summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig13
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c19
-rw-r--r--net/ipv4/fib_frontend.c1
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/inet_diag.c213
-rw-r--r--net/ipv4/ip_output.c3
-rw-r--r--net/ipv4/ping.c3
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c39
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c22
-rw-r--r--net/ipv4/sysfs_net_ipv4.c88
-rw-r--r--net/ipv4/tcp.c46
-rw-r--r--net/ipv4/tcp_diag.c19
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c25
-rw-r--r--net/ipv4/tcp_output.c2
-rw-r--r--net/ipv4/udp.c18
-rw-r--r--net/ipv4/udp_diag.c89
21 files changed, 517 insertions, 95 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 416dfa004cfb..c22920525e5d 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -436,6 +436,19 @@ config INET_UDP_DIAG
Support for UDP 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
+ default n
+ ---help---
+ Provides a SOCK_DESTROY operation that allows privileged processes
+ (e.g., a connection manager or a network administration tool such as
+ ss) to close sockets opened by other processes. Closing a socket in
+ this way interrupts any blocking read/write/connect operations on
+ the socket and causes future socket calls to behave as if the socket
+ had been disconnected.
+ If unsure, say N.
+
menuconfig TCP_CONG_ADVANCED
bool "TCP: advanced congestion control"
---help---
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c29809f765dc..854c4bfd6eea 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -16,6 +16,7 @@ obj-y := route.o inetpeer.o protocol.o \
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
+obj-$(CONFIG_SYSFS) += sysfs_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index afc18e9ca94a..68bf7bdf7fdb 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -121,6 +121,19 @@
#endif
#include <net/l3mdev.h>
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+
+static inline int current_has_network(void)
+{
+ return in_egroup_p(AID_INET) || capable(CAP_NET_RAW);
+}
+#else
+static inline int current_has_network(void)
+{
+ return 1;
+}
+#endif
/* The inetsw table contains everything that inet_create needs to
* build a new socket.
@@ -260,6 +273,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
if (protocol < 0 || protocol >= IPPROTO_MAX)
return -EINVAL;
+ if (!current_has_network())
+ return -EACCES;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
@@ -308,8 +324,7 @@ lookup_protocol:
}
err = -EPERM;
- if (sock->type == SOCK_RAW && !kern &&
- !ns_capable(net->user_ns, CAP_NET_RAW))
+ if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW))
goto out_rcu_unlock;
sock->ops = answer->ops;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1adba44f8fbc..a353d1d92f01 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -627,6 +627,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
+ [RTA_UID] = { .type = NLA_U32 },
};
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 36e26977c908..ef2d4322aba7 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -425,6 +425,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
fl4.daddr = daddr;
fl4.saddr = saddr;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = sock_net_uid(net, NULL);
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
@@ -473,6 +474,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
param->replyopts.opt.opt.faddr : iph->saddr);
fl4->saddr = saddr;
fl4->flowi4_mark = mark;
+ fl4->flowi4_uid = sock_net_uid(net, NULL);
fl4->flowi4_tos = RT_TOS(tos);
fl4->flowi4_proto = IPPROTO_ICMP;
fl4->fl4_icmp_type = type;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 64148914803a..c97a2108cd61 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -420,7 +420,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
@@ -457,7 +457,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
sk->sk_protocol, inet_sk_flowi_flags(sk),
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
- htons(ireq->ir_num));
+ htons(ireq->ir_num), sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index ab9f8a66615d..fcb83b2a61f0 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -44,6 +44,8 @@ struct inet_diag_entry {
u16 dport;
u16 family;
u16 userlocks;
+ u32 ifindex;
+ u32 mark;
};
static DEFINE_MUTEX(inet_diag_table_mutex);
@@ -96,6 +98,7 @@ static size_t inet_sk_attr_size(void)
+ nla_total_size(1) /* INET_DIAG_SHUTDOWN */
+ nla_total_size(1) /* INET_DIAG_TOS */
+ nla_total_size(1) /* INET_DIAG_TCLASS */
+ + nla_total_size(4) /* INET_DIAG_MARK */
+ nla_total_size(sizeof(struct inet_diag_meminfo))
+ nla_total_size(sizeof(struct inet_diag_msg))
+ nla_total_size(SK_MEMINFO_VARS * sizeof(u32))
@@ -108,7 +111,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
