Initial commit: Linux kernel 4.19 for Unplugged OS

This commit is contained in:
ziv committed 2025-10-06 13:52:42 +00:00
commit d30235b04c
80519 files changed
+35800681

No files matched your search

+58
View File
@@ -0,0 +1,58 @@
#
# RxRPC session sockets
#
config AF_RXRPC
tristate "RxRPC session sockets"
depends on INET
select CRYPTO
select KEYS
help
Say Y or M here to include support for RxRPC session sockets (just
the transport part, not the presentation part: (un)marshalling is
left to the application).
These are used for AFS kernel filesystem and userspace utilities.
This module at the moment only supports client operations and is
currently incomplete.
See Documentation/networking/rxrpc.txt.
config AF_RXRPC_IPV6
bool "IPv6 support for RxRPC"
depends on (IPV6 = m && AF_RXRPC = m) || (IPV6 = y && AF_RXRPC)
help
Say Y here to allow AF_RXRPC to use IPV6 UDP as well as IPV4 UDP as
its network transport.
config AF_RXRPC_INJECT_LOSS
bool "Inject packet loss into RxRPC packet stream"
depends on AF_RXRPC
help
Say Y here to inject packet loss by discarding some received and some
transmitted packets.
config AF_RXRPC_DEBUG
bool "RxRPC dynamic debugging"
depends on AF_RXRPC
help
Say Y here to make runtime controllable debugging messages appear.
See Documentation/networking/rxrpc.txt.
config RXKAD
bool "RxRPC Kerberos security"
depends on AF_RXRPC
select CRYPTO
select CRYPTO_MANAGER
select CRYPTO_BLKCIPHER
select CRYPTO_PCBC
select CRYPTO_FCRYPT
help
Provide kerberos 4 and AFS kaserver security handling for AF_RXRPC
through the use of the key retention service.
See Documentation/networking/rxrpc.txt.
+35
View File
@@ -0,0 +1,35 @@
# SPDX-License-Identifier: GPL-2.0
#
# Makefile for Linux kernel RxRPC
#
obj-$(CONFIG_AF_RXRPC) += rxrpc.o
rxrpc-y := \
af_rxrpc.o \
call_accept.o \
call_event.o \
call_object.o \
conn_client.o \
conn_event.o \
conn_object.o \
conn_service.o \
input.o \
insecure.o \
key.o \
local_event.o \
local_object.o \
misc.o \
net_ns.o \
output.o \
peer_event.o \
peer_object.o \
recvmsg.o \
security.o \
sendmsg.o \
skbuff.o \
utils.o
rxrpc-$(CONFIG_PROC_FS) += proc.o
rxrpc-$(CONFIG_RXKAD) += rxkad.o
rxrpc-$(CONFIG_SYSCTL) += sysctl.o
+1097
View File
File diff suppressed because it is too large. Load diff
File diff suppressed because it is too large. Load diff
+667
View File
@@ -0,0 +1,667 @@
/* incoming 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/icmp.h>
#include <linux/gfp.h>
#include <linux/circ_buf.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include "ar-internal.h"
static void rxrpc_dummy_notify(struct sock *sk, struct rxrpc_call *call,
unsigned long user_call_ID)
{
}
/*
* Preallocate a single service call, connection and peer and, if possible,
* give them a user ID and attach the user's side of the ID to them.
*/
static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
struct rxrpc_backlog *b,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
unsigned long user_call_ID, gfp_t gfp,
unsigned int debug_id)
{
const void *here = __builtin_return_address(0);
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
int max, tmp;
unsigned int size = RXRPC_BACKLOG_MAX;
unsigned int head, tail, call_head, call_tail;
max = rx->sk.sk_max_ack_backlog;
tmp = rx->sk.sk_ack_backlog;
if (tmp >= max) {
_leave(" = -ENOBUFS [full %u]", max);
return -ENOBUFS;
}
max -= tmp;
/* We don't need more conns and peers than we have calls, but on the
* other hand, we shouldn't ever use more peers than conns or conns
* than calls.
*/
call_head = b->call_backlog_head;
call_tail = READ_ONCE(b->call_backlog_tail);
tmp = CIRC_CNT(call_head, call_tail, size);
if (tmp >= max) {
_leave(" = -ENOBUFS [enough %u]", tmp);
return -ENOBUFS;
}
max = tmp + 1;
head = b->peer_backlog_head;
tail = READ_ONCE(b->peer_backlog_tail);
if (CIRC_CNT(head, tail, size) < max) {
struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp);
if (!peer)
return -ENOMEM;
b->peer_backlog[head] = peer;
smp_store_release(&b->peer_backlog_head,
(head + 1) & (size - 1));
}
head = b->conn_backlog_head;
tail = READ_ONCE(b->conn_backlog_tail);
if (CIRC_CNT(head, tail, size) < max) {
struct rxrpc_connection *conn;
conn = rxrpc_prealloc_service_connection(rxnet, gfp);
if (!conn)
return -ENOMEM;
b->conn_backlog[head] = conn;
smp_store_release(&b->conn_backlog_head,
(head + 1) & (size - 1));
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
atomic_read(&conn->usage), here);
}
/* Now it gets complicated, because calls get registered with the
* socket here, particularly if a user ID is preassigned by the user.
*/
call = rxrpc_alloc_call(rx, gfp, debug_id);
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
call->state = RXRPC_CALL_SERVER_PREALLOC;
trace_rxrpc_call(call, rxrpc_call_new_service,
atomic_read(&call->usage),
here, (const void *)user_call_ID);
write_lock(&rx->call_lock);
if (user_attach_call) {
struct rxrpc_call *xcall;
struct rb_node *parent, **pp;
/* Check the user ID isn't already in use */
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
xcall = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < xcall->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > xcall->user_call_ID)
pp = &(*pp)->rb_right;
else
goto id_in_use;
}
call->user_call_ID = user_call_ID;
call->notify_rx = notify_rx;
rxrpc_get_call(call, rxrpc_call_got_kernel);
user_attach_call(call, user_call_ID);
rxrpc_get_call(call, rxrpc_call_got_userid);
rb_link_node(&call->sock_node, parent, pp);
rb_insert_color(&call->sock_node, &rx->calls);
set_bit(RXRPC_CALL_HAS_USERID, &call->flags);
}
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);
b->call_backlog[call_head] = call;
smp_store_release(&b->call_backlog_head, (call_head + 1) & (size - 1));
_leave(" = 0 [%d -> %lx]", call->debug_id, user_call_ID);
return 0;
id_in_use:
write_unlock(&rx->call_lock);
rxrpc_cleanup_call(call);
_leave(" = -EBADSLT");
return -EBADSLT;
}
/*
* Preallocate sufficient service connections, calls and peers to cover the
* entire backlog of a socket. When a new call comes in, if we don't have
* sufficient of each available, the call gets rejected as busy or ignored.
*
* The backlog is replenished when a connection is accepted or rejected.
*/
int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
{
struct rxrpc_backlog *b = rx->backlog;
if (!b) {
b = kzalloc(sizeof(struct rxrpc_backlog), gfp);
if (!b)
return -ENOMEM;
rx->backlog = b;
}
if (rx->discard_new_call)
return 0;
while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp,
atomic_inc_return(&rxrpc_debug_id)) == 0)
;
return 0;
}
/*
* Discard the preallocation on a service.
*/
void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
{
struct rxrpc_backlog *b = rx->backlog;
struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk));
unsigned int size = RXRPC_BACKLOG_MAX, head, tail;
if (!b)
return;
rx->backlog = NULL;
/* Make sure that there aren't any incoming calls in progress before we
* clear the preallocation buffers.
*/
spin_lock_bh(&rx->incoming_lock);
spin_unlock_bh(&rx->incoming_lock);
head = b->peer_backlog_head;
tail = b->peer_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_peer *peer = b->peer_backlog[tail];
rxrpc_put_local(peer->local);
kfree(peer);
tail = (tail + 1) & (size - 1);
}
head = b->conn_backlog_head;
tail = b->conn_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_connection *conn = b->conn_backlog[tail];
write_lock(&rxnet->conn_lock);
list_del(&conn->link);
list_del(&conn->proc_link);
write_unlock(&rxnet->conn_lock);
kfree(conn);
if (atomic_dec_and_test(&rxnet->nr_conns))
wake_up_var(&rxnet->nr_conns);
tail = (tail + 1) & (size - 1);
}
head = b->call_backlog_head;
tail = b->call_backlog_tail;
while (CIRC_CNT(head, tail, size) > 0) {
struct rxrpc_call *call = b->call_backlog[tail];
rcu_assign_pointer(call->socket, rx);
if (rx->discard_new_call) {
_debug("discard %lx", call->user_call_ID);
rx->discard_new_call(call, call->user_call_ID);
if (call->notify_rx)
call->notify_rx = rxrpc_dummy_notify;
rxrpc_put_call(call, rxrpc_call_put_kernel);
}
rxrpc_call_completed(call);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
tail = (tail + 1) & (size - 1);
}
kfree(b);
}
/*
* Allocate a new incoming call from the prealloc pool, along with a connection
* and a peer as necessary.
*/
static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
struct rxrpc_local *local,
struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
struct rxrpc_call *call;
unsigned short call_head, conn_head, peer_head;
unsigned short call_tail, conn_tail, peer_tail;
unsigned short call_count, conn_count;
/* #calls >= #conns >= #peers must hold true. */
call_head = smp_load_acquire(&b->call_backlog_head);
call_tail = b->call_backlog_tail;
call_count = CIRC_CNT(call_head, call_tail, RXRPC_BACKLOG_MAX);
conn_head = smp_load_acquire(&b->conn_backlog_head);
conn_tail = b->conn_backlog_tail;
conn_count = CIRC_CNT(conn_head, conn_tail, RXRPC_BACKLOG_MAX);
ASSERTCMP(conn_count, >=, call_count);
peer_head = smp_load_acquire(&b->peer_backlog_head);
peer_tail = b->peer_backlog_tail;
ASSERTCMP(CIRC_CNT(peer_head, peer_tail, RXRPC_BACKLOG_MAX), >=,
conn_count);
if (call_count == 0)
return NULL;
if (!conn) {
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
peer = b->peer_backlog[peer_tail];
if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0)
return NULL;
b->peer_backlog[peer_tail] = NULL;
smp_store_release(&b->peer_backlog_tail,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
rxrpc_new_incoming_peer(rx, local, peer);
}
/* Now allocate and set up the connection */
conn = b->conn_backlog[conn_tail];
b->conn_backlog[conn_tail] = NULL;
smp_store_release(&b->conn_backlog_tail,
(conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1));
conn->params.local = rxrpc_get_local(local);
conn->params.peer = peer;
rxrpc_see_connection(conn);
rxrpc_new_incoming_connection(rx, conn, skb);
} else {
rxrpc_get_connection(conn);
}
/* And now we can allocate and set up a new call */
call = b->call_backlog[call_tail];
b->call_backlog[call_tail] = NULL;
smp_store_release(&b->call_backlog_tail,
(call_tail + 1) & (RXRPC_BACKLOG_MAX - 1));
rxrpc_see_call(call);
call->conn = conn;
call->peer = rxrpc_get_peer(conn->params.peer);
call->cong_cwnd = call->peer->cong_cwnd;
return call;
}
/*
* Set up a new incoming call. Called in BH context with the RCU read lock
* held.
*
* If this is for a kernel service, when we allocate the call, it will have
* three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the
* retainer ref obtained from the backlog buffer. Prealloc calls for userspace
* services only have the ref from the backlog buffer. We want to pass this
* ref to non-BH context to dispose of.
*
* If we want to report an error, we mark the skb with the packet type and
* abort code and return NULL.
*
* The call is returned with the user access mutex held.
