aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c2
-rw-r--r--net/ipv4/cipso_ipv4.c39
-rw-r--r--net/ipv4/esp4.c13
-rw-r--r--net/ipv4/fib_frontend.c12
-rw-r--r--net/ipv4/icmp.c1
-rw-r--r--net/ipv4/ip_gre.c14
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_lblcr.c76
-rw-r--r--net/ipv4/ipvs/ip_vs_sync.c5
-rw-r--r--net/ipv4/ipvs/ip_vs_xmit.c2
-rw-r--r--net/ipv4/netfilter/Kconfig4
-rw-r--r--net/ipv4/proc.c10
-rw-r--r--net/ipv4/tcp.c2
-rw-r--r--net/ipv4/tcp_input.c61
-rw-r--r--net/ipv4/tcp_ipv4.c15
-rw-r--r--net/ipv4/tcp_vegas.c37
-rw-r--r--net/ipv4/udp.c2
18 files changed, 118 insertions, 181 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 621b128..d2f22e7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -323,7 +323,7 @@ lookup_protocol:
BUG_TRAP(answer_prot->slab != NULL);
err = -ENOBUFS;
- sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot, 1);
+ sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
if (sk == NULL)
goto out;
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 805a78e6..f18e88b 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -504,22 +504,16 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def)
INIT_RCU_HEAD(&doi_def->rcu);
INIT_LIST_HEAD(&doi_def->dom_list);
- rcu_read_lock();
- if (cipso_v4_doi_search(doi_def->doi) != NULL)
- goto doi_add_failure_rlock;
spin_lock(&cipso_v4_doi_list_lock);
if (cipso_v4_doi_search(doi_def->doi) != NULL)
- goto doi_add_failure_slock;
+ goto doi_add_failure;
list_add_tail_rcu(&doi_def->list, &cipso_v4_doi_list);
spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
return 0;
-doi_add_failure_slock:
+doi_add_failure:
spin_unlock(&cipso_v4_doi_list_lock);
-doi_add_failure_rlock:
- rcu_read_unlock();
return -EEXIST;
}
@@ -543,29 +537,23 @@ int cipso_v4_doi_remove(u32 doi,
struct cipso_v4_doi *doi_def;
struct cipso_v4_domhsh_entry *dom_iter;
- rcu_read_lock();
- if (cipso_v4_doi_search(doi) != NULL) {
- spin_lock(&cipso_v4_doi_list_lock);
- doi_def = cipso_v4_doi_search(doi);
- if (doi_def == NULL) {
- spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
- return -ENOENT;
- }
+ spin_lock(&cipso_v4_doi_list_lock);
+ doi_def = cipso_v4_doi_search(doi);
+ if (doi_def != NULL) {
doi_def->valid = 0;
list_del_rcu(&doi_def->list);
spin_unlock(&cipso_v4_doi_list_lock);
+ rcu_read_lock();
list_for_each_entry_rcu(dom_iter, &doi_def->dom_list, list)
if (dom_iter->valid)
netlbl_domhsh_remove(dom_iter->domain,
audit_info);
- cipso_v4_cache_invalidate();
rcu_read_unlock();
-
+ cipso_v4_cache_invalidate();
call_rcu(&doi_def->rcu, callback);
return 0;
}
- rcu_read_unlock();
+ spin_unlock(&cipso_v4_doi_list_lock);
return -ENOENT;
}
@@ -653,22 +641,19 @@ int cipso_v4_doi_domhsh_add(struct cipso_v4_doi *doi_def, const char *domain)
new_dom->valid = 1;
INIT_RCU_HEAD(&new_dom->rcu);
- rcu_read_lock();
spin_lock(&cipso_v4_doi_list_lock);
- list_for_each_entry_rcu(iter, &doi_def->dom_list, list)
+ list_for_each_entry(iter, &doi_def->dom_list, list)
if (iter->valid &&
((domain != NULL && iter->domain != NULL &&
strcmp(iter->domain, domain) == 0) ||
(domain == NULL && iter->domain == NULL))) {
spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
kfree(new_dom->domain);
kfree(new_dom);
return -EEXIST;
}
list_add_tail_rcu(&new_dom->list, &doi_def->dom_list);
spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
return 0;
}
@@ -689,9 +674,8 @@ int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
{
struct cipso_v4_domhsh_entry *iter;
- rcu_read_lock();
spin_lock(&cipso_v4_doi_list_lock);
- list_for_each_entry_rcu(iter, &doi_def->dom_list, list)
+ list_for_each_entry(iter, &doi_def->dom_list, list)
if (iter->valid &&
((domain != NULL && iter->domain != NULL &&
