linux/net/ipv6/inet6_connection_sock.c

267 lines
7.2 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.
*
* Support for INET6 connection oriented protocols.
*
* Authors: See the TCPv6 sources
*
* 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/module.h>
#include <linux/in6.h>
#include <linux/ipv6.h>
#include <linux/jhash.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <net/addrconf.h>
#include <net/inet_connection_sock.h>
#include <net/inet_ecn.h>
#include <net/inet_hashtables.h>
#include <net/ip6_route.h>
#include <net/sock.h>
#include <net/inet6_connection_sock.h>
int inet6_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax)
{
const struct sock *sk2;
int reuse = sk->sk_reuse;
int reuseport = sk->sk_reuseport;
kuid_t uid = sock_i_uid((struct sock *)sk);
/* We must walk the whole port owner list in this case. -DaveM */
/*
* See comment in inet_csk_bind_conflict about sock lookup
* vs net namespaces issues.
*/
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 09:06:00 +08:00
sk_for_each_bound(sk2, &tb->owners) {
if (sk != sk2 &&
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
if ((!reuse || !sk2->sk_reuse ||
sk2->sk_state == TCP_LISTEN) &&
(!reuseport || !sk2->sk_reuseport ||
(sk2->sk_state != TCP_TIME_WAIT &&
!uid_eq(uid,
sock_i_uid((struct sock *)sk2))))) {
if (ipv6_rcv_saddr_equal(sk, sk2))
break;
}
if (!relax && reuse && sk2->sk_reuse &&
sk2->sk_state != TCP_LISTEN &&
ipv6_rcv_saddr_equal(sk, sk2))
break;
}
}
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 09:06:00 +08:00
return sk2 != NULL;
}
EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict);
struct dst_entry *inet6_csk_route_req(struct sock *sk,
struct flowi6 *fl6,
const struct request_sock *req)
{
struct inet_request_sock *ireq = inet_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *final_p, final;
struct dst_entry *dst;
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = IPPROTO_TCP;
fl6->daddr = ireq->ir_v6_rmt_addr;
final_p = fl6_update_dst(fl6, np->opt, &final);
fl6->saddr = ireq->ir_v6_loc_addr;
fl6->flowi6_oif = ireq->ir_iif;
fl6->flowi6_mark = ireq->ir_mark;
fl6->fl6_dport = ireq->ir_rmt_port;
fl6->fl6_sport = htons(ireq->ir_num);
security_req_classify_flow(req, flowi6_to_flowi(fl6));
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
if (IS_ERR(dst))
return NULL;
return dst;
}
/*
* request_sock (formerly open request) hash tables.
*/
static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport,
const u32 rnd, const u32 synq_hsize)
{
u32 c;
c = jhash_3words((__force u32)raddr->s6_addr32[0],
(__force u32)raddr->s6_addr32[1],
(__force u32)raddr->s6_addr32[2],
rnd);
c = jhash_2words((__force u32)raddr->s6_addr32[3],
(__force u32)rport,
c);
return c & (synq_hsize - 1);
}
struct request_sock *inet6_csk_search_req(const struct sock *sk,
struct request_sock ***prevp,
const __be16 rport,
const struct in6_addr *raddr,
const struct in6_addr *laddr,
const int iif)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
struct request_sock *req, **prev;
for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport,
lopt->hash_rnd,
lopt->nr_table_entries)];
(req = *prev) != NULL;
prev = &req->dl_next) {
const struct inet_request_sock *ireq = inet_rsk(req);
if (ireq->ir_rmt_port == rport &&
req->rsk_ops->family == AF_INET6 &&
ipv6_addr_equal(&ireq->ir_v6_rmt_addr, raddr) &&
ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) &&
(!ireq->ir_iif || ireq->ir_iif == iif)) {
WARN_ON(req->sk != NULL);
*prevp = prev;
return req;
}
}
return NULL;
}
EXPORT_SYMBOL_GPL(inet6_csk_search_req);
void inet6_csk_reqsk_queue_hash_add(struct sock *sk,
struct request_sock *req,
const unsigned long timeout)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
const u32 h = inet6_synq_hash(&inet_rsk(req)->ir_v6_rmt_addr,
inet_rsk(req)->ir_rmt_port,
lopt->hash_rnd, lopt->nr_table_entries);
reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
inet_csk_reqsk_queue_added(sk, timeout);
}
EXPORT_SYMBOL_GPL(inet6_csk_reqsk_queue_hash_add);
void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
{
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
sin6->sin6_family = AF_INET6;
sin6->sin6_addr = sk->sk_v6_daddr;
sin6->sin6_port = inet_sk(sk)->inet_dport;
/* We do not store received flowlabel for TCP */
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
sk->sk_bound_dev_if);
}
EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
static inline
void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
__ip6_dst_store(sk, dst, daddr, saddr);
}
static inline
struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
{
return __sk_dst_check(sk, cookie);
}
static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
struct flowi6 *fl6)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *final_p, final;
struct dst_entry *dst;
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_proto = sk->sk_protocol;
fl6->daddr = sk->sk_v6_daddr;
fl6->saddr = np->saddr;
fl6->flowlabel = np->flow_label;
IP6_ECN_flow_xmit(sk, fl6->flowlabel);
fl6->flowi6_oif = sk->sk_bound_dev_if;
fl6->flowi6_mark = sk->sk_mark;
fl6->fl6_sport = inet->inet_sport;
fl6->fl6_dport = inet->inet_dport;
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
final_p = fl6_update_dst(fl6, np->opt, &final);
dst = __inet6_csk_dst_check(sk, np->dst_cookie);
if (!dst) {
dst = ip6_dst_lookup_flow(sk, fl6, final_p);
if (!IS_ERR(dst))
__inet6_csk_dst_store(sk, dst, NULL, NULL);
}
return dst;
}
int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct flowi6 fl6;
struct dst_entry *dst;
int res;
dst = inet6_csk_route_socket(sk, &fl6);
if (IS_ERR(dst)) {
sk->sk_err_soft = -PTR_ERR(dst);
sk->sk_route_caps = 0;
kfree_skb(skb);
return PTR_ERR(dst);
}
rcu_read_lock();
skb_dst_set_noref(skb, dst);
/* Restore final destination back after routing done */
fl6.daddr = sk->sk_v6_daddr;
res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL_GPL(inet6_csk_xmit);
struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu)
{
struct flowi6 fl6;
struct dst_entry *dst = inet6_csk_route_socket(sk, &fl6);
if (IS_ERR(dst))
return NULL;
dst->ops->update_pmtu(dst, sk, NULL, mtu);
dst = inet6_csk_route_socket(sk, &fl6);
return IS_ERR(dst) ? NULL : dst;
}
EXPORT_SYMBOL_GPL(inet6_csk_update_pmtu);