4 files changed, 62 insertions, 114 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a5beab1dc958..24a29a39e9a8 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -793,6 +793,7 @@ static int __ip_append_data(struct sock *sk,
 			    struct flowi4 *fl4,
 			    struct sk_buff_head *queue,
 			    struct inet_cork *cork,
+			    struct page_frag *pfrag,
 			    int getfrag(void *from, char *to, int offset,
 					int len, int odd, struct sk_buff *skb),
 			    void *from, int length, int transhdrlen,
@@ -987,47 +988,30 @@ alloc_new_skb:
 			}
 		} else {
 			int i = skb_shinfo(skb)->nr_frags;
-			skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
-			struct page *page = cork->page;
-			int off = cork->off;
-			unsigned int left;
-
-			if (page && (left = PAGE_SIZE - off) > 0) {
-				if (copy >= left)
-					copy = left;
-				if (page != skb_frag_page(frag)) {
-					if (i == MAX_SKB_FRAGS) {
-						err = -EMSGSIZE;
-						goto error;
-					}
-					skb_fill_page_desc(skb, i, page, off, 0);
-					skb_frag_ref(skb, i);
-					frag = &skb_shinfo(skb)->frags[i];
-				}
-			} else if (i < MAX_SKB_FRAGS) {
-				if (copy > PAGE_SIZE)
-					copy = PAGE_SIZE;
-				page = alloc_pages(sk->sk_allocation, 0);
-				if (page == NULL)  {
-					err = -ENOMEM;
-					goto error;
-				}
-				cork->page = page;
-				cork->off = 0;
 
-				skb_fill_page_desc(skb, i, page, 0, 0);
-				frag = &skb_shinfo(skb)->frags[i];
-			} else {
-				err = -EMSGSIZE;
-				goto error;
-			}
-			if (getfrag(from, skb_frag_address(frag)+skb_frag_size(frag),
-				    offset, copy, skb->len, skb) < 0) {
-				err = -EFAULT;
+			err = -ENOMEM;
+			if (!sk_page_frag_refill(sk, pfrag))
 				goto error;
+
+			if (!skb_can_coalesce(skb, i, pfrag->page,
+					      pfrag->offset)) {
+				err = -EMSGSIZE;
+				if (i == MAX_SKB_FRAGS)
+					goto error;
+
+				__skb_fill_page_desc(skb, i, pfrag->page,
+						     pfrag->offset, 0);
+				skb_shinfo(skb)->nr_frags = ++i;
+				get_page(pfrag->page);
 			}
-			cork->off += copy;
-			skb_frag_size_add(frag, copy);
+			copy = min_t(int, copy, pfrag->size - pfrag->offset);
+			if (getfrag(from,
+				    page_address(pfrag->page) + pfrag->offset,
+				    offset, copy, skb->len, skb) < 0)
+				goto error_efault;
+
+			pfrag->offset += copy;
+			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 			skb->len += copy;
 			skb->data_len += copy;
 			skb->truesize += copy;
@@ -1039,6 +1023,8 @@ alloc_new_skb:
 
 	return 0;
 
+error_efault:
+	err = -EFAULT;
 error:
 	cork->length -= length;
 	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS);
@@ -1079,8 +1065,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->dst = &rt->dst;
 	cork->length = 0;
 	cork->tx_flags = ipc->tx_flags;
-	cork->page = NULL;
-	cork->off = 0;
 
 	return 0;
 }
@@ -1117,7 +1101,8 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4,
 		transhdrlen = 0;
 	}
 
-	return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, getfrag,
+	return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base,
+				sk_page_frag(sk), getfrag,
 				from, length, transhdrlen, flags);
 }
 
@@ -1439,7 +1424,8 @@ struct sk_buff *ip_make_skb(struct sock *sk,
 	if (err)
 		return ERR_PTR(err);
 
-	err = __ip_append_data(sk, fl4, &queue, &cork, getfrag,
+	err = __ip_append_data(sk, fl4, &queue, &cork,
+			       &current->task_frag, getfrag,
 			       from, length, transhdrlen, flags);
 	if (err) {
 		__ip_flush_pending_frames(sk, &queue, &cork);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index f2425785d40a..a80740ba4248 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -131,18 +131,23 @@ found:
  *	0 - deliver
  *	1 - block
  */
-static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
+static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
 {
-	int type;
-
-	if (!pskb_may_pull(skb, sizeof(struct icmphdr)))
+	struct icmphdr _hdr;
+	const struct icmphdr *hdr;
+
+	pr_err("icmp_filter skb_transport_offset %d data-head %ld len %d/%d\n",
+		skb_transport_offset(skb), skb->data - skb->head, skb->len, skb->data_len);
+	hdr = skb_header_pointer(skb, skb_transport_offset(skb),
+				 sizeof(_hdr), &_hdr);
+	pr_err("head %p data %p hdr %p type %d\n", skb->head, skb->data, hdr, hdr ? hdr->type : -1);
+	if (!hdr)
 		return 1;
 
