summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c6
-rw-r--r--net/ipv4/icmp.c71
-rw-r--r--net/ipv4/inet_connection_sock.c28
-rw-r--r--net/ipv4/ip_sockglue.c553
-rw-r--r--net/ipv4/netfilter/arp_tables.c84
-rw-r--r--net/ipv4/netfilter/ip_tables.c85
-rw-r--r--net/ipv4/proc.c1
-rw-r--r--net/ipv4/raw.c22
-rw-r--r--net/ipv4/tcp.c24
-rw-r--r--net/ipv4/tcp_input.c81
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/udp.c24
-rw-r--r--net/ipv4/udp_impl.h6
-rw-r--r--net/ipv4/udplite.c4
14 files changed, 404 insertions, 593 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ff141d630bdf..4307503a6f0b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1043,8 +1043,6 @@ const struct proto_ops inet_stream_ops = {
.sendpage_locked = tcp_sendpage_locked,
.peek_len = tcp_peek_len,
#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
.set_rcvlowat = tcp_set_rcvlowat,
@@ -1073,8 +1071,6 @@ const struct proto_ops inet_dgram_ops = {
.sendpage = inet_sendpage,
.set_peek_off = sk_set_peek_off,
#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
};
@@ -1105,8 +1101,6 @@ static const struct proto_ops inet_sockraw_ops = {
.mmap = sock_no_mmap,
.sendpage = inet_sendpage,
#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
.compat_ioctl = inet_compat_ioctl,
#endif
};
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index e30515f89802..793aebf07c2a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1116,6 +1116,77 @@ error:
goto drop;
}
+static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off)
+{
+ struct icmp_extobj_hdr *objh, _objh;
+ struct icmp_ext_hdr *exth, _exth;
+ u16 olen;
+
+ exth = skb_header_pointer(skb, off, sizeof(_exth), &_exth);
+ if (!exth)
+ return false;
+ if (exth->version != 2)
+ return true;
+
+ if (exth->checksum &&
+ csum_fold(skb_checksum(skb, off, skb->len - off, 0)))
+ return false;
+
+ off += sizeof(_exth);
+ while (off < skb->len) {
+ objh = skb_header_pointer(skb, off, sizeof(_objh), &_objh);
+ if (!objh)
+ return false;
+
+ olen = ntohs(objh->length);
+ if (olen < sizeof(_objh))
+ return false;
+
+ off += olen;
+ if (off > skb->len)
+ return false;
+ }
+
+ return true;
+}
+
+void ip_icmp_error_rfc4884(const struct sk_buff *skb,
+ struct sock_ee_data_rfc4884 *out)
+{
+ int hlen, off;
+
+ switch (icmp_hdr(skb)->type) {
+ case ICMP_DEST_UNREACH:
+ case ICMP_TIME_EXCEEDED:
+ case ICMP_PARAMETERPROB:
+ break;
+ default:
+ return;
+ }
+
+ /* outer headers up to inner iph. skb->data is at inner payload */
+ hlen = -skb_transport_offset(skb) - sizeof(struct icmphdr);
+
+ /* per rfc 791: maximum packet length of 576 bytes */
+ if (hlen + skb->len > 576)
+ return;
+
+ /* per rfc 4884: minimal datagram length of 128 bytes */
+ off = icmp_hdr(skb)->un.reserved[1] * sizeof(u32);
+ if (off < 128)
+ return;
+
+ /* kernel has stripped headers: return payload offset in bytes */
+ off -= hlen;
+ if (off + sizeof(struct icmp_ext_hdr) > skb->len)
+ return;
+
+ out->len = off;
+
+ if (!ip_icmp_error_rfc4884_validate(skb, off))
+ out->flags |= SO_EE_RFC4884_FLAG_INVALID;
+}
+
int icmp_err(struct sk_buff *skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 22b0e7336360..d1a3913eebe0 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1057,34 +1057,6 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
}
EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
-#ifdef CONFIG_COMPAT
-int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_af_ops->compat_getsockopt)
- return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->getsockopt(sk, level, optname,
- optval, optlen);
-}
-EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
-
-int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- const struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_af_ops->compat_setsockopt)
- return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname,
- optval, optlen);
- return icsk->icsk_af_ops->setsockopt(sk, level, optname,
- optval, optlen);
-}
-EXPORT_SYMBOL_GPL(inet_csk_compat_setsockopt);
-#endif
-
static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
{
const struct inet_sock *inet = inet_sk(sk);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 84ec3703c909..a5ea02d7a183 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -411,6 +411,9 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err,
serr->port = port;
if (skb_pull(skb, payload - skb->data)) {
+ if (inet_sk(sk)->recverr_rfc4884)
+ ip_icmp_error_rfc4884(skb, &serr->ee.ee_rfc4884);
+
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb) == 0)
return;
@@ -679,20 +682,48 @@ Eaddrnotavail:
return -EADDRNOTAVAIL;
}
+static int copy_group_source_from_user(struct group_source_req *greqs,
+ void __user *optval, int optlen)
+{
+ if (in_compat_syscall()) {
+ struct compat_group_source_req gr32;
+
+ if (optlen != sizeof(gr32))
