linux/net/dccp/proto.c

1263 lines
30 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/dccp/proto.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*/
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/random.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 08:04:11 +00:00
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/inet_sock.h>
dccp: defer ccid_hc_tx_delete() at dismantle time syszkaller team reported another problem in DCCP [1] Problem here is that the structure holding RTO timer (ccid2_hc_tx_rto_expire() handler) is freed too soon. We can not use del_timer_sync() to cancel the timer since this timer wants to grab socket lock (that would risk a dead lock) Solution is to defer the freeing of memory when all references to the socket were released. Socket timers do own a reference, so this should fix the issue. [1] ================================================================== BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365 CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events_unbound call_usermodehelper_exec_work Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x24e/0x340 mm/kasan/report.c:409 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268 expire_timers kernel/time/timer.c:1307 [inline] __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1cc/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:638 [inline] smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702 RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline] RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline] RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343 RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10 RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006 RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98 RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60 R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0 </IRQ> release_task+0xe9e/0x1a40 kernel/exit.c:220 wait_task_zombie kernel/exit.c:1162 [inline] wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389 do_wait_thread kernel/exit.c:1452 [inline] do_wait+0x441/0xa90 kernel/exit.c:1523 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665 SYSC_wait4+0x134/0x140 kernel/exit.c:1677 SyS_wait4+0x2c/0x40 kernel/exit.c:1673 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline] call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097 worker_thread+0x223/0x1860 kernel/workqueue.c:2231 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425 Allocated by task 21267: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561 ccid_new+0x20e/0x390 net/dccp/ccid.c:151 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline] dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __release_sock+0x124/0x360 net/core/sock.c:2269 release_sock+0xa4/0x2a0 net/core/sock.c:2784 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline] __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682 SYSC_connect+0x204/0x470 net/socket.c:1642 SyS_connect+0x24/0x30 net/socket.c:1623 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3049: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kmem_cache_free+0x77/0x280 mm/slab.c:3763 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833 dccp_done+0xb7/0xd0 net/dccp/proto.c:145 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:248 [inline] ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:477 [inline] ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:248 [inline] ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455 process_backlog+0x203/0x740 net/core/dev.c:5130 napi_poll net/core/dev.c:5527 [inline] net_rx_action+0x792/0x1910 net/core/dev.c:5593 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 The buggy address belongs to the object at ffff8801d2660100 which belongs to the cache ccid2_hc_tx_sock of size 1240 The buggy address is located 1088 bytes inside of 1240-byte region [ffff8801d2660100, ffff8801d26605d8) The buggy address belongs to the page: page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0 flags: 0x200000000008100(slab|head) raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005 raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 14:03:15 +00:00
#include <net/inet_common.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <asm/ioctls.h>
#include <linux/spinlock.h>
#include <linux/timer.h>
#include <linux/delay.h>
#include <linux/poll.h>
#include "ccid.h"
#include "dccp.h"
#include "feat.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
EXPORT_SYMBOL_GPL(dccp_statistics);
struct percpu_counter dccp_orphan_count;
EXPORT_SYMBOL_GPL(dccp_orphan_count);
struct inet_hashinfo dccp_hashinfo;
EXPORT_SYMBOL_GPL(dccp_hashinfo);
/* the maximum queue length for tx in packets. 0 is no limit */
int sysctl_dccp_tx_qlen __read_mostly = 5;
#ifdef CONFIG_IP_DCCP_DEBUG
static const char *dccp_state_name(const int state)
{
static const char *const dccp_state_names[] = {
[DCCP_OPEN] = "OPEN",
[DCCP_REQUESTING] = "REQUESTING",
[DCCP_PARTOPEN] = "PARTOPEN",
[DCCP_LISTEN] = "LISTEN",
[DCCP_RESPOND] = "RESPOND",
[DCCP_CLOSING] = "CLOSING",
[DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ",
[DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE",
[DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ",
[DCCP_TIME_WAIT] = "TIME_WAIT",
[DCCP_CLOSED] = "CLOSED",
};
if (state >= DCCP_MAX_STATES)
return "INVALID STATE!";
else
return dccp_state_names[state];
}
#endif
void dccp_set_state(struct sock *sk, const int state)
{
const int oldstate = sk->sk_state;
dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk,
dccp_state_name(oldstate), dccp_state_name(state));
WARN_ON(state == oldstate);
switch (state) {
case DCCP_OPEN:
if (oldstate != DCCP_OPEN)
DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
/* Client retransmits all Confirm options until entering OPEN */
if (oldstate == DCCP_PARTOPEN)
dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg);
break;
case DCCP_CLOSED:
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ ||
oldstate == DCCP_CLOSING)
DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash != NULL &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 12:06:04 +00:00
inet_put_port(sk);
/* fall through */
default:
if (oldstate == DCCP_OPEN)
DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
}
/* Change state AFTER socket is unhashed to avoid closed
* socket sitting in hash tables.
*/
inet_sk_set_state(sk, state);
}
EXPORT_SYMBOL_GPL(dccp_set_state);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
static void dccp_finish_passive_close(struct sock *sk)
{
switch (sk->sk_state) {
case DCCP_PASSIVE_CLOSE:
/* Node (client or server) has received Close packet. */
dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
dccp_set_state(sk, DCCP_CLOSED);
break;
case DCCP_PASSIVE_CLOSEREQ:
/*
* Client received CloseReq. We set the `active' flag so that
* dccp_send_close() retransmits the Close as per RFC 4340, 8.3.
*/
dccp_send_close(sk, 1);
dccp_set_state(sk, DCCP_CLOSING);
}
}
void dccp_done(struct sock *sk)
{
dccp_set_state(sk, DCCP_CLOSED);
dccp_clear_xmit_timers(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
else
inet_csk_destroy_sock(sk);
}
EXPORT_SYMBOL_GPL(dccp_done);
const char *dccp_packet_name(const int type)
{
static const char *const dccp_packet_names[] = {
[DCCP_PKT_REQUEST] = "REQUEST",
[DCCP_PKT_RESPONSE] = "RESPONSE",
[DCCP_PKT_DATA] = "DATA",
[DCCP_PKT_ACK] = "ACK",
[DCCP_PKT_DATAACK] = "DATAACK",
[DCCP_PKT_CLOSEREQ] = "CLOSEREQ",
[DCCP_PKT_CLOSE] = "CLOSE",
[DCCP_PKT_RESET] = "RESET",
[DCCP_PKT_SYNC] = "SYNC",
[DCCP_PKT_SYNCACK] = "SYNCACK",
};
if (type >= DCCP_NR_PKT_TYPES)
return "INVALID";
else
return dccp_packet_names[type];
}
EXPORT_SYMBOL_GPL(dccp_packet_name);
