linux/net/rxrpc/sendmsg.c
David Howells 019ed251b5 rxrpc: Return an error to sendmsg if call failed
[ Upstream commit 4ba68c5192554876bd8c3afd904e3064d2915341 ]

If at the end of rxrpc sendmsg() or rxrpc_kernel_send_data() the call that
was being given data was aborted remotely or otherwise failed, return an
error rather than returning the amount of data buffered for transmission.

The call (presumably) did not complete, so there's not much point
continuing with it.  AF_RXRPC considers it "complete" and so will be
unwilling to do anything else with it - and won't send a notification for
it, deeming the return from sendmsg sufficient.

Not returning an error causes afs to incorrectly handle a StoreData
operation that gets interrupted by a change of address due to NAT
reconfiguration.

This doesn't normally affect most operations since their request parameters
tend to fit into a single UDP packet and afs_make_call() returns before the
server responds; StoreData is different as it involves transmission of a
lot of data.

This can be triggered on a client by doing something like:

	dd if=/dev/zero of=/afs/example.com/foo bs=1M count=512

at one prompt, and then changing the network address at another prompt,
e.g.:

	ifconfig enp6s0 inet 192.168.6.2 && route add 192.168.6.1 dev enp6s0

Tracing packets on an Auristor fileserver looks something like:

192.168.6.1 -> 192.168.6.3  RX 107 ACK Idle  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.3 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(64538) (64538)
192.168.6.3 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(64538) (64538)
192.168.6.1 -> 192.168.6.3  RX 107 ACK Idle  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
<ARP exchange for 192.168.6.2>
192.168.6.2 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(0) (0)
192.168.6.2 -> 192.168.6.1  AFS (RX) 1482 FS Request: Unknown(0) (0)
192.168.6.1 -> 192.168.6.2  RX 107 ACK Exceeds Window  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.1 -> 192.168.6.2  RX 74 ABORT  Seq: 0  Call: 4  Source Port: 7000  Destination Port: 7001
192.168.6.1 -> 192.168.6.2  RX 74 ABORT  Seq: 29321  Call: 4  Source Port: 7000  Destination Port: 7001

The Auristor fileserver logs code -453 (RXGEN_SS_UNMARSHAL), but the abort
code received by kafs is -5 (RX_PROTOCOL_ERROR) as the rx layer sees the
condition and generates an abort first and the unmarshal error is a
consequence of that at the application layer.

Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-afs@lists.infradead.org
Link: http://lists.infradead.org/pipermail/linux-afs/2021-December/004810.html # v1
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2022-06-14 16:52:30 +02:00

