summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorSteve French <sfrench@hera.kernel.org>2005-06-30 20:57:39 -0700
committerSteve French <sfrench@hera.kernel.org>2005-06-30 20:57:39 -0700
commitab997aaeb9cf7a0da1cecc46c5bb6c7262416917 (patch)
treeb8a09ed676101a2478d17c1d71da1274293c3c64 /net
parentfa5cfae37799177769e9ae2c0527fbdfea462fa9 (diff)
parentbd53d1270f51c6cfb53b06c8f93fd42327871d6b (diff)
Merge with rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
Diffstat (limited to 'net')
-rw-r--r--net/bridge/br_netfilter.c2
-rw-r--r--net/bridge/netfilter/ebt_log.c6
-rw-r--r--net/core/dev.c125
-rw-r--r--net/core/neighbour.c6
-rw-r--r--net/core/pktgen.c29
-rw-r--r--net/core/rtnetlink.c2
-rw-r--r--net/core/skbuff.c157
-rw-r--r--net/core/sysctl_net_core.c46
-rw-r--r--net/core/wireless.c1
-rw-r--r--net/ethernet/eth.c7
-rw-r--r--net/ipv4/Kconfig83
-rw-r--r--net/ipv4/fib_trie.c56
-rw-r--r--net/ipv4/ip_input.c6
-rw-r--r--net/ipv4/ip_output.c8
-rw-r--r--net/ipv4/ipconfig.c4
-rw-r--r--net/ipv4/ipmr.c10
-rw-r--r--net/ipv4/ipvs/ip_vs_conn.c25
-rw-r--r--net/ipv4/ipvs/ip_vs_ctl.c8
-rw-r--r--net/ipv4/ipvs/ip_vs_sync.c4
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c7
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c31
-rw-r--r--net/ipv4/tcp_cong.c46
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv6/addrconf.c19
-rw-r--r--net/ipv6/ip6_flowlabel.c1
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/netlink/af_netlink.c11
-rw-r--r--net/rxrpc/krxiod.c2
-rw-r--r--net/rxrpc/krxsecd.c2
-rw-r--r--net/rxrpc/krxtimod.c2
-rw-r--r--net/sched/Kconfig13
-rw-r--r--net/sched/Makefile1
-rw-r--r--net/sched/act_api.c10
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/cls_rsvp.h1
-rw-r--r--net/sched/em_text.c157
-rw-r--r--net/sched/sch_api.c2
-rw-r--r--net/sched/sch_cbq.c3
-rw-r--r--net/sctp/endpointola.c13
-rw-r--r--net/sctp/protocol.c5
-rw-r--r--net/sctp/sm_statefuns.c16
-rw-r--r--net/sctp/sysctl.c13
-rw-r--r--net/sctp/transport.c1
-rw-r--r--net/sunrpc/sunrpc_syms.c1
-rw-r--r--net/sunrpc/svcsock.c6
-rw-r--r--net/sunrpc/xprt.c4
47 files changed, 664 insertions, 303 deletions
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 03ae4edddac3..2d52fee63a8c 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -844,7 +844,7 @@ static unsigned int ip_sabotage_out(unsigned int hook, struct sk_buff **pskb,
* doesn't use the bridge parent of the indev by using
* the BRNF_DONT_TAKE_PARENT mask. */
if (hook == NF_IP_FORWARD && nf_bridge->physindev == NULL) {
- nf_bridge->mask &= BRNF_DONT_TAKE_PARENT;
+ nf_bridge->mask |= BRNF_DONT_TAKE_PARENT;
nf_bridge->physindev = (struct net_device *)in;
}
#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index e4ae34b88925..662975be3d1d 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -61,8 +61,6 @@ static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
{
struct ebt_log_info *info = (struct ebt_log_info *)data;
char level_string[4] = "< >";
- union {struct iphdr iph; struct tcpudphdr ports;
- struct arphdr arph; struct arppayload arpp;} u;
level_string[1] = '0' + info->loglevel;
spin_lock_bh(&ebt_log_lock);
@@ -88,7 +86,7 @@ static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
}
printk(" IP SRC=%u.%u.%u.%u IP DST=%u.%u.%u.%u,",
NIPQUAD(ih->saddr), NIPQUAD(ih->daddr));
- printk(" IP tos=0x%02X, IP proto=%d", u.iph.tos,
+ printk(" IP tos=0x%02X, IP proto=%d", ih->tos,
ih->protocol);
if (ih->protocol == IPPROTO_TCP ||
ih->protocol == IPPROTO_UDP) {
@@ -127,7 +125,7 @@ static void ebt_log(const struct sk_buff *skb, unsigned int hooknr,
ah->ar_pln == sizeof(uint32_t)) {
struct arppayload _arpp, *ap;
- ap = skb_header_pointer(skb, sizeof(u.arph),
+ ap = skb_header_pointer(skb, sizeof(_arph),
sizeof(_arpp), &_arpp);
if (ap == NULL) {
printk(" INCOMPLETE ARP payload");
diff --git a/net/core/dev.c b/net/core/dev.c
index ab935778ce81..7016e0c36b3d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -115,18 +115,6 @@
#endif /* CONFIG_NET_RADIO */
#include <asm/current.h>
-/* This define, if set, will randomly drop a packet when congestion
- * is more than moderate. It helps fairness in the multi-interface
- * case when one of them is a hog, but it kills performance for the
- * single interface case so it is off now by default.
- */
-#undef RAND_LIE
-
-/* Setting this will sample the queue lengths and thus congestion
- * via a timer instead of as each packet is received.
- */
-#undef OFFLINE_SAMPLE
-
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
@@ -159,11 +147,6 @@ static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[16]; /* 16 way hashed list */
static struct list_head ptype_all; /* Taps */
-#ifdef OFFLINE_SAMPLE
-static void sample_queue(unsigned long dummy);
-static struct timer_list samp_timer = TIMER_INITIALIZER(sample_queue, 0, 0);
-#endif
-
/*
* The @dev_base list is protected by @dev_base_lock and the rtln
* semaphore.
@@ -215,7 +198,7 @@ static struct notifier_block *netdev_chain;
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
-DEFINE_PER_CPU(struct softnet_data, softnet_data) = { 0, };
+DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };
#ifdef CONFIG_SYSFS
extern int netdev_sysfs_init(void);
@@ -1363,71 +1346,13 @@ out:
Receiver routines
=======================================================================*/
-int netdev_max_backlog = 300;
+int netdev_max_backlog = 1000;
+int netdev_budget = 300;
int weight_p = 64; /* old backlog weight */
-/* These numbers are selected based on intuition and some
- * experimentatiom, if you have more scientific way of doing this
- * please go ahead and fix things.
- */
-int no_cong_thresh = 10;
-int no_cong = 20;
-int lo_cong = 100;
-int mod_cong = 290;
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
-static void get_sample_stats(int cpu)
-{
-#ifdef RAND_LIE
- unsigned long rd;
- int rq;
-#endif
- struct softnet_data *sd = &per_cpu(softnet_data, cpu);
- int blog = sd->input_pkt_queue.qlen;
- int avg_blog = sd->avg_blog;
-
- avg_blog = (avg_blog >> 1) + (blog >> 1);
-
- if (avg_blog > mod_cong) {
- /* Above moderate congestion levels. */
- sd->cng_level = NET_RX_CN_HIGH;
-#ifdef RAND_LIE
- rd = net_random();
- rq = rd % netdev_max_backlog;
- if (rq < avg_blog) /* unlucky bastard */
- sd->cng_level = NET_RX_DROP;
-#endif
- } else if (avg_blog > lo_cong) {
- sd->cng_level = NET_RX_CN_MOD;
-#ifdef RAND_LIE
- rd = net_random();
- rq = rd % netdev_max_backlog;
- if (rq < avg_blog) /* unlucky bastard */
- sd->cng_level = NET_RX_CN_HIGH;
-#endif
- } else if (avg_blog > no_cong)
- sd->cng_level = NET_RX_CN_LOW;
- else /* no congestion */
- sd->cng_level = NET_RX_SUCCESS;
-
- sd->avg_blog = avg_blog;
-}
-
-#ifdef OFFLINE_SAMPLE
-static void sample_queue(unsigned long dummy)
-{
-/* 10 ms 0r 1ms -- i don't care -- JHS */
- int next_tick = 1;
- int cpu = smp_processor_id();
-
- get_sample_stats(cpu);
- next_tick += jiffies;
- mod_timer(&samp_timer, next_tick);
-}
-#endif
-
-
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
@@ -1448,7 +1373,6 @@ static void sample_queue(unsigned long dummy)
int netif_rx(struct sk_buff *skb)
{
- int this_cpu;
struct softnet_data *queue;
unsigned long flags;
@@ -1464,38 +1388,22 @@ int netif_rx(struct sk_buff *skb)
* short when CPU is congested, but is still operating.
