860 lines · 21.6 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-or-later/* AF_RXRPC sendmsg() implementation. * * Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/net.h>#include <linux/gfp.h>#include <linux/skbuff.h>#include <linux/export.h>#include <linux/sched/signal.h> #include <net/sock.h>#include <net/af_rxrpc.h>#include "ar-internal.h" /* * Return true if there's sufficient Tx queue space. */static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win){	unsigned int win_size =		min_t(unsigned int, call->tx_winsize,		      call->cong_cwnd + call->cong_extra);	rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); 	if (_tx_win)		*_tx_win = tx_win;	return call->tx_top - tx_win < win_size;} /* * Wait for space to appear in the Tx queue or a signal to occur. */static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx,					 struct rxrpc_call *call,					 long *timeo){	for (;;) {		set_current_state(TASK_INTERRUPTIBLE);		if (rxrpc_check_tx_space(call, NULL))			return 0; 		if (call->state >= RXRPC_CALL_COMPLETE)			return call->error; 		if (signal_pending(current))			return sock_intr_errno(*timeo); 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);		mutex_unlock(&call->user_mutex);		*timeo = schedule_timeout(*timeo);		if (mutex_lock_interruptible(&call->user_mutex) < 0)			return sock_intr_errno(*timeo);	}} /* * Wait for space to appear in the Tx queue uninterruptibly, but with * a timeout of 2*RTT if no progress was made and a signal occurred. */static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx,					    struct rxrpc_call *call){	rxrpc_seq_t tx_start, tx_win;	signed long rtt, timeout; 	rtt = READ_ONCE(call->peer->srtt_us) >> 3;	rtt = usecs_to_jiffies(rtt) * 2;	if (rtt < 2)		rtt = 2; 	timeout = rtt;	tx_start = READ_ONCE(call->tx_hard_ack); 	for (;;) {		set_current_state(TASK_UNINTERRUPTIBLE); 		tx_win = READ_ONCE(call->tx_hard_ack);		if (rxrpc_check_tx_space(call, &tx_win))			return 0; 		if (call->state >= RXRPC_CALL_COMPLETE)			return call->error; 		if (timeout == 0 &&		    tx_win == tx_start && signal_pending(current))			return -EINTR; 		if (tx_win != tx_start) {			timeout = rtt;			tx_start = tx_win;		} 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);		timeout = schedule_timeout(timeout);	}} /* * Wait for space to appear in the Tx queue uninterruptibly. */static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx,					    struct rxrpc_call *call,					    long *timeo){	for (;;) {		set_current_state(TASK_UNINTERRUPTIBLE);		if (rxrpc_check_tx_space(call, NULL))			return 0; 		if (call->state >= RXRPC_CALL_COMPLETE)			return call->error; 		trace_rxrpc_transmit(call, rxrpc_transmit_wait);		*timeo = schedule_timeout(*timeo);	}} /* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx,				    struct rxrpc_call *call,				    long *timeo,				    bool waitall){	DECLARE_WAITQUEUE(myself, current);	int ret; 	_enter(",{%u,%u,%u}",	       call->tx_hard_ack, call->tx_top, call->tx_winsize); 	add_wait_queue(&call->waitq, &myself); 	switch (call->interruptibility) {	case RXRPC_INTERRUPTIBLE:		if (waitall)			ret = rxrpc_wait_for_tx_window_waitall(rx, call);		else			ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);		break;	case RXRPC_PREINTERRUPTIBLE:	case RXRPC_UNINTERRUPTIBLE:	default:		ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo);		break;	} 	remove_wait_queue(&call->waitq, &myself);	set_current_state(TASK_RUNNING);	_leave(" = %d", ret);	return ret;} /* * Schedule an instant Tx resend. */static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix){	spin_lock_bh(&call->lock); 	if (call->state < RXRPC_CALL_COMPLETE) {		call->rxtx_annotations[ix] =			(call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) |			RXRPC_TX_ANNO_RETRANS;		if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))			rxrpc_queue_call(call);	} 	spin_unlock_bh(&call->lock);} /* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. */static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call,				rxrpc_notify_end_tx_t notify_end_tx){	if (notify_end_tx)		notify_end_tx(&rx->sk, call, call->user_call_ID);} /* * Queue a DATA packet for transmission, set the resend timeout and send * the packet immediately.  Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,			      struct sk_buff *skb, bool last,			      rxrpc_notify_end_tx_t notify_end_tx){	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);	unsigned long now;	rxrpc_seq_t seq = sp->hdr.seq;	int ret, ix;	u8 annotation = RXRPC_TX_ANNO_UNACK; 	_net("queue skb %p [%d]", skb, seq); 	ASSERTCMP(seq, ==, call->tx_top + 1); 	if (last)		annotation |= RXRPC_TX_ANNO_LAST; 	/* We have to set the timestamp before queueing as the retransmit	 * algorithm can see the packet as soon as we queue it.	 */	skb->tstamp = ktime_get_real(); 	ix = seq & RXRPC_RXTX_BUFF_MASK;	rxrpc_get_skb(skb, rxrpc_skb_got);	call->rxtx_annotations[ix] = annotation;	smp_wmb();	call->rxtx_buffer[ix] = skb;	call->tx_top = seq;	if (last)		trace_rxrpc_transmit(call, rxrpc_transmit_queue_last);	else		trace_rxrpc_transmit(call, rxrpc_transmit_queue); 	if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {		_debug("________awaiting reply/ACK__________");		write_lock_bh(&call->state_lock);		switch (call->state) {		case RXRPC_CALL_CLIENT_SEND_REQUEST:			call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;			rxrpc_notify_end_tx(rx, call, notify_end_tx);			break;		case RXRPC_CALL_SERVER_ACK_REQUEST:			call->state = RXRPC_CALL_SERVER_SEND_REPLY;			now = jiffies;			WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET);			if (call->ackr_reason == RXRPC_ACK_DELAY)				call->ackr_reason = 0;			trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now);			if (!last)				break;			fallthrough;		case RXRPC_CALL_SERVER_SEND_REPLY:			call->state = RXRPC_CALL_SERVER_AWAIT_ACK;			rxrpc_notify_end_tx(rx, call, notify_end_tx);			break;		default:			break;		}		write_unlock_bh(&call->state_lock);	} 	if (seq == 1 && rxrpc_is_client_call(call))		rxrpc_expose_client_call(call); 	ret = rxrpc_send_data_packet(call, skb, false);	if (ret < 0) {		switch (ret) {		case -ENETUNREACH:		case -EHOSTUNREACH:		case -ECONNREFUSED:			rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,						  0, ret);			goto out;		}		_debug("need instant resend %d", ret);		rxrpc_instant_resend(call, ix);	} else {		unsigned long now = jiffies;		unsigned long resend_at = now + call->peer->rto_j; 		WRITE_ONCE(call->resend_at, resend_at);		rxrpc_reduce_call_timer(call, resend_at, now,					rxrpc_timer_set_for_send);	} out:	rxrpc_free_skb(skb, rxrpc_skb_freed);	_leave(" = %d", ret);	return ret;} /* * send data through a socket * - must be called in process context * - The caller holds the call user access mutex, but not the socket lock. */static int rxrpc_send_data(struct rxrpc_sock *rx,			   struct rxrpc_call *call,			   struct msghdr *msg, size_t len,			   rxrpc_notify_end_tx_t notify_end_tx){	struct rxrpc_skb_priv *sp;	struct sk_buff *skb;	struct sock *sk = &rx->sk;	long timeo;	bool more;	int ret, copied; 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); 	/* this should be in poll */	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); 	if (sk->sk_shutdown & SEND_SHUTDOWN)		return -EPIPE; 	more = msg->msg_flags & MSG_MORE; 	if (call->tx_total_len != -1) {		if (len > call->tx_total_len)			return -EMSGSIZE;		if (!more && len != call->tx_total_len)			return -EMSGSIZE;	} 	skb = call->tx_pending;	call->tx_pending = NULL;	rxrpc_see_skb(skb, rxrpc_skb_seen); 	copied = 0;	do {		/* Check to see if there's a ping ACK to reply to. */		if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE)			rxrpc_send_ack_packet(call, false, NULL); 		if (!skb) {			size_t remain, bufsize, chunk, offset; 			_debug("alloc"); 			if (!rxrpc_check_tx_space(call, NULL)) {				ret = -EAGAIN;				if (msg->msg_flags & MSG_DONTWAIT)					goto maybe_error;				ret = rxrpc_wait_for_tx_window(rx, call,							       &timeo,							       msg->msg_flags & MSG_WAITALL);				if (ret < 0)					goto maybe_error;			} 			/* Work out the maximum size of a packet.  