Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index c6f51ad..06fcdb4 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -25,6 +25,7 @@
struct in_ifaddr *ifa_list; /* IP ifaddr chain */
rwlock_t mc_list_lock;
struct ip_mc_list *mc_list; /* IP multicast filter chain */
+ int mc_count; /* Number of installed mcasts */
spinlock_t mc_tomb_lock;
struct ip_mc_list *mc_tomb;
unsigned long mr_v1_seen;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 720b688..2725f4e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -968,6 +968,9 @@
skb_shinfo(skb)->nr_frags = i + 1;
}
+extern void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page,
+ int off, int size);
+
#define SKB_PAGE_ASSERT(skb) BUG_ON(skb_shinfo(skb)->nr_frags)
#define SKB_FRAG_ASSERT(skb) BUG_ON(skb_shinfo(skb)->frag_list)
#define SKB_LINEAR_ASSERT(skb) BUG_ON(skb_is_nonlinear(skb))
@@ -1382,6 +1385,26 @@
return __netdev_alloc_skb(dev, length, GFP_ATOMIC);
}
+extern struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask);
+
+/**
+ * netdev_alloc_page - allocate a page for ps-rx on a specific device
+ * @dev: network device to receive on
+ *
+ * Allocate a new page node local to the specified device.
+ *
+ * %NULL is returned if there is no free memory.
+ */
+static inline struct page *netdev_alloc_page(struct net_device *dev)
+{
+ return __netdev_alloc_page(dev, GFP_ATOMIC);
+}
+
+static inline void netdev_free_page(struct net_device *dev, struct page *page)
+{
+ __free_page(page);
+}
+
/**
* skb_clone_writable - is the header of a clone writable
* @skb: buffer to check
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 7672906..fe77e14 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -312,8 +312,11 @@
u32 retrans_out; /* Retransmitted packets out */
u16 urg_data; /* Saved octet of OOB data and control flags */
- u8 urg_mode; /* In urgent mode */
u8 ecn_flags; /* ECN status bits. */
+ u8 reordering; /* Packet reordering metric. */
+ u32 snd_up; /* Urgent pointer */
+
+ u8 keepalive_probes; /* num of allowed keep alive probes */
/*
* Options received (usually on last packet, some only on SYN packets).
*/
@@ -361,8 +364,6 @@
u32 lost_retrans_low; /* Sent seq after any rxmit (lowest) */
- u8 reordering; /* Packet reordering metric. */
- u8 keepalive_probes; /* num of allowed keep alive probes */
u32 prior_ssthresh; /* ssthresh saved at recovery start */
u32 high_seq; /* snd_nxt at onset of congestion */
@@ -374,8 +375,6 @@
u32 total_retrans; /* Total retransmits for entire connection */
u32 urg_seq; /* Seq of received urgent pointer */
- u32 snd_up; /* Urgent pointer */
-
unsigned int keepalive_time; /* time before keep alive takes place */
unsigned int keepalive_intvl; /* time interval between keep alive probes */
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index e48989f..f74665d 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -91,6 +91,21 @@
return inet6_lookup_listener(net, hashinfo, daddr, hnum, dif);
}
+static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb,
+ const __be16 sport,
+ const __be16 dport)
+{
+ struct sock *sk;
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else return __inet6_lookup(dev_net(skb->dst->dev), hashinfo,
+ &ipv6_hdr(skb)->saddr, sport,
+ &ipv6_hdr(skb)->daddr, ntohs(dport),
+ inet6_iif(skb));
+}
+
extern struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
const struct in6_addr *saddr, const __be16 sport,
const struct in6_addr *daddr, const __be16 dport,
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index bb619d8..5cc182f 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -16,6 +16,7 @@
#include <linux/interrupt.h>
+#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/list.h>
#include <linux/slab.h>
@@ -28,6 +29,7 @@
#include <net/inet_connection_sock.h>
#include <net/inet_sock.h>
#include <net/sock.h>
+#include <net/route.h>
#include <net/tcp_states.h>
#include <net/netns/hash.h>
@@ -371,6 +373,22 @@
return sk;