dccp: defer ccid_hc_tx_delete() at dismantle time syszkaller team reported another problem in DCCP [1] Problem here is that the structure holding RTO timer (ccid2_hc_tx_rto_expire() handler) is freed too soon. We can not use del_timer_sync() to cancel the timer since this timer wants to grab socket lock (that would risk a dead lock) Solution is to defer the freeing of memory when all references to the socket were released. Socket timers do own a reference, so this should fix the issue. [1] ================================================================== BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365 CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events_unbound call_usermodehelper_exec_work Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x24e/0x340 mm/kasan/report.c:409 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268 expire_timers kernel/time/timer.c:1307 [inline] __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1cc/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:638 [inline] smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702 RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline] RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline] RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343 RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10 RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006 RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98 RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60 R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0 </IRQ> release_task+0xe9e/0x1a40 kernel/exit.c:220 wait_task_zombie kernel/exit.c:1162 [inline] wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389 do_wait_thread kernel/exit.c:1452 [inline] do_wait+0x441/0xa90 kernel/exit.c:1523 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665 SYSC_wait4+0x134/0x140 kernel/exit.c:1677 SyS_wait4+0x2c/0x40 kernel/exit.c:1673 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline] call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097 worker_thread+0x223/0x1860 kernel/workqueue.c:2231 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425 Allocated by task 21267: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561 ccid_new+0x20e/0x390 net/dccp/ccid.c:151 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline] dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __release_sock+0x124/0x360 net/core/sock.c:2269 release_sock+0xa4/0x2a0 net/core/sock.c:2784 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline] __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682 SYSC_connect+0x204/0x470 net/socket.c:1642 SyS_connect+0x24/0x30 net/socket.c:1623 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3049: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kmem_cache_free+0x77/0x280 mm/slab.c:3763 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833 dccp_done+0xb7/0xd0 net/dccp/proto.c:145 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:248 [inline] ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:477 [inline] ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:248 [inline] ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455 process_backlog+0x203/0x740 net/core/dev.c:5130 napi_poll net/core/dev.c:5527 [inline] net_rx_action+0x792/0x1910 net/core/dev.c:5593 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 The buggy address belongs to the object at ffff8801d2660100 which belongs to the cache ccid2_hc_tx_sock of size 1240 The buggy address is located 1088 bytes inside of 1240-byte region [ffff8801d2660100, ffff8801d26605d8) The buggy address belongs to the page: page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0 flags: 0x200000000008100(slab|head) raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005 raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 14:03:15 +00:00
static void dccp_sk_destruct(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
dp->dccps_hc_tx_ccid = NULL;
inet_sock_destruct(sk);
}
int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
struct dccp_sock *dp = dccp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
icsk->icsk_rto = DCCP_TIMEOUT_INIT;
icsk->icsk_syn_retries = sysctl_dccp_request_retries;
sk->sk_state = DCCP_CLOSED;
sk->sk_write_space = dccp_write_space;
dccp: defer ccid_hc_tx_delete() at dismantle time syszkaller team reported another problem in DCCP [1] Problem here is that the structure holding RTO timer (ccid2_hc_tx_rto_expire() handler) is freed too soon. We can not use del_timer_sync() to cancel the timer since this timer wants to grab socket lock (that would risk a dead lock) Solution is to defer the freeing of memory when all references to the socket were released. Socket timers do own a reference, so this should fix the issue. [1] ================================================================== BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365 CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events_unbound call_usermodehelper_exec_work Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x24e/0x340 mm/kasan/report.c:409 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268 expire_timers kernel/time/timer.c:1307 [inline] __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1cc/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:638 [inline] smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702 RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline] RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline] RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343 RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10 RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006 RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98 RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60 R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0 </IRQ> release_task+0xe9e/0x1a40 kernel/exit.c:220 wait_task_zombie kernel/exit.c:1162 [inline] wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389 do_wait_thread kernel/exit.c:1452 [inline] do_wait+0x441/0xa90 kernel/exit.c:1523 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665 SYSC_wait4+0x134/0x140 kernel/exit.c:1677 SyS_wait4+0x2c/0x40 kernel/exit.c:1673 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline] call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097 worker_thread+0x223/0x1860 kernel/workqueue.c:2231 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425 Allocated by task 21267: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561 ccid_new+0x20e/0x390 net/dccp/ccid.c:151 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline] dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __release_sock+0x124/0x360 net/core/sock.c:2269 release_sock+0xa4/0x2a0 net/core/sock.c:2784 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline] __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682 SYSC_connect+0x204/0x470 net/socket.c:1642 SyS_connect+0x24/0x30 net/socket.c:1623 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3049: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kmem_cache_free+0x77/0x280 mm/slab.c:3763 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833 dccp_done+0xb7/0xd0 net/dccp/proto.c:145 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:248 [inline] ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:477 [inline] ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:248 [inline] ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455 process_backlog+0x203/0x740 net/core/dev.c:5130 napi_poll net/core/dev.c:5527 [inline] net_rx_action+0x792/0x1910 net/core/dev.c:5593 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 The buggy address belongs to the object at ffff8801d2660100 which belongs to the cache ccid2_hc_tx_sock of size 1240 The buggy address is located 1088 bytes inside of 1240-byte region [ffff8801d2660100, ffff8801d26605d8) The buggy address belongs to the page: page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0 flags: 0x200000000008100(slab|head) raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005 raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 14:03:15 +00:00
sk->sk_destruct = dccp_sk_destruct;
icsk->icsk_sync_mss = dccp_sync_mss;
dp->dccps_mss_cache = 536;
dp->dccps_rate_last = jiffies;
dp->dccps_role = DCCP_ROLE_UNDEFINED;
dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT;
dp->dccps_tx_qlen = sysctl_dccp_tx_qlen;
dccp_init_xmit_timers(sk);
INIT_LIST_HEAD(&dp->dccps_featneg);
/* control socket doesn't need feat nego */
if (likely(ctl_sock_initialized))
return dccp_feat_init(sk);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_init_sock);
void dccp_destroy_sock(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
dccp: purge write queue in dccp_destroy_sock() syzkaller reported that DCCP could have a non empty write queue at dismantle time. WARNING: CPU: 1 PID: 2953 at net/core/stream.c:199 sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 2953 Comm: syz-executor0 Not tainted 4.13.0-rc4+ #2 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:180 __warn+0x1c4/0x1d9 kernel/panic.c:541 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:273 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:846 RIP: 0010:sk_stream_kill_queues+0x3ce/0x520 net/core/stream.c:199 RSP: 0018:ffff8801d182f108 EFLAGS: 00010297 RAX: ffff8801d1144140 RBX: ffff8801d13cb280 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff85137b00 RDI: ffff8801d13cb280 RBP: ffff8801d182f148 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801d13cb4d0 R13: ffff8801d13cb3b8 R14: ffff8801d13cb300 R15: ffff8801d13cb3b8 inet_csk_destroy_sock+0x175/0x3f0 net/ipv4/inet_connection_sock.c:835 dccp_close+0x84d/0xc10 net/dccp/proto.c:1067 inet_release+0xed/0x1c0 net/ipv4/af_inet.c:425 sock_release+0x8d/0x1e0 net/socket.c:597 sock_close+0x16/0x20 net/socket.c:1126 __fput+0x327/0x7e0 fs/file_table.c:210 ____fput+0x15/0x20 fs/file_table.c:246 task_work_run+0x18a/0x260 kernel/task_work.c:116 exit_task_work include/linux/task_work.h:21 [inline] do_exit+0xa32/0x1b10 kernel/exit.c:865 do_group_exit+0x149/0x400 kernel/exit.c:969 get_signal+0x7e8/0x17e0 kernel/signal.c:2330 do_signal+0x94/0x1ee0 arch/x86/kernel/signal.c:808 exit_to_usermode_loop+0x21c/0x2d0 arch/x86/entry/common.c:157 prepare_exit_to_usermode arch/x86/entry/common.c:194 [inline] syscall_return_slowpath+0x3a7/0x450 arch/x86/entry/common.c:263 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-14 21:10:25 +00:00