+ return -EINVAL;
+ if (copy_from_user(&gr32, optval, sizeof(gr32)))
+ return -EFAULT;
+ greqs->gsr_interface = gr32.gsr_interface;
+ greqs->gsr_group = gr32.gsr_group;
+ greqs->gsr_source = gr32.gsr_source;
+ } else {
+ if (optlen != sizeof(*greqs))
+ return -EINVAL;
+ if (copy_from_user(greqs, optval, sizeof(*greqs)))
+ return -EFAULT;
+ }
+
+ return 0;
+}
+
static int do_mcast_group_source(struct sock *sk, int optname,
- struct group_source_req *greqs)
+ void __user *optval, int optlen)
{
+ struct group_source_req greqs;
struct ip_mreq_source mreqs;
struct sockaddr_in *psin;
int omode, add, err;
- if (greqs->gsr_group.ss_family != AF_INET ||
- greqs->gsr_source.ss_family != AF_INET)
+ err = copy_group_source_from_user(&greqs, optval, optlen);
+ if (err)
+ return err;
+
+ if (greqs.gsr_group.ss_family != AF_INET ||
+ greqs.gsr_source.ss_family != AF_INET)
return -EADDRNOTAVAIL;
- psin = (struct sockaddr_in *)&greqs->gsr_group;
+ psin = (struct sockaddr_in *)&greqs.gsr_group;
mreqs.imr_multiaddr = psin->sin_addr.s_addr;
- psin = (struct sockaddr_in *)&greqs->gsr_source;
+ psin = (struct sockaddr_in *)&greqs.gsr_source;
mreqs.imr_sourceaddr = psin->sin_addr.s_addr;
mreqs.imr_interface = 0; /* use index for mc_source */
@@ -705,21 +736,142 @@ static int do_mcast_group_source(struct sock *sk, int optname,
} else if (optname == MCAST_JOIN_SOURCE_GROUP) {
struct ip_mreqn mreq;
- psin = (struct sockaddr_in *)&greqs->gsr_group;
+ psin = (struct sockaddr_in *)&greqs.gsr_group;
mreq.imr_multiaddr = psin->sin_addr;
mreq.imr_address.s_addr = 0;
- mreq.imr_ifindex = greqs->gsr_interface;
+ mreq.imr_ifindex = greqs.gsr_interface;
err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
if (err && err != -EADDRINUSE)
return err;
- greqs->gsr_interface = mreq.imr_ifindex;
+ greqs.gsr_interface = mreq.imr_ifindex;
omode = MCAST_INCLUDE;
add = 1;
} else /* MCAST_LEAVE_SOURCE_GROUP */ {
omode = MCAST_INCLUDE;
add = 0;
}
- return ip_mc_source(add, omode, sk, &mreqs, greqs->gsr_interface);
+ return ip_mc_source(add, omode, sk, &mreqs, greqs.gsr_interface);
+}
+
+static int ip_set_mcast_msfilter(struct sock *sk, void __user *optval,
+ int optlen)
+{
+ struct group_filter *gsf = NULL;
+ int err;
+
+ if (optlen < GROUP_FILTER_SIZE(0))
+ return -EINVAL;
+ if (optlen > sysctl_optmem_max)
+ return -ENOBUFS;
+
+ gsf = memdup_user(optval, optlen);
+ if (IS_ERR(gsf))
+ return PTR_ERR(gsf);
+
+ /* numsrc >= (4G-140)/128 overflow in 32 bits */
+ err = -ENOBUFS;
+ if (gsf->gf_numsrc >= 0x1ffffff ||
+ gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+ goto out_free_gsf;
+
+ err = -EINVAL;
+ if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen)
+ goto out_free_gsf;
+
+ err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc,
+ gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist);
+out_free_gsf:
+ kfree(gsf);
+ return err;
+}
+
+static int compat_ip_set_mcast_msfilter(struct sock *sk, void __user *optval,
+ int optlen)
+{
+ const int size0 = offsetof(struct compat_group_filter, gf_slist);
+ struct compat_group_filter *gf32;
+ unsigned int n;
+ void *p;
+ int err;
+
+ if (optlen < size0)
+ return -EINVAL;
+ if (optlen > sysctl_optmem_max - 4)
+ return -ENOBUFS;
+
+ p = kmalloc(optlen + 4, GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+ gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */
+
+ err = -EFAULT;
+ if (copy_from_user(gf32, optval, optlen))
+ goto out_free_gsf;
+
+ /* numsrc >= (4G-140)/128 overflow in 32 bits */
+ n = gf32->gf_numsrc;
+ err = -ENOBUFS;
+ if (n >= 0x1ffffff)
+ goto out_free_gsf;
+
+ err = -EINVAL;
+ if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen)
+ goto out_free_gsf;
+
+ /* numsrc >= (4G-140)/128 overflow in 32 bits */
+ err = -ENOBUFS;
+ if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+ goto out_free_gsf;
+ err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode,
+ &gf32->gf_group, gf32->gf_slist);
+out_free_gsf:
+ kfree(p);
+ return err;
+}
+
+static int ip_mcast_join_leave(struct sock *sk, int optname,
+ void __user *optval, int optlen)
+{
+ struct ip_mreqn mreq = { };
+ struct sockaddr_in *psin;
+ struct group_req greq;
+
+ if (optlen < sizeof(struct group_req))
+ return -EINVAL;
+ if (copy_from_user(&greq, optval, sizeof(greq)))
+ return -EFAULT;
+
+ psin = (struct sockaddr_in *)&greq.gr_group;
+ if (psin->sin_family != AF_INET)
+ return -EINVAL;
+ mreq.imr_multiaddr = psin->sin_addr;
+ mreq.imr_ifindex = greq.gr_interface;
+ if (optname == MCAST_JOIN_GROUP)
+ return ip_mc_join_group(sk, &mreq);
+ return ip_mc_leave_group(sk, &mreq);
+}
+
+static int compat_ip_mcast_join_leave(struct sock *sk, int optname,
+ void __user *optval, int optlen)
+{
+ struct compat_group_req greq;
+ struct ip_mreqn mreq = { };
+ struct sockaddr_in *psin;
+