}
+static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
+ struct sk_buff *skb,
+ const __be16 sport,
+ const __be16 dport)
+{
+ struct sock *sk;
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __inet_lookup(dev_net(skb->dst->dev), hashinfo,
+ iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb));
+}
+
extern int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk, u32 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h
index 4491476..4e58f05 100644
--- a/include/net/netns/mib.h
+++ b/include/net/netns/mib.h
@@ -11,6 +11,12 @@
DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics);
DEFINE_SNMP_STAT(struct icmp_mib, icmp_statistics);
DEFINE_SNMP_STAT(struct icmpmsg_mib, icmpmsg_statistics);
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct proc_dir_entry *proc_net_devsnmp6;
+ DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6);
+ DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6);
+#endif
};
#endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 75a312d..ada50c0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -482,6 +482,11 @@
skb->next = NULL;
}
+static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
+{
+ return sk->sk_backlog_rcv(sk, skb);
+}
+
#define sk_wait_event(__sk, __timeo, __condition) \
({ int __rc; \
release_sock(__sk); \
@@ -1324,6 +1329,18 @@
sock_net_set(sk, hold_net(net));
}
+static inline struct sock *skb_steal_sock(struct sk_buff *skb)
+{
+ if (unlikely(skb->sk)) {
+ struct sock *sk = skb->sk;
+
+ skb->destructor = NULL;
+ skb->sk = NULL;
+ return sk;
+ }
+ return NULL;
+}
+
extern void sock_enable_timestamp(struct sock *sk);
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
extern int sock_get_timestampns(struct sock *, struct timespec __user *);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f6cc341..438014d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -896,7 +896,7 @@
BUG_ON(sock_owned_by_user(sk));
while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
- sk->sk_backlog_rcv(sk, skb1);
+ sk_backlog_rcv(sk, skb1);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED);
}
diff --git a/include/net/udp.h b/include/net/udp.h
index d38f6f2..1e20509 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -152,11 +152,6 @@
__be32 daddr, __be16 dport,
int dif);
-DECLARE_SNMP_STAT(struct udp_mib, udp_stats_in6);
-
-/* UDP-Lite does not have a standardized MIB yet, so we inherit from UDP */
-DECLARE_SNMP_STAT(struct udp_mib, udplite_stats_in6);
-
/*
* SNMP statistics for UDP and UDP-Lite
*/
@@ -167,12 +162,14 @@
if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_statistics, field); \
else SNMP_INC_STATS_BH((net)->mib.udp_statistics, field); } while(0)
-#define UDP6_INC_STATS_BH(net, field, is_udplite) do { (void)net; \
- if (is_udplite) SNMP_INC_STATS_BH(udplite_stats_in6, field); \
- else SNMP_INC_STATS_BH(udp_stats_in6, field); } while(0)
-#define UDP6_INC_STATS_USER(net, field, is_udplite) do { (void)net; \
- if (is_udplite) SNMP_INC_STATS_USER(udplite_stats_in6, field); \
- else SNMP_INC_STATS_USER(udp_stats_in6, field); } while(0)
+#define UDP6_INC_STATS_BH(net, field, is_udplite) do { \
+ if (is_udplite) SNMP_INC_STATS_BH((net)->mib.udplite_stats_in6, field);\
+ else SNMP_INC_STATS_BH((net)->mib.udp_stats_in6, field); \
+} while(0)
+#define UDP6_INC_STATS_USER(net, field, __lite) do { \
+ if (__lite) SNMP_INC_STATS_USER((net)->mib.udplite_stats_in6, field); \
+ else SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field); \
+} while(0)
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define UDPX_INC_STATS_BH(sk, field) \
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8bd248a..7f7bb1a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -263,6 +263,26 @@
return skb;
}
+struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
+{
+ int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
+ struct page *page;
+
+ page = alloc_pages_node(node, gfp_mask, 0);