__skb_queue_purge(&sk->sk_write_queue);
if (sk->sk_send_head != NULL) {
kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
}
/* Clean up a referenced DCCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash != NULL)
[SOCK] proto: Add hashinfo member to struct proto This way we can remove TCP and DCCP specific versions of sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port sk->sk_prot->hash: inet_hash is directly used, only v6 need a specific version to deal with mapped sockets sk->sk_prot->unhash: both v4 and v6 use inet_hash directly struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so that inet_csk_get_port can find the per family routine. Now only the lookup routines receive as a parameter a struct inet_hashtable. With this we further reuse code, reducing the difference among INET transport protocols. Eventually work has to be done on UDP and SCTP to make them share this infrastructure and get as a bonus inet_diag interfaces so that iproute can be used with these protocols. net-2.6/net/ipv4/inet_hashtables.c: struct proto | +8 struct inet_connection_sock_af_ops | +8 2 structs changed __inet_hash_nolisten | +18 __inet_hash | -210 inet_put_port | +8 inet_bind_bucket_create | +1 __inet_hash_connect | -8 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191 net-2.6/net/core/sock.c: proto_seq_show | +3 1 function changed, 3 bytes added, diff: +3 net-2.6/net/ipv4/inet_connection_sock.c: inet_csk_get_port | +15 1 function changed, 15 bytes added, diff: +15 net-2.6/net/ipv4/tcp.c: tcp_set_state | -7 1 function changed, 7 bytes removed, diff: -7 net-2.6/net/ipv4/tcp_ipv4.c: tcp_v4_get_port | -31 tcp_v4_hash | -48 tcp_v4_destroy_sock | -7 tcp_v4_syn_recv_sock | -2 tcp_unhash | -179 5 functions changed, 267 bytes removed, diff: -267 net-2.6/net/ipv6/inet6_hashtables.c: __inet6_hash | +8 1 function changed, 8 bytes added, diff: +8 net-2.6/net/ipv4/inet_hashtables.c: inet_unhash | +190 inet_hash | +242 2 functions changed, 432 bytes added, diff: +432 vmlinux: 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7 /home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c: tcp_v6_get_port | -31 tcp_v6_hash | -7 tcp_v6_syn_recv_sock | -9 3 functions changed, 47 bytes removed, diff: -47 /home/acme/git/net-2.6/net/dccp/proto.c: dccp_destroy_sock | -7 dccp_unhash | -179 dccp_hash | -49 dccp_set_state | -7 dccp_done | +1 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241 /home/acme/git/net-2.6/net/dccp/ipv4.c: dccp_v4_get_port | -31 dccp_v4_request_recv_sock | -2 2 functions changed, 33 bytes removed, diff: -33 /home/acme/git/net-2.6/net/dccp/ipv6.c: dccp_v6_get_port | -31 dccp_v6_hash | -7 dccp_v6_request_recv_sock | +5 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33 Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-02-03 12:06:04 +00:00
inet_put_port(sk);
kfree(dp->dccps_service_list);
dp->dccps_service_list = NULL;
dccp ccid-2: Phase out the use of boolean Ack Vector sysctl This removes the use of the sysctl and the minisock variable for the Send Ack Vector feature, as it now is handled fully dynamically via feature negotiation (i.e. when CCID-2 is enabled, Ack Vectors are automatically enabled as per RFC 4341, 4.). Using a sysctl in parallel to this implementation would open the door to crashes, since much of the code relies on tests of the boolean minisock / sysctl variable. Thus, this patch replaces all tests of type if (dccp_msk(sk)->dccpms_send_ack_vector) /* ... */ with if (dp->dccps_hc_rx_ackvec != NULL) /* ... */ The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature negotiation concluded that Ack Vectors are to be used on the half-connection. Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child), so that the test is a valid one. The activation handler for Ack Vectors is called as soon as the feature negotiation has concluded at the * server when the Ack marking the transition RESPOND => OPEN arrives; * client after it has sent its ACK, marking the transition REQUEST => PARTOPEN. Adding the sequence number of the Response packet to the Ack Vector has been removed, since (a) connection establishment implies that the Response has been received; (b) the CCIDs only look at packets received in the (PART)OPEN state, i.e. this entry will always be ignored; (c) it can not be used for anything useful - to detect loss for instance, only packets received after the loss can serve as pseudo-dupacks. There was a FIXME to change the error code when dccp_ackvec_add() fails. I removed this after finding out that: * the check whether ackno < ISN is already made earlier, * this Response is likely the 1st packet with an Ackno that the client gets, * so when dccp_ackvec_add() fails, the reason is likely not a packet error. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-08 09:19:06 +00:00
if (dp->dccps_hc_rx_ackvec != NULL) {
dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
dp->dccps_hc_rx_ackvec = NULL;
}
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
dccp: defer ccid_hc_tx_delete() at dismantle time syszkaller team reported another problem in DCCP [1] Problem here is that the structure holding RTO timer (ccid2_hc_tx_rto_expire() handler) is freed too soon. We can not use del_timer_sync() to cancel the timer since this timer wants to grab socket lock (that would risk a dead lock) Solution is to defer the freeing of memory when all references to the socket were released. Socket timers do own a reference, so this should fix the issue. [1] ================================================================== BUG: KASAN: use-after-free in ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 Read of size 4 at addr ffff8801d2660540 by task kworker/u4:7/3365 CPU: 1 PID: 3365 Comm: kworker/u4:7 Not tainted 4.13.0-rc4+ #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: events_unbound call_usermodehelper_exec_work Call Trace: <IRQ> __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 print_address_description+0x73/0x250 mm/kasan/report.c:252 kasan_report_error mm/kasan/report.c:351 [inline] kasan_report+0x24e/0x340 mm/kasan/report.c:409 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:429 ccid2_hc_tx_rto_expire+0x51c/0x5c0 net/dccp/ccids/ccid2.c:144 call_timer_fn+0x233/0x830 kernel/time/timer.c:1268 expire_timers kernel/time/timer.c:1307 [inline] __run_timers+0x7fd/0xb90 kernel/time/timer.c:1601 run_timer_softirq+0x21/0x80 kernel/time/timer.c:1614 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 invoke_softirq kernel/softirq.c:364 [inline] irq_exit+0x1cc/0x200 kernel/softirq.c:405 exiting_irq arch/x86/include/asm/apic.h:638 [inline] smp_apic_timer_interrupt+0x76/0xa0 arch/x86/kernel/apic/apic.c:1044 apic_timer_interrupt+0x93/0xa0 arch/x86/entry/entry_64.S:702 RIP: 0010:arch_local_irq_enable arch/x86/include/asm/paravirt.h:824 [inline] RIP: 0010:__raw_write_unlock_irq include/linux/rwlock_api_smp.h:267 [inline] RIP: 0010:_raw_write_unlock_irq+0x56/0x70 kernel/locking/spinlock.c:343 RSP: 0018:ffff8801cd50eaa8 EFLAGS: 00000286 ORIG_RAX: ffffffffffffff10 RAX: dffffc0000000000 RBX: ffffffff85a090c0 RCX: 0000000000000006 RDX: 1ffffffff0b595f3 RSI: 1ffff1003962f989 RDI: ffffffff85acaf98 RBP: ffff8801cd50eab0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff8801cc96ea60 R13: dffffc0000000000 R14: ffff8801cc96e4c0 R15: ffff8801cc96e4c0 </IRQ> release_task+0xe9e/0x1a40 kernel/exit.c:220 wait_task_zombie kernel/exit.c:1162 [inline] wait_consider_task+0x29b8/0x33c0 kernel/exit.c:1389 do_wait_thread kernel/exit.c:1452 [inline] do_wait+0x441/0xa90 kernel/exit.c:1523 kernel_wait4+0x1f5/0x370 kernel/exit.c:1665 SYSC_wait4+0x134/0x140 kernel/exit.c:1677 SyS_wait4+0x2c/0x40 kernel/exit.c:1673 call_usermodehelper_exec_sync kernel/kmod.c:286 [inline] call_usermodehelper_exec_work+0x1a0/0x2c0 kernel/kmod.c:323 process_one_work+0xbf3/0x1bc0 kernel/workqueue.c:2097 worker_thread+0x223/0x1860 kernel/workqueue.c:2231 kthread+0x35e/0x430 kernel/kthread.c:231 ret_from_fork+0x2a/0x40 arch/x86/entry/entry_64.S:425 Allocated by task 21267: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551 kasan_slab_alloc+0x12/0x20 mm/kasan/kasan.c:489 kmem_cache_alloc+0x127/0x750 mm/slab.c:3561 ccid_new+0x20e/0x390 net/dccp/ccid.c:151 dccp_hdlr_ccid+0x27/0x140 net/dccp/feat.c:44 __dccp_feat_activate+0x142/0x2a0 net/dccp/feat.c:344 dccp_feat_activate_values+0x34e/0xa90 net/dccp/feat.c:1538 dccp_rcv_request_sent_state_process net/dccp/input.c:472 [inline] dccp_rcv_state_process+0xed1/0x1620 net/dccp/input.c:677 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __release_sock+0x124/0x360 net/core/sock.c:2269 release_sock+0xa4/0x2a0 net/core/sock.c:2784 inet_wait_for_connect net/ipv4/af_inet.c:557 [inline] __inet_stream_connect+0x671/0xf00 net/ipv4/af_inet.c:643 inet_stream_connect+0x58/0xa0 net/ipv4/af_inet.c:682 SYSC_connect+0x204/0x470 net/socket.c:1642 SyS_connect+0x24/0x30 net/socket.c:1623 entry_SYSCALL_64_fastpath+0x1f/0xbe Freed by task 3049: save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59 save_stack+0x43/0xd0 