+ if (optlen < sizeof(struct compat_group_req))
+ return -EINVAL;
+ if (copy_from_user(&greq, optval, sizeof(greq)))
+ return -EFAULT;
+
+ psin = (struct sockaddr_in *)&greq.gr_group;
+ if (psin->sin_family != AF_INET)
+ return -EINVAL;
+ mreq.imr_multiaddr = psin->sin_addr;
+ mreq.imr_ifindex = greq.gr_interface;
+
+ if (optname == MCAST_JOIN_GROUP)
+ return ip_mc_join_group(sk, &mreq);
+ return ip_mc_leave_group(sk, &mreq);
}
static int do_ip_setsockopt(struct sock *sk, int level,
@@ -755,6 +907,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
case IP_RECVORIGDSTADDR:
case IP_CHECKSUM:
case IP_RECVFRAGSIZE:
+ case IP_RECVERR_RFC4884:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
@@ -914,6 +1067,11 @@ static int do_ip_setsockopt(struct sock *sk, int level,
if (!val)
skb_queue_purge(&sk->sk_error_queue);
break;
+ case IP_RECVERR_RFC4884:
+ if (val < 0 || val > 1)
+ goto e_inval;
+ inet->recverr_rfc4884 = !!val;
+ break;
case IP_MULTICAST_TTL:
if (sk->sk_type == SOCK_STREAM)
goto e_inval;
@@ -1127,77 +1285,24 @@ static int do_ip_setsockopt(struct sock *sk, int level,
}
case MCAST_JOIN_GROUP:
case MCAST_LEAVE_GROUP:
- {
- struct group_req greq;
- struct sockaddr_in *psin;
- struct ip_mreqn mreq;
-
- if (optlen < sizeof(struct group_req))
- goto e_inval;
- err = -EFAULT;
- if (copy_from_user(&greq, optval, sizeof(greq)))
- break;
- psin = (struct sockaddr_in *)&greq.gr_group;
- if (psin->sin_family != AF_INET)
- goto e_inval;
- memset(&mreq, 0, sizeof(mreq));
- mreq.imr_multiaddr = psin->sin_addr;
- mreq.imr_ifindex = greq.gr_interface;
-
- if (optname == MCAST_JOIN_GROUP)
- err = ip_mc_join_group(sk, &mreq);
+ if (in_compat_syscall())
+ err = compat_ip_mcast_join_leave(sk, optname, optval,
+ optlen);
else
- err = ip_mc_leave_group(sk, &mreq);
+ err = ip_mcast_join_leave(sk, optname, optval, optlen);
break;
- }
case MCAST_JOIN_SOURCE_GROUP:
case MCAST_LEAVE_SOURCE_GROUP:
case MCAST_BLOCK_SOURCE:
case MCAST_UNBLOCK_SOURCE:
- {
- struct group_source_req greqs;
-
- if (optlen != sizeof(struct group_source_req))
- goto e_inval;
- if (copy_from_user(&greqs, optval, sizeof(greqs))) {
- err = -EFAULT;
- break;
- }
- err = do_mcast_group_source(sk, optname, &greqs);
+ err = do_mcast_group_source(sk, optname, optval, optlen);
break;
- }
case MCAST_MSFILTER:
- {
- struct group_filter *gsf = NULL;
-
- if (optlen < GROUP_FILTER_SIZE(0))
- goto e_inval;
- if (optlen > sysctl_optmem_max) {
- err = -ENOBUFS;
- break;
- }
- gsf = memdup_user(optval, optlen);
- if (IS_ERR(gsf)) {
- err = PTR_ERR(gsf);
- break;
- }
- /* numsrc >= (4G-140)/128 overflow in 32 bits */
- if (gsf->gf_numsrc >= 0x1ffffff ||
- gsf->gf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
- err = -ENOBUFS;
- goto mc_msf_out;
- }
- if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) {
- err = -EINVAL;
- goto mc_msf_out;
- }
- err = set_mcast_msfilter(sk, gsf->gf_interface,
- gsf->gf_numsrc, gsf->gf_fmode,
- &gsf->gf_group, gsf->gf_slist);
-mc_msf_out:
- kfree(gsf);
+ if (in_compat_syscall())
+ err = compat_ip_set_mcast_msfilter(sk, optval, optlen);
+ else
+ err = ip_set_mcast_msfilter(sk, optval, optlen);
break;
- }
case IP_MULTICAST_ALL:
if (optlen < 1)
goto e_inval;
@@ -1322,138 +1427,6 @@ int ip_setsockopt(struct sock *sk, int level,
}
EXPORT_SYMBOL(ip_setsockopt);
-#ifdef CONFIG_COMPAT
-int compat_ip_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- int err;
-
- if (level != SOL_IP)
- return -ENOPROTOOPT;
-
- switch (optname) {
- case MCAST_JOIN_GROUP:
- case MCAST_LEAVE_GROUP:
- {
- struct compat_group_req __user *gr32 = (void __user *)optval;
- struct group_req greq;
- struct sockaddr_in *psin = (struct sockaddr_in *)&greq.gr_group;
- struct ip_mreqn mreq;
-
- if (optlen < sizeof(struct compat_group_req))
- return -EINVAL;
-
- if (get_user(greq.gr_interface, &gr32->gr_interface) ||
- copy_from_user(&greq.gr_group, &gr32->gr_group,
- sizeof(greq.gr_group)))
- return -EFAULT;
-
- if (psin->sin_family != AF_INET)
- return -EINVAL;
-
- memset(&mreq, 0, sizeof(mreq));
- mreq.imr_multiaddr = psin->sin_addr;
- mreq.imr_ifindex = greq.gr_interface;
-
- rtnl_lock();
- lock_sock(sk);
- if (optname == MCAST_JOIN_GROUP)
- err = ip_mc_join_group(sk, &mreq);
- else
- err = ip_mc_leave_group(sk, &mreq);
- release_sock(sk);
- rtnl_unlock();
- return err;
- }
- case MCAST_JOIN_SOURCE_GROUP:
- case MCAST_LEAVE_SOURCE_GROUP:
- case MCAST_BLOCK_SOURCE:
- case MCAST_UNBLOCK_SOURCE:
- {
- struct compat_group_source_req __user *gsr32 = (void __user *)optval;
- struct group_source_req greqs;
-
- if (optlen != sizeof(struct compat_group_source_req))
- return -EINVAL;
-
- if (get_user(greqs.gsr_interface, &gsr32->gsr_interface) ||
- copy_from_user(&greqs.gsr_group, &gsr32->gsr_group,
- sizeof(greqs.gsr_group)) ||
- copy_from_user(&greqs.gsr_source, &gsr32->gsr_source,
