OpenCloudOS-Kernel/include/net/request_sock.h

233 lines
6.3 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* 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
*/
#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 <linux/refcount.h>
#include <net/sock.h>
struct request_sock;
struct sk_buff;
struct dst_entry;
struct proto;
struct request_sock_ops {
int family;
unsigned int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(const struct sock *sk,
struct request_sock *req);
void (*send_ack)(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(const struct sock *sk,
struct sk_buff *skb);
void (*destructor)(struct request_sock *req);
void (*syn_ack_timeout)(const struct request_sock *req);
};
int inet_rtx_syn_ack(const struct sock *parent, 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
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
struct sock_common __req_common;
#define rsk_refcnt __req_common.skc_refcnt
#define rsk_hash __req_common.skc_hash
#define rsk_listener __req_common.skc_listener
#define rsk_window_clamp __req_common.skc_window_clamp
#define rsk_rcv_wnd __req_common.skc_rcv_wnd
struct request_sock *dl_next;
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 */
u32 ts_recent;
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
u32 *saved_syn;
u32 secid;
u32 peer_secid;
};
static inline struct request_sock *inet_reqsk(const struct sock *sk)
{
return (struct request_sock *)sk;
}
static inline struct sock *req_to_sk(struct request_sock *req)
{
return (struct sock *)req;
}
static inline struct request_sock *
reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
bool attach_listener)
{
struct request_sock *req;
req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
if (!req)
return NULL;
req->rsk_listener = NULL;
if (attach_listener) {
if (unlikely(!refcount_inc_not_zero(&sk_listener->sk_refcnt))) {
kmem_cache_free(ops->slab, req);
return NULL;
}
req->rsk_listener = sk_listener;
}
req->rsk_ops = ops;
req_to_sk(req)->sk_prot = sk_listener->sk_prot;
sk_node_init(&req_to_sk(req)->sk_node);
sk_tx_queue_clear(req_to_sk(req));
req->saved_syn = NULL;
inet: clear num_timeout reqsk_alloc() KMSAN caught uninit-value in tcp_create_openreq_child() [1] This is caused by a recent change, combined by the fact that TCP cleared num_timeout, num_retrans and sk fields only when a request socket was about to be queued. Under syncookie mode, a temporary request socket is used, and req->num_timeout could contain garbage. Lets clear these three fields sooner, there is really no point trying to defer this and risk other bugs. [1] BUG: KMSAN: uninit-value in tcp_create_openreq_child+0x157f/0x1cc0 net/ipv4/tcp_minisocks.c:526 CPU: 1 PID: 13357 Comm: syz-executor591 Not tainted 5.2.0-rc4+ #3 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <IRQ> __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x191/0x1f0 lib/dump_stack.c:113 kmsan_report+0x162/0x2d0 mm/kmsan/kmsan.c:611 __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:304 tcp_create_openreq_child+0x157f/0x1cc0 net/ipv4/tcp_minisocks.c:526 tcp_v6_syn_recv_sock+0x761/0x2d80 net/ipv6/tcp_ipv6.c:1152 tcp_get_cookie_sock+0x16e/0x6b0 net/ipv4/syncookies.c:209 cookie_v6_check+0x27e0/0x29a0 net/ipv6/syncookies.c:252 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1039 [inline] tcp_v6_do_rcv+0xf1c/0x1ce0 net/ipv6/tcp_ipv6.c:1344 tcp_v6_rcv+0x60b7/0x6a30 net/ipv6/tcp_ipv6.c:1554 ip6_protocol_deliver_rcu+0x1433/0x22f0 net/ipv6/ip6_input.c:397 ip6_input_finish net/ipv6/ip6_input.c:438 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ip6_input+0x2af/0x340 net/ipv6/ip6_input.c:447 dst_input include/net/dst.h:439 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core net/core/dev.c:4981 [inline] __netif_receive_skb net/core/dev.c:5095 [inline] process_backlog+0x721/0x1410 net/core/dev.c:5906 