summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig8
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/fou.c23
-rw-r--r--net/ipv4/inet_diag.c25
-rw-r--r--net/ipv4/ip_tunnel.c6
-rw-r--r--net/ipv4/raw.c21
-rw-r--r--net/ipv4/raw_diag.c262
-rw-r--r--net/ipv4/tcp_bbr.c32
-rw-r--r--net/ipv4/tcp_input.c8
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_metrics.c23
-rw-r--r--net/ipv4/udp.c149
12 files changed, 483 insertions, 81 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 300b06888fdf..28e051a8e847 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -430,6 +430,14 @@ config INET_UDP_DIAG
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
+config INET_RAW_DIAG
+ tristate "RAW: socket monitoring interface"
+ depends on INET_DIAG && (IPV6 || IPV6=n)
+ default n
+ ---help---
+ Support for RAW socket monitoring interface used by the ss tool.
+ If unsure, say Y.
+
config INET_DIAG_DESTROY
bool "INET: allow privileged process to administratively close sockets"
depends on INET_DIAG
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index bc6a6c8b9bcd..48af58a5686e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/
obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
+obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BBR) += tcp_bbr.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 030d1531e897..805f6607f8d9 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -622,14 +622,7 @@ static int fou_destroy(struct net *net, struct fou_cfg *cfg)
return err;
}
-static struct genl_family fou_nl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = 0,
- .name = FOU_GENL_NAME,
- .version = FOU_GENL_VERSION,
- .maxattr = FOU_ATTR_MAX,
- .netnsok = true,
-};
+static struct genl_family fou_nl_family;
static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
[FOU_ATTR_PORT] = { .type = NLA_U16, },
@@ -831,6 +824,17 @@ static const struct genl_ops fou_nl_ops[] = {
},
};
+static struct genl_family fou_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = FOU_GENL_NAME,
+ .version = FOU_GENL_VERSION,
+ .maxattr = FOU_ATTR_MAX,
+ .netnsok = true,
+ .module = THIS_MODULE,
+ .ops = fou_nl_ops,
+ .n_ops = ARRAY_SIZE(fou_nl_ops),
+};
+
size_t fou_encap_hlen(struct ip_tunnel_encap *e)
{
return sizeof(struct udphdr);
@@ -1086,8 +1090,7 @@ static int __init fou_init(void)
if (ret)
goto exit;
- ret = genl_register_family_with_ops(&fou_nl_family,
- fou_nl_ops);
+ ret = genl_register_family(&fou_nl_family);
if (ret < 0)
goto unregister;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index e4d16fc5bbb3..3b34024202d8 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -200,6 +200,15 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
+ /*
+ * RAW sockets might have user-defined protocols assigned,
+ * so report the one supplied on socket creation.
