mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-05-26 11:40:24 +02:00
d2bc90cf6c
This improves the fix for CVE-2026-43500.
Fix the pagecache corruption from in-place decryption of a DATA packet
transmitted locally by splice() by getting rid of the packet sharing in the
I/O thread and unconditionally extracting the packet content into a bounce
buffer in which the buffer is decrypted. recvmsg() (or the kernel
equivalent) then copies the data from the bounce buffer to the destination
buffer. The sk_buff then remains unmodified.
This has an additional advantage in that the packet is then arranged in the
buffer with the correct alignment required for the crypto algorithms to
process directly. The performance of the crypto does seem to be a little
faster and, surprisingly, the unencrypted performance doesn't seem to
change much - possibly due to removing complexity from the I/O thread.
Yet another advantage is that the I/O thread doesn't have to copy packets
which would slow down packet distribution, ACK generation, etc..
The buffer belongs to the call and is allocated initially at 2K,
sufficiently large to hold a whole jumbo subpacket, but the buffer will be
increased in size if needed. However, to take this work, MSG_PEEK may
cause a later packet to be decrypted into the buffer, in which case the
earlier one will need re-decrypting for a subsequent recvmsg().
Note that rx_pkt_offset may legitimately see 0 as a valid offset now, so
switch to using USHRT_MAX to indicate an invalid offset.
Note also that I would generally prefer to replace the buffers of the
current sk_buff with a new kmalloc'd buffer of the right size, ditching the
old data and frags as this makes the handling of MSG_PEEK easier and
removes the re-decryption issue, but this looks like quite a complicated
thing to achieve. skb_morph() looks half way to what I want, but I don't
want to have to allocate a new sk_buff.
Fixes: d0d5c0cd1e ("rxrpc: Use skb_unshare() rather than skb_cow_data()")
Reported-by: Hyunwoo Kim <imv4bel@gmail.com>
Closes: https://lore.kernel.org/r/afKV2zGR6rrelPC7@v4bel/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Simon Horman <horms@kernel.org>
cc: Jiayuan Chen <jiayuan.chen@linux.dev>
cc: linux-afs@lists.infradead.org
Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Link: https://patch.msgid.link/20260515230516.2718212-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
776 lines
21 KiB
C
776 lines
21 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/* RxRPC individual remote procedure call handling
|
|
*
|
|
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*/
|
|
|
|
#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_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 DEFINE_SEMAPHORE(rxrpc_call_limiter, 1000);
|
|
static DEFINE_SEMAPHORE(rxrpc_kernel_call_limiter, 1000);
|
|
|
|
void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what)
|
|
{
|
|
struct rxrpc_local *local = call->local;
|
|
bool busy;
|
|
|
|
if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) {
|
|
spin_lock_irq(&local->lock);
|
|
busy = !list_empty(&call->attend_link);
|
|
trace_rxrpc_poke_call(call, busy, what);
|
|
if (!busy && !rxrpc_try_get_call(call, rxrpc_call_get_poke))
|
|
busy = true;
|
|
if (!busy) {
|
|
list_add_tail(&call->attend_link, &local->call_attend_q);
|
|
}
|
|
spin_unlock_irq(&local->lock);
|
|
if (!busy)
|
|
rxrpc_wake_up_io_thread(local);
|
|
}
|
|
}
|
|
|
|
static void rxrpc_call_timer_expired(struct timer_list *t)
|
|
{
|
|
struct rxrpc_call *call = timer_container_of(call, t, timer);
|
|
|
|
_enter("%d", call->debug_id);
|
|
|
|
if (!__rxrpc_call_is_complete(call)) {
|
|
trace_rxrpc_timer_expired(call);
|
|
rxrpc_poke_call(call, rxrpc_call_poke_timer);
