[PATCH] POLLRDHUP/EPOLLRDHUP handling for half-closed devices notifications

[linux-2.6-omap-h63xx.git] / net / core / datagram.c

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 1bcfef51ac581562988c54fe9cee885572f819d6..aecddcc304012d48769e9f98b91157aa946cd60d 100644 (file)
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -47,6 +47,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/poll.h>
 #include <linux/highmem.h>
+#include <linux/spinlock.h>
 
 #include <net/protocol.h>
 #include <linux/skbuff.h>
@@ -199,6 +200,41 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
        kfree_skb(skb);
 }
 
+/**
+ *     skb_kill_datagram - Free a datagram skbuff forcibly
+ *     @sk: socket
+ *     @skb: datagram skbuff
+ *     @flags: MSG_ flags
+ *
+ *     This function frees a datagram skbuff that was received by
+ *     skb_recv_datagram.  The flags argument must match the one
+ *     used for skb_recv_datagram.
+ *
+ *     If the MSG_PEEK flag is set, and the packet is still on the
+ *     receive queue of the socket, it will be taken off the queue
+ *     before it is freed.
+ *
+ *     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.
+ */
+
+void skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
+{
+       if (flags & MSG_PEEK) {
+               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);
+               }
+               spin_unlock_bh(&sk->sk_receive_queue.lock);
+       }
+
+       kfree_skb(skb);
+}
+
+EXPORT_SYMBOL(skb_kill_datagram);
+
 /**
  *     skb_copy_datagram_iovec - Copy a datagram to an iovec.
  *     @skb: buffer to copy
@@ -211,49 +247,74 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
 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;
 
-       if (!len)
-               return 0;
+       /* 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;
+       }
 
-next_skb:
-       fraglen = skb_headlen(skb);
-       i = -1;
+       /* Copy paged appendix. Hmm... why does this look so complicated? */
+       for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+               int end;
 
-       while (1) {
-               int start = end;
+               BUG_TRAP(start <= offset + len);
 
-               if ((end += fraglen) > offset) {
-                       int copy = end - offset, o = offset - start;
+               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_toiovec(to, vaddr + frag->page_offset +
+                                            offset - start, copy);
+                       kunmap(page);
                        if (err)
                                goto fault;
                        if (!(len -= copy))
                                return 0;
                        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;
+
+       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) {
+                               if (copy > len)
+                                       copy = len;
+                               if (skb_copy_datagram_iovec(list,
+                                                           offset - start,
+                                                           to, copy))
+                                       goto fault;
+                               if ((len -= copy) == 0)
+                                       return 0;
+                               offset += copy;
+                       }
+                       start = end;
+               }
        }
+       if (!len)
+               return 0;
+
 fault:
        return -EFAULT;
 }
@@ -439,6 +500,8 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
        /* 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;