1// SPDX-License-Identifier: GPL-2.0-or-later
2/* incoming call handling
3 *
4 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
5 * Written by David Howells (dhowells@redhat.com)
6 */
7
8#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
9
10#include <linux/module.h>
11#include <linux/net.h>
12#include <linux/skbuff.h>
13#include <linux/errqueue.h>
14#include <linux/udp.h>
15#include <linux/in.h>
16#include <linux/in6.h>
17#include <linux/icmp.h>
18#include <linux/gfp.h>
19#include <linux/circ_buf.h>
20#include <net/sock.h>
21#include <net/af_rxrpc.h>
22#include <net/ip.h>
23#include "ar-internal.h"
24
25static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
26			       unsigned long user_call_ID)
27{
28}
29
30/*
31 * Preallocate a single service call, connection and peer and, if possible,
32 * give them a user ID and attach the user's side of the ID to them.
33 */
34static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
35				      struct rxrpc_backlog *b,
36				      rxrpc_notify_rx_t notify_rx,
37				      rxrpc_user_attach_call_t user_attach_call,
38				      unsigned long user_call_ID, gfp_t gfp,
39				      unsigned int debug_id)
40{
41	const void *here = __builtin_return_address(0);
42	struct rxrpc_call *call, *xcall;
43	struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
44	struct rb_node *parent, **pp;
45	int max, tmp;
46	unsigned int size = RXRPC_BACKLOG_MAX;
47	unsigned int head, tail, call_head, call_tail;
48
49	max = rx->sk.sk_max_ack_backlog;
50	tmp = rx->sk.sk_ack_backlog;
51	if (tmp >= max) {
52		_leave(" = -ENOBUFS [full %u]", max);
53		return -ENOBUFS;
54	}
55	max -= tmp;
56
57	/* We don't need more conns and peers than we have calls, but on the
58	 * other hand, we shouldn't ever use more peers than conns or conns
59	 * than calls.
60	 */
61	call_head = b->call_backlog_head;
62	call_tail = READ_ONCE(b->call_backlog_tail);
63	tmp = CIRC_CNT(call_head, call_tail, size);
64	if (tmp >= max) {
65		_leave(" = -ENOBUFS [enough %u]", tmp);
66		return -ENOBUFS;
67	}
68	max = tmp + 1;
69
70	head = b->peer_backlog_head;
71	tail = READ_ONCE(b->peer_backlog_tail);
72	if (CIRC_CNT(head, tail, size) < max) {
73		struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp);
74		if (!peer)
75			return -ENOMEM;
76		b->peer_backlog[head] = peer;
77		smp_store_release(&b->peer_backlog_head,
78				  (head + 1) & (size - 1));
79	}
80
81	head = b->conn_backlog_head;
82	tail = READ_ONCE(b->conn_backlog_tail);
83	if (CIRC_CNT(head, tail, size) < max) {
84		struct rxrpc_connection *conn;
85
86		conn = rxrpc_prealloc_service_connection(rxnet, gfp);
87		if (!conn)
88			return -ENOMEM;
89		b->conn_backlog[head] = conn;
90		smp_store_release(&b->conn_backlog_head,
91				  (head + 1) & (size - 1));
92
93		trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
94				 refcount_read(&conn->ref), here);
95	}
96
97	/* Now it gets complicated, because calls get registered with the
98	 * socket here, with a user ID preassigned by the user.