|
|
}
|
|
}
|
|
|
|
static struct lock_class_key rxrpc_call_user_mutex_lock_class_key;
|
|
|
|
static void rxrpc_destroy_call(struct work_struct *);
|
|
|
|
/*
|
|
* 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_get_sendmsg);
|
|
read_unlock(&rx->call_lock);
|
|
_leave(" = %p [%d]", call, refcount_read(&call->ref));
|
|
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;
|
|
|
|
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->destroyer, rxrpc_destroy_call);
|
|
INIT_LIST_HEAD(&call->link);
|
|
INIT_LIST_HEAD(&call->wait_link);
|
|
INIT_LIST_HEAD(&call->accept_link);
|
|
INIT_LIST_HEAD(&call->recvmsg_link);
|
|
INIT_LIST_HEAD(&call->sock_link);
|
|
INIT_LIST_HEAD(&call->attend_link);
|
|
skb_queue_head_init(&call->recvmsg_queue);
|
|
skb_queue_head_init(&call->rx_queue);
|
|
skb_queue_head_init(&call->rx_oos_queue);
|
|
init_waitqueue_head(&call->waitq);
|
|
spin_lock_init(&call->notify_lock);
|
|
refcount_set(&call->ref, 1);
|
|
call->debug_id = debug_id;
|
|
call->rx_pkt_offset = USHRT_MAX;
|
|
call->tx_total_len = -1;
|
|
call->tx_jumbo_max = 1;
|
|
call->next_rx_timo = 20 * HZ;
|
|
call->next_req_timo = 1 * HZ;
|
|
call->ackr_window = 1;
|
|
call->ackr_wtop = 1;
|
|
call->delay_ack_at = KTIME_MAX;
|
|
call->rack_timo_at = KTIME_MAX;
|
|
call->ping_at = KTIME_MAX;
|
|
call->keepalive_at = KTIME_MAX;
|
|
call->expect_rx_by = KTIME_MAX;
|
|
call->expect_req_by = KTIME_MAX;
|
|
call->expect_term_by = KTIME_MAX;
|
|
|
|
memset(&call->sock_node, 0xed, sizeof(call->sock_node));
|
|
|
|
call->rx_winsize = rxrpc_rx_window_size;
|
|
call->tx_winsize = 16;
|
|
|
|
call->cong_cwnd = RXRPC_MIN_CWND;
|
|
call->cong_ssthresh = RXRPC_TX_MAX_WINDOW;
|
|
|
|
rxrpc_call_init_rtt(call);
|
|
|
|
call->rxnet = rxnet;
|
|
call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK;
|
|
atomic_inc(&rxnet->nr_calls);
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* Allocate a new client call.
|
|
*/
|
|
static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
|
|
struct rxrpc_conn_parameters *cp,
|
|
struct rxrpc_call_params *p,
|
|
gfp_t gfp,
|
|
unsigned int debug_id)
|
|
{
|
|
struct rxrpc_call *call;
|
|
ktime_t now;
|
|
int ret;
|
|
|
|
_enter("");
|
|
|
|
call = rxrpc_alloc_call(rx, gfp, debug_id);
|
|
if (!call)
|
|
return ERR_PTR(-ENOMEM);
|
|
now = ktime_get_real();
|
|
call->acks_latest_ts = now;
|
|
call->cong_tstamp = now;
|
|
call->dest_srx = cp->peer->srx;
|
|
call->dest_srx.srx_service = cp->service_id;
|
|
call->interruptibility = p->interruptibility;
|
|
call->tx_total_len = p->tx_total_len;
|
|
call->key = key_get(cp->key);
|
|
call->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_call);
|
|
call->local = rxrpc_get_local(cp->local, rxrpc_local_get_call);
|
|
call->security_level = cp->security_level;
|
|
if (p->kernel)
|
|
__set_bit(RXRPC_CALL_KERNEL, &call->flags);
|
|
if (cp->upgrade)
|
|
__set_bit(RXRPC_CALL_UPGRADE, &call->flags);
|
|
if (cp->exclusive)
|
|
__set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags);
|
|
|
|
if (p->timeouts.normal)
|
|
call->next_rx_timo = umin(p->timeouts.normal, 1);
|
|
if (p->timeouts.idle)
|
|
call->next_req_timo = umin(p->timeouts.idle, 1);
|
|
if (p->timeouts.hard)
|
|
call->hard_timo = p->timeouts.hard;
|
|
|
|
ret = rxrpc_init_client_call_security(call);
|
|
if (ret < 0) {
|
|
rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret);
|
|
rxrpc_put_call(call, rxrpc_call_put_discard_error);
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN);
|
|
|
|
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
|
|
p->user_call_ID, rxrpc_call_new_client);
|
|
|
|
_leave(" = %p", call);
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* Initiate the call ack/resend/expiry timer.