napi_poll net/core/dev.c:6329 [inline] net_rx_action+0x738/0x1940 net/core/dev.c:6395 __do_softirq+0x4ad/0x858 kernel/softirq.c:293 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1052 </IRQ> do_softirq kernel/softirq.c:338 [inline] __local_bh_enable_ip+0x199/0x1e0 kernel/softirq.c:190 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:682 [inline] ip6_finish_output2+0x213f/0x2670 net/ipv6/ip6_output.c:117 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:150 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x5d3/0x720 net/ipv6/ip6_output.c:167 dst_output include/net/dst.h:433 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ip6_xmit+0x1f53/0x2650 net/ipv6/ip6_output.c:271 inet6_csk_xmit+0x3df/0x4f0 net/ipv6/inet6_connection_sock.c:135 __tcp_transmit_skb+0x4076/0x5b40 net/ipv4/tcp_output.c:1156 tcp_transmit_skb net/ipv4/tcp_output.c:1172 [inline] tcp_write_xmit+0x39a9/0xa730 net/ipv4/tcp_output.c:2397 __tcp_push_pending_frames+0x124/0x4e0 net/ipv4/tcp_output.c:2573 tcp_send_fin+0xd43/0x1540 net/ipv4/tcp_output.c:3118 tcp_close+0x16ba/0x1860 net/ipv4/tcp.c:2403 inet_release+0x1f7/0x270 net/ipv4/af_inet.c:427 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:470 __sock_release net/socket.c:601 [inline] sock_close+0x156/0x490 net/socket.c:1273 __fput+0x4c9/0xba0 fs/file_table.c:280 ____fput+0x37/0x40 fs/file_table.c:313 task_work_run+0x22e/0x2a0 kernel/task_work.c:113 tracehook_notify_resume include/linux/tracehook.h:185 [inline] exit_to_usermode_loop arch/x86/entry/common.c:168 [inline] prepare_exit_to_usermode+0x39d/0x4d0 arch/x86/entry/common.c:199 syscall_return_slowpath+0x90/0x5c0 arch/x86/entry/common.c:279 do_syscall_64+0xe2/0xf0 arch/x86/entry/common.c:305 entry_SYSCALL_64_after_hwframe+0x63/0xe7 RIP: 0033:0x401d50 Code: 01 f0 ff ff 0f 83 40 0d 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d dd 8d 2d 00 00 75 14 b8 03 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 14 0d 00 00 c3 48 83 ec 08 e8 7a 02 00 00 RSP: 002b:00007fff1cf58cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 RAX: 0000000000000000 RBX: 0000000000000004 RCX: 0000000000401d50 RDX: 000000000000001c RSI: 0000000000000000 RDI: 0000000000000003 RBP: 00000000004a9050 R08: 0000000020000040 R09: 000000000000001c R10: 0000000020004004 R11: 0000000000000246 R12: 0000000000402ef0 R13: 0000000000402f80 R14: 0000000000000000 R15: 0000000000000000 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:201 [inline] kmsan_internal_poison_shadow+0x53/0xa0 mm/kmsan/kmsan.c:160 kmsan_kmalloc+0xa4/0x130 mm/kmsan/kmsan_hooks.c:177 kmem_cache_alloc+0x534/0xb00 mm/slub.c:2781 reqsk_alloc include/net/request_sock.h:84 [inline] inet_reqsk_alloc+0xa8/0x600 net/ipv4/tcp_input.c:6384 cookie_v6_check+0xadb/0x29a0 net/ipv6/syncookies.c:173 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1039 [inline] tcp_v6_do_rcv+0xf1c/0x1ce0 net/ipv6/tcp_ipv6.c:1344 tcp_v6_rcv+0x60b7/0x6a30 net/ipv6/tcp_ipv6.c:1554 ip6_protocol_deliver_rcu+0x1433/0x22f0 net/ipv6/ip6_input.c:397 ip6_input_finish net/ipv6/ip6_input.c:438 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ip6_input+0x2af/0x340 net/ipv6/ip6_input.c:447 dst_input include/net/dst.h:439 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:272 __netif_receive_skb_one_core net/core/dev.c:4981 [inline] __netif_receive_skb net/core/dev.c:5095 [inline] process_backlog+0x721/0x1410 net/core/dev.c:5906 napi_poll net/core/dev.c:6329 [inline] net_rx_action+0x738/0x1940 net/core/dev.c:6395 __do_softirq+0x4ad/0x858 kernel/softirq.c:293 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1052 do_softirq kernel/softirq.c:338 [inline] __local_bh_enable_ip+0x199/0x1e0 kernel/softirq.c:190 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32 rcu_read_unlock_bh include/linux/rcupdate.h:682 [inline] ip6_finish_output2+0x213f/0x2670 net/ipv6/ip6_output.c:117 