strcmp(iter->domain, domain) == 0) ||
@@ -699,13 +683,10 @@ int cipso_v4_doi_domhsh_remove(struct cipso_v4_doi *doi_def,
iter->valid = 0;
list_del_rcu(&iter->list);
spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
call_rcu(&iter->rcu, cipso_v4_doi_domhsh_free);
-
return 0;
}
spin_unlock(&cipso_v4_doi_list_lock);
- rcu_read_unlock();
return -ENOENT;
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 6b1a31a..c31bccb 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -3,7 +3,7 @@
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
-#include <asm/scatterlist.h>
+#include <linux/scatterlist.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
#include <linux/pfkeyv2.h>
@@ -110,7 +110,11 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
if (!sg)
goto unlock;
}
- skb_to_sgvec(skb, sg, esph->enc_data+esp->conf.ivlen-skb->data, clen);
+ sg_init_table(sg, nfrags);
+ skb_to_sgvec(skb, sg,
+ esph->enc_data +
+ esp->conf.ivlen -
+ skb->data, clen);
err = crypto_blkcipher_encrypt(&desc, sg, sg, clen);
if (unlikely(sg != &esp->sgbuf[0]))
kfree(sg);
@@ -201,7 +205,10 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
if (!sg)
goto out;
}
- skb_to_sgvec(skb, sg, sizeof(*esph) + esp->conf.ivlen, elen);
+ sg_init_table(sg, nfrags);
+ skb_to_sgvec(skb, sg,
+ sizeof(*esph) + esp->conf.ivlen,
+ elen);
err = crypto_blkcipher_decrypt(&desc, sg, sg, elen);
if (unlikely(sg != &esp->sgbuf[0]))
kfree(sg);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 78b514b..6012390 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -128,13 +128,14 @@ struct net_device * ip_dev_find(__be32 addr)
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
struct fib_result res;
struct net_device *dev = NULL;
+ struct fib_table *local_table;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
- if (!ip_fib_local_table ||
- ip_fib_local_table->tb_lookup(ip_fib_local_table, &fl, &res))
+ local_table = fib_get_table(RT_TABLE_LOCAL);
+ if (!local_table || local_table->tb_lookup(local_table, &fl, &res))
return NULL;
if (res.type != RTN_LOCAL)
goto out;
@@ -152,6 +153,7 @@ unsigned inet_addr_type(__be32 addr)
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
struct fib_result res;
unsigned ret = RTN_BROADCAST;
+ struct fib_table *local_table;
if (ZERONET(addr) || BADCLASS(addr))
return RTN_BROADCAST;
@@ -162,10 +164,10 @@ unsigned inet_addr_type(__be32 addr)
res.r = NULL;
#endif
- if (ip_fib_local_table) {
+ local_table = fib_get_table(RT_TABLE_LOCAL);
+ if (local_table) {
ret = RTN_UNICAST;
- if (!ip_fib_local_table->tb_lookup(ip_fib_local_table,
- &fl, &res)) {
+ if (!local_table->tb_lookup(local_table, &fl, &res)) {
ret = res.type;
fib_res_put(&res);
}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 272c69e..233de06 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1104,5 +1104,4 @@ void __init icmp_init(struct net_proto_family *ops)
EXPORT_SYMBOL(icmp_err_convert);
EXPORT_SYMBOL(icmp_send);
EXPORT_SYMBOL(icmp_statistics);
-EXPORT_SYMBOL(icmpmsg_statistics);
EXPORT_SYMBOL(xrlim_allow);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f151900..02b02a8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -674,7 +674,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
- int max_headroom; /* The extra header space needed */
+ unsigned int max_headroom; /* The extra header space needed */
int gre_hlen;
__be32 dst;
int mtu;
@@ -1033,7 +1033,6 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
return 0;
}
-#ifdef CONFIG_NET_IPGRE_BROADCAST
/* Nice toy. Unfortunately, useless in real life :-)
It allows to construct virtual multiprotocol broadcast "LAN"
over the Internet, provided multicast routing is tuned.