|
|
*/
|
|
void rxrpc_start_call_timer(struct rxrpc_call *call)
|
|
{
|
|
if (call->hard_timo) {
|
|
ktime_t delay = ms_to_ktime(call->hard_timo * 1000);
|
|
|
|
call->expect_term_by = ktime_add(ktime_get_real(), delay);
|
|
trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard);
|
|
}
|
|
call->timer.expires = jiffies;
|
|
}
|
|
|
|
/*
|
|
* Wait for a call slot to become available.
|
|
*/
|
|
static struct semaphore *rxrpc_get_call_slot(struct rxrpc_call_params *p, gfp_t gfp)
|
|
{
|
|
struct semaphore *limiter = &rxrpc_call_limiter;
|
|
|
|
if (p->kernel)
|
|
limiter = &rxrpc_kernel_call_limiter;
|
|
if (p->interruptibility == RXRPC_UNINTERRUPTIBLE) {
|
|
down(limiter);
|
|
return limiter;
|
|
}
|
|
return down_interruptible(limiter) < 0 ? NULL : limiter;
|
|
}
|
|
|
|
/*
|
|
* Release a call slot.
|
|
*/
|
|
static void rxrpc_put_call_slot(struct rxrpc_call *call)
|
|
{
|
|
struct semaphore *limiter = &rxrpc_call_limiter;
|
|
|
|
if (test_bit(RXRPC_CALL_KERNEL, &call->flags))
|
|
limiter = &rxrpc_kernel_call_limiter;
|
|
up(limiter);
|
|
}
|
|
|
|
/*
|
|
* Start the process of connecting a call. We obtain a peer and a connection
|
|
* bundle, but the actual association of a call with a connection is offloaded
|
|
* to the I/O thread to simplify locking.
|
|
*/
|
|
static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp)
|
|
{
|
|
struct rxrpc_local *local = call->local;
|
|
int ret = -ENOMEM;
|
|
|
|
_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
|
|
|
|
ret = rxrpc_look_up_bundle(call, gfp);
|
|
if (ret < 0)
|
|
goto error;
|
|
|
|
trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call);
|
|
rxrpc_get_call(call, rxrpc_call_get_io_thread);
|
|
spin_lock_irq(&local->client_call_lock);
|
|
list_add_tail(&call->wait_link, &local->new_client_calls);
|
|
spin_unlock_irq(&local->client_call_lock);
|
|
rxrpc_wake_up_io_thread(local);
|
|
return 0;
|
|
|
|
error:
|
|
__set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* 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 rxrpc_call_params *p,
|
|
gfp_t gfp,
|
|
unsigned int debug_id)
|
|
__releases(&rx->sk.sk_lock)
|
|
__acquires(&call->user_mutex)
|
|
{
|
|
struct rxrpc_call *call, *xcall;
|
|
struct rxrpc_net *rxnet;
|
|
struct semaphore *limiter;
|
|
struct rb_node *parent, **pp;
|
|
int ret;
|
|
|
|
_enter("%p,%lx", rx, p->user_call_ID);
|
|
|
|
if (WARN_ON_ONCE(!cp->peer)) {
|
|
release_sock(&rx->sk);
|
|
return ERR_PTR(-EIO);
|
|
}
|
|
|
|
limiter = rxrpc_get_call_slot(p, gfp);
|
|
if (!limiter) {
|
|
release_sock(&rx->sk);
|
|
return ERR_PTR(-ERESTARTSYS);
|
|
}
|
|
|
|
call = rxrpc_alloc_client_call(rx, cp, p, gfp, debug_id);
|
|
if (IS_ERR(call)) {
|
|
release_sock(&rx->sk);
|
|
up(limiter);
|
|
_leave(" = %ld", PTR_ERR(call));
|
|
return call;
|
|
}
|
|
|
|
/* 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_get_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;
|
|
spin_lock(&rxnet->call_lock);
|
|
list_add_tail_rcu(&call->link, &rxnet->calls);
|
|
spin_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(call, gfp);
