summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c30
-rw-r--r--net/ipv4/fib_frontend.c112
-rw-r--r--net/ipv4/fib_lookup.h3
-rw-r--r--net/ipv4/fib_semantics.c47
-rw-r--r--net/ipv4/fib_trie.c14
-rw-r--r--net/ipv4/route.c8
-rw-r--r--net/ipv4/tcp_input.c22
7 files changed, 166 insertions, 70 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 6d85800daeb7..5345b0bee6df 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -64,6 +64,8 @@
#include <net/rtnetlink.h>
#include <net/net_namespace.h>
+#include "fib_lookup.h"
+
static struct ipv4_devconf ipv4_devconf = {
.data = {
[IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1,
@@ -151,6 +153,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
break;
}
}
+ if (!result) {
+ struct flowi4 fl4 = { .daddr = addr };
+ struct fib_result res = { 0 };
+ struct fib_table *local;
+
+ /* Fallback to FIB local table so that communication
+ * over loopback subnets work.
+ */
+ local = fib_get_table(net, RT_TABLE_LOCAL);
+ if (local &&
+ !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
+ res.type == RTN_LOCAL)
+ result = FIB_RES_DEV(res);
+ }
if (result && devref)
dev_hold(result);
rcu_read_unlock();
@@ -345,6 +361,17 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
}
}
+ /* On promotion all secondaries from subnet are changing
+ * the primary IP, we must remove all their routes silently
+ * and later to add them back with new prefsrc. Do this
+ * while all addresses are on the device list.
+ */
+ for (ifa = promote; ifa; ifa = ifa->ifa_next) {
+ if (ifa1->ifa_mask == ifa->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, ifa))
+ fib_del_ifaddr(ifa, ifa1);
+ }
+
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
@@ -364,6 +391,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);
if (promote) {
+ struct in_ifaddr *next_sec = promote->ifa_next;
if (prev_prom) {
prev_prom->ifa_next = promote->ifa_next;
@@ -375,7 +403,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid);
blocking_notifier_call_chain(&inetaddr_chain,
NETDEV_UP, promote);
- for (ifa = promote->ifa_next; ifa; ifa = ifa->ifa_next) {
+ for (ifa = next_sec; ifa; ifa = ifa->ifa_next) {
if (ifa1->ifa_mask != ifa->ifa_mask ||
!inet_ifa_match(ifa1->ifa_address, ifa))
continue;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a373a259253c..f116ce8f1b46 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -228,7 +228,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
if (res.type != RTN_LOCAL || !accept_local)
goto e_inval;
}
- *spec_dst = FIB_RES_PREFSRC(res);
+ *spec_dst = FIB_RES_PREFSRC(net, res);
fib_combine_itag(itag, &res);
dev_match = false;
@@ -258,7 +258,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
ret = 0;
if (fib_lookup(net, &fl4, &res) == 0) {
if (res.type == RTN_UNICAST) {
- *spec_dst = FIB_RES_PREFSRC(res);
+ *spec_dst = FIB_RES_PREFSRC(net, res);
ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
}
}
@@ -722,12 +722,17 @@ void fib_add_ifaddr(struct in_ifaddr *ifa)
}
}
-static void fib_del_ifaddr(struct in_ifaddr *ifa)
+/* Delete primary or secondary address.
+ * Optionally, on secondary address promotion consider the addresses
+ * from subnet iprim as deleted, even if they are in device list.
+ * In this case the secondary ifa can be in device list.