- sizeof(greqs.gsr_source)))
- return -EFAULT;
-
- rtnl_lock();
- lock_sock(sk);
- err = do_mcast_group_source(sk, optname, &greqs);
- release_sock(sk);
- rtnl_unlock();
- return err;
- }
- case MCAST_MSFILTER:
- {
- const int size0 = offsetof(struct compat_group_filter, gf_slist);
- struct compat_group_filter *gf32;
- unsigned int n;
- void *p;
-
- if (optlen < size0)
- return -EINVAL;
- if (optlen > sysctl_optmem_max - 4)
- return -ENOBUFS;
-
- p = kmalloc(optlen + 4, GFP_KERNEL);
- if (!p)
- return -ENOMEM;
- gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */
- if (copy_from_user(gf32, optval, optlen)) {
- err = -EFAULT;
- goto mc_msf_out;
- }
-
- n = gf32->gf_numsrc;
- /* numsrc >= (4G-140)/128 overflow in 32 bits */
- if (n >= 0x1ffffff) {
- err = -ENOBUFS;
- goto mc_msf_out;
- }
- if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) {
- err = -EINVAL;
- goto mc_msf_out;
- }
-
- rtnl_lock();
- lock_sock(sk);
- /* numsrc >= (4G-140)/128 overflow in 32 bits */
- if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
- err = -ENOBUFS;
- else
- err = set_mcast_msfilter(sk, gf32->gf_interface,
- n, gf32->gf_fmode,
- &gf32->gf_group, gf32->gf_slist);
- release_sock(sk);
- rtnl_unlock();
-mc_msf_out:
- kfree(p);
- return err;
- }
- }
-
- err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#ifdef CONFIG_NETFILTER
- /* we need to exclude all possible ENOPROTOOPTs except default case */
- if (err == -ENOPROTOOPT && optname != IP_HDRINCL &&
- optname != IP_IPSEC_POLICY &&
- optname != IP_XFRM_POLICY &&
- !ip_mroute_opt(optname))
- err = compat_nf_setsockopt(sk, PF_INET, optname, optval,
- optlen);
-#endif
- return err;
-}
-EXPORT_SYMBOL(compat_ip_setsockopt);
-#endif
-
/*
* Get the options. Note for future reference. The GET of IP options gets
* the _received_ ones. The set sets the _sent_ ones.
@@ -1469,8 +1442,67 @@ static bool getsockopt_needs_rtnl(int optname)
return false;
}
+static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
+ int __user *optlen, int len)
+{
+ const int size0 = offsetof(struct group_filter, gf_slist);
+ struct group_filter __user *p = optval;
+ struct group_filter gsf;
+ int num;
+ int err;
+
+ if (len < size0)
+ return -EINVAL;
+ if (copy_from_user(&gsf, p, size0))
+ return -EFAULT;
+
+ num = gsf.gf_numsrc;
+ err = ip_mc_gsfget(sk, &gsf, p->gf_slist);
+ if (err)
+ return err;
+ if (gsf.gf_numsrc < num)
+ num = gsf.gf_numsrc;
+ if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
+ copy_to_user(p, &gsf, size0))
+ return -EFAULT;
+ return 0;
+}
+
+static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval,
+ int __user *optlen, int len)
+{
+ const int size0 = offsetof(struct compat_group_filter, gf_slist);
+ struct compat_group_filter __user *p = optval;
+ struct compat_group_filter gf32;
+ struct group_filter gf;
+ int num;
+ int err;
+
+ if (len < size0)
+ return -EINVAL;
+ if (copy_from_user(&gf32, p, size0))
+ return -EFAULT;
+
+ gf.gf_interface = gf32.gf_interface;
+ gf.gf_fmode = gf32.gf_fmode;
+ num = gf.gf_numsrc = gf32.gf_numsrc;
+ gf.gf_group = gf32.gf_group;
+
+ err = ip_mc_gsfget(sk, &gf, p->gf_slist);
+ if (err)
+ return err;
+ if (gf.gf_numsrc < num)
+ num = gf.gf_numsrc;
+ len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32));
+ if (put_user(len, optlen) ||
+ put_user(gf.gf_fmode, &p->gf_fmode) ||
+ put_user(gf.gf_numsrc, &p->gf_numsrc))
+ return -EFAULT;
+ return 0;
+}
+
static int do_ip_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen, unsigned int flags)
+ char __user *optval, int __user *optlen)
{
struct inet_sock *inet = inet_sk(sk);
bool needs_rtnl = getsockopt_needs_rtnl(optname);
@@ -1588,6 +1620,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
case IP_RECVERR:
val = inet->recverr;
break;
+ case IP_RECVERR_RFC4884:
+ val = inet->recverr_rfc4884;
+ break;
case IP_MULTICAST_TTL:
val = inet->mc_ttl;
break;
@@ -1627,31 +1662,12 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
goto out;
}
case MCAST_MSFILTER:
- {
- struct group_filter __user *p = (void __user *)optval;
- struct group_filter gsf;
- const int size0 = offsetof(struct group_filter, gf_slist);
- int num;
-
- if (len < size0) {
- err = -EINVAL;
- goto out;
- }
- if (copy_from_user(&gsf, p, size0)) {
- err = -EFAULT;
- goto out;
- }
- num = gsf.gf_numsrc;
- err = ip_mc_gsfget(sk, &gsf, p->gf_slist);
- if (err)
- goto out;
- if (gsf.gf_numsrc < num)
- num = gsf.gf_numsrc;
- if (put_user(GROUP_FILTER_SIZE(num), optlen) ||
- copy_to_user(p, &gsf, size0))
- err = -EFAULT;
+ if (in_compat_syscall())
+ err = compat_ip_get_mcast_msfilter(sk, optval, optlen,
+ len);
+ else
+ err = ip_get_mcast_msfilter(sk, optval, optlen, len);
goto out;
- }
case IP_MULTICAST_ALL:
val = inet->mc_all;
break;
@@ -1667,7 +1683,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
