X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fcore%2Fdatagram.c;h=2dccd4ee591b3a755242c05b8889489a380dc8bd;hb=f935aa9e99d6ec74a50871c120e6b21de7256efb;hp=f8d322e1ea9276c3f581fbda2393c829b6fd17f0;hpb=3305b80c214c642b89cd5c21af83bc91ec13f8bd;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/core/datagram.c b/net/core/datagram.c
index f8d322e..2dccd4e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -9,7 +9,7 @@
  *	identical recvmsg() code. So we share it here. The poll was
  *	shared before but buried in udp.c so I moved it.
  *
- *	Authors:	Alan Cox <alan@redhat.com>. (datagram_poll() from old
+ *	Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>. (datagram_poll() from old
  *						     udp.c code)
  *
  *	Fixes:
@@ -48,6 +48,7 @@
 #include <linux/poll.h>
 #include <linux/highmem.h>
 #include <linux/spinlock.h>
+#include <linux/slab.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -55,6 +56,7 @@
 #include <net/checksum.h>
 #include <net/sock.h>
 #include <net/tcp_states.h>
+#include <trace/events/skb.h>
 
 /*
  *	Is a socket 'connection oriented' ?
@@ -64,13 +66,25 @@ static inline int connection_based(struct sock *sk)
 	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
 }
 
+static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync,
+				  void *key)
+{
+	unsigned long bits = (unsigned long)key;
+
+	/*
+	 * Avoid a wakeup if event not interesting for us
+	 */
+	if (bits && !(bits & (POLLIN | POLLERR)))
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
 /*
  * Wait for a packet..
  */
 static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
 {
 	int error;
-	DEFINE_WAIT(wait);
+	DEFINE_WAIT_FUNC(wait, receiver_wake_function);
 
 	prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
 
@@ -115,10 +129,10 @@ out_noerr:
 }
 
 /**
- *	skb_recv_datagram - Receive a datagram skbuff
+ *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
  *	@flags: MSG_ flags
- *	@noblock: blocking operation?
+ *	@peeked: returns non-zero if this packet has been seen before
  *	@err: error code returned
  *
  *	Get a datagram skbuff, understands the peeking, nonblocking wakeups
@@ -143,8 +157,8 @@ out_noerr:
  *	quite explicitly by POSIX 1003.1g, don't change them without having
  *	the standard around please.
  */
-struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
-				  int noblock, int *err)
+struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+				    int *peeked, int *err)
 {
 	struct sk_buff *skb;
 	long timeo;
@@ -156,7 +170,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
 	if (error)
 		goto no_packet;
 
-	timeo = sock_rcvtimeo(sk, noblock);
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	do {
 		/* Again only user level code calls this function, so nothing
@@ -165,18 +179,19 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was corrent in any case. 8)
 		 */
-		if (flags & MSG_PEEK) {
-			unsigned long cpu_flags;
-
-			spin_lock_irqsave(&sk->sk_receive_queue.lock,
-					  cpu_flags);
-			skb = skb_peek(&sk->sk_receive_queue);
-			if (skb)
+		unsigned long cpu_flags;
+
+		spin_lock_irqsave(&sk->sk_receive_queue.lock, cpu_flags);
+		skb = skb_peek(&sk->sk_receive_queue);
+		if (skb) {
+			*peeked = skb->peeked;
+			if (flags & MSG_PEEK) {
+				skb->peeked = 1;
 				atomic_inc(&skb->users);
-			spin_unlock_irqrestore(&sk->sk_receive_queue.lock,
-					       cpu_flags);
-		} else
-			skb = skb_dequeue(&sk->sk_receive_queue);
+			} else
+				__skb_unlink(skb, &sk->sk_receive_queue);
+		}
+		spin_unlock_irqrestore(&sk->sk_receive_queue.lock, cpu_flags);
 
 		if (skb)
 			return skb;
@@ -194,11 +209,31 @@ no_packet:
 	*err = error;
 	return NULL;
 }
+EXPORT_SYMBOL(__skb_recv_datagram);
+
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
+				  int noblock, int *err)
+{
+	int peeked;
+
+	return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+				   &peeked, err);
+}
 
 void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
 {
-	kfree_skb(skb);
+	consume_skb(skb);
+	sk_mem_reclaim_partial(sk);
 }
+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);
+}
+EXPORT_SYMBOL(skb_free_datagram_locked);
 
