16 files changed, 49 insertions, 39 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 06c08e5740fb..e68103475cca 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -831,7 +831,7 @@ const struct proto_ops inet_stream_ops = {
         .shutdown          = inet_shutdown,
         .setsockopt        = sock_common_setsockopt,
         .getsockopt        = sock_common_getsockopt,
-        .sendmsg           = inet_sendmsg,
+        .sendmsg           = tcp_sendmsg,
         .recvmsg           = sock_common_recvmsg,
         .mmap              = sock_no_mmap,
         .sendpage          = tcp_sendpage,
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c9e2b5e6305e..0f1d7beacf78 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -75,7 +75,6 @@
 #include <net/icmp.h>
 #include <net/checksum.h>
 #include <net/inetpeer.h>
-#include <net/checksum.h>
 #include <linux/igmp.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_bridge.h>
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 342ca8d89458..c5b247077539 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1281,9 +1281,9 @@ static int __init ip_auto_config(void)
          */
         if (ic_myaddr == NONE ||
 #ifdef CONFIG_ROOT_NFS
-            (MAJOR(ROOT_DEV) == UNNAMED_MAJOR
-             && root_server_addr == NONE
-             && ic_servaddr == NONE) ||
+            (root_server_addr == NONE
+             && ic_servaddr == NONE
+             && ROOT_DEV == Root_NFS) ||
 #endif
             ic_first_dev->next) {
 #ifdef IPCONFIG_DYNAMIC
diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c
index e1052bcf4ed1..902fd578aa3c 100644
--- a/net/ipv4/ipvs/ip_vs_ctl.c
+++ b/net/ipv4/ipvs/ip_vs_ctl.c
@@ -29,7 +29,6 @@
 #include <linux/proc_fs.h>
 #include <linux/workqueue.h>
 #include <linux/swap.h>
-#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
 #include <linux/netfilter.h>
@@ -909,7 +908,7 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest)
         write_lock_bh(&__ip_vs_svc_lock);
 
         /* Wait until all other svc users go away */
-        while (atomic_read(&svc->usecnt) > 1) {};
+        IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);
 
         /* call the update_service, because server weight may be changed */
         svc->scheduler->update_service(svc);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index dcc12b183474..69bd362b5fa2 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -19,7 +19,6 @@
 #include <linux/udp.h>
 #include <linux/icmp.h>
 #include <linux/if_arp.h>
-#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
diff --git a/net/ipv4/netfilter/ipt_recent.c b/net/ipv4/netfilter/ipt_recent.c
index 321804315659..6d0c0f7364ad 100644
--- a/net/ipv4/netfilter/ipt_recent.c
+++ b/net/ipv4/netfilter/ipt_recent.c
@@ -387,12 +387,17 @@ static int recent_seq_open(struct inode *inode, struct file *file)
         st = kzalloc(sizeof(*st), GFP_KERNEL);
         if (st == NULL)
                 return -ENOMEM;
+
         ret = seq_open(file, &recent_seq_ops);
-        if (ret)
+        if (ret) {
                 kfree(st);
+                goto out;
+        }
+
         st->table    = pde->data;
         seq          = file->private_data;
         seq->private = st;
+out:
         return ret;
 }
 
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 64552afd01cb..d9b5177989c6 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -509,3 +509,9 @@ static void __exit nf_conntrack_l3proto_ipv4_fini(void)
 
 module_init(nf_conntrack_l3proto_ipv4_init);
 module_exit(nf_conntrack_l3proto_ipv4_fini);
+
+void need_ipv4_conntrack(void)
+{
+        return;
+}
+EXPORT_SYMBOL_GPL(need_ipv4_conntrack);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 27c7918e442a..b3dd5de9a258 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -294,15 +294,14 @@ static int exp_open(struct inode *inode, struct file *file)
         struct ct_expect_iter_state *st;
         int ret;
 
