linux_old1/include/net/request_sock.h

286 lines
8.1 KiB
C
Raw Normal View History

/*
* NET Generic infrastructure for Network protocols.
*
* Definitions for request_sock
*
* Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* From code originally in include/net/tcp.h
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _REQUEST_SOCK_H
#define _REQUEST_SOCK_H
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/bug.h>
#include <net/sock.h>
struct request_sock;
struct sk_buff;
struct dst_entry;
struct proto;
/* empty to "strongly type" an otherwise void parameter.
*/
struct request_values {
};
struct request_sock_ops {
int family;
int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(struct sock *sk,
struct request_sock *req,
struct request_values *rvp);
tcp: Fix kernel panic when calling tcp_v(4/6)_md5_do_lookup If the following packet flow happen, kernel will panic. MathineA MathineB SYN ----------------------> SYN+ACK <---------------------- ACK(bad seq) ----------------------> When a bad seq ACK is received, tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr)) is finally called by tcp_v4_reqsk_send_ack(), but the first parameter(skb->sk) is NULL at that moment, so kernel panic happens. This patch fixes this bug. OOPS output is as following: [ 302.812793] IP: [<c05cfaa6>] tcp_v4_md5_do_lookup+0x12/0x42 [ 302.817075] Oops: 0000 [#1] SMP [ 302.819815] Modules linked in: ipv6 loop dm_multipath rtc_cmos rtc_core rtc_lib pcspkr pcnet32 mii i2c_piix4 parport_pc i2c_core parport ac button ata_piix libata dm_mod mptspi mptscsih mptbase scsi_transport_spi sd_mod scsi_mod crc_t10dif ext3 jbd mbcache uhci_hcd ohci_hcd ehci_hcd [last unloaded: scsi_wait_scan] [ 302.849946] [ 302.851198] Pid: 0, comm: swapper Not tainted (2.6.27-rc1-guijf #5) [ 302.855184] EIP: 0060:[<c05cfaa6>] EFLAGS: 00010296 CPU: 0 [ 302.858296] EIP is at tcp_v4_md5_do_lookup+0x12/0x42 [ 302.861027] EAX: 0000001e EBX: 00000000 ECX: 00000046 EDX: 00000046 [ 302.864867] ESI: ceb69e00 EDI: 1467a8c0 EBP: cf75f180 ESP: c0792e54 [ 302.868333] DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 [ 302.871287] Process swapper (pid: 0, ti=c0792000 task=c0712340 task.ti=c0746000) [ 302.875592] Stack: c06f413a 00000000 cf75f180 ceb69e00 00000000 c05d0d86 000016d0 ceac5400 [ 302.883275] c05d28f8 000016d0 ceb69e00 ceb69e20 681bf6e3 00001000 00000000 0a67a8c0 [ 302.890971] ceac5400 c04250a3 c06f413a c0792eb0 c0792edc cf59a620 cf59a620 cf59a634 [ 302.900140] Call Trace: [ 302.902392] [<c05d0d86>] tcp_v4_reqsk_send_ack+0x17/0x35 [ 302.907060] [<c05d28f8>] tcp_check_req+0x156/0x372 [ 302.910082] [<c04250a3>] printk+0x14/0x18 [ 302.912868] [<c05d0aa1>] tcp_v4_do_rcv+0x1d3/0x2bf [ 302.917423] [<c05d26be>] tcp_v4_rcv+0x563/0x5b9 [ 302.920453] [<c05bb20f>] ip_local_deliver_finish+0xe8/0x183 [ 302.923865] [<c05bb10a>] ip_rcv_finish+0x286/0x2a3 [ 302.928569] [<c059e438>] dev_alloc_skb+0x11/0x25 [ 302.931563] [<c05a211f>] netif_receive_skb+0x2d6/0x33a [ 302.934914] [<d0917941>] pcnet32_poll+0x333/0x680 [pcnet32] [ 302.938735] [<c05a3b48>] net_rx_action+0x5c/0xfe [ 302.941792] [<c042856b>] __do_softirq+0x5d/0xc1 [ 302.944788] [<c042850e>] __do_softirq+0x0/0xc1 [ 302.948999] [<c040564b>] do_softirq+0x55/0x88 [ 302.951870] [<c04501b1>] handle_fasteoi_irq+0x0/0xa4 [ 302.954986] [<c04284da>] irq_exit+0x35/0x69 [ 302.959081] [<c0405717>] do_IRQ+0x99/0xae [ 302.961896] [<c040422b>] common_interrupt+0x23/0x28 [ 302.966279] [<c040819d>] default_idle+0x2a/0x3d [ 302.969212] [<c0402552>] cpu_idle+0xb2/0xd2 [ 302.972169] ======================= [ 302.974274] Code: fc ff 84 d2 0f 84 df fd ff ff e9 34 fe ff ff 83 c4 0c 5b 5e 5f 5d c3 90 90 57 89 d7 56 53 89 c3 50 68 3a 41 6f c0 e8 e9 55 e5 ff <8b> 93 9c 04 00 00 58 85 d2 59 74 1e 8b 72 10 31 db 31 c9 85 f6 [ 303.011610] EIP: [<c05cfaa6>] tcp_v4_md5_do_lookup+0x12/0x42 SS:ESP 0068:c0792e54 [ 303.018360] Kernel panic - not syncing: Fatal exception in interrupt Signed-off-by: Gui Jianfeng <guijianfeng@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-07 14:50:04 +08:00
void (*send_ack)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(struct sock *sk,
struct sk_buff *skb);
void (*destructor)(struct request_sock *req);
void (*syn_ack_timeout)(struct sock *sk,
struct request_sock *req);
};
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 07:16:46 +08:00
extern int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
struct request_sock *dl_next; /* Must be first member! */
u16 mss;
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 07:16:46 +08:00
u8 num_retrans; /* number of retransmits */
u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
u8 num_timeout:7; /* number of timeouts */
/* The following two fields can be easily recomputed I think -AK */
u32 window_clamp; /* window clamp at creation time */
u32 rcv_wnd; /* rcv_wnd offered first time */
u32 ts_recent;
unsigned long expires;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
u32 secid;
u32 peer_secid;
};
static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops)
{
struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC);
if (req != NULL)
req->rsk_ops = ops;
return req;
