1 files changed, 73 insertions, 79 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 46febcacb729..9bcdec3ad772 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,11 +282,9 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
-EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
@@ -374,7 +372,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	unsigned int mask;
 	struct sock *sk = sock->sk;
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 	if (sk->sk_state == TCP_LISTEN)
@@ -524,11 +522,11 @@ EXPORT_SYMBOL(tcp_ioctl);
 
 static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
 {
-	TCP_SKB_CB(skb)->flags |= TCPHDR_PSH;
+	TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH;
 	tp->pushed_seq = tp->write_seq;
 }
 
-static inline int forced_push(struct tcp_sock *tp)
+static inline int forced_push(const struct tcp_sock *tp)
 {
 	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
 }
@@ -540,7 +538,7 @@ static inline void skb_entail(struct sock *sk, struct sk_buff *skb)
 
 	skb->csum    = 0;
 	tcb->seq     = tcb->end_seq = tp->write_seq;
-	tcb->flags   = TCPHDR_ACK;
+	tcb->tcp_flags = TCPHDR_ACK;
 	tcb->sacked  = 0;
 	skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
@@ -813,7 +811,7 @@ new_segment:
 			goto wait_for_memory;
 
 		if (can_coalesce) {
-			skb_shinfo(skb)->frags[i - 1].size += copy;
+			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 		} else {
 			get_page(page);
 			skb_fill_page_desc(skb, i, page, offset, copy);
@@ -830,7 +828,7 @@ new_segment:
 		skb_shinfo(skb)->gso_segs = 0;
 
 		if (!copied)
-			TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;
+			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
 		copied += copy;
 		poffset += copy;
@@ -888,18 +886,18 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 }
 EXPORT_SYMBOL(tcp_sendpage);
 
-#define TCP_PAGE(sk)	(sk->sk_sndmsg_page)
-#define TCP_OFF(sk)	(sk->sk_sndmsg_off)
-
-static inline int select_size(struct sock *sk, int sg)
+static inline int select_size(const struct sock *sk, bool sg)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	int tmp = tp->mss_cache;
 
 	if (sg) {
-		if (sk_can_gso(sk))
-			tmp = 0;
-		else {
+		if (sk_can_gso(sk)) {
+			/* Small frames wont use a full page:
+			 * Payload will immediately follow tcp header.
+			 */
+			tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+		} else {
 			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
 
 			if (tmp >= pgbreak &&
@@ -917,9 +915,9 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags;
+	int iovlen, flags, err, copied;
 	int mss_now, size_goal;
-	int sg, err, copied;
+	bool sg;
 	long timeo;
 
 	lock_sock(sk);
@@ -946,7 +944,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		goto out_err;
 
-	sg = sk->sk_route_caps & NETIF_F_SG;
+	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
 	while (--iovlen >= 0) {
 		size_t seglen = iov->iov_len;
@@ -1005,8 +1003,13 @@ new_segment:
 			} else {
 				int merge = 0;
 				int i = skb_shinfo(skb)->nr_frags;
-				struct page *page = TCP_PAGE(sk);
-				int off = TCP_OFF(sk);
+				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) {
@@ -1023,7 +1026,7 @@ new_segment:
 				} else if (page) {
 					if (off == PAGE_SIZE) {
 						put_page(page);
-						TCP_PAGE(sk) = page = NULL;
+						sk->sk_sndmsg_page = page = NULL;
 						off = 0;
 					}
 				} else
@@ -1049,32 +1052,31 @@ new_segment:
 					/* If this page was new, give it to the
 					 * socket so it does not get leaked.
 					 */
-					if (!TCP_PAGE(sk)) {
-						TCP_PAGE(sk) = page;
-						TCP_OFF(sk) = 0;
+					if (!sk->sk_sndmsg_page) {
+						sk->sk_sndmsg_page = page;
+						sk->sk_sndmsg_off = 0;
 					}
 					goto do_error;
 				}
 
