mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 20:27:23 +07:00
c1e15b4944
The rxrpc_input_packet() function and its call tree was built around the
assumption that data_ready() handler called from UDP to inform a kernel
service that there is data to be had was non-reentrant. This means that
certain locking could be dispensed with.
This, however, turns out not to be the case with a multi-queue network card
that can deliver packets to multiple cpus simultaneously. Each of those
cpus can be in the rxrpc_input_packet() function at the same time.
Fix by adding or changing some structure members:
(1) Add peer->rtt_input_lock to serialise access to the RTT buffer.
(2) Make conn->service_id into a 32-bit variable so that it can be
cmpxchg'd on all arches.
(3) Add call->input_lock to serialise access to the Rx/Tx state. Note
that although the Rx and Tx states are (almost) entirely separate,
there's no point completing the separation and having separate locks
since it's a bi-phasal RPC protocol rather than a bi-direction
streaming protocol. Data transmission and data reception do not take
place simultaneously on any particular call.
and making the following functional changes:
(1) In rxrpc_input_data(), hold call->input_lock around the core to
prevent simultaneous producing of packets into the Rx ring and
updating of tracking state for a particular call.
(2) In rxrpc_input_ping_response(), only read call->ping_serial once, and
check it before checking RXRPC_CALL_PINGING as that's a cheaper test.
The bit test and bit clear can then be combined. No further locking
is needed here.
(3) In rxrpc_input_ack(), take call->input_lock after we've parsed much of
the ACK packet. The superseded ACK check is then done both before and
after the lock is taken.
The handing of ackinfo data is split, parsing before the lock is taken
and processing with it held. This is keyed on rxMTU being non-zero.
Congestion management is also done within the locked section.
(4) In rxrpc_input_ackall(), take call->input_lock around the Tx window
rotation. The ACKALL packet carries no information and is only really
useful after all packets have been transmitted since it's imprecise.
(5) In rxrpc_input_implicit_end_call(), we use rx->incoming_lock to
prevent calls being simultaneously implicitly ended on two cpus and
also to prevent any races with incoming call setup.
(6) In rxrpc_input_packet(), use cmpxchg() to effect the service upgrade
on a connection. It is only permitted to happen once for a
connection.
(7) In rxrpc_new_incoming_call(), we have to recheck the routing inside
rx->incoming_lock to see if someone else set up the call, connection
or peer whilst we were getting there. We can't trust the values from
the earlier routing check unless we pin refs on them - which we want
to avoid.
Further, we need to allow for an incoming call to have its state
changed on another CPU between us making it live and us adjusting it
because the conn is now in the RXRPC_CONN_SERVICE state.
(8) In rxrpc_peer_add_rtt(), take peer->rtt_input_lock around the access
to the RTT buffer. Don't need to lock around setting peer->rtt.
For reference, the inventory of state-accessing or state-altering functions
used by the packet input procedure is:
> rxrpc_input_packet()
* PACKET CHECKING
* ROUTING
> rxrpc_post_packet_to_local()
> rxrpc_find_connection_rcu() - uses RCU
> rxrpc_lookup_peer_rcu() - uses RCU
> rxrpc_find_service_conn_rcu() - uses RCU
> idr_find() - uses RCU