-        st = kmalloc(sizeof(struct ct_expect_iter_state), GFP_KERNEL);
-        if (st == NULL)
+        st = kzalloc(sizeof(struct ct_expect_iter_state), GFP_KERNEL);
+        if (!st)
                 return -ENOMEM;
         ret = seq_open(file, &exp_seq_ops);
         if (ret)
                 goto out_free;
         seq          = file->private_data;
         seq->private = st;
-        memset(st, 0, sizeof(struct ct_expect_iter_state));
         return ret;
 out_free:
         kfree(st);
diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c
index a889ec3ec83a..e14d41976c27 100644
--- a/net/ipv4/netfilter/nf_nat_sip.c
+++ b/net/ipv4/netfilter/nf_nat_sip.c
@@ -104,7 +104,7 @@ static unsigned int ip_nat_sip(struct sk_buff **pskb,
         dataoff = ip_hdrlen(*pskb) + sizeof(struct udphdr);
         datalen = (*pskb)->len - dataoff;
         if (datalen < sizeof("SIP/2.0") - 1)
-                return NF_DROP;
+                return NF_ACCEPT;
 
         addr_map_init(ct, &map);
 
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index 332814dac503..46cc99def165 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -328,7 +328,7 @@ static int __init nf_nat_standalone_init(void)
 {
         int ret = 0;
 
-        need_conntrack();
+        need_ipv4_conntrack();
 
 #ifdef CONFIG_XFRM
         BUG_ON(ip_nat_decode_session != NULL);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 24d7c9f31918..c6d71526f625 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -900,8 +900,9 @@ static int raw_seq_open(struct inode *inode, struct file *file)
 {
         struct seq_file *seq;
         int rc = -ENOMEM;
-        struct raw_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+        struct raw_iter_state *s;
 
+        s = kzalloc(sizeof(*s), GFP_KERNEL);
         if (!s)
                 goto out;
         rc = seq_open(file, &raw_seq_ops);
@@ -910,7 +911,6 @@ static int raw_seq_open(struct inode *inode, struct file *file)
 
         seq = file->private_data;
         seq->private = s;
-        memset(s, 0, sizeof(*s));
 out:
         return rc;
 out_kfree:
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index df42b7fb3268..c7ca94bd152c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -374,8 +374,9 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file)
 {
         struct seq_file *seq;
         int rc = -ENOMEM;
-        struct rt_cache_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);
+        struct rt_cache_iter_state *s;
 
+        s = kzalloc(sizeof(*s), GFP_KERNEL);
         if (!s)
                 goto out;
         rc = seq_open(file, &rt_cache_seq_ops);
@@ -383,7 +384,6 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file)
                 goto out_kfree;
         seq          = file->private_data;
         seq->private = s;
-        memset(s, 0, sizeof(*s));
 out:
         return rc;
 out_kfree:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index da4c0b6ab79a..7e740112b238 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -658,9 +658,10 @@ static inline int select_size(struct sock *sk)
         return tmp;
 }
 
-int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+int tcp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
                 size_t size)
 {
+        struct sock *sk = sock->sk;
         struct iovec *iov;
         struct tcp_sock *tp = tcp_sk(sk);
         struct sk_buff *skb;
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index b66556c0a5bd..5215691f2760 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -79,7 +79,6 @@ static u32 htcp_cwnd_undo(struct sock *sk)
 static inline void measure_rtt(struct sock *sk, u32 srtt)
 {
         const struct inet_connection_sock *icsk = inet_csk(sk);
-        const struct tcp_sock *tp = tcp_sk(sk);
         struct htcp *ca = inet_csk_ca(sk);
 
         /* keep track of minimum RTT seen so far, minRTT is zero at first */
@@ -87,8 +86,7 @@ static inline void measure_rtt(struct sock *sk, u32 srtt)
                 ca->minRTT = srtt;
 