+ */
+ if (sk->sk_type == SOCK_RAW) {
+ if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
+ goto errout;
+ }
+
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
@@ -863,7 +872,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
s_num = num = cb->args[2];
if (cb->args[0] == 0) {
- if (!(idiag_states & TCPF_LISTEN))
+ if (!(idiag_states & TCPF_LISTEN) || r->id.idiag_dport)
goto skip_listen_ht;
for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
@@ -872,7 +881,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
num = 0;
ilb = &hashinfo->listening_hash[i];
- spin_lock_bh(&ilb->lock);
+ spin_lock(&ilb->lock);
sk_for_each(sk, &ilb->head) {
struct inet_sock *inet = inet_sk(sk);
@@ -892,26 +901,18 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
r->id.idiag_sport)
goto next_listen;
- if (r->id.idiag_dport ||
- cb->args[3] > 0)
- goto next_listen;
-
if (inet_csk_diag_dump(sk, skb, cb, r,
bc, net_admin) < 0) {
- spin_unlock_bh(&ilb->lock);
+ spin_unlock(&ilb->lock);
goto done;
}
next_listen:
- cb->args[3] = 0;
- cb->args[4] = 0;
++num;
}
- spin_unlock_bh(&ilb->lock);
+ spin_unlock(&ilb->lock);
s_num = 0;
- cb->args[3] = 0;
- cb->args[4] = 0;
}
skip_listen_ht:
cb->args[0] = 1;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5719d6ba0824..12a92e3349ed 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -358,6 +358,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
{
struct ip_tunnel *nt;
struct net_device *dev;
+ int t_hlen;
BUG_ON(!itn->fb_tunnel_dev);
dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms);
@@ -367,6 +368,9 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
dev->mtu = ip_tunnel_bind_dev(dev);
nt = netdev_priv(dev);
+ t_hlen = nt->hlen + sizeof(struct iphdr);
+ dev->min_mtu = ETH_MIN_MTU;
+ dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
ip_tunnel_add(itn, nt);
return nt;
}
@@ -929,7 +933,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
- if (new_mtu < 68)
+ if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
if (new_mtu > max_mtu) {
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index ecbe5a7c2d6d..d78d738fb172 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -89,9 +89,10 @@ struct raw_frag_vec {
int hlen;
};
-static struct raw_hashinfo raw_v4_hashinfo = {
+struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
int raw_hash_sk(struct sock *sk)
{
@@ -120,7 +121,7 @@ void raw_unhash_sk(struct sock *sk)
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);
-static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
unsigned short num, __be32 raddr, __be32 laddr, int dif)
{
sk_for_each_from(sk) {
@@ -136,6 +137,7 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v4_lookup);
/*
* 0 - deliver
@@ -912,6 +914,20 @@ static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg
}
#endif
+int raw_abort(struct sock *sk, int err)
+{
+ lock_sock(sk);
+
+ sk->sk_err = err;
+ sk->sk_error_report(sk);
+ udp_disconnect(sk, 0);
+
+ release_sock(sk);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(raw_abort);
+
struct proto raw_prot = {
.name = "RAW",
.owner = THIS_MODULE,
@@ -937,6 +953,7 @@ struct proto raw_prot = {
.compat_getsockopt = compat_raw_getsockopt,
.compat_ioctl = compat_raw_ioctl,
#endif
+ .diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c
new file mode 100644
index 000000000000..be930908bcf9
--- /dev/null
+++ b/net/ipv4/raw_diag.c
@@ -0,0 +1,262 @@
+#include <linux/module.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+#include <net/inet_sock.h>
+#include <net/raw.h>
+#include <net/rawv6.h>
+
+#ifdef pr_fmt
+# undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+static struct raw_hashinfo *
+raw_get_hashinfo(const struct inet_diag_req_v2 *r)
+{
+ if (r->sdiag_family == AF_INET) {
+ return &raw_v4_hashinfo;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (r->sdiag_family == AF_INET6) {
+ return &raw_v6_hashinfo;
+#endif
+ } else {
+ pr_warn_once("Unexpected inet family %d\n",
+ r->sdiag_family);
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+ }
+}
+
+/*
+ * Due to requirement of not breaking user API we can't simply
+ * rename @pad field in inet_diag_req_v2 structure, instead
+ * use helper to figure it out.
+ */
+
+static struct sock *raw_lookup(struct net *net, struct sock *from,
+ const struct inet_diag_req_v2 *req)
+{
+ struct inet_diag_req_raw *r = (void *)req;
+ struct sock *sk = NULL;
+
+ if (r->sdiag_family == AF_INET)
+ sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
+ r->id.idiag_dst[0],
+ r->id.idiag_src[0],
+ r->id.idiag_if);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
+ (const struct in6_addr *)r->id.idiag_src,
+ (const struct in6_addr *)r->id.idiag_dst,
+ r->id.idiag_if);
+#endif
+ return sk;
+}
+
+static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
+{
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct sock *sk = NULL, *s;
+ int slot;
+
+ if (IS_ERR(hashinfo))
+ return ERR_CAST(hashinfo);
+
+ read_lock(&hashinfo->lock);
+ for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
+ sk_for_each(s, &hashinfo->ht[slot]) {
+ sk = raw_lookup(net, s, r);
+ if (sk) {
+ /*
+ * Grab it and keep until we fill
+ * diag meaage to be reported, so
+ * caller should call sock_put then.