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:150 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip6_output+0x5d3/0x720 net/ipv6/ip6_output.c:167 dst_output include/net/dst.h:433 [inline] NF_HOOK include/linux/netfilter.h:305 [inline] ip6_xmit+0x1f53/0x2650 net/ipv6/ip6_output.c:271 inet6_csk_xmit+0x3df/0x4f0 net/ipv6/inet6_connection_sock.c:135 __tcp_transmit_skb+0x4076/0x5b40 net/ipv4/tcp_output.c:1156 tcp_transmit_skb net/ipv4/tcp_output.c:1172 [inline] tcp_write_xmit+0x39a9/0xa730 net/ipv4/tcp_output.c:2397 __tcp_push_pending_frames+0x124/0x4e0 net/ipv4/tcp_output.c:2573 tcp_send_fin+0xd43/0x1540 net/ipv4/tcp_output.c:3118 tcp_close+0x16ba/0x1860 net/ipv4/tcp.c:2403 inet_release+0x1f7/0x270 net/ipv4/af_inet.c:427 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:470 __sock_release net/socket.c:601 [inline] sock_close+0x156/0x490 net/socket.c:1273 __fput+0x4c9/0xba0 fs/file_table.c:280 ____fput+0x37/0x40 fs/file_table.c:313 task_work_run+0x22e/0x2a0 kernel/task_work.c:113 tracehook_notify_resume include/linux/tracehook.h:185 [inline] exit_to_usermode_loop arch/x86/entry/common.c:168 [inline] prepare_exit_to_usermode+0x39d/0x4d0 arch/x86/entry/common.c:199 syscall_return_slowpath+0x90/0x5c0 arch/x86/entry/common.c:279 do_syscall_64+0xe2/0xf0 arch/x86/entry/common.c:305 entry_SYSCALL_64_after_hwframe+0x63/0xe7 Fixes: 336c39a03151 ("tcp: undo init congestion window on false SYNACK timeout") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Soheil Hassas Yeganeh <soheil@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-20 00:38:38 +08:00
req->num_timeout = 0;
req->num_retrans = 0;
req->sk = NULL;
refcount_set(&req->rsk_refcnt, 0);
return req;
}
static inline void __reqsk_free(struct request_sock *req)
{
req->rsk_ops->destructor(req);
if (req->rsk_listener)
sock_put(req->rsk_listener);
kfree(req->saved_syn);
kmem_cache_free(req->rsk_ops->slab, req);
}
static inline void reqsk_free(struct request_sock *req)
{
WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
__reqsk_free(req);
}
static inline void reqsk_put(struct request_sock *req)
{
if (refcount_dec_and_test(&req->rsk_refcnt))
reqsk_free(req);
}
/*
* 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 tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */
};
/** 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()
*
*/
struct request_sock_queue {
spinlock_t rskq_lock;
u8 rskq_defer_accept;
u32 synflood_warned;
atomic_t qlen;
atomic_t young;
struct request_sock *rskq_accept_head;
struct request_sock *rskq_accept_tail;
struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine
* if TFO is enabled.
*/
};
void reqsk_queue_alloc(struct request_sock_queue *queue);
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset);
static inline bool reqsk_queue_empty(const struct request_sock_queue *queue)
{
return queue->rskq_accept_head == NULL;
}
static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue,
struct sock *parent)
{
struct request_sock *req;
spin_lock_bh(&queue->rskq_lock);
req = queue->rskq_accept_head;
if (req) {
sk_acceptq_removed(parent);
queue->rskq_accept_head = req->dl_next;
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_tail = NULL;
}
spin_unlock_bh(&queue->rskq_lock);
return req;
}
static inline void reqsk_queue_removed(struct request_sock_queue *queue,
const 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
if (req->num_timeout == 0)
atomic_dec(&queue->young);
atomic_dec(&queue->qlen);
}
static inline void reqsk_queue_added(struct request_sock_queue *queue)
{
atomic_inc(&queue->young);
atomic_inc(&queue->qlen);
}
static inline int reqsk_queue_len(const struct request_sock_queue *queue)
{
return atomic_read(&queue->qlen);
}
static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
{
return atomic_read(&queue->young);
}
#endif /* _REQUEST_SOCK_H */