*/
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
struct rxrpc_sock *rx,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rxrpc_connection *conn;
struct rxrpc_peer *peer = NULL;
struct rxrpc_call *call;
_enter("");
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
skb->priority = RX_INVALID_OPERATION;
_leave(" = NULL [close]");
call = NULL;
goto out;
}
/* The peer, connection and call may all have sprung into existence due
* to a duplicate packet being handled on another CPU in parallel, so
* we have to recheck the routing. However, we're now holding
* rx->incoming_lock, so the values should remain stable.
*/
conn = rxrpc_find_connection_rcu(local, skb, &peer);
call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
if (!call) {
skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
_leave(" = NULL [busy]");
call = NULL;
goto out;
}
trace_rxrpc_receive(call, rxrpc_receive_incoming,
sp->hdr.serial, sp->hdr.seq);
/* Lock the call to prevent rxrpc_kernel_send/recv_data() and
* sendmsg()/recvmsg() inconveniently stealing the mutex once the
* notification is generated.
*
* The BUG should never happen because the kernel should be well
* behaved enough not to access the call before the first notification
* event and userspace is prevented from doing so until the state is
* appropriate.
*/
if (!mutex_trylock(&call->user_mutex))
BUG();
/* Make the call live. */
rxrpc_incoming_call(rx, call, skb);
conn = call->conn;
if (rx->notify_new_call)
rx->notify_new_call(&rx->sk, call, call->user_call_ID);
else
sk_acceptq_added(&rx->sk);
spin_lock(&conn->state_lock);
switch (conn->state) {
case RXRPC_CONN_SERVICE_UNSECURED:
conn->state = RXRPC_CONN_SERVICE_CHALLENGING;
set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events);
rxrpc_queue_conn(call->conn);
break;
case RXRPC_CONN_SERVICE:
write_lock(&call->state_lock);
if (call->state < RXRPC_CALL_COMPLETE) {
if (rx->discard_new_call)
call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
else
call->state = RXRPC_CALL_SERVER_ACCEPTING;
}
write_unlock(&call->state_lock);
break;
case RXRPC_CONN_REMOTELY_ABORTED:
rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED,
conn->abort_code, conn->error);
break;
case RXRPC_CONN_LOCALLY_ABORTED:
rxrpc_abort_call("CON", call, sp->hdr.seq,
conn->abort_code, conn->error);
break;
default:
BUG();
}
spin_unlock(&conn->state_lock);
if (call->state == RXRPC_CALL_SERVER_ACCEPTING)
rxrpc_notify_socket(call);
/* We have to discard the prealloc queue's ref here and rely on a
* combination of the RCU read lock and refs held either by the socket
* (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel
* service to prevent the call from being deallocated too early.
*/
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %p{%d}", call, call->debug_id);
out:
spin_unlock(&rx->incoming_lock);
return call;
}
/*
* handle acceptance of a call by userspace
* - assign the user call ID to the call at the front of the queue
* - called with the socket locked.
*/
struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx,
unsigned long user_call_ID,
rxrpc_notify_rx_t notify_rx)
__releases(&rx->sk.sk_lock.slock)
__acquires(call->user_mutex)
{
struct rxrpc_call *call;
struct rb_node *parent, **pp;
int ret;
_enter(",%lx", user_call_ID);
ASSERT(!irqs_disabled());
write_lock(&rx->call_lock);
if (list_empty(&rx->to_be_accepted)) {
write_unlock(&rx->call_lock);
release_sock(&rx->sk);
kleave(" = -ENODATA [empty]");
return ERR_PTR(-ENODATA);
}
/* check the user ID isn't already in use */
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
call = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > call->user_call_ID)
pp = &(*pp)->rb_right;
else
goto id_in_use;
}
/* Dequeue the first call and check it's still valid. We gain
* responsibility for the queue's reference.
*/
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
write_unlock(&rx->call_lock);
/* We need to gain the mutex from the interrupt handler without
* upsetting lockdep, so we have to release it there and take it here.
* We are, however, still holding the socket lock, so other accepts
* must wait for us and no one can add the user ID behind our backs.
*/
if (mutex_lock_interruptible(&call->user_mutex) < 0) {
release_sock(&rx->sk);
kleave(" = -ERESTARTSYS");
return ERR_PTR(-ERESTARTSYS);
}
write_lock(&rx->call_lock);
list_del_init(&call->accept_link);
sk_acceptq_removed(&rx->sk);
rxrpc_see_call(call);
/* Find the user ID insertion point. */
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
call = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > call->user_call_ID)
pp = &(*pp)->rb_right;
else
BUG();
}
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
call->state = RXRPC_CALL_SERVER_RECV_REQUEST;
break;
case RXRPC_CALL_COMPLETE:
ret = call->error;
goto out_release;
default:
BUG();
}
/* formalise the acceptance */
call->notify_rx = notify_rx;
call->user_call_ID = user_call_ID;
rxrpc_get_call(call, rxrpc_call_got_userid);
rb_link_node(&call->sock_node, parent, pp);
rb_insert_color(&call->sock_node, &rx->calls);
if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags))
BUG();
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
rxrpc_notify_socket(call);
rxrpc_service_prealloc(rx, GFP_KERNEL);
release_sock(&rx->sk);
_leave(" = %p{%d}", call, call->debug_id);
return call;
out_release:
_debug("release %p", call);
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
goto out;
id_in_use:
ret = -EBADSLT;
write_unlock(&rx->call_lock);
out:
rxrpc_service_prealloc(rx, GFP_KERNEL);
release_sock(&rx->sk);
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/*
* Handle rejection of a call by userspace
* - reject the call at the front of the queue
*/
int rxrpc_reject_call(struct rxrpc_sock *rx)
{
struct rxrpc_call *call;
bool abort = false;
int ret;
_enter("");
ASSERT(!irqs_disabled());
write_lock(&rx->call_lock);
if (list_empty(&rx->to_be_accepted)) {
write_unlock(&rx->call_lock);
return -ENODATA;
}
/* Dequeue the first call and check it's still valid. We gain
* responsibility for the queue's reference.
*/
call = list_entry(rx->to_be_accepted.next,
struct rxrpc_call, accept_link);
list_del_init(&call->accept_link);
sk_acceptq_removed(&rx->sk);
rxrpc_see_call(call);
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_SERVER_ACCEPTING:
__rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED);
abort = true;
/* fall through */
case RXRPC_CALL_COMPLETE:
ret = call->error;
goto out_discard;
default:
BUG();
}
out_discard:
write_unlock_bh(&call->state_lock);
write_unlock(&rx->call_lock);
if (abort) {
rxrpc_send_abort_packet(call);
rxrpc_release_call(rx, call);
rxrpc_put_call(call, rxrpc_call_put);
}
rxrpc_service_prealloc(rx, GFP_KERNEL);
_leave(" = %d", ret);
return ret;
}
/*
* rxrpc_kernel_charge_accept - Charge up socket with preallocated calls
* @sock: The socket on which to preallocate
* @notify_rx: Event notification function for the call
* @user_attach_call: Func to attach call to user_call_ID
* @user_call_ID: The tag to attach to the preallocated call
* @gfp: The allocation conditions.
* @debug_id: The tracing debug ID.
*
* Charge up the socket with preallocated calls, each with a user ID. A
* function should be provided to effect the attachment from the user's side.
* The user is given a ref to hold on the call.
*
* Note that the call may be come connected before this function returns.
*/
int rxrpc_kernel_charge_accept(struct socket *sock,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
unsigned long user_call_ID, gfp_t gfp,
unsigned int debug_id)
{
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct rxrpc_backlog *b = rx->backlog;
if (sock->sk->sk_state == RXRPC_CLOSE)
return -ESHUTDOWN;
return rxrpc_service_prealloc_one(rx, b, notify_rx,
user_attach_call, user_call_ID,
gfp, debug_id);
}
EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
+469
View File
@@ -0,0 +1,469 @@
/* Management of Tx window, Tx resend, ACKs and out-of-sequence reception
*
* 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/module.h>
#include <linux/circ_buf.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/udp.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
/*
* Propose a PING ACK be sent.
*/
static void rxrpc_propose_ping(struct rxrpc_call *call,
bool immediate, bool background)
{
if (immediate) {
if (background &&
!test_and_set_bit(RXRPC_CALL_EV_PING, &call->events))
rxrpc_queue_call(call);
} else {
unsigned long now = jiffies;
unsigned long ping_at = now + rxrpc_idle_ack_delay;
if (time_before(ping_at, call->ping_at)) {
WRITE_ONCE(call->ping_at, ping_at);
rxrpc_reduce_call_timer(call, ping_at, now,
rxrpc_timer_set_for_ping);
}
}
}
/*
* propose an ACK be sent
*/
static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
u16 skew, u32 serial, bool immediate,
bool background,
enum rxrpc_propose_ack_trace why)
{
enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use;
unsigned long expiry = rxrpc_soft_ack_delay;
s8 prior = rxrpc_ack_priority[ack_reason];
/* Pings are handled specially because we don't want to accidentally
* lose a ping response by subsuming it into a ping.
*/
if (ack_reason == RXRPC_ACK_PING) {
rxrpc_propose_ping(call, immediate, background);
goto trace;
}
/* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial
* numbers, but we don't alter the timeout.
*/
_debug("prior %u %u vs %u %u",
ack_reason, prior,
call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]);
if (ack_reason == call->ackr_reason) {
if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) {
outcome = rxrpc_propose_ack_update;
call->ackr_serial = serial;
call->ackr_skew = skew;
}
if (!immediate)
goto trace;
} else if (prior > rxrpc_ack_priority[call->ackr_reason]) {
call->ackr_reason = ack_reason;
call->ackr_serial = serial;
call->ackr_skew = skew;
} else {
outcome = rxrpc_propose_ack_subsume;
}
switch (ack_reason) {
case RXRPC_ACK_REQUESTED:
if (rxrpc_requested_ack_delay < expiry)
expiry = rxrpc_requested_ack_delay;
if (serial == 1)
immediate = false;
break;
case RXRPC_ACK_DELAY:
if (rxrpc_soft_ack_delay < expiry)
expiry = rxrpc_soft_ack_delay;
break;
case RXRPC_ACK_IDLE:
if (rxrpc_idle_ack_delay < expiry)
expiry = rxrpc_idle_ack_delay;
break;
default:
immediate = true;
break;
}
if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) {
_debug("already scheduled");
} else if (immediate || expiry == 0) {
_debug("immediate ACK %lx", call->events);
if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) &&
background)
rxrpc_queue_call(call);
} else {
unsigned long now = jiffies, ack_at;
if (call->peer->rtt_usage > 0)
ack_at = nsecs_to_jiffies(call->peer->rtt);
else
ack_at = expiry;
ack_at += READ_ONCE(call->tx_backoff);
ack_at += now;
if (time_before(ack_at, call->ack_at)) {
WRITE_ONCE(call->ack_at, ack_at);
rxrpc_reduce_call_timer(call, ack_at, now,
rxrpc_timer_set_for_ack);
}
}
trace:
trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate,
background, outcome);
}
/*
* propose an ACK be sent, locking the call structure
*/
void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
u16 skew, u32 serial, bool immediate, bool background,
enum rxrpc_propose_ack_trace why)
{
spin_lock_bh(&call->lock);
__rxrpc_propose_ACK(call, ack_reason, skew, serial,
immediate, background, why);
spin_unlock_bh(&call->lock);
}
/*
* Handle congestion being detected by the retransmit timeout.
*/
static void rxrpc_congestion_timeout(struct rxrpc_call *call)
{
set_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags);
}
/*
* Perform retransmission of NAK'd and unack'd packets.