* CONNECTION-LEVEL PROCESSING
- Service upgrade
- Can only happen once per conn
! Changed to use cmpxchg
> rxrpc_post_packet_to_conn()
- Setting conn->hi_serial
- Probably safe not using locks
- Maybe use cmpxchg
* CALL-LEVEL PROCESSING
> Old-call checking
> rxrpc_input_implicit_end_call()
> rxrpc_call_completed()
> rxrpc_queue_call()
! Need to take rx->incoming_lock
> __rxrpc_disconnect_call()
> rxrpc_notify_socket()
> rxrpc_new_incoming_call()
- Uses rx->incoming_lock for the entire process
- Might be able to drop this earlier in favour of the call lock
> rxrpc_incoming_call()
! Conflicts with rxrpc_input_implicit_end_call()
> rxrpc_send_ping()
- Don't need locks to check rtt state
> rxrpc_propose_ACK
* PACKET DISTRIBUTION
> rxrpc_input_call_packet()
> rxrpc_input_data()
* QUEUE DATA PACKET ON CALL
> rxrpc_reduce_call_timer()
- Uses timer_reduce()
! Needs call->input_lock()
> rxrpc_receiving_reply()
! Needs locking around ack state
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_proto_abort()
> rxrpc_input_dup_data()
- Fills the Rx buffer
- rxrpc_propose_ACK()
- rxrpc_notify_socket()
> rxrpc_input_ack()
* APPLY ACK PACKET TO CALL AND DISCARD PACKET
> rxrpc_input_ping_response()
- Probably doesn't need any extra locking
! Need READ_ONCE() on call->ping_serial
> rxrpc_input_check_for_lost_ack()
- Takes call->lock to consult Tx buffer
> rxrpc_peer_add_rtt()
! Needs to take a lock (peer->rtt_input_lock)
! Could perhaps manage with cmpxchg() and xadd() instead
> rxrpc_input_requested_ack
- Consults Tx buffer
! Probably needs a lock
> rxrpc_peer_add_rtt()
> rxrpc_propose_ack()
> rxrpc_input_ackinfo()
- Changes call->tx_winsize
! Use cmpxchg to handle change
! Should perhaps track serial number
- Uses peer->lock to record MTU specification changes
> rxrpc_proto_abort()
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_input_soft_acks()
- Consults the Tx buffer
> rxrpc_congestion_management()
- Modifies the Tx annotations
! Needs call->input_lock()
> rxrpc_queue_call()
> rxrpc_input_abort()
* APPLY ABORT PACKET TO CALL AND DISCARD PACKET
> rxrpc_set_call_completion()
> rxrpc_notify_socket()
> rxrpc_input_ackall()
* APPLY ACKALL PACKET TO CALL AND DISCARD PACKET
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_reject_packet()
There are some functions used by the above that queue the packet, after
which the procedure is terminated:
- rxrpc_post_packet_to_local()
- local->event_queue is an sk_buff_head
- local->processor is a work_struct
- rxrpc_post_packet_to_conn()
- conn->rx_queue is an sk_buff_head
- conn->processor is a work_struct
- rxrpc_reject_packet()
- local->reject_queue is an sk_buff_head
- local->processor is a work_struct
And some that offload processing to process context:
- rxrpc_notify_socket()
- Uses RCU lock
- Uses call->notify_lock to call call->notify_rx
- Uses call->recvmsg_lock to queue recvmsg side
- rxrpc_queue_call()
- call->processor is a work_struct
- rxrpc_propose_ACK()
- Uses call->lock to wrap __rxrpc_propose_ACK()
And a bunch that complete a call, all of which use call->state_lock to
protect the call state:
- rxrpc_call_completed()
- rxrpc_set_call_completion()
- rxrpc_abort_call()
- rxrpc_proto_abort()
- Also uses rxrpc_queue_call()
Fixes: 17926a7932
("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
731 lines
19 KiB
C
731 lines
19 KiB
C
/* RxRPC individual remote procedure call handling
|
|
*
|
|