+ return page;
+}
+EXPORT_SYMBOL(__netdev_alloc_page);
+
+void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
+ int size)
+{
+ skb_fill_page_desc(skb, i, page, off, size);
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += size;
+}
+EXPORT_SYMBOL(skb_add_rx_frag);
+
/**
* dev_alloc_skb - allocate an skbuff for receiving
* @length: length to allocate
diff --git a/net/core/sock.c b/net/core/sock.c
index 2d358dd..5e2a313 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -327,7 +327,7 @@
*/
mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);
- rc = sk->sk_backlog_rcv(sk, skb);
+ rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
} else
@@ -1374,7 +1374,7 @@
struct sk_buff *next = skb->next;
skb->next = NULL;
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
/*
* We are in process context here with softirqs
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 882c5c4..e3dfdda 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -811,9 +811,8 @@
/* Step 2:
* Look up flow ID in table and get corresponding socket */
- sk = __inet_lookup(dev_net(skb->dst->dev), &dccp_hashinfo,
- iph->saddr, dh->dccph_sport,
- iph->daddr, dh->dccph_dport, inet_iif(skb));
+ sk = __inet_lookup_skb(&dccp_hashinfo, skb,
+ dh->dccph_sport, dh->dccph_dport);
/*
* Step 2:
* If no socket ...
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 5e1ee0d..caa7f34 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -805,10 +805,8 @@
/* Step 2:
* Look up flow ID in table and get corresponding socket */
- sk = __inet6_lookup(dev_net(skb->dst->dev), &dccp_hashinfo,
- &ipv6_hdr(skb)->saddr, dh->dccph_sport,
- &ipv6_hdr(skb)->daddr, ntohs(dh->dccph_dport),
- inet6_iif(skb));
+ sk = __inet6_lookup_skb(&dccp_hashinfo, skb,
+ dh->dccph_sport, dh->dccph_dport);
/*
* Step 2:
* If no socket ...
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index f70fac6..7f9e337 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1234,6 +1234,7 @@
write_lock_bh(&in_dev->mc_list_lock);
im->next=in_dev->mc_list;
in_dev->mc_list=im;
+ in_dev->mc_count++;
write_unlock_bh(&in_dev->mc_list_lock);
#ifdef CONFIG_IP_MULTICAST
igmpv3_del_delrec(in_dev, im->multiaddr);
@@ -1282,6 +1283,7 @@
if (--i->users == 0) {
write_lock_bh(&in_dev->mc_list_lock);
*ip = i->next;
+ in_dev->mc_count--;
write_unlock_bh(&in_dev->mc_list_lock);
igmp_group_dropped(i);
@@ -1330,6 +1332,7 @@
setup_timer(&in_dev->mr_gq_timer, igmp_gq_timer_expire,
(unsigned long)in_dev);
in_dev->mr_ifc_count = 0;
+ in_dev->mc_count = 0;
setup_timer(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire,
(unsigned long)in_dev);
in_dev->mr_qrv = IGMP_Unsolicited_Report_Count;
@@ -1369,8 +1372,8 @@
write_lock_bh(&in_dev->mc_list_lock);
while ((i = in_dev->mc_list) != NULL) {
in_dev->mc_list = i->next;
+ in_dev->mc_count--;
write_unlock_bh(&in_dev->mc_list_lock);
-
igmp_group_dropped(i);
ip_ma_put(i);
@@ -2383,7 +2386,7 @@
if (state->in_dev->mc_list == im) {
seq_printf(seq, "%d\t%-10s: %5d %7s\n",
- state->dev->ifindex, state->dev->name, state->dev->mc_count, querier);
+ state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier);
}
seq_printf(seq,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7d81a1e..eccb716 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -497,10 +497,8 @@
static inline void tcp_mark_urg(struct tcp_sock *tp, int flags,
struct sk_buff *skb)
{
- if (flags & MSG_OOB) {
- tp->urg_mode = 1;
+ if (flags & MSG_OOB)
tp->snd_up = tp->write_seq;
- }
}
static inline void tcp_push(struct sock *sk, int flags, int mss_now,
@@ -1161,7 +1159,7 @@
* necessary */
local_bh_disable();
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
local_bh_enable();
/* Clear memory counter. */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3b76bce..63da393 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2836,7 +2836,8 @@
* is before the ack sequence we can discard it as it's confirmed to have
* arrived at the other end.