*/
static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
{
struct sk_buff *skb;
unsigned long resend_at;
rxrpc_seq_t cursor, seq, top;
ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo;
int ix;
u8 annotation, anno_type, retrans = 0, unacked = 0;
_enter("{%d,%d}", call->tx_hard_ack, call->tx_top);
if (call->peer->rtt_usage > 1)
timeout = ns_to_ktime(call->peer->rtt * 3 / 2);
else
timeout = ms_to_ktime(rxrpc_resend_timeout);
min_timeo = ns_to_ktime((1000000000 / HZ) * 4);
if (ktime_before(timeout, min_timeo))
timeout = min_timeo;
now = ktime_get_real();
max_age = ktime_sub(now, timeout);
spin_lock_bh(&call->lock);
cursor = call->tx_hard_ack;
top = call->tx_top;
ASSERT(before_eq(cursor, top));
if (cursor == top)
goto out_unlock;
/* Scan the packet list without dropping the lock and decide which of
* the packets in the Tx buffer we're going to resend and what the new
* resend timeout will be.
*/
trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK);
oldest = now;
for (seq = cursor + 1; before_eq(seq, top); seq++) {
ix = seq & RXRPC_RXTX_BUFF_MASK;
annotation = call->rxtx_annotations[ix];
anno_type = annotation & RXRPC_TX_ANNO_MASK;
annotation &= ~RXRPC_TX_ANNO_MASK;
if (anno_type == RXRPC_TX_ANNO_ACK)
continue;
skb = call->rxtx_buffer[ix];
rxrpc_see_skb(skb, rxrpc_skb_tx_seen);
if (anno_type == RXRPC_TX_ANNO_UNACK) {
if (ktime_after(skb->tstamp, max_age)) {
if (ktime_before(skb->tstamp, oldest))
oldest = skb->tstamp;
continue;
}
if (!(annotation & RXRPC_TX_ANNO_RESENT))
unacked++;
}
/* Okay, we need to retransmit a packet. */
call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation;
retrans++;
trace_rxrpc_retransmit(call, seq, annotation | anno_type,
ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
}
resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
resend_at += jiffies + rxrpc_resend_timeout;
WRITE_ONCE(call->resend_at, resend_at);
if (unacked)
rxrpc_congestion_timeout(call);
/* If there was nothing that needed retransmission then it's likely
* that an ACK got lost somewhere. Send a ping to find out instead of
* retransmitting data.
*/
if (!retrans) {
rxrpc_reduce_call_timer(call, resend_at, now_j,
rxrpc_timer_set_for_resend);
spin_unlock_bh(&call->lock);
ack_ts = ktime_sub(now, call->acks_latest_ts);
if (ktime_to_ns(ack_ts) < call->peer->rtt)
goto out;
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
rxrpc_send_ack_packet(call, true, NULL);
goto out;
}
/* Now go through the Tx window and perform the retransmissions. We
* have to drop the lock for each send. If an ACK comes in whilst the
* lock is dropped, it may clear some of the retransmission markers for
* packets that it soft-ACKs.
*/
for (seq = cursor + 1; before_eq(seq, top); seq++) {
ix = seq & RXRPC_RXTX_BUFF_MASK;
annotation = call->rxtx_annotations[ix];
anno_type = annotation & RXRPC_TX_ANNO_MASK;
if (anno_type != RXRPC_TX_ANNO_RETRANS)
continue;
skb = call->rxtx_buffer[ix];
rxrpc_get_skb(skb, rxrpc_skb_tx_got);
spin_unlock_bh(&call->lock);
if (rxrpc_send_data_packet(call, skb, true) < 0) {
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
return;
}
if (rxrpc_is_client_call(call))
rxrpc_expose_client_call(call);
rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
spin_lock_bh(&call->lock);
/* We need to clear the retransmit state, but there are two
* things we need to be aware of: A new ACK/NAK might have been
* received and the packet might have been hard-ACK'd (in which
* case it will no longer be in the buffer).
*/
if (after(seq, call->tx_hard_ack)) {
annotation = call->rxtx_annotations[ix];
anno_type = annotation & RXRPC_TX_ANNO_MASK;
if (anno_type == RXRPC_TX_ANNO_RETRANS ||
anno_type == RXRPC_TX_ANNO_NAK) {
annotation &= ~RXRPC_TX_ANNO_MASK;
annotation |= RXRPC_TX_ANNO_UNACK;
}
annotation |= RXRPC_TX_ANNO_RESENT;
call->rxtx_annotations[ix] = annotation;
}
if (after(call->tx_hard_ack, seq))
seq = call->tx_hard_ack;
}
out_unlock:
spin_unlock_bh(&call->lock);
out:
_leave("");
}
/*
* Handle retransmission and deferred ACK/abort generation.
*/
void rxrpc_process_call(struct work_struct *work)
{
struct rxrpc_call *call =
container_of(work, struct rxrpc_call, processor);
rxrpc_serial_t *send_ack;
unsigned long now, next, t;
unsigned int iterations = 0;
rxrpc_see_call(call);
//printk("\n--------------------\n");
_enter("{%d,%s,%lx}",
call->debug_id, rxrpc_call_states[call->state], call->events);
recheck_state:
/* Limit the number of times we do this before returning to the manager */
iterations++;
if (iterations > 5)
goto requeue;
if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
rxrpc_send_abort_packet(call);
goto recheck_state;
}
if (call->state == RXRPC_CALL_COMPLETE) {
del_timer_sync(&call->timer);
rxrpc_notify_socket(call);
goto out_put;
}
/* Work out if any timeouts tripped */
now = jiffies;
t = READ_ONCE(call->expect_rx_by);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now);
set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
}
t = READ_ONCE(call->expect_req_by);
if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST &&
time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now);
set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
}
t = READ_ONCE(call->expect_term_by);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now);
set_bit(RXRPC_CALL_EV_EXPIRED, &call->events);
}
t = READ_ONCE(call->ack_at);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now);
cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET);
set_bit(RXRPC_CALL_EV_ACK, &call->events);
}
t = READ_ONCE(call->ack_lost_at);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now);
cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET);
set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events);
}
t = READ_ONCE(call->keepalive_at);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now);
cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET);
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true,
rxrpc_propose_ack_ping_for_keepalive);
set_bit(RXRPC_CALL_EV_PING, &call->events);
}
t = READ_ONCE(call->ping_at);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now);
cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET);
set_bit(RXRPC_CALL_EV_PING, &call->events);
}
t = READ_ONCE(call->resend_at);
if (time_after_eq(now, t)) {
trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now);
cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET);
set_bit(RXRPC_CALL_EV_RESEND, &call->events);
}
/* Process events */
if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) {
if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) &&
(int)call->conn->hi_serial - (int)call->rx_serial > 0) {
trace_rxrpc_call_reset(call);
rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ECONNRESET);
} else {
rxrpc_abort_call("EXP", call, 0, RX_USER_ABORT, -ETIME);
}
set_bit(RXRPC_CALL_EV_ABORT, &call->events);
goto recheck_state;
}
send_ack = NULL;
if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) {
call->acks_lost_top = call->tx_top;
rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
rxrpc_propose_ack_ping_for_lost_ack);
send_ack = &call->acks_lost_ping;
}
if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) ||
send_ack) {
if (call->ackr_reason) {
rxrpc_send_ack_packet(call, false, send_ack);
goto recheck_state;
}
}
if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) {
rxrpc_send_ack_packet(call, true, NULL);
goto recheck_state;
}
if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) {
rxrpc_resend(call, now);
goto recheck_state;
}
/* Make sure the timer is restarted */
next = call->expect_rx_by;
#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; }
set(call->expect_req_by);
set(call->expect_term_by);
set(call->ack_at);
set(call->ack_lost_at);
set(call->resend_at);
set(call->keepalive_at);
set(call->ping_at);
now = jiffies;
if (time_after_eq(now, next))
goto recheck_state;
rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
/* other events may have been raised since we started checking */
if (call->events && call->state < RXRPC_CALL_COMPLETE)
goto requeue;
out_put:
rxrpc_put_call(call, rxrpc_call_put);
out:
_leave("");
return;
requeue:
__rxrpc_queue_call(call);
goto out;
}
+757
View File
@@ -0,0 +1,757 @@
/* 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_attached_to_socket;
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);
__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
RX_CALL_DEAD, -EEXIST);
trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
here, ERR_PTR(-EEXIST));
rxrpc_release_call(rx, call);
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put);
_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
* completing the call queues it. Return 0 from sys_sendmsg() and
* leave the error to recvmsg() to deal with.
*/
error_attached_to_socket:
trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage),
here, ERR_PTR(ret));
set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
__rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
RX_CALL_DEAD, ret);
_leave(" = c=%08x [err]", call->debug_id);
return call;
}
/*
* 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 && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
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 - 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, processor);
struct rxrpc_net *rxnet = call->rxnet;
rxrpc_put_connection(call->conn);
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);
}
/*
* 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);
if (in_softirq()) {
INIT_WORK(&call->processor, rxrpc_destroy_call);
if (!rxrpc_queue_work(&call->processor))
BUG();
} else {
rxrpc_destroy_call(&call->processor);
}
}
/*
* 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));
/* 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)) {
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));
}
File diff suppressed because it is too large. Load diff
+518
View File
@@ -0,0 +1,518 @@
/* connection-level event 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include "ar-internal.h"
/*
* Retransmit terminal ACK or ABORT of the previous call.
*/
static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
struct sk_buff *skb,
unsigned int channel)
{
struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL;
struct rxrpc_channel *chan;
struct msghdr msg;
struct kvec iov[3];
struct {
struct rxrpc_wire_header whdr;
union {
__be32 abort_code;
struct rxrpc_ackpacket ack;
};
} __attribute__((packed)) pkt;
struct rxrpc_ackinfo ack_info;
size_t len;
int ret, ioc;
u32 serial, mtu, call_id, padding;
_enter("%d", conn->debug_id);
chan = &conn->channels[channel];
/* If the last call got moved on whilst we were waiting to run, just
* ignore this packet.
*/
call_id = READ_ONCE(chan->last_call);
/* Sync with __rxrpc_disconnect_call() */
smp_rmb();
if (skb && call_id != sp->hdr.callNumber)
return;
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
iov[0].iov_base = &pkt;
iov[0].iov_len = sizeof(pkt.whdr);
iov[1].iov_base = &padding;
iov[1].iov_len = 3;
iov[2].iov_base = &ack_info;
iov[2].iov_len = sizeof(ack_info);
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(conn->proto.cid | channel);
pkt.whdr.callNumber = htonl(call_id);
pkt.whdr.seq = 0;
pkt.whdr.type = chan->last_type;
pkt.whdr.flags = conn->out_clientflag;
pkt.whdr.userStatus = 0;
pkt.whdr.securityIndex = conn->security_ix;
pkt.whdr._rsvd = 0;
pkt.whdr.serviceId = htons(conn->service_id);
len = sizeof(pkt.whdr);
switch (chan->last_type) {
case RXRPC_PACKET_TYPE_ABORT:
pkt.abort_code = htonl(chan->last_abort);
iov[0].iov_len += sizeof(pkt.abort_code);
len += sizeof(pkt.abort_code);
ioc = 1;
break;
case RXRPC_PACKET_TYPE_ACK:
mtu = conn->params.peer->if_mtu;
mtu -= conn->params.peer->hdrsize;
pkt.ack.bufferSpace = 0;
pkt.ack.maxSkew = htons(skb ? skb->priority : 0);
pkt.ack.firstPacket = htonl(chan->last_seq + 1);
pkt.ack.previousPacket = htonl(chan->last_seq);
pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0);
pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE;
pkt.ack.nAcks = 0;
ack_info.rxMTU = htonl(rxrpc_rx_mtu);
ack_info.maxMTU = htonl(mtu);
ack_info.rwind = htonl(rxrpc_rx_window_size);
ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max);
pkt.whdr.flags |= RXRPC_SLOW_START_OK;
padding = 0;
iov[0].iov_len += sizeof(pkt.ack);
len += sizeof(pkt.ack) + 3 + sizeof(ack_info);
ioc = 3;
break;
default:
return;
}
/* Resync with __rxrpc_disconnect_call() and check that the last call
* didn't get advanced whilst we were filling out the packets.