+ */
+void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
{
struct in_device *in_dev = ifa->ifa_dev;
struct net_device *dev = in_dev->dev;
struct in_ifaddr *ifa1;
- struct in_ifaddr *prim = ifa;
+ struct in_ifaddr *prim = ifa, *prim1 = NULL;
__be32 brd = ifa->ifa_address | ~ifa->ifa_mask;
__be32 any = ifa->ifa_address & ifa->ifa_mask;
#define LOCAL_OK 1
@@ -735,17 +740,26 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
#define BRD0_OK 4
#define BRD1_OK 8
unsigned ok = 0;
+ int subnet = 0; /* Primary network */
+ int gone = 1; /* Address is missing */
+ int same_prefsrc = 0; /* Another primary with same IP */
- if (!(ifa->ifa_flags & IFA_F_SECONDARY))
- fib_magic(RTM_DELROUTE,
- dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
- any, ifa->ifa_prefixlen, prim);
- else {
+ if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
if (prim == NULL) {
printk(KERN_WARNING "fib_del_ifaddr: bug: prim == NULL\n");
return;
}
+ if (iprim && iprim != prim) {
+ printk(KERN_WARNING "fib_del_ifaddr: bug: iprim != prim\n");
+ return;
+ }
+ } else if (!ipv4_is_zeronet(any) &&
+ (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) {
+ fib_magic(RTM_DELROUTE,
+ dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
+ any, ifa->ifa_prefixlen, prim);
+ subnet = 1;
}
/* Deletion is more complicated than add.
@@ -755,6 +769,49 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
*/
for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
+ if (ifa1 == ifa) {
+ /* promotion, keep the IP */
+ gone = 0;
+ continue;
+ }
+ /* Ignore IFAs from our subnet */
+ if (iprim && ifa1->ifa_mask == iprim->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, iprim))
+ continue;
+
+ /* Ignore ifa1 if it uses different primary IP (prefsrc) */
+ if (ifa1->ifa_flags & IFA_F_SECONDARY) {
+ /* Another address from our subnet? */
+ if (ifa1->ifa_mask == prim->ifa_mask &&
+ inet_ifa_match(ifa1->ifa_address, prim))
+ prim1 = prim;
+ else {
+ /* We reached the secondaries, so
+ * same_prefsrc should be determined.
+ */
+ if (!same_prefsrc)
+ continue;
+ /* Search new prim1 if ifa1 is not
+ * using the current prim1
+ */
+ if (!prim1 ||
+ ifa1->ifa_mask != prim1->ifa_mask ||
+ !inet_ifa_match(ifa1->ifa_address, prim1))
+ prim1 = inet_ifa_byprefix(in_dev,
+ ifa1->ifa_address,
+ ifa1->ifa_mask);
+ if (!prim1)
+ continue;
+ if (prim1->ifa_local != prim->ifa_local)
+ continue;
+ }
+ } else {
+ if (prim->ifa_local != ifa1->ifa_local)
+ continue;
+ prim1 = ifa1;
+ if (prim != prim1)
+ same_prefsrc = 1;
+ }
if (ifa->ifa_local == ifa1->ifa_local)
ok |= LOCAL_OK;
if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
@@ -763,19 +820,37 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa)
ok |= BRD1_OK;
if (any == ifa1->ifa_broadcast)
ok |= BRD0_OK;
+ /* primary has network specific broadcasts */
+ if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) {
+ __be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask;
+ __be32 any1 = ifa1->ifa_address & ifa1->ifa_mask;
+
+ if (!ipv4_is_zeronet(any1)) {
+ if (ifa->ifa_broadcast == brd1 ||
+ ifa->ifa_broadcast == any1)
+ ok |= BRD_OK;
+ if (brd == brd1 || brd == any1)
+ ok |= BRD1_OK;
+ if (any == brd1 || any == any1)
+ ok |= BRD0_OK;
+ }
+ }
}
if (!(ok & BRD_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
- if (!(ok & BRD1_OK))
- fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
- if (!(ok & BRD0_OK))
- fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
+ if (subnet && ifa->ifa_prefixlen < 31) {
+ if (!(ok & BRD1_OK))
+ fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
+ if (!(ok & BRD0_OK))
+ fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
+ }
if (!(ok & LOCAL_OK)) {
fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);
/* Check, that this local address finally disappeared. */
- if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
+ if (gone &&
+ inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) {
/* And the last, but not the least thing.
* We must flush stray FIB entries.