*/
-static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets)
+static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
+ u32 prior_snd_una)
{
struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2903,9 +2904,6 @@
if (sacked & TCPCB_LOST)
tp->lost_out -= acked_pcount;
- if (unlikely(tp->urg_mode && !before(end_seq, tp->snd_up)))
- tp->urg_mode = 0;
-
tp->packets_out -= acked_pcount;
pkts_acked += acked_pcount;
@@ -2935,6 +2933,9 @@
tp->lost_skb_hint = NULL;
}
+ if (likely(between(tp->snd_up, prior_snd_una, tp->snd_una)))
+ tp->snd_up = tp->snd_una;
+
if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
flag |= FLAG_SACK_RENEGING;
@@ -3311,7 +3312,7 @@
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- flag |= tcp_clean_rtx_queue(sk, prior_fackets);
+ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
if (tp->frto_counter)
frto_cwnd = tcp_process_frto(sk, flag);
@@ -4460,8 +4461,8 @@
if (tcp_should_expand_sndbuf(sk)) {
int sndmem = max_t(u32, tp->rx_opt.mss_clamp, tp->mss_cache) +
- MAX_TCP_HEADER + 16 + sizeof(struct sk_buff),
- demanded = max_t(unsigned int, tp->snd_cwnd,
+ MAX_TCP_HEADER + 16 + sizeof(struct sk_buff);
+ int demanded = max_t(unsigned int, tp->snd_cwnd,
tp->reordering + 1);
sndmem *= 2 * demanded;
if (sndmem > sk->sk_sndbuf)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8b24bd8..24ffc5e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1577,8 +1577,7 @@
TCP_SKB_CB(skb)->flags = iph->tos;
TCP_SKB_CB(skb)->sacked = 0;
- sk = __inet_lookup(net, &tcp_hashinfo, iph->saddr,
- th->source, iph->daddr, th->dest, inet_iif(skb));
+ sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
if (!sk)
goto no_tcp_socket;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f976fc5..779f2e9 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -395,6 +395,7 @@
newtp->pred_flags = 0;
newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
+ newtp->snd_up = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 493553c..990a584 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -345,6 +345,11 @@
TCP_SKB_CB(skb)->end_seq = seq;
}
+static inline int tcp_urg_mode(const struct tcp_sock *tp)
+{
+ return tp->snd_una != tp->snd_up;
+}
+
#define OPTION_SACK_ADVERTISE (1 << 0)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
@@ -646,7 +651,8 @@
th->check = 0;
th->urg_ptr = 0;
- if (unlikely(tp->urg_mode &&
+ /* The urg_mode check is necessary during a below snd_una win probe */
+ if (unlikely(tcp_urg_mode(tp) &&
between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) {
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
@@ -1012,7 +1018,7 @@
/* Compute the current effective MSS, taking SACKs and IP options,
* and even PMTU discovery events into account.
*
- * LARGESEND note: !urg_mode is overkill, only frames up to snd_up
+ * LARGESEND note: !tcp_urg_mode is overkill, only frames up to snd_up
* cannot be large. However, taking into account rare use of URG, this
* is not a big flaw.
*/
@@ -1029,7 +1035,7 @@
mss_now = tp->mss_cache;
- if (large_allowed && sk_can_gso(sk) && !tp->urg_mode)
+ if (large_allowed && sk_can_gso(sk) && !tcp_urg_mode(tp))
doing_tso = 1;
if (dst) {
@@ -1193,7 +1199,7 @@
/* Don't use the nagle rule for urgent data (or for the final FIN).
* Nagle can be ignored during F-RTO too (see RFC4138).