*/
local_irq_save(flags);
- this_cpu = smp_processor_id();
queue = &__get_cpu_var(softnet_data);
__get_cpu_var(netdev_rx_stat).total++;
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
- if (queue->throttle)
- goto drop;
-
enqueue:
dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
-#ifndef OFFLINE_SAMPLE
- get_sample_stats(this_cpu);
-#endif
local_irq_restore(flags);
- return queue->cng_level;
+ return NET_RX_SUCCESS;
}
- if (queue->throttle)
- queue->throttle = 0;
-
netif_rx_schedule(&queue->backlog_dev);
goto enqueue;
}
- if (!queue->throttle) {
- queue->throttle = 1;
- __get_cpu_var(netdev_rx_stat).throttled++;
- }
-
-drop:
__get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);
@@ -1780,8 +1688,6 @@ job_done:
smp_mb__before_clear_bit();
netif_poll_enable(backlog_dev);
- if (queue->throttle)
- queue->throttle = 0;
local_irq_enable();
return 0;
}
@@ -1790,8 +1696,7 @@ static void net_rx_action(struct softirq_action *h)
{
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
- int budget = netdev_max_backlog;
-
+ int budget = netdev_budget;
local_irq_disable();
@@ -2055,15 +1960,9 @@ static int softnet_seq_show(struct seq_file *seq, void *v)
struct netif_rx_stats *s = v;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- s->total, s->dropped, s->time_squeeze, s->throttled,
- s->fastroute_hit, s->fastroute_success, s->fastroute_defer,
- s->fastroute_deferred_out,
-#if 0
- s->fastroute_latency_reduction
-#else
- s->cpu_collision
-#endif
- );
+ s->total, s->dropped, s->time_squeeze, 0,
+ 0, 0, 0, 0, /* was fastroute */
+ s->cpu_collision );
return 0;
}
@@ -3305,9 +3204,6 @@ static int __init net_dev_init(void)
queue = &per_cpu(softnet_data, i);
skb_queue_head_init(&queue->input_pkt_queue);
- queue->throttle = 0;
- queue->cng_level = 0;
- queue->avg_blog = 10; /* arbitrary non-zero */
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
@@ -3316,11 +3212,6 @@ static int __init net_dev_init(void)
atomic_set(&queue->backlog_dev.refcnt, 1);
}
-#ifdef OFFLINE_SAMPLE
- samp_timer.expires = jiffies + (10 * HZ);
- add_timer(&samp_timer);
-#endif
-
dev_boot_phase = 0;
open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 851eb927ed97..1beb782ac41b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1598,6 +1598,8 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb,
read_lock_bh(&tbl->lock);
ndtmsg->ndtm_family = tbl->family;
+ ndtmsg->ndtm_pad1 = 0;
+ ndtmsg->ndtm_pad2 = 0;
RTA_PUT_STRING(skb, NDTA_NAME, tbl->id);
RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
@@ -1683,6 +1685,8 @@ static int neightbl_fill_param_info(struct neigh_table *tbl,
read_lock_bh(&tbl->lock);
ndtmsg->ndtm_family = tbl->family;
+ ndtmsg->ndtm_pad1 = 0;
+ ndtmsg->ndtm_pad2 = 0;
RTA_PUT_STRING(skb, NDTA_NAME, tbl->id);
if (neightbl_fill_parms(skb, parms) < 0)
@@ -1872,6 +1876,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n,
struct ndmsg *ndm = NLMSG_DATA(nlh);
ndm->ndm_family = n->ops->family;
+ ndm->ndm_pad1 = 0;
+ ndm->ndm_pad2 = 0;
ndm->ndm_flags = n->flags;
ndm->ndm_type = n->type;
ndm->ndm_ifindex = n->dev->ifindex;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index c57b06bc79f3..975d651312dc 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -151,7 +151,7 @@
#include <asm/timex.h>
-#define VERSION "pktgen v2.61: Packet Generator for packet performance testing.\n"
+#define VERSION "pktgen v2.62: Packet Generator for packet performance testing.\n"
/* #define PG_DEBUG(a) a */
#define PG_DEBUG(a)
@@ -1921,6 +1921,11 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
struct iphdr *iph;
struct pktgen_hdr *pgh = NULL;
+ /* Update any of the values, used when we're incrementing various
+ * fields.
+ */
+ mod_cur_headers(pkt_dev);
+
skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16, GFP_ATOMIC);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
@@ -1934,11 +1939,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr));
udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr));
- /* Update any of the values, used when we're incrementing various
- * fields.
- */
- mod_cur_headers(pkt_dev);
-
memcpy(eth, pkt_dev->hh, 12);
*(u16*)&eth[12] = __constant_htons(ETH_P_IP);
@@ -2192,7 +2192,12 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
int datalen;
struct ipv6hdr *iph;
struct pktgen_hdr *pgh = NULL;
-
+
+ /* Update any of the values, used when we're incrementing various
+ * fields.
+ */
+ mod_cur_headers(pkt_dev);
+
skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16, GFP_ATOMIC);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
@@ -2206,17 +2211,9 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr));
udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr));
-
- /* Update any of the values, used when we're incrementing various
- * fields.
- */
- mod_cur_headers(pkt_dev);
-
-
memcpy(eth, pkt_dev->hh, 12);
*(u16*)&eth[12] = __constant_htons(ETH_P_IPV6);
-
-
+
datalen = pkt_dev->cur_pkt_size-14-
sizeof(struct ipv6hdr)-sizeof(struct udphdr); /* Eth + IPh + UDPh */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e013d836a7ab..4b1bb30e6381 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -126,6 +126,7 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data
rta->rta_type = attrtype;
rta->rta_len = size;
memcpy(RTA_DATA(rta), data, attrlen);
+ memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size);
}
size_t rtattr_strlcpy(char *dest, const struct rtattr *rta, size_t size)
@@ -188,6 +189,7 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags);
r = NLMSG_DATA(nlh);
r->ifi_family = AF_UNSPEC;
+ r->__ifi_pad = 0;
r->ifi_type = dev->type;
r->ifi_index = dev->ifindex;
r->ifi_flags = dev_get_flags(dev);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 6d68c03bc051..bb73b2190ec7 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1500,6 +1500,159 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len)
skb_split_no_header(skb, skb1, len, pos);
}
+/**
+ * skb_prepare_seq_read - Prepare a sequential read of skb data
+ * @skb: the buffer to read
+ * @from: lower offset of data to be read
+ * @to: upper offset of data to be read
+ * @st: state variable
+ *
+ * Initializes the specified state variable. Must be called before
+ * invoking skb_seq_read() for the first time.
+ */
+void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
+ unsigned int to, struct skb_seq_state *st)
+{
+ st->lower_offset = from;
+ st->upper_offset = to;
+ st->root_skb = st->cur_skb = skb;
+ st->frag_idx = st->stepped_offset = 0;
+ st->frag_data = NULL;
+}
+
+/**
+ * skb_seq_read - Sequentially read skb data
+ * @consumed: number of bytes consumed by the caller so far
+ * @data: destination pointer for data to be returned
+ * @st: state variable
+ *
+ * Reads a block of skb data at &consumed relative to the
+ * lower offset specified to skb_prepare_seq_read(). Assigns
+ * the head of the data block to &data and returns the length
+ * of the block or 0 if the end of the skb data or the upper
+ * offset has been reached.