*/
smp_rmb();
if (READ_ONCE(chan->last_call) != call_id)
return;
serial = atomic_inc_return(&conn->serial);
pkt.whdr.serial = htonl(serial);
switch (chan->last_type) {
case RXRPC_PACKET_TYPE_ABORT:
_proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code);
break;
case RXRPC_PACKET_TYPE_ACK:
trace_rxrpc_tx_ack(chan->call_debug_id, serial,
ntohl(pkt.ack.firstPacket),
ntohl(pkt.ack.serial),
pkt.ack.reason, 0);
_proto("Tx ACK %%%u [re]", serial);
break;
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret,
rxrpc_tx_point_call_final_resend);
else
trace_rxrpc_tx_packet(chan->call_debug_id, &pkt.whdr,
rxrpc_tx_point_call_final_resend);
_leave("");
}
/*
* pass a connection-level abort onto all calls on that connection
*/
static void rxrpc_abort_calls(struct rxrpc_connection *conn,
enum rxrpc_call_completion compl)
{
struct rxrpc_call *call;
int i;
_enter("{%d},%x", conn->debug_id, conn->abort_code);
spin_lock(&conn->channel_lock);
for (i = 0; i < RXRPC_MAXCALLS; i++) {
call = rcu_dereference_protected(
conn->channels[i].call,
lockdep_is_held(&conn->channel_lock));
if (call) {
if (compl == RXRPC_CALL_LOCALLY_ABORTED)
trace_rxrpc_abort(call->debug_id,
"CON", call->cid,
call->call_id, 0,
conn->abort_code,
conn->error);
if (rxrpc_set_call_completion(call, compl,
conn->abort_code,
conn->error))
rxrpc_notify_socket(call);
}
}
spin_unlock(&conn->channel_lock);
_leave("");
}
/*
* generate a connection-level abort
*/
static int rxrpc_abort_connection(struct rxrpc_connection *conn,
int error, u32 abort_code)
{
struct rxrpc_wire_header whdr;
struct msghdr msg;
struct kvec iov[2];
__be32 word;
size_t len;
u32 serial;
int ret;
_enter("%d,,%u,%u", conn->debug_id, error, abort_code);
/* generate a connection-level abort */
spin_lock_bh(&conn->state_lock);
if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
spin_unlock_bh(&conn->state_lock);
_leave(" = 0 [already dead]");
return 0;
}
conn->error = error;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_LOCALLY_ABORTED;
spin_unlock_bh(&conn->state_lock);
rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
msg.msg_name = &conn->params.peer->srx.transport;
msg.msg_namelen = conn->params.peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
whdr.epoch = htonl(conn->proto.epoch);
whdr.cid = htonl(conn->proto.cid);
whdr.callNumber = 0;
whdr.seq = 0;
whdr.type = RXRPC_PACKET_TYPE_ABORT;
whdr.flags = conn->out_clientflag;
whdr.userStatus = 0;
whdr.securityIndex = conn->security_ix;
whdr._rsvd = 0;
whdr.serviceId = htons(conn->service_id);
word = htonl(conn->abort_code);
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = &word;
iov[1].iov_len = sizeof(word);
len = iov[0].iov_len + iov[1].iov_len;
serial = atomic_inc_return(&conn->serial);
whdr.serial = htonl(serial);
_proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
if (ret < 0) {
trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
rxrpc_tx_point_conn_abort);
_debug("sendmsg failed: %d", ret);
return -EAGAIN;
}
trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
conn->params.peer->last_tx_at = ktime_get_seconds();
_leave(" = 0");
return 0;
}
/*
* mark a call as being on a now-secured channel
* - must be called with BH's disabled.
*/
static void rxrpc_call_is_secure(struct rxrpc_call *call)
{
_enter("%p", call);
if (call) {
write_lock_bh(&call->state_lock);
if (call->state == RXRPC_CALL_SERVER_SECURING) {
call->state = RXRPC_CALL_SERVER_ACCEPTING;
rxrpc_notify_socket(call);
}
write_unlock_bh(&call->state_lock);
}
}
/*
* connection-level Rx packet processor
*/
static int rxrpc_process_event(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
__be32 wtmp;
u32 abort_code;
int loop, ret;
if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) {
_leave(" = -ECONNABORTED [%u]", conn->state);
return -ECONNABORTED;
}
_enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_DATA:
case RXRPC_PACKET_TYPE_ACK:
rxrpc_conn_retransmit_call(conn, skb,
sp->hdr.cid & RXRPC_CHANNELMASK);
return 0;
case RXRPC_PACKET_TYPE_BUSY:
/* Just ignore BUSY packets for now. */
return 0;
case RXRPC_PACKET_TYPE_ABORT:
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&wtmp, sizeof(wtmp)) < 0) {
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("bad_abort"));
return -EPROTO;
}
abort_code = ntohl(wtmp);
_proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code);
conn->error = -ECONNABORTED;
conn->abort_code = abort_code;
conn->state = RXRPC_CONN_REMOTELY_ABORTED;
rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
return -ECONNABORTED;
case RXRPC_PACKET_TYPE_CHALLENGE:
return conn->security->respond_to_challenge(conn, skb,
_abort_code);
case RXRPC_PACKET_TYPE_RESPONSE:
ret = conn->security->verify_response(conn, skb, _abort_code);
if (ret < 0)
return ret;
ret = conn->security->init_connection_security(conn);
if (ret < 0)
return ret;
ret = conn->security->prime_packet_security(conn);
if (ret < 0)
return ret;
spin_lock(&conn->channel_lock);
spin_lock_bh(&conn->state_lock);
if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
conn->state = RXRPC_CONN_SERVICE;
spin_unlock_bh(&conn->state_lock);
for (loop = 0; loop < RXRPC_MAXCALLS; loop++)
rxrpc_call_is_secure(
rcu_dereference_protected(
conn->channels[loop].call,
lockdep_is_held(&conn->channel_lock)));
} else {
spin_unlock_bh(&conn->state_lock);
}
spin_unlock(&conn->channel_lock);
return 0;
default:
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("bad_conn_pkt"));
return -EPROTO;
}
}
/*
* set up security and issue a challenge
*/
static void rxrpc_secure_connection(struct rxrpc_connection *conn)
{
u32 abort_code;
int ret;
_enter("{%d}", conn->debug_id);
ASSERT(conn->security_ix != 0);
if (!conn->params.key) {
_debug("set up security");
ret = rxrpc_init_server_conn_security(conn);
switch (ret) {
case 0:
break;
case -ENOENT:
abort_code = RX_CALL_DEAD;
goto abort;
default:
abort_code = RXKADNOAUTH;
goto abort;
}
}
if (conn->security->issue_challenge(conn) < 0) {
abort_code = RX_CALL_DEAD;
ret = -ENOMEM;
goto abort;
}
_leave("");
return;
abort:
_debug("abort %d, %d", ret, abort_code);
rxrpc_abort_connection(conn, ret, abort_code);
_leave(" [aborted]");
}
/*
* Process delayed final ACKs that we haven't subsumed into a subsequent call.
*/
static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn)
{
unsigned long j = jiffies, next_j;
unsigned int channel;
bool set;
again:
next_j = j + LONG_MAX;
set = false;
for (channel = 0; channel < RXRPC_MAXCALLS; channel++) {
struct rxrpc_channel *chan = &conn->channels[channel];
unsigned long ack_at;
if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags))
continue;
smp_rmb(); /* vs rxrpc_disconnect_client_call */
ack_at = READ_ONCE(chan->final_ack_at);
if (time_before(j, ack_at)) {
if (time_before(ack_at, next_j)) {
next_j = ack_at;
set = true;
}
continue;
}
if (test_and_clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel,
&conn->flags))
rxrpc_conn_retransmit_call(conn, NULL, channel);
}
j = jiffies;
if (time_before_eq(next_j, j))
goto again;
if (set)
rxrpc_reduce_conn_timer(conn, next_j);
}
/*
* connection-level event processor
*/
static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
{
struct sk_buff *skb;
u32 abort_code = RX_PROTOCOL_ERROR;
int ret;
if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events))
rxrpc_secure_connection(conn);
/* Process delayed ACKs whose time has come. */
if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
rxrpc_process_delayed_final_acks(conn);
/* go through the conn-level event packets, releasing the ref on this
* connection that each one has when we've finished with it */
while ((skb = skb_dequeue(&conn->rx_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
ret = rxrpc_process_event(conn, skb, &abort_code);
switch (ret) {
case -EPROTO:
case -EKEYEXPIRED:
case -EKEYREJECTED:
goto protocol_error;
case -ENOMEM:
case -EAGAIN:
goto requeue_and_leave;
case -ECONNABORTED:
default:
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
break;
}
}
return;
requeue_and_leave:
skb_queue_head(&conn->rx_queue, skb);
return;
protocol_error:
if (rxrpc_abort_connection(conn, ret, abort_code) < 0)
goto requeue_and_leave;
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
return;
}
void rxrpc_process_connection(struct work_struct *work)
{
struct rxrpc_connection *conn =
container_of(work, struct rxrpc_connection, processor);
rxrpc_see_connection(conn);
if (__rxrpc_use_local(conn->params.local)) {
rxrpc_do_process_connection(conn);
rxrpc_unuse_local(conn->params.local);
}
rxrpc_put_connection(conn);
_leave("");
return;
}
+491
View File
@@ -0,0 +1,491 @@
/* RxRPC virtual connection handler, common bits.
*
* 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 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/module.h>
#include <linux/slab.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include "ar-internal.h"
/*
* Time till a connection expires after last use (in seconds).
*/
unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60;
unsigned int __read_mostly rxrpc_closed_conn_expiry = 10;
static void rxrpc_destroy_connection(struct rcu_head *);
static void rxrpc_connection_timer(struct timer_list *timer)
{
struct rxrpc_connection *conn =
container_of(timer, struct rxrpc_connection, timer);
rxrpc_queue_conn(conn);
}
/*
* allocate a new connection
*/
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
{
struct rxrpc_connection *conn;
_enter("");
conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
if (conn) {
INIT_LIST_HEAD(&conn->cache_link);
spin_lock_init(&conn->channel_lock);
INIT_LIST_HEAD(&conn->waiting_calls);
timer_setup(&conn->timer, &rxrpc_connection_timer, 0);
INIT_WORK(&conn->processor, &rxrpc_process_connection);
INIT_LIST_HEAD(&conn->proc_link);
INIT_LIST_HEAD(&conn->link);
skb_queue_head_init(&conn->rx_queue);
conn->security = &rxrpc_no_security;
spin_lock_init(&conn->state_lock);
conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
conn->size_align = 4;
conn->idle_timestamp = jiffies;
}
_leave(" = %p{%d}", conn, conn ? conn->debug_id : 0);
return conn;
}
/*
* Look up a connection in the cache by protocol parameters.
*
* If successful, a pointer to the connection is returned, but no ref is taken.
* NULL is returned if there is no match.
*
* When searching for a service call, if we find a peer but no connection, we
* return that through *_peer in case we need to create a new service call.
*
* The caller must be holding the RCU read lock.