+ * We can do that because we're keeping
+ * hashinfo->lock here.
+ */
+ sock_hold(sk);
+ break;
+ }
+ }
+ }
+ read_unlock(&hashinfo->lock);
+
+ return sk ? sk : ERR_PTR(-ENOENT);
+}
+
+static int raw_diag_dump_one(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ const struct inet_diag_req_v2 *r)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *rep;
+ struct sock *sk;
+ int err;
+
+ sk = raw_sock_get(net, r);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ rep = nlmsg_new(sizeof(struct inet_diag_msg) +
+ sizeof(struct inet_diag_meminfo) + 64,
+ GFP_KERNEL);
+ if (!rep) {
+ sock_put(sk);
+ return -ENOMEM;
+ }
+
+ err = inet_sk_diag_fill(sk, NULL, rep, r,
+ sk_user_ns(NETLINK_CB(in_skb).sk),
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0, nlh,
+ netlink_net_capable(in_skb, CAP_NET_ADMIN));
+ sock_put(sk);
+
+ if (err < 0) {
+ kfree_skb(rep);
+ return err;
+ }
+
+ err = netlink_unicast(net->diag_nlsk, rep,
+ NETLINK_CB(in_skb).portid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+ return err;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
+ struct netlink_callback *cb,
+ const struct inet_diag_req_v2 *r,
+ struct nlattr *bc, bool net_admin)
+{
+ if (!inet_diag_bc_sk(bc, sk))
+ return 0;
+
+ return inet_sk_diag_fill(sk, NULL, skb, r,
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ cb->nlh, net_admin);
+}
+
+static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ const struct inet_diag_req_v2 *r, struct nlattr *bc)
+{
+ bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct net *net = sock_net(skb->sk);
+ int num, s_num, slot, s_slot;
+ struct sock *sk = NULL;
+
+ if (IS_ERR(hashinfo))
+ return;
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ read_lock(&hashinfo->lock);
+ for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) {
+ num = 0;
+
+ sk_for_each(sk, &hashinfo->ht[slot]) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (!net_eq(sock_net(sk), net))
+ continue;
+ if (num < s_num)
+ goto next;
+ if (sk->sk_family != r->sdiag_family)
+ goto next;
+ if (r->id.idiag_sport != inet->inet_sport &&
+ r->id.idiag_sport)
+ goto next;
+ if (r->id.idiag_dport != inet->inet_dport &&
+ r->id.idiag_dport)
+ goto next;
+ if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0)
+ goto out_unlock;
+next:
+ num++;
+ }
+ }
+
+out_unlock:
+ read_unlock(&hashinfo->lock);
+
+ cb->args[0] = slot;
+ cb->args[1] = num;
+}
+
+static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+ void *info)
+{
+ r->idiag_rqueue = sk_rmem_alloc_get(sk);
+ r->idiag_wqueue = sk_wmem_alloc_get(sk);
+}
+
+#ifdef CONFIG_INET_DIAG_DESTROY
+static int raw_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *r)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sock *sk;
+
+ sk = raw_sock_get(net, r);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+ return sock_diag_destroy(sk, ECONNABORTED);
+}
+#endif
+
+static const struct inet_diag_handler raw_diag_handler = {
+ .dump = raw_diag_dump,
+ .dump_one = raw_diag_dump_one,
+ .idiag_get_info = raw_diag_get_info,
+ .idiag_type = IPPROTO_RAW,
+ .idiag_info_size = 0,
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = raw_diag_destroy,
+#endif
+};
+
+static void __always_unused __check_inet_diag_req_raw(void)
+{
+ /*
+ * Make sure the two structures are identical,
+ * except the @pad field.