struct sk_buff *skb, const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh)
+ const struct nlmsghdr *unlh,
+ bool net_admin)
{
const struct inet_sock *inet = inet_sk(sk);
const struct tcp_congestion_ops *ca_ops;
@@ -158,6 +162,9 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
}
#endif
+ if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark))
+ goto errout;
+
r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
r->idiag_inode = sock_i_ino(sk);
@@ -256,10 +263,11 @@ static int inet_csk_diag_fill(struct sock *sk,
const struct inet_diag_req_v2 *req,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh)
+ const struct nlmsghdr *unlh,
+ bool net_admin)
{
- return inet_sk_diag_fill(sk, inet_csk(sk), skb, req,
- user_ns, portid, seq, nlmsg_flags, unlh);
+ return inet_sk_diag_fill(sk, inet_csk(sk), skb, req, user_ns,
+ portid, seq, nlmsg_flags, unlh, net_admin);
}
static int inet_twsk_diag_fill(struct sock *sk,
@@ -301,8 +309,9 @@ static int inet_twsk_diag_fill(struct sock *sk,
static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh)
+ const struct nlmsghdr *unlh, bool net_admin)
{
+ struct request_sock *reqsk = inet_reqsk(sk);
struct inet_diag_msg *r;
struct nlmsghdr *nlh;
long tmo;
@@ -316,7 +325,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
inet_diag_msg_common_fill(r, sk);
r->idiag_state = TCP_SYN_RECV;
r->idiag_timer = 1;
- r->idiag_retrans = inet_reqsk(sk)->num_retrans;
+ r->idiag_retrans = reqsk->num_retrans;
BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) !=
offsetof(struct sock, sk_cookie));
@@ -328,6 +337,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
r->idiag_uid = 0;
r->idiag_inode = 0;
+ if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
+ inet_rsk(reqsk)->ir_mark))
+ return -EMSGSIZE;
+
nlmsg_end(skb, nlh);
return 0;
}
@@ -336,7 +349,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
const struct inet_diag_req_v2 *r,
struct user_namespace *user_ns,
u32 portid, u32 seq, u16 nlmsg_flags,
- const struct nlmsghdr *unlh)
+ const struct nlmsghdr *unlh, bool net_admin)
{
if (sk->sk_state == TCP_TIME_WAIT)
return inet_twsk_diag_fill(sk, skb, portid, seq,
@@ -344,46 +357,66 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
if (sk->sk_state == TCP_NEW_SYN_RECV)
return inet_req_diag_fill(sk, skb, portid, seq,
- nlmsg_flags, unlh);
+ nlmsg_flags, unlh, net_admin);
return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq,
- nlmsg_flags, unlh);
+ nlmsg_flags, unlh, net_admin);
}
-int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
- struct sk_buff *in_skb,
- const struct nlmsghdr *nlh,
- const struct inet_diag_req_v2 *req)
+struct sock *inet_diag_find_one_icsk(struct net *net,
+ struct inet_hashinfo *hashinfo,
+ const struct inet_diag_req_v2 *req)
{
- struct net *net = sock_net(in_skb->sk);
- struct sk_buff *rep;
struct sock *sk;
- int err;
- err = -EINVAL;
if (req->sdiag_family == AF_INET)
sk = inet_lookup(net, hashinfo, req->id.idiag_dst[0],
req->id.idiag_dport, req->id.idiag_src[0],
req->id.idiag_sport, req->id.idiag_if);
#if IS_ENABLED(CONFIG_IPV6)
- else if (req->sdiag_family == AF_INET6)
- sk = inet6_lookup(net, hashinfo,
- (struct in6_addr *)req->id.idiag_dst,
- req->id.idiag_dport,
- (struct in6_addr *)req->id.idiag_src,
- req->id.idiag_sport,
- req->id.idiag_if);
+ else if (req->sdiag_family == AF_INET6) {
+ if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+ sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
+ req->id.idiag_dport, req->id.idiag_src[3],
+ req->id.idiag_sport, req->id.idiag_if);
+ else
+ sk = inet6_lookup(net, hashinfo,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ req->id.idiag_if);
+ }
#endif
else
- goto out_nosk;
+ return ERR_PTR(-EINVAL);
- err = -ENOENT;
if (!sk)
- goto out_nosk;
+ return ERR_PTR(-ENOENT);
- err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
- if (err)
- goto out;
+ if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
+ sock_gen_put(sk);
+ return ERR_PTR(-ENOENT);
+ }
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(inet_diag_find_one_icsk);
+
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
+ struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ const struct inet_diag_req_v2 *req)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *rep;
+ struct sock *sk;
+ int err;
+
+ sk = inet_diag_find_one_icsk(net, hashinfo, req);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
rep = nlmsg_new(inet_sk_attr_size(), GFP_KERNEL);
if (!rep) {
@@ -394,7 +427,8 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
err = sk_diag_fill(sk, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0, nlh);
+ nlh->nlmsg_seq, 0, nlh,
+ netlink_net_capable(in_skb, CAP_NET_ADMIN));
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
nlmsg_free(rep);