619 lines
15 KiB
C

/* AF_RXRPC sendmsg() implementation.
*
* Copyright (C) 2007, 2016 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/net.h>
#include <linux/gfp.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
enum rxrpc_command {
RXRPC_CMD_SEND_DATA, /* send data message */
RXRPC_CMD_SEND_ABORT, /* request abort generation */
RXRPC_CMD_ACCEPT, /* [server] accept incoming call */
RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */
};
/*
* 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)
{
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);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
ret = 0;
if (call->tx_top - call->tx_hard_ack <
min_t(unsigned int, call->tx_winsize,
call->cong_cwnd + call->cong_extra))
break;
if (call->state >= RXRPC_CALL_COMPLETE) {
ret = -call->error;
break;
}
if (signal_pending(current)) {
ret = sock_intr_errno(*timeo);
break;
}
trace_rxrpc_transmit(call, rxrpc_transmit_wait);
release_sock(&rx->sk);
*timeo = schedule_timeout(*timeo);
lock_sock(&rx->sk);
}
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);
}
/*
* Queue a DATA packet for transmission, set the resend timeout and send the
* packet immediately
*/
static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
bool last)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
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_tx_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;
break;
case RXRPC_CALL_SERVER_ACK_REQUEST:
call->state = RXRPC_CALL_SERVER_SEND_REPLY;
call->ack_at = call->expire_at;
if (call->ackr_reason == RXRPC_ACK_DELAY)
call->ackr_reason = 0;
__rxrpc_set_timer(call, rxrpc_timer_init_for_send_reply,
ktime_get_real());
if (!last)
break;
case RXRPC_CALL_SERVER_SEND_REPLY:
call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
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) {
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
ktime_t now = ktime_get_real(), resend_at;
resend_at = ktime_add_ms(now, rxrpc_resend_timeout);
if (ktime_before(resend_at, call->resend_at)) {
call->resend_at = resend_at;
rxrpc_set_timer(call, rxrpc_timer_set_for_send, now);
}
}
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
_leave("");
}
/*
* send data through a socket
* - must be called in process context
* - caller holds the socket locked
*/
static int rxrpc_send_data(struct rxrpc_sock *rx,
struct rxrpc_call *call,
struct msghdr *msg, size_t len)
{
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;
skb = call->tx_pending;
call->tx_pending = NULL;
rxrpc_see_skb(skb, rxrpc_skb_tx_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);
if (!skb) {
size_t size, chunk, max, space;
_debug("alloc");
if (call->tx_top - call->tx_hard_ack >=
min_t(unsigned int, call->tx_winsize,
call->cong_cwnd + call->cong_extra)) {
ret = -EAGAIN;
if (msg->msg_flags & MSG_DONTWAIT)
goto maybe_error;
ret = rxrpc_wait_for_tx_window(rx, call,
&timeo);
if (ret < 0)
goto maybe_error;
}
max = RXRPC_JUMBO_DATALEN;
max -= call->conn->security_size;
max &= ~(call->conn->size_align - 1UL);
chunk = max;
if (chunk > msg_data_left(msg) && !more)
chunk = msg_data_left(msg);
space = chunk + call->conn->size_align;
space &= ~(call->conn->size_align - 1UL);
size = space + call->conn->security_size;
_debug("SIZE: %zu/%zu/%zu", chunk, space, size);
/* create a buffer that we can retain until it's ACK'd */
skb = sock_alloc_send_skb(
sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
if (!skb)
goto maybe_error;
rxrpc_new_skb(skb, rxrpc_skb_tx_new);
_debug("ALLOC SEND %p", skb);
ASSERTCMP(skb->mark, ==, 0);
_debug("HS: %u", call->conn->security_size);
skb_reserve(skb, call->conn->security_size);
skb->len += call->conn->security_size;
sp = rxrpc_skb(skb);
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;
}
/* 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;
size_t pad;
/* pad out if we're using security */
if (conn->security_ix) {
pad = conn->security_size + skb->mark;
pad = conn->size_align - pad;
pad &= conn->size_align - 1;
_debug("pad %zu", pad);
if (pad)
memset(skb_put(skb, pad), 0, pad);
}
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 = conn->security->secure_packet(
call, skb, skb->mark, skb->head);
if (ret < 0)
goto out;
rxrpc_queue_packet(call, skb, !msg_data_left(msg) && !more);
skb = NULL;
}
} while (msg_data_left(msg) > 0);
success:
ret = copied;
if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) {
read_lock_bh(&call->state_lock);
if (call->error < 0)
ret = call->error;
read_unlock_bh(&call->state_lock);
}
out:
call->tx_pending = skb;
_leave(" = %d", ret);
return ret;
call_terminated:
rxrpc_free_skb(skb, rxrpc_skb_tx_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,
unsigned long *user_call_ID,
enum rxrpc_command *command,
u32 *abort_code,
bool *_exclusive)
{
struct cmsghdr *cmsg;
bool got_user_ID = false;
int len;
*command = RXRPC_CMD_SEND_DATA;
if (msg->msg_controllen == 0)
return -EINVAL;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
len = cmsg->cmsg_len - CMSG_ALIGN(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;
*user_call_ID = *(u32 *) CMSG_DATA(cmsg);
} else {
if (len != sizeof(unsigned long))
return -EINVAL;
*user_call_ID = *(unsigned long *)
CMSG_DATA(cmsg);
