summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c18
-rw-r--r--net/ipv4/inet_fragment.c3
-rw-r--r--net/ipv4/ip_fragment.c1
-rw-r--r--net/ipv4/ip_output.c25
-rw-r--r--net/ipv4/ip_vti.c14
-rw-r--r--net/ipv4/sysctl_net_ipv4.c85
-rw-r--r--net/ipv4/tcp.c12
-rw-r--r--net/ipv4/tcp_input.c4
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_memcontrol.c90
-rw-r--r--net/ipv4/tcp_metrics.c5
-rw-r--r--net/ipv4/tcp_offload.c1
-rw-r--r--net/ipv4/tcp_output.c12
-rw-r--r--net/ipv4/tcp_timer.c6
-rw-r--r--net/ipv4/xfrm4_policy.c1
15 files changed, 95 insertions, 183 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9433a6186f54..09d78d4a3cff 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1251,8 +1251,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
struct sk_buff *segs = ERR_PTR(-EINVAL);
const struct net_offload *ops;
unsigned int offset = 0;
+ bool udpfrag, encap;
struct iphdr *iph;
- bool tunnel;
int proto;
int nhoff;
int ihl;
@@ -1265,6 +1265,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_IPIP |
+ SKB_GSO_SIT |
SKB_GSO_TCPV6 |
SKB_GSO_UDP_TUNNEL |
SKB_GSO_MPLS |
@@ -1289,8 +1290,8 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
goto out;
__skb_pull(skb, ihl);
- tunnel = SKB_GSO_CB(skb)->encap_level > 0;
- if (tunnel)
+ encap = SKB_GSO_CB(skb)->encap_level > 0;
+ if (encap)
features = skb->dev->hw_enc_features & netif_skb_features(skb);
SKB_GSO_CB(skb)->encap_level += ihl;
@@ -1305,24 +1306,23 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
if (IS_ERR_OR_NULL(segs))
goto out;
+ udpfrag = !!skb->encapsulation && proto == IPPROTO_UDP;
skb = segs;
do {
iph = (struct iphdr *)(skb_mac_header(skb) + nhoff);
- if (!tunnel && proto == IPPROTO_UDP) {
+ if (udpfrag) {
iph->id = htons(id);
iph->frag_off = htons(offset >> 3);
if (skb->next != NULL)
iph->frag_off |= htons(IP_MF);
offset += skb->len - nhoff - ihl;
- } else {
+ } else {
iph->id = htons(id++);
}
iph->tot_len = htons(skb->len - nhoff);
ip_send_check(iph);
- if (tunnel) {
+ if (encap)
skb_reset_inner_headers(skb);
- skb->encapsulation = 1;
- }
skb->network_header = (u8 *)iph - skb->head;
} while ((skb = skb->next));
@@ -1697,8 +1697,6 @@ static int __init inet_init(void)
ip_static_sysctl_init();
#endif
- tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
-
/*
* Add all the base protocols.
*/
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c5313a9c019b..bb075fc9a14f 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -93,9 +93,6 @@ void inet_frags_init(struct inet_frags *f)
}
rwlock_init(&f->lock);
- f->rnd = (u32) ((totalram_pages ^ (totalram_pages >> 7)) ^
- (jiffies ^ (jiffies >> 6)));
-
setup_timer(&f->secret_timer, inet_frag_secret_rebuild,
(unsigned long)f);
f->secret_timer.expires = jiffies + f->secret_interval;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b66910aaef4d..2481993a4970 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -106,6 +106,7 @@ struct ip4_create_arg {
static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot)
{
+ net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd));
return jhash_3words((__force u32)id << 16 | prot,
(__force u32)saddr, (__force u32)daddr,
ip4_frags.rnd) & (INETFRAGS_HASHSZ - 1);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 7d8357bb2ba6..51be64e18e32 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -772,15 +772,20 @@ static inline int ip_ufo_append_data(struct sock *sk,
/* initialize protocol header pointer */
skb->transport_header = skb->network_header + fragheaderlen;
- skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum = 0;
- /* specify the length of each IP datagram fragment */
- skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
- skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
__skb_queue_tail(queue, skb);
+ } else if (skb_is_gso(skb)) {
+ goto append;
}
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ /* specify the length of each IP datagram fragment */
+ skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen;
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+
+append:
return skb_append_datato_frags(sk, skb, getfrag, from,
(length - transhdrlen));
}
@@ -805,7 +810,7 @@ static int __ip_append_data(struct sock *sk,
int copy;
int err;
int offset = 0;
- unsigned int maxfraglen, fragheaderlen;
+ unsigned int maxfraglen, fragheaderlen, maxnonfragsize;
int csummode = CHECKSUM_NONE;
struct rtable *rt = (struct rtable *)cork->dst;
@@ -818,8 +823,10 @@ static int __ip_append_data(struct sock *sk,
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+ maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+ mtu : 0xFFFF;
- if (cork->length + length > 0xFFFF - fragheaderlen) {
+ if (cork->length + length > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
mtu-exthdrlen);
return -EMSGSIZE;
@@ -1117,7 +1124,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
int mtu;
int len;
int err;
- unsigned int maxfraglen, fragheaderlen, fraggap;
+ unsigned int maxfraglen, fragheaderlen, fraggap, maxnonfragsize;
if (inet->hdrincl)
return -EPERM;
@@ -1141,8 +1148,10 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
+ maxnonfragsize = (inet->pmtudisc >= IP_PMTUDISC_DO) ?