@@ -1092,10 +1091,19 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
return -t->hlen;
}
+static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+ struct iphdr *iph = (struct iphdr*) skb_mac_header(skb);
+ memcpy(haddr, &iph->saddr, 4);
+ return 4;
+}
+
static const struct header_ops ipgre_header_ops = {
.create = ipgre_header,
+ .parse = ipgre_header_parse,
};
+#ifdef CONFIG_NET_IPGRE_BROADCAST
static int ipgre_open(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
@@ -1197,6 +1205,8 @@ static int ipgre_tunnel_init(struct net_device *dev)
dev->stop = ipgre_close;
}
#endif
+ } else {
+ dev->header_ops = &ipgre_header_ops;
}
if (!tdev && tunnel->parms.link)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index f508835..e5f7dc2 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -161,7 +161,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
struct dst_entry *dst = skb->dst;
struct rtable *rt = (struct rtable *)dst;
struct net_device *dev = dst->dev;
- int hh_len = LL_RESERVED_SPACE(dev);
+ unsigned int hh_len = LL_RESERVED_SPACE(dev);
if (rt->rt_type == RTN_MULTICAST)
IP_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 5cd5bbe..8c2b2b0 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -515,7 +515,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
struct iphdr *iph; /* Our new IP header */
- int max_headroom; /* The extra header space needed */
+ unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c
index 6a1fec4..427b593 100644
--- a/net/ipv4/ipvs/ip_vs_lblcr.c
+++ b/net/ipv4/ipvs/ip_vs_lblcr.c
@@ -48,8 +48,6 @@
/* for sysctl */
#include <linux/fs.h>
#include <linux/sysctl.h>
-/* for proc_net_create/proc_net_remove */
-#include <linux/proc_fs.h>
#include <net/net_namespace.h>
#include <net/ip_vs.h>
@@ -547,71 +545,6 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
mod_timer(&tbl->periodic_timer, jiffies+CHECK_EXPIRE_INTERVAL);
}
-
-#ifdef CONFIG_IP_VS_LBLCR_DEBUG
-static struct ip_vs_lblcr_table *lblcr_table_list;
-
-/*
- * /proc/net/ip_vs_lblcr to display the mappings of
- * destination IP address <==> its serverSet
- */
-static int
-ip_vs_lblcr_getinfo(char *buffer, char **start, off_t offset, int length)
-{
- off_t pos=0, begin;
- int len=0, size;
- struct ip_vs_lblcr_table *tbl;
- unsigned long now = jiffies;
- int i;
- struct ip_vs_lblcr_entry *en;
-
- tbl = lblcr_table_list;
-
- size = sprintf(buffer, "LastTime Dest IP address Server set\n");
- pos += size;
- len += size;
-
- for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
- read_lock_bh(&tbl->lock);
- list_for_each_entry(en, &tbl->bucket[i], list) {
- char tbuf[16];
- struct ip_vs_dest_list *d;
-
- sprintf(tbuf, "%u.%u.%u.%u", NIPQUAD(en->addr));
- size = sprintf(buffer+len, "%8lu %-16s ",
- now-en->lastuse, tbuf);
-
- read_lock(&en->set.lock);
- for (d=en->set.list; d!=NULL; d=d->next) {
- size += sprintf(buffer+len+size,
- "%u.%u.%u.%u ",
- NIPQUAD(d->dest->addr));
- }
- read_unlock(&en->set.lock);
- size += sprintf(buffer+len+size, "\n");
- len += size;
- pos += size;
- if (pos <= offset)
- len=0;
- if (pos >= offset+length) {
- read_unlock_bh(&tbl->lock);