 				/* Update the skb. */
 				if (merge) {
-					skb_shinfo(skb)->frags[i - 1].size +=
-									copy;
+					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 				} else {
 					skb_fill_page_desc(skb, i, page, off, copy);
-					if (TCP_PAGE(sk)) {
+					if (sk->sk_sndmsg_page) {
 						get_page(page);
 					} else if (off + copy < PAGE_SIZE) {
 						get_page(page);
-						TCP_PAGE(sk) = page;
+						sk->sk_sndmsg_page = page;
 					}
 				}
 
-				TCP_OFF(sk) = off + copy;
+				sk->sk_sndmsg_off = off + copy;
 			}
 
 			if (!copied)
-				TCP_SKB_CB(skb)->flags &= ~TCPHDR_PSH;
+				TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
 			tp->write_seq += copy;
 			TCP_SKB_CB(skb)->end_seq += copy;
@@ -1194,13 +1196,11 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int time_to_ack = 0;
 
-#if TCP_DEBUG
 	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
 
 	WARN(skb && !before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq),
 	     "cleanup rbuf bug: copied %X seq %X rcvnxt %X\n",
 	     tp->copied_seq, TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt);
-#endif
 
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2409,7 +2409,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		   unsigned int optlen)
 {
-	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct inet_connection_sock *icsk = inet_csk(sk);
 
 	if (level != SOL_TCP)
 		return icsk->icsk_af_ops->setsockopt(sk, level, optname,
@@ -2431,9 +2431,9 @@ EXPORT_SYMBOL(compat_tcp_setsockopt);
 #endif
 
 /* Return information about state of tcp endpoint in API format. */
-void tcp_get_info(struct sock *sk, struct tcp_info *info)
+void tcp_get_info(const struct sock *sk, struct tcp_info *info)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
 
@@ -2455,8 +2455,10 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
 	}
 
-	if (tp->ecn_flags&TCP_ECN_OK)
+	if (tp->ecn_flags & TCP_ECN_OK)
 		info->tcpi_options |= TCPI_OPT_ECN;
+	if (tp->ecn_flags & TCP_ECN_SEEN)
+		info->tcpi_options |= TCPI_OPT_ECN_SEEN;
 
 	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
 	info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
@@ -2654,7 +2656,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct tcphdr *th;
@@ -2857,26 +2860,25 @@ EXPORT_SYMBOL(tcp_gro_complete);
 
 #ifdef CONFIG_TCP_MD5SIG
 static unsigned long tcp_md5sig_users;
-static struct tcp_md5sig_pool * __percpu *tcp_md5sig_pool;
+static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool;
 static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
 
-static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool * __percpu *pool)
+static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
 {
 	int cpu;
+
 	for_each_possible_cpu(cpu) {
-		struct tcp_md5sig_pool *p = *per_cpu_ptr(pool, cpu);
-		if (p) {
-			if (p->md5_desc.tfm)
-				crypto_free_hash(p->md5_desc.tfm);
-			kfree(p);
-		}
+		struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu);
+
+		if (p->md5_desc.tfm)
+			crypto_free_hash(p->md5_desc.tfm);
 	}
 	free_percpu(pool);
 }
 
 void tcp_free_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool * __percpu *pool = NULL;
+	struct tcp_md5sig_pool __percpu *pool = NULL;
 
 	spin_lock_bh(&tcp_md5sig_pool_lock);
 	if (--tcp_md5sig_users == 0) {
@@ -2889,30 +2891,24 @@ void tcp_free_md5sig_pool(void)
 }
 EXPORT_SYMBOL(tcp_free_md5sig_pool);
 
-static struct tcp_md5sig_pool * __percpu *
+static struct tcp_md5sig_pool __percpu *
 __tcp_alloc_md5sig_pool(struct sock *sk)
 {
 	int cpu;
-	struct tcp_md5sig_pool * __percpu *pool;
+	struct tcp_md5sig_pool __percpu *pool;
 
-	pool = alloc_percpu(struct tcp_md5sig_pool *);
+	pool = alloc_percpu(struct tcp_md5sig_pool);
 	if (!pool)
 		return NULL;
 
 	for_each_possible_cpu(cpu) {
-		struct tcp_md5sig_pool *p;
 		struct crypto_hash *hash;
 