99	 */
100	call = rxrpc_alloc_call(rx, gfp, debug_id);
101	if (!call)
102		return -ENOMEM;
103	call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
104	call->state = RXRPC_CALL_SERVER_PREALLOC;
105
106	trace_rxrpc_call(call->debug_id, rxrpc_call_new_service,
107			 refcount_read(&call->ref),
108			 here, (const void *)user_call_ID);
109
110	write_lock(&rx->call_lock);
111
112	/* Check the user ID isn't already in use */
113	pp = &rx->calls.rb_node;
114	parent = NULL;
115	while (*pp) {
116		parent = *pp;
117		xcall = rb_entry(parent, struct rxrpc_call, sock_node);
118		if (user_call_ID < xcall->user_call_ID)
119			pp = &(*pp)->rb_left;
120		else if (user_call_ID > xcall->user_call_ID)
121			pp = &(*pp)->rb_right;
122		else
123			goto id_in_use;
124	}
125
126	call->user_call_ID = user_call_ID;
127	call->notify_rx = notify_rx;
128	if (user_attach_call) {
129		rxrpc_get_call(call, rxrpc_call_got_kernel);
130		user_attach_call(call, user_call_ID);
131	}
132
133	rxrpc_get_call(call, rxrpc_call_got_userid);
134	rb_link_node(&call->sock_node, parent, pp);
135	rb_insert_color(&call->sock_node, &rx->calls);
136	set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
137
138	list_add(&call->sock_link, &rx->sock_calls);
139
140	write_unlock(&rx->call_lock);
141
142	rxnet = call->rxnet;
143	write_lock(&rxnet->call_lock);
144	list_add_tail(&call->link, &rxnet->calls);
145	write_unlock(&rxnet->call_lock);
146
147	b->call_backlog[call_head] = call;
148	smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
149	_leave(" = 0 [%d -> %lx]", call->debug_id, user_call_ID);
150	return 0;
151
152id_in_use:
153	write_unlock(&rx->call_lock);
154	rxrpc_cleanup_call(call);
155	_leave(" = -EBADSLT");
156	return -EBADSLT;
157}
158
159/*
160 * Allocate the preallocation buffers for incoming service calls.  These must
161 * be charged manually.
162 */
163int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
164{
165	struct rxrpc_backlog *b = rx->backlog;
166
167	if (!b) {
168		b = kzalloc(sizeof(struct rxrpc_backlog), gfp);
169		if (!b)
170			return -ENOMEM;
171		rx->backlog = b;
172	}
173
174	return 0;
175}
176
177/*
178 * Discard the preallocation on a service.
179 */
180void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
181{
182	struct rxrpc_backlog *b = rx->backlog;
183	struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
184	unsigned int size = RXRPC_BACKLOG_MAX, head, tail;
185
186	if (!b)
187		return;
188	rx->backlog = NULL;
189
190	/* Make sure that there aren't any incoming calls in progress before we
191	 * clear the preallocation buffers.
192	 */
193	spin_lock_bh(&rx->incoming_lock);
194	spin_unlock_bh(&rx->incoming_lock);
195
196	head = b->peer_backlog_head;
197	tail = b->peer_backlog_tail;
198	while (CIRC_CNT(head, tail, size) > 0) {
199		struct rxrpc_peer *peer = b->peer_backlog[tail];
200		rxrpc_put_local(peer->local);
201		kfree(peer);
202		tail = (tail + 1) & (size - 1);
203	}
204
205	head = b->conn_backlog_head;
206	tail = b->conn_backlog_tail;
207	while (CIRC_CNT(head, tail, size) > 0) {
208		struct rxrpc_connection *conn = b->conn_backlog[tail];
209		write_lock(&rxnet->conn_lock);
210		list_del(&conn->link);
211		list_del(&conn->proc_link);
212		write_unlock(&rxnet->conn_lock);
213		kfree(conn);
214		if (atomic_dec_and_test(&rxnet->nr_conns))
215			wake_up_var(&rxnet->nr_conns);
216		tail = (tail + 1) & (size - 1);
217	}
218
219	head = b->call_backlog_head;
220	tail = b->call_backlog_tail;
221	while (CIRC_CNT(head, tail, size) > 0) {
222		struct rxrpc_call *call = b->call_backlog[tail];
223		rcu_assign_pointer(call->socket, rx);
224		if (rx->discard_new_call) {
225			_debug("discard %lx", call->user_call_ID);
226			rx->discard_new_call(call, call->user_call_ID);
227			if (call->notify_rx)
228				call->notify_rx = rxrpc_dummy_notify;
229			rxrpc_put_call(call, rxrpc_call_put_kernel);
230		}
231		rxrpc_call_completed(call);
232		rxrpc_release_call(rx, call);
233		rxrpc_put_call(call, rxrpc_call_put);
234		tail = (tail + 1) & (size - 1);
235	}
236
237	kfree(b);
238}
239
240/*
241 * Ping the other end to fill our RTT cache and to retrieve the rwind
242 * and MTU parameters.
243 */
244static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb)
245{
246	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
247	ktime_t now = skb->tstamp;
248
249	if (call->peer->rtt_count < 3 ||
250	    ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now))
251		rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial,
252				  true, true,
253				  rxrpc_propose_ack_ping_for_params);
254}
255
256/*
257 * Allocate a new incoming call from the prealloc pool, along with a connection
258 * and a peer as necessary.
