kevent: network notifications.

index 802ae76..3473f5c 100644
@@ -49,4 +49,6 @@ #define SO_ACCEPTCONN		30
 
 #define SO_PEERSEC		31
 
+#define SO_ASYNC_SOCK		34
+
 #endif /* _ASM_SOCKET_H */

index 66f8819..ea914c3 100644
@@ -1269,6 +1269,8 @@ extern struct sk_buff *skb_recv_datagram
 					 int noblock, int *err);
 extern unsigned int    datagram_poll(struct file *file, struct socket *sock,
 				     struct poll_table_struct *wait);
+extern int	       skb_copy_datagram(const struct sk_buff *from, 
+					 int offset, void *dst, int size);
 extern int	       skb_copy_datagram_iovec(const struct sk_buff *from,
 					       int offset, struct iovec *to,
 					       int size);

index d10dfec..7a2bee3 100644
@@ -47,6 +47,7 @@ #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>	/* struct sk_buff */
 #include <linux/security.h>
+#include <linux/kevent.h>
 
 #include <linux/filter.h>
 

@@ -386,6 +387,8 @@ enum sock_flags {
 	SOCK_NO_LARGESEND, /* whether to sent large segments or not */
 	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
 	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
+	SOCK_ASYNC,
+	SOCK_ASYNC_INUSE,
 };
 
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)

@@ -445,6 +448,21 @@ static inline int sk_stream_memory_free(
 
 extern void sk_stream_rfree(struct sk_buff *skb);
 
+struct socket_alloc {
+	struct socket socket;
+	struct inode vfs_inode;
+};
+
+static inline struct socket *SOCKET_I(struct inode *inode)
+{
+	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
+}
+
+static inline struct inode *SOCK_INODE(struct socket *socket)
+{
+	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
+}
+
 static inline void sk_stream_set_owner_r(struct sk_buff *skb, struct sock *sk)
 {
 	skb->sk = sk;

@@ -472,6 +490,7 @@ static inline void sk_add_backlog(struct
 		sk->sk_backlog.tail = skb;
 	}
 	skb->next = NULL;
+	kevent_socket_notify(sk, KEVENT_SOCKET_RECV);
 }
 
 #define sk_wait_event(__sk, __timeo, __condition)		\

@@ -543,6 +562,12 @@ struct proto {
 
 	int			(*backlog_rcv) (struct sock *sk, 
 						struct sk_buff *skb);
+	
+	int			(*async_recv) (struct sock *sk, 
+						void *dst, size_t size);
+	int			(*async_send) (struct sock *sk, 
+						struct page **pages, unsigned int poffset, 
+						size_t size);
 
 	/* Keeping track of sk's, looking them up, and port selection methods. */
 	void			(*hash)(struct sock *sk);

@@ -674,21 +699,6 @@ static inline struct kiocb *siocb_to_kio
 	return si->kiocb;
 }
 
-struct socket_alloc {
-	struct socket socket;
-	struct inode vfs_inode;
-};
-
-static inline struct socket *SOCKET_I(struct inode *inode)
-{
-	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
-}
-
-static inline struct inode *SOCK_INODE(struct socket *socket)
-{
-	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
-}
-
 extern void __sk_stream_mem_reclaim(struct sock *sk);
 extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind);
 

index 5f4eb5c..820cd5a 100644
@@ -364,6 +364,8 @@ extern int			compat_tcp_setsockopt(struc
 					int level, int optname,
 					char __user *optval, int optlen);
 extern void			tcp_set_keepalive(struct sock *sk, int val);
+extern int			tcp_async_recv(struct sock *sk, void *dst, size_t size);
+extern int			tcp_async_send(struct sock *sk, struct page **pages, unsigned int poffset, size_t size);
 extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
 					    struct msghdr *msg,
 					    size_t len, int nonblock, 

@@ -857,6 +859,7 @@ static inline int tcp_prequeue(struct so
 			tp->ucopy.memory = 0;
 		} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
 			wake_up_interruptible(sk->sk_sleep);
+			kevent_socket_notify(sk, KEVENT_SOCKET_RECV|KEVENT_SOCKET_SEND);
 			if (!inet_csk_ack_scheduled(sk))
 				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
 						          (3 * TCP_RTO_MIN) / 4,

