1 files changed, 36 insertions, 155 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 541f26a67ba2..1bec4e76d88c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -274,7 +274,6 @@
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
-#include <net/netdma.h>
 #include <net/sock.h>
 
 #include <asm/uaccess.h>
@@ -405,7 +404,7 @@ void tcp_init_sock(struct sock *sk)
 
 	tp->reordering = sysctl_tcp_reordering;
 	tcp_enable_early_retrans(tp);
-	icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
 
@@ -609,7 +608,7 @@ static inline bool forced_push(const struct tcp_sock *tp)
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
 
-static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
+static void skb_entail(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
@@ -618,7 +617,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->seq     = tcb->end_seq = tp->write_seq;
 	tcb->tcp_flags = TCPHDR_ACK;
 	tcb->sacked  = 0;
-	skb_header_release(skb);
+	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
 	sk->sk_wmem_queued += skb->truesize;
 	sk_mem_charge(sk, skb->truesize);
@@ -963,7 +962,7 @@ new_segment:
 		skb->ip_summed = CHECKSUM_PARTIAL;
 		tp->write_seq += copy;
 		TCP_SKB_CB(skb)->end_seq += copy;
-		skb_shinfo(skb)->gso_segs = 0;
+		tcp_skb_pcount_set(skb, 0);
 
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
@@ -1261,7 +1260,7 @@ new_segment:
 
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
-			skb_shinfo(skb)->gso_segs = 0;
+			tcp_skb_pcount_set(skb, 0);
 
 			from += copy;
 			copied += copy;
@@ -1394,7 +1393,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-void tcp_cleanup_rbuf(struct sock *sk, int copied)
+static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1470,39 +1469,6 @@ static void tcp_prequeue_process(struct sock *sk)
 	tp->ucopy.memory = 0;
 }
 
-#ifdef CONFIG_NET_DMA
-static void tcp_service_net_dma(struct sock *sk, bool wait)
-{
-	dma_cookie_t done, used;
-	dma_cookie_t last_issued;
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (!tp->ucopy.dma_chan)
-		return;
-
-	last_issued = tp->ucopy.dma_cookie;
-	dma_async_issue_pending(tp->ucopy.dma_chan);
-
-	do {
-		if (dma_async_is_tx_complete(tp->ucopy.dma_chan,
-					      last_issued, &done,
-					      &used) == DMA_COMPLETE) {
-			/* Safe to free early-copied skbs now */
-			__skb_queue_purge(&sk->sk_async_wait_queue);
-			break;
-		} else {
-			struct sk_buff *skb;
-			while ((skb = skb_peek(&sk->sk_async_wait_queue)) &&
-			       (dma_async_is_complete(skb->dma_cookie, done,
-						      used) == DMA_COMPLETE)) {
-				__skb_dequeue(&sk->sk_async_wait_queue);
-				kfree_skb(skb);
-			}
-		}
-	} while (wait);
-}
-#endif
-
 static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 {
 	struct sk_buff *skb;
@@ -1510,9 +1476,9 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 
 	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		offset = seq - TCP_SKB_CB(skb)->seq;
-		if (tcp_hdr(skb)->syn)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 			offset--;
-		if (offset < skb->len || tcp_hdr(skb)->fin) {
+		if (offset < skb->len || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) {
 			*off = offset;
 			return skb;
 		}
@@ -1520,7 +1486,7 @@ static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
 		 * splitted a fat GRO packet, while we released socket lock
 		 * in skb_splice_bits()
 		 */
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 	}
 	return NULL;
 }
@@ -1585,12 +1551,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 			if (offset + 1 != skb->len)
 				continue;
 		}
-		if (tcp_hdr(skb)->fin) {
-			sk_eat_skb(sk, skb, false);
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) {
+			sk_eat_skb(sk, skb);
 			++seq;
 			break;
 		}
-		sk_eat_skb(sk, skb, false);
+		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
 		tp->copied_seq = seq;
@@ -1628,7 +1594,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct task_struct *user_recv = NULL;
-	bool copied_early = false;
 	struct sk_buff *skb;
 	u32 urg_hole = 0;
 
@@ -1674,28 +1639,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
-#ifdef CONFIG_NET_DMA
-	tp->ucopy.dma_chan = NULL;
-	preempt_disable();
-	skb = skb_peek_tail(&sk->sk_receive_queue);
-	{
-		int available = 0;
-
-		if (skb)
-			available = TCP_SKB_CB(skb)->seq + skb->len - (*seq);
-		if ((available < target) &&
-		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
-		    !sysctl_tcp_low_latency &&
-		    net_dma_find_channel()) {
-			preempt_enable();
-			tp->ucopy.pinned_list =
-					dma_pin_iovec_pages(msg->msg_iov, len);
-		} else {
-			preempt_enable();
-		}
-	}
-#endif
-
 	do {
 		u32 offset;
 
@@ -1722,11 +1665,11 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 				break;
 
 			offset = *seq - TCP_SKB_CB(skb)->seq;
-			if (tcp_hdr(skb)->syn)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 				offset--;
 			if (offset < skb->len)
 				goto found_ok_skb;
-			if (tcp_hdr(skb)->fin)
+			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 				goto found_fin_ok;
 			WARN(!(flags & MSG_PEEK),
 			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
@@ -1826,16 +1769,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			/* __ Set realtime policy in scheduler __ */
 		}
 