*/
- if (tp->urg_mode || (tp->frto_counter == 2) ||
+ if (tcp_urg_mode(tp) || (tp->frto_counter == 2) ||
(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN))
return 1;
@@ -2358,6 +2364,7 @@
tcp_init_wl(tp, tp->write_seq, 0);
tp->snd_una = tp->write_seq;
tp->snd_sml = tp->write_seq;
+ tp->snd_up = tp->write_seq;
tp->rcv_nxt = 0;
tp->rcv_wup = 0;
tp->copied_seq = 0;
@@ -2567,8 +2574,7 @@
tcp_event_new_data_sent(sk, skb);
return err;
} else {
- if (tp->urg_mode &&
- between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
+ if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF))
tcp_xmit_probe_skb(sk, 1);
return tcp_xmit_probe_skb(sk, 0);
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 5ab6ba1..6b6dff1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -201,7 +201,7 @@
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);
while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
- sk->sk_backlog_rcv(sk, skb);
+ sk_backlog_rcv(sk, skb);
tp->ucopy.memory = 0;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c83d0ef..85f8e8e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -108,9 +108,6 @@
* Snmp MIB for the UDP layer
*/
-DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
-EXPORT_SYMBOL(udp_stats_in6);
-
struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);
@@ -302,6 +299,21 @@
return result;
}
+static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
+ __be16 sport, __be16 dport,
+ struct hlist_head udptable[])
+{
+ struct sock *sk;
+ const struct iphdr *iph = ip_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __udp4_lib_lookup(dev_net(skb->dst->dev), iph->saddr, sport,
+ iph->daddr, dport, inet_iif(skb),
+ udptable);
+}
+
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
@@ -1208,8 +1220,7 @@
return __udp4_lib_mcast_deliver(net, skb, uh,
saddr, daddr, udptable);
- sk = __udp4_lib_lookup(net, saddr, uh->source, daddr,
- uh->dest, inet_iif(skb), udptable);
+ sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk != NULL) {
int ret = udp_queue_rcv_skb(sk, skb);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f018704..127b240 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -806,17 +806,8 @@
if (snmp_mib_init((void **)icmpv6msg_statistics,
sizeof(struct icmpv6msg_mib)) < 0)
goto err_icmpmsg_mib;
- if (snmp_mib_init((void **)udp_stats_in6, sizeof (struct udp_mib)) < 0)
- goto err_udp_mib;
- if (snmp_mib_init((void **)udplite_stats_in6,
- sizeof (struct udp_mib)) < 0)
- goto err_udplite_mib;
return 0;
-err_udplite_mib:
- snmp_mib_free((void **)udp_stats_in6);
-err_udp_mib:
- snmp_mib_free((void **)icmpv6msg_statistics);
err_icmpmsg_mib:
snmp_mib_free((void **)icmpv6_statistics);
err_icmp_mib:
@@ -831,8 +822,27 @@
snmp_mib_free((void **)ipv6_statistics);
snmp_mib_free((void **)icmpv6_statistics);
snmp_mib_free((void **)icmpv6msg_statistics);
- snmp_mib_free((void **)udp_stats_in6);
- snmp_mib_free((void **)udplite_stats_in6);
+}
+
+static int __net_init ipv6_init_mibs(struct net *net)
+{
+ if (snmp_mib_init((void **)net->mib.udp_stats_in6,
+ sizeof (struct udp_mib)) < 0)
+ return -ENOMEM;
+ if (snmp_mib_init((void **)net->mib.udplite_stats_in6,
+ sizeof (struct udp_mib)) < 0)
+ goto err_udplite_mib;
+ return 0;
+
+err_udplite_mib:
+ snmp_mib_free((void **)net->mib.udp_stats_in6);
+ return -ENOMEM;
+}
+
+static void __net_exit ipv6_cleanup_mibs(struct net *net)
+{
+ snmp_mib_free((void **)net->mib.udp_stats_in6);
+ snmp_mib_free((void **)net->mib.udplite_stats_in6);
}