mm/kasan/kasan.c:447 set_track mm/kasan/kasan.c:459 [inline] kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524 __cache_free mm/slab.c:3503 [inline] kmem_cache_free+0x77/0x280 mm/slab.c:3763 ccid_hc_tx_delete+0xc5/0x100 net/dccp/ccid.c:190 dccp_destroy_sock+0x1d1/0x2b0 net/dccp/proto.c:225 inet_csk_destroy_sock+0x166/0x3f0 net/ipv4/inet_connection_sock.c:833 dccp_done+0xb7/0xd0 net/dccp/proto.c:145 dccp_time_wait+0x13d/0x300 net/dccp/minisocks.c:72 dccp_rcv_reset+0x1d1/0x5b0 net/dccp/input.c:160 dccp_rcv_state_process+0x8fc/0x1620 net/dccp/input.c:663 dccp_v4_do_rcv+0xeb/0x160 net/dccp/ipv4.c:679 sk_backlog_rcv include/net/sock.h:911 [inline] __sk_receive_skb+0x33e/0xc00 net/core/sock.c:521 dccp_v4_rcv+0xef1/0x1c00 net/dccp/ipv4.c:871 ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216 NF_HOOK include/linux/netfilter.h:248 [inline] ip_local_deliver+0x1ce/0x6d0 net/ipv4/ip_input.c:257 dst_input include/net/dst.h:477 [inline] ip_rcv_finish+0x8db/0x19c0 net/ipv4/ip_input.c:397 NF_HOOK include/linux/netfilter.h:248 [inline] ip_rcv+0xc3f/0x17d0 net/ipv4/ip_input.c:488 __netif_receive_skb_core+0x19af/0x33d0 net/core/dev.c:4417 __netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4455 process_backlog+0x203/0x740 net/core/dev.c:5130 napi_poll net/core/dev.c:5527 [inline] net_rx_action+0x792/0x1910 net/core/dev.c:5593 __do_softirq+0x2f5/0xba3 kernel/softirq.c:284 The buggy address belongs to the object at ffff8801d2660100 which belongs to the cache ccid2_hc_tx_sock of size 1240 The buggy address is located 1088 bytes inside of 1240-byte region [ffff8801d2660100, ffff8801d26605d8) The buggy address belongs to the page: page:ffffea0007499800 count:1 mapcount:0 mapping:ffff8801d2660100 index:0x0 compound_mapcount: 0 flags: 0x200000000008100(slab|head) raw: 0200000000008100 ffff8801d2660100 0000000000000000 0000000100000005 raw: ffffea00075271a0 ffffea0007538820 ffff8801d3aef9c0 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801d2660400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801d2660480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801d2660500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8801d2660580: fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc fc ffff8801d2660600: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 14:03:15 +00:00
dp->dccps_hc_rx_ccid = NULL;
/* clean up feature negotiation state */
dccp_feat_list_purge(&dp->dccps_featneg);
}
EXPORT_SYMBOL_GPL(dccp_destroy_sock);
static inline int dccp_listen_start(struct sock *sk, int backlog)
{
struct dccp_sock *dp = dccp_sk(sk);
dp->dccps_role = DCCP_ROLE_LISTEN;
dccp: Resolve dependencies of features on choice of CCID This provides a missing link in the code chain, as several features implicitly depend and/or rely on the choice of CCID. Most notably, this is the Send Ack Vector feature, but also Ack Ratio and Send Loss Event Rate (also taken care of). For Send Ack Vector, the situation is as follows: * since CCID2 mandates the use of Ack Vectors, there is no point in allowing endpoints which use CCID2 to disable Ack Vector features such a connection; * a peer with a TX CCID of CCID2 will always expect Ack Vectors, and a peer with a RX CCID of CCID2 must always send Ack Vectors (RFC 4341, sec. 4); * for all other CCIDs, the use of (Send) Ack Vector is optional and thus negotiable. However, this implies that the code negotiating the use of Ack Vectors also supports it (i.e. is able to supply and to either parse or ignore received Ack Vectors). Since this is not the case (CCID-3 has no Ack Vector support), the use of Ack Vectors is here disabled, with a comment in the source code. An analogous consideration arises for the Send Loss Event Rate feature, since the CCID-3 implementation does not support the loss interval options of RFC 4342. To make such use explicit, corresponding feature-negotiation options are inserted which signal the use of the loss event rate option, as it is used by the CCID3 code. Lastly, the values of the Ack Ratio feature are matched to the choice of CCID. The patch implements this as a function which is called after the user has made all other registrations for changing default values of features. The table is variable-length, the reserved (and hence for feature-negotiation invalid, confirmed by considering section 19.4 of RFC 4340) feature number `0' is used to mark the end of the table. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-12 08:48:44 +00:00
/* do not start to listen if feature negotiation setup fails */
if (dccp_feat_finalise_settings(dp))
return -EPROTO;
return inet_csk_listen_start(sk, backlog);
}
static inline int dccp_need_reset(int state)
{
return state != DCCP_CLOSED && state != DCCP_LISTEN &&
state != DCCP_REQUESTING;
}
int dccp_disconnect(struct sock *sk, int flags)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const int old_state = sk->sk_state;
if (old_state != DCCP_CLOSED)
dccp_set_state(sk, DCCP_CLOSED);
/*
* This corresponds to the ABORT function of RFC793, sec. 3.8
* TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted".
*/
if (old_state == DCCP_LISTEN) {
inet_csk_listen_stop(sk);
} else if (dccp_need_reset(old_state)) {
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
sk->sk_err = ECONNRESET;
} else if (old_state == DCCP_REQUESTING)
sk->sk_err = ECONNRESET;
dccp_clear_xmit_timers(sk);
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
dp->dccps_hc_rx_ccid = NULL;
__skb_queue_purge(&sk->sk_receive_queue);
__skb_queue_purge(&sk->sk_write_queue);
if (sk->sk_send_head != NULL) {
__kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
}
inet->inet_dport = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
icsk->icsk_backoff = 0;
inet_csk_delack_init(sk);
__sk_dst_reset(sk);
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
sk->sk_error_report(sk);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_disconnect);
/*
* Wait for a DCCP event.
*
* Note that we don't need to lock the socket, as the upper poll layers
* take care of normal races (between the test and the event) and we don't
* go look at any of the socket buffers directly.
*/
__poll_t dccp_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
__poll_t mask;
struct sock *sk = sock->sk;
sock_poll_wait(file, sock, wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
/* Socket is not locked. We are protected from async events
by poll logic and correct handling of state changes
made by another threads is impossible in any case.
*/
mask = 0;
if (sk->sk_err)
mask = EPOLLERR;
if (sk->sk_shutdown == SHUTDOWN_MASK || sk->sk_state == DCCP_CLOSED)
mask |= EPOLLHUP;
if (sk->sk_shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected? */
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
if (atomic_read(&sk->sk_rmem_alloc) > 0)
mask |= EPOLLIN | EPOLLRDNORM;
if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
if (sk_stream_is_writeable(sk)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
/* Race breaker. If space is freed after
* wspace test but before the flags are set,
* IO signal will be lost.
*/
if (sk_stream_is_writeable(sk))
mask |= EPOLLOUT | EPOLLWRNORM;
}
}
}
return mask;
}
EXPORT_SYMBOL_GPL(dccp_poll);
int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
int rc = -ENOTCONN;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN)
goto out;
switch (cmd) {
case SIOCOUTQ: {
int amount = sk_wmem_alloc_get(sk);
/* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and
* always 0, comparably to UDP.
*/
rc = put_user(amount, (int __user *)arg);
}
break;
case SIOCINQ: {
struct sk_buff *skb;
unsigned long amount = 0;
skb = skb_peek(&sk->sk_receive_queue);
if (skb != NULL) {
/*
* We will only return the amount of this packet since
* that is all that will be read.
*/
amount = skb->len;
}
rc = put_user(amount, (int __user *)arg);
}
break;
default:
rc = -ENOIOCTLCMD;
break;
}
out:
release_sock(sk);
return rc;
}
EXPORT_SYMBOL_GPL(dccp_ioctl);
static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
char __user *optval, unsigned int optlen)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_service_list *sl = NULL;
if (service == DCCP_SERVICE_INVALID_VALUE ||
optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32))
return -EINVAL;
if (optlen > sizeof(service)) {
sl = kmalloc(optlen, GFP_KERNEL);
if (sl == NULL)
return -ENOMEM;
sl->dccpsl_nr = optlen / sizeof(u32) - 1;
if (copy_from_user(sl->dccpsl_list,
optval + sizeof(service),
optlen - sizeof(service)) ||
dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
kfree(sl);
return -EFAULT;
}
}
lock_sock(sk);
dp->dccps_service = service;
kfree(dp->dccps_service_list);
dp->dccps_service_list = sl;
release_sock(sk);
return 0;
}
static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
{
u8 *list, len;
int i, rc;
if (cscov < 0 || cscov > 15)
return -EINVAL;
/*
* Populate a list of permissible values, in the range cscov...15. This
* is necessary since feature negotiation of single values only works if
* both sides incidentally choose the same value. Since the list starts
* lowest-value first, negotiation will pick the smallest shared value.