msg.msg_control_is_user = true;
msg.msg_control_user = optval;
msg.msg_controllen = len;
- msg.msg_flags = flags;
+ msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0;
if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
struct in_pktinfo info;
@@ -1731,7 +1747,8 @@ int ip_getsockopt(struct sock *sk, int level,
{
int err;
- err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0);
+ err = do_ip_getsockopt(sk, level, optname, optval, optlen);
+
#if IS_ENABLED(CONFIG_BPFILTER_UMH)
if (optname >= BPFILTER_IPT_SO_GET_INFO &&
optname < BPFILTER_IPT_GET_MAX)
@@ -1755,79 +1772,3 @@ int ip_getsockopt(struct sock *sk, int level,
return err;
}
EXPORT_SYMBOL(ip_getsockopt);
-
-#ifdef CONFIG_COMPAT
-int compat_ip_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- int err;
-
- if (optname == MCAST_MSFILTER) {
- const int size0 = offsetof(struct compat_group_filter, gf_slist);
- struct compat_group_filter __user *p = (void __user *)optval;
- struct compat_group_filter gf32;
- struct group_filter gf;
- int ulen, err;
- int num;
-
- if (level != SOL_IP)
- return -EOPNOTSUPP;
-
- if (get_user(ulen, optlen))
- return -EFAULT;
-
- if (ulen < size0)
- return -EINVAL;
-
- if (copy_from_user(&gf32, p, size0))
- return -EFAULT;
-
- gf.gf_interface = gf32.gf_interface;
- gf.gf_fmode = gf32.gf_fmode;
- num = gf.gf_numsrc = gf32.gf_numsrc;
- gf.gf_group = gf32.gf_group;
-
- rtnl_lock();
- lock_sock(sk);
- err = ip_mc_gsfget(sk, &gf, p->gf_slist);
- release_sock(sk);
- rtnl_unlock();
- if (err)
- return err;
- if (gf.gf_numsrc < num)
- num = gf.gf_numsrc;
- ulen = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32));
- if (put_user(ulen, optlen) ||
- put_user(gf.gf_fmode, &p->gf_fmode) ||
- put_user(gf.gf_numsrc, &p->gf_numsrc))
- return -EFAULT;
- return 0;
- }
-
- err = do_ip_getsockopt(sk, level, optname, optval, optlen,
- MSG_CMSG_COMPAT);
-
-#if IS_ENABLED(CONFIG_BPFILTER_UMH)
- if (optname >= BPFILTER_IPT_SO_GET_INFO &&
- optname < BPFILTER_IPT_GET_MAX)
- err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
-#endif
-#ifdef CONFIG_NETFILTER
- /* we need to exclude all possible ENOPROTOOPTs except default case */
- if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS &&
- !ip_mroute_opt(optname)) {
- int len;
-
- if (get_user(len, optlen))
- return -EFAULT;
-
- err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len);
- if (err >= 0)
- err = put_user(len, optlen);
- return err;
- }
-#endif
- return err;
-}
-EXPORT_SYMBOL(compat_ip_getsockopt);
-#endif
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b167f4a5b684..2c8a4dad39d7 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -787,8 +787,7 @@ static int compat_table_info(const struct xt_table_info *info,
}
#endif
-static int get_info(struct net *net, void __user *user,
- const int *len, int compat)
+static int get_info(struct net *net, void __user *user, const int *len)
{
char name[XT_TABLE_MAXNAMELEN];
struct xt_table *t;
@@ -802,7 +801,7 @@ static int get_info(struct net *net, void __user *user,
name[XT_TABLE_MAXNAMELEN-1] = '\0';
#ifdef CONFIG_COMPAT
- if (compat)
+ if (in_compat_syscall())
xt_compat_lock(NFPROTO_ARP);
#endif
t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
@@ -812,7 +811,7 @@ static int get_info(struct net *net, void __user *user,
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
- if (compat) {
+ if (in_compat_syscall()) {
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(NFPROTO_ARP);
private = &tmp;
@@ -837,7 +836,7 @@ static int get_info(struct net *net, void __user *user,
} else
ret = PTR_ERR(t);
#ifdef CONFIG_COMPAT
- if (compat)
+ if (in_compat_syscall())
xt_compat_unlock(NFPROTO_ARP);
#endif
return ret;
@@ -998,7 +997,7 @@ static int do_replace(struct net *net, const void __user *user,
}
static int do_add_counters(struct net *net, const void __user *user,
- unsigned int len, int compat)
+ unsigned int len)
{
unsigned int i;
struct xt_counters_info tmp;
@@ -1009,7 +1008,7 @@ static int do_add_counters(struct net *net, const void __user *user,
struct arpt_entry *iter;
unsigned int addend;
- paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+ paddc = xt_copy_counters_from_user(user, len, &tmp);
if (IS_ERR(paddc))
return PTR_ERR(paddc);
@@ -1294,30 +1293,6 @@ static int compat_do_replace(struct net *net, void __user *user,
return ret;
}
-static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user,
- unsigned int len)
-{
- int ret;
-
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
-
- switch (cmd) {
- case ARPT_SO_SET_REPLACE:
- ret = compat_do_replace(sock_net(sk), user, len);
- break;
-
- case ARPT_SO_SET_ADD_COUNTERS:
- ret = do_add_counters(sock_net(sk), user, len, 1);
- break;
-
- default:
- ret = -EINVAL;
- }
-
- return ret;
-}
-
static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr,
