6 files changed, 52 insertions, 46 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index b2cf91e4cca..5b919f7b45d 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -407,8 +407,8 @@ config INET_XFRM_MODE_BEET
           If unsure, say Y.
 
 config INET_LRO
-        tristate "Large Receive Offload (ipv4/tcp)"
-
+        bool "Large Receive Offload (ipv4/tcp)"
+        default y
         ---help---
           Support for Large Receive Offload (ipv4/tcp).
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ec0ae490f0b..33c7c85dfe4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -986,9 +986,12 @@ fib_find_node(struct trie *t, u32 key)
 static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
 {
         int wasfull;
-        t_key cindex, key = tn->key;
+        t_key cindex, key;
         struct tnode *tp;
 
+        preempt_disable();
+        key = tn->key;
+
         while (tn != NULL && (tp = node_parent((struct node *)tn)) != NULL) {
                 cindex = tkey_extract_bits(key, tp->pos, tp->bits);
                 wasfull = tnode_full(tp, tnode_get_child(tp, cindex));
@@ -1007,6 +1010,7 @@ static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
         if (IS_TNODE(tn))
                 tn = (struct tnode *)resize(t, (struct tnode *)tn);
 
+        preempt_enable();
         return (struct node *)tn;
 }
 
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 90d22ae0a41..88bf051d0cb 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -139,6 +139,8 @@ __be32 ic_servaddr = NONE;	/* Boot server IP address */
 __be32 root_server_addr = NONE; /* Address of NFS server */
 u8 root_server_path[256] = { 0, };      /* Path to mount as root */
 
+u32 ic_dev_xid;         /* Device under configuration */
+
 /* vendor class identifier */
 static char vendor_class_identifier[253] __initdata;
 
@@ -932,6 +934,13 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str
                 goto drop_unlock;
         }
 
+        /* Is it a reply for the device we are configuring? */
+        if (b->xid != ic_dev_xid) {
+                if (net_ratelimit())
+                        printk(KERN_ERR "DHCP/BOOTP: Ignoring delayed packet \n");
+                goto drop_unlock;
+        }
+
         /* Parse extensions */
         if (ext_len >= 4 &&
             !memcmp(b->exten, ic_bootp_cookie, 4)) { /* Check magic cookie */
@@ -1115,6 +1124,9 @@ static int __init ic_dynamic(void)
         get_random_bytes(&timeout, sizeof(timeout));
         timeout = CONF_BASE_TIMEOUT + (timeout % (unsigned) CONF_TIMEOUT_RANDOM);
         for (;;) {
+                /* Track the device we are configuring */
+                ic_dev_xid = d->xid;
+
 #ifdef IPCONFIG_BOOTP
                 if (do_bootp && (d->able & IC_BOOTP))
                         ic_bootp_send_if(d, jiffies - start_jiffies);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c4c60e9f068..28205e5bfa9 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -784,8 +784,8 @@ static void rt_check_expire(void)
 {
         static unsigned int rover;
         unsigned int i = rover, goal;
-        struct rtable *rth, **rthp;
-        unsigned long length = 0, samples = 0;
+        struct rtable *rth, *aux, **rthp;
+        unsigned long samples = 0;
         unsigned long sum = 0, sum2 = 0;
         u64 mult;
 
@@ -795,9 +795,9 @@ static void rt_check_expire(void)
         goal = (unsigned int)mult;
         if (goal > rt_hash_mask)
                 goal = rt_hash_mask + 1;
-        length = 0;
         for (; goal > 0; goal--) {
                 unsigned long tmo = ip_rt_gc_timeout;
+                unsigned long length;
 
                 i = (i + 1) & rt_hash_mask;
                 rthp = &rt_hash_table[i].chain;
@@ -809,8 +809,10 @@ static void rt_check_expire(void)
 
                 if (*rthp == NULL)
                         continue;
+                length = 0;
                 spin_lock_bh(rt_hash_lock_addr(i));
                 while ((rth = *rthp) != NULL) {
+                        prefetch(rth->u.dst.rt_next);
                         if (rt_is_expired(rth)) {
                                 *rthp = rth->u.dst.rt_next;
                                 rt_free(rth);
@@ -819,33 +821,30 @@ static void rt_check_expire(void)
                         if (rth->u.dst.expires) {
                                 /* Entry is expired even if it is in use */
                                 if (time_before_eq(jiffies, rth->u.dst.expires)) {
+nofree:
                                         tmo >>= 1;
                                         rthp = &rth->u.dst.rt_next;
                                         /*
-                                         * Only bump our length if the hash
-                                         * inputs on entries n and n+1 are not
-                                         * the same, we only count entries on
+                                         * We only count entries on
                                          * a chain with equal hash inputs once
                                          * so that entries for different QOS
                                          * levels, and other non-hash input
                                          * attributes don't unfairly skew
                                          * the length computation
                                          */
-                                        if ((*rthp == NULL) ||
-                                            !compare_hash_inputs(&(*rthp)->fl,
-                                                                 &rth->fl))
-                                                length += ONE;
+                                        for (aux = rt_hash_table[i].chain;;) {
+                                                if (aux == rth) {
+                                                        length += ONE;
+                                                        break;
+                                                }
+                                                if (compare_hash_inputs(&aux->fl, &rth->fl))
+                                                        break;
+                                                aux = aux->u.dst.rt_next;
+                                        }
                                         continue;
                                 }
-                        } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
-                                tmo >>= 1;
-                                rthp = &rth->u.dst.rt_next;
-                                if ((*rthp == NULL) ||
-                                    !compare_hash_inputs(&(*rthp)->fl,
-                                                         &rth->fl))
-                                        length += ONE;
-                                continue;
-                        }
+                        } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+                                goto nofree;
 