* Copyright (C) 2007 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 License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/slab.h>
|
|
#include <linux/module.h>
|
|
#include <linux/circ_buf.h>
|
|
#include <linux/spinlock_types.h>
|
|
#include <net/sock.h>
|
|
#include <net/af_rxrpc.h>
|
|
#include "ar-internal.h"
|
|
|
|
const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = {
|
|
[RXRPC_CALL_UNINITIALISED] = "Uninit ",
|
|
[RXRPC_CALL_CLIENT_AWAIT_CONN] = "ClWtConn",
|
|
[RXRPC_CALL_CLIENT_SEND_REQUEST] = "ClSndReq",
|
|
[RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl",
|
|
[RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl",
|
|
[RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc",
|
|
[RXRPC_CALL_SERVER_SECURING] = "SvSecure",
|
|
[RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept",
|
|
[RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq",
|
|
[RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq",
|
|
[RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl",
|
|
[RXRPC_CALL_SERVER_AWAIT_ACK] = "SvAwtACK",
|
|
[RXRPC_CALL_COMPLETE] = "Complete",
|
|
};
|
|
|
|
const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = {
|
|
[RXRPC_CALL_SUCCEEDED] = "Complete",
|
|
[RXRPC_CALL_REMOTELY_ABORTED] = "RmtAbort",
|
|
[RXRPC_CALL_LOCALLY_ABORTED] = "LocAbort",
|
|
[RXRPC_CALL_LOCAL_ERROR] = "LocError",
|
|
[RXRPC_CALL_NETWORK_ERROR] = "NetError",
|
|
};
|
|
|
|
struct kmem_cache *rxrpc_call_jar;
|
|
|
|
static void rxrpc_call_timer_expired(struct timer_list *t)
|
|
{
|
|
struct rxrpc_call *call = from_timer(call, t, timer);
|
|
|
|
_enter("%d", call->debug_id);
|
|
|
|
if (call->state < RXRPC_CALL_COMPLETE) {
|
|
trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies);
|
|
rxrpc_queue_call(call);
|
|
}
|
|
}
|
|
|
|
static struct lock_class_key rxrpc_call_user_mutex_lock_class_key;
|
|
|
|
/*
|
|
* find an extant server call
|
|
* - called in process context with IRQs enabled
|
|
*/
|
|
struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx,
|
|
unsigned long user_call_ID)
|
|
{
|
|
struct rxrpc_call *call;
|
|
struct rb_node *p;
|
|
|
|
_enter("%p,%lx", rx, user_call_ID);
|
|
|
|
read_lock(&rx->call_lock);
|
|
|
|
p = rx->calls.rb_node;
|
|
while (p) {
|
|
call = rb_entry(p, struct rxrpc_call, sock_node);
|
|
|
|
if (user_call_ID < call->user_call_ID)
|
|
p = p->rb_left;
|
|
else if (user_call_ID > call->user_call_ID)
|
|
p = p->rb_right;
|
|
else
|
|
goto found_extant_call;
|
|
}
|
|
|
|
read_unlock(&rx->call_lock);
|
|
_leave(" = NULL");
|
|
return NULL;
|
|
|
|
found_extant_call:
|
|
rxrpc_get_call(call, rxrpc_call_got);
|
|
read_unlock(&rx->call_lock);
|
|
_leave(" = %p [%d]", call, atomic_read(&call->usage));
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* allocate a new call
|
|
*/
|
|
struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
|
|
unsigned int debug_id)
|
|
{
|
|
struct rxrpc_call *call;
|
|
struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
|
|
|
|
call = kmem_cache_zalloc(rxrpc_call_jar, gfp);
|
|
if (!call)
|
|
return NULL;
|
|
|
|
call->rxtx_buffer = kcalloc(RXRPC_RXTX_BUFF_SIZE,
|
|
sizeof(struct sk_buff *),
|
|
gfp);
|
|
if (!call->rxtx_buffer)
|
|
goto nomem;
|
|
|
|
call->rxtx_annotations = kcalloc(RXRPC_RXTX_BUFF_SIZE, sizeof(u8), gfp);
|
|
if (!call->rxtx_annotations)
|
|
goto nomem_2;
|
|
|
|
mutex_init(&call->user_mutex);
|
|
|
|
/* Prevent lockdep reporting a deadlock false positive between the afs
|
|
* filesystem and sys_sendmsg() via the mmap sem.