- goto done;
- }
- }
- read_unlock_bh(&tbl->lock);
- }
-
- done:
- begin = len - (pos - offset);
- *start = buffer + begin;
- len -= begin;
- if(len>length)
- len = length;
- return len;
-}
-#endif
-
-
static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
{
int i;
@@ -650,9 +583,6 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
tbl->periodic_timer.expires = jiffies+CHECK_EXPIRE_INTERVAL;
add_timer(&tbl->periodic_timer);
-#ifdef CONFIG_IP_VS_LBLCR_DEBUG
- lblcr_table_list = tbl;
-#endif
return 0;
}
@@ -843,18 +773,12 @@ static int __init ip_vs_lblcr_init(void)
{
INIT_LIST_HEAD(&ip_vs_lblcr_scheduler.n_list);
sysctl_header = register_sysctl_table(lblcr_root_table);
-#ifdef CONFIG_IP_VS_LBLCR_DEBUG
- proc_net_create(&init_net, "ip_vs_lblcr", 0, ip_vs_lblcr_getinfo);
-#endif
return register_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
}
static void __exit ip_vs_lblcr_cleanup(void)
{
-#ifdef CONFIG_IP_VS_LBLCR_DEBUG
- proc_net_remove(&init_net, "ip_vs_lblcr");
-#endif
unregister_sysctl_table(sysctl_header);
unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler);
}
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index c99f2a3..0d4d972 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -72,7 +72,6 @@ struct ip_vs_sync_thread_data {
int state;
};
-#define IP_VS_SYNC_CONN_TIMEOUT (3*60*HZ)
#define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn))
#define FULL_CONN_SIZE \
(sizeof(struct ip_vs_sync_conn) + sizeof(struct ip_vs_sync_conn_options))
@@ -284,6 +283,7 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
struct ip_vs_sync_conn *s;
struct ip_vs_sync_conn_options *opt;
struct ip_vs_conn *cp;
+ struct ip_vs_protocol *pp;
char *p;
int i;
@@ -342,7 +342,8 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen)
p += SIMPLE_CONN_SIZE;
atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]);
- cp->timeout = IP_VS_SYNC_CONN_TIMEOUT;
+ pp = ip_vs_proto_get(s->protocol);
+ cp->timeout = pp->timeout_table[cp->state];
ip_vs_conn_put(cp);
if (p > buffer+buflen) {
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index d0a92de..7c074e3 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -325,7 +325,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
__be16 df = old_iph->frag_off;
sk_buff_data_t old_transport_header = skb->transport_header;
struct iphdr *iph; /* Our new IP header */
- int max_headroom; /* The extra header space needed */
+ unsigned int max_headroom; /* The extra header space needed */
int mtu;
EnterFunction(10);
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index fa97947..9aca9c5 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -128,7 +128,7 @@ config IP_NF_MATCH_ADDRTYPE
eg. UNICAST, LOCAL, BROADCAST, ...
If you want to compile it as a module, say M here and read
- <file:Documentation/modules.txt>. If unsure, say `N'.
+ <file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
# `filter', generic and specific targets
config IP_NF_FILTER
@@ -371,7 +371,7 @@ config IP_NF_RAW
and OUTPUT chains.
If you want to compile it as a module, say M here and read
- <file:Documentation/modules.txt>. If unsure, say `N'.
