + +static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh, struct nlattr **tb) +{ + return 0; +} + +static int ip6mr_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + return 1; +} + +static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct fib_rule_hdr *frh) +{ + frh->dst_len = 0; + frh->src_len = 0; + frh->tos = 0; + return 0; +} + +static const struct fib_rules_ops __net_initdata ip6mr_rules_ops_template = { + .family = RTNL_FAMILY_IP6MR, + .rule_size = sizeof(struct ip6mr_rule), + .addr_size = sizeof(struct in6_addr), + .action = ip6mr_rule_action, + .match = ip6mr_rule_match, + .configure = ip6mr_rule_configure, + .compare = ip6mr_rule_compare, + .default_pref = fib_default_rule_pref, + .fill = ip6mr_rule_fill, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = ip6mr_rule_policy, + .owner = THIS_MODULE, +}; + +static int __net_init ip6mr_rules_init(struct net *net) +{ + struct fib_rules_ops *ops; + struct mr6_table *mrt; + int err; + + ops = fib_rules_register(&ip6mr_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + + INIT_LIST_HEAD(&net->ipv6.mr6_tables); + + mrt = ip6mr_new_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) { + err = -ENOMEM; + goto err1; + } + + err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0); + if (err < 0) + goto err2; + + net->ipv6.mr6_rules_ops = ops; + return 0; + +err2: + kfree(mrt); +err1: + fib_rules_unregister(ops); + return err; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + struct mr6_table *mrt, *next; + + list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) + ip6mr_free_table(mrt); + fib_rules_unregister(net->ipv6.mr6_rules_ops); +} +#else +#define ip6mr_for_each_table(mrt, net) \ + for (mrt = net->ipv6.mrt6; mrt; mrt = NULL) + +static struct mr6_table *ip6mr_get_table(struct net *net, u32 id) +{ + return net->ipv6.mrt6; +} + +static int ip6mr_fib_lookup(struct net *net, struct flowi *flp, + struct mr6_table **mrt) +{ + *mrt = net->ipv6.mrt6; + return 0; +} + +static int __net_init ip6mr_rules_init(struct net *net) +{ + net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT); + return net->ipv6.mrt6 ? 0 : -ENOMEM; +} + +static void __net_exit ip6mr_rules_exit(struct net *net) +{ + ip6mr_free_table(net->ipv6.mrt6); +} +#endif + +static struct mr6_table *ip6mr_new_table(struct net *net, u32 id) +{ + struct mr6_table *mrt; + unsigned int i; + + mrt = ip6mr_get_table(net, id); + if (mrt != NULL) + return mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (mrt == NULL) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + /* Forwarding cache */ + for (i = 0; i < MFC6_LINES; i++) + INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); + + INIT_LIST_HEAD(&mrt->mfc6_unres_queue); + + setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, + (unsigned long)mrt); + +#ifdef CONFIG_IPV6_PIMSM_V2 + mrt->mroute_reg_vif_num = -1; +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables); +#endif + return mrt; +} + +static void ip6mr_free_table(struct mr6_table *mrt) +{ + del_timer(&mrt->ipmr_expire_timer); + mroute_clean_tables(mrt); + kfree(mrt); +} #ifdef CONFIG_PROC_FS struct ipmr_mfc_iter { struct seq_net_private p; + struct mr6_table *mrt; struct list_head *cache; int ct; }; @@ -115,7 +337,7 @@ struct ipmr_mfc_iter { static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_mfc_iter *it, loff_t pos) { - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt = it->mrt; struct mfc6_cache *mfc; read_lock(&mrt_lock); @@ -144,6 +366,7 @@ static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net, struct ipmr_vif_iter { struct seq_net_private p; + struct mr6_table *mrt; int ct; }; @@ -151,7 +374,7 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, struct ipmr_vif_iter *iter, loff_t pos) { - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt = iter->mrt; for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { if (!MIF_EXISTS(mrt, iter->ct)) @@ -165,7 +388,15 @@ static struct mif_device *ip6mr_vif_seq_idx(struct net *net, static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { + struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + + iter->mrt = mrt; read_lock(&mrt_lock); return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1) @@ -176,7 +407,7 @@ static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ipmr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) @@ -198,8 +429,8 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) { - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = net->ipv6.mrt6; + struct ipmr_vif_iter *iter = seq->private; + struct mr6_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -241,8 +472,15 @@ static const struct file_operations ip6mr_vif_fops = { static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { + struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return ERR_PTR(-ENOENT); + it->mrt = mrt; return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) : SEQ_START_TOKEN; } @@ -252,7 +490,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct mfc6_cache *mfc = v; struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt = it->mrt; ++*pos; @@ -293,8 +531,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) { struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt = it->mrt; if (it->cache == &mrt->mfc6_unres_queue) spin_unlock_bh(&mfc_unres_lock); @@ -305,8 +542,6 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) { int n; - struct net *net = seq_file_net(seq); - struct mr6_table *mrt = net->ipv6.mrt6; if (v == SEQ_START_TOKEN) { seq_puts(seq, @@ -316,6 +551,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) } else { const struct mfc6_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; + struct mr6_table *mrt = it->mrt; seq_printf(seq, "%pI6 %pI6 %-3hd", &mfc->mf6c_mcastgrp, &mfc->mf6c_origin, @@ -375,8 +611,12 @@ static int pim6_rcv(struct sk_buff *skb) struct ipv6hdr *encap; struct net_device *reg_dev = NULL; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt = net->ipv6.mrt6; - int reg_vif_num = mrt->mroute_reg_vif_num; + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int reg_vif_num; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; @@ -399,6 +639,10 @@ static int pim6_rcv(struct sk_buff *skb) ntohs(encap->payload_len) + sizeof(*pim) > skb->len) goto drop; + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + goto drop; + reg_vif_num = mrt->mroute_reg_vif_num; + read_lock(&mrt_lock); if (reg_vif_num >= 0) reg_dev = mrt->vif6_table[reg_vif_num].dev; @@ -438,7 +682,17 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) { struct net *net = dev_net(dev); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + struct flowi fl = { + .oif = dev->ifindex, + .iif = skb->skb_iif, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; @@ -463,11 +717,17 @@ static void reg_vif_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static struct net_device *ip6mr_reg_vif(struct net *net) +static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt) { struct net_device *dev; + char name[IFNAMSIZ]; + + if (mrt->id == RT6_TABLE_DFLT) + sprintf(name, "pim6reg"); + else + sprintf(name, "pim6reg%u", mrt->id); - dev = alloc_netdev(0, "pim6reg", reg_vif_setup); + dev = alloc_netdev(0, name, reg_vif_setup); if (dev == NULL) return NULL; @@ -665,7 +925,7 @@ static int mif6_add(struct net *net, struct mr6_table *mrt, */ if (mrt->mroute_reg_vif_num >= 0) return -EADDRINUSE; - dev = ip6mr_reg_vif(net); + dev = ip6mr_reg_vif(net, mrt); if (!dev) return -ENOBUFS; err = dev_set_allmulti(dev, 1); @@ -995,7 +1255,7 @@ static int ip6mr_device_event(struct notifier_block *this, { struct net_device *dev = ptr; struct net *net = dev_net(dev); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; struct mif_device *v; int ct; LIST_HEAD(list); @@ -1003,10 +1263,12 @@ static int ip6mr_device_event(struct notifier_block *this, if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - v = &mrt->vif6_table[0]; - for (ct = 0; ct < mrt->maxvif; ct++, v++) { - if (v->dev == dev) - mif6_delete(mrt, ct, &list); + ip6mr_for_each_table(mrt, net) { + v = &mrt->vif6_table[0]; + for (ct = 0; ct < mrt->maxvif; ct++, v++) { + if (v->dev == dev) + mif6_delete(mrt, ct, &list); + } } unregister_netdevice_many(&list); @@ -1023,29 +1285,11 @@ static struct notifier_block ip6_mr_notifier = { static int __net_init ip6mr_net_init(struct net *net) { - struct mr6_table *mrt; - unsigned int i; - int err = 0; + int err; - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (mrt == NULL) { - err = -ENOMEM; + err = ip6mr_rules_init(net); + if (err < 0) goto fail; - } - - write_pnet(&mrt->net, net); - - for (i = 0; i < MFC6_LINES; i++) - INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]); - - INIT_LIST_HEAD(&mrt->mfc6_unres_queue); - - setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process, - (unsigned long)mrt); - -#ifdef CONFIG_IPV6_PIMSM_V2 - mrt->mroute_reg_vif_num = -1; -#endif #ifdef CONFIG_PROC_FS err = -ENOMEM; @@ -1055,14 +1299,13 @@ static int __net_init ip6mr_net_init(struct net *net) goto proc_cache_fail; #endif - net->ipv6.mrt6 = mrt; return 0; #ifdef CONFIG_PROC_FS proc_cache_fail: proc_net_remove(net, "ip6_mr_vif"); proc_vif_fail: - kfree(mrt); + ip6mr_rules_exit(net); #endif fail: return err; @@ -1070,15 +1313,11 @@ fail: static void __net_exit ip6mr_net_exit(struct net *net) { - struct mr6_table *mrt = net->ipv6.mrt6; - #ifdef CONFIG_PROC_FS proc_net_remove(net, "ip6_mr_cache"); proc_net_remove(net, "ip6_mr_vif"); #endif - del_timer(&mrt->ipmr_expire_timer); - mroute_clean_tables(mrt); - kfree(mrt); + ip6mr_rules_exit(net); } static struct pernet_operations ip6mr_net_ops = { @@ -1279,28 +1518,39 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk) int ip6mr_sk_done(struct sock *sk) { - int err = 0; + int err = -EACCES; struct net *net = sock_net(sk); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; rtnl_lock(); - if (sk == mrt->mroute6_sk) { - write_lock_bh(&mrt_lock); - mrt->mroute6_sk = NULL; - net->ipv6.devconf_all->mc_forwarding--; - write_unlock_bh(&mrt_lock); + ip6mr_for_each_table(mrt, net) { + if (sk == mrt->mroute6_sk) { + write_lock_bh(&mrt_lock); + mrt->mroute6_sk = NULL; + net->ipv6.devconf_all->mc_forwarding--; + write_unlock_bh(&mrt_lock); - mroute_clean_tables(mrt); - } else - err = -EACCES; + mroute_clean_tables(mrt); + err = 0; + break; + } + } rtnl_unlock(); return err; } -struct sock *mroute6_socket(struct net *net) +struct sock *mroute6_socket(struct net *net, struct sk_buff *skb) { - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->skb_iif, + .oif = skb->dev->ifindex, + .mark = skb->mark, + }; + + if (ip6mr_fib_lookup(net, &fl, &mrt) < 0) + return NULL; return mrt->mroute6_sk; } @@ -1319,7 +1569,11 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns struct mf6cctl mfc; mifi_t mifi; struct net *net = sock_net(sk); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; if (optname != MRT6_INIT) { if (sk != mrt->mroute6_sk && !capable(CAP_NET_ADMIN)) @@ -1408,6 +1662,27 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns return ret; } +#endif +#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES + case MRT6_TABLE: + { + u32 v; + + if (optlen != sizeof(u32)) + return -EINVAL; + if (get_user(v, (u32 __user *)optval)) + return -EFAULT; + if (sk == mrt->mroute6_sk) + return -EBUSY; + + rtnl_lock(); + ret = 0; + if (!ip6mr_new_table(net, v)) + ret = -ENOMEM; + raw6_sk(sk)->ip6mr_table = v; + rtnl_unlock(); + return ret; + } #endif /* * Spurious command, or MRT6_VERSION which you cannot @@ -1428,7 +1703,11 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int olr; int val; struct net *net = sock_net(sk); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (optname) { case MRT6_VERSION: @@ -1471,7 +1750,11 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + + mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; switch (cmd) { case SIOCGETMIFCNT_IN6: @@ -1683,7 +1966,16 @@ int ip6_mr_input(struct sk_buff *skb) { struct mfc6_cache *cache; struct net *net = dev_net(skb->dev); - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; + struct flowi fl = { + .iif = skb->dev->ifindex, + .mark = skb->mark, + }; + int err; + + err = ip6mr_fib_lookup(net, &fl, &mrt); + if (err < 0) + return err; read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, @@ -1758,10 +2050,14 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm, int nowait) { int err; - struct mr6_table *mrt = net->ipv6.mrt6; + struct mr6_table *mrt; struct mfc6_cache *cache; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); + mrt = ip6mr_get_table(net, RT6_TABLE_DFLT); + if (mrt == NULL) + return -ENOENT; + read_lock(&mrt_lock); cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr); -- cgit v1.2.3-70-g09d2 From 5ce6e438d5d9ed8ed775cd1e94f92002c8da2bad Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 11 May 2010 16:20:57 +0200 Subject: mac80211: add offload channel switch support This adds support for offloading the channel switch operation to devices that support such, typically by having specific firmware API for it. The reasons for this could be that the firmware provides better timing or that regulatory enforcement done by the device requires special handling of CSAs. In order to allow drivers to specify the timing to the device, the new channel_switch callback will pass through the received frame's mactime, where available. Signed-off-by: Wey-Yi Guy Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- include/net/mac80211.h | 39 +++++++++++++++++++++++++++++++ net/mac80211/driver-ops.h | 11 +++++++++ net/mac80211/driver-trace.h | 49 +++++++++++++++++++++++++++++++++++++++ net/mac80211/ieee80211_i.h | 3 ++- net/mac80211/mlme.c | 56 +++++++++++++++++++++++++++++++++++++++++---- 5 files changed, 153 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 9448a5b1bb1..389e86a54fc 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -711,6 +711,28 @@ struct ieee80211_conf { enum ieee80211_smps_mode smps_mode; }; +/** + * struct ieee80211_channel_switch - holds the channel switch data + * + * The information provided in this structure is required for channel switch + * operation. + * + * @timestamp: value in microseconds of the 64-bit Time Synchronization + * Function (TSF) timer when the frame containing the channel switch + * announcement was received. This is simply the rx.mactime parameter + * the driver passed into mac80211. + * @block_tx: Indicates whether transmission must be blocked before the + * scheduled channel switch, as indicated by the AP. + * @channel: the new channel to switch to + * @count: the number of TBTT's until the channel switch event + */ +struct ieee80211_channel_switch { + u64 timestamp; + bool block_tx; + struct ieee80211_channel *channel; + u8 count; +}; + /** * struct ieee80211_vif - per-interface data * @@ -1631,6 +1653,11 @@ enum ieee80211_ampdu_mlme_action { * @flush: Flush all pending frames from the hardware queue, making sure * that the hardware queues are empty. If the parameter @drop is set * to %true, pending frames may be dropped. The callback can sleep. + * + * @channel_switch: Drivers that need (or want) to offload the channel + * switch operation for CSAs received from the AP may implement this + * callback. They must then call ieee80211_chswitch_done() to indicate + * completion of the channel switch. */ struct ieee80211_ops { int (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb); @@ -1694,6 +1721,8 @@ struct ieee80211_ops { int (*testmode_cmd)(struct ieee80211_hw *hw, void *data, int len); #endif void (*flush)(struct ieee80211_hw *hw, bool drop); + void (*channel_switch)(struct ieee80211_hw *hw, + struct ieee80211_channel_switch *ch_switch); }; /** @@ -2444,6 +2473,16 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, enum nl80211_cqm_rssi_threshold_event rssi_event, gfp_t gfp); +/** + * ieee80211_chswitch_done - Complete channel switch process + * @vif: &struct ieee80211_vif pointer from the add_interface callback. + * @success: make the channel switch successful or not + * + * Complete the channel switch post-process: set the new operational channel + * and wake up the suspended queues. + */ +void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success); + /* Rate control API */ /** diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 997008e236f..5662bb5190c 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -373,4 +373,15 @@ static inline void drv_flush(struct ieee80211_local *local, bool drop) if (local->ops->flush) local->ops->flush(&local->hw, drop); } + +static inline void drv_channel_switch(struct ieee80211_local *local, + struct ieee80211_channel_switch *ch_switch) +{ + might_sleep(); + + local->ops->channel_switch(&local->hw, ch_switch); + + trace_drv_channel_switch(local, ch_switch); +} + #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index ce734b58d07..6a9b2342a9c 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -774,6 +774,34 @@ TRACE_EVENT(drv_flush, ) ); +TRACE_EVENT(drv_channel_switch, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_channel_switch *ch_switch), + + TP_ARGS(local, ch_switch), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u64, timestamp) + __field(bool, block_tx) + __field(u16, freq) + __field(u8, count) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->timestamp = ch_switch->timestamp; + __entry->block_tx = ch_switch->block_tx; + __entry->freq = ch_switch->channel->center_freq; + __entry->count = ch_switch->count; + ), + + TP_printk( + LOCAL_PR_FMT " new freq:%u count:%d", + LOCAL_PR_ARG, __entry->freq, __entry->count + ) +); + /* * Tracing for API calls that drivers call. */ @@ -992,6 +1020,27 @@ TRACE_EVENT(api_sta_block_awake, ) ); +TRACE_EVENT(api_chswitch_done, + TP_PROTO(struct ieee80211_sub_if_data *sdata, bool success), + + TP_ARGS(sdata, success), + + TP_STRUCT__entry( + VIF_ENTRY + __field(bool, success) + ), + + TP_fast_assign( + VIF_ASSIGN; + __entry->success = success; + ), + + TP_printk( + VIF_PR_FMT " success=%d", + VIF_PR_ARG, __entry->success + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 69e7f4131f4..1c8e2470668 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -999,7 +999,8 @@ int ieee80211_max_network_latency(struct notifier_block *nb, unsigned long data, void *dummy); void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_sw_ie *sw_elem, - struct ieee80211_bss *bss); + struct ieee80211_bss *bss, + u64 timestamp); void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata); void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7bfb0ebaaf0..6b74489fb9c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -341,7 +341,11 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; sdata->local->oper_channel = sdata->local->csa_channel; - ieee80211_hw_config(sdata->local, IEEE80211_CONF_CHANGE_CHANNEL); + if (!sdata->local->ops->channel_switch) { + /* call "hw_config" only if doing sw channel switch */ + ieee80211_hw_config(sdata->local, + IEEE80211_CONF_CHANGE_CHANNEL); + } /* XXX: shouldn't really modify cfg80211-owned data! */ ifmgd->associated->channel = sdata->local->oper_channel; @@ -353,6 +357,29 @@ static void ieee80211_chswitch_work(struct work_struct *work) mutex_unlock(&ifmgd->mtx); } +void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_if_managed *ifmgd; + + sdata = vif_to_sdata(vif); + ifmgd = &sdata->u.mgd; + + trace_api_chswitch_done(sdata, success); + if (!success) { + /* + * If the channel switch was not successful, stay + * around on the old channel. We currently lack + * good handling of this situation, possibly we + * should just drop the association. + */ + sdata->local->csa_channel = sdata->local->oper_channel; + } + + ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work); +} +EXPORT_SYMBOL(ieee80211_chswitch_done); + static void ieee80211_chswitch_timer(unsigned long data) { struct ieee80211_sub_if_data *sdata = @@ -369,7 +396,8 @@ static void ieee80211_chswitch_timer(unsigned long data) void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, struct ieee80211_channel_sw_ie *sw_elem, - struct ieee80211_bss *bss) + struct ieee80211_bss *bss, + u64 timestamp) { struct cfg80211_bss *cbss = container_of((void *)bss, struct cfg80211_bss, priv); @@ -397,6 +425,24 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->local->csa_channel = new_ch; + if (sdata->local->ops->channel_switch) { + /* use driver's channel switch callback */ + struct ieee80211_channel_switch ch_switch; + memset(&ch_switch, 0, sizeof(ch_switch)); + ch_switch.timestamp = timestamp; + if (sw_elem->mode) { + ch_switch.block_tx = true; + ieee80211_stop_queues_by_reason(&sdata->local->hw, + IEEE80211_QUEUE_STOP_REASON_CSA); + } + ch_switch.channel = new_ch; + ch_switch.count = sw_elem->count; + ifmgd->flags |= IEEE80211_STA_CSA_RECEIVED; + drv_channel_switch(sdata->local, &ch_switch); + return; + } + + /* channel switch handled in software */ if (sw_elem->count <= 1) { ieee80211_queue_work(&sdata->local->hw, &ifmgd->chswitch_work); } else { @@ -1316,7 +1362,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, ETH_ALEN) == 0)) { struct ieee80211_channel_sw_ie *sw_elem = (struct ieee80211_channel_sw_ie *)elems->ch_switch_elem; - ieee80211_sta_process_chanswitch(sdata, sw_elem, bss); + ieee80211_sta_process_chanswitch(sdata, sw_elem, + bss, rx_status->mactime); } } @@ -1648,7 +1695,8 @@ static void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, ieee80211_sta_process_chanswitch(sdata, &mgmt->u.action.u.chan_switch.sw_elem, - (void *)ifmgd->associated->priv); + (void *)ifmgd->associated->priv, + rx_status->mactime); break; } mutex_unlock(&ifmgd->mtx); -- cgit v1.2.3-70-g09d2 From 8e1c298c01d4596fa2837913e531a93a791a7bec Mon Sep 17 00:00:00 2001 From: Allan Stephens Date: Tue, 11 May 2010 14:30:09 +0000 Subject: tipc: Update commenting in TIPC API Eliminate comments in TIPC's main API files that are either obsolete, incorrect, misleading, or unhelpful. It also adds in one new comment. Signed-off-by: Allan Stephens Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- include/linux/tipc.h | 6 +++--- include/net/tipc/tipc.h | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/net') diff --git a/include/linux/tipc.h b/include/linux/tipc.h index 9536d8aeadf..181c8d0e6f7 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -107,7 +107,7 @@ static inline unsigned int tipc_node(__u32 addr) * Message importance levels */ -#define TIPC_LOW_IMPORTANCE 0 /* default */ +#define TIPC_LOW_IMPORTANCE 0 #define TIPC_MEDIUM_IMPORTANCE 1 #define TIPC_HIGH_IMPORTANCE 2 #define TIPC_CRITICAL_IMPORTANCE 3 @@ -182,7 +182,7 @@ struct sockaddr_tipc { struct tipc_name_seq nameseq; struct { struct tipc_name name; - __u32 domain; /* 0: own zone */ + __u32 domain; } name; } addr; }; @@ -200,7 +200,7 @@ struct sockaddr_tipc { */ #define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */ -#define TIPC_SRC_DROPPABLE 128 /* Default: 0 (resend congested msg) */ +#define TIPC_SRC_DROPPABLE 128 /* Default: based on socket type */ #define TIPC_DEST_DROPPABLE 129 /* Default: based on socket type */ #define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */ #define TIPC_NODE_RECVQ_DEPTH 131 /* Default: none (read only) */ diff --git a/include/net/tipc/tipc.h b/include/net/tipc/tipc.h index 9566608c88c..15af6dca0b4 100644 --- a/include/net/tipc/tipc.h +++ b/include/net/tipc/tipc.h @@ -2,7 +2,7 @@ * include/net/tipc/tipc.h: Main include file for TIPC users * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005,2010 Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -126,7 +126,7 @@ int tipc_createport(unsigned int tipc_user, tipc_msg_event message_cb, tipc_named_msg_event named_message_cb, tipc_conn_msg_event conn_message_cb, - tipc_continue_event continue_event_cb,/* May be zero */ + tipc_continue_event continue_event_cb, u32 *portref); int tipc_deleteport(u32 portref); @@ -145,13 +145,13 @@ int tipc_set_portunreturnable(u32 portref, unsigned int isunreturnable); int tipc_publish(u32 portref, unsigned int scope, struct tipc_name_seq const *name_seq); int tipc_withdraw(u32 portref, unsigned int scope, - struct tipc_name_seq const *name_seq); /* 0: all */ + struct tipc_name_seq const *name_seq); int tipc_connect2port(u32 portref, struct tipc_portid const *port); int tipc_disconnect(u32 portref); -int tipc_shutdown(u32 ref); /* Sends SHUTDOWN msg */ +int tipc_shutdown(u32 ref); int tipc_isconnected(u32 portref, int *isconnected); @@ -176,7 +176,7 @@ int tipc_send_buf(u32 portref, int tipc_send2name(u32 portref, struct tipc_name const *name, - u32 domain, /* 0:own zone */ + u32 domain, unsigned int num_sect, struct iovec const *msg_sect); @@ -188,7 +188,7 @@ int tipc_send_buf2name(u32 portref, int tipc_forward2name(u32 portref, struct tipc_name const *name, - u32 domain, /*0: own zone */ + u32 domain, unsigned int section_count, struct iovec const *msg_sect, struct tipc_portid const *origin, @@ -228,14 +228,14 @@ int tipc_forward_buf2port(u32 portref, int tipc_multicast(u32 portref, struct tipc_name_seq const *seq, - u32 domain, /* 0:own zone */ + u32 domain, /* currently unused */ unsigned int section_count, struct iovec const *msg); #if 0 int tipc_multicast_buf(u32 portref, struct tipc_name_seq const *seq, - u32 domain, /* 0:own zone */ + u32 domain, void *buf, unsigned int size); #endif -- cgit v1.2.3-70-g09d2 From