|
|
*/
|
|
if (rx->sk.sk_kern_sock)
|
|
lockdep_set_class(&call->user_mutex,
|
|
&rxrpc_call_user_mutex_lock_class_key);
|
|
|
|
timer_setup(&call->timer, rxrpc_call_timer_expired, 0);
|
|
INIT_WORK(&call->processor, &rxrpc_process_call);
|
|
INIT_LIST_HEAD(&call->link);
|
|
INIT_LIST_HEAD(&call->chan_wait_link);
|
|
INIT_LIST_HEAD(&call->accept_link);
|
|
INIT_LIST_HEAD(&call->recvmsg_link);
|
|
INIT_LIST_HEAD(&call->sock_link);
|
|
init_waitqueue_head(&call->waitq);
|
|
spin_lock_init(&call->lock);
|
|
spin_lock_init(&call->notify_lock);
|
|
spin_lock_init(&call->input_lock);
|
|
rwlock_init(&call->state_lock);
|
|
atomic_set(&call->usage, 1);
|
|
call->debug_id = debug_id;
|
|
call->tx_total_len = -1;
|
|
call->next_rx_timo = 20 * HZ;
|
|
call->next_req_timo = 1 * HZ;
|
|
|
|
memset(&call->sock_node, 0xed, sizeof(call->sock_node));
|
|
|
|
/* Leave space in the ring to handle a maxed-out jumbo packet */
|
|
call->rx_winsize = rxrpc_rx_window_size;
|
|
call->tx_winsize = 16;
|
|
call->rx_expect_next = 1;
|
|
|
|
call->cong_cwnd = 2;
|
|
call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1;
|
|
|
|
call->rxnet = rxnet;
|
|
atomic_inc(&rxnet->nr_calls);
|
|
return call;
|
|
|
|
nomem_2:
|
|
kfree(call->rxtx_buffer);
|
|
nomem:
|
|
kmem_cache_free(rxrpc_call_jar, call);
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* Allocate a new client call.
|
|
*/
|
|
static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
|
|
struct sockaddr_rxrpc *srx,
|
|
gfp_t gfp,
|
|
unsigned int debug_id)
|
|
{
|
|
struct rxrpc_call *call;
|
|
ktime_t now;
|
|
|
|
_enter("");
|
|
|
|
call = rxrpc_alloc_call(rx, gfp, debug_id);
|
|
if (!call)
|
|
return ERR_PTR(-ENOMEM);
|
|
call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
|
|
call->service_id = srx->srx_service;
|
|
call->tx_phase = true;
|
|
now = ktime_get_real();
|
|
call->acks_latest_ts = now;
|
|
call->cong_tstamp = now;
|
|
|
|
_leave(" = %p", call);
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* Initiate the call ack/resend/expiry timer.
|
|
*/
|
|
static void rxrpc_start_call_timer(struct rxrpc_call *call)
|
|
{
|
|
unsigned long now = jiffies;
|
|
unsigned long j = now + MAX_JIFFY_OFFSET;
|
|
|
|
call->ack_at = j;
|
|
call->ack_lost_at = j;
|
|
call->resend_at = j;
|
|
call->ping_at = j;
|
|
call->expect_rx_by = j;
|
|
call->expect_req_by = j;
|
|
call->expect_term_by = j;
|
|
call->timer.expires = now;
|
|
}
|
|
|
|
/*
|
|
* Set up a call for the given parameters.
|
|
* - Called with the socket lock held, which it must release.
|
|
* - If it returns a call, the call's lock will need releasing by the caller.
|
|
*/
|
|
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
|
|
struct rxrpc_conn_parameters *cp,
|
|
struct sockaddr_rxrpc *srx,
|
|
struct rxrpc_call_params *p,
|
|
gfp_t gfp,
|
|
unsigned int debug_id)
|
|
__releases(&rx->sk.sk_lock.slock)
|
|
__acquires(&call->user_mutex)
|
|
{
|
|
struct rxrpc_call *call, *xcall;
|
|
struct rxrpc_net *rxnet;
|
|
struct rb_node *parent, **pp;
|
|
const void *here = __builtin_return_address(0);
|
|
int ret;
|
|
|
|
_enter("%p,%lx", rx, p->user_call_ID);
|
|
|
|
call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
|
|
if (IS_ERR(call)) {
|
|
release_sock(&rx->sk);
|
|
_leave(" = %ld", PTR_ERR(call));
|
|
return call;
|
|
}
|
|
|
|
call->tx_total_len = p->tx_total_len;
|
|
trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage),
|
|
here, (const void *)p->user_call_ID);
|
|
|
|
/* We need to protect a partially set up call against the user as we
|
|
* will be acting outside the socket lock.
