From 71951b64a5a87c09eb6fde59ce51aaab2fdaeab2 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 24 Apr 2009 16:58:41 +0200 Subject: netfilter: nf_ct_dccp: add missing role attributes for DCCP This patch adds missing role attribute to the DCCP type, otherwise the creation of entries is not of any use. The attribute added is CTA_PROTOINFO_DCCP_ROLE which contains the role of the conntrack original tuple. Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- include/linux/netfilter/nfnetlink_conntrack.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 29fe9ea1d34..1a865e48b8e 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -100,6 +100,7 @@ enum ctattr_protoinfo_tcp { enum ctattr_protoinfo_dccp { CTA_PROTOINFO_DCCP_UNSPEC, CTA_PROTOINFO_DCCP_STATE, + CTA_PROTOINFO_DCCP_ROLE, __CTA_PROTOINFO_DCCP_MAX, }; #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1) -- cgit v1.2.3 From c759a6b4e1cae6aff71f58c9c85404ebcd81b6e0 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Mon, 27 Apr 2009 02:36:20 -0700 Subject: net: Fix LL_MAX_HEADER for CONFIG_TR_MODULE Unless I miss anything this should fix a bug. Signed-off-by: Adrian Bunk Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2e7783f4a75..453be9a674c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -104,7 +104,7 @@ struct wireless_dev; # else # define LL_MAX_HEADER 96 # endif -#elif defined(CONFIG_TR) +#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) # define LL_MAX_HEADER 48 #else # define LL_MAX_HEADER 32 -- cgit v1.2.3 From 37b607c5ac3b7c92a6a3624bb29f1cdcdcf7044a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Mon, 27 Apr 2009 05:45:54 -0700 Subject: net: Fix typo in net_device_ops description. Signed-off-by: Mike Rapoport Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 453be9a674c..5a96a1a406e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -500,7 +500,7 @@ struct netdev_queue { * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address - * needs to be changed. If not this interface is not defined, the + * needs to be changed. If this interface is not defined, the * mac address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); -- cgit v1.2.3 From bf368e4e70cd4e0f880923c44e95a4273d725ab4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2009 02:24:21 -0700 Subject: net: Avoid extra wakeups of threads blocked in wait_for_packet() In 2.6.25 we added UDP mem accounting. This unfortunatly added a penalty when a frame is transmitted, since we have at TX completion time to call sock_wfree() to perform necessary memory accounting. This calls sock_def_write_space() and utimately scheduler if any thread is waiting on the socket. Thread(s) waiting for an incoming frame was scheduled, then had to sleep again as event was meaningless. (All threads waiting on a socket are using same sk_sleep anchor) This adds lot of extra wakeups and increases latencies, as noted by Christoph Lameter, and slows down softirq handler. Reference : http://marc.info/?l=linux-netdev&m=124060437012283&w=2 Fortunatly, Davide Libenzi recently added concept of keyed wakeups into kernel, and particularly for sockets (see commit 37e5540b3c9d838eb20f2ca8ea2eb8072271e403 epoll keyed wakeups: make sockets use keyed wakeups) Davide goal was to optimize epoll, but this new wakeup infrastructure can help non epoll users as well, if they care to setup an appropriate handler. This patch introduces new DEFINE_WAIT_FUNC() helper and uses it in wait_for_packet(), so that only relevant event can wakeup a thread blocked in this function. Trace of function calls from bnx2 TX completion bnx2_poll_work() is : __kfree_skb() skb_release_head_state() sock_wfree() sock_def_write_space() __wake_up_sync_key() __wake_up_common() receiver_wake_function() : Stops here since thread is waiting for an INPUT Reported-by: Christoph Lameter Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/wait.