+ *
+ * The caller is not required to consume all of the data
+ * returned, i.e. &consumed is typically set to the number
+ * of bytes already consumed and the next call to
+ * skb_seq_read() will return the remaining part of the block.
+ *
+ * Note: The size of each block of data returned can be arbitary,
+ * this limitation is the cost for zerocopy seqeuental
+ * reads of potentially non linear data.
+ *
+ * Note: Fragment lists within fragments are not implemented
+ * at the moment, state->root_skb could be replaced with
+ * a stack for this purpose.
+ */
+unsigned int skb_seq_read(unsigned int consumed, const u8 **data,
+ struct skb_seq_state *st)
+{
+ unsigned int block_limit, abs_offset = consumed + st->lower_offset;
+ skb_frag_t *frag;
+
+ if (unlikely(abs_offset >= st->upper_offset))
+ return 0;
+
+next_skb:
+ block_limit = skb_headlen(st->cur_skb);
+
+ if (abs_offset < block_limit) {
+ *data = st->cur_skb->data + abs_offset;
+ return block_limit - abs_offset;
+ }
+
+ if (st->frag_idx == 0 && !st->frag_data)
+ st->stepped_offset += skb_headlen(st->cur_skb);
+
+ while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+ frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
+ block_limit = frag->size + st->stepped_offset;
+
+ if (abs_offset < block_limit) {
+ if (!st->frag_data)
+ st->frag_data = kmap_skb_frag(frag);
+
+ *data = (u8 *) st->frag_data + frag->page_offset +
+ (abs_offset - st->stepped_offset);
+
+ return block_limit - abs_offset;
+ }
+
+ if (st->frag_data) {
+ kunmap_skb_frag(st->frag_data);
+ st->frag_data = NULL;
+ }
+
+ st->frag_idx++;
+ st->stepped_offset += frag->size;
+ }
+
+ if (st->cur_skb->next) {
+ st->cur_skb = st->cur_skb->next;
+ st->frag_idx = 0;
+ goto next_skb;
+ } else if (st->root_skb == st->cur_skb &&
+ skb_shinfo(st->root_skb)->frag_list) {
+ st->cur_skb = skb_shinfo(st->root_skb)->frag_list;
+ goto next_skb;
+ }
+
+ return 0;
+}
+
+/**
+ * skb_abort_seq_read - Abort a sequential read of skb data
+ * @st: state variable
+ *
+ * Must be called if skb_seq_read() was not called until it
+ * returned 0.
+ */
+void skb_abort_seq_read(struct skb_seq_state *st)
+{
+ if (st->frag_data)
+ kunmap_skb_frag(st->frag_data);
+}
+
+#define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb))
+
+static unsigned int skb_ts_get_next_block(unsigned int offset, const u8 **text,
+ struct ts_config *conf,
+ struct ts_state *state)
+{
+ return skb_seq_read(offset, text, TS_SKB_CB(state));
+}
+
+static void skb_ts_finish(struct ts_config *conf, struct ts_state *state)
+{
+ skb_abort_seq_read(TS_SKB_CB(state));
+}
+
+/**
+ * skb_find_text - Find a text pattern in skb data
+ * @skb: the buffer to look in
+ * @from: search offset
+ * @to: search limit
+ * @config: textsearch configuration
+ * @state: uninitialized textsearch state variable
+ *
+ * Finds a pattern in the skb data according to the specified
+ * textsearch configuration. Use textsearch_next() to retrieve
+ * subsequent occurrences of the pattern. Returns the offset
+ * to the first occurrence or UINT_MAX if no match was found.
+ */
+unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
+ unsigned int to, struct ts_config *config,
+ struct ts_state *state)
+{
+ config->get_next_block = skb_ts_get_next_block;
+ config->finish = skb_ts_finish;
+
+ skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state));
+
+ return textsearch_find(config, state);
+}
+
void __init skb_init(void)
{
skbuff_head_cache = kmem_cache_create("skbuff_head_cache",
@@ -1538,3 +1691,7 @@ EXPORT_SYMBOL(skb_queue_tail);
EXPORT_SYMBOL(skb_unlink);
EXPORT_SYMBOL(skb_append);
EXPORT_SYMBOL(skb_split);
+EXPORT_SYMBOL(skb_prepare_seq_read);
+EXPORT_SYMBOL(skb_seq_read);
+EXPORT_SYMBOL(skb_abort_seq_read);
+EXPORT_SYMBOL(skb_find_text);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 880a88815211..8f817ad9f546 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -13,12 +13,8 @@
#ifdef CONFIG_SYSCTL
extern int netdev_max_backlog;
+extern int netdev_budget;
extern int weight_p;
-extern int no_cong_thresh;
-extern int no_cong;
-extern int lo_cong;
-extern int mod_cong;
-extern int netdev_fastroute;
extern int net_msg_cost;
extern int net_msg_burst;
@@ -86,38 +82,6 @@ ctl_table core_table[] = {
.proc_handler = &proc_dointvec
},
{
- .ctl_name = NET_CORE_NO_CONG_THRESH,
- .procname = "no_cong_thresh",
- .data = &no_cong_thresh,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec
- },
- {
- .ctl_name = NET_CORE_NO_CONG,
- .procname = "no_cong",
- .data = &no_cong,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec
- },
- {
- .ctl_name = NET_CORE_LO_CONG,
- .procname = "lo_cong",
- .data = &lo_cong,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec
- },
- {
- .ctl_name = NET_CORE_MOD_CONG,
- .procname = "mod_cong",
- .data = &mod_cong,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = &proc_dointvec
- },
- {
.ctl_name = NET_CORE_MSG_COST,
.procname = "message_cost",
.data = &net_msg_cost,
@@ -161,6 +125,14 @@ ctl_table core_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec
},
+ {
+ .ctl_name = NET_CORE_BUDGET,
+ .procname = "netdev_budget",
+ .data = &netdev_budget,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec
+ },
{ .ctl_name = 0 }
};
diff --git a/net/core/wireless.c b/net/core/wireless.c
index b2fe378dfbf8..3ff5639c0b78 100644
--- a/net/core/wireless.c
+++ b/net/core/wireless.c
@@ -1102,6 +1102,7 @@ static inline int rtnetlink_fill_iwinfo(struct sk_buff * skb,
nlh = NLMSG_PUT(skb, 0, 0, type, sizeof(*r));
r = NLMSG_DATA(nlh);
r->ifi_family = AF_UNSPEC;
+ r->__ifi_pad = 0;
r->ifi_type = dev->type;
r->ifi_index = dev->ifindex;
r->ifi_flags = dev->flags;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 6617ea47d365..ab60ea63688e 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -92,10 +92,9 @@ int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
* Set the source hardware address.
*/
- if(saddr)
- memcpy(eth->h_source,saddr,dev->addr_len);
- else
- memcpy(eth->h_source,dev->dev_addr,dev->addr_len);
+ if(!saddr)
+ saddr = dev->dev_addr;
+ memcpy(eth->h_source,saddr,dev->addr_len);
/*
* Anyway, the loopback-device should never use this function...
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 690e88ba2484..3e63123f7bbd 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -1,32 +1,6 @@
#
# IP configuration
#
-choice
- prompt "Choose IP: FIB lookup"
- depends on INET
- default IP_FIB_HASH
-
-config IP_FIB_HASH
- bool "FIB_HASH"
- ---help---
- Current FIB is very proven and good enough for most users.
-
-config IP_FIB_TRIE
- bool "FIB_TRIE"
- ---help---
- Use new experimental LC-trie as FIB lookup algoritm.
- This improves lookup performance
-
- LC-trie is described in:
-
- IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
- IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999
- An experimental study of compression methods for dynamic tries
- Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002.
- http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/
-
-endchoice
-
config IP_MULTICAST
bool "IP: multicasting"
depends on INET
@@ -79,6 +53,44 @@ config IP_ADVANCED_ROUTER
If unsure, say N here.
+choice
+ prompt "Choose IP: FIB lookup algorithm (choose FIB_HASH if unsure)"
+ depends on IP_ADVANCED_ROUTER
+ default IP_FIB_HASH
+
+config IP_FIB_HASH
+ bool "FIB_HASH"
+ ---help---
+ Current FIB is very proven and good enough for most users.