|
|
*/
|
|
mutex_lock(&call->user_mutex);
|
|
|
|
/* Publish the call, even though it is incompletely set up as yet */
|
|
write_lock(&rx->call_lock);
|
|
|
|
pp = &rx->calls.rb_node;
|
|
parent = NULL;
|
|
while (*pp) {
|
|
parent = *pp;
|
|
xcall = rb_entry(parent, struct rxrpc_call, sock_node);
|
|
|
|
if (p->user_call_ID < xcall->user_call_ID)
|
|
pp = &(*pp)->rb_left;
|
|
else if (p->user_call_ID > xcall->user_call_ID)
|
|
pp = &(*pp)->rb_right;
|
|
else
|
|
goto error_dup_user_ID;
|
|
}
|
|
|
|
rcu_assign_pointer(call->socket, rx);
|
|
call->user_call_ID = p->user_call_ID;
|
|
__set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
|
|
rxrpc_get_call(call, rxrpc_call_got_userid);
|
|
rb_link_node(&call->sock_node, parent, pp);
|
|
rb_insert_color(&call->sock_node, &rx->calls);
|
|
list_add(&call->sock_link, &rx->sock_calls);
|
|
|
|
write_unlock(&rx->call_lock);
|
|
|
|
rxnet = call->rxnet;
|
|
write_lock(&rxnet->call_lock);
|
|
list_add_tail(&call->link, &rxnet->calls);
|
|
write_unlock(&rxnet->call_lock);
|
|
|
|
/* From this point on, the call is protected by its own lock. */
|
|
release_sock(&rx->sk);
|
|
|
|
/* Set up or get a connection record and set the protocol parameters,
|
|
* including channel number and call ID.
|
|
*/
|
|
ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
|
|
if (ret < 0)
|
|
goto error;
|
|
|
|
trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
|
|
here, NULL);
|
|
|
|
rxrpc_start_call_timer(call);
|
|
|
|
_net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id);
|
|
|
|
_leave(" = %p [new]", call);
|
|
return call;
|
|
|
|
/* We unexpectedly found the user ID in the list after taking
|
|
* the call_lock. This shouldn't happen unless the user races
|
|
* with itself and tries to add the same user ID twice at the
|
|
* same time in different threads.
|
|
*/
|
|
error_dup_user_ID:
|
|
write_unlock(&rx->call_lock);
|
|
release_sock(&rx->sk);
|
|
ret = -EEXIST;
|
|
|
|
error:
|
|
__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
|
|
RX_CALL_DEAD, ret);
|
|
trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
|
|
here, ERR_PTR(ret));
|
|
rxrpc_release_call(rx, call);
|
|
mutex_unlock(&call->user_mutex);
|
|
rxrpc_put_call(call, rxrpc_call_put);
|
|
_leave(" = %d", ret);
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
/*
|
|
* Retry a call to a new address. It is expected that the Tx queue of the call
|
|
* will contain data previously packaged for an old call.
|
|
*/
|
|
int rxrpc_retry_client_call(struct rxrpc_sock *rx,
|
|
struct rxrpc_call *call,
|
|
struct rxrpc_conn_parameters *cp,
|
|
struct sockaddr_rxrpc *srx,
|
|
gfp_t gfp)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
int ret;
|
|
|
|
/* Set up or get a connection record and set the protocol parameters,
|
|
* including channel number and call ID.
|
|
*/
|
|
ret = rxrpc_connect_call(rx, call, cp, srx, gfp);
|
|
if (ret < 0)
|
|
goto error;
|
|
|
|
trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage),
|
|
here, NULL);
|
|
|
|
rxrpc_start_call_timer(call);
|
|
|
|
_net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id);
|
|
|
|
if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
|
|
rxrpc_queue_call(call);
|
|
|
|
_leave(" = 0");
|
|
return 0;
|
|
|
|
error:
|
|
rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
|
|
RX_CALL_DEAD, ret);
|
|
trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
|
|
here, ERR_PTR(ret));
|
|
_leave(" = %d", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Set up an incoming call. call->conn points to the connection.