|
|
if (ret < 0)
|
|
goto error_attached_to_socket;
|
|
|
|
_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);
|
|
rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST);
|
|
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0,
|
|
rxrpc_call_see_userid_exists);
|
|
mutex_unlock(&call->user_mutex);
|
|
rxrpc_put_call(call, rxrpc_call_put_userid_exists);
|
|
_leave(" = -EEXIST");
|
|
return ERR_PTR(-EEXIST);
|
|
|
|
/* We got an error, but the call is attached to the socket and is in
|
|
* need of release. However, we might now race with recvmsg() when it
|
|
* completion notifies the socket. Return 0 from sys_sendmsg() and
|
|
* leave the error to recvmsg() to deal with.
|
|
*/
|
|
error_attached_to_socket:
|
|
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret,
|
|
rxrpc_call_see_connect_failed);
|
|
rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
|
|
_leave(" = c=%08x [err]", call->debug_id);
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* Set up an incoming call. call->conn points to the connection.
|
|
* This is called with interrupts disabled 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->dest_srx.srx_service = sp->hdr.serviceId;
|
|
call->cid = sp->hdr.cid;
|
|
call->cong_tstamp = skb->tstamp;
|
|
|
|
__set_bit(RXRPC_CALL_EXPOSED, &call->flags);
|
|
rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST);
|
|
|
|
spin_lock(&conn->state_lock);
|
|
|
|
switch (conn->state) {
|
|
case RXRPC_CONN_SERVICE_UNSECURED:
|
|
case RXRPC_CONN_SERVICE_CHALLENGING:
|
|
__set_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags);
|
|
break;
|
|
case RXRPC_CONN_SERVICE:
|
|
break;
|
|
|
|
case RXRPC_CONN_ABORTED:
|
|
rxrpc_set_call_completion(call, conn->completion,
|
|
conn->abort_code, conn->error);
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
|
|
rxrpc_get_call(call, rxrpc_call_get_io_thread);
|
|
|
|
/* 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;
|
|
conn->channels[chan].call = call;
|
|
spin_unlock(&conn->state_lock);
|
|
|
|
spin_lock(&conn->peer->lock);
|
|
hlist_add_head(&call->error_link, &conn->peer->error_targets);
|
|
spin_unlock(&conn->peer->lock);
|
|
|
|
rxrpc_start_call_timer(call);
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* Note the re-emergence of a call.
|
|
*/
|
|
void rxrpc_see_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
|
|
{
|
|
if (call) {
|
|
int r = refcount_read(&call->ref);
|
|
|
|
trace_rxrpc_call(call->debug_id, r, 0, why);
|
|
}
|
|
}
|
|
|
|
struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *call,
|
|
enum rxrpc_call_trace why)
|
|
{
|
|
int r;
|
|
|
|
if (!call || !__refcount_inc_not_zero(&call->ref, &r))
|
|
return NULL;
|
|
trace_rxrpc_call(call->debug_id, r + 1, 0, why);
|
|
return call;
|
|
}
|
|
|
|
/*
|
|
* Note the addition of a ref on a call.
|
|
*/
|
|
void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
|
|
{
|
|
int r;
|
|
|
|
__refcount_inc(&call->ref, &r);
|
|
trace_rxrpc_call(call->debug_id, r + 1, 0, why);
|
|
}
|
|
|
|
/*
|
|
* Clean up the transmission buffers.