 /**
  *	skb_kill_datagram - Free a datagram skbuff forcibly
@@ -217,20 +252,30 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
  *	This function currently only disables BH when acquiring the
  *	sk_receive_queue lock.  Therefore it must not be used in a
  *	context where that lock is acquired in an IRQ context.
+ *
+ *	It returns 0 if the packet was removed by us.
  */
 
-void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
+int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 {
+	int err = 0;
+
 	if (flags & MSG_PEEK) {
+		err = -ENOENT;
 		spin_lock_bh(&sk->sk_receive_queue.lock);
 		if (skb == skb_peek(&sk->sk_receive_queue)) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
+			err = 0;
 		}
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
 	}
 
 	kfree_skb(skb);
+	atomic_inc(&sk->sk_drops);
+	sk_mem_reclaim_partial(sk);
+
+	return err;
 }
 
 EXPORT_SYMBOL(skb_kill_datagram);
@@ -247,60 +292,267 @@ EXPORT_SYMBOL(skb_kill_datagram);
 int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
 			    struct iovec *to, int len)
 {
-	int i, err, fraglen, end = 0;
-	struct sk_buff *next = skb_shinfo(skb)->frag_list;
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	trace_skb_copy_datagram_iovec(skb, len);
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_toiovec(to, skb->data + offset, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = frag->page;
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_toiovec(to, vaddr + frag->page_offset +
+					     offset - start, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_iovec(frag_iter,
+						    offset - start,
+						    to, copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+
+/**
+ *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: io vector to copy to
+ *	@to_offset: offset in the io vector to start copying to
+ *	@len: amount of data to copy from buffer to iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is not modified during the copy.
+ */
+int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
+				  const struct iovec *to, int to_offset,
+				  int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		to_offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
 
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = frag->page;
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
+						offset - start, to_offset, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+			to_offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_const_iovec(frag_iter,
+							  offset - start,
+							  to, to_offset,
+							  copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			to_offset += copy;
+		}
+		start = end;
+	}
 	if (!len)
 		return 0;
 
-next_skb:
-	fraglen = skb_headlen(skb);
-	i = -1;
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
 
-	while (1) {
-		int start = end;
+/**
+ *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying to
+ *	@from: io vector to copy to
+ *	@from_offset: offset in the io vector to start copying from
+ *	@len: amount of data to copy to buffer from iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is not modified during the copy.
+ */
+int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
+				 const struct iovec *from, int from_offset,
+				 int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
 
-		if ((end += fraglen) > offset) {
-			int copy = end - offset, o = offset - start;
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_fromiovecend(skb->data + offset, from, from_offset,
+					copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		from_offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_shinfo(skb)->frags[i].size;
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			struct page *page = frag->page;
 
 			if (copy > len)
 				copy = len;
-			if (i == -1)
-				err = memcpy_toiovec(to, skb->data + o, copy);
-			else {
-				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-				struct page *page = frag->page;
-				void *p = kmap(page) + frag->page_offset + o;
-				err = memcpy_toiovec(to, p, copy);
-				kunmap(page);
-			}
+			vaddr = kmap(page);
+			err = memcpy_fromiovecend(vaddr + frag->page_offset +
+						  offset - start,
+						  from, from_offset, copy);
+			kunmap(page);
 			if (err)
 				goto fault;
+
 			if (!(len -= copy))
 				return 0;
 			offset += copy;
+			from_offset += copy;
 		}
-		if (++i >= skb_shinfo(skb)->nr_frags)
-			break;
-		fraglen = skb_shinfo(skb)->frags[i].size;
+		start = end;
 	}
-	if (next) {
-		skb = next;
-		BUG_ON(skb_shinfo(skb)->frag_list);
-		next = skb->next;
-		goto next_skb;
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_from_iovec(frag_iter,
+							 offset - start,
+							 from,
+							 from_offset,
+							 copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			from_offset += copy;
+		}
+		start = end;
 	}
+	if (!len)
+		return 0;
+
 fault:
 	return -EFAULT;
 }
+EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
 
 static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      u8 __user *to, int len,
-				      unsigned int *csump)
+				      __wsum *csump)
 {
 	int start = skb_headlen(skb);
-	int pos = 0;
 	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+	int pos = 0;
 