|
|
* This is called in BH context and isn't allowed to fail.
|
|
*/
|
|
void rxrpc_incoming_call(struct rxrpc_sock *rx,
|
|
struct rxrpc_call *call,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct rxrpc_connection *conn = call->conn;
|
|
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
|
|
u32 chan;
|
|
|
|
_enter(",%d", call->conn->debug_id);
|
|
|
|
rcu_assign_pointer(call->socket, rx);
|
|
call->call_id = sp->hdr.callNumber;
|
|
call->service_id = sp->hdr.serviceId;
|
|
call->cid = sp->hdr.cid;
|
|
call->state = RXRPC_CALL_SERVER_ACCEPTING;
|
|
if (sp->hdr.securityIndex > 0)
|
|
call->state = RXRPC_CALL_SERVER_SECURING;
|
|
call->cong_tstamp = skb->tstamp;
|
|
|
|
/* Set the channel for this call. We don't get channel_lock as we're
|
|
* only defending against the data_ready handler (which we're called
|
|
* from) and the RESPONSE packet parser (which is only really
|
|
* interested in call_counter and can cope with a disagreement with the
|
|
* call pointer).
|
|
*/
|
|
chan = sp->hdr.cid & RXRPC_CHANNELMASK;
|
|
conn->channels[chan].call_counter = call->call_id;
|
|
conn->channels[chan].call_id = call->call_id;
|
|
rcu_assign_pointer(conn->channels[chan].call, call);
|
|
|
|
spin_lock(&conn->params.peer->lock);
|
|
hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets);
|
|
spin_unlock(&conn->params.peer->lock);
|
|
|
|
_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
|
|
|
|
rxrpc_start_call_timer(call);
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* Queue a call's work processor, getting a ref to pass to the work queue.
|
|
*/
|
|
bool rxrpc_queue_call(struct rxrpc_call *call)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
int n = atomic_fetch_add_unless(&call->usage, 1, 0);
|
|
if (n == 0)
|
|
return false;
|
|
if (rxrpc_queue_work(&call->processor))
|
|
trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL);
|
|
else
|
|
rxrpc_put_call(call, rxrpc_call_put_noqueue);
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Queue a call's work processor, passing the callers ref to the work queue.
|
|
*/
|
|
bool __rxrpc_queue_call(struct rxrpc_call *call)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
int n = atomic_read(&call->usage);
|
|
ASSERTCMP(n, >=, 1);
|
|
if (rxrpc_queue_work(&call->processor))
|
|
trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL);
|
|
else
|
|
rxrpc_put_call(call, rxrpc_call_put_noqueue);
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Note the re-emergence of a call.
|
|
*/
|
|
void rxrpc_see_call(struct rxrpc_call *call)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
if (call) {
|
|
int n = atomic_read(&call->usage);
|
|
|
|
trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Note the addition of a ref on a call.
|
|
*/
|
|
void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
int n = atomic_inc_return(&call->usage);
|
|
|
|
trace_rxrpc_call(call, op, n, here, NULL);
|
|
}
|
|
|
|
/*
|
|
* Detach a call from its owning socket.