}
static inline void __reqsk_free(struct request_sock *req)
{
kmem_cache_free(req->rsk_ops->slab, req);
}
static inline void reqsk_free(struct request_sock *req)
{
req->rsk_ops->destructor(req);
__reqsk_free(req);
}
extern int sysctl_max_syn_backlog;
/** struct listen_sock - listen state
*
* @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs
*/
struct listen_sock {
u8 max_qlen_log;
u8 synflood_warned;
/* 2 bytes hole, try to use */
int qlen;
int qlen_young;
int clock_hand;
u32 hash_rnd;
u32 nr_table_entries;
struct request_sock *syn_table[0];
};
/*
* For a TCP Fast Open listener -
* lock - protects the access to all the reqsk, which is co-owned by
* the listener and the child socket.
* qlen - pending TFO requests (still in TCP_SYN_RECV).
* max_qlen - max TFO reqs allowed before TFO is disabled.
*
* XXX (TFO) - ideally these fields can be made as part of "listen_sock"
* structure above. But there is some implementation difficulty due to
* listen_sock being part of request_sock_queue hence will be freed when
* a listener is stopped. But TFO related fields may continue to be
* accessed even after a listener is closed, until its sk_refcnt drops
* to 0 implying no more outstanding TFO reqs. One solution is to keep
* listen_opt around until sk_refcnt drops to 0. But there is some other
* complexity that needs to be resolved. E.g., a listener can be disabled
* temporarily through shutdown()->tcp_disconnect(), and re-enabled later.
*/
struct fastopen_queue {
struct request_sock *rskq_rst_head; /* Keep track of past TFO */
struct request_sock *rskq_rst_tail; /* requests that caused RST.
* This is part of the defense
* against spoofing attack.
*/
spinlock_t lock;
int qlen; /* # of pending (TCP_SYN_RECV) reqs */
int max_qlen; /* != 0 iff TFO is currently enabled */
};
/** struct request_sock_queue - queue of request_socks
*
* @rskq_accept_head - FIFO head of established children
* @rskq_accept_tail - FIFO tail of established children
* @rskq_defer_accept - User waits for some data after accept()
* @syn_wait_lock - serializer
*
* %syn_wait_lock is necessary only to avoid proc interface having to grab the main
* lock sock while browsing the listening hash (otherwise it's deadlock prone).
*
* This lock is acquired in read mode only from listening_get_next() seq_file
* op and it's acquired in write mode _only_ from code that is actively
* changing rskq_accept_head. All readers that are holding the master sock lock
* don't need to grab this lock in read mode too as rskq_accept_head. writes
* are always protected from the main sock lock.
*/
struct request_sock_queue {
struct request_sock *rskq_accept_head;
struct request_sock *rskq_accept_tail;
rwlock_t syn_wait_lock;
tcp: Revert 'process defer accept as established' changes. This reverts two changesets, ec3c0982a2dd1e671bad8e9d26c28dcba0039d87 ("[TCP]: TCP_DEFER_ACCEPT updates - process as established") and the follow-on bug fix 9ae27e0adbf471c7a6b80102e38e1d5a346b3b38 ("tcp: Fix slab corruption with ipv6 and tcp6fuzz"). This change causes several problems, first reported by Ingo Molnar as a distcc-over-loopback regression where connections were getting stuck. Ilpo Järvinen first spotted the locking problems. The new function added by this code, tcp_defer_accept_check(), only has the child socket locked, yet it is modifying state of the parent listening socket. Fixing that is non-trivial at best, because we can't simply just grab the parent listening socket lock at this point, because it would create an ABBA deadlock. The normal ordering is parent listening socket --> child socket, but this code path would require the reverse lock ordering. Next is a problem noticed by Vitaliy Gusev, he noted: ---------------------------------------- >--- a/net/ipv4/tcp_timer.c >+++ b/net/ipv4/tcp_timer.c >@@ -481,6 +481,11 @@ static void tcp_keepalive_timer (unsigned long data) > goto death; > } > >+ if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { >+ tcp_send_active_reset(sk, GFP_ATOMIC); >+ goto death; Here socket sk is not attached to listening socket's request queue. tcp_done() will not call inet_csk_destroy_sock() (and tcp_v4_destroy_sock() which should release this sk) as socket is not DEAD. Therefore socket sk will be lost for freeing. ---------------------------------------- Finally, Alexey Kuznetsov argues that there might not even be any real value or advantage to these new semantics even if we fix all of the bugs: ---------------------------------------- Hiding from accept() sockets with only out-of-order data only is the only thing which is impossible with old approach. Is this really so valuable? My opinion: no, this is nothing but a new loophole to consume memory without control. ---------------------------------------- So revert this thing for now. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-13 07:31:35 +08:00
u8 rskq_defer_accept;
/* 3 bytes hole, try to pack */
struct listen_sock *listen_opt;
struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been
* enabled on this listener. Check
* max_qlen != 0 in fastopen_queue
* to determine if TFO is enabled
* right at this moment.