compat_uint_t *size,
struct xt_counters *counters,
@@ -1425,29 +1400,6 @@ static int compat_get_entries(struct net *net,
xt_compat_unlock(NFPROTO_ARP);
return ret;
}
-
-static int do_arpt_get_ctl(struct sock *, int, void __user *, int *);
-
-static int compat_do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user,
- int *len)
-{
- int ret;
-
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
-
- switch (cmd) {
- case ARPT_SO_GET_INFO:
- ret = get_info(sock_net(sk), user, len, 1);
- break;
- case ARPT_SO_GET_ENTRIES:
- ret = compat_get_entries(sock_net(sk), user, len);
- break;
- default:
- ret = do_arpt_get_ctl(sk, cmd, user, len);
- }
- return ret;
-}
#endif
static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
@@ -1459,11 +1411,16 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned
switch (cmd) {
case ARPT_SO_SET_REPLACE:
- ret = do_replace(sock_net(sk), user, len);
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = compat_do_replace(sock_net(sk), user, len);
+ else
+#endif
+ ret = do_replace(sock_net(sk), user, len);
break;
case ARPT_SO_SET_ADD_COUNTERS:
- ret = do_add_counters(sock_net(sk), user, len, 0);
+ ret = do_add_counters(sock_net(sk), user, len);
break;
default:
@@ -1482,11 +1439,16 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len
switch (cmd) {
case ARPT_SO_GET_INFO:
- ret = get_info(sock_net(sk), user, len, 0);
+ ret = get_info(sock_net(sk), user, len);
break;
case ARPT_SO_GET_ENTRIES:
- ret = get_entries(sock_net(sk), user, len);
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = compat_get_entries(sock_net(sk), user, len);
+ else
+#endif
+ ret = get_entries(sock_net(sk), user, len);
break;
case ARPT_SO_GET_REVISION_TARGET: {
@@ -1610,15 +1572,9 @@ static struct nf_sockopt_ops arpt_sockopts = {
.set_optmin = ARPT_BASE_CTL,
.set_optmax = ARPT_SO_SET_MAX+1,
.set = do_arpt_set_ctl,
-#ifdef CONFIG_COMPAT
- .compat_set = compat_do_arpt_set_ctl,
-#endif
.get_optmin = ARPT_BASE_CTL,
.get_optmax = ARPT_SO_GET_MAX+1,
.get = do_arpt_get_ctl,
-#ifdef CONFIG_COMPAT
- .compat_get = compat_do_arpt_get_ctl,
-#endif
.owner = THIS_MODULE,
};
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 5bf9fa06aee0..161901dd1cae 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -944,8 +944,7 @@ static int compat_table_info(const struct xt_table_info *info,
}
#endif
-static int get_info(struct net *net, void __user *user,
- const int *len, int compat)
+static int get_info(struct net *net, void __user *user, const int *len)
{
char name[XT_TABLE_MAXNAMELEN];
struct xt_table *t;
@@ -959,7 +958,7 @@ static int get_info(struct net *net, void __user *user,
name[XT_TABLE_MAXNAMELEN-1] = '\0';
#ifdef CONFIG_COMPAT
- if (compat)
+ if (in_compat_syscall())
xt_compat_lock(AF_INET);
#endif
t = xt_request_find_table_lock(net, AF_INET, name);
@@ -969,7 +968,7 @@ static int get_info(struct net *net, void __user *user,
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
- if (compat) {
+ if (in_compat_syscall()) {
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(AF_INET);
private = &tmp;
@@ -995,7 +994,7 @@ static int get_info(struct net *net, void __user *user,
} else
ret = PTR_ERR(t);
#ifdef CONFIG_COMPAT
- if (compat)
+ if (in_compat_syscall())
xt_compat_unlock(AF_INET);
#endif
return ret;
@@ -1153,7 +1152,7 @@ do_replace(struct net *net, const void __user *user, unsigned int len)
static int
do_add_counters(struct net *net, const void __user *user,
- unsigned int len, int compat)
+ unsigned int len)
{
unsigned int i;
struct xt_counters_info tmp;
@@ -1164,7 +1163,7 @@ do_add_counters(struct net *net, const void __user *user,
struct ipt_entry *iter;
unsigned int addend;
- paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+ paddc = xt_copy_counters_from_user(user, len, &tmp);
if (IS_ERR(paddc))
return PTR_ERR(paddc);
@@ -1534,31 +1533,6 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
return ret;
}
-static int
-compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user,
- unsigned int len)
-{
- int ret;
-
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
-
- switch (cmd) {
- case IPT_SO_SET_REPLACE:
- ret = compat_do_replace(sock_net(sk), user, len);
- break;
-
- case IPT_SO_SET_ADD_COUNTERS:
- ret = do_add_counters(sock_net(sk), user, len, 1);
- break;
-
- default:
- ret = -EINVAL;
- }
-
- return ret;
-}
-
struct compat_ipt_get_entries {
char name[XT_TABLE_MAXNAMELEN];
compat_uint_t size;
@@ -1634,29 +1608,6 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
xt_compat_unlock(AF_INET);
return ret;
}
-
-static int do_ipt_get_ctl(struct sock *, int, void __user *, int *);
-
-static int
-compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
-{
- int ret;
-
- if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
- return -EPERM;
-
- switch (cmd) {
- case IPT_SO_GET_INFO:
- ret = get_info(sock_net(sk), user, len, 1);
- break;
- case IPT_SO_GET_ENTRIES:
- ret = compat_get_entries(sock_net(sk), user, len);
- break;
- default:
- ret = do_ipt_get_ctl(sk, cmd, user, len);
- }
- return ret;
-}
#endif
static int
@@ -1669,11 +1620,16 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
switch (cmd) {
case IPT_SO_SET_REPLACE:
- ret = do_replace(sock_net(sk), user, len);
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = compat_do_replace(sock_net(sk), user, len);
+ else
+#endif
+ ret = do_replace(sock_net(sk), user, len);
break;
case IPT_SO_SET_ADD_COUNTERS:
- ret = do_add_counters(sock_net(sk), user, len, 0);
+ ret = do_add_counters(sock_net(sk), user, len);
break;
default:
@@ -1693,11 +1649,16 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
switch (cmd) {
case IPT_SO_GET_INFO:
- ret = get_info(sock_net(sk), user, len, 0);
+ ret = get_info(sock_net(sk), user, len);
break;
case IPT_SO_GET_ENTRIES:
- ret = get_entries(sock_net(sk), user, len);
+#ifdef CONFIG_COMPAT
+ if (in_compat_syscall())
+ ret = compat_get_entries(sock_net(sk), user, len);
+ else
+#endif
+ ret = get_entries(sock_net(sk), user, len);
break;
case IPT_SO_GET_REVISION_MATCH:
@@ -1886,15 +1847,9 @@ static struct nf_sockopt_ops ipt_sockopts = {
.set_optmin = IPT_BASE_CTL,
.set_optmax = IPT_SO_SET_MAX+1,
.set = do_ipt_set_ctl,
-#ifdef CONFIG_COMPAT
- .compat_set = compat_do_ipt_set_ctl,
-#endif
.get_optmin = IPT_BASE_CTL,
.get_optmax = IPT_SO_GET_MAX+1,
.get = do_ipt_get_ctl,
-#ifdef CONFIG_COMPAT
- .compat_get = compat_do_ipt_get_ctl,
-#endif
.owner = THIS_MODULE,
};
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 75545a829a2b..1074df726ec0 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -292,6 +292,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPFastOpenPassiveAltKey", LINUX_MIB_TCPFASTOPENPASSIVEALTKEY),
SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH),
SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH),
+ SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 47665919048f..2a57d633b31e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -857,16 +857,6 @@ static int raw_setsockopt(struct sock *sk, int level, int optname,
return do_raw_setsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- if (level != SOL_RAW)
- return compat_ip_setsockopt(sk, level, optname, optval, optlen);
- return do_raw_setsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
static int do_raw_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -887,16 +877,6 @@ static int raw_getsockopt(struct sock *sk, int level, int optname,
return do_raw_getsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level != SOL_RAW)
- return compat_ip_getsockopt(sk, level, optname, optval, optlen);
- return do_raw_getsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
switch (cmd) {
@@ -980,8 +960,6 @@ struct proto raw_prot = {
.usersize = sizeof_field(struct raw_sock, filter),
.h.raw_hash = &raw_v4_hashinfo,
#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_raw_setsockopt,
- .compat_getsockopt = compat_raw_getsockopt,
.compat_ioctl = compat_raw_ioctl,
#endif
.diag_destroy = raw_abort,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 254b6a4cc95b..58ede3d62b2e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3337,18 +3337,6 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval,
}
EXPORT_SYMBOL(tcp_setsockopt);
-#ifdef CONFIG_COMPAT
-int compat_tcp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- if (level != SOL_TCP)
- return inet_csk_compat_setsockopt(sk, level, optname,
- optval, optlen);
- return do_tcp_setsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(compat_tcp_setsockopt);
-#endif
-
static void tcp_get_info_chrono_stats(const struct tcp_sock *tp,
struct tcp_info *info)
{
@@ -3896,18 +3884,6 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
}
EXPORT_SYMBOL(tcp_getsockopt);
-#ifdef CONFIG_COMPAT
-int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level != SOL_TCP)
- return inet_csk_compat_getsockopt(sk, level, optname,
- optval, optlen);
- return do_tcp_getsockopt(sk, level, optname, optval, optlen);
-}
-EXPORT_SYMBOL(compat_tcp_getsockopt);
-#endif
-
#ifdef CONFIG_TCP_MD5SIG
static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
static DEFINE_MUTEX(tcp_md5sig_mutex);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b03ca68d4111..82906deb7874 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -871,12 +871,41 @@ __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst)
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
+struct tcp_sacktag_state {
+ /* Timestamps for earliest and latest never-retransmitted segment
+ * that was SACKed. RTO needs the earliest RTT to stay conservative,
+ * but congestion control should still get an accurate delay signal.