@@ -409,12 +443,11 @@ out:
if (sk)
sock_gen_put(sk);
-out_nosk:
return err;
}
EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
-static int inet_diag_get_exact(struct sk_buff *in_skb,
+static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb,
const struct nlmsghdr *nlh,
const struct inet_diag_req_v2 *req)
{
@@ -424,8 +457,12 @@ static int inet_diag_get_exact(struct sk_buff *in_skb,
handler = inet_diag_lock_handler(req->sdiag_protocol);
if (IS_ERR(handler))
err = PTR_ERR(handler);
- else
+ else if (cmd == SOCK_DIAG_BY_FAMILY)
err = handler->dump_one(in_skb, nlh, req);
+ else if (cmd == SOCK_DESTROY_BACKPORT && handler->destroy)
+ err = handler->destroy(in_skb, req);
+ else
+ err = -EOPNOTSUPP;
inet_diag_unlock_handler(handler);
return err;
@@ -529,6 +566,22 @@ static int inet_diag_bc_run(const struct nlattr *_bc,
yes = 0;
break;
}
+ case INET_DIAG_BC_DEV_COND: {
+ u32 ifindex;
+
+ ifindex = *((const u32 *)(op + 1));
+ if (ifindex != entry->ifindex)
+ yes = 0;
+ break;
+ }
+ case INET_DIAG_BC_MARK_COND: {
+ struct inet_diag_markcond *cond;
+
+ cond = (struct inet_diag_markcond *)(op + 1);
+ if ((entry->mark & cond->mask) != cond->mark)
+ yes = 0;
+ break;
+ }
}
if (yes) {
@@ -571,7 +624,14 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
entry_fill_addrs(&entry, sk);
entry.sport = inet->inet_num;
entry.dport = ntohs(inet->inet_dport);
+ entry.ifindex = sk->sk_bound_dev_if;
entry.userlocks = sk_fullsock(sk) ? sk->sk_userlocks : 0;
+ if (sk_fullsock(sk))
+ entry.mark = sk->sk_mark;
+ else if (sk->sk_state == TCP_NEW_SYN_RECV)
+ entry.mark = inet_rsk(inet_reqsk(sk))->ir_mark;
+ else
+ entry.mark = 0;
return inet_diag_bc_run(bc, &entry);
}
@@ -594,6 +654,17 @@ static int valid_cc(const void *bc, int len, int cc)
return 0;
}
+/* data is u32 ifindex */
+static bool valid_devcond(const struct inet_diag_bc_op *op, int len,
+ int *min_len)
+{
+ /* Check ifindex space. */
+ *min_len += sizeof(u32);
+ if (len < *min_len)
+ return false;
+
+ return true;
+}
/* Validate an inet_diag_hostcond. */
static bool valid_hostcond(const struct inet_diag_bc_op *op, int len,
int *min_len)
@@ -643,10 +714,25 @@ static bool valid_port_comparison(const struct inet_diag_bc_op *op,
return true;
}
-static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
+static bool valid_markcond(const struct inet_diag_bc_op *op, int len,
+ int *min_len)
+{
+ *min_len += sizeof(struct inet_diag_markcond);
+ return len >= *min_len;
+}
+
+static int inet_diag_bc_audit(const struct nlattr *attr,
+ const struct sk_buff *skb)
{
- const void *bc = bytecode;
- int len = bytecode_len;
+ bool net_admin = netlink_net_capable(skb, CAP_NET_ADMIN);
+ const void *bytecode, *bc;
+ int bytecode_len, len;
+
+ if (!attr || nla_len(attr) < sizeof(struct inet_diag_bc_op))
+ return -EINVAL;
+
+ bytecode = bc = nla_data(attr);
+ len = bytecode_len = nla_len(attr);
while (len > 0) {
int min_len = sizeof(struct inet_diag_bc_op);
@@ -658,6 +744,10 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
if (!valid_hostcond(bc, len, &min_len))
return -EINVAL;
break;
+ case INET_DIAG_BC_DEV_COND:
+ if (!valid_devcond(bc, len, &min_len))
+ return -EINVAL;
+ break;
case INET_DIAG_BC_S_GE:
case INET_DIAG_BC_S_LE:
case INET_DIAG_BC_D_GE:
@@ -665,6 +755,12 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
if (!valid_port_comparison(bc, len, &min_len))
return -EINVAL;
break;
+ case INET_DIAG_BC_MARK_COND:
+ if (!net_admin)
+ return -EPERM;
+ if (!valid_markcond(bc, len, &min_len))
+ return -EINVAL;
+ break;
case INET_DIAG_BC_AUTO:
case INET_DIAG_BC_JMP:
case INET_DIAG_BC_NOP:
@@ -693,7 +789,8 @@ static int inet_csk_diag_dump(struct sock *sk,
struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *r,
- const struct nlattr *bc)
+ const struct nlattr *bc,
+ bool net_admin)
{
if (!inet_diag_bc_sk(bc, sk))
return 0;
@@ -701,7 +798,8 @@ static int inet_csk_diag_dump(struct sock *sk,
return inet_csk_diag_fill(sk, skb, r,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
+ cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh,
+ net_admin);
}
static void twsk_build_assert(void)
@@ -737,6 +835,7 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
struct net *net = sock_net(skb->sk);
int i, num, s_i, s_num;
u32 idiag_states = r->idiag_states;
+ bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
if (idiag_states & TCPF_SYN_RECV)
idiag_states |= TCPF_NEW_SYN_RECV;
@@ -778,7 +877,8 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
cb->args[3] > 0)
goto next_listen;
- if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
+ if (inet_csk_diag_dump(sk, skb, cb, r,
+ bc, net_admin) < 0) {
spin_unlock_bh(&ilb->lock);
goto done;
}
@@ -846,7 +946,7 @@ skip_listen_ht:
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, NLM_F_MULTI,