*/
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
struct sk_buff *skb,
struct rxrpc_peer **_peer)
{
struct rxrpc_connection *conn;
struct rxrpc_conn_proto k;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct sockaddr_rxrpc srx;
struct rxrpc_peer *peer;
_enter(",%x", sp->hdr.cid & RXRPC_CIDMASK);
if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
goto not_found;
/* We may have to handle mixing IPv4 and IPv6 */
if (srx.transport.family != local->srx.transport.family) {
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
srx.transport.family,
local->srx.transport.family);
goto not_found;
}
k.epoch = sp->hdr.epoch;
k.cid = sp->hdr.cid & RXRPC_CIDMASK;
if (rxrpc_to_server(sp)) {
/* We need to look up service connections by the full protocol
* parameter set. We look up the peer first as an intermediate
* step and then the connection from the peer's tree.
*/
peer = rxrpc_lookup_peer_rcu(local, &srx);
if (!peer)
goto not_found;
*_peer = peer;
conn = rxrpc_find_service_conn_rcu(peer, skb);
if (!conn || atomic_read(&conn->usage) == 0)
goto not_found;
_leave(" = %p", conn);
return conn;
} else {
/* Look up client connections by connection ID alone as their
* IDs are unique for this machine.
*/
conn = idr_find(&rxrpc_client_conn_ids,
sp->hdr.cid >> RXRPC_CIDSHIFT);
if (!conn || atomic_read(&conn->usage) == 0) {
_debug("no conn");
goto not_found;
}
if (conn->proto.epoch != k.epoch ||
conn->params.local != local)
goto not_found;
peer = conn->params.peer;
switch (srx.transport.family) {
case AF_INET:
if (peer->srx.transport.sin.sin_port !=
srx.transport.sin.sin_port ||
peer->srx.transport.sin.sin_addr.s_addr !=
srx.transport.sin.sin_addr.s_addr)
goto not_found;
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
if (peer->srx.transport.sin6.sin6_port !=
srx.transport.sin6.sin6_port ||
memcmp(&peer->srx.transport.sin6.sin6_addr,
&srx.transport.sin6.sin6_addr,
sizeof(struct in6_addr)) != 0)
goto not_found;
break;
#endif
default:
BUG();
}
_leave(" = %p", conn);
return conn;
}
not_found:
_leave(" = NULL");
return NULL;
}
/*
* Disconnect a call and clear any channel it occupies when that call
* terminates. The caller must hold the channel_lock and must release the
* call's ref on the connection.
*/
void __rxrpc_disconnect_call(struct rxrpc_connection *conn,
struct rxrpc_call *call)
{
struct rxrpc_channel *chan =
&conn->channels[call->cid & RXRPC_CHANNELMASK];
_enter("%d,%x", conn->debug_id, call->cid);
if (rcu_access_pointer(chan->call) == call) {
/* Save the result of the call so that we can repeat it if necessary
* through the channel, whilst disposing of the actual call record.
*/
trace_rxrpc_disconnect_call(call);
switch (call->completion) {
case RXRPC_CALL_SUCCEEDED:
chan->last_seq = call->rx_hard_ack;
chan->last_type = RXRPC_PACKET_TYPE_ACK;
break;
case RXRPC_CALL_LOCALLY_ABORTED:
chan->last_abort = call->abort_code;
chan->last_type = RXRPC_PACKET_TYPE_ABORT;
break;
default:
chan->last_abort = RX_USER_ABORT;
chan->last_type = RXRPC_PACKET_TYPE_ABORT;
break;
}
/* Sync with rxrpc_conn_retransmit(). */
smp_wmb();
chan->last_call = chan->call_id;
chan->call_id = chan->call_counter;
rcu_assign_pointer(chan->call, NULL);
}
_leave("");
}
/*
* Disconnect a call and clear any channel it occupies when that call
* terminates.
*/
void rxrpc_disconnect_call(struct rxrpc_call *call)
{
struct rxrpc_connection *conn = call->conn;
call->peer->cong_cwnd = call->cong_cwnd;
if (!hlist_unhashed(&call->error_link)) {
spin_lock_bh(&call->peer->lock);
hlist_del_rcu(&call->error_link);
spin_unlock_bh(&call->peer->lock);
}
if (rxrpc_is_client_call(call))
return rxrpc_disconnect_client_call(call);
spin_lock(&conn->channel_lock);
__rxrpc_disconnect_call(conn, call);
spin_unlock(&conn->channel_lock);
set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
conn->idle_timestamp = jiffies;
}
/*
* Kill off a connection.
*/
void rxrpc_kill_connection(struct rxrpc_connection *conn)
{
struct rxrpc_net *rxnet = conn->params.local->rxnet;
ASSERT(!rcu_access_pointer(conn->channels[0].call) &&
!rcu_access_pointer(conn->channels[1].call) &&
!rcu_access_pointer(conn->channels[2].call) &&
!rcu_access_pointer(conn->channels[3].call));
ASSERT(list_empty(&conn->cache_link));
write_lock(&rxnet->conn_lock);
list_del_init(&conn->proc_link);
write_unlock(&rxnet->conn_lock);
/* Drain the Rx queue. Note that even though we've unpublished, an
* incoming packet could still be being added to our Rx queue, so we
* will need to drain it again in the RCU cleanup handler.
*/
rxrpc_purge_queue(&conn->rx_queue);
/* Leave final destruction to RCU. The connection processor work item
* must carry a ref on the connection to prevent us getting here whilst
* it is queued or running.
*/
call_rcu(&conn->rcu, rxrpc_destroy_connection);
}
/*
* Queue a connection's work processor, getting a ref to pass to the work
* queue.
*/
bool rxrpc_queue_conn(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
if (n == 0)
return false;
if (rxrpc_queue_work(&conn->processor))
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here);
else
rxrpc_put_connection(conn);
return true;
}
/*
* Note the re-emergence of a connection.
*/
void rxrpc_see_connection(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
if (conn) {
int n = atomic_read(&conn->usage);
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here);
}
}
/*
* Get a ref on a connection.
*/
void rxrpc_get_connection(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
int n = atomic_inc_return(&conn->usage);
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here);
}
/*
* Try to get a ref on a connection.
*/
struct rxrpc_connection *
rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
if (conn) {
int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
if (n > 0)
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here);
else
conn = NULL;
}
return conn;
}
/*
* Set the service connection reap timer.
*/
static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet,
unsigned long reap_at)
{
if (rxnet->live)
timer_reduce(&rxnet->service_conn_reap_timer, reap_at);
}
/*
* Release a service connection
*/
void rxrpc_put_service_conn(struct rxrpc_connection *conn)
{
const void *here = __builtin_return_address(0);
unsigned int debug_id = conn->debug_id;
int n;
n = atomic_dec_return(&conn->usage);
trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here);
ASSERTCMP(n, >=, 0);
if (n == 1)
rxrpc_set_service_reap_timer(conn->params.local->rxnet,
jiffies + rxrpc_connection_expiry);
}
/*
* destroy a virtual connection
*/
static void rxrpc_destroy_connection(struct rcu_head *rcu)
{
struct rxrpc_connection *conn =
container_of(rcu, struct rxrpc_connection, rcu);
_enter("{%d,u=%d}", conn->debug_id, atomic_read(&conn->usage));
ASSERTCMP(atomic_read(&conn->usage), ==, 0);
_net("DESTROY CONN %d", conn->debug_id);
del_timer_sync(&conn->timer);
rxrpc_purge_queue(&conn->rx_queue);
conn->security->clear(conn);
key_put(conn->params.key);
key_put(conn->server_key);
rxrpc_put_peer(conn->params.peer);
if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns))
wake_up_var(&conn->params.local->rxnet->nr_conns);
rxrpc_put_local(conn->params.local);
kfree(conn);
_leave("");
}
/*
* reap dead service connections
*/
void rxrpc_service_connection_reaper(struct work_struct *work)
{
struct rxrpc_connection *conn, *_p;
struct rxrpc_net *rxnet =
container_of(work, struct rxrpc_net, service_conn_reaper);
unsigned long expire_at, earliest, idle_timestamp, now;
LIST_HEAD(graveyard);
_enter("");
now = jiffies;
earliest = now + MAX_JIFFY_OFFSET;
write_lock(&rxnet->conn_lock);
list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) {
ASSERTCMP(atomic_read(&conn->usage), >, 0);
if (likely(atomic_read(&conn->usage) > 1))
continue;
if (conn->state == RXRPC_CONN_SERVICE_PREALLOC)
continue;
if (rxnet->live && !conn->params.local->dead) {
idle_timestamp = READ_ONCE(conn->idle_timestamp);
expire_at = idle_timestamp + rxrpc_connection_expiry * HZ;
if (conn->params.local->service_closed)
expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ;
_debug("reap CONN %d { u=%d,t=%ld }",
conn->debug_id, atomic_read(&conn->usage),
(long)expire_at - (long)now);
if (time_before(now, expire_at)) {
if (time_before(expire_at, earliest))
earliest = expire_at;
continue;
}
}
/* The usage count sits at 1 whilst the object is unused on the
* list; we reduce that to 0 to make the object unavailable.
*/
if (atomic_cmpxchg(&conn->usage, 1, 0) != 1)
continue;
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL);
if (rxrpc_conn_is_client(conn))
BUG();
else
rxrpc_unpublish_service_conn(conn);
list_move_tail(&conn->link, &graveyard);
}
write_unlock(&rxnet->conn_lock);
if (earliest != now + MAX_JIFFY_OFFSET) {
_debug("reschedule reaper %ld", (long)earliest - (long)now);
ASSERT(time_after(earliest, now));
rxrpc_set_service_reap_timer(rxnet, earliest);
}
while (!list_empty(&graveyard)) {
conn = list_entry(graveyard.next, struct rxrpc_connection,
link);
list_del_init(&conn->link);
ASSERTCMP(atomic_read(&conn->usage), ==, 0);
rxrpc_kill_connection(conn);
}
_leave("");
}
/*
* preemptively destroy all the service connection records rather than
* waiting for them to time out
*/
void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet)
{
struct rxrpc_connection *conn, *_p;
bool leak = false;
_enter("");
atomic_dec(&rxnet->nr_conns);
rxrpc_destroy_all_client_connections(rxnet);
del_timer_sync(&rxnet->service_conn_reap_timer);
rxrpc_queue_work(&rxnet->service_conn_reaper);
flush_workqueue(rxrpc_workqueue);
write_lock(&rxnet->conn_lock);
list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) {
pr_err("AF_RXRPC: Leaked conn %p {%d}\n",
conn, atomic_read(&conn->usage));
leak = true;
}
write_unlock(&rxnet->conn_lock);
BUG_ON(leak);
ASSERT(list_empty(&rxnet->conn_proc_list));
/* We need to wait for the connections to be destroyed by RCU as they
* pin things that we still need to get rid of.
*/
wait_var_event(&rxnet->nr_conns, !atomic_read(&rxnet->nr_conns));
_leave("");
}
+198
View File
@@ -0,0 +1,198 @@
/* Service connection management
*
* Copyright (C) 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.
*/
#include <linux/slab.h>
#include "ar-internal.h"
/*
* Find a service connection under RCU conditions.
*
* We could use a hash table, but that is subject to bucket stuffing by an
* attacker as the client gets to pick the epoch and cid values and would know
* the hash function. So, instead, we use a hash table for the peer and from
* that an rbtree to find the service connection. Under ordinary circumstances
* it might be slower than a large hash table, but it is at least limited in
* depth.
*/
struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer,
struct sk_buff *skb)
{
struct rxrpc_connection *conn = NULL;
struct rxrpc_conn_proto k;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct rb_node *p;
unsigned int seq = 0;
k.epoch = sp->hdr.epoch;
k.cid = sp->hdr.cid & RXRPC_CIDMASK;
do {
/* Unfortunately, rbtree walking doesn't give reliable results
* under just the RCU read lock, so we have to check for
* changes.