+
+config IP_FIB_TRIE
+ bool "FIB_TRIE"
+ ---help---
+ Use new experimental LC-trie as FIB lookup algoritm.
+ This improves lookup performance if you have a large
+ number of routes.
+
+ LC-trie is a longest matching prefix lookup algorithm which
+ performs better than FIB_HASH for large routing tables.
+ But, it consumes more memory and is more complex.
+
+ LC-trie is described in:
+
+ IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
+ IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999
+ An experimental study of compression methods for dynamic tries
+ Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002.
+ http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/
+
+endchoice
+
+# If the user does not enable advanced routing, he gets the safe
+# default of the fib-hash algorithm.
+config IP_FIB_HASH
+ bool
+ depends on !IP_ADVANCED_ROUTER
+ default y
+
config IP_MULTIPLE_TABLES
bool "IP: policy routing"
depends on IP_ADVANCED_ROUTER
@@ -433,9 +445,21 @@ config IP_TCPDIAG
config IP_TCPDIAG_IPV6
def_bool (IP_TCPDIAG=y && IPV6=y) || (IP_TCPDIAG=m && IPV6)
+config TCP_CONG_ADVANCED
+ bool "TCP: advanced congestion control"
+ depends on INET
+ ---help---
+ Support for selection of various TCP congestion control
+ modules.
+
+ Nearly all users can safely say no here, and a safe default
+ selection will be made (BIC-TCP with new Reno as a fallback).
+
+ If unsure, say N.
+
# TCP Reno is builtin (required as fallback)
menu "TCP congestion control"
- depends on INET
+ depends on TCP_CONG_ADVANCED
config TCP_CONG_BIC
tristate "Binary Increase Congestion (BIC) control"
@@ -523,5 +547,10 @@ config TCP_CONG_SCALABLE
endmenu
+config TCP_CONG_BIC
+ tristate
+ depends on !TCP_CONG_ADVANCED
+ default y
+
source "net/ipv4/ipvs/Kconfig"
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 0671569ee6f0..b56e88edf1b3 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -43,7 +43,7 @@
* 2 of the License, or (at your option) any later version.
*/
-#define VERSION "0.323"
+#define VERSION "0.324"
#include <linux/config.h>
#include <asm/uaccess.h>
@@ -341,8 +341,10 @@ static struct leaf *leaf_new(void)
static struct leaf_info *leaf_info_new(int plen)
{
struct leaf_info *li = kmalloc(sizeof(struct leaf_info), GFP_KERNEL);
- li->plen = plen;
- INIT_LIST_HEAD(&li->falh);
+ if(li) {
+ li->plen = plen;
+ INIT_LIST_HEAD(&li->falh);
+ }
return li;
}
@@ -879,8 +881,8 @@ static struct node *trie_rebalance(struct trie *t, struct tnode *tn)
return (struct node*) tn;
}
-static struct list_head *
-fib_insert_node(struct trie *t, u32 key, int plen)
+static struct list_head *
+fib_insert_node(struct trie *t, int *err, u32 key, int plen)
{
int pos, newpos;
struct tnode *tp = NULL, *tn = NULL;
@@ -940,7 +942,6 @@ fib_insert_node(struct trie *t, u32 key, int plen)
if(tp && IS_LEAF(tp))
BUG();
- t->revision++;
/* Case 1: n is a leaf. Compare prefixes */
@@ -949,8 +950,10 @@ fib_insert_node(struct trie *t, u32 key, int plen)
li = leaf_info_new(plen);
- if(! li)
- BUG();
+ if(! li) {
+ *err = -ENOMEM;
+ goto err;
+ }
fa_head = &li->falh;
insert_leaf_info(&l->list, li);
@@ -959,14 +962,19 @@ fib_insert_node(struct trie *t, u32 key, int plen)
t->size++;
l = leaf_new();
- if(! l)
- BUG();
+ if(! l) {
+ *err = -ENOMEM;
+ goto err;
+ }
l->key = key;
li = leaf_info_new(plen);
- if(! li)
- BUG();
+ if(! li) {
+ tnode_free((struct tnode *) l);
+ *err = -ENOMEM;
+ goto err;
+ }
fa_head = &li->falh;
insert_leaf_info(&l->list, li);
@@ -1003,9 +1011,14 @@ fib_insert_node(struct trie *t, u32 key, int plen)
newpos = 0;
tn = tnode_new(key, newpos, 1); /* First tnode */
}
- if(!tn)
- trie_bug("tnode_pfx_new failed");
+ if(!tn) {
+ free_leaf_info(li);
+ tnode_free((struct tnode *) l);
+ *err = -ENOMEM;
+ goto err;
+ }
+
NODE_SET_PARENT(tn, tp);
missbit=tkey_extract_bits(key, newpos, 1);
@@ -1027,7 +1040,9 @@ fib_insert_node(struct trie *t, u32 key, int plen)
}
/* Rebalance the trie */
t->trie = trie_rebalance(t, tp);
-done:;
+done:
+ t->revision++;
+err:;
return fa_head;
}
@@ -1156,8 +1171,12 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
* Insert new entry to the list.
*/
- if(!fa_head)
- fa_head = fib_insert_node(t, key, plen);
+ if(!fa_head) {
+ fa_head = fib_insert_node(t, &err, key, plen);
+ err = 0;
+ if(err)
+ goto out_free_new_fa;
+ }
write_lock_bh(&fib_lock);
@@ -1170,6 +1189,9 @@ fn_trie_insert(struct fib_table *tb, struct rtmsg *r, struct kern_rta *rta,
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, nlhdr, req);
succeeded:
return 0;
+
+out_free_new_fa:
+ kmem_cache_free(fn_alias_kmem, new_fa);
out:
fib_release_info(fi);
err:;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index af2ec88bbb2f..c703528e0bcd 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -283,14 +283,18 @@ static inline int ip_rcv_finish(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = skb->nh.iph;
+ int err;
/*
* Initialise the virtual path cache for the packet. It describes
* how the packet travels inside Linux networking.
*/
if (skb->dst == NULL) {
- if (ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))
+ if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
+ if (err == -EHOSTUNREACH)
+ IP_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
goto drop;
+ }
}
#ifdef CONFIG_NET_CLS_ROUTE
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ee07aec215a0..6ce5c3292f9f 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -188,7 +188,13 @@ static inline int ip_finish_output2(struct sk_buff *skb)
skb = skb2;
}
- nf_reset(skb);
+#ifdef CONFIG_BRIDGE_NETFILTER
+ /* bridge-netfilter defers calling some IP hooks to the bridge layer
+ * and still needs the conntrack reference.