- cb->nlh);
+ cb->nlh, net_admin);
if (res < 0) {
spin_unlock_bh(lock);
goto done;
@@ -938,7 +1038,7 @@ static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
req.idiag_states = rc->idiag_states;
req.id = rc->id;
- return inet_diag_get_exact(in_skb, nlh, &req);
+ return inet_diag_cmd_exact(SOCK_DIAG_BY_FAMILY, in_skb, nlh, &req);
}
static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -953,13 +1053,13 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
if (nlh->nlmsg_flags & NLM_F_DUMP) {
if (nlmsg_attrlen(nlh, hdrlen)) {
struct nlattr *attr;
+ int err;
attr = nlmsg_find_attr(nlh, hdrlen,
INET_DIAG_REQ_BYTECODE);
- if (!attr ||
- nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
- inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
- return -EINVAL;
+ err = inet_diag_bc_audit(attr, skb);
+ if (err)
+ return err;
}
{
struct netlink_dump_control c = {
@@ -972,7 +1072,7 @@ static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
return inet_diag_get_exact_compat(skb, nlh);
}
-static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+static int inet_diag_handler_cmd(struct sk_buff *skb, struct nlmsghdr *h)
{
int hdrlen = sizeof(struct inet_diag_req_v2);
struct net *net = sock_net(skb->sk);
@@ -980,16 +1080,17 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
if (nlmsg_len(h) < hdrlen)
return -EINVAL;
- if (h->nlmsg_flags & NLM_F_DUMP) {
+ if (h->nlmsg_type == SOCK_DIAG_BY_FAMILY &&
+ h->nlmsg_flags & NLM_F_DUMP) {
if (nlmsg_attrlen(h, hdrlen)) {
struct nlattr *attr;
+ int err;
attr = nlmsg_find_attr(h, hdrlen,
INET_DIAG_REQ_BYTECODE);
- if (!attr ||
- nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
- inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
- return -EINVAL;
+ err = inet_diag_bc_audit(attr, skb);
+ if (err)
+ return err;
}
{
struct netlink_dump_control c = {
@@ -999,7 +1100,7 @@ static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
}
}
- return inet_diag_get_exact(skb, h, nlmsg_data(h));
+ return inet_diag_cmd_exact(h->nlmsg_type, skb, h, nlmsg_data(h));
}
static
@@ -1050,14 +1151,16 @@ int inet_diag_handler_get_info(struct sk_buff *skb, struct sock *sk)
static const struct sock_diag_handler inet_diag_handler = {
.family = AF_INET,
- .dump = inet_diag_handler_dump,
+ .dump = inet_diag_handler_cmd,
.get_info = inet_diag_handler_get_info,
+ .destroy = inet_diag_handler_cmd,
};
static const struct sock_diag_handler inet6_diag_handler = {
.family = AF_INET6,
- .dump = inet_diag_handler_dump,
+ .dump = inet_diag_handler_cmd,
.get_info = inet_diag_handler_get_info,
+ .destroy = inet_diag_handler_cmd,
};
int inet_diag_register(const struct inet_diag_handler *h)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 2b7283303650..661bda968594 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1580,7 +1580,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol,
ip_reply_arg_flowi_flags(arg),
daddr, saddr,
- tcp_hdr(skb)->source, tcp_hdr(skb)->dest);
+ tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
+ arg->uid);
security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 37a3b05d175c..a989aba861e0 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -798,7 +798,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
- inet_sk_flowi_flags(sk), faddr, saddr, 0, 0);
+ inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
+ sk->sk_uid);
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 7113bae4e6a0..6287418c1dfe 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -601,7 +601,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
- daddr, saddr, 0, 0);
+ daddr, saddr, 0, 0, sk->sk_uid);
if (!saddr && ipc.oif) {
err = l3mdev_get_saddr(net, ipc.oif, &fl4);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 375248b900ba..7e31491e9396 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -501,7 +501,8 @@ void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
+static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
+ const struct sock *sk,
const struct iphdr *iph,
int oif, u8 tos,
u8 prot, u32 mark, int flow_flags)
@@ -517,19 +518,21 @@ static void __build_flow_key(struct flowi4 *fl4, const struct sock *sk,
flowi4_init_output(fl4, oif, mark, tos,
RT_SCOPE_UNIVERSE, prot,
flow_flags,
- iph->daddr, iph->saddr, 0, 0);
+ iph->daddr, iph->saddr, 0, 0,
+ sock_net_uid(net, sk));
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
const struct sock *sk)
{
+ const struct net *net = dev_net(skb->dev);
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
u32 mark = skb->mark;
- __build_flow_key(fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
}
static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
@@ -546,7 +549,7 @@ static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
- daddr, inet->inet_saddr, 0, 0);
+ daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
@@ -789,6 +792,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
struct rtable *rt;
struct flowi4 fl4;
const struct iphdr *iph = (const struct iphdr *) skb->data;
+ struct net *net = dev_net(skb->dev);
int oif = skb->dev->ifindex;
u8 tos = RT_TOS(iph->tos);
u8 prot = iph->protocol;
@@ -796,7 +800,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
rt = (struct rtable *) dst;
- __build_flow_key(&fl4, sk, iph, oif, tos, prot, mark, 0);
+ __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
@@ -1014,7 +1018,7 @@ void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
if (!mark)
mark = IP4_REPLY_MARK(net, skb->mark);
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1030,7 +1034,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0);
if (!fl4.flowi4_mark)
fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark);
@@ -1049,6 +1053,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
struct rtable *rt;
struct dst_entry *odst = NULL;
bool new = false;
+ struct net *net = sock_net(sk);
bh_lock_sock(sk);
@@ -1062,7 +1067,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
goto out;
}
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
rt = (struct rtable *)odst;
if (odst->obsolete && !odst->ops->check(odst, 0)) {
@@ -1102,7 +1107,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
struct flowi4 fl4;
struct rtable *rt;
- __build_flow_key(&fl4, NULL, iph, oif,
+ __build_flow_key(net, &fl4, NULL, iph, oif,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
@@ -1117,9 +1122,10 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct flowi4 fl4;
struct rtable *rt;
+ struct net *net = sock_net(sk);
- __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
- rt = __ip_route_output_key(sock_net(sk), &fl4);
+ __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0);
+ rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
__ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
@@ -2487,6 +2493,11 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
+ if (!uid_eq(fl4->flowi4_uid, INVALID_UID) &&
+ nla_put_u32(skb, RTA_UID,
+ from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
+ goto nla_put_failure;
+
error = rt->dst.error;
if (rt_is_input_route(rt)) {
@@ -2539,6 +2550,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
int mark;
struct sk_buff *skb;
u32 table_id = RT_TABLE_MAIN;
+ kuid_t uid;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
@@ -2566,6 +2578,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ if (tb[RTA_UID])
+ uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID]));
+ else
+ uid = (iif ? INVALID_UID : current_uid());
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = dst;
@@ -2573,6 +2589,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
fl4.flowi4_tos = rtm->rtm_tos;
fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
fl4.flowi4_mark = mark;
+ fl4.flowi4_uid = uid;
if (netif_index_is_l3_master(net, fl4.flowi4_oif))
fl4.flowi4_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 4cbe9f0a4281..2dc982b15df8 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -375,7 +375,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, IPPROTO_TCP,
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
- ireq->ir_loc_addr, th->source, th->dest);
+ ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
security_req_classify_flow(req, flowi4_to_flowi(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 70fb352e317f..46123369144f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -152,6 +152,21 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
return ret;
}
+/* Validate changes from /proc interface. */
+static int proc_tcp_default_init_rwnd(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int old_value = *(int *)ctl->data;
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+ int new_value = *(int *)ctl->data;
+
+ if (write && ret == 0 && (new_value < 3 || new_value > 100))
+ *(int *)ctl->data = old_value;
+
+ return ret;
+}
+
static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -761,6 +776,13 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec_ms_jiffies,
},
{
+ .procname = "tcp_default_init_rwnd",
+ .data = &sysctl_tcp_default_init_rwnd,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_default_init_rwnd
+ },
+ {
.procname = "icmp_msgs_per_sec",
.data = &sysctl_icmp_msgs_per_sec,
.maxlen = sizeof(int),
diff --git a/net/ipv4/sysfs_net_ipv4.c b/net/ipv4/sysfs_net_ipv4.c
new file mode 100644
index 000000000000..0cbbf10026a6
--- /dev/null
+++ b/net/ipv4/sysfs_net_ipv4.c
@@ -0,0 +1,88 @@
+/*
+ * net/ipv4/sysfs_net_ipv4.c
+ *
+ * sysfs-based networking knobs (so we can, unlike with sysctl, control perms)
+ *
+ * Copyright (C) 2008 Google, Inc.