}
_debug("User Call ID %lx", *user_call_ID);
got_user_ID = true;
break;
case RXRPC_ABORT:
if (*command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
*command = RXRPC_CMD_SEND_ABORT;
if (len != sizeof(*abort_code))
return -EINVAL;
*abort_code = *(unsigned int *) CMSG_DATA(cmsg);
_debug("Abort %x", *abort_code);
if (*abort_code == 0)
return -EINVAL;
break;
case RXRPC_ACCEPT:
if (*command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
*command = RXRPC_CMD_ACCEPT;
if (len != 0)
return -EINVAL;
break;
case RXRPC_EXCLUSIVE_CALL:
*_exclusive = true;
if (len != 0)
return -EINVAL;
break;
default:
return -EINVAL;
}
}
if (!got_user_ID)
return -EINVAL;
_leave(" = 0");
return 0;
}
/*
* Create a new client call for sendmsg().
*/
static struct rxrpc_call *
rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
unsigned long user_call_ID, bool exclusive)
{
struct rxrpc_conn_parameters cp;
struct rxrpc_call *call;
struct key *key;
DECLARE_SOCKADDR(struct sockaddr_rxrpc *, srx, msg->msg_name);
_enter("");
if (!msg->msg_name)
return ERR_PTR(-EDESTADDRREQ);
key = rx->key;
if (key && !rx->key->payload.data[0])
key = NULL;
memset(&cp, 0, sizeof(cp));
cp.local = rx->local;
cp.key = rx->key;
cp.security_level = rx->min_sec_level;
cp.exclusive = rx->exclusive | exclusive;
cp.service_id = srx->srx_service;
call = rxrpc_new_client_call(rx, &cp, srx, user_call_ID, GFP_KERNEL);
_leave(" = %p\n", call);
return call;
}
/*
* send a message forming part of a client call through an RxRPC socket
* - caller holds the socket locked
* - the socket may be either a client socket or a server socket
*/
int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len)
{
enum rxrpc_command cmd;
struct rxrpc_call *call;
unsigned long user_call_ID = 0;
bool exclusive = false;
u32 abort_code = 0;
int ret;
_enter("");
ret = rxrpc_sendmsg_cmsg(msg, &user_call_ID, &cmd, &abort_code,
&exclusive);
if (ret < 0)
return ret;
if (cmd == RXRPC_CMD_ACCEPT) {
if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
return -EINVAL;
call = rxrpc_accept_call(rx, user_call_ID, NULL);
if (IS_ERR(call))
return PTR_ERR(call);
rxrpc_put_call(call, rxrpc_call_put);
return 0;
}
call = rxrpc_find_call_by_user_ID(rx, user_call_ID);
if (!call) {
if (cmd != RXRPC_CMD_SEND_DATA)
return -EBADSLT;
call = rxrpc_new_client_call_for_sendmsg(rx, msg, user_call_ID,
exclusive);
if (IS_ERR(call))
return PTR_ERR(call);
}
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
if (call->state >= RXRPC_CALL_COMPLETE) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (cmd == RXRPC_CMD_SEND_ABORT) {
ret = 0;
if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED))
ret = rxrpc_send_abort_packet(call);
} else if (cmd != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else if (rxrpc_is_client_call(call) &&
call->state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
/* request phase complete for this client call */
ret = -EPROTO;
} else if (rxrpc_is_service_call(call) &&
call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
/* Reply phase not begun or not complete for service call. */
ret = -EPROTO;
} else {
ret = rxrpc_send_data(rx, call, msg, len);
}
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %d", ret);
return ret;
}
/**
* rxrpc_kernel_send_data - Allow a kernel service to send data on a call
* @sock: The socket the call is on
* @call: The call to send data through
* @msg: The data to send
* @len: The amount of data to send
*
* Allow a kernel service to send data on a call. The call must be in an state
* appropriate to sending data. No control data should be supplied in @msg,
* nor should an address be supplied. MSG_MORE should be flagged if there's
* more data to come, otherwise this data will end the transmission phase.
*/
int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, size_t len)
{
int ret;
_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
ASSERTCMP(msg->msg_name, ==, NULL);
ASSERTCMP(msg->msg_control, ==, NULL);
lock_sock(sock->sk);
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
if (call->state >= RXRPC_CALL_COMPLETE) {
ret = -ESHUTDOWN; /* it's too late for this call */
} else if (call->state != RXRPC_CALL_CLIENT_SEND_REQUEST &&
call->state != RXRPC_CALL_SERVER_ACK_REQUEST &&
call->state != RXRPC_CALL_SERVER_SEND_REPLY) {
ret = -EPROTO; /* request phase complete for this client call */
} else {
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len);
}
release_sock(sock->sk);
_leave(" = %d", ret);
return ret;
}
EXPORT_SYMBOL(rxrpc_kernel_send_data);
/**
* rxrpc_kernel_abort_call - Allow a kernel service to abort a call
* @sock: The socket the call is on
* @call: The call to be aborted
* @abort_code: The abort code to stick into the ABORT packet
* @error: Local error value
* @why: 3-char string indicating why.
*
* Allow a kernel service to abort a call, if it's still in an abortable state.
*/
void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
u32 abort_code, int error, const char *why)
{
_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
lock_sock(sock->sk);
if (rxrpc_abort_call(why, call, 0, abort_code, error))
rxrpc_send_abort_packet(call);
release_sock(sock->sk);
_leave("");
}
EXPORT_SYMBOL(rxrpc_kernel_abort_call);