+ */
+#define __offset_mismatch(m1, m2) \
+ (offsetof(struct inet_diag_req_v2, m1) != \
+ offsetof(struct inet_diag_req_raw, m2))
+
+ BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) !=
+ sizeof(struct inet_diag_req_raw));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext));
+ BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states));
+ BUILD_BUG_ON(__offset_mismatch(id, id));
+#undef __offset_mismatch
+}
+
+static int __init raw_diag_init(void)
+{
+ return inet_diag_register(&raw_diag_handler);
+}
+
+static void __exit raw_diag_exit(void)
+{
+ inet_diag_unregister(&raw_diag_handler);
+}
+
+module_init(raw_diag_init);
+module_exit(raw_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 0ea66c2c9344..b89bce4c721e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -14,6 +14,36 @@
* observed, or adjust the sending rate if it estimates there is a
* traffic policer, in order to keep the drop rate reasonable.
*
+ * Here is a state transition diagram for BBR:
+ *
+ * |
+ * V
+ * +---> STARTUP ----+
+ * | | |
+ * | V |
+ * | DRAIN ----+
+ * | | |
+ * | V |
+ * +---> PROBE_BW ----+
+ * | ^ | |
+ * | | | |
+ * | +----+ |
+ * | |
+ * +---- PROBE_RTT <--+
+ *
+ * A BBR flow starts in STARTUP, and ramps up its sending rate quickly.
+ * When it estimates the pipe is full, it enters DRAIN to drain the queue.
+ * In steady state a BBR flow only uses PROBE_BW and PROBE_RTT.
+ * A long-lived BBR flow spends the vast majority of its time remaining
+ * (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth
+ * in a fair manner, with a small, bounded queue. *If* a flow has been
+ * continuously sending for the entire min_rtt window, and hasn't seen an RTT
+ * sample that matches or decreases its min_rtt estimate for 10 seconds, then
+ * it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe
+ * the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if
+ * we estimated that we reached the full bw of the pipe then we enter PROBE_BW;
+ * otherwise we enter STARTUP to try to fill the pipe.
+ *
* BBR is described in detail in:
* "BBR: Congestion-Based Congestion Control",
* Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
@@ -51,7 +81,7 @@ enum bbr_mode {
BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */
BBR_DRAIN, /* drain any queue created during startup */
BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */
- BBR_PROBE_RTT, /* cut cwnd to min to probe min_rtt */
+ BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */
};
/* BBR congestion control block */
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a27b9c0e27c0..f2c59c8e57ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6298,13 +6298,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
goto drop;
}
-
- /* Accept backlog is full. If we have already queued enough
- * of warm entries in syn queue, drop request. It is better than
- * clogging syn queue with openreqs with exponentially increasing
- * timeout.