+ */
+ u64 first_sackt;
+ u64 last_sackt;
+ u32 reord;
+ u32 sack_delivered;
+ int flag;
+ unsigned int mss_now;
+ struct rate_sample *rate;
+};
+
/* Take a notice that peer is sending D-SACKs */
-static void tcp_dsack_seen(struct tcp_sock *tp)
+static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq,
+ u32 end_seq, struct tcp_sacktag_state *state)
{
+ u32 seq_len, dup_segs = 1;
+
+ if (before(start_seq, end_seq)) {
+ seq_len = end_seq - start_seq;
+ if (seq_len > tp->mss_cache)
+ dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache);
+ }
+
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
tp->rack.dsack_seen = 1;
- tp->dsack_dups++;
+ tp->dsack_dups += dup_segs;
+
+ state->flag |= FLAG_DSACKING_ACK;
+ /* A spurious retransmission is delivered */
+ state->sack_delivered += dup_segs;
+
+ return dup_segs;
}
/* It's reordering when higher sequence was delivered (i.e. sacked) before
@@ -1103,53 +1132,38 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack,
static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb,
struct tcp_sack_block_wire *sp, int num_sacks,
- u32 prior_snd_una)
+ u32 prior_snd_una, struct tcp_sacktag_state *state)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 start_seq_0 = get_unaligned_be32(&sp[0].start_seq);
u32 end_seq_0 = get_unaligned_be32(&sp[0].end_seq);
- bool dup_sack = false;
+ u32 dup_segs;
if (before(start_seq_0, TCP_SKB_CB(ack_skb)->ack_seq)) {
- dup_sack = true;
- tcp_dsack_seen(tp);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECV);
} else if (num_sacks > 1) {
u32 end_seq_1 = get_unaligned_be32(&sp[1].end_seq);
u32 start_seq_1 = get_unaligned_be32(&sp[1].start_seq);
- if (!after(end_seq_0, end_seq_1) &&
- !before(start_seq_0, start_seq_1)) {
- dup_sack = true;
- tcp_dsack_seen(tp);
- NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPDSACKOFORECV);
- }
+ if (after(end_seq_0, end_seq_1) || before(start_seq_0, start_seq_1))
+ return false;
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKOFORECV);
+ } else {
+ return false;
}
+ dup_segs = tcp_dsack_seen(tp, start_seq_0, end_seq_0, state);
+ NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECVSEGS, dup_segs);
+
/* D-SACK for already forgotten data... Do dumb counting. */
- if (dup_sack && tp->undo_marker && tp->undo_retrans > 0 &&
+ if (tp->undo_marker && tp->undo_retrans > 0 &&
!after(end_seq_0, prior_snd_una) &&
after(end_seq_0, tp->undo_marker))
- tp->undo_retrans--;
+ tp->undo_retrans = max_t(int, 0, tp->undo_retrans - dup_segs);
- return dup_sack;
+ return true;
}
-struct tcp_sacktag_state {
- u32 reord;
- /* Timestamps for earliest and latest never-retransmitted segment
- * that was SACKed. RTO needs the earliest RTT to stay conservative,
- * but congestion control should still get an accurate delay signal.
- */
- u64 first_sackt;
- u64 last_sackt;
- struct rate_sample *rate;
- int flag;
- unsigned int mss_now;
- u32 sack_delivered;
-};
-
/* Check if skb is fully within the SACK block. In presence of GSO skbs,
* the incoming SACK may not exactly match but we can find smaller MSS
* aligned portion of it that matches. Therefore we might need to fragment
@@ -1692,12 +1706,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb,
tcp_highest_sack_reset(sk);
found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire,
- num_sacks, prior_snd_una);
- if (found_dup_sack) {
- state->flag |= FLAG_DSACKING_ACK;
- /* A spurious retransmission is delivered */
- state->sack_delivered++;
- }
+ num_sacks, prior_snd_una, state);
/* Eliminate too old ACKs, but take into
* account more or less fresh ones, they can
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a7f1b41482f8..daa39d33702b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2135,10 +2135,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_ip_setsockopt,
- .compat_getsockopt = compat_ip_getsockopt,
-#endif
.mtu_reduced = tcp_v4_mtu_reduced,
};
EXPORT_SYMBOL(ipv4_specific);
@@ -2774,10 +2770,6 @@ struct proto tcp_prot = {
.rsk_prot = &tcp_request_sock_ops,
.h.hashinfo = &tcp_hashinfo,
.no_autobind = true,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_tcp_setsockopt,
- .compat_getsockopt = compat_tcp_getsockopt,
-#endif
.diag_destroy = tcp_abort,
};
EXPORT_SYMBOL(tcp_prot);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b5231ab350e0..bb95cddcb040 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2712,17 +2712,6 @@ int udp_setsockopt(struct sock *sk, int level, int optname,
return ip_setsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-int compat_udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- if (level == SOL_UDP || level == SOL_UDPLITE)
- return udp_lib_setsockopt(sk, level, optname, optval, optlen,
- udp_push_pending_frames);
- return compat_ip_setsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -2788,15 +2777,6 @@ int udp_getsockopt(struct sock *sk, int level, int optname,
return ip_getsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-int compat_udp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level == SOL_UDP || level == SOL_UDPLITE)
- return udp_lib_getsockopt(sk, level, optname, optval, optlen);
- return compat_ip_getsockopt(sk, level, optname, optval, optlen);
-}
-#endif
/**
* udp_poll - wait for a UDP event.
* @file: - file struct
@@ -2868,10 +2848,6 @@ struct proto udp_prot = {
.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
.obj_size = sizeof(struct udp_sock),
.h.udp_table = &udp_table,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_udp_setsockopt,
- .compat_getsockopt = compat_udp_getsockopt,
-#endif
.diag_destroy = udp_abort,
};
EXPORT_SYMBOL(udp_prot);
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 6b2fa77eeb1c..ab313702c87f 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -17,12 +17,6 @@ int udp_setsockopt(struct sock *sk, int level, int optname,
int udp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
-#ifdef CONFIG_COMPAT
-int compat_udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen);
-int compat_udp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen);
-#endif
int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
int flags, int *addr_len);
int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 5936d66d1ce2..bd8773b49e72 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -56,10 +56,6 @@ struct proto udplite_prot = {
.sysctl_mem = sysctl_udp_mem,
.obj_size = sizeof(struct udp_sock),
.h.udp_table = &udplite_table,
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_udp_setsockopt,
- .compat_getsockopt = compat_udp_getsockopt,
-#endif
};
EXPORT_SYMBOL(udplite_prot);
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-04 22:44:16 +0300