259 */
260static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
261						    struct rxrpc_local *local,
262						    struct rxrpc_peer *peer,
263						    struct rxrpc_connection *conn,
264						    const struct rxrpc_security *sec,
265						    struct key *key,
266						    struct sk_buff *skb)
267{
268	struct rxrpc_backlog *b = rx->backlog;
269	struct rxrpc_call *call;
270	unsigned short call_head, conn_head, peer_head;
271	unsigned short call_tail, conn_tail, peer_tail;
272	unsigned short call_count, conn_count;
273
274	/* #calls >= #conns >= #peers must hold true. */
275	call_head = smp_load_acquire(&b->call_backlog_head);
276	call_tail = b->call_backlog_tail;
277	call_count = CIRC_CNT(call_head, call_tail, RXRPC_BACKLOG_MAX);
278	conn_head = smp_load_acquire(&b->conn_backlog_head);
279	conn_tail = b->conn_backlog_tail;
280	conn_count = CIRC_CNT(conn_head, conn_tail, RXRPC_BACKLOG_MAX);
281	ASSERTCMP(conn_count, >=, call_count);
282	peer_head = smp_load_acquire(&b->peer_backlog_head);
283	peer_tail = b->peer_backlog_tail;
284	ASSERTCMP(CIRC_CNT(peer_head, peer_tail, RXRPC_BACKLOG_MAX), >=,
285		  conn_count);
286
287	if (call_count == 0)
288		return NULL;
289
290	if (!conn) {
291		if (peer && !rxrpc_get_peer_maybe(peer))
292			peer = NULL;
293		if (!peer) {
294			peer = b->peer_backlog[peer_tail];
295			if (rxrpc_extract_addr_from_skb(&peer->srx, skb) < 0)
296				return NULL;
297			b->peer_backlog[peer_tail] = NULL;
298			smp_store_release(&b->peer_backlog_tail,
299					  (peer_tail + 1) &
300					  (RXRPC_BACKLOG_MAX - 1));
301
302			rxrpc_new_incoming_peer(rx, local, peer);
303		}
304
305		/* Now allocate and set up the connection */
306		conn = b->conn_backlog[conn_tail];
307		b->conn_backlog[conn_tail] = NULL;
308		smp_store_release(&b->conn_backlog_tail,
309				  (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1));
310		conn->params.local = rxrpc_get_local(local);
311		conn->params.peer = peer;
312		rxrpc_see_connection(conn);
313		rxrpc_new_incoming_connection(rx, conn, sec, key, skb);
314	} else {
315		rxrpc_get_connection(conn);
316	}
317
318	/* And now we can allocate and set up a new call */
319	call = b->call_backlog[call_tail];
320	b->call_backlog[call_tail] = NULL;
321	smp_store_release(&b->call_backlog_tail,
322			  (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1));
323
324	rxrpc_see_call(call);
325	call->conn = conn;
326	call->security = conn->security;
327	call->security_ix = conn->security_ix;
328	call->peer = rxrpc_get_peer(conn->params.peer);
329	call->cong_cwnd = call->peer->cong_cwnd;
330	return call;
331}
332
333/*
334 * Set up a new incoming call.  Called in BH context with the RCU read lock
335 * held.
336 *
337 * If this is for a kernel service, when we allocate the call, it will have
338 * three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the
339 * retainer ref obtained from the backlog buffer.  Prealloc calls for userspace
340 * services only have the ref from the backlog buffer.  We want to pass this
341 * ref to non-BH context to dispose of.
342 *
343 * If we want to report an error, we mark the skb with the packet type and
344 * abort code and return NULL.
345 *
346 * The call is returned with the user access mutex held.
347 */
348struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
349					   struct rxrpc_sock *rx,
350					   struct sk_buff *skb)
351{
352	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
353	const struct rxrpc_security *sec = NULL;
354	struct rxrpc_connection *conn;
355	struct rxrpc_peer *peer = NULL;
356	struct rxrpc_call *call = NULL;
357	struct key *key = NULL;
358
359	_enter("");
360
361	spin_lock(&rx->incoming_lock);
362	if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
363	    rx->sk.sk_state == RXRPC_CLOSE) {
364		trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
365				  sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
366		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
367		skb->priority = RX_INVALID_OPERATION;
368		goto no_call;
369	}
370
371	/* The peer, connection and call may all have sprung into existence due
372	 * to a duplicate packet being handled on another CPU in parallel, so
373	 * we have to recheck the routing.  However, we're now holding
374	 * rx->incoming_lock, so the values should remain stable.