+ *
+ * Robert Love <rlove@google.com>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/init.h>
+#include <net/tcp.h>
+
+#define CREATE_IPV4_FILE(_name, _var) \
+static ssize_t _name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+{ \
+ return sprintf(buf, "%d\n", _var); \
+} \
+static ssize_t _name##_store(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ int val, ret; \
+ ret = sscanf(buf, "%d", &val); \
+ if (ret != 1) \
+ return -EINVAL; \
+ if (val < 0) \
+ return -EINVAL; \
+ _var = val; \
+ return count; \
+} \
+static struct kobj_attribute _name##_attr = \
+ __ATTR(_name, 0644, _name##_show, _name##_store)
+
+CREATE_IPV4_FILE(tcp_wmem_min, sysctl_tcp_wmem[0]);
+CREATE_IPV4_FILE(tcp_wmem_def, sysctl_tcp_wmem[1]);
+CREATE_IPV4_FILE(tcp_wmem_max, sysctl_tcp_wmem[2]);
+
+CREATE_IPV4_FILE(tcp_rmem_min, sysctl_tcp_rmem[0]);
+CREATE_IPV4_FILE(tcp_rmem_def, sysctl_tcp_rmem[1]);
+CREATE_IPV4_FILE(tcp_rmem_max, sysctl_tcp_rmem[2]);
+
+static struct attribute *ipv4_attrs[] = {
+ &tcp_wmem_min_attr.attr,
+ &tcp_wmem_def_attr.attr,
+ &tcp_wmem_max_attr.attr,
+ &tcp_rmem_min_attr.attr,
+ &tcp_rmem_def_attr.attr,
+ &tcp_rmem_max_attr.attr,
+ NULL
+};
+
+static struct attribute_group ipv4_attr_group = {
+ .attrs = ipv4_attrs,
+};
+
+static __init int sysfs_ipv4_init(void)
+{
+ struct kobject *ipv4_kobject;
+ int ret;
+
+ ipv4_kobject = kobject_create_and_add("ipv4", kernel_kobj);
+ if (!ipv4_kobject)
+ return -ENOMEM;
+
+ ret = sysfs_create_group(ipv4_kobject, &ipv4_attr_group);
+ if (ret) {
+ kobject_put(ipv4_kobject);
+ return ret;
+ }
+
+ return 0;
+}
+
+subsys_initcall(sysfs_ipv4_init);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e1d51370977b..44181ba2d6bf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3091,6 +3091,52 @@ void tcp_done(struct sock *sk)
}
EXPORT_SYMBOL_GPL(tcp_done);
+int tcp_abort(struct sock *sk, int err)
+{
+ if (!sk_fullsock(sk)) {
+ if (sk->sk_state == TCP_NEW_SYN_RECV) {
+ struct request_sock *req = inet_reqsk(sk);
+
+ local_bh_disable();
+ inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
+ req);
+ local_bh_enable();
+ return 0;
+ }
+ sock_gen_put(sk);
+ return -EOPNOTSUPP;
+ }
+
+ /* Don't race with userspace socket closes such as tcp_close. */
+ lock_sock(sk);
+
+ if (sk->sk_state == TCP_LISTEN) {
+ tcp_set_state(sk, TCP_CLOSE);
+ inet_csk_listen_stop(sk);
+ }
+
+ /* Don't race with BH socket closes such as inet_csk_listen_stop. */
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ sk->sk_err = err;
+ /* This barrier is coupled with smp_rmb() in tcp_poll() */
+ smp_wmb();
+ sk->sk_error_report(sk);
+ if (tcp_need_reset(sk->sk_state))
+ tcp_send_active_reset(sk, GFP_ATOMIC);
+ tcp_done(sk);
+ }
+
+ bh_unlock_sock(sk);
+ local_bh_enable();
+ release_sock(sk);
+ sock_put(sk);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tcp_abort);
+
extern struct tcp_congestion_ops tcp_reno;
static __initdata unsigned long thash_entries;
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index b31604086edd..4d610934fb39 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -10,6 +10,8 @@
*/
#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/sock_diag.h>
#include <linux/inet_diag.h>
#include <linux/tcp.h>
@@ -46,12 +48,29 @@ static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
}