|
|
*/
|
|
static void rxrpc_cleanup_tx_buffers(struct rxrpc_call *call)
|
|
{
|
|
struct rxrpc_txqueue *tq, *next;
|
|
|
|
for (tq = call->tx_queue; tq; tq = next) {
|
|
next = tq->next;
|
|
for (int i = 0; i < RXRPC_NR_TXQUEUE; i++)
|
|
if (tq->bufs[i])
|
|
rxrpc_put_txbuf(tq->bufs[i], rxrpc_txbuf_put_cleaned);
|
|
trace_rxrpc_tq(call, tq, 0, rxrpc_tq_cleaned);
|
|
kfree(tq);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Clean up the receive buffers.
|
|
*/
|
|
static void rxrpc_cleanup_rx_buffers(struct rxrpc_call *call)
|
|
{
|
|
rxrpc_purge_queue(&call->recvmsg_queue);
|
|
rxrpc_purge_queue(&call->rx_queue);
|
|
rxrpc_purge_queue(&call->rx_oos_queue);
|
|
kfree(call->rx_dec_buffer);
|
|
}
|
|
|
|
/*
|
|
* Detach a call from its owning socket.
|
|
*/
|
|
void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
|
|
{
|
|
struct rxrpc_connection *conn = call->conn;
|
|
bool putu = false;
|
|
|
|
_enter("{%d,%d}", call->debug_id, refcount_read(&call->ref));
|
|
|
|
trace_rxrpc_call(call->debug_id, refcount_read(&call->ref),
|
|
call->flags, rxrpc_call_see_release);
|
|
|
|
if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags))
|
|
BUG();
|
|
|
|
rxrpc_put_call_slot(call);
|
|
|
|
/* Note that at this point, the call may still be on or may have been
|
|
* added back on to the socket receive queue. recvmsg() must discard
|
|
* released calls. The CALL_RELEASED flag should prevent further
|
|
* notifications.
|
|
*/
|
|
spin_lock_irq(&rx->recvmsg_lock);
|
|
spin_unlock_irq(&rx->recvmsg_lock);
|
|
|
|
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));
|
|
putu = true;
|
|
}
|
|
|
|
list_del(&call->sock_link);
|
|
write_unlock(&rx->call_lock);
|
|
|
|
_debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn);
|
|
|
|
if (putu)
|
|
rxrpc_put_call(call, rxrpc_call_put_userid);
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* 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_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
|
|
rxrpc_abort_call_sock_release_tba);
|
|
rxrpc_put_call(call, rxrpc_call_put_release_sock_tba);
|
|
}
|
|
|
|
while (!list_empty(&rx->sock_calls)) {
|
|
call = list_entry(rx->sock_calls.next,
|
|
struct rxrpc_call, sock_link);
|
|
rxrpc_get_call(call, rxrpc_call_get_release_sock);
|
|
rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET,
|
|
rxrpc_abort_call_sock_release);
|
|
rxrpc_release_call(rx, call);
|
|
rxrpc_put_call(call, rxrpc_call_put_release_sock);
|
|
}
|
|
|
|
while ((call = list_first_entry_or_null(&rx->recvmsg_q,
|
|
struct rxrpc_call, recvmsg_link))) {
|
|
list_del_init(&call->recvmsg_link);
|
|
rxrpc_put_call(call, rxrpc_call_put_release_recvmsg_q);
|
|
}
|
|
|
|
_leave("");
|
|
}
|
|
|
|
/*
|
|
* release a call
|
|
*/
|
|
void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why)
|
|
{
|
|
struct rxrpc_net *rxnet = call->rxnet;
|
|
unsigned int debug_id = call->debug_id;
|
|
bool dead;
|
|
int r;
|
|
|
|
ASSERT(call != NULL);
|
|
|
|
dead = __refcount_dec_and_test(&call->ref, &r);
|
|
trace_rxrpc_call(debug_id, r - 1, 0, why);
|
|
if (dead) {
|
|
ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
|
|
|
|
spin_lock(&rxnet->call_lock);
|
|
list_del_rcu(&call->link);
|
|
spin_unlock(&rxnet->call_lock);
|
|
|
|
rxrpc_cleanup_call(call);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Free up the call under RCU.