*/
read_seqbegin_or_lock(&peer->service_conn_lock, &seq);
p = rcu_dereference_raw(peer->service_conns.rb_node);
while (p) {
conn = rb_entry(p, struct rxrpc_connection, service_node);
if (conn->proto.index_key < k.index_key)
p = rcu_dereference_raw(p->rb_left);
else if (conn->proto.index_key > k.index_key)
p = rcu_dereference_raw(p->rb_right);
else
break;
conn = NULL;
}
} while (need_seqretry(&peer->service_conn_lock, seq));
done_seqretry(&peer->service_conn_lock, seq);
_leave(" = %d", conn ? conn->debug_id : -1);
return conn;
}
/*
* Insert a service connection into a peer's tree, thereby making it a target
* for incoming packets.
*/
static void rxrpc_publish_service_conn(struct rxrpc_peer *peer,
struct rxrpc_connection *conn)
{
struct rxrpc_connection *cursor = NULL;
struct rxrpc_conn_proto k = conn->proto;
struct rb_node **pp, *parent;
write_seqlock_bh(&peer->service_conn_lock);
pp = &peer->service_conns.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
cursor = rb_entry(parent,
struct rxrpc_connection, service_node);
if (cursor->proto.index_key < k.index_key)
pp = &(*pp)->rb_left;
else if (cursor->proto.index_key > k.index_key)
pp = &(*pp)->rb_right;
else
goto found_extant_conn;
}
rb_link_node_rcu(&conn->service_node, parent, pp);
rb_insert_color(&conn->service_node, &peer->service_conns);
conn_published:
set_bit(RXRPC_CONN_IN_SERVICE_CONNS, &conn->flags);
write_sequnlock_bh(&peer->service_conn_lock);
_leave(" = %d [new]", conn->debug_id);
return;
found_extant_conn:
if (atomic_read(&cursor->usage) == 0)
goto replace_old_connection;
write_sequnlock_bh(&peer->service_conn_lock);
/* We should not be able to get here. rxrpc_incoming_connection() is
* called in a non-reentrant context, so there can't be a race to
* insert a new connection.
*/
BUG();
replace_old_connection:
/* The old connection is from an outdated epoch. */
_debug("replace conn");
rb_replace_node_rcu(&cursor->service_node,
&conn->service_node,
&peer->service_conns);
clear_bit(RXRPC_CONN_IN_SERVICE_CONNS, &cursor->flags);
goto conn_published;
}
/*
* Preallocate a service connection. The connection is placed on the proc and
* reap lists so that we don't have to get the lock from BH context.
*/
struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxnet,
gfp_t gfp)
{
struct rxrpc_connection *conn = rxrpc_alloc_connection(gfp);
if (conn) {
/* We maintain an extra ref on the connection whilst it is on
* the rxrpc_connections list.
*/
conn->state = RXRPC_CONN_SERVICE_PREALLOC;
atomic_set(&conn->usage, 2);
atomic_inc(&rxnet->nr_conns);
write_lock(&rxnet->conn_lock);
list_add_tail(&conn->link, &rxnet->service_conns);
list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
write_unlock(&rxnet->conn_lock);
trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service,
atomic_read(&conn->usage),
__builtin_return_address(0));
}
return conn;
}
/*
* Set up an incoming connection. This is called in BH context with the RCU
* read lock held.
*/
void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
_enter("");
conn->proto.epoch = sp->hdr.epoch;
conn->proto.cid = sp->hdr.cid & RXRPC_CIDMASK;
conn->params.service_id = sp->hdr.serviceId;
conn->service_id = sp->hdr.serviceId;
conn->security_ix = sp->hdr.securityIndex;
conn->out_clientflag = 0;
if (conn->security_ix)
conn->state = RXRPC_CONN_SERVICE_UNSECURED;
else
conn->state = RXRPC_CONN_SERVICE;
/* See if we should upgrade the service. This can only happen on the
* first packet on a new connection. Once done, it applies to all
* subsequent calls on that connection.
*/
if (sp->hdr.userStatus == RXRPC_USERSTATUS_SERVICE_UPGRADE &&
conn->service_id == rx->service_upgrade.from)
conn->service_id = rx->service_upgrade.to;
/* Make the connection a target for incoming packets. */
rxrpc_publish_service_conn(conn->params.peer, conn);
_net("CONNECTION new %d {%x}", conn->debug_id, conn->proto.cid);
}
/*
* Remove the service connection from the peer's tree, thereby removing it as a
* target for incoming packets.
*/
void rxrpc_unpublish_service_conn(struct rxrpc_connection *conn)
{
struct rxrpc_peer *peer = conn->params.peer;
write_seqlock_bh(&peer->service_conn_lock);
if (test_and_clear_bit(RXRPC_CONN_IN_SERVICE_CONNS, &conn->flags))
rb_erase(&conn->service_node, &peer->service_conns);
write_sequnlock_bh(&peer->service_conn_lock);
}
+1456
View File
File diff suppressed because it is too large. Load diff
+96
View File
@@ -0,0 +1,96 @@
/* Null security operations.
*
* Copyright (C) 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.
*/
#include <net/af_rxrpc.h>
#include "ar-internal.h"
static int none_init_connection_security(struct rxrpc_connection *conn)
{
return 0;
}
static int none_prime_packet_security(struct rxrpc_connection *conn)
{
return 0;
}
static int none_secure_packet(struct rxrpc_call *call,
struct sk_buff *skb,
size_t data_size,
void *sechdr)
{
return 0;
}
static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
unsigned int offset, unsigned int len,
rxrpc_seq_t seq, u16 expected_cksum)
{
return 0;
}
static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
unsigned int *_offset, unsigned int *_len)
{
}
static int none_respond_to_challenge(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("chall_none"));
return -EPROTO;
}
static int none_verify_response(struct rxrpc_connection *conn,
struct sk_buff *skb,
u32 *_abort_code)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
trace_rxrpc_rx_eproto(NULL, sp->hdr.serial,
tracepoint_string("resp_none"));
return -EPROTO;
}
static void none_clear(struct rxrpc_connection *conn)
{
}
static int none_init(void)
{
return 0;
}
static void none_exit(void)
{
}
/*
* RxRPC Kerberos-based security
*/
const struct rxrpc_security rxrpc_no_security = {
.name = "none",
.security_index = RXRPC_SECURITY_NONE,
.init = none_init,
.exit = none_exit,
.init_connection_security = none_init_connection_security,
.prime_packet_security = none_prime_packet_security,
.secure_packet = none_secure_packet,
.verify_packet = none_verify_packet,
.locate_data = none_locate_data,
.respond_to_challenge = none_respond_to_challenge,
.verify_response = none_verify_response,
.clear = none_clear,
};
+1248
View File
File diff suppressed because it is too large. Load diff
+119
View File
@@ -0,0 +1,119 @@
/* AF_RXRPC local endpoint management
*
* 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <generated/utsrelease.h>
#include "ar-internal.h"
static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC";
/*
* Reply to a version request
*/
static void rxrpc_send_version_request(struct rxrpc_local *local,
struct rxrpc_host_header *hdr,
struct sk_buff *skb)
{
struct rxrpc_wire_header whdr;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct sockaddr_rxrpc srx;
struct msghdr msg;
struct kvec iov[2];
size_t len;
int ret;
_enter("");
if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
return;
msg.msg_name = &srx.transport;
msg.msg_namelen = srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
whdr.epoch = htonl(sp->hdr.epoch);
whdr.cid = htonl(sp->hdr.cid);
whdr.callNumber = htonl(sp->hdr.callNumber);
whdr.seq = 0;
whdr.serial = 0;
whdr.type = RXRPC_PACKET_TYPE_VERSION;
whdr.flags = RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
whdr.userStatus = 0;
whdr.securityIndex = 0;
whdr._rsvd = 0;
whdr.serviceId = htons(sp->hdr.serviceId);
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = (char *)rxrpc_version_string;
iov[1].iov_len = sizeof(rxrpc_version_string);
len = iov[0].iov_len + iov[1].iov_len;
_proto("Tx VERSION (reply)");
ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
if (ret < 0)
trace_rxrpc_tx_fail(local->debug_id, 0, ret,
rxrpc_tx_point_version_reply);
else
trace_rxrpc_tx_packet(local->debug_id, &whdr,
rxrpc_tx_point_version_reply);
_leave("");
}
/*
* Process event packets targetted at a local endpoint.
*/
void rxrpc_process_local_events(struct rxrpc_local *local)
{
struct sk_buff *skb;
char v;
_enter("");
skb = skb_dequeue(&local->event_queue);
if (skb) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
_debug("{%d},{%u}", local->debug_id, sp->hdr.type);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
&v, 1) < 0)
return;
_proto("Rx VERSION { %02x }", v);
if (v == 0)
rxrpc_send_version_request(local, &sp->hdr, skb);
break;
default:
/* Just ignore anything we don't understand */
break;
}
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
}
_leave("");
}
+517
View File
@@ -0,0 +1,517 @@
/* Local endpoint object management
*
* Copyright (C) 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/udp.h>
#include <linux/ip.h>
#include <linux/hashtable.h>
#include <net/sock.h>
#include <net/udp.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
static void rxrpc_local_processor(struct work_struct *);
static void rxrpc_local_rcu(struct rcu_head *);
/*
* Compare a local to an address. Return -ve, 0 or +ve to indicate less than,
* same or greater than.
*
* We explicitly don't compare the RxRPC service ID as we want to reject
* conflicting uses by differing services. Further, we don't want to share
* addresses with different options (IPv6), so we don't compare those bits
* either.
*/
static long rxrpc_local_cmp_key(const struct rxrpc_local *local,
const struct sockaddr_rxrpc *srx)
{
long diff;
diff = ((local->srx.transport_type - srx->transport_type) ?:
(local->srx.transport_len - srx->transport_len) ?:
(local->srx.transport.family - srx->transport.family));
if (diff != 0)
return diff;
switch (srx->transport.family) {
case AF_INET:
/* If the choice of UDP port is left up to the transport, then
* the endpoint record doesn't match.
*/
return ((u16 __force)local->srx.transport.sin.sin_port -
(u16 __force)srx->transport.sin.sin_port) ?:
memcmp(&local->srx.transport.sin.sin_addr,
&srx->transport.sin.sin_addr,
sizeof(struct in_addr));
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
/* If the choice of UDP6 port is left up to the transport, then
* the endpoint record doesn't match.
*/
return ((u16 __force)local->srx.transport.sin6.sin6_port -
(u16 __force)srx->transport.sin6.sin6_port) ?:
memcmp(&local->srx.transport.sin6.sin6_addr,
&srx->transport.sin6.sin6_addr,
sizeof(struct in6_addr));
#endif
default:
BUG();
}
}
/*
* Allocate a new local endpoint.