|
|
*/
|
|
void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
struct rxrpc_connection *conn = call->conn;
|
|
bool put = false;
|
|
int i;
|
|
|
|
_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
|
|
|
|
trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage),
|
|
here, (const void *)call->flags);
|
|
|
|
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
|
|
|
|
spin_lock_bh(&call->lock);
|
|
if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags))
|
|
BUG();
|
|
spin_unlock_bh(&call->lock);
|
|
|
|
del_timer_sync(&call->timer);
|
|
|
|
/* Make sure we don't get any more notifications */
|
|
write_lock_bh(&rx->recvmsg_lock);
|
|
|
|
if (!list_empty(&call->recvmsg_link)) {
|
|
_debug("unlinking once-pending call %p { e=%lx f=%lx }",
|
|
call, call->events, call->flags);
|
|
list_del(&call->recvmsg_link);
|
|
put = true;
|
|
}
|
|
|
|
/* list_empty() must return false in rxrpc_notify_socket() */
|
|
call->recvmsg_link.next = NULL;
|
|
call->recvmsg_link.prev = NULL;
|
|
|
|
write_unlock_bh(&rx->recvmsg_lock);
|
|
if (put)
|
|
rxrpc_put_call(call, rxrpc_call_put);
|
|
|
|
write_lock(&rx->call_lock);
|
|
|
|
if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
|
|
rb_erase(&call->sock_node, &rx->calls);
|
|
memset(&call->sock_node, 0xdd, sizeof(call->sock_node));
|
|
rxrpc_put_call(call, rxrpc_call_put_userid);
|
|
}
|
|
|
|
list_del(&call->sock_link);
|
|
write_unlock(&rx->call_lock);
|
|
|
|
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
|
|
|
|
if (conn)
|
|
rxrpc_disconnect_call(call);
|
|
|
|
for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) {
|
|
rxrpc_free_skb(call->rxtx_buffer[i],
|
|
(call->tx_phase ? rxrpc_skb_tx_cleaned :
|
|
rxrpc_skb_rx_cleaned));
|
|
call->rxtx_buffer[i] = NULL;
|
|
}
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* Prepare a kernel service call for retry.
|
|
*/
|
|
int rxrpc_prepare_call_for_retry(struct rxrpc_sock *rx, struct rxrpc_call *call)
|
|
{
|
|
const void *here = __builtin_return_address(0);
|
|
int i;
|
|
u8 last = 0;
|
|
|
|
_enter("{%d,%d}", call->debug_id, atomic_read(&call->usage));
|
|
|
|
trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage),
|
|
here, (const void *)call->flags);
|
|
|
|
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
|
|
ASSERTCMP(call->completion, !=, RXRPC_CALL_REMOTELY_ABORTED);
|
|
ASSERTCMP(call->completion, !=, RXRPC_CALL_LOCALLY_ABORTED);
|
|
ASSERT(list_empty(&call->recvmsg_link));
|
|
|
|
del_timer_sync(&call->timer);
|
|
|
|
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, call->conn);
|
|
|
|
if (call->conn)
|
|
rxrpc_disconnect_call(call);
|
|
|
|
if (rxrpc_is_service_call(call) ||
|
|
!call->tx_phase ||
|
|
call->tx_hard_ack != 0 ||
|
|
call->rx_hard_ack != 0 ||
|
|
call->rx_top != 0)
|
|
return -EINVAL;
|
|
|
|
call->state = RXRPC_CALL_UNINITIALISED;
|
|
call->completion = RXRPC_CALL_SUCCEEDED;
|
|
call->call_id = 0;
|
|
call->cid = 0;
|
|
call->cong_cwnd = 0;
|
|
call->cong_extra = 0;
|
|
call->cong_ssthresh = 0;
|
|
call->cong_mode = 0;
|
|
call->cong_dup_acks = 0;
|
|
call->cong_cumul_acks = 0;
|
|
call->acks_lowest_nak = 0;
|
|
|
|
for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) {
|
|
last |= call->rxtx_annotations[i];
|
|
call->rxtx_annotations[i] &= RXRPC_TX_ANNO_LAST;
|
|
call->rxtx_annotations[i] |= RXRPC_TX_ANNO_RETRANS;
|
|
}
|
|
|
|
_leave(" = 0");
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* release all the calls associated with a socket
|
|
*/
|
|
void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx)
|
|
{
|
|
struct rxrpc_call *call;
|
|
|
|
_enter("%p", rx);
|
|
|
|