 	/* Copy header. */
 	if (copy > 0) {
@@ -321,11 +573,11 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
 
-		BUG_TRAP(start <= offset + len);
+		WARN_ON(start > offset + len);
 
 		end = start + skb_shinfo(skb)->frags[i].size;
 		if ((copy = end - offset) > 0) {
-			unsigned int csum2;
+			__wsum csum2;
 			int err = 0;
 			u8  *vaddr;
 			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
@@ -351,33 +603,29 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 		start = end;
 	}
 
-	if (skb_shinfo(skb)->frag_list) {
-		struct sk_buff *list = skb_shinfo(skb)->frag_list;
-
-		for (; list; list=list->next) {
-			int end;
-
-			BUG_TRAP(start <= offset + len);
-
-			end = start + list->len;
-			if ((copy = end - offset) > 0) {
-				unsigned int csum2 = 0;
-				if (copy > len)
-					copy = len;
-				if (skb_copy_and_csum_datagram(list,
-							       offset - start,
-							       to, copy,
-							       &csum2))
-					goto fault;
-				*csump = csum_block_add(*csump, csum2, pos);
-				if ((len -= copy) == 0)
-					return 0;
-				offset += copy;
-				to += copy;
-				pos += copy;
-			}
-			start = end;
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			__wsum csum2 = 0;
+			if (copy > len)
+				copy = len;
+			if (skb_copy_and_csum_datagram(frag_iter,
+						       offset - start,
+						       to, copy,
+						       &csum2))
+				goto fault;
+			*csump = csum_block_add(*csump, csum2, pos);
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			to += copy;
+			pos += copy;
 		}
+		start = end;
 	}
 	if (!len)
 		return 0;
@@ -386,18 +634,24 @@ fault:
 	return -EFAULT;
 }
 
-unsigned int __skb_checksum_complete(struct sk_buff *skb)
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 {
-	unsigned int sum;
+	__sum16 sum;
 
-	sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
+	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
 	if (likely(!sum)) {
-		if (unlikely(skb->ip_summed == CHECKSUM_HW))
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 	return sum;
 }
+EXPORT_SYMBOL(__skb_checksum_complete_head);
+
+__sum16 __skb_checksum_complete(struct sk_buff *skb)
+{
+	return __skb_checksum_complete_head(skb, skb->len);
+}
 EXPORT_SYMBOL(__skb_checksum_complete);
 
 /**
@@ -405,7 +659,7 @@ EXPORT_SYMBOL(__skb_checksum_complete);
  *	@skb: skbuff
  *	@hlen: hardware length
  *	@iov: io vector
- * 
+ *
  *	Caller _must_ check that skb will fit to this iovec.
  *
  *	Returns: 0       - success.
@@ -416,9 +670,12 @@ EXPORT_SYMBOL(__skb_checksum_complete);
 int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
 				     int hlen, struct iovec *iov)
 {
-	unsigned int csum;
+	__wsum csum;
 	int chunk = skb->len - hlen;
 
+	if (!chunk)
+		return 0;
+
 	/* Skip filled elements.
 	 * Pretty silly, look at memcpy_toiovec, though 8)
 	 */
@@ -435,9 +692,9 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
 		if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
 					       chunk, &csum))
 			goto fault;
-		if ((unsigned short)csum_fold(csum))
+		if (csum_fold(csum))
 			goto csum_error;
-		if (unlikely(skb->ip_summed == CHECKSUM_HW))
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
 			netdev_rx_csum_fault(skb->dev);
 		iov->iov_len -= chunk;
 		iov->iov_base += chunk;
@@ -469,12 +726,14 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	unsigned int mask;
 
-	poll_wait(file, sk->sk_sleep, wait);
+	sock_poll_wait(file, sk->sk_sleep, wait);
 	mask = 0;
 
 	/* exceptional events? */
 	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
 		mask |= POLLERR;
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		mask |= POLLRDHUP;
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
 		mask |= POLLHUP;
 
@@ -504,5 +763,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
 EXPORT_SYMBOL(datagram_poll);
 EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
 EXPORT_SYMBOL(skb_copy_datagram_iovec);
-EXPORT_SYMBOL(skb_free_datagram);
 EXPORT_SYMBOL(skb_recv_datagram);