+ mtu : 0xFFFF;
- if (cork->length + size > 0xFFFF - fragheaderlen) {
+ if (cork->length + size > maxnonfragsize - fragheaderlen) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, mtu);
return -EMSGSIZE;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 91f69bc883fe..5d9c845d288a 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -61,8 +61,17 @@ static int vti_rcv(struct sk_buff *skb)
iph->saddr, iph->daddr, 0);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ u32 oldmark = skb->mark;
+ int ret;
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+ /* temporarily mark the skb with the tunnel o_key, to
+ * only match policies with this mark.
+ */
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+ ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+ skb->mark = oldmark;
+ if (!ret)
return -1;
tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -71,7 +80,6 @@ static int vti_rcv(struct sk_buff *skb)
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- skb->mark = 0;
secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
@@ -103,7 +111,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 4b161d5aba0b..d5b1390eebbe 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -200,49 +200,6 @@ static int proc_allowed_congestion_control(struct ctl_table *ctl,
return ret;
}
-static int ipv4_tcp_mem(struct ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int ret;
- unsigned long vec[3];
- struct net *net = current->nsproxy->net_ns;
-#ifdef CONFIG_MEMCG_KMEM
- struct mem_cgroup *memcg;
-#endif
-
- struct ctl_table tmp = {
- .data = &vec,
- .maxlen = sizeof(vec),
- .mode = ctl->mode,
- };
-
- if (!write) {
- ctl->data = &net->ipv4.sysctl_tcp_mem;
- return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
- }
-
- ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
- if (ret)
- return ret;
-
-#ifdef CONFIG_MEMCG_KMEM
- rcu_read_lock();
- memcg = mem_cgroup_from_task(current);
-
- tcp_prot_mem(memcg, vec[0], 0);
- tcp_prot_mem(memcg, vec[1], 1);
- tcp_prot_mem(memcg, vec[2], 2);
- rcu_read_unlock();
-#endif
-
- net->ipv4.sysctl_tcp_mem[0] = vec[0];
- net->ipv4.sysctl_tcp_mem[1] = vec[1];
- net->ipv4.sysctl_tcp_mem[2] = vec[2];
-
- return 0;
-}
-
static int proc_tcp_fastopen_key(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
@@ -557,6 +514,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec
},
{
+ .procname = "tcp_mem",
+ .maxlen = sizeof(sysctl_tcp_mem),
+ .data = &sysctl_tcp_mem,
+ .mode = 0644,
+ .proc_handler = proc_doulongvec_minmax,
+ },
+ {
.procname = "tcp_wmem",
.data = &sysctl_tcp_wmem,
.maxlen = sizeof(sysctl_tcp_wmem),
@@ -865,12 +829,6 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = ipv4_local_port_range,
},
- {
- .procname = "tcp_mem",
- .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem),
- .mode = 0644,
- .proc_handler = ipv4_tcp_mem,
- },
{ }
};
@@ -880,32 +838,15 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
table = ipv4_net_table;
if (!net_eq(net, &init_net)) {
+ int i;
+
table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
- table[0].data =
- &net->ipv4.sysctl_icmp_echo_ignore_all;
- table[1].data =
- &net->ipv4.sysctl_icmp_echo_ignore_broadcasts;
- table[2].data =
- &net->ipv4.sysctl_icmp_ignore_bogus_error_responses;
- table[3].data =
- &net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr;
- table[4].data =
- &net->ipv4.sysctl_icmp_ratelimit;
- table[5].data =
- &net->ipv4.sysctl_icmp_ratemask;
- table[6].data =
- &net->ipv4.sysctl_ping_group_range;
- table[7].data =
- &net->ipv4.sysctl_tcp_ecn;
- table[8].data =
- &net->ipv4.sysctl_local_ports.range;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
+ /* Update the variables to point into the current struct net */
+ for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++)
+ table[i].data += (void *)net - (void *)&init_net;
}
/*
@@ -922,8 +863,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
net->ipv4.sysctl_local_ports.range[0] = 32768;
net->ipv4.sysctl_local_ports.range[1] = 61000;
- tcp_init_mem(net);
-
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
if (net->ipv4.ipv4_hdr == NULL)
goto err_reg;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index be4b161802e8..8e8529d3c8c9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -288,9 +288,11 @@ int sysctl_tcp_min_tso_segs __read_mostly = 2;
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
+long sysctl_tcp_mem[3] __read_mostly;
int sysctl_tcp_wmem[3] __read_mostly;
int sysctl_tcp_rmem[3] __read_mostly;
+EXPORT_SYMBOL(sysctl_tcp_mem);
EXPORT_SYMBOL(sysctl_tcp_rmem);
EXPORT_SYMBOL(sysctl_tcp_wmem);
@@ -3097,13 +3099,13 @@ static int __init set_thash_entries(char *str)
}
__setup("thash_entries=", set_thash_entries);
-void tcp_init_mem(struct net *net)
+static void tcp_init_mem(void)