+ */
+ if (skb->nf_bridge == NULL)
+#endif
+ nf_reset(skb);
if (hh) {
int hh_alen;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index f2509034ce72..d2bf8e1930a3 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1149,8 +1149,10 @@ static int __init ic_dynamic(void)
ic_rarp_cleanup();
#endif
- if (!ic_got_reply)
+ if (!ic_got_reply) {
+ ic_myaddr = INADDR_NONE;
return -1;
+ }
printk("IP-Config: Got %s answer from %u.%u.%u.%u, ",
((ic_got_reply & IC_RARP) ? "RARP"
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index e4f809a93f47..7833d920bdba 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -297,6 +297,7 @@ static int vif_delete(int vifi)
static void ipmr_destroy_unres(struct mfc_cache *c)
{
struct sk_buff *skb;
+ struct nlmsgerr *e;
atomic_dec(&cache_resolve_queue_len);
@@ -306,7 +307,9 @@ static void ipmr_destroy_unres(struct mfc_cache *c)
nlh->nlmsg_type = NLMSG_ERROR;
nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- ((struct nlmsgerr*)NLMSG_DATA(nlh))->error = -ETIMEDOUT;
+ e = NLMSG_DATA(nlh);
+ e->error = -ETIMEDOUT;
+ memset(&e->msg, 0, sizeof(e->msg));
netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT);
} else
kfree_skb(skb);
@@ -499,6 +502,7 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void)
static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
{
struct sk_buff *skb;
+ struct nlmsgerr *e;
/*
* Play the pending entries through our router
@@ -515,7 +519,9 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c)
nlh->nlmsg_type = NLMSG_ERROR;
nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
- ((struct nlmsgerr*)NLMSG_DATA(nlh))->error = -EMSGSIZE;
+ e = NLMSG_DATA(nlh);
+ e->error = -EMSGSIZE;
+ memset(&e->msg, 0, sizeof(e->msg));
}
err = netlink_unicast(rtnl, skb, NETLINK_CB(skb).dst_pid, MSG_DONTWAIT);
} else
diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index fd6feb5499fe..9f16ab309106 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -548,7 +548,6 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
{
if (del_timer(&cp->timer))
mod_timer(&cp->timer, jiffies);
- __ip_vs_conn_put(cp);
}
@@ -764,7 +763,6 @@ void ip_vs_random_dropentry(void)
{
int idx;
struct ip_vs_conn *cp;
- struct ip_vs_conn *ct;
/*
* Randomly scan 1/32 of the whole table every second
@@ -801,21 +799,12 @@ void ip_vs_random_dropentry(void)
continue;
}
- /*
- * Drop the entry, and drop its ct if not referenced
- */
- atomic_inc(&cp->refcnt);
- ct_write_unlock(hash);
-
- if ((ct = cp->control))
- atomic_inc(&ct->refcnt);
IP_VS_DBG(4, "del connection\n");
ip_vs_conn_expire_now(cp);
- if (ct) {
+ if (cp->control) {
IP_VS_DBG(4, "del conn template\n");
- ip_vs_conn_expire_now(ct);
+ ip_vs_conn_expire_now(cp->control);
}
- ct_write_lock(hash);
}
ct_write_unlock(hash);
}
@@ -829,7 +818,6 @@ static void ip_vs_conn_flush(void)
{
int idx;
struct ip_vs_conn *cp;
- struct ip_vs_conn *ct;
flush_again:
for (idx=0; idx<IP_VS_CONN_TAB_SIZE; idx++) {
@@ -839,18 +827,13 @@ static void ip_vs_conn_flush(void)
ct_write_lock_bh(idx);
list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) {
- atomic_inc(&cp->refcnt);
- ct_write_unlock(idx);
- if ((ct = cp->control))
- atomic_inc(&ct->refcnt);
IP_VS_DBG(4, "del connection\n");
ip_vs_conn_expire_now(cp);
- if (ct) {
+ if (cp->control) {
IP_VS_DBG(4, "del conn template\n");
- ip_vs_conn_expire_now(ct);
+ ip_vs_conn_expire_now(cp->control);
}
- ct_write_lock(idx);
}
ct_write_unlock_bh(idx);
}
diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c
index 218d9701036e..12a82e91d22a 100644
--- a/net/ipv4/ipvs/ip_vs_ctl.c
+++ b/net/ipv4/ipvs/ip_vs_ctl.c
@@ -2059,7 +2059,7 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
dst->addr = src->addr;
dst->port = src->port;
dst->fwmark = src->fwmark;
- strcpy(dst->sched_name, src->scheduler->name);
+ strlcpy(dst->sched_name, src->scheduler->name, sizeof(dst->sched_name));
dst->flags = src->flags;
dst->timeout = src->timeout / HZ;
dst->netmask = src->netmask;
@@ -2080,6 +2080,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
if (count >= get->num_services)
goto out;
+ memset(&entry, 0, sizeof(entry));
ip_vs_copy_service(&entry, svc);
if (copy_to_user(&uptr->entrytable[count],
&entry, sizeof(entry))) {
@@ -2094,6 +2095,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get,
list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
if (count >= get->num_services)
goto out;
+ memset(&entry, 0, sizeof(entry));
ip_vs_copy_service(&entry, svc);
if (copy_to_user(&uptr->entrytable[count],
&entry, sizeof(entry))) {
@@ -2304,12 +2306,12 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
memset(&d, 0, sizeof(d));
if (ip_vs_sync_state & IP_VS_STATE_MASTER) {
d[0].state = IP_VS_STATE_MASTER;
- strcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn);
+ strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn));
d[0].syncid = ip_vs_master_syncid;
}
if (ip_vs_sync_state & IP_VS_STATE_BACKUP) {
d[1].state = IP_VS_STATE_BACKUP;
- strcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn);
+ strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn));
d[1].syncid = ip_vs_backup_syncid;
}
if (copy_to_user(user, &d, sizeof(d)) != 0)
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index 25c479550a32..574d1f509b46 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -839,10 +839,10 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid)
ip_vs_sync_state |= state;
if (state == IP_VS_STATE_MASTER) {
- strcpy(ip_vs_master_mcast_ifn, mcast_ifn);
+ strlcpy(ip_vs_master_mcast_ifn, mcast_ifn, sizeof(ip_vs_master_mcast_ifn));
ip_vs_master_syncid = syncid;
} else {
- strcpy(ip_vs_backup_mcast_ifn, mcast_ifn);
+ strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn, sizeof(ip_vs_backup_mcast_ifn));
ip_vs_backup_syncid = syncid;
}
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 9cde8c61f525..6706d3a1bc4f 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -30,7 +30,7 @@
#include <linux/netfilter_ipv4/ipt_CLUSTERIP.h>
#include <linux/netfilter_ipv4/ip_conntrack.h>
-#define CLUSTERIP_VERSION "0.6"
+#define CLUSTERIP_VERSION "0.7"
#define DEBUG_CLUSTERIP
@@ -524,8 +524,9 @@ arp_mangle(unsigned int hook,
|| arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN)
return NF_ACCEPT;
- /* we only want to mangle arp replies */
- if (arp->ar_op != htons(ARPOP_REPLY))
+ /* we only want to mangle arp requests and replies */
+ if (arp->ar_op != htons(ARPOP_REPLY)
+ && arp->ar_op != htons(ARPOP_REQUEST))
return NF_ACCEPT;
payload = (void *)(arp+1);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 80cf633d9f4a..12a1cf306f67 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1909,7 +1909,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
*/
if ((err = fib_lookup(&fl, &res)) != 0) {
if (!IN_DEV_FORWARD(in_dev))
- goto e_inval;
+ goto e_hostunreach;
goto no_route;
}
free_res = 1;
@@ -1933,7 +1933,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
}
if (!IN_DEV_FORWARD(in_dev))
- goto e_inval;
+ goto e_hostunreach;
if (res.type != RTN_UNICAST)
goto martian_destination;
@@ -2025,6 +2025,11 @@ martian_destination:
"%u.%u.%u.%u, dev %s\n",
NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
#endif
+
+e_hostunreach:
+ err = -EHOSTUNREACH;
+ goto done;
+
e_inval:
err = -EINVAL;
goto done;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f3dbc8dc1263..882436da9a3a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1927,6 +1927,25 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
return tp->af_specific->setsockopt(sk, level, optname,
optval, optlen);
+ /* This is a string value all the others are int's */
+ if (optname == TCP_CONGESTION) {
+ char name[TCP_CA_NAME_MAX];
+
+ if (optlen < 1)
+ return -EINVAL;
+
+ val = strncpy_from_user(name, optval,
+ min(TCP_CA_NAME_MAX-1, optlen));
+ if (val < 0)
+ return -EFAULT;
+ name[val] = 0;
+
+ lock_sock(sk);
+ err = tcp_set_congestion_control(tp, name);
+ release_sock(sk);
+ return err;
+ }
+
if (optlen < sizeof(int))
return -EINVAL;
@@ -2211,6 +2230,16 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
case TCP_QUICKACK:
val = !tp->ack.pingpong;
break;
+
+ case TCP_CONGESTION:
+ if (get_user(len, optlen))
+ return -EFAULT;
+ len = min_t(unsigned int, len, TCP_CA_NAME_MAX);
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, tp->ca_ops->name, len))
+ return -EFAULT;
+ return 0;
default:
return -ENOPROTOOPT;
};
@@ -2224,7 +2253,7 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
extern void __skb_cb_too_small_for_tcp(int, int);
-extern void tcpdiag_init(void);
+extern struct tcp_congestion_ops tcp_reno;
static __initdata unsigned long thash_entries;
static int __init set_thash_entries(char *str)
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 665394a63ae4..4970d10a7785 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -21,7 +21,7 @@ static struct tcp_congestion_ops *tcp_ca_find(const char *name)
{
struct tcp_congestion_ops *e;
- list_for_each_entry(e, &tcp_cong_list, list) {
+ list_for_each_entry_rcu(e, &tcp_cong_list, list) {
if (strcmp(e->name, name) == 0)
return e;
}
@@ -77,6 +77,9 @@ void tcp_init_congestion_control(struct tcp_sock *tp)
{
struct tcp_congestion_ops *ca;
+ if (tp->ca_ops != &tcp_init_congestion_ops)
+ return;
+
rcu_read_lock();
list_for_each_entry_rcu(ca, &tcp_cong_list, list) {
if (try_module_get(ca->owner)) {
@@ -139,6 +142,34 @@ void tcp_get_default_congestion_control(char *name)
rcu_read_unlock();
}
+/* Change congestion control for socket */
+int tcp_set_congestion_control(struct tcp_sock *tp, const char *name)
+{
+ struct tcp_congestion_ops *ca;
+ int err = 0;
+
+ rcu_read_lock();
+ ca = tcp_ca_find(name);
+ if (ca == tp->ca_ops)
+ goto out;
+
+ if (!ca)
+ err = -ENOENT;
+
+ else if (!try_module_get(ca->owner))
+ err = -EBUSY;
+
+ else {
+ tcp_cleanup_congestion_control(tp);
+ tp->ca_ops = ca;
+ if (tp->ca_ops->init)
+ tp->ca_ops->init(tp);
+ }
+ out:
+ rcu_read_unlock();
+ return err;
+}
+
/*
* TCP Reno congestion control
* This is special case used for fallback as well.