while (!list_empty(&rx->to_be_accepted)) {
|
|
call = list_entry(rx->to_be_accepted.next,
|
|
struct rxrpc_call, accept_link);
|
|
list_del(&call->accept_link);
|
|
rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET);
|
|
rxrpc_put_call(call, rxrpc_call_put);
|
|
}
|
|
|
|
while (!list_empty(&rx->sock_calls)) {
|
|
call = list_entry(rx->sock_calls.next,
|
|
struct rxrpc_call, sock_link);
|
|
rxrpc_get_call(call, rxrpc_call_got);
|
|
rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET);
|
|
rxrpc_send_abort_packet(call);
|
|
rxrpc_release_call(rx, call);
|
|
rxrpc_put_call(call, rxrpc_call_put);
|
|
}
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* release a call
|
|
*/
|
|
void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op)
|
|
{
|
|
struct rxrpc_net *rxnet = call->rxnet;
|
|
const void *here = __builtin_return_address(0);
|
|
int n;
|
|
|
|
ASSERT(call != NULL);
|
|
|
|
n = atomic_dec_return(&call->usage);
|
|
trace_rxrpc_call(call, op, n, here, NULL);
|
|
ASSERTCMP(n, >=, 0);
|
|
if (n == 0) {
|
|
_debug("call %d dead", call->debug_id);
|
|
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
|
|
|
|
if (!list_empty(&call->link)) {
|
|
write_lock(&rxnet->call_lock);
|
|
list_del_init(&call->link);
|
|
write_unlock(&rxnet->call_lock);
|
|
}
|
|
|
|
rxrpc_cleanup_call(call);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Final call destruction under RCU.
|
|
*/
|
|
static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
|
|
{
|
|
struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
|
|
struct rxrpc_net *rxnet = call->rxnet;
|
|
|
|
rxrpc_put_peer(call->peer);
|
|
kfree(call->rxtx_buffer);
|
|
kfree(call->rxtx_annotations);
|
|
kmem_cache_free(rxrpc_call_jar, call);
|
|
if (atomic_dec_and_test(&rxnet->nr_calls))
|
|
wake_up_var(&rxnet->nr_calls);
|
|
}
|
|
|
|
/*
|
|
* clean up a call
|
|
*/
|
|
void rxrpc_cleanup_call(struct rxrpc_call *call)
|
|
{
|
|
int i;
|
|
|
|
_net("DESTROY CALL %d", call->debug_id);
|
|
|
|
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
|
|
|
|
del_timer_sync(&call->timer);
|
|
|
|
ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE);
|
|
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
|
|
ASSERTCMP(call->conn, ==, NULL);
|
|
|
|
/* Clean up the Rx/Tx buffer */
|
|
for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++)
|
|
rxrpc_free_skb(call->rxtx_buffer[i],
|
|
(call->tx_phase ? rxrpc_skb_tx_cleaned :
|
|
rxrpc_skb_rx_cleaned));
|
|
|
|
rxrpc_free_skb(call->tx_pending, rxrpc_skb_tx_cleaned);
|
|
|
|
call_rcu(&call->rcu, rxrpc_rcu_destroy_call);
|
|
}
|
|
|
|
/*
|
|
* Make sure that all calls are gone from a network namespace. To reach this
|
|
* point, any open UDP sockets in that namespace must have been closed, so any
|
|
* outstanding calls cannot be doing I/O.
|
|
*/
|
|
void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
|
|
{
|
|
struct rxrpc_call *call;
|
|
|
|
_enter("");
|
|
|
|
if (list_empty(&rxnet->calls))
|
|
return;
|
|
|
|
write_lock(&rxnet->call_lock);
|
|
|
|
while (!list_empty(&rxnet->calls)) {
|
|
call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
|
|
_debug("Zapping call %p", call);
|
|
|
|
rxrpc_see_call(call);
|
|
list_del_init(&call->link);
|
|
|
|
pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
|
|
call, atomic_read(&call->usage),
|
|
rxrpc_call_states[call->state],
|
|
call->flags, call->events);
|
|
|
|
write_unlock(&rxnet->call_lock);
|
|
cond_resched();
|
|
write_lock(&rxnet->call_lock);
|
|
}
|
|
|
|
write_unlock(&rxnet->call_lock);
|
|
|
|
atomic_dec(&rxnet->nr_calls);
|
|
wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
|
|
}
|