+ <file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
# ARP tables
config IP_NF_ARPTABLES
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index fd16cb8..ffdccc0 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -121,14 +121,6 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_SENTINEL
};
-static const struct snmp_mib snmp4_icmp_list[] = {
- SNMP_MIB_ITEM("InMsgs", ICMP_MIB_INMSGS),
- SNMP_MIB_ITEM("InErrors", ICMP_MIB_INERRORS),
- SNMP_MIB_ITEM("OutMsgs", ICMP_MIB_OUTMSGS),
- SNMP_MIB_ITEM("OutErrors", ICMP_MIB_OUTERRORS),
- SNMP_MIB_SENTINEL
-};
-
static struct {
char *name;
int index;
@@ -312,7 +304,7 @@ static void icmp_put(struct seq_file *seq)
for (i=0; icmpmibmap[i].name != NULL; i++)
seq_printf(seq, " %lu",
snmp_fold_field((void **) icmpmsg_statistics,
- icmpmibmap[i].index));
+ icmpmibmap[i].index | 0x100));
}
/*
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2e6ad6d..c64072b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2453,7 +2453,7 @@ void __init tcp_init(void)
0,
&tcp_hashinfo.ehash_size,
NULL,
- 0);
+ thash_entries ? 0 : 512 * 1024);
tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size;
for (i = 0; i < tcp_hashinfo.ehash_size; i++) {
rwlock_init(&tcp_hashinfo.ehash[i].lock);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9288220..ca9590f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -103,7 +103,7 @@ int sysctl_tcp_abc __read_mostly;
#define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/
#define FLAG_ONLY_ORIG_SACKED 0x200 /* SACKs only non-rexmit sent before RTO */
#define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */
-#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained DSACK info */
+#define FLAG_DSACKING_ACK 0x800 /* SACK blocks contained D-SACK info */
#define FLAG_NONHEAD_RETRANS_ACKED 0x1000 /* Non-head rexmitted data was ACKed */
#define FLAG_ACKED (FLAG_DATA_ACKED|FLAG_SYN_ACKED)
@@ -866,7 +866,7 @@ static void tcp_disable_fack(struct tcp_sock *tp)
tp->rx_opt.sack_ok &= ~2;
}
-/* Take a notice that peer is sending DSACKs */
+/* Take a notice that peer is sending D-SACKs */
static void tcp_dsack_seen(struct tcp_sock *tp)
{
tp->rx_opt.sack_ok |= 4;
@@ -1058,7 +1058,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
*
* With D-SACK the lower bound is extended to cover sequence space below
* SND.UNA down to undo_marker, which is the last point of interest. Yet
- * again, DSACK block must not to go across snd_una (for the same reason as
+ * again, D-SACK block must not to go across snd_una (for the same reason as
* for the normal SACK blocks, explained above). But there all simplicity
* ends, TCP might receive valid D-SACKs below that. As long as they reside
* fully below undo_marker they do not affect behavior in anyway and can
@@ -1080,7 +1080,7 @@ static int tcp_is_sackblock_valid(struct tcp_sock *tp, int is_dsack,
if (!before(start_seq, tp->snd_nxt))
return 0;
- /* In outstanding window? ...This is valid exit for DSACKs too.
+ /* In outstanding window? ...This is valid exit for D-SACKs too.
* start_seq == snd_una is non-sensical (see comments above)
*/
if (after(start_seq, tp->snd_una))
@@ -1204,8 +1204,8 @@ static int tcp_check_dsack(struct tcp_sock *tp, struct sk_buff *ack_skb,
* which may fail and creates some hassle (caller must handle error case
* returns).