@@ -192,4 +223,15 @@ struct tcp_congestion_ops tcp_reno = {
.min_cwnd = tcp_reno_min_cwnd,
};
-EXPORT_SYMBOL_GPL(tcp_reno);
+/* Initial congestion control used (until SYN)
+ * really reno under another name so we can tell difference
+ * during tcp_set_default_congestion_control
+ */
+struct tcp_congestion_ops tcp_init_congestion_ops = {
+ .name = "",
+ .owner = THIS_MODULE,
+ .ssthresh = tcp_reno_ssthresh,
+ .cong_avoid = tcp_reno_cong_avoid,
+ .min_cwnd = tcp_reno_min_cwnd,
+};
+EXPORT_SYMBOL_GPL(tcp_init_congestion_ops);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9122814c13ad..ebf112347a97 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2048,7 +2048,7 @@ static int tcp_v4_init_sock(struct sock *sk)
tp->mss_cache_std = tp->mss_cache = 536;
tp->reordering = sysctl_tcp_reordering;
- tp->ca_ops = &tcp_reno;
+ tp->ca_ops = &tcp_init_congestion_ops;
sk->sk_state = TCP_CLOSE;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a54d4ef3fd35..77004b9456c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2777,7 +2777,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
read_lock_bh(&idev->lock);
switch (type) {
case UNICAST_ADDR:
- /* unicast address */
+ /* unicast address incl. temp addr */
for (ifa = idev->addr_list; ifa;
ifa = ifa->if_next, ip_idx++) {
if (ip_idx < s_ip_idx)
@@ -2788,19 +2788,6 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
NLM_F_MULTI)) <= 0)
goto done;
}
- /* temp addr */
-#ifdef CONFIG_IPV6_PRIVACY
- for (ifa = idev->tempaddr_list; ifa;
- ifa = ifa->tmp_next, ip_idx++) {
- if (ip_idx < s_ip_idx)
- continue;
- if ((err = inet6_fill_ifaddr(skb, ifa,
- NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, RTM_NEWADDR,
- NLM_F_MULTI)) <= 0)
- goto done;
- }
-#endif
break;
case MULTICAST_ADDR:
/* multicast address */
@@ -2923,6 +2910,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*r), flags);
r = NLMSG_DATA(nlh);
r->ifi_family = AF_INET6;
+ r->__ifi_pad = 0;
r->ifi_type = dev->type;
r->ifi_index = dev->ifindex;
r->ifi_flags = dev_get_flags(dev);
@@ -3030,9 +3018,12 @@ static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev,
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*pmsg), flags);
pmsg = NLMSG_DATA(nlh);
pmsg->prefix_family = AF_INET6;
+ pmsg->prefix_pad1 = 0;
+ pmsg->prefix_pad2 = 0;
pmsg->prefix_ifindex = idev->dev->ifindex;
pmsg->prefix_len = pinfo->prefix_len;
pmsg->prefix_type = pinfo->type;
+ pmsg->prefix_pad3 = 0;
pmsg->prefix_flags = 0;
if (pinfo->onlink)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 0e5f7499debb..b6c73da5ff35 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -244,7 +244,6 @@ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions * opt_space,
opt_space->opt_nflen = 0;
}
opt_space->dst1opt = fopt->dst1opt;
- opt_space->auth = fopt->auth;
opt_space->opt_flen = fopt->opt_flen;
return opt_space;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fce56039b0e9..9dac7fdf4726 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2025,7 +2025,7 @@ static int tcp_v6_init_sock(struct sock *sk)
sk->sk_state = TCP_CLOSE;
tp->af_specific = &ipv6_specific;
- tp->ca_ops = &tcp_reno;
+ tp->ca_ops = &tcp_init_congestion_ops;
sk->sk_write_space = sk_stream_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 70bcd4744d93..fc456a7aaec3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -315,8 +315,8 @@ err:
static void netlink_remove(struct sock *sk)
{
netlink_table_grab();
- nl_table[sk->sk_protocol].hash.entries--;
- sk_del_node_init(sk);
+ if (sk_del_node_init(sk))
+ nl_table[sk->sk_protocol].hash.entries--;
if (nlk_sk(sk)->groups)
__sk_del_bind_node(sk);
netlink_table_ungrab();
@@ -429,7 +429,12 @@ retry:
err = netlink_insert(sk, pid);
if (err == -EADDRINUSE)
goto retry;
- return 0;
+
+ /* If 2 threads race to autobind, that is fine. */
+ if (err == -EBUSY)
+ err = 0;
+
+ return err;
}
static inline int netlink_capable(struct socket *sock, unsigned int flag)
diff --git a/net/rxrpc/krxiod.c b/net/rxrpc/krxiod.c
index 2b537f425a17..dada34a77b21 100644
--- a/net/rxrpc/krxiod.c
+++ b/net/rxrpc/krxiod.c
@@ -138,7 +138,7 @@ static int rxrpc_krxiod(void *arg)
_debug("### End Work");
- try_to_freeze(PF_FREEZE);
+ try_to_freeze();
/* discard pending signals */
rxrpc_discard_my_signals();
diff --git a/net/rxrpc/krxsecd.c b/net/rxrpc/krxsecd.c
index 6020c89d9228..1aadd026d354 100644
--- a/net/rxrpc/krxsecd.c
+++ b/net/rxrpc/krxsecd.c
@@ -107,7 +107,7 @@ static int rxrpc_krxsecd(void *arg)
_debug("### End Inbound Calls");
- try_to_freeze(PF_FREEZE);
+ try_to_freeze();
/* discard pending signals */
rxrpc_discard_my_signals();
diff --git a/net/rxrpc/krxtimod.c b/net/rxrpc/krxtimod.c
index 249c2b0290bb..3ac81cdd1211 100644
--- a/net/rxrpc/krxtimod.c
+++ b/net/rxrpc/krxtimod.c
@@ -90,7 +90,7 @@ static int krxtimod(void *arg)
complete_and_exit(&krxtimod_dead, 0);
}
- try_to_freeze(PF_FREEZE);
+ try_to_freeze();
/* discard pending signals */
rxrpc_discard_my_signals();
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index b22c9beb604d..7bac249258e3 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -449,6 +449,19 @@ config NET_EMATCH_META
To compile this code as a module, choose M here: the
module will be called em_meta.
+config NET_EMATCH_TEXT
+ tristate "Textsearch"
+ depends on NET_EMATCH
+ select TEXTSEARCH
+ select TEXTSEARCH_KMP
+ select TEXTSEARCH_FSM
+ ---help---
+ Say Y here if you want to be ablt to classify packets based on
+ textsearch comparisons.