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 5d631c17eae..bc024632f36 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -440,13 +440,15 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key); int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); -#define DEFINE_WAIT(name) \ +#define DEFINE_WAIT_FUNC(name, function) \ wait_queue_t name = { \ .private = current, \ - .func = autoremove_wake_function, \ + .func = function, \ .task_list = LIST_HEAD_INIT((name).task_list), \ } +#define DEFINE_WAIT(name) DEFINE_WAIT_FUNC(name, autoremove_wake_function) + #define DEFINE_WAIT_BIT(name, word, bit) \ struct wait_bit_queue name = { \ .key = __WAIT_BIT_KEY_INITIALIZER(word, bit), \ -- cgit v1.2.3 From 942e4a2bd680c606af0211e64eb216be2e19bf61 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Tue, 28 Apr 2009 22:36:33 -0700 Subject: netfilter: revised locking for x_tables The x_tables are organized with a table structure and a per-cpu copies of the counters and rules. On older kernels there was a reader/writer lock per table which was a performance bottleneck. In 2.6.30-rc, this was converted to use RCU and the counters/rules which solved the performance problems for do_table but made replacing rules much slower because of the necessary RCU grace period. This version uses a per-cpu set of spinlocks and counters to allow to table processing to proceed without the cache thrashing of a global reader lock and keeps the same performance for table updates. Signed-off-by: Stephen Hemminger Acked-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/netfilter/x_tables.h | 73 +++++++++++++++++++++++++++++++++++--- 1 file changed, 68 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 7b1a652066c..1b2e43502ef 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -354,9 +354,6 @@ struct xt_table /* What hooks you will enter on */ unsigned int valid_hooks; - /* Lock for the curtain */ - struct mutex lock; - /* Man behind the curtain... */ struct xt_table_info *private; @@ -434,8 +431,74 @@ extern void xt_proto_fini(struct net *net, u_int8_t af); extern struct xt_table_info *xt_alloc_table_info(unsigned int size); extern void xt_free_table_info(struct xt_table_info *info); -extern void xt_table_entry_swap_rcu(struct xt_table_info *old, - struct xt_table_info *new); + +/* + * Per-CPU spinlock associated with per-cpu table entries, and + * with a counter for the "reading" side that allows a recursive + * reader to avoid taking the lock and deadlocking. + * + * "reading" is used by ip/arp/ip6 tables rule processing which runs per-cpu. + * It needs to ensure that the rules are not being changed while the packet + * is being processed. In some cases, the read lock will be acquired + * twice on the same CPU; this is okay because of the count. + * + * "writing" is used when reading counters. + * During replace any readers that are using the old tables have to complete + * before freeing the old table. This is handled by the write locking + * necessary for reading the counters. + */ +struct xt_info_lock { + spinlock_t lock; + unsigned char readers; +}; +DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks); + +/* + * Note: we need to ensure that preemption is disabled before acquiring + * the per-cpu-variable, so we do it as a two step process rather than + * using "spin_lock_bh()". + * + * We _also_ need to disable bottom half processing before updating our + * nesting count, to make sure that the only kind of re-entrancy is this + * code being called by itself: since the count+lock is not an atomic + * operation, we can allow no races. + * + * _Only_ that special combination of being per-cpu and never getting + * re-entered asynchronously means that the count is safe. + */ +static inline void xt_info_rdlock_bh(void) +{ + struct xt_info_lock *lock; + + local_bh_disable(); + lock = &__get_cpu_var(xt_info_locks); + if (!lock->readers++) + spin_lock(&lock->lock); +} + +static inline void xt_info_rdunlock_bh(void) +{ + struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks); + + if (!--lock->readers) + spin_unlock(&lock->lock); + local_bh_enable(); +} + +/* + * The "writer" side needs to get exclusive access to the lock, + * regardless of readers. This must be called with bottom half + * processing (and thus also preemption) disabled. + */ +static inline void xt_info_wrlock(unsigned int cpu) +{ + spin_lock(&per_cpu(xt_info_locks, cpu).lock); +} + +static inline void xt_info_wrunlock(unsigned int cpu) +{ + spin_unlock(&per_cpu(xt_info_locks, cpu).lock); +} /* * This helper is performance critical and must be inlined -- cgit v1.2.3