*/
-int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
- u32 start_seq, u32 end_seq)
+static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb,
+ u32 start_seq, u32 end_seq)
{
int in_sack, err;
unsigned int pkt_len;
@@ -1248,6 +1248,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
int cached_fack_count;
int i;
int first_sack_index;
+ int force_one_sack;
if (!tp->sacked_out) {
if (WARN_ON(tp->fackets_out))
@@ -1272,18 +1273,18 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
* if the only SACK change is the increase of the end_seq of
* the first block then only apply that SACK block
* and use retrans queue hinting otherwise slowpath */
- flag = 1;
+ force_one_sack = 1;
for (i = 0; i < num_sacks; i++) {
__be32 start_seq = sp[i].start_seq;
__be32 end_seq = sp[i].end_seq;
if (i == 0) {
if (tp->recv_sack_cache[i].start_seq != start_seq)
- flag = 0;
+ force_one_sack = 0;
} else {
if ((tp->recv_sack_cache[i].start_seq != start_seq) ||
(tp->recv_sack_cache[i].end_seq != end_seq))
- flag = 0;
+ force_one_sack = 0;
}
tp->recv_sack_cache[i].start_seq = start_seq;
tp->recv_sack_cache[i].end_seq = end_seq;
@@ -1295,7 +1296,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
}
first_sack_index = 0;
- if (flag)
+ if (force_one_sack)
num_sacks = 1;
else {
int j;
@@ -1321,9 +1322,6 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
}
}
- /* clear flag as used for different purpose in following code */
- flag = 0;
-
/* Use SACK fastpath hint if valid */
cached_skb = tp->fastpath_skb_hint;
cached_fack_count = tp->fastpath_cnt_hint;
@@ -1332,12 +1330,15 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
cached_fack_count = 0;
}
- for (i=0; i<num_sacks; i++, sp++) {
+ for (i = 0; i < num_sacks; i++) {
struct sk_buff *skb;
__u32 start_seq = ntohl(sp->start_seq);
__u32 end_seq = ntohl(sp->end_seq);
int fack_count;
int dup_sack = (found_dup_sack && (i == first_sack_index));
+ int next_dup = (found_dup_sack && (i+1 == first_sack_index));
+
+ sp++;
if (!tcp_is_sackblock_valid(tp, dup_sack, start_seq, end_seq)) {
if (dup_sack) {
@@ -1363,7 +1364,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
flag |= FLAG_DATA_LOST;
tcp_for_write_queue_from(skb, sk) {
- int in_sack;
+ int in_sack = 0;
u8 sacked;
if (skb == tcp_send_head(sk))
@@ -1382,7 +1383,23 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
+ dup_sack = (found_dup_sack && (i == first_sack_index));
+
+ /* Due to sorting DSACK may reside within this SACK block! */
+ if (next_dup) {
+ u32 dup_start = ntohl(sp->start_seq);
+ u32 dup_end = ntohl(sp->end_seq);
+
+ if (before(TCP_SKB_CB(skb)->seq, dup_end)) {
+ in_sack = tcp_match_skb_to_sack(sk, skb, dup_start, dup_end);
+ if (in_sack > 0)
+ dup_sack = 1;
+ }
+ }
+
+ /* DSACK info lost if out-of-mem, try SACK still */
+ if (in_sack <= 0)
+ in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, end_seq);
if (in_sack < 0)
break;
@@ -1615,7 +1632,7 @@ void tcp_enter_frto(struct sock *sk)
!icsk->icsk_retransmits)) {
tp->prior_ssthresh = tcp_current_ssthresh(sk);
/* Our state is too optimistic in ssthresh() call because cwnd
- * is not reduced until tcp_enter_frto_loss() when previous FRTO
+ * is not reduced until tcp_enter_frto_loss() when previous F-RTO
* recovery has not yet completed. Pattern would be this: RTO,
* Cumulative ACK, RTO (2xRTO for the same segment does not end
* up here twice).