+
+ To compile this code as a module, choose M here: the
+ module will be called em_text.
+
config NET_CLS_ACT
bool "Packet ACTION"
depends on EXPERIMENTAL && NET_CLS && NET_QOS
diff --git a/net/sched/Makefile b/net/sched/Makefile
index eb3fe583eba8..8f58cecd6266 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -40,3 +40,4 @@ obj-$(CONFIG_NET_EMATCH_CMP) += em_cmp.o
obj-$(CONFIG_NET_EMATCH_NBYTE) += em_nbyte.o
obj-$(CONFIG_NET_EMATCH_U32) += em_u32.o
obj-$(CONFIG_NET_EMATCH_META) += em_meta.o
+obj-$(CONFIG_NET_EMATCH_TEXT) += em_text.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9594206e6035..249c61936ea0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -439,6 +439,8 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq,
t = NLMSG_DATA(nlh);
t->tca_family = AF_UNSPEC;
+ t->tca__pad1 = 0;
+ t->tca__pad2 = 0;
x = (struct rtattr*) skb->tail;
RTA_PUT(skb, TCA_ACT_TAB, 0, NULL);
@@ -580,6 +582,8 @@ static int tca_action_flush(struct rtattr *rta, struct nlmsghdr *n, u32 pid)
nlh = NLMSG_PUT(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t));
t = NLMSG_DATA(nlh);
t->tca_family = AF_UNSPEC;
+ t->tca__pad1 = 0;
+ t->tca__pad2 = 0;
x = (struct rtattr *) skb->tail;
RTA_PUT(skb, TCA_ACT_TAB, 0, NULL);
@@ -687,7 +691,9 @@ static int tcf_add_notify(struct tc_action *a, u32 pid, u32 seq, int event,
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*t), flags);
t = NLMSG_DATA(nlh);
t->tca_family = AF_UNSPEC;
-
+ t->tca__pad1 = 0;
+ t->tca__pad2 = 0;
+
x = (struct rtattr*) skb->tail;
RTA_PUT(skb, TCA_ACT_TAB, 0, NULL);
@@ -842,6 +848,8 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
cb->nlh->nlmsg_type, sizeof(*t));
t = NLMSG_DATA(nlh);
t->tca_family = AF_UNSPEC;
+ t->tca__pad1 = 0;
+ t->tca__pad2 = 0;
x = (struct rtattr *) skb->tail;
RTA_PUT(skb, TCA_ACT_TAB, 0, NULL);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1616bf5c9627..3b5714ef4d1a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -331,6 +331,8 @@ tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, unsigned long fh,
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
tcm = NLMSG_DATA(nlh);
tcm->tcm_family = AF_UNSPEC;
+ tcm->tcm__pad1 = 0;
+ tcm->tcm__pad1 = 0;
tcm->tcm_ifindex = tp->q->dev->ifindex;
tcm->tcm_parent = tp->classid;
tcm->tcm_info = TC_H_MAKE(tp->prio, tp->protocol);
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 232fb9196810..006168d69376 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -618,6 +618,7 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh,
pinfo.protocol = s->protocol;
pinfo.tunnelid = s->tunnelid;
pinfo.tunnelhdr = f->tunnelhdr;
+ pinfo.pad = 0;
RTA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo);
if (f->res.classid)
RTA_PUT(skb, TCA_RSVP_CLASSID, 4, &f->res.classid);
diff --git a/net/sched/em_text.c b/net/sched/em_text.c
new file mode 100644
index 000000000000..873840d8d072
--- /dev/null
+++ b/net/sched/em_text.c
@@ -0,0 +1,157 @@
+/*
+ * net/sched/em_text.c Textsearch ematch
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <linux/textsearch.h>
+#include <linux/tc_ematch/tc_em_text.h>
+#include <net/pkt_cls.h>
+
+struct text_match
+{
+ u16 from_offset;
+ u16 to_offset;
+ u8 from_layer;
+ u8 to_layer;
+ struct ts_config *config;
+};
+
+#define EM_TEXT_PRIV(m) ((struct text_match *) (m)->data)
+
+static int em_text_match(struct sk_buff *skb, struct tcf_ematch *m,
+ struct tcf_pkt_info *info)
+{
+ struct text_match *tm = EM_TEXT_PRIV(m);
+ int from, to;
+ struct ts_state state;
+
+ from = tcf_get_base_ptr(skb, tm->from_layer) - skb->data;
+ from += tm->from_offset;
+
+ to = tcf_get_base_ptr(skb, tm->to_layer) - skb->data;
+ to += tm->to_offset;
+
+ return skb_find_text(skb, from, to, tm->config, &state) != UINT_MAX;
+}
+
+static int em_text_change(struct tcf_proto *tp, void *data, int len,
+ struct tcf_ematch *m)
+{
+ struct text_match *tm;
+ struct tcf_em_text *conf = data;
+ struct ts_config *ts_conf;
+ int flags = 0;
+
+ printk("Configuring text: %s from %d:%d to %d:%d len %d\n", conf->algo, conf->from_offset,
+ conf->from_layer, conf->to_offset, conf->to_layer, conf->pattern_len);
+
+ if (len < sizeof(*conf) || len < (sizeof(*conf) + conf->pattern_len))
+ return -EINVAL;
+
+ if (conf->from_layer > conf->to_layer)
+ return -EINVAL;
+
+ if (conf->from_layer == conf->to_layer &&
+ conf->from_offset > conf->to_offset)
+ return -EINVAL;
+
+retry:
+ ts_conf = textsearch_prepare(conf->algo, (u8 *) conf + sizeof(*conf),
+ conf->pattern_len, GFP_KERNEL, flags);
+
+ if (flags & TS_AUTOLOAD)
+ rtnl_lock();
+
+ if (IS_ERR(ts_conf)) {
+ if (PTR_ERR(ts_conf) == -ENOENT && !(flags & TS_AUTOLOAD)) {
+ rtnl_unlock();
+ flags |= TS_AUTOLOAD;
+ goto retry;
+ } else
+ return PTR_ERR(ts_conf);
+ } else if (flags & TS_AUTOLOAD) {
+ textsearch_destroy(ts_conf);
+ return -EAGAIN;
+ }
+
+ tm = kmalloc(sizeof(*tm), GFP_KERNEL);
+ if (tm == NULL) {
+ textsearch_destroy(ts_conf);
+ return -ENOBUFS;
+ }
+
+ tm->from_offset = conf->from_offset;
+ tm->to_offset = conf->to_offset;
+ tm->from_layer = conf->from_layer;
+ tm->to_layer = conf->to_layer;
+ tm->config = ts_conf;
+
+ m->datalen = sizeof(*tm);
+ m->data = (unsigned long) tm;
+
+ return 0;
+}
+
+static void em_text_destroy(struct tcf_proto *tp, struct tcf_ematch *m)
+{
+ textsearch_destroy(EM_TEXT_PRIV(m)->config);
+}
+
+static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)
+{
+ struct text_match *tm = EM_TEXT_PRIV(m);
+ struct tcf_em_text conf;
+
+ strncpy(conf.algo, tm->config->ops->name, sizeof(conf.algo) - 1);
+ conf.from_offset = tm->from_offset;
+ conf.to_offset = tm->to_offset;
+ conf.from_layer = tm->from_layer;
+ conf.to_layer = tm->to_layer;
+ conf.pattern_len = textsearch_get_pattern_len(tm->config);
+ conf.pad = 0;
+
+ RTA_PUT_NOHDR(skb, sizeof(conf), &conf);
+ RTA_APPEND(skb, conf.pattern_len, textsearch_get_pattern(tm->config));
+ return 0;
+
+rtattr_failure:
+ return -1;
+}
+
+static struct tcf_ematch_ops em_text_ops = {
+ .kind = TCF_EM_TEXT,
+ .change = em_text_change,
+ .match = em_text_match,
+ .destroy = em_text_destroy,
+ .dump = em_text_dump,
+ .owner = THIS_MODULE,
+ .link = LIST_HEAD_INIT(em_text_ops.link)
+};
+
+static int __init init_em_text(void)
+{
+ return tcf_em_register(&em_text_ops);
+}
+
+static void __exit exit_em_text(void)
+{
+ tcf_em_unregister(&em_text_ops);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_em_text);
+module_exit(exit_em_text);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 97c1c75d5c78..05e6e0a799da 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -770,6 +770,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
tcm = NLMSG_DATA(nlh);
tcm->tcm_family = AF_UNSPEC;
+ tcm->tcm__pad1 = 0;
+ tcm->tcm__pad2 = 0;
tcm->tcm_ifindex = q->dev->ifindex;
tcm->tcm_parent = clid;
tcm->tcm_handle = q->handle;
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d43e3b8cbf6a..09453f997d8c 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1528,6 +1528,7 @@ static __inline__ int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl)