*/
if (cscov == 0)
return 0;
len = 16 - cscov;
list = kmalloc(len, GFP_KERNEL);
if (list == NULL)
return -ENOBUFS;
for (i = 0; i < len; i++)
list[i] = cscov++;
rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len);
if (rc == 0) {
if (rx)
dccp_sk(sk)->dccps_pcrlen = cscov;
else
dccp_sk(sk)->dccps_pcslen = cscov;
}
kfree(list);
return rc;
}
static int dccp_setsockopt_ccid(struct sock *sk, int type,
char __user *optval, unsigned int optlen)
{
u8 *val;
int rc = 0;
if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
return -EINVAL;
val = memdup_user(optval, optlen);
if (IS_ERR(val))
return PTR_ERR(val);
lock_sock(sk);
if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen);
if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID))
rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen);
release_sock(sk);
kfree(val);
return rc;
}
static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct dccp_sock *dp = dccp_sk(sk);
int val, err = 0;
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_CHANGE_L:
case DCCP_SOCKOPT_CHANGE_R:
DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_CCID:
case DCCP_SOCKOPT_RX_CCID:
case DCCP_SOCKOPT_TX_CCID:
return dccp_setsockopt_ccid(sk, optname, optval, optlen);
}
if (optlen < (int)sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
return -EFAULT;
if (optname == DCCP_SOCKOPT_SERVICE)
return dccp_setsockopt_service(sk, val, optval, optlen);
lock_sock(sk);
switch (optname) {
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
if (dp->dccps_role != DCCP_ROLE_SERVER)
err = -EOPNOTSUPP;
else
dp->dccps_server_timewait = (val != 0);
break;
case DCCP_SOCKOPT_SEND_CSCOV:
err = dccp_setsockopt_cscov(sk, val, false);
break;
case DCCP_SOCKOPT_RECV_CSCOV:
err = dccp_setsockopt_cscov(sk, val, true);
break;
case DCCP_SOCKOPT_QPOLICY_ID:
if (sk->sk_state != DCCP_CLOSED)
err = -EISCONN;
else if (val < 0 || val >= DCCPQ_POLICY_MAX)
err = -EINVAL;
else
dp->dccps_qpolicy = val;
break;
case DCCP_SOCKOPT_QPOLICY_TXQLEN:
if (val < 0)
err = -EINVAL;
else
dp->dccps_tx_qlen = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
return err;
}
int dccp_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen)
{
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
optname, optval,
optlen);
return do_dccp_setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL_GPL(dccp_setsockopt);
static int dccp_getsockopt_service(struct sock *sk, int len,
__be32 __user *optval,
int __user *optlen)
{
const struct dccp_sock *dp = dccp_sk(sk);
const struct dccp_service_list *sl;
int err = -ENOENT, slen = 0, total_len = sizeof(u32);
lock_sock(sk);
if ((sl = dp->dccps_service_list) != NULL) {
slen = sl->dccpsl_nr * sizeof(u32);
total_len += slen;
}
err = -EINVAL;
if (total_len > len)
goto out;
err = 0;
if (put_user(total_len, optlen) ||
put_user(dp->dccps_service, optval) ||
(sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen)))
err = -EFAULT;
out:
release_sock(sk);
return err;
}
static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct dccp_sock *dp;
int val, len;
if (get_user(len, optlen))
return -EFAULT;
if (len < (int)sizeof(int))
return -EINVAL;
dp = dccp_sk(sk);
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_SERVICE:
return dccp_getsockopt_service(sk, len,
(__be32 __user *)optval, optlen);
case DCCP_SOCKOPT_GET_CUR_MPS:
val = dp->dccps_mss_cache;
break;
case DCCP_SOCKOPT_AVAILABLE_CCIDS:
return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
case DCCP_SOCKOPT_TX_CCID:
val = ccid_get_current_tx_ccid(dp);
if (val < 0)
return -ENOPROTOOPT;
break;
case DCCP_SOCKOPT_RX_CCID:
val = ccid_get_current_rx_ccid(dp);
if (val < 0)
return -ENOPROTOOPT;
break;
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
val = dp->dccps_server_timewait;
break;
case DCCP_SOCKOPT_SEND_CSCOV:
val = dp->dccps_pcslen;
break;
case DCCP_SOCKOPT_RECV_CSCOV:
val = dp->dccps_pcrlen;
break;
case DCCP_SOCKOPT_QPOLICY_ID:
val = dp->dccps_qpolicy;
break;
case DCCP_SOCKOPT_QPOLICY_TXQLEN:
val = dp->dccps_tx_qlen;
break;
case 128 ... 191:
return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
case 192 ... 255:
return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
default:
return -ENOPROTOOPT;
}
len = sizeof(val);
if (put_user(len, optlen) || copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
optname, optval,
optlen);
return do_dccp_getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL_GPL(dccp_getsockopt);
static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
{
struct cmsghdr *cmsg;
/*
* Assign an (opaque) qpolicy priority value to skb->priority.
*
* We are overloading this skb field for use with the qpolicy subystem.
* The skb->priority is normally used for the SO_PRIORITY option, which
* is initialised from sk_priority. Since the assignment of sk_priority
* to skb->priority happens later (on layer 3), we overload this field
* for use with queueing priorities as long as the skb is on layer 4.
* The default priority value (if nothing is set) is 0.
*/
skb->priority = 0;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
if (cmsg->cmsg_level != SOL_DCCP)
continue;
if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX &&
!dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type))
return -EINVAL;
switch (cmsg->cmsg_type) {
case DCCP_SCM_PRIORITY:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32)))
return -EINVAL;
skb->priority = *(__u32 *)CMSG_DATA(cmsg);
break;
default:
return -EINVAL;
}
}
return 0;
}
int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
const struct dccp_sock *dp = dccp_sk(sk);
const int flags = msg->msg_flags;
const int noblock = flags & MSG_DONTWAIT;
struct sk_buff *skb;
int rc, size;
long timeo;
trace_dccp_probe(sk, len);
if (len > dp->dccps_mss_cache)
return -EMSGSIZE;
lock_sock(sk);
if (dccp_qpolicy_full(sk)) {
rc = -EAGAIN;
goto out_release;
}
timeo = sock_sndtimeo(sk, noblock);
/*
* We have to use sk_stream_wait_connect here to set sk_write_pending,
* so that the trick in dccp_rcv_request_sent_state_process.
*/
/* Wait for a connection to finish. */
if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0)
goto out_release;
size = sk->sk_prot->max_header + len;
release_sock(sk);
skb = sock_alloc_send_skb(sk, size, noblock, &rc);
lock_sock(sk);
if (skb == NULL)
goto out_release;
if (sk->sk_state == DCCP_CLOSED) {
rc = -ENOTCONN;
goto out_discard;
}
skb_reserve(skb, sk->sk_prot->max_header);
rc = memcpy_from_msg(skb_put(skb, len), msg, len);
if (rc != 0)
goto out_discard;
rc = dccp_msghdr_parse(msg, skb);
if (rc != 0)
goto out_discard;
dccp_qpolicy_push(sk, skb);
dccp: Refine the wait-for-ccid mechanism This extends the existing wait-for-ccid routine so that it may be used with different types of CCID, addressing the following problems: 1) The queue-drain mechanism only works with rate-based CCIDs. If CCID-2 for example has a full TX queue and becomes network-limited just as the application wants to close, then waiting for CCID-2 to become unblocked could lead to an indefinite delay (i.e., application "hangs"). 2) Since each TX CCID in turn uses a feedback mechanism, there may be changes in its sending policy while the queue is being drained. This can lead to further delays during which the application will not be able to terminate. 3) The minimum wait time for CCID-3/4 can be expected to be the queue length times the current inter-packet delay. For example if tx_qlen=100 and a delay of 15 ms is used for each packet, then the application would have to wait for a minimum of 1.5 seconds before being allowed to exit. 4) There is no way for the user/application to control this behaviour. It would be good to use the timeout argument of dccp_close() as an upper bound. Then the maximum time that an application is willing to wait for its CCIDs to can be set via the SO_LINGER option. These problems are addressed by giving the CCID a grace period of up to the `timeout' value. The wait-for-ccid function is, as before, used when the application (a) has read all the data in its receive buffer and (b) if SO_LINGER was set with a non-zero linger time, or (c) the socket is either in the OPEN (active close) or in the PASSIVE_CLOSEREQ state (client application closes after receiving CloseReq). In addition, there is a catch-all case of __skb_queue_purge() after waiting for the CCID. This is necessary since the write queue may still have data when (a) the host has been passively-closed, (b) abnormal termination (unread data, zero linger time), (c) wait-for-ccid could not finish within the given time limit. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-27 19:16:27 +00:00
/*
* The xmit_timer is set if the TX CCID is rate-based and will expire
* when congestion control permits to release further packets into the
* network. Window-based CCIDs do not use this timer.