- */
- if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+ if (sk_acceptq_is_full(sk)) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
goto drop;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 61b7be303eec..b9b8282633d4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1891,7 +1891,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur)
if (!sk) {
get_head:
ilb = &tcp_hashinfo.listening_hash[st->bucket];
- spin_lock_bh(&ilb->lock);
+ spin_lock(&ilb->lock);
sk = sk_head(&ilb->head);
st->offset = 0;
goto get_sk;
@@ -1908,7 +1908,7 @@ get_sk:
if (sk->sk_family == st->family)
return sk;
}
- spin_unlock_bh(&ilb->lock);
+ spin_unlock(&ilb->lock);
st->offset = 0;
if (++st->bucket < INET_LHTABLE_SIZE)
goto get_head;
@@ -2116,7 +2116,7 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
switch (st->state) {
case TCP_SEQ_STATE_LISTENING:
if (v != SEQ_START_TOKEN)
- spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
+ spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock);
break;
case TCP_SEQ_STATE_ESTABLISHED:
if (v)
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index bf1f3b2b29d1..d46f4d5b1c62 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -742,14 +742,7 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss,
rcu_read_unlock();
}
-static struct genl_family tcp_metrics_nl_family = {
- .id = GENL_ID_GENERATE,
- .hdrsize = 0,
- .name = TCP_METRICS_GENL_NAME,
- .version = TCP_METRICS_GENL_VERSION,
- .maxattr = TCP_METRICS_ATTR_MAX,
- .netnsok = true,
-};
+static struct genl_family tcp_metrics_nl_family;
static const struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = {
[TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, },
@@ -1116,6 +1109,17 @@ static const struct genl_ops tcp_metrics_nl_ops[] = {
},
};
+static struct genl_family tcp_metrics_nl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = TCP_METRICS_GENL_NAME,
+ .version = TCP_METRICS_GENL_VERSION,
+ .maxattr = TCP_METRICS_ATTR_MAX,
+ .netnsok = true,
+ .module = THIS_MODULE,
+ .ops = tcp_metrics_nl_ops,
+ .n_ops = ARRAY_SIZE(tcp_metrics_nl_ops),
+};
+
static unsigned int tcpmhash_entries;
static int __init set_tcpmhash_entries(char *str)
{
@@ -1179,8 +1183,7 @@ void __init tcp_metrics_init(void)
if (ret < 0)
panic("Could not allocate the tcp_metrics hash table\n");
- ret = genl_register_family_with_ops(&tcp_metrics_nl_family,
- tcp_metrics_nl_ops);
+ ret = genl_register_family(&tcp_metrics_nl_family);
if (ret < 0)
panic("Could not register tcp_metrics generic netlink\n");
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d123d68f4d1d..195992e0440d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1172,6 +1172,112 @@ out:
return ret;
}
+static void udp_rmem_release(struct sock *sk, int size, int partial)
+{
+ int amt;
+
+ atomic_sub(size, &sk->sk_rmem_alloc);
+
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ sk->sk_forward_alloc += size;
+ amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1);
+ sk->sk_forward_alloc -= amt;
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+ if (amt)
+ __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
+}
+
+static void udp_rmem_free(struct sk_buff *skb)
+{
+ udp_rmem_release(skb->sk, skb->truesize, 1);
+}
+
+int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct sk_buff_head *list = &sk->sk_receive_queue;
+ int rmem, delta, amt, err = -ENOMEM;
+ int size = skb->truesize;
+
+ /* try to avoid the costly atomic add/sub pair when the receive
+ * queue is full; always allow at least a packet
+ */
+ rmem = atomic_read(&sk->sk_rmem_alloc);
+ if (rmem && (rmem + size > sk->sk_rcvbuf))
+ goto drop;
+
+ /* we drop only if the receive buf is full and the receive
+ * queue contains some other skb
+ */
+ rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
+ if ((rmem > sk->sk_rcvbuf) && (rmem > size))
+ goto uncharge_drop;
+
+ spin_lock(&list->lock);
+ if (size >= sk->sk_forward_alloc) {
+ amt = sk_mem_pages(size);
+ delta = amt << SK_MEM_QUANTUM_SHIFT;
+ if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
+ err = -ENOBUFS;
+ spin_unlock(&list->lock);
+ goto uncharge_drop;
+ }
+
+ sk->sk_forward_alloc += delta;
+ }