+#ifdef CONFIG_INET_DIAG_DESTROY
+static int tcp_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *req)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
+
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ return sock_diag_destroy(sk, ECONNABORTED);
+}
+#endif
+
static const struct inet_diag_handler tcp_diag_handler = {
.dump = tcp_diag_dump,
.dump_one = tcp_diag_dump_one,
.idiag_get_info = tcp_diag_get_info,
.idiag_type = IPPROTO_TCP,
.idiag_info_size = sizeof(struct tcp_info),
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = tcp_diag_destroy,
+#endif
};
static int __init tcp_diag_init(void)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 818630cec54f..fd34367472bd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -102,6 +102,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
int sysctl_tcp_early_retrans __read_mostly = 3;
int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
+int sysctl_tcp_default_init_rwnd __read_mostly = TCP_INIT_CWND * 2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
#define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 198fc2314c82..984de80590bc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -691,6 +691,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
arg.bound_dev_if = sk->sk_bound_dev_if;
arg.tos = ip_hdr(skb)->tos;
+ arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
@@ -712,8 +713,8 @@ release_sk1:
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct net *net,
- struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb,
+ u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
int reply_flags, u8 tos)
@@ -728,6 +729,7 @@ static void tcp_v4_send_ack(struct net *net,
];
} rep;
struct ip_reply_arg arg;
+ struct net *net = sock_net(sk);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -776,6 +778,7 @@ static void tcp_v4_send_ack(struct net *net,
if (oif)
arg.bound_dev_if = oif;
arg.tos = tos;
+ arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
skb, &TCP_SKB_CB(skb)->header.h4.opt,
ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
@@ -789,8 +792,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(sock_net(sk), skb,
- tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent,
@@ -809,17 +811,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
- u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
- tcp_sk(sk)->snd_nxt;
-
- /* RFC 7323 2.3
- * The window field (SEG.WND) of every outgoing segment, with the
- * exception of <SYN> segments, MUST be right-shifted by
- * Rcv.Wind.Shift bits:
- */
- tcp_v4_send_ack(sock_net(sk), skb, seq,
- tcp_rsk(req)->rcv_nxt,
- req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
+ tcp_v4_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
+ tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+ tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp,
req->ts_recent,
0,
@@ -2376,6 +2370,7 @@ struct proto tcp_prot = {
.destroy_cgroup = tcp_destroy_cgroup,
.proto_cgroup = tcp_proto_cgroup,
#endif
+ .diag_destroy = tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index de95714d021c..8a62ad0c850b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -191,7 +191,7 @@ u32 tcp_default_init_rwnd(u32 mss)
* (RFC 3517, Section 4, NextSeg() rule (2)). Further place a
* limit when mss is larger than 1460.