Assume that			 * the security header is going to be in the padded			 * region (enc blocksize), but the trailer is not.			 */			remain = more ? INT_MAX : msg_data_left(msg);			ret = call->conn->security->how_much_data(call, remain,								  &bufsize, &chunk, &offset);			if (ret < 0)				goto maybe_error; 			_debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); 			/* create a buffer that we can retain until it's ACK'd */			skb = sock_alloc_send_skb(				sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret);			if (!skb)				goto maybe_error; 			sp = rxrpc_skb(skb);			sp->rx_flags |= RXRPC_SKB_TX_BUFFER;			rxrpc_new_skb(skb, rxrpc_skb_new); 			_debug("ALLOC SEND %p", skb); 			ASSERTCMP(skb->mark, ==, 0); 			__skb_put(skb, offset); 			sp->remain = chunk;			if (sp->remain > skb_tailroom(skb))				sp->remain = skb_tailroom(skb); 			_net("skb: hr %d, tr %d, hl %d, rm %d",			       skb_headroom(skb),			       skb_tailroom(skb),			       skb_headlen(skb),			       sp->remain); 			skb->ip_summed = CHECKSUM_UNNECESSARY;		} 		_debug("append");		sp = rxrpc_skb(skb); 		/* append next segment of data to the current buffer */		if (msg_data_left(msg) > 0) {			int copy = skb_tailroom(skb);			ASSERTCMP(copy, >, 0);			if (copy > msg_data_left(msg))				copy = msg_data_left(msg);			if (copy > sp->remain)				copy = sp->remain; 			_debug("add");			ret = skb_add_data(skb, &msg->msg_iter, copy);			_debug("added");			if (ret < 0)				goto efault;			sp->remain -= copy;			skb->mark += copy;			copied += copy;			if (call->tx_total_len != -1)				call->tx_total_len -= copy;		} 		/* check for the far side aborting the call or a network error		 * occurring */		if (call->state == RXRPC_CALL_COMPLETE)			goto call_terminated; 		/* add the packet to the send queue if it's now full */		if (sp->remain <= 0 ||		    (msg_data_left(msg) == 0 && !more)) {			struct rxrpc_connection *conn = call->conn;			uint32_t seq; 			seq = call->tx_top + 1; 			sp->hdr.seq	= seq;			sp->hdr._rsvd	= 0;			sp->hdr.flags	= conn->out_clientflag; 			if (msg_data_left(msg) == 0 && !more)				sp->hdr.flags |= RXRPC_LAST_PACKET;			else if (call->tx_top - call->tx_hard_ack <				 call->tx_winsize)				sp->hdr.flags |= RXRPC_MORE_PACKETS; 			ret = call->security->secure_packet(call, skb, skb->mark);			if (ret < 0)				goto out; 			ret = rxrpc_queue_packet(rx, call, skb,						 !msg_data_left(msg) && !more,						 notify_end_tx);			/* Should check for failure here */			skb = NULL;		}	} while (msg_data_left(msg) > 0); success:	ret = copied;out:	call->tx_pending = skb;	_leave(" = %d", ret);	return ret; call_terminated:	rxrpc_free_skb(skb, rxrpc_skb_freed);	_leave(" = %d", call->error);	return call->error; maybe_error:	if (copied)		goto success;	goto out; efault:	ret = -EFAULT;	goto out;} /* * extract control messages from the sendmsg() control buffer */static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p){	struct cmsghdr *cmsg;	bool got_user_ID = false;	int len; 	if (msg->msg_controllen == 0)		return -EINVAL; 	for_each_cmsghdr(cmsg, msg) {		if (!CMSG_OK(msg, cmsg))			return -EINVAL; 		len = cmsg->cmsg_len - sizeof(struct cmsghdr);		_debug("CMSG %d, %d, %d",		       cmsg->cmsg_level, cmsg->cmsg_type, len); 		if (cmsg->cmsg_level != SOL_RXRPC)			continue; 		switch (cmsg->cmsg_type) {		case RXRPC_USER_CALL_ID:			if (msg->msg_flags & MSG_CMSG_COMPAT) {				if (len != sizeof(u32))					return -EINVAL;				p->call.user_call_ID = *(u32 *)CMSG_DATA(cmsg);			} else {				if (len != sizeof(unsigned long))					return -EINVAL;				p->call.user_call_ID = *(unsigned long *)					CMSG_DATA(cmsg);

Lines 1–500 of 860.