+
+ sk->sk_forward_alloc -= size;
+
+ /* the skb owner in now the udp socket */
+ skb->sk = sk;
+ skb->destructor = udp_rmem_free;
+ skb->dev = NULL;
+ sock_skb_set_dropcount(sk, skb);
+
+ __skb_queue_tail(list, skb);
+ spin_unlock(&list->lock);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_data_ready(sk);
+
+ return 0;
+
+uncharge_drop:
+ atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+
+drop:
+ atomic_inc(&sk->sk_drops);
+ return err;
+}
+EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
+
+static void udp_destruct_sock(struct sock *sk)
+{
+ /* reclaim completely the forward allocated memory */
+ __skb_queue_purge(&sk->sk_receive_queue);
+ udp_rmem_release(sk, 0, 0);
+ inet_sock_destruct(sk);
+}
+
+int udp_init_sock(struct sock *sk)
+{
+ sk->sk_destruct = udp_destruct_sock;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(udp_init_sock);
+
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
+{
+ if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
+ bool slow = lock_sock_fast(sk);
+
+ sk_peek_offset_bwd(sk, len);
+ unlock_sock_fast(sk, slow);
+ }
+ consume_skb(skb);
+}
+EXPORT_SYMBOL_GPL(skb_consume_udp);
+
/**
* first_packet_length - return length of first packet in receive queue
* @sk: socket
@@ -1201,13 +1307,7 @@ static int first_packet_length(struct sock *sk)
res = skb ? skb->len : -1;
spin_unlock_bh(&rcvq->lock);
- if (!skb_queue_empty(&list_kill)) {
- bool slow = lock_sock_fast(sk);
-
- __skb_queue_purge(&list_kill);
- sk_mem_reclaim_partial(sk);
- unlock_sock_fast(sk, slow);
- }
+ __skb_queue_purge(&list_kill);
return res;
}
@@ -1256,7 +1356,6 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
int err;
int is_udplite = IS_UDPLITE(sk);
bool checksum_valid = false;
- bool slow;
if (flags & MSG_ERRQUEUE)
return ip_recv_error(sk, msg, len, addr_len);
@@ -1297,13 +1396,12 @@ try_again:
}
if (unlikely(err)) {
- trace_kfree_skb(skb, udp_recvmsg);
if (!peeked) {
atomic_inc(&sk->sk_drops);
UDP_INC_STATS(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
}
- skb_free_datagram_locked(sk, skb);
+ kfree_skb(skb);
return err;
}
@@ -1328,16 +1426,15 @@ try_again:
if (flags & MSG_TRUNC)
err = ulen;
- __skb_free_datagram_locked(sk, skb, peeking ? -err : err);
+ skb_consume_udp(sk, skb, peeking ? -err : err);
return err;
csum_copy_err:
- slow = lock_sock_fast(sk);
- if (!skb_kill_datagram(sk, skb, flags)) {
+ if (!__sk_queue_drop_skb(sk, skb, flags)) {
UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
}
- unlock_sock_fast(sk, slow);
+ kfree_skb(skb);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
@@ -1465,7 +1562,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
sk_incoming_cpu_update(sk);
}
- rc = __sock_queue_rcv_skb(sk, skb);
+ rc = __udp_enqueue_schedule_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -1480,7 +1577,6 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
return 0;
-
}
static struct static_key udp_encap_needed __read_mostly;
@@ -1502,7 +1598,6 @@ EXPORT_SYMBOL(udp_encap_enable);
int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
- int rc;
int is_udplite = IS_UDPLITE(sk);
/*
@@ -1589,25 +1684,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto drop;
udp_csum_pull_header(skb);
- if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
- __UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
- is_udplite);
- goto drop;
- }
-
- rc = 0;
ipv4_pktinfo_prepare(sk, skb);
- bh_lock_sock(sk);
- if (!sock_owned_by_user(sk))
- rc = __udp_queue_rcv_skb(sk, skb);
- else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
- bh_unlock_sock(sk);
- goto drop;
- }
- bh_unlock_sock(sk);
-
- return rc;
+ return __udp_queue_rcv_skb(sk, skb);
csum_error:
__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
@@ -2217,13 +2296,13 @@ struct proto udp_prot = {
.connect = ip4_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
+ .init = udp_init_sock,
.destroy = udp_destroy_sock,
.setsockopt = udp_setsockopt,
.getsockopt = udp_getsockopt,
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = __udp_queue_rcv_skb,
.release_cb = ip4_datagram_release_cb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-03 21:32:21 +0300