opt.strategy = cl->ovl_strategy;
opt.priority2 = cl->priority2+1;
+ opt.pad = 0;
opt.penalty = (cl->penalty*1000)/HZ;
RTA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt);
return skb->len;
@@ -1563,6 +1564,8 @@ static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl)
if (cl->police) {
opt.police = cl->police;
+ opt.__res1 = 0;
+ opt.__res2 = 0;
RTA_PUT(skb, TCA_CBQ_POLICE, sizeof(opt), &opt);
}
return skb->len;
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 2ec0320fac3b..c44bf4165c6e 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -102,9 +102,9 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
/* Set up the base timeout information. */
ep->timeouts[SCTP_EVENT_TIMEOUT_NONE] = 0;
ep->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] =
- SCTP_DEFAULT_TIMEOUT_T1_COOKIE;
+ msecs_to_jiffies(sp->rtoinfo.srto_initial);
ep->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] =
- SCTP_DEFAULT_TIMEOUT_T1_INIT;
+ msecs_to_jiffies(sp->rtoinfo.srto_initial);
ep->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] =
msecs_to_jiffies(sp->rtoinfo.srto_initial);
ep->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] = 0;
@@ -117,12 +117,9 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
ep->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]
= 5 * msecs_to_jiffies(sp->rtoinfo.srto_max);
- ep->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] =
- SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
- ep->timeouts[SCTP_EVENT_TIMEOUT_SACK] =
- SCTP_DEFAULT_TIMEOUT_SACK;
- ep->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] =
- sp->autoclose * HZ;
+ ep->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0;
+ ep->timeouts[SCTP_EVENT_TIMEOUT_SACK] = sctp_sack_timeout;
+ ep->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;
/* Use SCTP specific send buffer space queues. */
ep->sndbuf_policy = sctp_sndbuf_policy;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 5135e1a25d25..e7f37faba7c0 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1050,7 +1050,10 @@ SCTP_STATIC __init int sctp_init(void)
sctp_sndbuf_policy = 0;
/* HB.interval - 30 seconds */
- sctp_hb_interval = 30 * HZ;
+ sctp_hb_interval = SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
+
+ /* delayed SACK timeout */
+ sctp_sack_timeout = SCTP_DEFAULT_TIMEOUT_SACK;
/* Implementation specific variables. */
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 058189684c7c..86073df418f5 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -92,6 +92,17 @@ static sctp_disposition_t sctp_sf_shut_8_4_5(const struct sctp_endpoint *ep,
sctp_cmd_seq_t *commands);
static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk);
+static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
+ __u16 error,
+ const struct sctp_association *asoc,
+ struct sctp_transport *transport);
+
+static sctp_disposition_t sctp_sf_violation_chunklen(
+ const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const sctp_subtype_t type,
+ void *arg,
+ sctp_cmd_seq_t *commands);
/* Small helper function that checks if the chunk length
* is of the appropriate length. The 'required_length' argument
@@ -2328,7 +2339,7 @@ sctp_disposition_t sctp_sf_cookie_echoed_abort(const struct sctp_endpoint *ep,
*
* This is common code called by several sctp_sf_*_abort() functions above.
*/
-sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
+static sctp_disposition_t sctp_stop_t1_and_abort(sctp_cmd_seq_t *commands,
__u16 error,
const struct sctp_association *asoc,
struct sctp_transport *transport)
@@ -3687,7 +3698,8 @@ sctp_disposition_t sctp_sf_violation(const struct sctp_endpoint *ep,
*
* Generate an ABORT chunk and terminate the association.
*/
-sctp_disposition_t sctp_sf_violation_chunklen(const struct sctp_endpoint *ep,
+static sctp_disposition_t sctp_sf_violation_chunklen(
+ const struct sctp_endpoint *ep,
const struct sctp_association *asoc,
const sctp_subtype_t type,
void *arg,
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index 7fc31849312b..dc4893474f18 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -47,6 +47,8 @@
static ctl_handler sctp_sysctl_jiffies_ms;
static long rto_timer_min = 1;
static long rto_timer_max = 86400000; /* One day */
+static long sack_timer_min = 1;
+static long sack_timer_max = 500;
static ctl_table sctp_table[] = {
{
@@ -187,6 +189,17 @@ static ctl_table sctp_table[] = {
.mode = 0644,
.proc_handler = &proc_dointvec
},
+ {
+ .ctl_name = NET_SCTP_SACK_TIMEOUT,
+ .procname = "sack_timeout",
+ .data = &sctp_sack_timeout,
+ .maxlen = sizeof(long),
+ .mode = 0644,
+ .proc_handler = &proc_doulongvec_ms_jiffies_minmax,
+ .strategy = &sctp_sysctl_jiffies_ms,
+ .extra1 = &sack_timer_min,
+ .extra2 = &sack_timer_max,
+ },
{ .ctl_name = 0 }
};
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 0ec0fde6e6c5..a63b69179607 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -103,7 +103,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
/* Set up the heartbeat timer. */
init_timer(&peer->hb_timer);
- peer->hb_interval = SCTP_DEFAULT_TIMEOUT_HEARTBEAT;
peer->hb_timer.function = sctp_generate_heartbeat_event;
peer->hb_timer.data = (unsigned long)peer;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 32e8acbc60fe..62a073495276 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -41,6 +41,7 @@ EXPORT_SYMBOL(rpc_release_task);
/* RPC client functions */
EXPORT_SYMBOL(rpc_create_client);
+EXPORT_SYMBOL(rpc_new_client);
EXPORT_SYMBOL(rpc_clone_client);
EXPORT_SYMBOL(rpc_bind_new_program);
EXPORT_SYMBOL(rpc_destroy_client);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 05907035bc96..56db8f13e6cb 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1185,8 +1185,8 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
arg->page_len = (pages-2)*PAGE_SIZE;
arg->len = (pages-1)*PAGE_SIZE;
arg->tail[0].iov_len = 0;
-
- try_to_freeze(PF_FREEZE);
+
+ try_to_freeze();
if (signalled())
return -EINTR;
@@ -1227,7 +1227,7 @@ svc_recv(struct svc_serv *serv, struct svc_rqst *rqstp, long timeout)
schedule_timeout(timeout);
- try_to_freeze(PF_FREEZE);
+ try_to_freeze();
spin_lock_bh(&serv->sv_lock);
remove_wait_queue(&rqstp->rq_wait, &wait);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index eca92405948f..269f217918a3 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -970,7 +970,7 @@ tcp_read_request(struct rpc_xprt *xprt, skb_reader_t *desc)
goto out;
}
- dprintk("RPC: XID %08x read %u bytes\n",
+ dprintk("RPC: XID %08x read %Zd bytes\n",
ntohl(xprt->tcp_xid), r);
dprintk("RPC: xprt = %p, tcp_copied = %lu, tcp_offset = %u, tcp_reclen = %u\n",
xprt, xprt->tcp_copied, xprt->tcp_offset, xprt->tcp_reclen);
@@ -1006,7 +1006,7 @@ tcp_read_discard(struct rpc_xprt *xprt, skb_reader_t *desc)
desc->count -= len;
desc->offset += len;
xprt->tcp_offset += len;
- dprintk("RPC: discarded %u bytes\n", len);
+ dprintk("RPC: discarded %Zu bytes\n", len);
tcp_check_recm(xprt);
}