*/
static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
atomic_set(&local->usage, 1);
atomic_set(&local->active_users, 1);
local->rxnet = rxnet;
INIT_LIST_HEAD(&local->link);
INIT_WORK(&local->processor, rxrpc_local_processor);
init_rwsem(&local->defrag_sem);
skb_queue_head_init(&local->reject_queue);
skb_queue_head_init(&local->event_queue);
local->client_conns = RB_ROOT;
spin_lock_init(&local->client_conns_lock);
spin_lock_init(&local->lock);
rwlock_init(&local->services_lock);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
local->srx.srx_service = 0;
trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL);
}
_leave(" = %p", local);
return local;
}
/*
* create the local socket
* - must be called with rxrpc_local_mutex locked
*/
static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
{
struct sock *usk;
int ret, opt;
_enter("%p{%d,%d}",
local, local->srx.transport_type, local->srx.transport.family);
/* create a socket to represent the local endpoint */
ret = sock_create_kern(net, local->srx.transport.family,
local->srx.transport_type, 0, &local->socket);
if (ret < 0) {
_leave(" = %d [socket]", ret);
return ret;
}
/* set the socket up */
usk = local->socket->sk;
inet_sk(usk)->mc_loop = 0;
/* Enable CHECKSUM_UNNECESSARY to CHECKSUM_COMPLETE conversion */
inet_inc_convert_csum(usk);
rcu_assign_sk_user_data(usk, local);
udp_sk(usk)->encap_type = UDP_ENCAP_RXRPC;
udp_sk(usk)->encap_rcv = rxrpc_input_packet;
udp_sk(usk)->encap_destroy = NULL;
udp_sk(usk)->gro_receive = NULL;
udp_sk(usk)->gro_complete = NULL;
udp_encap_enable();
#if IS_ENABLED(CONFIG_AF_RXRPC_IPV6)
if (local->srx.transport.family == AF_INET6)
udpv6_encap_enable();
#endif
usk->sk_error_report = rxrpc_error_report;
/* if a local address was supplied then bind it */
if (local->srx.transport_len > sizeof(sa_family_t)) {
_debug("bind");
ret = kernel_bind(local->socket,
(struct sockaddr *)&local->srx.transport,
local->srx.transport_len);
if (ret < 0) {
_debug("bind failed %d", ret);
goto error;
}
}
switch (local->srx.transport.family) {
case AF_INET6:
/* we want to receive ICMPv6 errors */
opt = 1;
ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
/* Fall through and set IPv4 options too otherwise we don't get
* errors from IPv4 packets sent through the IPv6 socket.
*/
case AF_INET:
/* we want to receive ICMP errors */
opt = 1;
ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
/* we want to set the don't fragment bit */
opt = IP_PMTUDISC_DO;
ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER,
(char *) &opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
/* We want receive timestamps. */
opt = 1;
ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS,
(char *)&opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
}
break;
default:
BUG();
}
_leave(" = 0");
return 0;
error:
kernel_sock_shutdown(local->socket, SHUT_RDWR);
local->socket->sk->sk_user_data = NULL;
sock_release(local->socket);
local->socket = NULL;
_leave(" = %d", ret);
return ret;
}
/*
* Look up or create a new local endpoint using the specified local address.
*/
struct rxrpc_local *rxrpc_lookup_local(struct net *net,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
struct rxrpc_net *rxnet = rxrpc_net(net);
struct list_head *cursor;
const char *age;
long diff;
int ret;
_enter("{%d,%d,%pISp}",
srx->transport_type, srx->transport.family, &srx->transport);
mutex_lock(&rxnet->local_mutex);
for (cursor = rxnet->local_endpoints.next;
cursor != &rxnet->local_endpoints;
cursor = cursor->next) {
local = list_entry(cursor, struct rxrpc_local, link);
diff = rxrpc_local_cmp_key(local, srx);
if (diff < 0)
continue;
if (diff > 0)
break;
/* Services aren't allowed to share transport sockets, so
* reject that here. It is possible that the object is dying -
* but it may also still have the local transport address that
* we want bound.
*/
if (srx->srx_service) {
local = NULL;
goto addr_in_use;
}
/* Found a match. We replace a dying object. Attempting to
* bind the transport socket may still fail if we're attempting
* to use a local address that the dying object is still using.
*/
if (!rxrpc_use_local(local))
break;
age = "old";
goto found;
}
local = rxrpc_alloc_local(rxnet, srx);
if (!local)
goto nomem;
ret = rxrpc_open_socket(local, net);
if (ret < 0)
goto sock_error;
if (cursor != &rxnet->local_endpoints)
list_replace_init(cursor, &local->link);
else
list_add_tail(&local->link, cursor);
age = "new";
found:
mutex_unlock(&rxnet->local_mutex);
_net("LOCAL %s %d {%pISp}",
age, local->debug_id, &local->srx.transport);
_leave(" = %p", local);
return local;
nomem:
ret = -ENOMEM;
sock_error:
mutex_unlock(&rxnet->local_mutex);
if (local)
call_rcu(&local->rcu, rxrpc_local_rcu);
_leave(" = %d", ret);
return ERR_PTR(ret);
addr_in_use:
mutex_unlock(&rxnet->local_mutex);
_leave(" = -EADDRINUSE");
return ERR_PTR(-EADDRINUSE);
}
/*
* Get a ref on a local endpoint.
*/
struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
int n;
n = atomic_inc_return(&local->usage);
trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here);
return local;
}
/*
* Get a ref on a local endpoint unless its usage has already reached 0.
*/
struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
if (local) {
int n = atomic_fetch_add_unless(&local->usage, 1, 0);
if (n > 0)
trace_rxrpc_local(local->debug_id, rxrpc_local_got,
n + 1, here);
else
local = NULL;
}
return local;
}
/*
* Queue a local endpoint and pass the caller's reference to the work item.
*/
void rxrpc_queue_local(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
unsigned int debug_id = local->debug_id;
int n = atomic_read(&local->usage);
if (rxrpc_queue_work(&local->processor))
trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here);
else
rxrpc_put_local(local);
}
/*
* Drop a ref on a local endpoint.
*/
void rxrpc_put_local(struct rxrpc_local *local)
{
const void *here = __builtin_return_address(0);
unsigned int debug_id;
int n;
if (local) {
debug_id = local->debug_id;
n = atomic_dec_return(&local->usage);
trace_rxrpc_local(debug_id, rxrpc_local_put, n, here);
if (n == 0)
call_rcu(&local->rcu, rxrpc_local_rcu);
}
}
/*
* Start using a local endpoint.
*/
struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local)
{
local = rxrpc_get_local_maybe(local);
if (!local)
return NULL;
if (!__rxrpc_use_local(local)) {
rxrpc_put_local(local);
return NULL;
}
return local;
}
/*
* Cease using a local endpoint. Once the number of active users reaches 0, we
* start the closure of the transport in the work processor.
*/
void rxrpc_unuse_local(struct rxrpc_local *local)
{
if (local) {
if (__rxrpc_unuse_local(local)) {
rxrpc_get_local(local);
rxrpc_queue_local(local);
}
}
}
/*
* Destroy a local endpoint's socket and then hand the record to RCU to dispose
* of.
*
* Closing the socket cannot be done from bottom half context or RCU callback
* context because it might sleep.
*/
static void rxrpc_local_destroyer(struct rxrpc_local *local)
{
struct socket *socket = local->socket;
struct rxrpc_net *rxnet = local->rxnet;
_enter("%d", local->debug_id);
local->dead = true;
mutex_lock(&rxnet->local_mutex);
list_del_init(&local->link);
mutex_unlock(&rxnet->local_mutex);
rxrpc_clean_up_local_conns(local);
rxrpc_service_connection_reaper(&rxnet->service_conn_reaper);
ASSERT(!local->service);
if (socket) {
local->socket = NULL;
kernel_sock_shutdown(socket, SHUT_RDWR);
socket->sk->sk_user_data = NULL;
sock_release(socket);
}
/* At this point, there should be no more packets coming in to the
* local endpoint.
*/
rxrpc_purge_queue(&local->reject_queue);
rxrpc_purge_queue(&local->event_queue);
}
/*
* Process events on an endpoint. The work item carries a ref which
* we must release.
*/
static void rxrpc_local_processor(struct work_struct *work)
{
struct rxrpc_local *local =
container_of(work, struct rxrpc_local, processor);
bool again;
trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
atomic_read(&local->usage), NULL);
do {
again = false;
if (!__rxrpc_use_local(local)) {
rxrpc_local_destroyer(local);
break;
}
if (!skb_queue_empty(&local->reject_queue)) {
rxrpc_reject_packets(local);
again = true;
}
if (!skb_queue_empty(&local->event_queue)) {
rxrpc_process_local_events(local);
again = true;
}
__rxrpc_unuse_local(local);
} while (again);
rxrpc_put_local(local);
}
/*
* Destroy a local endpoint after the RCU grace period expires.
*/
static void rxrpc_local_rcu(struct rcu_head *rcu)
{
struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu);
_enter("%d", local->debug_id);
ASSERT(!work_pending(&local->processor));
_net("DESTROY LOCAL %d", local->debug_id);
kfree(local);
_leave("");
}
/*
* Verify the local endpoint list is empty by this point.
*/
void rxrpc_destroy_all_locals(struct rxrpc_net *rxnet)
{
struct rxrpc_local *local;
_enter("");
flush_workqueue(rxrpc_workqueue);
if (!list_empty(&rxnet->local_endpoints)) {
mutex_lock(&rxnet->local_mutex);
list_for_each_entry(local, &rxnet->local_endpoints, link) {
pr_err("AF_RXRPC: Leaked local %p {%d}\n",
local, atomic_read(&local->usage));
}
mutex_unlock(&rxnet->local_mutex);
BUG();
}
}
+85
View File
@@ -0,0 +1,85 @@
/* Miscellaneous bits
*
* Copyright (C) 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.
*/
#include <linux/kernel.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
/*
* The maximum listening backlog queue size that may be set on a socket by
* listen().
*/
unsigned int rxrpc_max_backlog __read_mostly = 10;
/*
* How long to wait before scheduling ACK generation after seeing a
* packet with RXRPC_REQUEST_ACK set (in jiffies).
*/
unsigned long rxrpc_requested_ack_delay = 1;
/*
* How long to wait before scheduling an ACK with subtype DELAY (in jiffies).
*
* We use this when we've received new data packets. If those packets aren't
* all consumed within this time we will send a DELAY ACK if an ACK was not
* requested to let the sender know it doesn't need to resend.
*/
unsigned long rxrpc_soft_ack_delay = HZ;
/*
* How long to wait before scheduling an ACK with subtype IDLE (in jiffies).
*
* We use this when we've consumed some previously soft-ACK'd packets when
* further packets aren't immediately received to decide when to send an IDLE
* ACK let the other end know that it can free up its Tx buffer space.
*/
unsigned long rxrpc_idle_ack_delay = HZ / 2;
/*
* Receive window size in packets. This indicates the maximum number of
* unconsumed received packets we're willing to retain in memory. Once this
* limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further
* packets.
*/
unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE;
#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE
#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE
#endif
/*
* Maximum Rx MTU size. This indicates to the sender the size of jumbo packet
* made by gluing normal packets together that we're willing to handle.
*/
unsigned int rxrpc_rx_mtu = 5692;
/*
* The maximum number of fragments in a received jumbo packet that we tell the
* sender that we're willing to handle.
*/
unsigned int rxrpc_rx_jumbo_max = 4;
/*
* Time till packet resend (in milliseconds).
*/
unsigned long rxrpc_resend_timeout = 4 * HZ;
const s8 rxrpc_ack_priority[] = {
[0] = 0,
[RXRPC_ACK_DELAY] = 1,
[RXRPC_ACK_REQUESTED] = 2,
[RXRPC_ACK_IDLE] = 3,
[RXRPC_ACK_DUPLICATE] = 4,
[RXRPC_ACK_OUT_OF_SEQUENCE] = 5,
[RXRPC_ACK_EXCEEDS_WINDOW] = 6,
[RXRPC_ACK_NOSPACE] = 7,
[RXRPC_ACK_PING_RESPONSE] = 8,
};
+134
View File
@@ -0,0 +1,134 @@
/* rxrpc network namespace handling.
*
* Copyright (C) 2017 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.
*/
#include <linux/proc_fs.h>
#include "ar-internal.h"
unsigned int rxrpc_net_id;
static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, client_conn_reap_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->client_conn_reaper);
}
static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, service_conn_reap_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->service_conn_reaper);
}
static void rxrpc_peer_keepalive_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, peer_keepalive_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->peer_keepalive_work);
}
/*
* Initialise a per-network namespace record.