-#ifdef CONFIG_NET_DMA
-		if (tp->ucopy.dma_chan) {
-			if (tp->rcv_wnd == 0 &&
-			    !skb_queue_empty(&sk->sk_async_wait_queue)) {
-				tcp_service_net_dma(sk, true);
-				tcp_cleanup_rbuf(sk, copied);
-			} else
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-		}
-#endif
 		if (copied >= target) {
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
@@ -1843,11 +1776,6 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		} else
 			sk_wait_data(sk, &timeo);
 
-#ifdef CONFIG_NET_DMA
-		tcp_service_net_dma(sk, false);  /* Don't block */
-		tp->ucopy.wakeup = 0;
-#endif
-
 		if (user_recv) {
 			int chunk;
 
@@ -1905,43 +1833,13 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-#ifdef CONFIG_NET_DMA
-			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-				tp->ucopy.dma_chan = net_dma_find_channel();
-
-			if (tp->ucopy.dma_chan) {
-				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(
-					tp->ucopy.dma_chan, skb, offset,
-					msg->msg_iov, used,
-					tp->ucopy.pinned_list);
-
-				if (tp->ucopy.dma_cookie < 0) {
-
-					pr_alert("%s: dma_cookie < 0\n",
-						 __func__);
-
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
-
-				dma_async_issue_pending(tp->ucopy.dma_chan);
-
-				if ((offset + used) == skb->len)
-					copied_early = true;
-
-			} else
-#endif
-			{
-				err = skb_copy_datagram_iovec(skb, offset,
-						msg->msg_iov, used);
-				if (err) {
-					/* Exception. Bailout! */
-					if (!copied)
-						copied = -EFAULT;
-					break;
-				}
+			err = skb_copy_datagram_iovec(skb, offset,
+						      msg->msg_iov, used);
+			if (err) {
+				/* Exception. Bailout! */
+				if (!copied)
+					copied = -EFAULT;
+				break;
 			}
 		}
 
@@ -1959,21 +1857,17 @@ skip_copy:
 		if (used + offset < skb->len)
 			continue;
 
-		if (tcp_hdr(skb)->fin)
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		continue;
 
 	found_fin_ok:
 		/* Process the FIN. */
 		++*seq;
-		if (!(flags & MSG_PEEK)) {
-			sk_eat_skb(sk, skb, copied_early);
-			copied_early = false;
-		}
+		if (!(flags & MSG_PEEK))
+			sk_eat_skb(sk, skb);
 		break;
 	} while (len > 0);
 
@@ -1996,16 +1890,6 @@ skip_copy:
 		tp->ucopy.len = 0;
 	}
 
-#ifdef CONFIG_NET_DMA
-	tcp_service_net_dma(sk, true);  /* Wait for queue to drain */
-	tp->ucopy.dma_chan = NULL;
-
-	if (tp->ucopy.pinned_list) {
-		dma_unpin_iovec_pages(tp->ucopy.pinned_list);
-		tp->ucopy.pinned_list = NULL;
-	}
-#endif
-
 	/* According to UNIX98, msg_name/msg_namelen are ignored
 	 * on connected socket. I was just happy when found this 8) --ANK
 	 */
@@ -2160,8 +2044,10 @@ void tcp_close(struct sock *sk, long timeout)
 	 *  reader process may not have drained the data yet!
 	 */
 	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
-		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq -
-			  tcp_hdr(skb)->fin;
+		u32 len = TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq;
+
+		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+			len--;
 		data_was_unread += len;
 		__kfree_skb(skb);
 	}
@@ -2349,9 +2235,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	__skb_queue_purge(&sk->sk_receive_queue);
 	tcp_write_queue_purge(sk);
 	__skb_queue_purge(&tp->out_of_order_queue);
-#ifdef CONFIG_NET_DMA
-	__skb_queue_purge(&sk->sk_async_wait_queue);
-#endif
 
 	inet->inet_dport = 0;
 
@@ -2691,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		break;
 #endif
 	case TCP_USER_TIMEOUT:
-		/* Cap the max timeout in ms TCP will retry/retrans
+		/* Cap the max time in ms TCP will retry or probe the window
 		 * before giving up and aborting (ETIMEDOUT) a connection.
 		 */
 		if (val < 0)
@@ -3058,7 +2941,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	local_bh_disable();
 	p = ACCESS_ONCE(tcp_md5sig_pool);
 	if (p)
-		return __this_cpu_ptr(p);
+		return raw_cpu_ptr(p);
 
 	local_bh_enable();
 	return NULL;
@@ -3170,7 +3053,7 @@ static int __init set_thash_entries(char *str)
 }
 __setup("thash_entries=", set_thash_entries);
 
-static void tcp_init_mem(void)
+static void __init tcp_init_mem(void)
 {
 	unsigned long limit = nr_free_buffer_pages() / 8;
 	limit = max(limit, 128UL);
@@ -3188,8 +3071,8 @@ void __init tcp_init(void)
 
 	BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
 
-	percpu_counter_init(&tcp_sockets_allocated, 0);
-	percpu_counter_init(&tcp_orphan_count, 0);
+	percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL);
+	percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL);
 	tcp_hashinfo.bind_bucket_cachep =
 		kmem_cache_create("tcp_bind_bucket",
 				  sizeof(struct inet_bind_bucket), 0,
@@ -3256,8 +3139,6 @@ void __init tcp_init(void)
 		tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
 
 	tcp_metrics_init();
-
-	tcp_register_congestion_control(&tcp_reno);
-
+	BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0);
 	tcp_tasklet_init();
 }