239 lines not on this page · raw message

125 lines not on this page · raw message

67 lines not on this page · raw message

index 5d820c3..3345048 100644
@@ -564,6 +564,16 @@ #endif
 			spin_unlock_bh(&sk->sk_lock.slock);
 			ret = -ENONET;
 			break;
+#ifdef CONFIG_KEVENT_SOCKET
+		case SO_ASYNC_SOCK:
+			spin_lock_bh(&sk->sk_lock.slock);
+			if (valbool)
+				sock_set_flag(sk, SOCK_ASYNC);
+			else
+				sock_reset_flag(sk, SOCK_ASYNC);
+			spin_unlock_bh(&sk->sk_lock.slock);
+			break;
+#endif
 
 		/* We implement the SO_SNDLOWAT etc to
 		   not be settable (1003.1g 5.3) */

@@ -1313,6 +1323,7 @@ static void sock_def_wakeup(struct sock 
 	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
 		wake_up_interruptible_all(sk->sk_sleep);
 	read_unlock(&sk->sk_callback_lock);
+	kevent_socket_notify(sk, KEVENT_SOCKET_RECV|KEVENT_SOCKET_SEND);
 }
 
 static void sock_def_error_report(struct sock *sk)

@@ -1322,6 +1333,7 @@ static void sock_def_error_report(struct
 		wake_up_interruptible(sk->sk_sleep);
 	sk_wake_async(sk,0,POLL_ERR); 
 	read_unlock(&sk->sk_callback_lock);
+	kevent_socket_notify(sk, KEVENT_SOCKET_RECV|KEVENT_SOCKET_SEND);
 }
 
 static void sock_def_readable(struct sock *sk, int len)

@@ -1331,6 +1343,7 @@ static void sock_def_readable(struct soc
 		wake_up_interruptible(sk->sk_sleep);
 	sk_wake_async(sk,1,POLL_IN);
 	read_unlock(&sk->sk_callback_lock);
+	kevent_socket_notify(sk, KEVENT_SOCKET_RECV|KEVENT_SOCKET_SEND);
 }
 
 static void sock_def_write_space(struct sock *sk)

@@ -1350,6 +1363,7 @@ static void sock_def_write_space(struct 
 	}
 
 	read_unlock(&sk->sk_callback_lock);
+	kevent_socket_notify(sk, KEVENT_SOCKET_SEND|KEVENT_SOCKET_RECV);
 }
 
 static void sock_def_destruct(struct sock *sk)

@@ -1454,8 +1468,10 @@ void fastcall release_sock(struct sock *
 	if (sk->sk_backlog.tail)
 		__release_sock(sk);
 	sk->sk_lock.owner = NULL;
-        if (waitqueue_active(&(sk->sk_lock.wq)))
+        if (waitqueue_active(&(sk->sk_lock.wq))) {
 		wake_up(&(sk->sk_lock.wq));
+		kevent_socket_notify(sk, KEVENT_SOCKET_RECV|KEVENT_SOCKET_SEND);
+	}
 	spin_unlock_bh(&(sk->sk_lock.slock));
 }
 EXPORT_SYMBOL(release_sock);

index e948969..91e2e07 100644
@@ -36,6 +36,7 @@ void sk_stream_write_space(struct sock *
 			wake_up_interruptible(sk->sk_sleep);
 		if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
 			sock_wake_async(sock, 2, POLL_OUT);
+		kevent_socket_notify(sk, KEVENT_SOCKET_SEND|KEVENT_SOCKET_RECV);
 	}
 }
 

290 lines not on this page · raw message

index e08245b..5655b1e 100644
@@ -3113,6 +3113,7 @@ static void tcp_ofo_queue(struct sock *s
 
 		__skb_unlink(skb, &tp->out_of_order_queue);
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		kevent_socket_notify(sk, KEVENT_SOCKET_RECV);
 		tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
 		if(skb->h.th->fin)
 			tcp_fin(skb, sk, skb->h.th);

@@ -3956,7 +3957,8 @@ int tcp_rcv_established(struct sock *sk,
 			int copied_early = 0;
 
 			if (tp->copied_seq == tp->rcv_nxt &&
-			    len - tcp_header_len <= tp->ucopy.len) {
+			    len - tcp_header_len <= tp->ucopy.len &&
+			    !sock_async(sk)) {
 #ifdef CONFIG_NET_DMA
 				if (tcp_dma_try_early_copy(sk, skb, tcp_header_len)) {
 					copied_early = 1;

index 25ecc6e..05d7086 100644
@@ -62,6 +62,7 @@ #include <linux/cache.h>
 #include <linux/jhash.h>
 #include <linux/init.h>
 #include <linux/times.h>
+#include <linux/kevent.h>
 