         /* max RTT */
-        if (icsk->icsk_ca_state == TCP_CA_Open
-            && tp->snd_ssthresh < 0xFFFF && htcp_ccount(ca) > 3) {
+        if (icsk->icsk_ca_state == TCP_CA_Open) {
                 if (ca->maxRTT < ca->minRTT)
                         ca->maxRTT = ca->minRTT;
                 if (ca->maxRTT < srtt
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 378ca8a086a3..f030435e0eb4 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -102,11 +102,14 @@ int sysctl_tcp_abc __read_mostly;
 #define FLAG_DATA_LOST          0x80 /* SACK detected data lossage.             */
 #define FLAG_SLOWPATH           0x100 /* Do not skip RFC checks for window update.*/
 #define FLAG_ONLY_ORIG_SACKED   0x200 /* SACKs only non-rexmit sent before RTO */
+#define FLAG_SND_UNA_ADVANCED   0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
+#define FLAG_DSACKING_ACK       0x800 /* SACK blocks contained DSACK info */
 
 #define FLAG_ACKED              (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP            (FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
 #define FLAG_CA_ALERT           (FLAG_DATA_SACKED|FLAG_ECE)
 #define FLAG_FORWARD_PROGRESS   (FLAG_ACKED|FLAG_DATA_SACKED)
+#define FLAG_ANY_PROGRESS       (FLAG_FORWARD_PROGRESS|FLAG_SND_UNA_ADVANCED)
 
 #define IsReno(tp) ((tp)->rx_opt.sack_ok == 0)
 #define IsFack(tp) ((tp)->rx_opt.sack_ok & 2)
@@ -964,12 +967,14 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
 
         /* Check for D-SACK. */
         if (before(ntohl(sp[0].start_seq), TCP_SKB_CB(ack_skb)->ack_seq)) {
+                flag |= FLAG_DSACKING_ACK;
                 found_dup_sack = 1;
                 tp->rx_opt.sack_ok |= 4;
                 NET_INC_STATS_BH(LINUX_MIB_TCPDSACKRECV);
         } else if (num_sacks > 1 &&
                         !after(ntohl(sp[0].end_seq), ntohl(sp[1].end_seq)) &&
                         !before(ntohl(sp[0].start_seq), ntohl(sp[1].start_seq))) {
+                flag |= FLAG_DSACKING_ACK;
                 found_dup_sack = 1;
                 tp->rx_opt.sack_ok |= 4;
                 NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFORECV);
@@ -1856,7 +1861,7 @@ static void tcp_cwnd_down(struct sock *sk, int flag)
         struct tcp_sock *tp = tcp_sk(sk);
         int decr = tp->snd_cwnd_cnt + 1;
 
-        if ((flag&FLAG_FORWARD_PROGRESS) ||
+        if ((flag&(FLAG_ANY_PROGRESS|FLAG_DSACKING_ACK)) ||
             (IsReno(tp) && !(flag&FLAG_NOT_DUP))) {
                 tp->snd_cwnd_cnt = decr&1;
                 decr >>= 1;
@@ -2107,15 +2112,13 @@ static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb)
  * tcp_xmit_retransmit_queue().
  */
 static void
-tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
-                      int prior_packets, int flag)
+tcp_fastretrans_alert(struct sock *sk, int prior_packets, int flag)
 {
         struct inet_connection_sock *icsk = inet_csk(sk);
         struct tcp_sock *tp = tcp_sk(sk);
-        int is_dupack = (tp->snd_una == prior_snd_una &&
-                         (!(flag&FLAG_NOT_DUP) ||
-                          ((flag&FLAG_DATA_SACKED) &&
-                           (tp->fackets_out > tp->reordering))));
+        int is_dupack = !(flag&(FLAG_SND_UNA_ADVANCED|FLAG_NOT_DUP));
+        int do_lost = is_dupack || ((flag&FLAG_DATA_SACKED) &&
+                                    (tp->fackets_out > tp->reordering));
 