*
@@ -885,6 +960,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
{
struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
struct net_device *dev = ifa->ifa_dev->dev;
+ struct net *net = dev_net(dev);
switch (event) {
case NETDEV_UP:
@@ -892,12 +968,12 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
- fib_update_nh_saddrs(dev);
+ atomic_inc(&net->ipv4.dev_addr_genid);
rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
- fib_del_ifaddr(ifa);
- fib_update_nh_saddrs(dev);
+ fib_del_ifaddr(ifa, NULL);
+ atomic_inc(&net->ipv4.dev_addr_genid);
if (ifa->ifa_dev->ifa_list == NULL) {
/* Last address was deleted from this interface.
* Disable IP.
@@ -915,6 +991,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
{
struct net_device *dev = ptr;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
+ struct net *net = dev_net(dev);
if (event == NETDEV_UNREGISTER) {
fib_disable_ip(dev, 2, -1);
@@ -932,6 +1009,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
+ atomic_inc(&net->ipv4.dev_addr_genid);
rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 4ec323875a02..af0f14aba169 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -10,7 +10,6 @@ struct fib_alias {
struct fib_info *fa_info;
u8 fa_tos;
u8 fa_type;
- u8 fa_scope;
u8 fa_state;
struct rcu_head rcu;
};
@@ -29,7 +28,7 @@ extern void fib_release_info(struct fib_info *);
extern struct fib_info *fib_create_info(struct fib_config *cfg);
extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi);
extern int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
- u32 tb_id, u8 type, u8 scope, __be32 dst,
+ u32 tb_id, u8 type, __be32 dst,
int dst_len, u8 tos, struct fib_info *fi,
unsigned int);
extern void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 622ac4c95026..641a5a2a9f9c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -222,7 +222,7 @@ static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
unsigned int mask = (fib_info_hash_size - 1);
unsigned int val = fi->fib_nhs;
- val ^= fi->fib_protocol;
+ val ^= (fi->fib_protocol << 8) | fi->fib_scope;
val ^= (__force u32)fi->fib_prefsrc;
val ^= fi->fib_priority;
for_nexthops(fi) {
@@ -248,10 +248,11 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi)
if (fi->fib_nhs != nfi->fib_nhs)
continue;
if (nfi->fib_protocol == fi->fib_protocol &&
+ nfi->fib_scope == fi->fib_scope &&
nfi->fib_prefsrc == fi->fib_prefsrc &&
nfi->fib_priority == fi->fib_priority &&
memcmp(nfi->fib_metrics, fi->fib_metrics,
- sizeof(fi->fib_metrics)) == 0 &&
+ sizeof(u32) * RTAX_MAX) == 0 &&
((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 &&
(nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
return fi;
@@ -328,7 +329,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
goto errout;
err = fib_dump_info(skb, info->pid, seq, event, tb_id,
- fa->fa_type, fa->fa_scope, key, dst_len,
+ fa->fa_type, key, dst_len,
fa->fa_tos, fa->fa_info, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
@@ -695,6 +696,16 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
fib_info_hash_free(old_laddrhash, bytes);
}
+__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
+{
+ nh->nh_saddr = inet_select_addr(nh->nh_dev,
+ nh->nh_gw,
+ nh->nh_parent->fib_scope);
+ nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+
+ return nh->nh_saddr;
+}
+
struct fib_info *fib_create_info(struct fib_config *cfg)
{
int err;
@@ -753,6 +764,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
fi->fib_net = hold_net(net);
fi->fib_protocol = cfg->fc_protocol;
+ fi->fib_scope = cfg->fc_scope;
fi->fib_flags = cfg->fc_flags;
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
@@ -854,10 +866,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