{
unsigned long limit = nr_free_buffer_pages() / 8;
limit = max(limit, 128UL);
- net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
- net->ipv4.sysctl_tcp_mem[1] = limit;
- net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+ sysctl_tcp_mem[0] = limit / 4 * 3;
+ sysctl_tcp_mem[1] = limit;
+ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
}
void __init tcp_init(void)
@@ -3165,7 +3167,7 @@ void __init tcp_init(void)
sysctl_tcp_max_orphans = cnt / 2;
sysctl_max_syn_backlog = max(128, cnt / 256);
- tcp_init_mem(&init_net);
+ tcp_init_mem();
/* Set per-socket limits to no more than 1/128 the pressure threshold */
limit = nr_free_buffer_pages() << (PAGE_SHIFT - 7);
max_wshare = min(4UL*1024*1024, limit);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb651a069a6c..b935397c703c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3338,7 +3338,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
@@ -5751,6 +5751,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on first data packet */
tp->lsndtime = tcp_time_stamp;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 114d1b748cbb..300ab2c93f29 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2749,6 +2749,7 @@ struct proto tcp_prot = {
.orphan_count = &tcp_orphan_count,
.memory_allocated = &tcp_memory_allocated,
.memory_pressure = &tcp_memory_pressure,
+ .sysctl_mem = sysctl_tcp_mem,
.sysctl_wmem = sysctl_tcp_wmem,
.sysctl_rmem = sysctl_tcp_rmem,
.max_header = MAX_TCP_HEADER,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 559d4ae6ebf4..03e9154f7e68 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -6,15 +6,10 @@
#include <linux/memcontrol.h>
#include <linux/module.h>
-static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
-{
- return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
-}
-
static void memcg_tcp_enter_memory_pressure(struct sock *sk)
{
if (sk->sk_cgrp->memory_pressure)
- *sk->sk_cgrp->memory_pressure = 1;
+ sk->sk_cgrp->memory_pressure = 1;
}
EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
@@ -27,34 +22,24 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
*/
struct res_counter *res_parent = NULL;
struct cg_proto *cg_proto, *parent_cg;
- struct tcp_memcontrol *tcp;
struct mem_cgroup *parent = parent_mem_cgroup(memcg);
- struct net *net = current->nsproxy->net_ns;
cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto)
return 0;
- tcp = tcp_from_cgproto(cg_proto);
-
- tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
- tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
- tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
- tcp->tcp_memory_pressure = 0;
+ cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0];
+ cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1];
+ cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2];
+ cg_proto->memory_pressure = 0;
+ cg_proto->memcg = memcg;
parent_cg = tcp_prot.proto_cgroup(parent);
if (parent_cg)
- res_parent = parent_cg->memory_allocated;
-
- res_counter_init(&tcp->tcp_memory_allocated, res_parent);
- percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
+ res_parent = &parent_cg->memory_allocated;
- cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
- cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
- cg_proto->sysctl_mem = tcp->tcp_prot_mem;
- cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
- cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
- cg_proto->memcg = memcg;
+ res_counter_init(&cg_proto->memory_allocated, res_parent);
+ percpu_counter_init(&cg_proto->sockets_allocated, 0);
return 0;
}
@@ -63,21 +48,17 @@ EXPORT_SYMBOL(tcp_init_cgroup);
void tcp_destroy_cgroup(struct mem_cgroup *memcg)
{
struct cg_proto *cg_proto;
- struct tcp_memcontrol *tcp;
cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto)
return;
- tcp = tcp_from_cgproto(cg_proto);
- percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+ percpu_counter_destroy(&cg_proto->sockets_allocated);
}
EXPORT_SYMBOL(tcp_destroy_cgroup);
static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
{
- struct net *net = current->nsproxy->net_ns;
- struct tcp_memcontrol *tcp;
struct cg_proto *cg_proto;
u64 old_lim;
int i;
@@ -90,16 +71,14 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
if (val > RES_COUNTER_MAX)
val = RES_COUNTER_MAX;
- tcp = tcp_from_cgproto(cg_proto);
-
- old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
- ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
+ old_lim = res_counter_read_u64(&cg_proto->memory_allocated, RES_LIMIT);
+ ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
if (ret)
return ret;
for (i = 0; i < 3; i++)
- tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
- net->ipv4.sysctl_tcp_mem[i]);
+ cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+ sysctl_tcp_mem[i]);