         /* Some technical things:
          * 1. Reno does not count dupacks (sacked_out) automatically. */
@@ -2192,14 +2195,14 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
         /* F. Process state. */
         switch (icsk->icsk_ca_state) {
         case TCP_CA_Recovery:
-                if (prior_snd_una == tp->snd_una) {
+                if (!(flag & FLAG_SND_UNA_ADVANCED)) {
                         if (IsReno(tp) && is_dupack)
                                 tcp_add_reno_sack(sk);
                 } else {
                         int acked = prior_packets - tp->packets_out;
                         if (IsReno(tp))
                                 tcp_remove_reno_sacks(sk, acked);
-                        is_dupack = tcp_try_undo_partial(sk, acked);
+                        do_lost = tcp_try_undo_partial(sk, acked);
                 }
                 break;
         case TCP_CA_Loss:
@@ -2215,7 +2218,7 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
                 /* Loss is undone; fall through to processing in Open state. */
         default:
                 if (IsReno(tp)) {
-                        if (tp->snd_una != prior_snd_una)
+                        if (flag & FLAG_SND_UNA_ADVANCED)
                                 tcp_reset_reno_sack(tp);
                         if (is_dupack)
                                 tcp_add_reno_sack(sk);
@@ -2264,7 +2267,7 @@ tcp_fastretrans_alert(struct sock *sk, u32 prior_snd_una,
                 tcp_set_ca_state(sk, TCP_CA_Recovery);
         }
 
-        if (is_dupack || tcp_head_timedout(sk))
+        if (do_lost || tcp_head_timedout(sk))
                 tcp_update_scoreboard(sk);
         tcp_cwnd_down(sk, flag);
         tcp_xmit_retransmit_queue(sk);
@@ -2684,7 +2687,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag)
  *     to prove that the RTO is indeed spurious. It transfers the control
  *     from F-RTO to the conventional RTO recovery
  */
-static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
+static int tcp_process_frto(struct sock *sk, int flag)
 {
         struct tcp_sock *tp = tcp_sk(sk);
 
@@ -2704,8 +2707,7 @@ static int tcp_process_frto(struct sock *sk, u32 prior_snd_una, int flag)
                  * ACK isn't duplicate nor advances window, e.g., opposite dir
                  * data, winupdate
                  */
-                if ((tp->snd_una == prior_snd_una) && (flag&FLAG_NOT_DUP) &&
-                    !(flag&FLAG_FORWARD_PROGRESS))
+                if (!(flag&FLAG_ANY_PROGRESS) && (flag&FLAG_NOT_DUP))
                         return 1;
 
                 if (!(flag&FLAG_DATA_ACKED)) {
@@ -2785,6 +2787,9 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
         if (before(ack, prior_snd_una))
                 goto old_ack;
 
+        if (after(ack, prior_snd_una))
+                flag |= FLAG_SND_UNA_ADVANCED;
+
         if (sysctl_tcp_abc) {
                 if (icsk->icsk_ca_state < TCP_CA_CWR)
                         tp->bytes_acked += ack - prior_snd_una;
@@ -2837,14 +2842,14 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
         flag |= tcp_clean_rtx_queue(sk, &seq_rtt);
 
         if (tp->frto_counter)
-                frto_cwnd = tcp_process_frto(sk, prior_snd_una, flag);
+                frto_cwnd = tcp_process_frto(sk, flag);
 
         if (tcp_ack_is_dubious(sk, flag)) {
                 /* Advance CWND, if state allows this. */
                 if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
                     tcp_may_raise_cwnd(sk, flag))
                         tcp_cong_avoid(sk, ack, prior_in_flight, 0);
-                tcp_fastretrans_alert(sk, prior_snd_una, prior_packets, flag);
+                tcp_fastretrans_alert(sk, prior_packets, flag);
         } else {
                 if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
                         tcp_cong_avoid(sk, ack, prior_in_flight, 1);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3f5f7423b95c..9c94627c8c7e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2425,7 +2425,6 @@ struct proto tcp_prot = {
         .shutdown               = tcp_shutdown,
         .setsockopt             = tcp_setsockopt,
         .getsockopt             = tcp_getsockopt,
-        .sendmsg                = tcp_sendmsg,
         .recvmsg                = tcp_recvmsg,
         .backlog_rcv            = tcp_v4_do_rcv,
         .hash                   = tcp_v4_hash,