static int inet6_net_init(struct net *net)
@@ -840,16 +850,11 @@
int err = 0;
net->ipv6.sysctl.bindv6only = 0;
- net->ipv6.sysctl.flush_delay = 0;
- net->ipv6.sysctl.ip6_rt_max_size = 4096;
- net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
- net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
- net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
- net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
- net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
- net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
net->ipv6.sysctl.icmpv6_time = 1*HZ;
+ err = ipv6_init_mibs(net);
+ if (err)
+ return err;
#ifdef CONFIG_PROC_FS
err = udp6_proc_init(net);
if (err)
@@ -860,7 +865,6 @@
err = ac6_proc_init(net);
if (err)
goto proc_ac6_fail;
-out:
#endif
return err;
@@ -869,7 +873,9 @@
tcp6_proc_exit(net);
proc_tcp6_fail:
udp6_proc_exit(net);
- goto out;
+out:
+ ipv6_cleanup_mibs(net);
+ return err;
#endif
}
@@ -880,6 +886,7 @@
tcp6_proc_exit(net);
ac6_proc_exit(net);
#endif
+ ipv6_cleanup_mibs(net);
}
static struct pernet_operations inet6_net_ops = {
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 0179b66..c78cf754 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -29,8 +29,6 @@
#include <net/transp_v6.h>
#include <net/ipv6.h>
-static struct proc_dir_entry *proc_net_devsnmp6;
-
static int sockstat6_seq_show(struct seq_file *seq, void *v)
{
struct net *net = seq->private;
@@ -48,6 +46,19 @@
return 0;
}
+static int sockstat6_seq_open(struct inode *inode, struct file *file)
+{
+ return single_open_net(inode, file, sockstat6_seq_show);
+}
+
+static const struct file_operations sockstat6_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = sockstat6_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release_net,
+};
+
static struct snmp_mib snmp6_ipstats_list[] = {
/* ipv6 mib according to RFC 2465 */
SNMP_MIB_ITEM("Ip6InReceives", IPSTATS_MIB_INRECEIVES),
@@ -164,39 +175,21 @@
static int snmp6_seq_show(struct seq_file *seq, void *v)
{
- struct inet6_dev *idev = (struct inet6_dev *)seq->private;
+ struct net *net = (struct net *)seq->private;
- if (idev) {
- seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
- snmp6_seq_show_item(seq, (void **)idev->stats.ipv6, snmp6_ipstats_list);
- snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq, (void **)idev->stats.icmpv6msg);
- } else {
- snmp6_seq_show_item(seq, (void **)ipv6_statistics, snmp6_ipstats_list);
- snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list);
- snmp6_seq_show_icmpv6msg(seq, (void **)icmpv6msg_statistics);
- snmp6_seq_show_item(seq, (void **)udp_stats_in6, snmp6_udp6_list);
- snmp6_seq_show_item(seq, (void **)udplite_stats_in6, snmp6_udplite6_list);
- }
+ snmp6_seq_show_item(seq, (void **)ipv6_statistics, snmp6_ipstats_list);
+ snmp6_seq_show_item(seq, (void **)icmpv6_statistics, snmp6_icmp6_list);
+ snmp6_seq_show_icmpv6msg(seq, (void **)icmpv6msg_statistics);
+ snmp6_seq_show_item(seq, (void **)net->mib.udp_stats_in6,
+ snmp6_udp6_list);
+ snmp6_seq_show_item(seq, (void **)net->mib.udplite_stats_in6,
+ snmp6_udplite6_list);
return 0;
}
-static int sockstat6_seq_open(struct inode *inode, struct file *file)
-{
- return single_open_net(inode, file, sockstat6_seq_show);
-}
-
-static const struct file_operations sockstat6_seq_fops = {
- .owner = THIS_MODULE,
- .open = sockstat6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release_net,
-};
-
static int snmp6_seq_open(struct inode *inode, struct file *file)