}
change_nexthops(fi) {
- nexthop_nh->nh_cfg_scope = cfg->fc_scope;
- nexthop_nh->nh_saddr = inet_select_addr(nexthop_nh->nh_dev,
- nexthop_nh->nh_gw,
- nexthop_nh->nh_cfg_scope);
+ fib_info_update_nh_saddr(net, nexthop_nh);
} endfor_nexthops(fi)
link_it:
@@ -906,7 +915,7 @@ failure:
}
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
- u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
+ u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
struct fib_info *fi, unsigned int flags)
{
struct nlmsghdr *nlh;
@@ -928,7 +937,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
NLA_PUT_U32(skb, RTA_TABLE, tb_id);
rtm->rtm_type = type;
rtm->rtm_flags = fi->fib_flags;
- rtm->rtm_scope = scope;
+ rtm->rtm_scope = fi->fib_scope;
rtm->rtm_protocol = fi->fib_protocol;
if (rtm->rtm_dst_len)
@@ -1084,7 +1093,7 @@ void fib_select_default(struct fib_result *res)
list_for_each_entry_rcu(fa, fa_head, fa_list) {
struct fib_info *next_fi = fa->fa_info;
- if (fa->fa_scope != res->scope ||
+ if (next_fi->fib_scope != res->scope ||
fa->fa_type != RTN_UNICAST)
continue;
@@ -1128,24 +1137,6 @@ out:
return;
}
-void fib_update_nh_saddrs(struct net_device *dev)
-{
- struct hlist_head *head;
- struct hlist_node *node;
- struct fib_nh *nh;
- unsigned int hash;
-
- hash = fib_devindex_hashfn(dev->ifindex);
- head = &fib_info_devhash[hash];
- hlist_for_each_entry(nh, node, head, nh_hash) {
- if (nh->nh_dev != dev)
- continue;
- nh->nh_saddr = inet_select_addr(nh->nh_dev,
- nh->nh_gw,
- nh->nh_cfg_scope);
- }
-}
-
#ifdef CONFIG_IP_ROUTE_MULTIPATH
/*
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 3d28a35c2e1a..90a3ff605591 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1245,7 +1245,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
if (fa->fa_info->fib_priority != fi->fib_priority)
break;
if (fa->fa_type == cfg->fc_type &&
- fa->fa_scope == cfg->fc_scope &&
fa->fa_info == fi) {
fa_match = fa;
break;
@@ -1271,7 +1270,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_tos = fa->fa_tos;
new_fa->fa_info = fi;
new_fa->fa_type = cfg->fc_type;
- new_fa->fa_scope = cfg->fc_scope;
state = fa->fa_state;
new_fa->fa_state = state & ~FA_S_ACCESSED;
@@ -1308,7 +1306,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg)
new_fa->fa_info = fi;
new_fa->fa_tos = tos;
new_fa->fa_type = cfg->fc_type;
- new_fa->fa_scope = cfg->fc_scope;
new_fa->fa_state = 0;
/*
* Insert new entry to the list.
@@ -1362,7 +1359,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
continue;
- if (fa->fa_scope < flp->flowi4_scope)
+ if (fa->fa_info->fib_scope < flp->flowi4_scope)
continue;
fib_alias_accessed(fa);
err = fib_props[fa->fa_type].error;
@@ -1388,7 +1385,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l,
res->prefixlen = plen;
res->nh_sel = nhsel;
res->type = fa->fa_type;
- res->scope = fa->fa_scope;
+ res->scope = fa->fa_info->fib_scope;
res->fi = fi;
res->table = tb;
res->fa_head = &li->falh;
@@ -1664,7 +1661,9 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg)
if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) &&
(cfg->fc_scope == RT_SCOPE_NOWHERE ||
- fa->fa_scope == cfg->fc_scope) &&
+ fa->fa_info->fib_scope == cfg->fc_scope) &&
+ (!cfg->fc_prefsrc ||
+ fi->fib_prefsrc == cfg->fc_prefsrc) &&
(!cfg->fc_protocol ||
fi->fib_protocol == cfg->fc_protocol) &&
fib_nh_match(cfg, fi) == 0) {
@@ -1861,7 +1860,6 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah,
RTM_NEWROUTE,
tb->tb_id,
fa->fa_type,
- fa->fa_scope,
xkey,
plen,
fa->fa_tos,
@@ -2382,7 +2380,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v)
seq_indent(seq, iter->depth+1);
seq_printf(seq, " /%d %s %s", li->plen,