|
|
*/
|
|
static void rxrpc_rcu_free_call(struct rcu_head *rcu)
|
|
{
|
|
struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
|
|
struct rxrpc_net *rxnet = READ_ONCE(call->rxnet);
|
|
|
|
kmem_cache_free(rxrpc_call_jar, call);
|
|
if (atomic_dec_and_test(&rxnet->nr_calls))
|
|
wake_up_var(&rxnet->nr_calls);
|
|
}
|
|
|
|
/*
|
|
* Final call destruction - but must be done in process context.
|
|
*/
|
|
static void rxrpc_destroy_call(struct work_struct *work)
|
|
{
|
|
struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer);
|
|
|
|
timer_delete_sync(&call->timer);
|
|
|
|
rxrpc_cleanup_tx_buffers(call);
|
|
rxrpc_cleanup_rx_buffers(call);
|
|
rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned);
|
|
rxrpc_put_connection(call->conn, rxrpc_conn_put_call);
|
|
rxrpc_deactivate_bundle(call->bundle);
|
|
rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call);
|
|
rxrpc_put_peer(call->peer, rxrpc_peer_put_call);
|
|
rxrpc_put_local(call->local, rxrpc_local_put_call);
|
|
key_put(call->key);
|
|
call_rcu(&call->rcu, rxrpc_rcu_free_call);
|
|
}
|
|
|
|
/*
|
|
* clean up a call
|
|
*/
|
|
void rxrpc_cleanup_call(struct rxrpc_call *call)
|
|
{
|
|
memset(&call->sock_node, 0xcd, sizeof(call->sock_node));
|
|
|
|
ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE);
|
|
ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags));
|
|
|
|
timer_delete(&call->timer);
|
|
|
|
if (rcu_read_lock_held())
|
|
/* Can't use the rxrpc workqueue as we need to cancel/flush
|
|
* something that may be running/waiting there.
|
|
*/
|
|
schedule_work(&call->destroyer);
|
|
else
|
|
rxrpc_destroy_call(&call->destroyer);
|
|
}
|
|
|
|
/*
|
|
* 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)) {
|
|
int shown = 0;
|
|
|
|
spin_lock(&rxnet->call_lock);
|
|
|
|
list_for_each_entry(call, &rxnet->calls, link) {
|
|
rxrpc_see_call(call, rxrpc_call_see_still_live);
|
|
|
|
pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
|
|
call, refcount_read(&call->ref),
|
|
rxrpc_call_states[__rxrpc_call_state(call)],
|
|
call->flags, call->events);
|
|
|
|
if (++shown >= 10)
|
|
break;
|
|
}
|
|
|
|
spin_unlock(&rxnet->call_lock);
|
|
}
|
|
|
|
atomic_dec(&rxnet->nr_calls);
|
|
wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
|
|
}
|
|
|
|
/**
|
|
* rxrpc_kernel_query_call_security - Query call's security parameters
|
|
* @call: The call to query
|
|
* @_service_id: Where to return the service ID
|
|
* @_enctype: Where to return the "encoding type"
|
|
*
|
|
* This queries the security parameters of a call, setting *@_service_id and
|
|
* *@_enctype and returning the security class.
|
|
*
|
|
* Return: The security class protocol number.
|
|
*/
|
|
u8 rxrpc_kernel_query_call_security(struct rxrpc_call *call,
|
|
u16 *_service_id, u32 *_enctype)
|
|
{
|
|
*_service_id = call->dest_srx.srx_service;
|
|
*_enctype = call->security_enctype;
|
|
return call->security_ix;
|
|
}
|
|
EXPORT_SYMBOL(rxrpc_kernel_query_call_security);
|