{
- return single_open(file, snmp6_seq_show, PDE(inode)->data);
+ return single_open_net(inode, file, snmp6_seq_show);
}
static const struct file_operations snmp6_seq_fops = {
@@ -204,24 +197,48 @@
.open = snmp6_seq_open,
.read = seq_read,
.llseek = seq_lseek,
+ .release = single_release_net,
+};
+
+static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
+{
+ struct inet6_dev *idev = (struct inet6_dev *)seq->private;
+
+ seq_printf(seq, "%-32s\t%u\n", "ifIndex", idev->dev->ifindex);
+ snmp6_seq_show_item(seq, (void **)idev->stats.ipv6, snmp6_ipstats_list);
+ snmp6_seq_show_item(seq, (void **)idev->stats.icmpv6, snmp6_icmp6_list);
+ snmp6_seq_show_icmpv6msg(seq, (void **)idev->stats.icmpv6msg);
+ return 0;
+}
+
+static int snmp6_dev_seq_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, snmp6_dev_seq_show, PDE(inode)->data);
+}
+
+static const struct file_operations snmp6_dev_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = snmp6_dev_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
.release = single_release,
};
int snmp6_register_dev(struct inet6_dev *idev)
{
struct proc_dir_entry *p;
+ struct net *net;
if (!idev || !idev->dev)
return -EINVAL;
- if (!net_eq(dev_net(idev->dev), &init_net))
- return 0;
-
- if (!proc_net_devsnmp6)
+ net = dev_net(idev->dev);
+ if (!net->mib.proc_net_devsnmp6)
return -ENOENT;
p = proc_create_data(idev->dev->name, S_IRUGO,
- proc_net_devsnmp6, &snmp6_seq_fops, idev);
+ net->mib.proc_net_devsnmp6,
+ &snmp6_dev_seq_fops, idev);
if (!p)
return -ENOMEM;
@@ -231,12 +248,13 @@
int snmp6_unregister_dev(struct inet6_dev *idev)
{
- if (!proc_net_devsnmp6)
+ struct net *net = dev_net(idev->dev);
+ if (!net->mib.proc_net_devsnmp6)
return -ENOENT;
if (!idev || !idev->stats.proc_dir_entry)
return -EINVAL;
remove_proc_entry(idev->stats.proc_dir_entry->name,
- proc_net_devsnmp6);
+ net->mib.proc_net_devsnmp6);
idev->stats.proc_dir_entry = NULL;
return 0;
}
@@ -246,12 +264,27 @@
if (!proc_net_fops_create(net, "sockstat6", S_IRUGO,
&sockstat6_seq_fops))
return -ENOMEM;
+
+ if (!proc_net_fops_create(net, "snmp6", S_IRUGO, &snmp6_seq_fops))
+ goto proc_snmp6_fail;
+
+ net->mib.proc_net_devsnmp6 = proc_mkdir("dev_snmp6", net->proc_net);
+ if (!net->mib.proc_net_devsnmp6)
+ goto proc_dev_snmp6_fail;
return 0;
+
+proc_snmp6_fail:
+ proc_net_remove(net, "sockstat6");
+proc_dev_snmp6_fail:
+ proc_net_remove(net, "dev_snmp6");
+ return -ENOMEM;
}
static void ipv6_proc_exit_net(struct net *net)
{
proc_net_remove(net, "sockstat6");
+ proc_net_remove(net, "dev_snmp6");
+ proc_net_remove(net, "snmp6");
}
static struct pernet_operations ipv6_proc_ops = {
@@ -261,33 +294,11 @@
int __init ipv6_misc_proc_init(void)
{
- int rc = 0;
-
- if (register_pernet_subsys(&ipv6_proc_ops))
- goto proc_net_fail;
-
- if (!proc_net_fops_create(&init_net, "snmp6", S_IRUGO, &snmp6_seq_fops))
- goto proc_snmp6_fail;
-
- proc_net_devsnmp6 = proc_mkdir("dev_snmp6", init_net.proc_net);
- if (!proc_net_devsnmp6)
- goto proc_dev_snmp6_fail;
-out:
- return rc;
-
-proc_dev_snmp6_fail:
- proc_net_remove(&init_net, "snmp6");
-proc_snmp6_fail:
- unregister_pernet_subsys(&ipv6_proc_ops);
-proc_net_fail:
- rc = -ENOMEM;
- goto out;
+ return register_pernet_subsys(&ipv6_proc_ops);
}
void ipv6_misc_proc_exit(void)
{
- proc_net_remove(&init_net, "dev_snmp6");
- proc_net_remove(&init_net, "snmp6");
unregister_pernet_subsys(&ipv6_proc_ops);
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f4385a6..e10a170 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2631,10 +2631,8 @@