*/
};
extern int reqsk_queue_alloc(struct request_sock_queue *queue,
unsigned int nr_table_entries);
extern void __reqsk_queue_destroy(struct request_sock_queue *queue);
extern void reqsk_queue_destroy(struct request_sock_queue *queue);
extern void reqsk_fastopen_remove(struct sock *sk,
struct request_sock *req, bool reset);
static inline struct request_sock *
reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
{
struct request_sock *req = queue->rskq_accept_head;
queue->rskq_accept_head = NULL;
return req;
}
static inline int reqsk_queue_empty(struct request_sock_queue *queue)
{
return queue->rskq_accept_head == NULL;
}
static inline void reqsk_queue_unlink(struct request_sock_queue *queue,
struct request_sock *req,
struct request_sock **prev_req)
{
write_lock(&queue->syn_wait_lock);
*prev_req = req->dl_next;
write_unlock(&queue->syn_wait_lock);
}
static inline void reqsk_queue_add(struct request_sock_queue *queue,
struct request_sock *req,
struct sock *parent,
struct sock *child)
{
req->sk = child;
sk_acceptq_added(parent);
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_head = req;
else
queue->rskq_accept_tail->dl_next = req;
queue->rskq_accept_tail = req;
req->dl_next = NULL;
}
static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue)
{
struct request_sock *req = queue->rskq_accept_head;
WARN_ON(req == NULL);
queue->rskq_accept_head = req->dl_next;
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_tail = NULL;
return req;
}
static inline int reqsk_queue_removed(struct request_sock_queue *queue,
struct request_sock *req)
{
struct listen_sock *lopt = queue->listen_opt;
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 07:16:46 +08:00
if (req->num_timeout == 0)
--lopt->qlen_young;
return --lopt->qlen;
}
static inline int reqsk_queue_added(struct request_sock_queue *queue)
{
struct listen_sock *lopt = queue->listen_opt;
const int prev_qlen = lopt->qlen;
lopt->qlen_young++;
lopt->qlen++;
return prev_qlen;
}
static inline int reqsk_queue_len(const struct request_sock_queue *queue)
{
return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0;
}
static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
{
return queue->listen_opt->qlen_young;
}
static inline int reqsk_queue_is_full(const struct request_sock_queue *queue)
{
return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log;
}
static inline void reqsk_queue_hash_req(struct request_sock_queue *queue,
u32 hash, struct request_sock *req,
unsigned long timeout)
{
struct listen_sock *lopt = queue->listen_opt;
req->expires = jiffies + timeout;
tcp: better retrans tracking for defer-accept For passive TCP connections using TCP_DEFER_ACCEPT facility, we incorrectly increment req->retrans each time timeout triggers while no SYNACK is sent. SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for which we received the ACK from client). Only the last SYNACK is sent so that we can receive again an ACK from client, to move the req into accept queue. We plan to change this later to avoid the useless retransmit (and potential problem as this SYNACK could be lost) TCP_INFO later gives wrong information to user, claiming imaginary retransmits. Decouple req->retrans field into two independent fields : num_retrans : number of retransmit num_timeout : number of timeouts num_timeout is the counter that is incremented at each timeout, regardless of actual SYNACK being sent or not, and used to compute the exponential timeout. Introduce inet_rtx_syn_ack() helper to increment num_retrans only if ->rtx_syn_ack() succeeded. Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans when we re-send a SYNACK in answer to a (retransmitted) SYN. Prior to this patch, we were not counting these retransmits. Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS only if a synack packet was successfully queued. Reported-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Cc: Vijay Subramanian <subramanian.vijay@gmail.com> Cc: Elliott Hughes <enh@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-10-28 07:16:46 +08:00
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
req->dl_next = lopt->syn_table[hash];
write_lock(&queue->syn_wait_lock);
lopt->syn_table[hash] = req;
write_unlock(&queue->syn_wait_lock);
}
#endif /* _REQUEST_SOCK_H */