 #include <net/icmp.h>
 #include <net/inet_hashtables.h>

@@ -850,6 +851,7 @@ #endif
 	   	reqsk_free(req);
 	} else {
 		inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+		kevent_socket_notify(sk, KEVENT_SOCKET_ACCEPT);
 	}
 	return 0;
 

@@ -1089,24 +1091,30 @@ process:
 
 	skb->dev = NULL;
 
-	bh_lock_sock(sk);
 	ret = 0;
-	if (!sock_owned_by_user(sk)) {
+	if (sock_async(sk)) {
+		spin_lock_bh(&sk->sk_lock.slock);
+		ret = tcp_v4_do_rcv(sk, skb);
+		spin_unlock_bh(&sk->sk_lock.slock);
+	} else {
+		bh_lock_sock(sk);
+		if (!sock_owned_by_user(sk)) {
 #ifdef CONFIG_NET_DMA
-		struct tcp_sock *tp = tcp_sk(sk);
-		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = get_softnet_dma();
-		if (tp->ucopy.dma_chan)
-			ret = tcp_v4_do_rcv(sk, skb);
-		else
+			struct tcp_sock *tp = tcp_sk(sk);
+			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
+				tp->ucopy.dma_chan = get_softnet_dma();
+			if (tp->ucopy.dma_chan)
+				ret = tcp_v4_do_rcv(sk, skb);
+			else
 #endif
-		{
-			if (!tcp_prequeue(sk, skb))
-			ret = tcp_v4_do_rcv(sk, skb);
-		}
-	} else
-		sk_add_backlog(sk, skb);
-	bh_unlock_sock(sk);
+			{
+				if (!tcp_prequeue(sk, skb))
+				ret = tcp_v4_do_rcv(sk, skb);
+			}
+		} else
+			sk_add_backlog(sk, skb);
+		bh_unlock_sock(sk);
+	}
 
 	sock_put(sk);
 

@@ -1830,6 +1838,8 @@ struct proto tcp_prot = {
 	.getsockopt		= tcp_getsockopt,
 	.sendmsg		= tcp_sendmsg,
 	.recvmsg		= tcp_recvmsg,
+	.async_recv		= tcp_async_recv,
+	.async_send		= tcp_async_send,
 	.backlog_rcv		= tcp_v4_do_rcv,
 	.hash			= tcp_v4_hash,
 	.unhash			= tcp_unhash,

index a50eb30..e27e231 100644
@@ -1215,22 +1215,28 @@ process:
 
 	skb->dev = NULL;
 
-	bh_lock_sock(sk);
 	ret = 0;
-	if (!sock_owned_by_user(sk)) {
+	if (sock_async(sk)) {
+		spin_lock_bh(&sk->sk_lock.slock);
+		ret = tcp_v4_do_rcv(sk, skb);
+		spin_unlock_bh(&sk->sk_lock.slock);
+	} else {
+		bh_lock_sock(sk);
+		if (!sock_owned_by_user(sk)) {
 #ifdef CONFIG_NET_DMA
-                struct tcp_sock *tp = tcp_sk(sk);
-                if (tp->ucopy.dma_chan)
-                        ret = tcp_v6_do_rcv(sk, skb);
-                else
-#endif
-		{
-			if (!tcp_prequeue(sk, skb))
+			struct tcp_sock *tp = tcp_sk(sk);
+			if (tp->ucopy.dma_chan)
 				ret = tcp_v6_do_rcv(sk, skb);
-		}
-	} else
-		sk_add_backlog(sk, skb);
-	bh_unlock_sock(sk);
+			else
+#endif
+			{
+				if (!tcp_prequeue(sk, skb))
+					ret = tcp_v6_do_rcv(sk, skb);
+			}
+		} else
+			sk_add_backlog(sk, skb);
+		bh_unlock_sock(sk);
+	}
 
 	sock_put(sk);
 	return ret ? -1 : 0;

@@ -1580,6 +1586,8 @@ struct proto tcpv6_prot = {
 	.getsockopt		= tcp_getsockopt,
 	.sendmsg		= tcp_sendmsg,
 	.recvmsg		= tcp_recvmsg,
+	.async_recv		= tcp_async_recv,
+	.async_send		= tcp_async_send,
 	.backlog_rcv		= tcp_v6_do_rcv,
 	.hash			= tcp_v6_hash,
 	.unhash			= tcp_unhash,