@@ -1801,7 +1818,7 @@ void tcp_enter_loss(struct sock *sk, int how)
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
- /* Abort FRTO algorithm if one is in progress */
+ /* Abort F-RTO algorithm if one is in progress */
tp->frto_counter = 0;
}
@@ -1946,7 +1963,7 @@ static int tcp_time_to_recover(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
__u32 packets_out;
- /* Do not perform any recovery during FRTO algorithm */
+ /* Do not perform any recovery during F-RTO algorithm */
if (tp->frto_counter)
return 0;
@@ -2061,7 +2078,7 @@ static void tcp_update_scoreboard(struct sock *sk)
if (!tcp_skb_timedout(sk, skb))
break;
- if (!(TCP_SKB_CB(skb)->sacked&TCPCB_TAGBITS)) {
+ if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_SACKED_ACKED|TCPCB_LOST))) {
TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
tp->lost_out += tcp_skb_pcount(skb);
tcp_verify_retransmit_hint(tp, skb);
@@ -2962,7 +2979,7 @@ static int tcp_process_frto(struct sock *sk, int flag)
}
if (tp->frto_counter == 1) {
- /* Sending of the next skb must be allowed or no FRTO */
+ /* Sending of the next skb must be allowed or no F-RTO */
if (!tcp_send_head(sk) ||
after(TCP_SKB_CB(tcp_send_head(sk))->end_seq,
tp->snd_una + tp->snd_wnd)) {
@@ -3909,7 +3926,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list,
while (before(start, end)) {
struct sk_buff *nskb;
- int header = skb_headroom(skb);
+ unsigned int header = skb_headroom(skb);
int copy = SKB_MAX_ORDER(header, 0);
/* Too big header? This can happen with IPv6. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 38cf73a..eec02b2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -858,16 +858,16 @@ int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
u8 *newkey, u8 newkeylen)
{
/* Add Key to the list */
- struct tcp4_md5sig_key *key;
+ struct tcp_md5sig_key *key;
struct tcp_sock *tp = tcp_sk(sk);
struct tcp4_md5sig_key *keys;
- key = (struct tcp4_md5sig_key *)tcp_v4_md5_do_lookup(sk, addr);
+ key = tcp_v4_md5_do_lookup(sk, addr);
if (key) {
/* Pre-existing entry - just update that one. */
- kfree(key->base.key);
- key->base.key = newkey;
- key->base.keylen = newkeylen;
+ kfree(key->key);
+ key->key = newkey;
+ key->keylen = newkeylen;
} else {
struct tcp_md5sig_info *md5sig;
@@ -1055,6 +1055,9 @@ static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
bp->pad = 0;
bp->protocol = protocol;
bp->len = htons(tcplen);
+
+ sg_init_table(sg, 4);
+
sg_set_buf(&sg[block++], bp, sizeof(*bp));
nbytes += sizeof(*bp);
@@ -1080,6 +1083,8 @@ static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
sg_set_buf(&sg[block++], key->key, key->keylen);
nbytes += key->keylen;
+ __sg_mark_end(&sg[block - 1]);
+
/* Now store the Hash into the packet */
err = crypto_hash_init(desc);
if (err)
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index b49dedc..007304e 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -266,26 +266,25 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack,
*/
diff = (old_wnd << V_PARAM_SHIFT) - target_cwnd;
- if (tp->snd_cwnd <= tp->snd_ssthresh) {
- /* Slow start. */
- if (diff > gamma) {
- /* Going too fast. Time to slow down
- * and switch to congestion avoidance.
- */
- tp->snd_ssthresh = 2;
-
- /* Set cwnd to match the actual rate
- * exactly:
- * cwnd = (actual rate) * baseRTT
- * Then we add 1 because the integer
- * truncation robs us of full link
- * utilization.
- */
- tp->snd_cwnd = min(tp->snd_cwnd,
- (target_cwnd >>
- V_PARAM_SHIFT)+1);
+ if (diff > gamma && tp->snd_ssthresh > 2 ) {
+ /* Going too fast. Time to slow down
+ * and switch to congestion avoidance.
+ */
+ tp->snd_ssthresh = 2;
+
+ /* Set cwnd to match the actual rate
+ * exactly:
+ * cwnd = (actual rate) * baseRTT
+ * Then we add 1 because the integer
+ * truncation robs us of full link
+ * utilization.
+ */
+ tp->snd_cwnd = min(tp->snd_cwnd,
+ (target_cwnd >>
+ V_PARAM_SHIFT)+1);
- }
+ } else if (tp->snd_cwnd <= tp->snd_ssthresh) {
+ /* Slow start. */
tcp_slow_start(tp);
} else {
/* Congestion avoidance. */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 35d2b0e..4bc25b4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1152,7 +1152,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
- skb->dev->ifindex, udptable );
+ inet_iif(skb), udptable);
if (sk != NULL) {
int ret = udp_queue_rcv_skb(sk, skb);
generated by cgit v1.1 at 2025-08-16 02:38:38 +0000