375	 */
376	conn = rxrpc_find_connection_rcu(local, skb, &peer);
377
378	if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb))
379		goto no_call;
380
381	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb);
382	key_put(key);
383	if (!call) {
384		skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
385		goto no_call;
386	}
387
388	trace_rxrpc_receive(call, rxrpc_receive_incoming,
389			    sp->hdr.serial, sp->hdr.seq);
390
391	/* Make the call live. */
392	rxrpc_incoming_call(rx, call, skb);
393	conn = call->conn;
394
395	if (rx->notify_new_call)
396		rx->notify_new_call(&rx->sk, call, call->user_call_ID);
397
398	spin_lock(&conn->state_lock);
399	switch (conn->state) {
400	case RXRPC_CONN_SERVICE_UNSECURED:
401		conn->state = RXRPC_CONN_SERVICE_CHALLENGING;
402		set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events);
403		rxrpc_queue_conn(call->conn);
404		break;
405
406	case RXRPC_CONN_SERVICE:
407		write_lock(&call->state_lock);
408		if (call->state < RXRPC_CALL_COMPLETE)
409			call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
410		write_unlock(&call->state_lock);
411		break;
412
413	case RXRPC_CONN_REMOTELY_ABORTED:
414		rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
415					  conn->abort_code, conn->error);
416		break;
417	case RXRPC_CONN_LOCALLY_ABORTED:
418		rxrpc_abort_call("CON", call, sp->hdr.seq,
419				 conn->abort_code, conn->error);
420		break;
421	default:
422		BUG();
423	}
424	spin_unlock(&conn->state_lock);
425	spin_unlock(&rx->incoming_lock);
426
427	rxrpc_send_ping(call, skb);
428
429	/* We have to discard the prealloc queue's ref here and rely on a
430	 * combination of the RCU read lock and refs held either by the socket
431	 * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel
432	 * service to prevent the call from being deallocated too early.
433	 */
434	rxrpc_put_call(call, rxrpc_call_put);
435
436	_leave(" = %p{%d}", call, call->debug_id);
437	return call;
438
439no_call:
440	spin_unlock(&rx->incoming_lock);
441	_leave(" = NULL [%u]", skb->mark);
442	return NULL;
443}
444
445/*
446 * Charge up socket with preallocated calls, attaching user call IDs.
447 */
448int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID)
449{
450	struct rxrpc_backlog *b = rx->backlog;
451
452	if (rx->sk.sk_state == RXRPC_CLOSE)
453		return -ESHUTDOWN;
454
455	return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID,
456					  GFP_KERNEL,
457					  atomic_inc_return(&rxrpc_debug_id));
458}
459
460/*
461 * rxrpc_kernel_charge_accept - Charge up socket with preallocated calls
462 * @sock: The socket on which to preallocate
463 * @notify_rx: Event notification function for the call
464 * @user_attach_call: Func to attach call to user_call_ID
465 * @user_call_ID: The tag to attach to the preallocated call
466 * @gfp: The allocation conditions.
467 * @debug_id: The tracing debug ID.
468 *
469 * Charge up the socket with preallocated calls, each with a user ID.  A
470 * function should be provided to effect the attachment from the user's side.
471 * The user is given a ref to hold on the call.
472 *
473 * Note that the call may be come connected before this function returns.
474 */
475int rxrpc_kernel_charge_accept(struct socket *sock,
476			       rxrpc_notify_rx_t notify_rx,
477			       rxrpc_user_attach_call_t user_attach_call,
478			       unsigned long user_call_ID, gfp_t gfp,
479			       unsigned int debug_id)
480{
481	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
482	struct rxrpc_backlog *b = rx->backlog;
483
484	if (sock->sk->sk_state == RXRPC_CLOSE)
485		return -ESHUTDOWN;
486
487	return rxrpc_service_prealloc_one(rx, b, notify_rx,
488					  user_attach_call, user_call_ID,
489					  gfp, debug_id);
490}
491EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
492