-	type = icmp_hdr(skb)->type;
-	if (type < 32) {
+	if (hdr->type < 32) {
 		__u32 data = raw_sk(sk)->filter.data;
 
-		return ((1 << type) & data) != 0;
+		return ((1U << hdr->type) & data) != 0;
 	}
 
 	/* Do not block unknown ICMP types */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7b1e940393cf..72ea4752f21b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1150,78 +1150,43 @@ new_segment:
 				if (err)
 					goto do_fault;
 			} else {
-				bool merge = false;
+				bool merge = true;
 				int i = skb_shinfo(skb)->nr_frags;
-				struct page *page = sk->sk_sndmsg_page;
-				int off;
-
-				if (page && page_count(page) == 1)
-					sk->sk_sndmsg_off = 0;
-
-				off = sk->sk_sndmsg_off;
-
-				if (skb_can_coalesce(skb, i, page, off) &&
-				    off != PAGE_SIZE) {
-					/* We can extend the last page
-					 * fragment. */
-					merge = true;
-				} else if (i == MAX_SKB_FRAGS || !sg) {
-					/* Need to add new fragment and cannot
-					 * do this because interface is non-SG,
-					 * or because all the page slots are
-					 * busy. */
-					tcp_mark_push(tp, skb);
-					goto new_segment;
-				} else if (page) {
-					if (off == PAGE_SIZE) {
-						put_page(page);
-						sk->sk_sndmsg_page = page = NULL;
-						off = 0;
+				struct page_frag *pfrag = sk_page_frag(sk);
+
+				if (!sk_page_frag_refill(sk, pfrag))
+					goto wait_for_memory;
+
+				if (!skb_can_coalesce(skb, i, pfrag->page,
+						      pfrag->offset)) {
+					if (i == MAX_SKB_FRAGS || !sg) {
+						tcp_mark_push(tp, skb);
+						goto new_segment;
 					}
-				} else
-					off = 0;
+					merge = false;
+				}
 
-				if (copy > PAGE_SIZE - off)
-					copy = PAGE_SIZE - off;
+				copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
 				if (!sk_wmem_schedule(sk, copy))
 					goto wait_for_memory;
 
-				if (!page) {
-					/* Allocate new cache page. */
-					if (!(page = sk_stream_alloc_page(sk)))
-						goto wait_for_memory;
-				}
-
-				/* Time to copy data. We are close to
-				 * the end! */
 				err = skb_copy_to_page_nocache(sk, from, skb,
-							       page, off, copy);
-				if (err) {
-					/* If this page was new, give it to the
-					 * socket so it does not get leaked.
-					 */
-					if (!sk->sk_sndmsg_page) {
-						sk->sk_sndmsg_page = page;
-						sk->sk_sndmsg_off = 0;
-					}
+							       pfrag->page,
+							       pfrag->offset,
+							       copy);
+				if (err)
 					goto do_error;
-				}
 
 				/* Update the skb. */
 				if (merge) {
 					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 				} else {
-					skb_fill_page_desc(skb, i, page, off, copy);
-					if (sk->sk_sndmsg_page) {
-						get_page(page);
-					} else if (off + copy < PAGE_SIZE) {
-						get_page(page);
-						sk->sk_sndmsg_page = page;
-					}
+					skb_fill_page_desc(skb, i, pfrag->page,
+							   pfrag->offset, copy);
+					get_page(pfrag->page);
 				}
-
-				sk->sk_sndmsg_off = off + copy;
+				pfrag->offset += copy;
 			}
 
 			if (!copied)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0a7e020f16b5..93406c583f43 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2200,14 +2200,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
 
-	/*
-	 * If sendmsg cached page exists, toss it.
-	 */
-	if (sk->sk_sndmsg_page) {
-		__free_page(sk->sk_sndmsg_page);
-		sk->sk_sndmsg_page = NULL;
-	}
-
 	/* TCP Cookie Transactions */
 	if (tp->cookie_values != NULL) {
 		kref_put(&tp->cookie_values->kref,