*/
if (!timer_pending(&dp->dccps_xmit_timer))
dccp_write_xmit(sk);
out_release:
release_sock(sk);
return rc ? : len;
out_discard:
kfree_skb(skb);
goto out_release;
}
EXPORT_SYMBOL_GPL(dccp_sendmsg);
int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
int flags, int *addr_len)
{
const struct dccp_hdr *dh;
long timeo;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN) {
len = -ENOTCONN;
goto out;
}
timeo = sock_rcvtimeo(sk, nonblock);
do {
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
if (skb == NULL)
goto verify_sock_status;
dh = dccp_hdr(skb);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
switch (dh->dccph_type) {
case DCCP_PKT_DATA:
case DCCP_PKT_DATAACK:
goto found_ok_skb;
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
case DCCP_PKT_CLOSE:
case DCCP_PKT_CLOSEREQ:
if (!(flags & MSG_PEEK))
dccp_finish_passive_close(sk);
/* fall through */
case DCCP_PKT_RESET:
dccp_pr_debug("found fin (%s) ok!\n",
dccp_packet_name(dh->dccph_type));
len = 0;
goto found_fin_ok;
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
default:
dccp_pr_debug("packet_type=%s\n",
dccp_packet_name(dh->dccph_type));
sk_eat_skb(sk, skb);
}
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
break;
}
if (sk->sk_err) {
len = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN) {
len = 0;
break;
}
if (sk->sk_state == DCCP_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
* from never connected socket.
*/
len = -ENOTCONN;
break;
}
len = 0;
break;
}
if (!timeo) {
len = -EAGAIN;
break;
}
if (signal_pending(current)) {
len = sock_intr_errno(timeo);
break;
}
sk_wait_data(sk, &timeo, NULL);
continue;
found_ok_skb:
if (len > skb->len)
len = skb->len;
else if (len < skb->len)
msg->msg_flags |= MSG_TRUNC;
if (skb_copy_datagram_msg(skb, 0, msg, len)) {
/* Exception. Bailout! */
len = -EFAULT;
break;
}
if (flags & MSG_TRUNC)
len = skb->len;
found_fin_ok:
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb);
break;
} while (1);
out:
release_sock(sk);
return len;
}
EXPORT_SYMBOL_GPL(dccp_recvmsg);
int inet_dccp_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
unsigned char old_state;
int err;
lock_sock(sk);
err = -EINVAL;
if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP)
goto out;
old_state = sk->sk_state;
if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
goto out;
WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
/* Really, if the socket is already in listen state
* we can only allow the backlog to be adjusted.
*/
if (old_state != DCCP_LISTEN) {
/*
* FIXME: here it probably should be sk->sk_prot->listen_start
* see tcp_listen_start
*/
err = dccp_listen_start(sk, backlog);
if (err)
goto out;
}
err = 0;
out:
release_sock(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_dccp_listen);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
static void dccp_terminate_connection(struct sock *sk)
{
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
u8 next_state = DCCP_CLOSED;
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
switch (sk->sk_state) {
case DCCP_PASSIVE_CLOSE:
case DCCP_PASSIVE_CLOSEREQ:
dccp_finish_passive_close(sk);
break;
case DCCP_PARTOPEN:
dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
/* fall through */
case DCCP_OPEN:
dccp_send_close(sk, 1);
if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER &&
!dccp_sk(sk)->dccps_server_timewait)
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
next_state = DCCP_ACTIVE_CLOSEREQ;
else
next_state = DCCP_CLOSING;
/* fall through */
default:
dccp_set_state(sk, next_state);
}
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
u32 data_was_unread = 0;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == DCCP_LISTEN) {
dccp_set_state(sk, DCCP_CLOSED);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
sk_stop_timer(sk, &dp->dccps_xmit_timer);
/*
* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
*reader process may not have drained the data yet!
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
data_was_unread += skb->len;
__kfree_skb(skb);
}
dccp: do not send reset to already closed sockets Andrey reported following warning while fuzzing with syzkaller WARNING: CPU: 1 PID: 21072 at net/dccp/proto.c:83 dccp_set_state+0x229/0x290 Kernel panic - not syncing: panic_on_warn set ... CPU: 1 PID: 21072 Comm: syz-executor Not tainted 4.9.0-rc1+ #293 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 ffff88003d4c7738 ffffffff81b474f4 0000000000000003 dffffc0000000000 ffffffff844f8b00 ffff88003d4c7804 ffff88003d4c7800 ffffffff8140c06a 0000000041b58ab3 ffffffff8479ab7d ffffffff8140beae ffffffff8140cd00 Call Trace: [< inline >] __dump_stack lib/dump_stack.c:15 [<ffffffff81b474f4>] dump_stack+0xb3/0x10f lib/dump_stack.c:51 [<ffffffff8140c06a>] panic+0x1bc/0x39d kernel/panic.c:179 [<ffffffff8111125c>] __warn+0x1cc/0x1f0 kernel/panic.c:542 [<ffffffff8111144c>] warn_slowpath_null+0x2c/0x40 kernel/panic.c:585 [<ffffffff8389e5d9>] dccp_set_state+0x229/0x290 net/dccp/proto.c:83 [<ffffffff838a0aa2>] dccp_close+0x612/0xc10 net/dccp/proto.c:1016 [<ffffffff8316bf1f>] inet_release+0xef/0x1c0 net/ipv4/af_inet.c:415 [<ffffffff82b6e89e>] sock_release+0x8e/0x1d0 net/socket.c:570 [<ffffffff82b6e9f6>] sock_close+0x16/0x20 net/socket.c:1017 [<ffffffff815256ad>] __fput+0x29d/0x720 fs/file_table.c:208 [<ffffffff81525bb5>] ____fput+0x15/0x20 fs/file_table.c:244 [<ffffffff811727d8>] task_work_run+0xf8/0x170 kernel/task_work.c:116 [< inline >] exit_task_work include/linux/task_work.h:21 [<ffffffff8111bc53>] do_exit+0x883/0x2ac0 kernel/exit.c:828 [<ffffffff811221fe>] do_group_exit+0x10e/0x340 kernel/exit.c:931 [<ffffffff81143c94>] get_signal+0x634/0x15a0 kernel/signal.c:2307 [<ffffffff81054aad>] do_signal+0x8d/0x1a30 arch/x86/kernel/signal.c:807 [<ffffffff81003a05>] exit_to_usermode_loop+0xe5/0x130 arch/x86/entry/common.c:156 [< inline >] prepare_exit_to_usermode arch/x86/entry/common.c:190 [<ffffffff81006298>] syscall_return_slowpath+0x1a8/0x1e0 arch/x86/entry/common.c:259 [<ffffffff83fc1a62>] entry_SYSCALL_64_fastpath+0xc0/0xc2 Dumping ftrace buffer: (ftrace buffer empty) Kernel Offset: disabled Fix this the same way we did for TCP in commit 565b7b2d2e63 ("tcp: do not send reset to already closed sockets") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Andrey Konovalov <andreyknvl@google.com> Tested-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-03 01:04:24 +00:00
/* If socket has been already reset kill it. */
if (sk->sk_state == DCCP_CLOSED)
goto adjudge_to_death;
if (data_was_unread) {
/* Unread data was tossed, send an appropriate Reset Code */
DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
dccp_set_state(sk, DCCP_CLOSED);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
} else if (sk->sk_state != DCCP_CLOSED) {
dccp: Refine the wait-for-ccid mechanism This extends the existing wait-for-ccid routine so that it may be used with different types of CCID, addressing the following problems: 1) The queue-drain mechanism only works with rate-based CCIDs. If CCID-2 for example has a full TX queue and becomes network-limited just as the application wants to close, then waiting for CCID-2 to become unblocked could lead to an indefinite delay (i.e., application "hangs"). 2) Since each TX CCID in turn uses a feedback mechanism, there may be changes in its sending policy while the queue is being drained. This can lead to further delays during which the application will not be able to terminate. 3) The minimum wait time for CCID-3/4 can be expected to be the queue length times the current inter-packet delay. For example if tx_qlen=100 and a delay of 15 ms is used for each packet, then the application would have to wait for a minimum of 1.5 seconds before being allowed to exit. 4) There is no way for the user/application to control this behaviour. It would be good to use the timeout argument of dccp_close() as an upper bound. Then the maximum time that an application is willing to wait for its CCIDs to can be set via the SO_LINGER option. These problems are addressed by giving the CCID a grace period of up to the `timeout' value. The wait-for-ccid function is, as before, used when the application (a) has read all the data in its receive buffer and (b) if SO_LINGER was set with a non-zero linger time, or (c) the socket is either in the OPEN (active close) or in the PASSIVE_CLOSEREQ state (client application closes after receiving CloseReq). In addition, there is a catch-all case of __skb_queue_purge() after waiting for the CCID. This is necessary since the write queue may still have data when (a) the host has been passively-closed, (b) abnormal termination (unread data, zero linger time), (c) wait-for-ccid could not finish within the given time limit. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-27 19:16:27 +00:00
/*
* Normal connection termination. May need to wait if there are
* still packets in the TX queue that are delayed by the CCID.
*/
dccp_flush_write_queue(sk, &timeout);
[DCCP]: Integrate state transitions for passive-close This adds the necessary state transitions for the two forms of passive-close * PASSIVE_CLOSE - which is entered when a host receives a Close; * PASSIVE_CLOSEREQ - which is entered when a client receives a CloseReq. Here is a detailed account of what the patch does in each state. 1) Receiving CloseReq The pseudo-code in 8.5 says: Step 13: Process CloseReq If P.type == CloseReq and S.state < CLOSEREQ, Generate Close S.state := CLOSING Set CLOSING timer. This means we need to address what to do in CLOSED, LISTEN, REQUEST, RESPOND, PARTOPEN, and OPEN. * CLOSED: silently ignore - it may be a late or duplicate CloseReq; * LISTEN/RESPOND: will not appear, since Step 7 is performed first (we know we are the client); * REQUEST: perform Step 13 directly (no need to enqueue packet); * OPEN/PARTOPEN: enter PASSIVE_CLOSEREQ so that the application has a chance to process unread data. When already in PASSIVE_CLOSEREQ, no second CloseReq is enqueued. In any other state, the CloseReq is ignored. I think that this offers some robustness against rare and pathological cases: e.g. a simultaneous close where the client sends a Close and the server a CloseReq. The client will then be retransmitting its Close until it gets the Reset, so ignoring the CloseReq while in state CLOSING is sane. 2) Receiving Close The code below from 8.5 is unconditional. Step 14: Process Close If P.type == Close, Generate Reset(Closed) Tear down connection Drop packet and return Thus we need to consider all states: * CLOSED: silently ignore, since this can happen when a retransmitted or late Close arrives; * LISTEN: dccp_rcv_state_process() will generate a Reset ("No Connection"); * REQUEST: perform Step 14 directly (no need to enqueue packet); * RESPOND: dccp_check_req() will generate a Reset ("Packet Error") -- left it at that; * OPEN/PARTOPEN: enter PASSIVE_CLOSE so that application has a chance to process unread data; * CLOSEREQ: server performed active-close -- perform Step 14; * CLOSING: simultaneous-close: use a tie-breaker to avoid message ping-pong (see comment); * PASSIVE_CLOSEREQ: ignore - the peer has a bug (sending first a CloseReq and now a Close); * TIMEWAIT: packet is ignored. Note that the condition of receiving a packet in state CLOSED here is different from the condition "there is no socket for such a connection": the socket still exists, but its state indicates it is unusable. Last, dccp_finish_passive_close sets either DCCP_CLOSED or DCCP_CLOSING = TCP_CLOSING, so that sk_stream_wait_close() will wait for the final Reset (which will trigger CLOSING => CLOSED). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-28 13:59:48 +00:00
dccp_terminate_connection(sk);
}
dccp: Refine the wait-for-ccid mechanism This extends the existing wait-for-ccid routine so that it may be used with different types of CCID, addressing the following problems: 1) The queue-drain mechanism only works with rate-based CCIDs. If CCID-2 for example has a full TX queue and becomes network-limited just as the application wants to close, then waiting for CCID-2 to become unblocked could lead to an indefinite delay (i.e., application "hangs"). 2) Since each TX CCID in turn uses a feedback mechanism, there may be changes in its sending policy while the queue is being drained. This can lead to further delays during which the application will not be able to terminate. 3) The minimum wait time for CCID-3/4 can be expected to be the queue length times the current inter-packet delay. For example if tx_qlen=100 and a delay of 15 ms is used for each packet, then the application would have to wait for a minimum of 1.5 seconds before being allowed to exit. 4) There is no way for the user/application to control this behaviour. It would be good to use the timeout argument of dccp_close() as an upper bound. Then the maximum time that an application is willing to wait for its CCIDs to can be set via the SO_LINGER option. These problems are addressed by giving the CCID a grace period of up to the `timeout' value. The wait-for-ccid function is, as before, used when the application (a) has read all the data in its receive buffer and (b) if SO_LINGER was set with a non-zero linger time, or (c) the socket is either in the OPEN (active close) or in the PASSIVE_CLOSEREQ state (client application closes after receiving CloseReq). In addition, there is a catch-all case of __skb_queue_purge() after waiting for the CCID. This is necessary since the write queue may still have data when (a) the host has been passively-closed, (b) abnormal termination (unread data, zero linger time), (c) wait-for-ccid could not finish within the given time limit. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-27 19:16:27 +00:00
/*
* Flush write queue. This may be necessary in several cases:
* - we have been closed by the peer but still have application data;
* - abortive termination (unread data or zero linger time),
* - normal termination but queue could not be flushed within time limit
*/
__skb_queue_purge(&sk->sk_write_queue);
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
/*
* It is the last release_sock in its life. It will remove backlog.
*/
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
* to finish close. No need to check for user refs.
*/
local_bh_disable();
bh_lock_sock(sk);
WARN_ON(sock_owned_by_user(sk));
percpu_counter_inc(sk->sk_prot->orphan_count);
/* Have we already been destroyed by a softirq or backlog? */
if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
goto out;
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
EXPORT_SYMBOL_GPL(dccp_close);
void dccp_shutdown(struct sock *sk, int how)
{
[DCCP]: Honour and make use of shutdown option set by user This extends the DCCP socket API by honouring any shutdown(2) option set by the user. The behaviour is, as much as possible, made consistent with the API for TCP's shutdown. This patch exploits the information provided by the user via the socket API to reduce processing costs: * if the read end is closed (SHUT_RD), it is not necessary to deliver to input CCID; * if the write end is closed (SHUT_WR), the same idea applies, but with a difference - as long as the TX queue has not been drained, we need to receive feedback to keep congestion-control rates up to date. Hence SHUT_WR is honoured only after the last packet (under congestion control) has been sent; * although SHUT_RDWR seems nonsensical, it is nevertheless supported in the same manner as for TCP (and agrees with test for SHUTDOWN_MASK in dccp_poll() in net/dccp/proto.c). Furthermore, most of the code already honours the sk_shutdown flags (dccp_recvmsg() for instance sets the read length to 0 if SHUT_RD had been called); CCID handling is now added to this by the present patch. There will also no longer be any delivery when the socket is in the final stages, i.e. when one of dccp_close(), dccp_fin(), or dccp_done() has been called - which is fine since at that stage the connection is its final stages. Motivation and background are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/shutdown A FIXME has been added to notify the other end if SHUT_RD has been set (RFC 4340, 11.7). Note: There is a comment in inet_shutdown() in net/ipv4/af_inet.c which asks to "make sure the socket is a TCP socket". This should probably be extended to mean `TCP or DCCP socket' (the code is also used by UDP and raw sockets). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-21 11:56:48 +00:00
dccp_pr_debug("called shutdown(%x)\n", how);
}
EXPORT_SYMBOL_GPL(dccp_shutdown);
static inline int __init dccp_mib_init(void)
{
dccp_statistics = alloc_percpu(struct dccp_mib);
if (!dccp_statistics)
return -ENOMEM;
return 0;
}
static inline void dccp_mib_exit(void)
{
free_percpu(dccp_statistics);
}
static int thash_entries;
module_param(thash_entries, int, 0444);
MODULE_PARM_DESC(thash_entries, "Number of ehash buckets");
#ifdef CONFIG_IP_DCCP_DEBUG
bool dccp_debug;
module_param(dccp_debug, bool, 0644);
MODULE_PARM_DESC(dccp_debug, "Enable debug messages");
EXPORT_SYMBOL_GPL(dccp_debug);
#endif
static int __init dccp_init(void)
{
unsigned long goal;
unsigned long nr_pages = totalram_pages();
int ehash_order, bhash_order, i;
int rc;
BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
sizeof_field(struct sk_buff, cb));
rc = percpu_counter_init(&dccp_orphan_count, 0, GFP_KERNEL);
if (rc)
goto out_fail;
inet_hashinfo_init(&dccp_hashinfo);
rc = inet_hashinfo2_init_mod(&dccp_hashinfo);
if (rc)
goto out_free_percpu;
rc = -ENOBUFS;
dccp_hashinfo.bind_bucket_cachep =
kmem_cache_create("dccp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!dccp_hashinfo.bind_bucket_cachep)
goto out_free_hashinfo2;
/*
* Size and allocate the main established and bind bucket
* hash tables.
*
* The methodology is similar to that of the buffer cache.
*/
mm: reference totalram_pages and managed_pages once per function Patch series "mm: convert totalram_pages, totalhigh_pages and managed pages to atomic", v5. This series converts totalram_pages, totalhigh_pages and zone->managed_pages to atomic variables. totalram_pages, zone->managed_pages and totalhigh_pages updates are protected by managed_page_count_lock, but readers never care about it. Convert these variables to atomic to avoid readers potentially seeing a store tear. Main motivation was that managed_page_count_lock handling was complicating things. It was discussed in length here, https://lore.kernel.org/patchwork/patch/995739/#1181785 It seemes better to remove the lock and convert variables to atomic. With the change, preventing poteintial store-to-read tearing comes as a bonus. This patch (of 4): This is in preparation to a later patch which converts totalram_pages and zone->managed_pages to atomic variables. Please note that re-reading the value might lead to a different value and as such it could lead to unexpected behavior. There are no known bugs as a result of the current code but it is better to prevent from them in principle. Link: http://lkml.kernel.org/r/1542090790-21750-2-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:34:20 +00:00
if (nr_pages >= (128 * 1024))
goal = nr_pages >> (21 - PAGE_SHIFT);
else
mm: reference totalram_pages and managed_pages once per function Patch series "mm: convert totalram_pages, totalhigh_pages and managed pages to atomic", v5. This series converts totalram_pages, totalhigh_pages and zone->managed_pages to atomic variables. totalram_pages, zone->managed_pages and totalhigh_pages updates are protected by managed_page_count_lock, but readers never care about it. Convert these variables to atomic to avoid readers potentially seeing a store tear. Main motivation was that managed_page_count_lock handling was complicating things. It was discussed in length here, https://lore.kernel.org/patchwork/patch/995739/#1181785 It seemes better to remove the lock and convert variables to atomic. With the change, preventing poteintial store-to-read tearing comes as a bonus. This patch (of 4): This is in preparation to a later patch which converts totalram_pages and zone->managed_pages to atomic variables. Please note that re-reading the value might lead to a different value and as such it could lead to unexpected behavior. There are no known bugs as a result of the current code but it is better to prevent from them in principle. Link: http://lkml.kernel.org/r/1542090790-21750-2-git-send-email-arunks@codeaurora.org Signed-off-by: Arun KS <arunks@codeaurora.org> Reviewed-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Reviewed-by: David Hildenbrand <david@redhat.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-12-28 08:34:20 +00:00
goal = nr_pages >> (23 - PAGE_SHIFT);
if (thash_entries)
goal = (thash_entries *
sizeof(struct inet_ehash_bucket)) >> PAGE_SHIFT;
for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++)
;
do {
unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE /
sizeof(struct inet_ehash_bucket);
while (hash_size & (hash_size - 1))
hash_size--;
dccp_hashinfo.ehash_mask = hash_size - 1;
dccp_hashinfo.ehash = (struct inet_ehash_bucket *)
__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order);
} while (!dccp_hashinfo.ehash && --ehash_order > 0);
if (!dccp_hashinfo.ehash) {
DCCP_CRIT("Failed to allocate DCCP established hash table");
goto out_free_bind_bucket_cachep;
}
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 07:22:02 +00:00
for (i = 0; i <= dccp_hashinfo.ehash_mask; i++)
INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
if (inet_ehash_locks_alloc(&dccp_hashinfo))
goto out_free_dccp_ehash;
bhash_order = ehash_order;
do {
dccp_hashinfo.bhash_size = (1UL << bhash_order) * PAGE_SIZE /
sizeof(struct inet_bind_hashbucket);
if ((dccp_hashinfo.bhash_size > (64 * 1024)) &&
bhash_order > 0)
continue;
dccp_hashinfo.bhash = (struct inet_bind_hashbucket *)
__get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order);
} while (!dccp_hashinfo.bhash && --bhash_order >= 0);
if (!dccp_hashinfo.bhash) {
DCCP_CRIT("Failed to allocate DCCP bind hash table");
goto out_free_dccp_locks;
}
for (i = 0; i < dccp_hashinfo.bhash_size; i++) {
spin_lock_init(&dccp_hashinfo.bhash[i].lock);
INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain);
}
rc = dccp_mib_init();
if (rc)
goto out_free_dccp_bhash;
rc = dccp_ackvec_init();
if (rc)
goto out_free_dccp_mib;
rc = dccp_sysctl_init();
if (rc)
goto out_ackvec_exit;
rc = ccid_initialize_builtins();
if (rc)
goto out_sysctl_exit;
dccp_timestamping_init();
return 0;
out_sysctl_exit:
dccp_sysctl_exit();
out_ackvec_exit:
dccp_ackvec_exit();
out_free_dccp_mib:
dccp_mib_exit();
out_free_dccp_bhash:
free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order);
out_free_dccp_locks:
inet_ehash_locks_free(&dccp_hashinfo);
out_free_dccp_ehash:
free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order);
out_free_bind_bucket_cachep:
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
out_free_hashinfo2:
inet_hashinfo2_free_mod(&dccp_hashinfo);
out_free_percpu:
percpu_counter_destroy(&dccp_orphan_count);
out_fail:
dccp_hashinfo.bhash = NULL;
dccp_hashinfo.ehash = NULL;
dccp_hashinfo.bind_bucket_cachep = NULL;
return rc;
}
static void __exit dccp_fini(void)
{
ccid_cleanup_builtins();
dccp_mib_exit();
free_pages((unsigned long)dccp_hashinfo.bhash,
get_order(dccp_hashinfo.bhash_size *
sizeof(struct inet_bind_hashbucket)));
free_pages((unsigned long)dccp_hashinfo.ehash,
get_order((dccp_hashinfo.ehash_mask + 1) *
sizeof(struct inet_ehash_bucket)));
inet_ehash_locks_free(&dccp_hashinfo);
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
dccp_ackvec_exit();
dccp_sysctl_exit();
inet_hashinfo2_free_mod(&dccp_hashinfo);
percpu_counter_destroy(&dccp_orphan_count);
}
module_init(dccp_init);
module_exit(dccp_fini);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@conectiva.com.br>");
MODULE_DESCRIPTION("DCCP - Datagram Congestion Controlled Protocol");