                         /* Cleanup aged off entries. */
                         *rthp = rth->u.dst.rt_next;
@@ -1068,7 +1067,6 @@ out:	return 0;
 static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
 {
         struct rtable   *rth, **rthp;
-        struct rtable   *rthi;
         unsigned long   now;
         struct rtable *cand, **candp;
         u32             min_score;
@@ -1088,7 +1086,6 @@ restart:
         }
 
         rthp = &rt_hash_table[hash].chain;
-        rthi = NULL;
 
         spin_lock_bh(rt_hash_lock_addr(hash));
         while ((rth = *rthp) != NULL) {
@@ -1134,17 +1131,6 @@ restart:
                 chain_length++;
 
                 rthp = &rth->u.dst.rt_next;
-
-                /*
-                 * check to see if the next entry in the chain
-                 * contains the same hash input values as rt.  If it does
-                 * This is where we will insert into the list, instead of
-                 * at the head.  This groups entries that differ by aspects not
-                 * relvant to the hash function together, which we use to adjust
-                 * our chain length
-                 */
-                if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl))
-                        rthi = rth;
         }
 
         if (cand) {
@@ -1205,10 +1191,7 @@ restart:
                 }
         }
 
-        if (rthi)
-                rt->u.dst.rt_next = rthi->u.dst.rt_next;
-        else
-                rt->u.dst.rt_next = rt_hash_table[hash].chain;
+        rt->u.dst.rt_next = rt_hash_table[hash].chain;
 
 #if RT_CACHE_DEBUG >= 2
         if (rt->u.dst.rt_next) {
@@ -1224,10 +1207,7 @@ restart:
          * previous writes to rt are comitted to memory
          * before making rt visible to other CPUS.
          */
-        if (rthi)
-                rcu_assign_pointer(rthi->u.dst.rt_next, rt);
-        else
-                rcu_assign_pointer(rt_hash_table[hash].chain, rt);
+        rcu_assign_pointer(rt_hash_table[hash].chain, rt);
 
         spin_unlock_bh(rt_hash_lock_addr(hash));
         *rp = rt;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1d7f49c6f0c..7a0f0b27bf1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1321,6 +1321,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
         struct task_struct *user_recv = NULL;
         int copied_early = 0;
         struct sk_buff *skb;
+        u32 urg_hole = 0;
 
         lock_sock(sk);
 
@@ -1532,7 +1533,8 @@ do_prequeue:
                                 }
                         }
                 }
-                if ((flags & MSG_PEEK) && peek_seq != tp->copied_seq) {
+                if ((flags & MSG_PEEK) &&
+                    (peek_seq - copied - urg_hole != tp->copied_seq)) {
                         if (net_ratelimit())
                                 printk(KERN_DEBUG "TCP(%s:%d): Application bug, race in MSG_PEEK.\n",
                                        current->comm, task_pid_nr(current));
@@ -1553,6 +1555,7 @@ do_prequeue:
                                 if (!urg_offset) {
                                         if (!sock_flag(sk, SOCK_URGINLINE)) {
                                                 ++*seq;
+                                                urg_hole++;
                                                 offset++;
                                                 used--;
                                                 if (!used)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index a453aac91bd..c6743eec9b7 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -158,6 +158,11 @@ void tcp_vegas_cwnd_event(struct sock *sk, enum tcp_ca_event event)
 }
 EXPORT_SYMBOL_GPL(tcp_vegas_cwnd_event);
 
+static inline u32 tcp_vegas_ssthresh(struct tcp_sock *tp)
+{
+        return  min(tp->snd_ssthresh, tp->snd_cwnd-1);
+}
+
 static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 {
         struct tcp_sock *tp = tcp_sk(sk);
@@ -221,11 +226,10 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
                          */
                         diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT;
 
-                        if (diff > gamma && tp->snd_ssthresh > 2 ) {
+                        if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) {
                                 /* Going too fast. Time to slow down
                                  * and switch to congestion avoidance.
                                  */
-                                tp->snd_ssthresh = 2;
 
                                 /* Set cwnd to match the actual rate
                                  * exactly:
@@ -235,6 +239,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
                                  * utilization.
                                  */
                                 tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1);
+                                tp->snd_ssthresh = tcp_vegas_ssthresh(tp);
 
                         } else if (tp->snd_cwnd <= tp->snd_ssthresh) {
                                 /* Slow start.  */
@@ -250,6 +255,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
                                          * we slow down.
                                          */
                                         tp->snd_cwnd--;
+                                        tp->snd_ssthresh
+                                                = tcp_vegas_ssthresh(tp);
                                 } else if (diff < alpha) {
                                         /* We don't have enough extra packets
                                          * in the network, so speed up.