e3826f1e946e7d2354943232f1457be1455a29e2 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Wed, 5 May 2010 00:27:06 +0000 Subject: net: reserve ports for applications using fixed port numbers (Dropped the infiniband part, because Tetsuo modified the related code, I will send a separate patch for it once this is accepted.) This patch introduces /proc/sys/net/ipv4/ip_local_reserved_ports which allows users to reserve ports for third-party applications. The reserved ports will not be used by automatic port assignments (e.g. when calling connect() or bind() with port number 0). Explicit port allocation behavior is unchanged. Signed-off-by: Octavian Purdila Signed-off-by: WANG Cong Cc: Neil Horman Cc: Eric Dumazet Cc: Eric W. Biederman Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 31 +++++++++++++++++++++++++++++++ include/net/ip.h | 6 ++++++ net/ipv4/af_inet.c | 8 +++++++- net/ipv4/inet_connection_sock.c | 6 ++++++ net/ipv4/inet_hashtables.c | 2 ++ net/ipv4/sysctl_net_ipv4.c | 17 +++++++++++++++++ net/ipv4/udp.c | 3 ++- net/sctp/socket.c | 2 ++ 8 files changed, 73 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 8b72c88ba21..d0536b5a4e0 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -588,6 +588,37 @@ ip_local_port_range - 2 INTEGERS (i.e. by default) range 1024-4999 is enough to issue up to 2000 connections per second to systems supporting timestamps. +ip_local_reserved_ports - list of comma separated ranges + Specify the ports which are reserved for known third-party + applications. These ports will not be used by automatic port + assignments (e.g. when calling connect() or bind() with port + number 0). Explicit port allocation behavior is unchanged. + + The format used for both input and output is a comma separated + list of ranges (e.g. "1,2-4,10-10" for ports 1, 2, 3, 4 and + 10). Writing to the file will clear all previously reserved + ports and update the current list with the one given in the + input. + + Note that ip_local_port_range and ip_local_reserved_ports + settings are independent and both are considered by the kernel + when determining which ports are available for automatic port + assignments. + + You can reserve ports which are not in the current + ip_local_port_range, e.g.: + + $ cat /proc/sys/net/ipv4/ip_local_port_range + 32000 61000 + $ cat /proc/sys/net/ipv4/ip_local_reserved_ports + 8080,9148 + + although this is redundant. However such a setting is useful + if later the port range is changed to a value that will + include the reserved ports. + + Default: Empty + ip_nonlocal_bind - BOOLEAN If set, allows processes to bind() to non-local IP addresses, which can be quite useful - but may break some applications. diff --git a/include/net/ip.h b/include/net/ip.h index 8149b77cea9..63548f0a44b 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -184,6 +184,12 @@ extern struct local_ports { } sysctl_local_ports; extern void inet_get_local_port_range(int *low, int *high); +extern unsigned long *sysctl_local_reserved_ports; +static inline int inet_is_reserved_local_port(int port) +{ + return test_bit(port, sysctl_local_reserved_ports); +} + extern int sysctl_ip_default_ttl; extern int sysctl_ip_nonlocal_bind; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index c6c43bcd1c6..551ce564b03 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1573,9 +1573,13 @@ static int __init inet_init(void) BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb)); + sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); + if (!sysctl_local_reserved_ports) + goto out; + rc = proto_register(&tcp_prot, 1); if (rc) - goto out; + goto out_free_reserved_ports; rc = proto_register(&udp_prot, 1); if (rc) @@ -1674,6 +1678,8 @@ out_unregister_udp_proto: proto_unregister(&udp_prot); out_unregister_tcp_proto: proto_unregister(&tcp_prot); +out_free_reserved_ports: + kfree(sysctl_local_reserved_ports); goto out; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e0a3e3537b1..70eb3507c40 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -37,6 +37,9 @@ struct local_ports sysctl_local_ports __read_mostly = { .range = { 32768, 61000 }, }; +unsigned long *sysctl_local_reserved_ports; +EXPORT_SYMBOL(sysctl_local_reserved_ports); + void inet_get_local_port_range(int *low, int *high) { unsigned seq; @@ -108,6 +111,8 @@ again: smallest_size = -1; do { + if (inet_is_reserved_local_port(rover)) + goto next_nolock; head = &hashinfo->bhash[inet_bhashfn(net, rover, hashinfo->bhash_size)]; spin_lock(&head->lock); @@ -130,6 +135,7 @@ again: break; next: spin_unlock(&head->lock); + next_nolock: if (++rover > high) rover = low; } while (--remaining > 0); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 2b79377b468..d3e160a8821 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -456,6 +456,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, local_bh_disable(); for (i = 1; i <= remaining; i++) { port = low + (i + offset) % remaining; + if (inet_is_reserved_local_port(port)) + continue; head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock(&head->lock); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1cd5c15174b..d96c1da4b17 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -299,6 +299,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = ipv4_local_port_range, }, + { + .procname = "ip_local_reserved_ports", + .data = NULL, /* initialized in sysctl_ipv4_init */ + .maxlen = 65536, + .mode = 0644, + .proc_handler = proc_do_large_bitmap, + }, #ifdef CONFIG_IP_MULTICAST { .procname = "igmp_max_memberships", @@ -736,6 +743,16 @@ static __net_initdata struct pernet_operations ipv4_sysctl_ops = { static __init int sysctl_ipv4_init(void) { struct ctl_table_header *hdr; + struct ctl_table *i; + + for (i = ipv4_table; i->procname; i++) { + if (strcmp(i->procname, "ip_local_reserved_ports") == 0) { + i->data = sysctl_local_reserved_ports; + break; + } + } + if (!i->procname) + return -EINVAL; hdr = register_sysctl_paths(net_ipv4_ctl_path, ipv4_table); if (hdr == NULL) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f3e00c5cd1e..9de6a698f91 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -233,7 +233,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, */ do { if (low <= snum && snum <= high && - !test_bit(snum >> udptable->log, bitmap)) + !test_bit(snum >> udptable->log, bitmap) && + !inet_is_reserved_local_port(snum)) goto found; snum += rand; } while (snum != first); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ba1add0b13c..ca44917872d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5433,6 +5433,8 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) rover++; if ((rover < low) || (rover > high)) rover = low; + if (inet_is_reserved_local_port(rover)) + continue; index = sctp_phashfn(rover); head = &sctp_port_hashtable[index]; sctp_spin_lock(&head->lock); -- cgit v1.2.3-70-g09d2 From a465419b1febb603821f924805529cff89cafeed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 May 2010 00:36:33 -0700 Subject: net: Introduce sk_route_nocaps TCP-MD5 sessions have intermittent failures, when route cache is invalidated. ip_queue_xmit() has to find a new route, calls sk_setup_caps(sk, &rt->u.dst), destroying the sk->sk_route_caps &= ~NETIF_F_GSO_MASK that MD5 desperately try to make all over its way (from tcp_transmit_skb() for example) So we send few bad packets, and everything is fine when tcp_transmit_skb() is called again for this socket. Since ip_queue_xmit() is at a lower level than TCP-MD5, I chose to use a socket field, sk_route_nocaps, containing bits to mask on sk_route_caps. Reported-by: Bhaskar Dutta Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 8 ++++++++ net/core/sock.c | 1 + net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_output.c | 2 +- net/ipv6/tcp_ipv6.c | 4 ++-- 5 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index 328e03f47dd..aed16eb9db4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -177,6 +177,7 @@ struct sock_common { * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings * @sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) + * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_lingertime: %SO_LINGER l_linger setting @@ -276,6 +277,7 @@ struct sock { int sk_forward_alloc; gfp_t sk_allocation; int sk_route_caps; + int sk_route_nocaps; int sk_gso_type; unsigned int sk_gso_max_size; int sk_rcvlowat; @@ -1335,6 +1337,12 @@ static inline int sk_can_gso(const struct sock *sk) extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst); +static