if (val == RES_COUNTER_MAX)
clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
@@ -156,28 +135,24 @@ static int tcp_cgroup_write(struct cgroup_subsys_state *css, struct cftype *cft,
static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
{
- struct tcp_memcontrol *tcp;
struct cg_proto *cg_proto;
cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto)
return default_val;
- tcp = tcp_from_cgproto(cg_proto);
- return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
+ return res_counter_read_u64(&cg_proto->memory_allocated, type);
}
static u64 tcp_read_usage(struct mem_cgroup *memcg)
{
- struct tcp_memcontrol *tcp;
struct cg_proto *cg_proto;
cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto)
return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
- tcp = tcp_from_cgproto(cg_proto);
- return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+ return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
}
static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
@@ -205,54 +180,25 @@ static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
static int tcp_cgroup_reset(struct cgroup_subsys_state *css, unsigned int event)
{
struct mem_cgroup *memcg;
- struct tcp_memcontrol *tcp;
struct cg_proto *cg_proto;
memcg = mem_cgroup_from_css(css);
cg_proto = tcp_prot.proto_cgroup(memcg);
if (!cg_proto)
return 0;
- tcp = tcp_from_cgproto(cg_proto);
switch (event) {
case RES_MAX_USAGE:
- res_counter_reset_max(&tcp->tcp_memory_allocated);
+ res_counter_reset_max(&cg_proto->memory_allocated);
break;
case RES_FAILCNT:
- res_counter_reset_failcnt(&tcp->tcp_memory_allocated);
+ res_counter_reset_failcnt(&cg_proto->memory_allocated);
break;
}
return 0;
}
-unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
-{
- struct tcp_memcontrol *tcp;
- struct cg_proto *cg_proto;
-
- cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
- if (!cg_proto)
- return 0;
-
- tcp = tcp_from_cgproto(cg_proto);
- return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
-}
-
-void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
-{
- struct tcp_memcontrol *tcp;
- struct cg_proto *cg_proto;
-
- cg_proto = tcp_prot.proto_cgroup(memcg);
- if (!cg_proto)
- return;
-
- tcp = tcp_from_cgproto(cg_proto);
-
- tcp->tcp_prot_mem[idx] = val;
-}
-
static struct cftype tcp_files[] = {
{
.name = "kmem.tcp.limit_in_bytes",
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4a2a84110dfb..2ab09cbae74d 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -671,8 +671,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
struct tcp_fastopen_metrics *tfom = &tm->tcpm_fastopen;
write_seqlock_bh(&fastopen_seqlock);
- tfom->mss = mss;
- if (cookie->len > 0)
+ if (mss)
+ tfom->mss = mss;
+ if (cookie && cookie->len > 0)
tfom->cookie = *cookie;
if (syn_lost) {
++tfom->syn_loss;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index dfc96b00673e..a7a5583eab04 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -57,6 +57,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
SKB_GSO_TCPV6 |
SKB_GSO_GRE |
SKB_GSO_IPIP |
+ SKB_GSO_SIT |
SKB_GSO_MPLS |
SKB_GSO_UDP_TUNNEL |
0) ||
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ce7c4d9d9195..672854664ff5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -986,8 +986,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
- if (skb->len <= mss_now || !sk_can_gso(sk) ||
- skb->ip_summed == CHECKSUM_NONE) {
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
+ if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
* non-TSO case.
*/
@@ -1067,9 +1069,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -2344,6 +2344,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index af07b5b23ebf..64f0354c84c7 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -156,12 +156,16 @@ static bool retransmits_timed_out(struct sock *sk,
static int tcp_write_timeout(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
+ struct tcp_sock *tp = tcp_sk(sk);
int retry_until;
bool do_reset, syn_set = false;
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
- if (icsk->icsk_retransmits)
+ if (icsk->icsk_retransmits) {
dst_negative_advice(sk);
+ if (tp->syn_fastopen || tp->syn_data)
+ tcp_fastopen_cache_set(sk, 0, NULL, true);
+ }
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
syn_set = true;
} else {
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 9a459be24af7..ccde54248c8c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -107,6 +107,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
memset(fl4, 0, sizeof(struct flowi4));
fl4->flowi4_mark = skb->mark;
+ fl4->flowi4_oif = skb_dst(skb)->dev->ifindex;
if (!ip_is_fragment(iph)) {
switch (iph->protocol) {
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-08 19:34:25 +0000