-		p = kzalloc(sizeof(*p), sk->sk_allocation);
-		if (!p)
-			goto out_free;
-		*per_cpu_ptr(pool, cpu) = p;
-
 		hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
 		if (!hash || IS_ERR(hash))
 			goto out_free;
 
-		p->md5_desc.tfm = hash;
+		per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
 	}
 	return pool;
 out_free:
@@ -2920,9 +2916,9 @@ out_free:
 	return NULL;
 }
 
-struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
+struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
 {
-	struct tcp_md5sig_pool * __percpu *pool;
+	struct tcp_md5sig_pool __percpu *pool;
 	int alloc = 0;
 
 retry:
@@ -2941,7 +2937,7 @@ retry:
 
 	if (alloc) {
 		/* we cannot hold spinlock here because this may sleep. */
-		struct tcp_md5sig_pool * __percpu *p;
+		struct tcp_md5sig_pool __percpu *p;
 
 		p = __tcp_alloc_md5sig_pool(sk);
 		spin_lock_bh(&tcp_md5sig_pool_lock);
@@ -2974,7 +2970,7 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
  */
 struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool * __percpu *p;
+	struct tcp_md5sig_pool __percpu *p;
 
 	local_bh_disable();
 
@@ -2985,7 +2981,7 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 	spin_unlock(&tcp_md5sig_pool_lock);
 
 	if (p)
-		return *this_cpu_ptr(p);
+		return this_cpu_ptr(p);
 
 	local_bh_enable();
 	return NULL;
@@ -3000,23 +2996,25 @@ void tcp_put_md5sig_pool(void)
 EXPORT_SYMBOL(tcp_put_md5sig_pool);
 
 int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
-			struct tcphdr *th)
+			const struct tcphdr *th)
 {
 	struct scatterlist sg;
+	struct tcphdr hdr;
 	int err;
 
-	__sum16 old_checksum = th->check;
-	th->check = 0;
+	/* We are not allowed to change tcphdr, make a local copy */
+	memcpy(&hdr, th, sizeof(hdr));
+	hdr.check = 0;
+
 	/* options aren't included in the hash */
-	sg_init_one(&sg, th, sizeof(struct tcphdr));
-	err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(struct tcphdr));
-	th->check = old_checksum;
+	sg_init_one(&sg, &hdr, sizeof(hdr));
+	err = crypto_hash_update(&hp->md5_desc, &sg, sizeof(hdr));
 	return err;
 }
 EXPORT_SYMBOL(tcp_md5_hash_header);
 
 int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
-			  struct sk_buff *skb, unsigned header_len)
+			  const struct sk_buff *skb, unsigned int header_len)
 {
 	struct scatterlist sg;
 	const struct tcphdr *tp = tcp_hdr(skb);
@@ -3035,8 +3033,9 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 
 	for (i = 0; i < shi->nr_frags; ++i) {
 		const struct skb_frag_struct *f = &shi->frags[i];
-		sg_set_page(&sg, f->page, f->size, f->page_offset);
-		if (crypto_hash_update(desc, &sg, f->size))
+		struct page *page = skb_frag_page(f);
+		sg_set_page(&sg, page, skb_frag_size(f), f->page_offset);
+		if (crypto_hash_update(desc, &sg, skb_frag_size(f)))
 			return 1;
 	}
 
@@ -3048,7 +3047,7 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
 }
 EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
-int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, struct tcp_md5sig_key *key)
+int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
 {
 	struct scatterlist sg;
 
@@ -3277,14 +3276,9 @@ void __init tcp_init(void)
 	sysctl_tcp_max_orphans = cnt / 2;
 	sysctl_max_syn_backlog = max(128, cnt / 256);
 
-	limit = nr_free_buffer_pages() / 8;
-	limit = max(limit, 128UL);
-	sysctl_tcp_mem[0] = limit / 4 * 3;
-	sysctl_tcp_mem[1] = limit;
-	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
-
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
-	limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+	limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
+		<< (PAGE_SHIFT - 7);
 	max_share = min(4UL*1024*1024, limit);
 
 	sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;