inline void sk_nocaps_add(struct sock *sk, int flags) +{ + sk->sk_route_nocaps |= flags; + sk->sk_route_caps &= ~flags; +} + static inline int skb_copy_to_page(struct sock *sk, char __user *from, struct sk_buff *skb, struct page *page, int off, int copy) diff --git a/net/core/sock.c b/net/core/sock.c index 94c4affdda9..63530a03b8c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1231,6 +1231,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps = dst->dev->features; if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; + sk->sk_route_caps &= ~sk->sk_route_nocaps; if (sk_can_gso(sk)) { if (dst->header_len) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 771f8146a2e..202cf09c4cd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -891,7 +891,7 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -1021,7 +1021,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval, return -EINVAL; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, sk->sk_allocation); @@ -1462,7 +1462,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, if (newkey != NULL) tcp_v4_md5_do_add(newsk, newinet->inet_daddr, newkey, key->keylen); - newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5db3a2c6cb3..18a3302480c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -873,7 +873,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, NULL, skb); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6603511e367..2b7c3a100e2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -604,7 +604,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, struct in6_addr *peer, kfree(newkey); return -ENOMEM; } - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } if (tcp_alloc_md5sig_pool(sk) == NULL) { kfree(newkey); @@ -741,7 +741,7 @@ static int tcp_v6_parse_md5_keys (struct sock *sk, char __user *optval, return -ENOMEM; tp->md5sig_info = p; - sk->sk_route_caps &= ~NETIF_F_GSO_MASK; + sk_nocaps_add(sk, NETIF_F_GSO_MASK); } newkey = kmemdup(cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); -- cgit v1.2.3-70-g09d2 From 7fee226ad2397b635e2fd565a59ca3ae08a164cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 11 May 2010 23:19:48 +0000 Subject: net: add a noref bit on skb dst Use low order bit of skb->_skb_dst to tell dst is not refcounted. Change _skb_dst to _skb_refdst to make sure all uses are catched. skb_dst() returns the dst, regardless of noref bit set or not, but with a lockdep check to make sure a noref dst is not given if current user is not rcu protected. New skb_dst_set_noref() helper to set an notrefcounted dst on a skb. (with lockdep check) skb_dst_drop() drops a reference only if skb dst was refcounted. skb_dst_force() helper is used to force a refcount on dst, when skb is queued and not anymore RCU protected. Use skb_dst_force() in __sk_add_backlog(), __dev_xmit_skb() if !IFF_XMIT_DST_RELEASE or skb enqueued on qdisc queue, in sock_queue_rcv_skb(), in __nf_queue(). Use skb_dst_force() in dev_requeue_skb(). Note: dst_use_noref() still dirties dst, we might transform it later to do one dirtying per jiffies. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 58 ++++++++++++++++++++++++++++++++++++++++++++---- include/net/dst.h | 48 ++++++++++++++++++++++++++++++++++++--- include/net/sock.h | 13 ++++++----- net/core/dev.c | 3 +++ net/core/skbuff.c | 2 +- net/core/sock.c | 6 +++++ net/ipv4/icmp.c | 6 ++--- net/ipv4/ip_options.c | 9 ++++---- net/ipv4/netfilter.c | 6 ++--- net/ipv4/route.c | 2 +- net/netfilter/nf_queue.c | 2 ++ net/sched/sch_generic.c | 4 +++- 12 files changed, 134 insertions(+), 25 deletions(-) (limited to 'include/net') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9525bce80f..7cdfb4d5284 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -264,7 +264,7 @@ typedef unsigned char *sk_buff_data_t; * @transport_header: Transport layer header * @network_header: Network layer header * @mac_header: Link layer header - * @_skb_dst: destination entry + * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm * @cb: Control buffer. Free for use by every layer. Put private vars here * @len: Length of actual data @@ -328,7 +328,7 @@ struct sk_buff { */ char cb[48] __aligned(8); - unsigned long _skb_dst; + unsigned long _skb_refdst; #ifdef CONFIG_XFRM struct sec_path *sp; #endif @@ -419,14 +419,64 @@ struct sk_buff { #include +/* + * skb might have a dst pointer attached, refcounted or not. + * _skb_refdst low order bit is set if refcount was _not_ taken + */ +#define SKB_DST_NOREF 1UL +#define SKB_DST_PTRMASK ~(SKB_DST_NOREF) + +/** + * skb_dst - returns skb dst_entry + * @skb: buffer + * + * Returns skb dst_entry, regardless of reference taken or not. + */ static inline struct dst_entry *skb_dst(const struct sk_buff *skb) { - return (struct dst_entry *)skb->_skb_dst; + /* If refdst was not refcounted, check we still are in a + * rcu_read_lock section + */ + WARN_ON((skb->_skb_refdst & SKB_DST_NOREF) && + !rcu_read_lock_held() && + !rcu_read_lock_bh_held()); + return (struct dst_entry *)(skb->_skb_refdst & SKB_DST_PTRMASK); } +/** + * skb_dst_set - sets skb dst + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was taken on dst and should + * be released by skb_dst_drop() + */ static inline void skb_dst_set(struct sk_buff *skb, struct dst_entry *dst) { - skb->_skb_dst = (unsigned long)dst; + skb->_skb_refdst = (unsigned long)dst; +} + +/** + * skb_dst_set_noref - sets skb dst, without a reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst + * skb_dst_drop() should not dst_release() this dst + */ +static inline void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +{ + WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; +} + +/** + * skb_dst_is_noref - Test if skb dst isnt refcounted + * @skb: buffer + */ +static inline bool skb_dst_is_noref(const struct sk_buff *skb) +{ + return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } static inline struct rtable *skb_rtable(const struct sk_buff *skb) diff --git a/include/net/dst.h b/include/net/dst.h index aac5a5fcfda..27207a13f2a 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -168,6 +168,12 @@ static inline void dst_use(struct dst_entry *dst, unsigned long time) dst->lastuse = time; } +static inline void dst_use_noref(struct dst_entry *dst, unsigned long time) +{ + dst->__use++; + dst->lastuse = time; +} + static inline struct dst_entry * dst_clone(struct dst_entry * dst) { @@ -177,11 +183,47 @@ struct dst_entry * dst_clone(struct dst_entry * dst) } extern void dst_release(struct dst_entry *dst); + +static inline void refdst_drop(unsigned long refdst) +{ + if (!(refdst & SKB_DST_NOREF)) + dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK)); +} + +/** + * skb_dst_drop - drops skb dst + * @skb: buffer + * + * Drops dst reference count if a reference was taken. + */ static inline void skb_dst_drop(struct sk_buff *skb) { - if (skb->_skb_dst) - dst_release(skb_dst(skb)); - skb->_skb_dst = 0UL; + if (skb->_skb_refdst) { + refdst_drop(skb->_skb_refdst); + skb->_skb_refdst = 0UL; + } +} + +static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb) +{ + nskb->_skb_refdst = oskb->_skb_refdst; + if (!(nskb->_skb_refdst & SKB_DST_NOREF)) + dst_clone(skb_dst(nskb)); +} + +/** + * skb_dst_force - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted, let's do it + */ +static inline void skb_dst_force(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + WARN_ON(!rcu_read_lock_held()); + skb->_skb_refdst &= ~SKB_DST_NOREF; + dst_clone(skb_dst(skb)); + } } /* Children define the path of the packet through the diff --git a/include/net/sock.h b/include/net/sock.h index aed16eb9db4..5697caf8cc7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -600,12 +600,15 @@ static inline int sk_stream_memory_free(struct sock *sk) /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { - if (!sk->sk_backlog.tail) { - sk->sk_backlog.head = sk->sk_backlog.tail = skb; - } else { + /* dont let skb dst not refcounted, we are going to leave rcu lock */ + skb_dst_force(skb); + + if (!sk->sk_backlog.tail) + sk->sk_backlog.head = skb; + else sk->sk_backlog.tail->next = skb; - sk->sk_backlog.tail = skb; - } + + sk->sk_backlog.tail = skb; skb->next = NULL; } diff --git a/net/core/dev.c b/net/core/dev.c index cdcb9cbedf4..6c820650b80 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2052,6 +2052,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ + if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + skb_dst_force(skb); __qdisc_update_bstats(q, skb->len); if (sch_direct_xmit(skb, q, dev, txq, root_lock)) __qdisc_run(q); @@ -2060,6 +2062,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_SUCCESS; } else { + skb_dst_force(skb); rc = qdisc_enqueue_root(skb, q); qdisc_run(q); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a9b0e1f7780..c543dd25243 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -520,7 +520,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; - skb_dst_set(new, dst_clone(skb_dst(old))); + skb_dst_copy(new, old); new->rxhash = old->rxhash; #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); diff --git a/net/core/sock.c b/net/core/sock.c index 63530a03b8c..bf88a167c8f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -307,6 +307,11 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ skb_len = skb->len; + /* we escape from rcu protected region, make sure we dont leak + * a norefcounted dst + */ + skb_dst_force(skb); + spin_lock_irqsave(&list->lock, flags); skb->dropcount = atomic_read(&sk->sk_drops); __skb_queue_tail(list, skb); @@ -1536,6 +1541,7 @@ static void __release_sock(struct sock *sk) do { struct sk_buff *next = skb->next; + WARN_ON_ONCE(skb_dst_is_noref(skb)); skb->next = NULL; sk_backlog_rcv(sk, skb); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f3d339f728b..d65e9215bcd 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -587,20 +587,20 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) err = __ip_route_output_key(net, &rt2, &fl); else { struct flowi fl2 = {}; - struct dst_entry *odst; + unsigned long orefdst; fl2.fl4_dst = fl.fl4_src; if (ip_route_output_key(net, &rt2, &fl2)) goto relookup_failed; /* Ugh! */ - odst = skb_dst(skb_in); + orefdst = skb_in->_skb_refdst; /* save old refdst */ err = ip_route_input(skb_in, fl.fl4_dst, fl.fl4_src, RT_TOS(tos), rt2->u.dst.dev); dst_release(&rt2->u.dst); rt2 = skb_rtable(skb_in); - skb_dst_set(skb_in, odst); + skb_in->_skb_refdst = orefdst; /* restore old refdst */ } if (err) diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 4c09a31fd14..3244133c24f 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -601,6 +601,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) unsigned char *optptr = skb_network_header(skb) + opt->srr; struct rtable *rt = skb_rtable(skb); struct rtable *rt2; + unsigned long orefdst; int err; if (!opt->srr) @@ -624,16 +625,16 @@ int ip_options_rcv_srr(struct sk_buff *skb) } memcpy(&nexthop, &optptr[srrptr-1], 4); - rt = skb_rtable(skb); + orefdst = skb->_skb_refdst; skb_dst_set(skb, NULL); err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev); rt2 = skb_rtable(skb); if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) { - ip_rt_put(rt2); - skb_dst_set(skb, &rt->u.dst); + skb_dst_drop(skb); + skb->_skb_refdst = orefdst; return -EINVAL; } - ip_rt_put(rt); + refdst_drop(orefdst); if (rt2->rt_type != RTN_LOCAL) break; /* Superfast 8) loopback forward */ diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 82fb43c5c59..07de855e217 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,7 +17,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi fl = {}; - struct dst_entry *odst; + unsigned long orefdst; unsigned int hh_len; unsigned int type; @@ -51,14 +51,14 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) if (ip_route_output_key(net, &rt, &fl) != 0) return -1; - odst = skb_dst(skb); + orefdst = skb->_skb_refdst; if (ip_route_input(skb, iph->daddr, iph->saddr, RT_TOS(iph->tos), rt->u.dst.dev) != 0) { dst_release(&rt->u.dst); return -1; } dst_release(&rt->u.dst); - dst_release(odst); + refdst_drop(orefdst); } if (skb_dst(skb)->error) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index dea3f926425..705eccfb476 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3033,7 +3033,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; if (rt_is_expired(rt)) continue; - skb_dst_set(skb, dst_clone(&rt->u.dst)); + skb_dst_set_noref(skb, &rt->u.dst); if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 0b1103c0b1f..78b3cf9c519 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "nf_internals.h" @@ -170,6 +171,7 @@ static int __nf_queue(struct sk_buff *skb, dev_hold(physoutdev); } #endif + skb_dst_force(skb); afinfo->saveroute(skb, entry); status = qh->outfn(entry, queuenum); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a969b111bd7..a63029ef3ed 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -26,6 +26,7 @@ #include #include #include +#include /* Main transmission queue. */ @@ -40,6 +41,7 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { + skb_dst_force(skb); q->gso_skb = skb; q->qstats.requeues++; q->q.qlen++; /* it's still part of the queue */ @@ -179,7 +181,7 @@ static inline int qdisc_restart(struct Qdisc *q) skb = dequeue_skb(q); if (unlikely(!skb)) return 0; - + WARN_ON_ONCE(skb_dst_is_noref(skb)); root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); -- cgit v1.2.3-70-g09d2 From 407eadd996dc62a827db85f1d0c286a98fd5d336 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 10 May 2010 11:32:55 +0000 Subject: net: implements ip_route_input_noref() ip_route_input() is the version returning a refcounted dst, while ip_route_input_noref() returns a non refcounted one. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/route.h | 17 ++++++++++++++++- net/ipv4/route.c | 15 ++++++++++----- 2 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include/net') diff --git a/include/net/route.h b/include/net/route.h index 2c9fba7f773..af6cf4b4c9d 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -112,7 +112,22 @@ extern void rt_cache_flush_batch(void); extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); -extern int ip_route_input(struct sk_buff*, __be32 dst, __be32 src, u8 tos, struct net_device *devin); + +extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin, bool noref); + +static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin) +{ + return ip_route_input_common(skb, dst, src, tos, devin, false); +} + +static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src, + u8 tos, struct net_device *devin) +{ + return ip_route_input_common(skb, dst, src, tos, devin, true); +} + extern unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, unsigned short new_mtu, struct net_device *dev); extern void ip_rt_send_redirect(struct sk_buff *skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 705eccfb476..560acc677ce 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2277,8 +2277,8 @@ martian_source: goto e_inval; } -int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, - u8 tos, struct net_device *dev) +int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, bool noref) { struct rtable * rth; unsigned hash; @@ -2304,10 +2304,15 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.mark == skb->mark && net_eq(dev_net(rth->u.dst.dev), net) && !rt_is_expired(rth)) { - dst_use(&rth->u.dst, jiffies); + if (noref) { + dst_use_noref(&rth->u.dst, jiffies); + skb_dst_set_noref(skb, &rth->u.dst); + } else { + dst_use(&rth->u.dst, jiffies); + skb_dst_set(skb, &rth->u.dst); + } RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); - skb_dst_set(skb, &rth->u.dst); return 0; } RT_CACHE_STAT_INC(in_hlist_search); @@ -2350,6 +2355,7 @@ skip_cache: } return ip_route_input_slow(skb, daddr, saddr, tos, dev); } +EXPORT_SYMBOL(ip_route_input_common); static int __mkroute_output(struct rtable **result, struct fib_result *res, @@ -3361,5 +3367,4 @@ void __init ip_static_sysctl_init(void) #endif EXPORT_SYMBOL(__ip_select_ident); -EXPORT_SYMBOL(ip_route_input); EXPORT_SYMBOL(ip_route_output_key); -- cgit v1.2.3-70-g09d2 From cb863ffd4a04f9f8619f52c01d472a64ccc716bd Mon Sep 17 00:00:00 2001 From: andrew hendry Date: Sun, 16 May 2010 22:59:41 +0000 Subject: X25: Move qbit flag to bitfield Moves the X25 q bit flag from char into a bitfield to allow BKL cleanup. Signed-off-by: Andrew Hendry Signed-off-by: David S. Miller --- include/net/x25.h | 6 +++++- net/x25/af_x25.c | 17 ++++++++++------- 2 files changed, 15 insertions(+), 8 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 468551ea4f1..7b5795e1ceb 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -113,6 +113,9 @@ enum { #define X25_MAX_AE_LEN 40 /* Max num of semi-octets in AE - OSI Nw */ #define X25_MAX_DTE_FACIL_LEN 21 /* Max length of DTE facility params */ +/* Bitset in x25_sock->flags for misc flags */ +#define X25_Q_BIT_FLAG 0 + /** * struct x25_route - x25 routing entry * @node - entry in x25_list_lock @@ -146,10 +149,11 @@ struct x25_sock { struct x25_address source_addr, dest_addr; struct x25_neigh *neighbour; unsigned int lci, cudmatchlength; - unsigned char state, condition, qbitincl, intflag, accptapprv; + unsigned char state, condition, intflag, accptapprv; unsigned short vs, vr, va, vl; unsigned long t2, t21, t22, t23; unsigned short fraglen; + unsigned long flags; struct sk_buff_head ack_queue; struct sk_buff_head fragment_queue; struct sk_buff_head interrupt_in_queue; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 296e65e0106..720534ce1fd 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -465,7 +465,10 @@ static int x25_setsockopt(struct socket *sock, int level, int optname, if (get_user(opt, (int __user *)optval)) goto out; - x25_sk(sk)->qbitincl = !!opt; + if (opt) + set_bit(X25_Q_BIT_FLAG, &x25_sk(sk)->flags); + else + clear_bit(X25_Q_BIT_FLAG, &x25_sk(sk)->flags); rc = 0; out: unlock_kernel(); @@ -496,7 +499,7 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (put_user(len, optlen)) goto out; - val = x25_sk(sk)->qbitincl; + val = test_bit(X25_Q_BIT_FLAG, &x25_sk(sk)->flags); rc = copy_to_user(optval, &val, len) ? -EFAULT : 0; out: unlock_kernel(); @@ -632,8 +635,8 @@ static struct sock *x25_make_new(struct sock *osk) x25->t22 = ox25->t22; x25->t23 = ox25->t23; x25->t2 = ox25->t2; + x25->flags = ox25->flags; x25->facilities = ox25->facilities; - x25->qbitincl = ox25->qbitincl; x25->dte_facilities = ox25->dte_facilities; x25->cudmatchlength = ox25->cudmatchlength; x25->accptapprv = ox25->accptapprv; @@ -1186,7 +1189,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, * If the Q BIT Include socket option is in force, the first * byte of the user data is the logical value of the Q Bit. */ - if (x25->qbitincl) { + if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { qbit = skb->data[0]; skb_pull(skb, 1); } @@ -1242,7 +1245,7 @@ static int x25_sendmsg(struct kiocb *iocb, struct socket *sock, len = rc; if (rc < 0) kfree_skb(skb); - else if (x25->qbitincl) + else if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) len++; } @@ -1307,7 +1310,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, /* * No Q bit information on Interrupt data. */ - if (x25->qbitincl) { + if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { asmptr = skb_push(skb, 1); *asmptr = 0x00; } @@ -1325,7 +1328,7 @@ static int x25_recvmsg(struct kiocb *iocb, struct socket *sock, skb_pull(skb, x25->neighbour->extended ? X25_EXT_MIN_LEN : X25_STD_MIN_LEN); - if (x25->qbitincl) { + if (test_bit(X25_Q_BIT_FLAG, &x25->flags)) { asmptr = skb_push(skb, 1); *asmptr = qbit; } -- cgit v1.2.3-70-g09d2 From b7792e34cba641c49cd436d42fbfd2a632ff39d3 Mon Sep 17 00:00:00 2001 From: andrew hendry Date: Sun, 16 May 2010 23:00:02 +0000 Subject: X25: Move interrupt flag to bitfield Moves the x25 interrupt flag from char into bitfield. Signed-off-by: Andrew Hendry Signed-off-by: David S. Miller --- include/net/x25.h | 3 ++- net/x25/af_x25.c | 1 + net/x25/x25_in.c | 2 +- net/x25/x25_out.c | 5 +++-- 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 7b5795e1ceb..1576e92c6ce 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -115,6 +115,7 @@ enum { /* Bitset in x25_sock->flags for misc flags */ #define X25_Q_BIT_FLAG 0 +#define X25_INTERRUPT_FLAG 1 /** * struct x25_route - x25 routing entry @@ -149,7 +150,7 @@ struct x25_sock { struct x25_address source_addr, dest_addr; struct x25_neigh *neighbour; unsigned int lci, cudmatchlength; - unsigned char state, condition, intflag, accptapprv; + unsigned char state, condition, accptapprv; unsigned short vs, vr, va, vl; unsigned long t2, t21, t22, t23; unsigned short fraglen; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 720534ce1fd..3d97b8caf0b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -641,6 +641,7 @@ static struct sock *x25_make_new(struct sock *osk) x25->cudmatchlength = ox25->cudmatchlength; x25->accptapprv = ox25->accptapprv; + clear_bit(X25_INTERRUPT_FLAG, &x25->flags); x25_init_timers(sk); out: return sk; diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 372ac226e64..63178961efa 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -273,7 +273,7 @@ static int x25_state3_machine(struct sock *sk, struct sk_buff *skb, int frametyp break; case X25_INTERRUPT_CONFIRMATION: - x25->intflag = 0; + clear_bit(X25_INTERRUPT_FLAG, &x25->flags); break; case X25_INTERRUPT: diff --git a/net/x25/x25_out.c b/net/x25/x25_out.c index 52351a26b6f..d00649fb251 100644 --- a/net/x25/x25_out.c +++ b/net/x25/x25_out.c @@ -148,8 +148,9 @@ void x25_kick(struct sock *sk) /* * Transmit interrupt data. */ - if (!x25->intflag && skb_peek(&x25->interrupt_out_queue) != NULL) { - x25->intflag = 1; + if (skb_peek(&x25->interrupt_out_queue) != NULL && + !test_and_set_bit(X25_INTERRUPT_FLAG, &x25->flags)) { + skb = skb_dequeue(&x25->interrupt_out_queue); x25_transmit_link(skb, x25->neighbour); } -- cgit v1.2.3-70-g09d2 From 37cda78741ecdbf45dd9b64e4c99dbdb11b47b46 Mon Sep 17 00:00:00 2001 From: andrew hendry Date: Sun, 16 May 2010 23:00:27 +0000 Subject: X25: Move accept approve flag to bitfield Moves the x25 accept approve flag from char into bitfield. Signed-off-by: Andrew Hendry Signed-off-by: David S. Miller --- include/net/x25.h | 5 ++--- net/x25/af_x25.c | 12 ++++++------ 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/x25.h b/include/net/x25.h index 1576e92c6ce..1479cb4a41f 100644 --- a/include/net/x25.h +++ b/include/net/x25.h @@ -80,8 +80,6 @@ enum { #define X25_DEFAULT_PACKET_SIZE X25_PS128 /* Default Packet Size */ #define X25_DEFAULT_THROUGHPUT 0x0A /* Deafult Throughput */ #define X25_DEFAULT_REVERSE 0x00 /* Default Reverse Charging */ -#define X25_DENY_ACCPT_APPRV 0x01 /* Default value */ -#define X25_ALLOW_ACCPT_APPRV 0x00 /* Control enabled */ #define X25_SMODULUS 8 #define X25_EMODULUS 128 @@ -116,6 +114,7 @@ enum { /* Bitset in x25_sock->flags for misc flags */ #define X25_Q_BIT_FLAG 0 #define X25_INTERRUPT_FLAG 1 +#define X25_ACCPT_APPRV_FLAG 2 /** * struct x25_route - x25 routing entry @@ -150,7 +149,7 @@ struct x25_sock { struct x25_address source_addr, dest_addr; struct x25_neigh *neighbour; unsigned int lci, cudmatchlength; - unsigned char state, condition, accptapprv; + unsigned char state, condition; unsigned short vs, vr, va, vl; unsigned long t2, t21, t22, t23; unsigned short fraglen; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 3d97b8caf0b..e5c1e3298f8 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -586,7 +586,7 @@ static int x25_create(struct net *net, struct socket *sock, int protocol, x25->t2 = sysctl_x25_ack_holdback_timeout; x25->state = X25_STATE_0; x25->cudmatchlength = 0; - x25->accptapprv = X25_DENY_ACCPT_APPRV; /* normally no cud */ + set_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); /* normally no cud */ /* on call accept */ x25->facilities.winsize_in = X25_DEFAULT_WINDOW_SIZE; @@ -639,7 +639,6 @@ static struct sock *x25_make_new(struct sock *osk) x25->facilities = ox25->facilities; x25->dte_facilities = ox25->dte_facilities; x25->cudmatchlength = ox25->cudmatchlength; - x25->accptapprv = ox25->accptapprv; clear_bit(X25_INTERRUPT_FLAG, &x25->flags); x25_init_timers(sk); @@ -1057,8 +1056,8 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb, makex25->vc_facil_mask &= ~X25_MASK_CALLING_AE; makex25->cudmatchlength = x25_sk(sk)->cudmatchlength; - /* Normally all calls are accepted immediatly */ - if(makex25->accptapprv & X25_DENY_ACCPT_APPRV) { + /* Normally all calls are accepted immediately */ + if (test_bit(X25_ACCPT_APPRV_FLAG, &makex25->flags)) { x25_write_internal(make, X25_CALL_ACCEPTED); makex25->state = X25_STATE_3; } @@ -1580,7 +1579,7 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = -EINVAL; if (sk->sk_state != TCP_CLOSE) break; - x25->accptapprv = X25_ALLOW_ACCPT_APPRV; + clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); rc = 0; break; } @@ -1589,7 +1588,8 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) rc = -EINVAL; if (sk->sk_state != TCP_ESTABLISHED) break; - if (x25->accptapprv) /* must call accptapprv above */ + /* must call accptapprv above */ + if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags)) break; x25_write_internal(sk, X25_CALL_ACCEPTED); x25->state = X25_STATE_3; -- cgit v1.2.3-70-g09d2 From d19d56ddc88e7895429ef118db9c83c7bbe3ce6a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 