net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
sizeof(*net->ipv6.ip6_prohibit_entry),
GFP_KERNEL);
- if (!net->ipv6.ip6_prohibit_entry) {
- kfree(net->ipv6.ip6_null_entry);
- goto out;
- }
+ if (!net->ipv6.ip6_prohibit_entry)
+ goto out_ip6_null_entry;
net->ipv6.ip6_prohibit_entry->u.dst.path =
(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
net->ipv6.ip6_prohibit_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
@@ -2642,16 +2640,22 @@
net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
sizeof(*net->ipv6.ip6_blk_hole_entry),
GFP_KERNEL);
- if (!net->ipv6.ip6_blk_hole_entry) {
- kfree(net->ipv6.ip6_null_entry);
- kfree(net->ipv6.ip6_prohibit_entry);
- goto out;
- }
+ if (!net->ipv6.ip6_blk_hole_entry)
+ goto out_ip6_prohibit_entry;
net->ipv6.ip6_blk_hole_entry->u.dst.path =
(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
net->ipv6.ip6_blk_hole_entry->u.dst.ops = net->ipv6.ip6_dst_ops;
#endif
+ net->ipv6.sysctl.flush_delay = 0;
+ net->ipv6.sysctl.ip6_rt_max_size = 4096;
+ net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
+ net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
+ net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
+ net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
+ net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
+ net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;
+
#ifdef CONFIG_PROC_FS
proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
@@ -2662,6 +2666,12 @@
out:
return ret;
+#ifdef CONFIG_IPV6_MULTIPLE_TABLES
+out_ip6_prohibit_entry:
+ kfree(net->ipv6.ip6_prohibit_entry);
+out_ip6_null_entry:
+ kfree(net->ipv6.ip6_null_entry);
+#endif
out_ip6_dst_ops:
release_net(net->ipv6.ip6_dst_ops->dst_net);
kfree(net->ipv6.ip6_dst_ops);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index df16b68..6268d26 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1681,11 +1681,7 @@
TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb));
TCP_SKB_CB(skb)->sacked = 0;
- sk = __inet6_lookup(net, &tcp_hashinfo,
- &ipv6_hdr(skb)->saddr, th->source,
- &ipv6_hdr(skb)->daddr, ntohs(th->dest),
- inet6_iif(skb));
-
+ sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
if (!sk)
goto no_tcp_socket;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index a6aecf7..e51da8c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -107,6 +107,21 @@
return result;
}
+static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
+ __be16 sport, __be16 dport,
+ struct hlist_head udptable[])
+{
+ struct sock *sk;
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __udp6_lib_lookup(dev_net(skb->dst->dev), &iph->saddr, sport,
+ &iph->daddr, dport, inet6_iif(skb),
+ udptable);
+}
+
/*
* This should be easy, if there is something there we
* return it, otherwise we block.
@@ -488,8 +503,7 @@
* check socket cache ... must talk to Alan about his plans
* for sock caches... i'll skip this for now.
*/
- sk = __udp6_lib_lookup(net, saddr, uh->source,
- daddr, uh->dest, inet6_iif(skb), udptable);
+ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk == NULL) {
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index f6cdcb3..3cd1a1a 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -13,8 +13,6 @@
*/
#include "udp_impl.h"
-DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6) __read_mostly;
-
static int udplitev6_rcv(struct sk_buff *skb)
{
return __udp6_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE);