linux_dsm_epyc7002/net/ipv4/raw.c

1157 lines
27 KiB
C
Raw Normal View History

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* RAW - implementation of IP "raw" sockets.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* Fixes:
* Alan Cox : verify_area() fixed up
* Alan Cox : ICMP error handling
* Alan Cox : EMSGSIZE if you send too big a packet
* Alan Cox : Now uses generic datagrams and shared
* skbuff library. No more peek crashes,
* no more backlogs
* Alan Cox : Checks sk->broadcast.
* Alan Cox : Uses skb_free_datagram/skb_copy_datagram
* Alan Cox : Raw passes ip options too
* Alan Cox : Setsocketopt added
* Alan Cox : Fixed error return for broadcasts
* Alan Cox : Removed wake_up calls
* Alan Cox : Use ttl/tos
* Alan Cox : Cleaned up old debugging
* Alan Cox : Use new kernel side addresses
* Arnt Gulbrandsen : Fixed MSG_DONTROUTE in raw sockets.
* Alan Cox : BSD style RAW socket demultiplexing.
* Alan Cox : Beginnings of mrouted support.
* Alan Cox : Added IP_HDRINCL option.
* Alan Cox : Skip broadcast check if BSDism set.
* David S. Miller : New socket lookup architecture.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/types.h>
#include <linux/atomic.h>
#include <asm/byteorder.h>
#include <asm/current.h>
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <linux/stddef.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/mroute.h>
#include <linux/netdevice.h>
#include <linux/in_route.h>
#include <linux/route.h>
#include <linux/skbuff.h>
#include <linux/igmp.h>
#include <net/net_namespace.h>
#include <net/dst.h>
#include <net/sock.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/snmp.h>
#include <net/tcp_states.h>
#include <net/inet_common.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/compat.h>
#include <linux/uio.h>
struct raw_frag_vec {
struct msghdr *msg;
union {
struct icmphdr icmph;
char c[1];
} hdr;
int hlen;
};
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
int raw_hash_sk(struct sock *sk)
{
struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
struct hlist_head *head;
head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];
write_lock_bh(&h->lock);
sk_add_node(sk, head);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
write_unlock_bh(&h->lock);
return 0;
}
EXPORT_SYMBOL_GPL(raw_hash_sk);
void raw_unhash_sk(struct sock *sk)
{
struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
write_lock_bh(&h->lock);
if (sk_del_node_init(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
write_unlock_bh(&h->lock);
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
unsigned short num, __be32 raddr, __be32 laddr,
int dif, int sdif)
{
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 08:06:00 +07:00
sk_for_each_from(sk) {
struct inet_sock *inet = inet_sk(sk);
if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
!(inet->inet_daddr && inet->inet_daddr != raddr) &&
!(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
!(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
sk->sk_bound_dev_if != sdif))
goto found; /* gotcha */
}
sk = NULL;
found:
return sk;
}
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
EXPORT_SYMBOL_GPL(__raw_v4_lookup);
/*
* 0 - deliver
* 1 - block
*/
static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
{
struct icmphdr _hdr;
const struct icmphdr *hdr;
hdr = skb_header_pointer(skb, skb_transport_offset(skb),
sizeof(_hdr), &_hdr);
if (!hdr)
return 1;
if (hdr->type < 32) {
__u32 data = raw_sk(sk)->filter.data;
return ((1U << hdr->type) & data) != 0;
}
/* Do not block unknown ICMP types */
return 0;
}
/* IP input processing comes here for RAW socket delivery.
* Caller owns SKB, so we must make clones.
*
* RFC 1122: SHOULD pass TOS value up to the transport layer.
* -> It does. And not only TOS, but all IP header.
*/
static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
{
int sdif = inet_sdif(skb);
struct sock *sk;
struct hlist_head *head;
int delivered = 0;
struct net *net;
read_lock(&raw_v4_hashinfo.lock);
head = &raw_v4_hashinfo.ht[hash];
if (hlist_empty(head))
goto out;
net = dev_net(skb->dev);
sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
iph->saddr, iph->daddr,
skb->dev->ifindex, sdif);
while (sk) {
delivered = 1;
if ((iph->protocol != IPPROTO_ICMP || !icmp_filter(sk, skb)) &&
ip_mc_sf_allow(sk, iph->daddr, iph->saddr,
skb->dev->ifindex, sdif)) {
struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
/* Not releasing hash table! */
if (clone)
raw_rcv(sk, clone);
}
sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
iph->saddr, iph->daddr,
skb->dev->ifindex, sdif);
}
out:
read_unlock(&raw_v4_hashinfo.lock);
return delivered;
}
int raw_local_deliver(struct sk_buff *skb, int protocol)
{
int hash;
struct sock *raw_sk;
hash = protocol & (RAW_HTABLE_SIZE - 1);
raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
/* If there maybe a raw socket we must check - if not we
* don't care less
*/
if (raw_sk && !raw_v4_input(skb, ip_hdr(skb), hash))
raw_sk = NULL;
return raw_sk != NULL;
}
static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
{
struct inet_sock *inet = inet_sk(sk);
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
int err = 0;
int harderr = 0;
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
ipv4_sk_update_pmtu(skb, sk, info);
else if (type == ICMP_REDIRECT) {
ipv4_sk_redirect(skb, sk);
return;
}
/* Report error on raw socket, if:
1. User requested ip_recverr.
2. Socket is connected (otherwise the error indication
is useless without ip_recverr and error is hard.
*/
if (!inet->recverr && sk->sk_state != TCP_ESTABLISHED)
return;
switch (type) {
default:
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
case ICMP_SOURCE_QUENCH:
return;
case ICMP_PARAMETERPROB:
err = EPROTO;
harderr = 1;
break;
case ICMP_DEST_UNREACH:
err = EHOSTUNREACH;
if (code > NR_ICMP_UNREACH)
break;
err = icmp_err_convert[code].errno;
harderr = icmp_err_convert[code].fatal;
if (code == ICMP_FRAG_NEEDED) {
harderr = inet->pmtudisc != IP_PMTUDISC_DONT;
err = EMSGSIZE;
}
}
if (inet->recverr) {
const struct iphdr *iph = (const struct iphdr *)skb->data;
u8 *payload = skb->data + (iph->ihl << 2);
if (inet->hdrincl)
payload = skb->data;
ip_icmp_error(sk, skb, err, 0, info, payload);
}
if (inet->recverr || harderr) {
sk->sk_err = err;
sk->sk_error_report(sk);
}
}
void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
{
int hash;
struct sock *raw_sk;
const struct iphdr *iph;
struct net *net;
hash = protocol & (RAW_HTABLE_SIZE - 1);
read_lock(&raw_v4_hashinfo.lock);
raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
if (raw_sk) {
int dif = skb->dev->ifindex;
int sdif = inet_sdif(skb);
iph = (const struct iphdr *)skb->data;
net = dev_net(skb->dev);
while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
iph->daddr, iph->saddr,
dif, sdif)) != NULL) {
raw_err(raw_sk, skb, info);
raw_sk = sk_next(raw_sk);
iph = (const struct iphdr *)skb->data;
}
}
read_unlock(&raw_v4_hashinfo.lock);
}
static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
/* Charge it to the socket. */
ipv4_pktinfo_prepare(sk, skb);
ipv4: PKTINFO doesnt need dst reference Le lundi 07 novembre 2011 à 15:33 +0100, Eric Dumazet a écrit : > At least, in recent kernels we dont change dst->refcnt in forwarding > patch (usinf NOREF skb->dst) > > One particular point is the atomic_inc(dst->refcnt) we have to perform > when queuing an UDP packet if socket asked PKTINFO stuff (for example a > typical DNS server has to setup this option) > > I have one patch somewhere that stores the information in skb->cb[] and > avoid the atomic_{inc|dec}(dst->refcnt). > OK I found it, I did some extra tests and believe its ready. [PATCH net-next] ipv4: IP_PKTINFO doesnt need dst reference When a socket uses IP_PKTINFO notifications, we currently force a dst reference for each received skb. Reader has to access dst to get needed information (rt_iif & rt_spec_dst) and must release dst reference. We also forced a dst reference if skb was put in socket backlog, even without IP_PKTINFO handling. This happens under stress/load. We can instead store the needed information in skb->cb[], so that only softirq handler really access dst, improving cache hit ratios. This removes two atomic operations per packet, and false sharing as well. On a benchmark using a mono threaded receiver (doing only recvmsg() calls), I can reach 720.000 pps instead of 570.000 pps. IP_PKTINFO is typically used by DNS servers, and any multihomed aware UDP application. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 14:24:35 +07:00
if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
return NET_RX_SUCCESS;
}
int raw_rcv(struct sock *sk, struct sk_buff *skb)
{
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
atomic_inc(&sk->sk_drops);
kfree_skb(skb);
return NET_RX_DROP;
}
nf_reset(skb);
skb_push(skb, skb->data - skb_network_header(skb));
raw_rcv_skb(sk, skb);
return 0;
}
static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
struct msghdr *msg, size_t length,
struct rtable **rtp, unsigned int flags,
const struct sockcm_cookie *sockc)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct iphdr *iph;
struct sk_buff *skb;
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
int hlen, tlen;
if (length > rt->dst.dev->mtu) {
ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
rt->dst.dev->mtu);
return -EMSGSIZE;
}
ipv4, ipv6: ensure raw socket message is big enough to hold an IP header raw_send_hdrinc() and rawv6_send_hdrinc() expect that the buffer copied from the userspace contains the IPv4/IPv6 header, so if too few bytes are copied, parts of the header may remain uninitialized. This bug has been detected with KMSAN. For the record, the KMSAN report: ================================================================== BUG: KMSAN: use of unitialized memory in nf_ct_frag6_gather+0xf5a/0x44a0 inter: 0 CPU: 0 PID: 1036 Comm: probe Not tainted 4.11.0-rc5+ #2455 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 dump_stack+0x143/0x1b0 lib/dump_stack.c:52 kmsan_report+0x16b/0x1e0 mm/kmsan/kmsan.c:1078 __kmsan_warning_32+0x5c/0xa0 mm/kmsan/kmsan_instr.c:510 nf_ct_frag6_gather+0xf5a/0x44a0 net/ipv6/netfilter/nf_conntrack_reasm.c:577 ipv6_defrag+0x1d9/0x280 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:68 nf_hook_entry_hookfn ./include/linux/netfilter.h:102 nf_hook_slow+0x13f/0x3c0 net/netfilter/core.c:310 nf_hook ./include/linux/netfilter.h:212 NF_HOOK ./include/linux/netfilter.h:255 rawv6_send_hdrinc net/ipv6/raw.c:673 rawv6_sendmsg+0x2fcb/0x41a0 net/ipv6/raw.c:919 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 sock_sendmsg net/socket.c:643 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696 SyS_sendto+0xbc/0xe0 net/socket.c:1664 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285 entry_SYSCALL64_slow_path+0x25/0x25 arch/x86/entry/entry_64.S:246 RIP: 0033:0x436e03 RSP: 002b:00007ffce48baf38 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 00000000004002b0 RCX: 0000000000436e03 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00007ffce48baf90 R08: 00007ffce48baf50 R09: 000000000000001c R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000401790 R14: 0000000000401820 R15: 0000000000000000 origin: 00000000d9400053 save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:362 kmsan_internal_poison_shadow+0xb1/0x1a0 mm/kmsan/kmsan.c:257 kmsan_poison_shadow+0x6d/0xc0 mm/kmsan/kmsan.c:270 slab_alloc_node mm/slub.c:2735 __kmalloc_node_track_caller+0x1f4/0x390 mm/slub.c:4341 __kmalloc_reserve net/core/skbuff.c:138 __alloc_skb+0x2cd/0x740 net/core/skbuff.c:231 alloc_skb ./include/linux/skbuff.h:933 alloc_skb_with_frags+0x209/0xbc0 net/core/skbuff.c:4678 sock_alloc_send_pskb+0x9ff/0xe00 net/core/sock.c:1903 sock_alloc_send_skb+0xe4/0x100 net/core/sock.c:1920 rawv6_send_hdrinc net/ipv6/raw.c:638 rawv6_sendmsg+0x2918/0x41a0 net/ipv6/raw.c:919 inet_sendmsg+0x3f8/0x6d0 net/ipv4/af_inet.c:762 sock_sendmsg_nosec net/socket.c:633 sock_sendmsg net/socket.c:643 SYSC_sendto+0x6a5/0x7c0 net/socket.c:1696 SyS_sendto+0xbc/0xe0 net/socket.c:1664 do_syscall_64+0x72/0xa0 arch/x86/entry/common.c:285 return_from_SYSCALL_64+0x0/0x6a arch/x86/entry/entry_64.S:246 ================================================================== , triggered by the following syscalls: socket(PF_INET6, SOCK_RAW, IPPROTO_RAW) = 3 sendto(3, NULL, 0, 0, {sa_family=AF_INET6, sin6_port=htons(0), inet_pton(AF_INET6, "ff00::", &sin6_addr), sin6_flowinfo=0, sin6_scope_id=0}, 28) = -1 EPERM A similar report is triggered in net/ipv4/raw.c if we use a PF_INET socket instead of a PF_INET6 one. Signed-off-by: Alexander Potapenko <glider@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-03 22:06:58 +07:00
if (length < sizeof(struct iphdr))
return -EINVAL;
if (flags&MSG_PROBE)
goto out;
hlen = LL_RESERVED_SPACE(rt->dst.dev);
tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (!skb)
goto error;
skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, &rt->dst);
*rtp = NULL;
skb_reset_network_header(skb);
iph = ip_hdr(skb);
skb_put(skb, length);
skb->ip_summed = CHECKSUM_NONE;
sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
if (flags & MSG_CONFIRM)
skb_set_dst_pending_confirm(skb, 1);
skb->transport_header = skb->network_header;
AF_RAW: Augment raw_send_hdrinc to expand skb to fit iphdr->ihl (v2) Augment raw_send_hdrinc to correct for incorrect ip header length values A series of oopses was reported to me recently. Apparently when using AF_RAW sockets to send data to peers that were reachable via ipsec encapsulation, people could panic or BUG halt their systems. I've tracked the problem down to user space sending an invalid ip header over an AF_RAW socket with IP_HDRINCL set to 1. Basically what happens is that userspace sends down an ip frame that includes only the header (no data), but sets the ip header ihl value to a large number, one that is larger than the total amount of data passed to the sendmsg call. In raw_send_hdrincl, we allocate an skb based on the size of the data in the msghdr that was passed in, but assume the data is all valid. Later during ipsec encapsulation, xfrm4_tranport_output moves the entire frame back in the skbuff to provide headroom for the ipsec headers. During this operation, the skb->transport_header is repointed to a spot computed by skb->network_header + the ip header length (ihl). Since so little data was passed in relative to the value of ihl provided by the raw socket, we point transport header to an unknown location, resulting in various crashes. This fix for this is pretty straightforward, simply validate the value of of iph->ihl when sending over a raw socket. If (iph->ihl*4U) > user data buffer size, drop the frame and return -EINVAL. I just confirmed this fixes the reported crashes. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-28 15:59:47 +07:00
err = -EFAULT;
if (memcpy_from_msg(iph, msg, length))
AF_RAW: Augment raw_send_hdrinc to expand skb to fit iphdr->ihl (v2) Augment raw_send_hdrinc to correct for incorrect ip header length values A series of oopses was reported to me recently. Apparently when using AF_RAW sockets to send data to peers that were reachable via ipsec encapsulation, people could panic or BUG halt their systems. I've tracked the problem down to user space sending an invalid ip header over an AF_RAW socket with IP_HDRINCL set to 1. Basically what happens is that userspace sends down an ip frame that includes only the header (no data), but sets the ip header ihl value to a large number, one that is larger than the total amount of data passed to the sendmsg call. In raw_send_hdrincl, we allocate an skb based on the size of the data in the msghdr that was passed in, but assume the data is all valid. Later during ipsec encapsulation, xfrm4_tranport_output moves the entire frame back in the skbuff to provide headroom for the ipsec headers. During this operation, the skb->transport_header is repointed to a spot computed by skb->network_header + the ip header length (ihl). Since so little data was passed in relative to the value of ihl provided by the raw socket, we point transport header to an unknown location, resulting in various crashes. This fix for this is pretty straightforward, simply validate the value of of iph->ihl when sending over a raw socket. If (iph->ihl*4U) > user data buffer size, drop the frame and return -EINVAL. I just confirmed this fixes the reported crashes. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-28 15:59:47 +07:00
goto error_free;
iphlen = iph->ihl * 4;
AF_RAW: Augment raw_send_hdrinc to expand skb to fit iphdr->ihl (v2) Augment raw_send_hdrinc to correct for incorrect ip header length values A series of oopses was reported to me recently. Apparently when using AF_RAW sockets to send data to peers that were reachable via ipsec encapsulation, people could panic or BUG halt their systems. I've tracked the problem down to user space sending an invalid ip header over an AF_RAW socket with IP_HDRINCL set to 1. Basically what happens is that userspace sends down an ip frame that includes only the header (no data), but sets the ip header ihl value to a large number, one that is larger than the total amount of data passed to the sendmsg call. In raw_send_hdrincl, we allocate an skb based on the size of the data in the msghdr that was passed in, but assume the data is all valid. Later during ipsec encapsulation, xfrm4_tranport_output moves the entire frame back in the skbuff to provide headroom for the ipsec headers. During this operation, the skb->transport_header is repointed to a spot computed by skb->network_header + the ip header length (ihl). Since so little data was passed in relative to the value of ihl provided by the raw socket, we point transport header to an unknown location, resulting in various crashes. This fix for this is pretty straightforward, simply validate the value of of iph->ihl when sending over a raw socket. If (iph->ihl*4U) > user data buffer size, drop the frame and return -EINVAL. I just confirmed this fixes the reported crashes. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-28 15:59:47 +07:00
/*
* We don't want to modify the ip header, but we do need to
* be sure that it won't cause problems later along the network
* stack. Specifically we want to make sure that iph->ihl is a
* sane value. If ihl points beyond the length of the buffer passed
* in, reject the frame as invalid
*/
err = -EINVAL;
if (iphlen > length)
goto error_free;
if (iphlen >= sizeof(*iph)) {
if (!iph->saddr)
iph->saddr = fl4->saddr;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
ip_select_ident(net, skb, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
skb->transport_header += iphlen;
if (iph->protocol == IPPROTO_ICMP &&
length >= iphlen + sizeof(struct icmphdr))
icmp_out_count(net, ((struct icmphdr *)
skb_transport_header(skb))->type);
}
2015-09-16 08:04:16 +07:00
err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT,
net, sk, skb, NULL, rt->dst.dev,
dst_output);
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
out:
return 0;
AF_RAW: Augment raw_send_hdrinc to expand skb to fit iphdr->ihl (v2) Augment raw_send_hdrinc to correct for incorrect ip header length values A series of oopses was reported to me recently. Apparently when using AF_RAW sockets to send data to peers that were reachable via ipsec encapsulation, people could panic or BUG halt their systems. I've tracked the problem down to user space sending an invalid ip header over an AF_RAW socket with IP_HDRINCL set to 1. Basically what happens is that userspace sends down an ip frame that includes only the header (no data), but sets the ip header ihl value to a large number, one that is larger than the total amount of data passed to the sendmsg call. In raw_send_hdrincl, we allocate an skb based on the size of the data in the msghdr that was passed in, but assume the data is all valid. Later during ipsec encapsulation, xfrm4_tranport_output moves the entire frame back in the skbuff to provide headroom for the ipsec headers. During this operation, the skb->transport_header is repointed to a spot computed by skb->network_header + the ip header length (ihl). Since so little data was passed in relative to the value of ihl provided by the raw socket, we point transport header to an unknown location, resulting in various crashes. This fix for this is pretty straightforward, simply validate the value of of iph->ihl when sending over a raw socket. If (iph->ihl*4U) > user data buffer size, drop the frame and return -EINVAL. I just confirmed this fixes the reported crashes. Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-28 15:59:47 +07:00
error_free:
kfree_skb(skb);
error:
IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
return err;
}
static int raw_probe_proto_opt(struct raw_frag_vec *rfv, struct flowi4 *fl4)
{
int err;
if (fl4->flowi4_proto != IPPROTO_ICMP)
return 0;
/* We only need the first two bytes. */
rfv->hlen = 2;
err = memcpy_from_msg(rfv->hdr.c, rfv->msg, rfv->hlen);
if (err)
return err;
fl4->fl4_icmp_type = rfv->hdr.icmph.type;
fl4->fl4_icmp_code = rfv->hdr.icmph.code;
return 0;
}
static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
struct sk_buff *skb)
{
struct raw_frag_vec *rfv = from;
if (offset < rfv->hlen) {
int copy = min(rfv->hlen - offset, len);
if (skb->ip_summed == CHECKSUM_PARTIAL)
memcpy(to, rfv->hdr.c + offset, copy);
else
skb->csum = csum_block_add(
skb->csum,
csum_partial_copy_nocheck(rfv->hdr.c + offset,
to, copy, 0),
odd);
odd = 0;
offset += copy;
to += copy;
len -= copy;
if (!len)
return 0;
}
offset -= rfv->hlen;
return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
}
static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
struct flowi4 fl4;
int free = 0;
__be32 daddr;
__be32 saddr;
u8 tos;
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
int hdrincl;
err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;
/* hdrincl should be READ_ONCE(inet->hdrincl)
* but READ_ONCE() doesn't work with bit fields.
* Doing this indirectly yields the same result.
*/
hdrincl = inet->hdrincl;
hdrincl = READ_ONCE(hdrincl);
/*
* Check the flags.
*/
err = -EOPNOTSUPP;
if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message */
goto out; /* compatibility */
/*
* Get and verify the address.
*/
if (msg->msg_namelen) {
DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
__func__, current->comm);
err = -EAFNOSUPPORT;
if (usin->sin_family)
goto out;
}
daddr = usin->sin_addr.s_addr;
/* ANK: I did not forget to get protocol from port field.
* I just do not know, who uses this weirdness.
* IP_HDRINCL is much more convenient.
*/
} else {
err = -EDESTADDRREQ;
if (sk->sk_state != TCP_ESTABLISHED)
goto out;
daddr = inet->inet_daddr;
}
ipc.sockc.tsflags = sk->sk_tsflags;
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
ipc.ttl = 0;
ipc.tos = -1;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
err = ip_cmsg_send(sk, msg, &ipc, false);
if (unlikely(err)) {
kfree(ipc.opt);
goto out;
}
if (ipc.opt)
free = 1;
}
saddr = ipc.addr;
ipc.addr = daddr;
if (!ipc.opt) {
struct ip_options_rcu *inet_opt;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt) {
memcpy(&opt_copy, inet_opt,
sizeof(*inet_opt) + inet_opt->opt.optlen);
ipc.opt = &opt_copy.opt;
}
rcu_read_unlock();
}
if (ipc.opt) {
err = -EINVAL;
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
goto done;
daddr = ipc.opt->opt.faddr;
}
}
tos = get_rtconn_flags(&ipc, sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
if (ipv4_is_multicast(daddr)) {
if (!ipc.oif)
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
ipv4: Implement IP_UNICAST_IF socket option. The IP_UNICAST_IF feature is needed by the Wine project. This patch implements the feature by setting the outgoing interface in a similar fashion to that of IP_MULTICAST_IF. A separate option is needed to handle this feature since the existing options do not provide all of the characteristics required by IP_UNICAST_IF, a summary is provided below. SO_BINDTODEVICE: * SO_BINDTODEVICE requires administrative privileges, IP_UNICAST_IF does not. From reading some old mailing list articles my understanding is that SO_BINDTODEVICE requires administrative privileges because it can override the administrator's routing settings. * The SO_BINDTODEVICE option restricts both outbound and inbound traffic, IP_UNICAST_IF only impacts outbound traffic. IP_PKTINFO: * Since IP_PKTINFO and IP_UNICAST_IF are independent options, implementing IP_UNICAST_IF with IP_PKTINFO will likely break some applications. * Implementing IP_UNICAST_IF on top of IP_PKTINFO significantly complicates the Wine codebase and reduces the socket performance (doing this requires a lot of extra communication between the "server" and "user" layers). bind(): * bind() does not work on broadcast packets, IP_UNICAST_IF is specifically intended to work with broadcast packets. * Like SO_BINDTODEVICE, bind() restricts both outbound and inbound traffic. Signed-off-by: Erich E. Hoover <ehoover@mines.edu> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-02-08 16:11:07 +07:00
} else if (!ipc.oif)
ipc.oif = inet->uc_index;
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
(hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);
if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;
err = raw_probe_proto_opt(&rfv, &fl4);
if (err)
goto done;
}
security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto done;
}
err = -EACCES;
if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
goto done;
if (msg->msg_flags & MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags, &ipc.sockc);
else {
sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
if (!ipc.addr)
ipc.addr = fl4.daddr;
lock_sock(sk);
err = ip_append_data(sk, &fl4, raw_getfrag,
&rfv, len, 0,
&ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE)) {
err = ip_push_pending_frames(sk, &fl4);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
}
release_sock(sk);
}
done:
if (free)
kfree(ipc.opt);
ip_rt_put(rt);
out:
if (err < 0)
return err;
return len;
do_confirm:
if (msg->msg_flags & MSG_PROBE)
dst_confirm_neigh(&rt->dst, &fl4.daddr);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
static void raw_close(struct sock *sk, long timeout)
{
/*
* Raw sockets may have direct kernel references. Kill them.
*/
rtnl_lock();
ip_ra_control(sk, 0, NULL);
rtnl_unlock();
sk_common_release(sk);
}
static void raw_destroy(struct sock *sk)
{
lock_sock(sk);
ip_flush_pending_frames(sk);
release_sock(sk);
}
/* This gets rid of all the nasties in af_inet. -DaveM */
static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
u32 tb_id = RT_TABLE_LOCAL;
int ret = -EINVAL;
int chk_addr_ret;
if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
goto out;
if (sk->sk_bound_dev_if)
tb_id = l3mdev_fib_table_by_index(sock_net(sk),
sk->sk_bound_dev_if) ? : tb_id;
chk_addr_ret = inet_addr_type_table(sock_net(sk), addr->sin_addr.s_addr,
tb_id);
ret = -EADDRNOTAVAIL;
if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
goto out;
inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr;
if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
inet->inet_saddr = 0; /* Use device */
sk_dst_reset(sk);
ret = 0;
out: return ret;
}
/*
* This should be easy, if there is something there
* we return it, otherwise we block.
*/
static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int noblock, int flags, int *addr_len)
{
struct inet_sock *inet = inet_sk(sk);
size_t copied = 0;
int err = -EOPNOTSUPP;
DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct sk_buff *skb;
if (flags & MSG_OOB)
goto out;
if (flags & MSG_ERRQUEUE) {
err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
copied = skb->len;
if (len < copied) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_msg(skb, 0, msg, copied);
if (err)
goto done;
net: Generalize socket rx gap / receive queue overflow cmsg Create a new socket level option to report number of queue overflows Recently I augmented the AF_PACKET protocol to report the number of frames lost on the socket receive queue between any two enqueued frames. This value was exported via a SOL_PACKET level cmsg. AFter I completed that work it was requested that this feature be generalized so that any datagram oriented socket could make use of this option. As such I've created this patch, It creates a new SOL_SOCKET level option called SO_RXQ_OVFL, which when enabled exports a SOL_SOCKET level cmsg that reports the nubmer of times the sk_receive_queue overflowed between any two given frames. It also augments the AF_PACKET protocol to take advantage of this new feature (as it previously did not touch sk->sk_drops, which this patch uses to record the overflow count). Tested successfully by me. Notes: 1) Unlike my previous patch, this patch simply records the sk_drops value, which is not a number of drops between packets, but rather a total number of drops. Deltas must be computed in user space. 2) While this patch currently works with datagram oriented protocols, it will also be accepted by non-datagram oriented protocols. I'm not sure if thats agreeable to everyone, but my argument in favor of doing so is that, for those protocols which aren't applicable to this option, sk_drops will always be zero, and reporting no drops on a receive queue that isn't used for those non-participating protocols seems reasonable to me. This also saves us having to code in a per-protocol opt in mechanism. 3) This applies cleanly to net-next assuming that commit 977750076d98c7ff6cbda51858bb5a5894a9d9ab (my af packet cmsg patch) is reverted Signed-off-by: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-10-13 03:26:31 +07:00
sock_recv_ts_and_drops(msg, sk, skb);
/* Copy the address. */
if (sin) {
sin->sin_family = AF_INET;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
*addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
if (flags & MSG_TRUNC)
copied = skb->len;
done:
skb_free_datagram(sk, skb);
out:
if (err)
return err;
return copied;
}
static int raw_init(struct sock *sk)
{
struct raw_sock *rp = raw_sk(sk);
if (inet_sk(sk)->inet_num == IPPROTO_ICMP)
memset(&rp->filter, 0, sizeof(rp->filter));
return 0;
}
static int raw_seticmpfilter(struct sock *sk, char __user *optval, int optlen)
{
if (optlen > sizeof(struct icmp_filter))
optlen = sizeof(struct icmp_filter);
if (copy_from_user(&raw_sk(sk)->filter, optval, optlen))
return -EFAULT;
return 0;
}
static int raw_geticmpfilter(struct sock *sk, char __user *optval, int __user *optlen)
{
int len, ret = -EFAULT;
if (get_user(len, optlen))
goto out;
ret = -EINVAL;
if (len < 0)
goto out;
if (len > sizeof(struct icmp_filter))
len = sizeof(struct icmp_filter);
ret = -EFAULT;
if (put_user(len, optlen) ||
copy_to_user(optval, &raw_sk(sk)->filter, len))
goto out;
ret = 0;
out: return ret;
}
static int do_raw_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
if (optname == ICMP_FILTER) {
if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
return -EOPNOTSUPP;
else
return raw_seticmpfilter(sk, optval, optlen);
}
return -ENOPROTOOPT;
}
static int raw_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
if (level != SOL_RAW)
return ip_setsockopt(sk, level, optname, optval, optlen);
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)
{
if (optname == ICMP_FILTER) {
if (inet_sk(sk)->inet_num != IPPROTO_ICMP)
return -EOPNOTSUPP;
else
return raw_geticmpfilter(sk, optval, optlen);
}
return -ENOPROTOOPT;
}
static int raw_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level != SOL_RAW)
return ip_getsockopt(sk, level, optname, optval, optlen);
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) {
case SIOCOUTQ: {
int amount = sk_wmem_alloc_get(sk);
return put_user(amount, (int __user *)arg);
}
case SIOCINQ: {
struct sk_buff *skb;
int amount = 0;
spin_lock_bh(&sk->sk_receive_queue.lock);
skb = skb_peek(&sk->sk_receive_queue);
if (skb)
amount = skb->len;
spin_unlock_bh(&sk->sk_receive_queue.lock);
return put_user(amount, (int __user *)arg);
}
default:
#ifdef CONFIG_IP_MROUTE
return ipmr_ioctl(sk, cmd, (void __user *)arg);
#else
return -ENOIOCTLCMD;
#endif
}
}
#ifdef CONFIG_COMPAT
static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
{
switch (cmd) {
case SIOCOUTQ:
case SIOCINQ:
return -ENOIOCTLCMD;
default:
#ifdef CONFIG_IP_MROUTE
return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg));
#else
return -ENOIOCTLCMD;
#endif
}
}
#endif
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
int raw_abort(struct sock *sk, int err)
{
lock_sock(sk);
sk->sk_err = err;
sk->sk_error_report(sk);
2016-11-02 03:05:00 +07:00
__udp_disconnect(sk, 0);
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
release_sock(sk);
return 0;
}
EXPORT_SYMBOL_GPL(raw_abort);
struct proto raw_prot = {
.name = "RAW",
.owner = THIS_MODULE,
.close = raw_close,
.destroy = raw_destroy,
.connect = ip4_datagram_connect,
.disconnect = __udp_disconnect,
.ioctl = raw_ioctl,
.init = raw_init,
.setsockopt = raw_setsockopt,
.getsockopt = raw_getsockopt,
.sendmsg = raw_sendmsg,
.recvmsg = raw_recvmsg,
.bind = raw_bind,
.backlog_rcv = raw_rcv_skb,
.release_cb = ip4_datagram_release_cb,
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw_sock),
.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
net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller <davem@davemloft.net> CC: Eric Dumazet <eric.dumazet@gmail.com> CC: David Ahern <dsa@cumulusnetworks.com> CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> CC: James Morris <jmorris@namei.org> CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> CC: Patrick McHardy <kaber@trash.net> CC: Andrey Vagin <avagin@openvz.org> CC: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-10-21 17:03:44 +07:00
.diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
static struct sock *raw_get_first(struct seq_file *seq)
{
struct sock *sk;
struct raw_iter_state *state = raw_seq_private(seq);
for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
++state->bucket) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 08:06:00 +07:00
sk_for_each(sk, &state->h->ht[state->bucket])
if (sock_net(sk) == seq_file_net(seq))
goto found;
}
sk = NULL;
found:
return sk;
}
static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
{
struct raw_iter_state *state = raw_seq_private(seq);
do {
sk = sk_next(sk);
try_again:
;
} while (sk && sock_net(sk) != seq_file_net(seq));
if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
sk = sk_head(&state->h->ht[state->bucket]);
goto try_again;
}
return sk;
}
static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
{
struct sock *sk = raw_get_first(seq);
if (sk)
while (pos && (sk = raw_get_next(seq, sk)) != NULL)
--pos;
return pos ? NULL : sk;
}
void *raw_seq_start(struct seq_file *seq, loff_t *pos)
{
struct raw_iter_state *state = raw_seq_private(seq);
read_lock(&state->h->lock);
return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}
EXPORT_SYMBOL_GPL(raw_seq_start);
void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
if (v == SEQ_START_TOKEN)
sk = raw_get_first(seq);
else
sk = raw_get_next(seq, v);
++*pos;
return sk;
}
EXPORT_SYMBOL_GPL(raw_seq_next);
void raw_seq_stop(struct seq_file *seq, void *v)
{
struct raw_iter_state *state = raw_seq_private(seq);
read_unlock(&state->h->lock);
}
EXPORT_SYMBOL_GPL(raw_seq_stop);
static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
{
struct inet_sock *inet = inet_sk(sp);
__be32 dest = inet->inet_daddr,
src = inet->inet_rcv_saddr;
__u16 destp = 0,
srcp = inet->inet_num;
seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
i, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
0, 0L, 0,
from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
0, sock_i_ino(sp),
refcount_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
}
static int raw_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, " sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
"inode ref pointer drops\n");
else
raw_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
return 0;
}
static const struct seq_operations raw_seq_ops = {
.start = raw_seq_start,
.next = raw_seq_next,
.stop = raw_seq_stop,
.show = raw_seq_show,
};
int raw_seq_open(struct inode *ino, struct file *file,
struct raw_hashinfo *h, const struct seq_operations *ops)
{
int err;
struct raw_iter_state *i;
err = seq_open_net(ino, file, ops, sizeof(struct raw_iter_state));
if (err < 0)
return err;
i = raw_seq_private((struct seq_file *)file->private_data);
i->h = h;
return 0;
}
EXPORT_SYMBOL_GPL(raw_seq_open);
static int raw_v4_seq_open(struct inode *inode, struct file *file)
{
return raw_seq_open(inode, file, &raw_v4_hashinfo, &raw_seq_ops);
}
static const struct file_operations raw_seq_fops = {
.owner = THIS_MODULE,
.open = raw_v4_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
static __net_init int raw_init_net(struct net *net)
{
if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops))
return -ENOMEM;
return 0;
}
static __net_exit void raw_exit_net(struct net *net)
{
remove_proc_entry("raw", net->proc_net);
}
static __net_initdata struct pernet_operations raw_net_ops = {
.init = raw_init_net,
.exit = raw_exit_net,
};
int __init raw_proc_init(void)
{
return register_pernet_subsys(&raw_net_ops);
}
void __init raw_proc_exit(void)
{
unregister_pernet_subsys(&raw_net_ops);
}
#endif /* CONFIG_PROC_FS */