*/
- u32 init_rwnd = TCP_INIT_CWND * 2;
+ u32 init_rwnd = sysctl_tcp_default_init_rwnd;
if (mss > 1460)
init_rwnd = max((1460 * init_rwnd) / mss, 2U);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e9513e397c4f..ad3d1534c524 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1025,7 +1025,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE, sk->sk_protocol,
flow_flags,
- faddr, saddr, dport, inet->inet_sport);
+ faddr, saddr, dport, inet->inet_sport,
+ sk->sk_uid);
if (!saddr && ipc.oif) {
err = l3mdev_get_saddr(net, ipc.oif, fl4);
@@ -2264,6 +2265,20 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
}
EXPORT_SYMBOL(udp_poll);
+int udp_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(udp_abort);
+
struct proto udp_prot = {
.name = "UDP",
.owner = THIS_MODULE,
@@ -2295,6 +2310,7 @@ struct proto udp_prot = {
.compat_getsockopt = compat_udp_getsockopt,
#endif
.clear_sk = sk_prot_clear_portaddr_nulls,
+ .diag_destroy = udp_abort,
};
EXPORT_SYMBOL(udp_prot);
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 6116604bf6e8..092aa60e8b92 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -20,7 +20,7 @@
static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
struct netlink_callback *cb,
const struct inet_diag_req_v2 *req,
- struct nlattr *bc)
+ struct nlattr *bc, bool net_admin)
{
if (!inet_diag_bc_sk(bc, sk))
return 0;
@@ -28,7 +28,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
return inet_sk_diag_fill(sk, NULL, skb, req,
sk_user_ns(NETLINK_CB(cb->skb).sk),
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
+ cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh, net_admin);
}
static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
@@ -75,7 +75,8 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
err = inet_sk_diag_fill(sk, NULL, rep, req,
sk_user_ns(NETLINK_CB(in_skb).sk),
NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0, nlh);
+ nlh->nlmsg_seq, 0, nlh,
+ netlink_net_capable(in_skb, CAP_NET_ADMIN));
if (err < 0) {
WARN_ON(err == -EMSGSIZE);
kfree_skb(rep);
@@ -98,6 +99,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb,
{
int num, s_num, slot, s_slot;
struct net *net = sock_net(skb->sk);
+ bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
s_slot = cb->args[0];
num = s_num = cb->args[1];
@@ -132,7 +134,7 @@ static void udp_dump(struct udp_table *table, struct sk_buff *skb,
r->id.idiag_dport)
goto next;
- if (sk_diag_dump(sk, skb, cb, r, bc) < 0) {
+ if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0) {
spin_unlock_bh(&hslot->lock);
goto done;
}
@@ -165,12 +167,88 @@ static void udp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
r->idiag_wqueue = sk_wmem_alloc_get(sk);
}
+#ifdef CONFIG_INET_DIAG_DESTROY
+static int __udp_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *req,
+ struct udp_table *tbl)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sock *sk;
+ int err;
+
+ rcu_read_lock();
+
+ if (req->sdiag_family == AF_INET)
+ sk = __udp4_lib_lookup(net,
+ req->id.idiag_dst[0], req->id.idiag_dport,
+ req->id.idiag_src[0], req->id.idiag_sport,
+ req->id.idiag_if, tbl);
+#if IS_ENABLED(CONFIG_IPV6)
+ else if (req->sdiag_family == AF_INET6) {
+ if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+ ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+ sk = __udp4_lib_lookup(net,
+ req->id.idiag_dst[3], req->id.idiag_dport,
+ req->id.idiag_src[3], req->id.idiag_sport,
+ req->id.idiag_if, tbl);
+
+ else
+ sk = __udp6_lib_lookup(net,
+ (struct in6_addr *)req->id.idiag_dst,
+ req->id.idiag_dport,
+ (struct in6_addr *)req->id.idiag_src,
+ req->id.idiag_sport,
+ req->id.idiag_if, tbl);
+ }
+#endif
+ else {
+ rcu_read_unlock();
+ return -EINVAL;
+ }
+
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
+
+ rcu_read_unlock();
+
+ if (!sk)
+ return -ENOENT;
+
+ if (sock_diag_check_cookie(sk, req->id.idiag_cookie)) {
+ sock_put(sk);
+ return -ENOENT;
+ }
+
+ err = sock_diag_destroy(sk, ECONNABORTED);
+
+ sock_put(sk);
+
+ return err;
+}
+
+static int udp_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *req)
+{
+ return __udp_diag_destroy(in_skb, req, &udp_table);
+}
+
+static int udplite_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *req)
+{
+ return __udp_diag_destroy(in_skb, req, &udplite_table);
+}
+
+#endif
+
static const struct inet_diag_handler udp_diag_handler = {
.dump = udp_diag_dump,
.dump_one = udp_diag_dump_one,
.idiag_get_info = udp_diag_get_info,
.idiag_type = IPPROTO_UDP,
.idiag_info_size = 0,
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = udp_diag_destroy,
+#endif
};
static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
@@ -192,6 +270,9 @@ static const struct inet_diag_handler udplite_diag_handler = {
.idiag_get_info = udp_diag_get_info,
.idiag_type = IPPROTO_UDPLITE,
.idiag_info_size = 0,
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = udplite_diag_destroy,
+#endif
};
static int __init udp_diag_init(void)
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-22 23:41:47 +0000