17 May 2010 22:36:55 -0700 Subject: net: Introduce skb_tunnel_rx() helper skb rxhash should be cleared when a skb is handled by a tunnel before being delivered again, so that correct packet steering can take place. There are other cleanups and accounting that we can factorize in a new helper, skb_tunnel_rx() Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 20 ++++++++++++++++++++ net/ipv4/ip_gre.c | 9 +-------- net/ipv4/ipip.c | 7 ++----- net/ipv4/ipmr.c | 8 +++----- net/ipv6/ip6_tunnel.c | 8 ++------ net/ipv6/ip6mr.c | 8 +++----- net/ipv6/sit.c | 8 +++----- 7 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/net') diff --git a/include/net/dst.h b/include/net/dst.h index 27207a13f2a..612069beda7 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -226,6 +226,26 @@ static inline void skb_dst_force(struct sk_buff *skb) } } + +/** + * skb_tunnel_rx - prepare skb for rx reinsert + * @skb: buffer + * @dev: tunnel device + * + * After decapsulation, packet is going to re-enter (netif_rx()) our stack, + * so make some cleanups, and perform accounting. + */ +static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev) +{ + skb->dev = dev; + /* TODO : stats should be SMP safe */ + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; + skb->rxhash = 0; + skb_dst_drop(skb); + nf_reset(skb); +} + /* Children define the path of the packet through the * Linux networking. Thus, destinations are stackable. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index fe381d12ecd..498cf69c797 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -538,7 +538,6 @@ static int ipgre_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; int offset = 4; __be16 gre_proto; - unsigned int len; if (!pskb_may_pull(skb, 16)) goto drop_nolock; @@ -629,8 +628,6 @@ static int ipgre_rcv(struct sk_buff *skb) tunnel->i_seqno = seqno + 1; } - len = skb->len; - /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -644,11 +641,7 @@ static int ipgre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - stats->rx_packets++; - stats->rx_bytes += len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + skb_tunnel_rx(skb, tunnel->dev); skb_reset_network_header(skb); ipgre_ecn_decapsulate(iph, skb); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 0b27b14dcc9..7fd63671103 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -374,11 +374,8 @@ static int ipip_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); skb->pkt_type = PACKET_HOST; - tunnel->dev->stats.rx_packets++; - tunnel->dev->stats.rx_bytes += skb->len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + skb_tunnel_rx(skb, tunnel->dev); + ipip_ecn_decapsulate(iph, skb); netif_rx(skb); rcu_read_unlock(); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7a7ee1cc3b5..217ebe035b3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1831,14 +1831,12 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, skb->mac_header = skb->network_header; skb_pull(skb, (u8*)encap - skb->data); skb_reset_network_header(skb); - skb->dev = reg_dev; skb->protocol = htons(ETH_P_IP); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - skb_dst_drop(skb); - reg_dev->stats.rx_bytes += skb->len; - reg_dev->stats.rx_packets++; - nf_reset(skb); + + skb_tunnel_rx(skb, reg_dev); + netif_rx(skb); dev_put(reg_dev); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 2599870747e..8f39893d808 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -723,14 +723,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, skb->protocol = htons(protocol); skb->pkt_type = PACKET_HOST; memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); - skb->dev = t->dev; - skb_dst_drop(skb); - nf_reset(skb); - dscp_ecn_decapsulate(t, ipv6h, skb); + skb_tunnel_rx(skb, t->dev); - t->dev->stats.rx_packets++; - t->dev->stats.rx_bytes += skb->len; + dscp_ecn_decapsulate(t, ipv6h, skb); netif_rx(skb); rcu_read_unlock(); return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 163850e22b1..bd9e7d3e9c8 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -658,14 +658,12 @@ static int pim6_rcv(struct sk_buff *skb) skb->mac_header = skb->network_header; skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); - skb->dev = reg_dev; skb->protocol = htons(ETH_P_IPV6); skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; - skb_dst_drop(skb); - reg_dev->stats.rx_bytes += skb->len; - reg_dev->stats.rx_packets++; - nf_reset(skb); + + skb_tunnel_rx(skb, reg_dev); + netif_rx(skb); dev_put(reg_dev); return 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 5abae10cd88..e51e650ea80 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -566,11 +566,9 @@ static int ipip6_rcv(struct sk_buff *skb) kfree_skb(skb); return 0; } - tunnel->dev->stats.rx_packets++; - tunnel->dev->stats.rx_bytes += skb->len; - skb->dev = tunnel->dev; - skb_dst_drop(skb); - nf_reset(skb); + + skb_tunnel_rx(skb, tunnel->dev); + ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); rcu_read_unlock(); -- cgit v1.2.3-70-g09d2 From e9d3e084975869754d16f639378675c353560be9 Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Tue, 18 May 2010 15:36:06 -0700 Subject: ipv6: Replace inet6_ifaddr->dead with state This patch replaces the boolean dead flag on inet6_ifaddr with a state enum. This allows us to roll back changes when deleting an address according to whether DAD has completed or not. This patch only adds the state field and does not change the logic. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/if_inet6.h | 12 ++++++++++-- net/ipv6/addrconf.c | 16 +++++++++------- 2 files changed, 19 insertions(+), 9 deletions(-) (limited to 'include/net') diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 13f9fc086d5..f95ff8d9aa4 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -32,6 +32,13 @@ #ifdef __KERNEL__ +enum { + INET6_IFADDR_STATE_DAD, + INET6_IFADDR_STATE_POSTDAD, + INET6_IFADDR_STATE_UP, + INET6_IFADDR_STATE_DEAD, +}; + struct inet6_ifaddr { struct in6_addr addr; __u32 prefix_len; @@ -40,6 +47,9 @@ struct inet6_ifaddr { __u32 prefered_lft; atomic_t refcnt; spinlock_t lock; + spinlock_t state_lock; + + int state; __u8 probes; __u8 flags; @@ -62,8 +72,6 @@ struct inet6_ifaddr { struct inet6_ifaddr *ifpub; int regen_count; #endif - - int dead; struct rcu_head rcu; }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 75d3b8c1e85..4e5ad9de167 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -553,7 +553,7 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) if (del_timer(&ifp->timer)) pr_notice("Timer is still running, when freeing ifa=%p\n", ifp); - if (!ifp->dead) { + if (ifp->state != INET6_IFADDR_STATE_DEAD) { pr_warning("Freeing alive inet6 address %p\n", ifp); return; } @@ -648,6 +648,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, ipv6_addr_copy(&ifa->addr, addr); spin_lock_init(&ifa->lock); + spin_lock_init(&ifa->state_lock); init_timer(&ifa->timer); INIT_HLIST_NODE(&ifa->addr_lst); ifa->timer.data = (unsigned long) ifa; @@ -720,7 +721,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) hash = ipv6_addr_hash(&ifp->addr); - ifp->dead = 1; + ifp->state = INET6_IFADDR_STATE_DEAD; spin_lock_bh(&addrconf_hash_lock); hlist_del_init_rcu(&ifp->addr_lst); @@ -2665,7 +2666,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) ifa = list_first_entry(&idev->tempaddr_list, struct inet6_ifaddr, tmp_list); list_del(&ifa->tmp_list); - ifa->dead = 1; + ifa->state = INET6_IFADDR_STATE_DEAD; write_unlock_bh(&idev->lock); spin_lock_bh(&ifa->lock); @@ -2707,7 +2708,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_unlock_bh(&idev->lock); } else { list_del(&ifa->if_list); - ifa->dead = 1; + ifa->state = INET6_IFADDR_STATE_DEAD; write_unlock_bh(&idev->lock); /* clear hash table */ @@ -2717,7 +2718,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) } __ipv6_ifa_notify(RTM_DELADDR, ifa); - if (ifa->dead) + if (ifa->state == INET6_IFADDR_STATE_DEAD) atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); in6_ifa_put(ifa); @@ -2815,7 +2816,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) net_srandom(ifp->addr.s6_addr32[3]); read_lock_bh(&idev->lock); - if (ifp->dead) + if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; spin_lock(&ifp->lock); @@ -4050,7 +4051,8 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->u.dst); - if (ifp->dead && ip6_del_rt(ifp->rt)) + if (ifp->state == INET6_IFADDR_STATE_DEAD && + ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->u.dst); break; } -- cgit v1.2.3-70-g09d2