4 files changed, 75 insertions, 9 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2e7783f4a755..5a96a1a406e9 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
@@ -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);
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 29fe9ea1d346..1a865e48b8eb 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)
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 7b1a652066c0..1b2e43502ef7 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
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 5d631c17eaee..bc024632f365 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),           \