rtn_scope(buf1, sizeof(buf1),
- fa->fa_scope),
+ fa->fa_info->fib_scope),
rtn_type(buf2, sizeof(buf2),
fa->fa_type));
if (fa->fa_tos)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 870b5182ddd8..4b0c81180804 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1593,8 +1593,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
rt->rt_peer_genid = rt_peer_genid();
}
check_peer_pmtu(dst, peer);
-
- inet_putpeer(peer);
}
}
@@ -1720,7 +1718,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt)
rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
- src = FIB_RES_PREFSRC(res);
+ src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
else
src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
RT_SCOPE_UNIVERSE);
@@ -2617,7 +2615,7 @@ static struct rtable *ip_route_output_slow(struct net *net,
fib_select_default(&res);
if (!fl4.saddr)
- fl4.saddr = FIB_RES_PREFSRC(res);
+ fl4.saddr = FIB_RES_PREFSRC(net, res);
dev_out = FIB_RES_DEV(res);
fl4.flowi4_oif = dev_out->ifindex;
@@ -3221,6 +3219,8 @@ static __net_init int rt_genid_init(struct net *net)
{
get_random_bytes(&net->ipv4.rt_genid,
sizeof(net->ipv4.rt_genid));
+ get_random_bytes(&net->ipv4.dev_addr_genid,
+ sizeof(net->ipv4.dev_addr_genid));
return 0;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index da782e7ab16d..bef9f04c22ba 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2659,7 +2659,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
#define DBGUNDO(x...) do { } while (0)
#endif
-static void tcp_undo_cwr(struct sock *sk, const int undo)
+static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2671,14 +2671,13 @@ static void tcp_undo_cwr(struct sock *sk, const int undo)
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
- if (undo && tp->prior_ssthresh > tp->snd_ssthresh) {
+ if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
} else {
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
- tcp_moderate_cwnd(tp);
tp->snd_cwnd_stamp = tcp_time_stamp;
}
@@ -2699,7 +2698,7 @@ static int tcp_try_undo_recovery(struct sock *sk)
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
@@ -2726,7 +2725,7 @@ static void tcp_try_undo_dsack(struct sock *sk)
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
tp->undo_marker = 0;
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
}
@@ -2779,7 +2778,7 @@ static int tcp_try_undo_partial(struct sock *sk, int acked)
tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
DBGUNDO(sk, "Hoe");
- tcp_undo_cwr(sk, 0);
+ tcp_undo_cwr(sk, false);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
/* So... Do not make Hoe's retransmit yet.
@@ -2808,7 +2807,7 @@ static int tcp_try_undo_loss(struct sock *sk)
DBGUNDO(sk, "partial loss");
tp->lost_out = 0;
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
inet_csk(sk)->icsk_retransmits = 0;
tp->undo_marker = 0;
@@ -2822,8 +2821,11 @@ static int tcp_try_undo_loss(struct sock *sk)
static inline void tcp_complete_cwr(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
- tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
- tp->snd_cwnd_stamp = tcp_time_stamp;
+ /* Do not moderate cwnd if it's already undone in cwr or recovery */
+ if (tp->undo_marker && tp->snd_cwnd > tp->snd_ssthresh) {
+ tp->snd_cwnd = tp->snd_ssthresh;
+ tp->snd_cwnd_stamp = tcp_time_stamp;
+ }
tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR);
}
@@ -3494,7 +3496,7 @@ static void tcp_undo_spur_to_response(struct sock *sk, int flag)
if (flag & FLAG_ECE)
tcp_ratehalving_spur_to_response(sk);
else
- tcp_undo_cwr(sk, 1);
+ tcp_undo_cwr(sk, true);
}
/* F-RTO spurious RTO detection algorithm (RFC4138)
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-05 14:21:21 +0000