*/
static __net_init int rxrpc_init_net(struct net *net)
{
struct rxrpc_net *rxnet = rxrpc_net(net);
int ret, i;
rxnet->live = true;
get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch));
rxnet->epoch |= RXRPC_RANDOM_EPOCH;
INIT_LIST_HEAD(&rxnet->calls);
rwlock_init(&rxnet->call_lock);
atomic_set(&rxnet->nr_calls, 1);
atomic_set(&rxnet->nr_conns, 1);
INIT_LIST_HEAD(&rxnet->conn_proc_list);
INIT_LIST_HEAD(&rxnet->service_conns);
rwlock_init(&rxnet->conn_lock);
INIT_WORK(&rxnet->service_conn_reaper,
rxrpc_service_connection_reaper);
timer_setup(&rxnet->service_conn_reap_timer,
rxrpc_service_conn_reap_timeout, 0);
rxnet->nr_client_conns = 0;
rxnet->nr_active_client_conns = 0;
rxnet->kill_all_client_conns = false;
spin_lock_init(&rxnet->client_conn_cache_lock);
spin_lock_init(&rxnet->client_conn_discard_lock);
INIT_LIST_HEAD(&rxnet->waiting_client_conns);
INIT_LIST_HEAD(&rxnet->active_client_conns);
INIT_LIST_HEAD(&rxnet->idle_client_conns);
INIT_WORK(&rxnet->client_conn_reaper,
rxrpc_discard_expired_client_conns);
timer_setup(&rxnet->client_conn_reap_timer,
rxrpc_client_conn_reap_timeout, 0);
INIT_LIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
hash_init(rxnet->peer_hash);
spin_lock_init(&rxnet->peer_hash_lock);
for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
timer_setup(&rxnet->peer_keepalive_timer,
rxrpc_peer_keepalive_timeout, 0);
INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
rxnet->peer_keepalive_base = ktime_get_seconds();
ret = -ENOMEM;
rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
if (!rxnet->proc_net)
goto err_proc;
proc_create_net("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_ops,
sizeof(struct seq_net_private));
proc_create_net("conns", 0444, rxnet->proc_net,
&rxrpc_connection_seq_ops,
sizeof(struct seq_net_private));
return 0;
err_proc:
rxnet->live = false;
return ret;
}
/*
* Clean up a per-network namespace record.
*/
static __net_exit void rxrpc_exit_net(struct net *net)
{
struct rxrpc_net *rxnet = rxrpc_net(net);
rxnet->live = false;
del_timer_sync(&rxnet->peer_keepalive_timer);
cancel_work_sync(&rxnet->peer_keepalive_work);
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_peers(rxnet);
rxrpc_destroy_all_locals(rxnet);
proc_remove(rxnet->proc_net);
}
struct pernet_operations rxrpc_net_ops = {
.init = rxrpc_init_net,
.exit = rxrpc_exit_net,
.id = &rxrpc_net_id,
.size = sizeof(struct rxrpc_net),
};
+642
View File
@@ -0,0 +1,642 @@
/* RxRPC packet transmission
*
* 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/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"
struct rxrpc_ack_buffer {
struct rxrpc_wire_header whdr;
struct rxrpc_ackpacket ack;
u8 acks[255];
u8 pad[3];
struct rxrpc_ackinfo ackinfo;
};
struct rxrpc_abort_buffer {
struct rxrpc_wire_header whdr;
__be32 abort_code;
};
static const char rxrpc_keepalive_string[] = "";
/*
* Increase Tx backoff on transmission failure and clear it on success.
*/
static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret)
{
if (ret < 0) {
u16 tx_backoff = READ_ONCE(call->tx_backoff);
if (tx_backoff < HZ)
WRITE_ONCE(call->tx_backoff, tx_backoff + 1);
} else {
WRITE_ONCE(call->tx_backoff, 0);
}
}
/*
* Arrange for a keepalive ping a certain time after we last transmitted. This
* lets the far side know we're still interested in this call and helps keep
* the route through any intervening firewall open.
*
* Receiving a response to the ping will prevent the ->expect_rx_by timer from
* expiring.
*/
static void rxrpc_set_keepalive(struct rxrpc_call *call)
{
unsigned long now = jiffies, keepalive_at = call->next_rx_timo / 6;
keepalive_at += now;
WRITE_ONCE(call->keepalive_at, keepalive_at);
rxrpc_reduce_call_timer(call, keepalive_at, now,
rxrpc_timer_set_for_keepalive);
}
/*
* Fill out an ACK packet.
*/
static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn,
struct rxrpc_call *call,
struct rxrpc_ack_buffer *pkt,
rxrpc_seq_t *_hard_ack,
rxrpc_seq_t *_top,
u8 reason)
{
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top, seq;
int ix;
u32 mtu, jmax;
u8 *ackp = pkt->acks;
/* Barrier against rxrpc_input_data(). */
serial = call->ackr_serial;
hard_ack = READ_ONCE(call->rx_hard_ack);
top = smp_load_acquire(&call->rx_top);
*_hard_ack = hard_ack;
*_top = top;
pkt->ack.bufferSpace = htons(8);
pkt->ack.maxSkew = htons(call->ackr_skew);
pkt->ack.firstPacket = htonl(hard_ack + 1);
pkt->ack.previousPacket = htonl(call->ackr_prev_seq);
pkt->ack.serial = htonl(serial);
pkt->ack.reason = reason;
pkt->ack.nAcks = top - hard_ack;
if (reason == RXRPC_ACK_PING)
pkt->whdr.flags |= RXRPC_REQUEST_ACK;
if (after(top, hard_ack)) {
seq = hard_ack + 1;
do {
ix = seq & RXRPC_RXTX_BUFF_MASK;
if (call->rxtx_buffer[ix])
*ackp++ = RXRPC_ACK_TYPE_ACK;
else
*ackp++ = RXRPC_ACK_TYPE_NACK;
seq++;
} while (before_eq(seq, top));
}
mtu = conn->params.peer->if_mtu;
mtu -= conn->params.peer->hdrsize;
jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max;
pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu);
pkt->ackinfo.maxMTU = htonl(mtu);
pkt->ackinfo.rwind = htonl(call->rx_winsize);
pkt->ackinfo.jumbo_max = htonl(jmax);
*ackp++ = 0;
*ackp++ = 0;
*ackp++ = 0;
return top - hard_ack + 3;
}
/*
* Send an ACK call packet.
*/
int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
rxrpc_serial_t *_serial)
{
struct rxrpc_connection *conn;
struct rxrpc_ack_buffer *pkt;
struct msghdr msg;
struct kvec iov[2];
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
size_t len, n;
int ret;
u8 reason;
if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
return -ECONNRESET;
pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
if (!pkt)
return -ENOMEM;
conn = call->conn;
msg.msg_name = &call->peer->srx.transport;
msg.msg_namelen = call->peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
pkt->whdr.epoch = htonl(conn->proto.epoch);
pkt->whdr.cid = htonl(call->cid);
pkt->whdr.callNumber = htonl(call->call_id);
pkt->whdr.seq = 0;
pkt->whdr.type = RXRPC_PACKET_TYPE_ACK;
pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag;
pkt->whdr.userStatus = 0;
pkt->whdr.securityIndex = call->security_ix;
pkt->whdr._rsvd = 0;
pkt->whdr.serviceId = htons(call->service_id);
spin_lock_bh(&call->lock);
if (ping) {
reason = RXRPC_ACK_PING;
} else {
reason = call->ackr_reason;
if (!call->ackr_reason) {
spin_unlock_bh(&call->lock);
ret = 0;
goto out;
}
call->ackr_reason = 0;
}
n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason);
spin_unlock_bh(&call->lock);
iov[0].iov_base = pkt;
iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n;
iov[1].iov_base = &pkt->ackinfo;
iov[1].iov_len = sizeof(pkt->ackinfo);
len = iov[0].iov_len + iov[1].iov_len;
serial = atomic_inc_return(&conn->serial);
pkt->whdr.serial = htonl(serial);
trace_rxrpc_tx_ack(call->debug_id, serial,
ntohl(pkt->ack.firstPacket),
ntohl(pkt->ack.serial),
pkt->ack.reason, pkt->ack.nAcks);
if (_serial)
*_serial = serial;
if (ping) {
call->ping_serial = serial;
smp_wmb();
/* We need to stick a time in before we send the packet in case
* the reply gets back before kernel_sendmsg() completes - but
* asking UDP to send the packet can take a relatively long
* time.
*/
call->ping_time = ktime_get_real();
set_bit(RXRPC_CALL_PINGING, &call->flags);
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial);
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_point_call_ack);
else
trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr,
rxrpc_tx_point_call_ack);
rxrpc_tx_backoff(call, ret);
if (call->state < RXRPC_CALL_COMPLETE) {
if (ret < 0) {
if (ping)
clear_bit(RXRPC_CALL_PINGING, &call->flags);
rxrpc_propose_ACK(call, pkt->ack.reason,
ntohs(pkt->ack.maxSkew),
ntohl(pkt->ack.serial),
false, true,
rxrpc_propose_ack_retry_tx);
} else {
spin_lock_bh(&call->lock);
if (after(hard_ack, call->ackr_consumed))
call->ackr_consumed = hard_ack;
if (after(top, call->ackr_seen))
call->ackr_seen = top;
spin_unlock_bh(&call->lock);
}
rxrpc_set_keepalive(call);
}
out:
kfree(pkt);
return ret;
}
/*
* Send an ABORT call packet.
*/
int rxrpc_send_abort_packet(struct rxrpc_call *call)
{
struct rxrpc_connection *conn;
struct rxrpc_abort_buffer pkt;
struct msghdr msg;
struct kvec iov[1];
rxrpc_serial_t serial;
int ret;
/* Don't bother sending aborts for a client call once the server has
* hard-ACK'd all of its request data. After that point, we're not
* going to stop the operation proceeding, and whilst we might limit
* the reply, it's not worth it if we can send a new call on the same
* channel instead, thereby closing off this call.
*/
if (rxrpc_is_client_call(call) &&
test_bit(RXRPC_CALL_TX_LAST, &call->flags))
return 0;
if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags))
return -ECONNRESET;
conn = call->conn;
msg.msg_name = &call->peer->srx.transport;
msg.msg_namelen = call->peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
pkt.whdr.epoch = htonl(conn->proto.epoch);
pkt.whdr.cid = htonl(call->cid);
pkt.whdr.callNumber = htonl(call->call_id);
pkt.whdr.seq = 0;
pkt.whdr.type = RXRPC_PACKET_TYPE_ABORT;
pkt.whdr.flags = conn->out_clientflag;
pkt.whdr.userStatus = 0;
pkt.whdr.securityIndex = call->security_ix;
pkt.whdr._rsvd = 0;
pkt.whdr.serviceId = htons(call->service_id);
pkt.abort_code = htonl(call->abort_code);
iov[0].iov_base = &pkt;
iov[0].iov_len = sizeof(pkt);
serial = atomic_inc_return(&conn->serial);
pkt.whdr.serial = htonl(serial);
ret = kernel_sendmsg(conn->params.local->socket,
&msg, iov, 1, sizeof(pkt));
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_point_call_abort);
else
trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
rxrpc_tx_point_call_abort);
rxrpc_tx_backoff(call, ret);
return ret;
}
/*
* send a packet through the transport endpoint
*/
int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
bool retrans)
{
struct rxrpc_connection *conn = call->conn;
struct rxrpc_wire_header whdr;
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
struct msghdr msg;
struct kvec iov[2];
rxrpc_serial_t serial;
size_t len;
bool lost = false;
int ret, opt;
_enter(",{%d}", skb->len);
/* Each transmission of a Tx packet needs a new serial number */
serial = atomic_inc_return(&conn->serial);
whdr.epoch = htonl(conn->proto.epoch);
whdr.cid = htonl(call->cid);
whdr.callNumber = htonl(call->call_id);
whdr.seq = htonl(sp->hdr.seq);
whdr.serial = htonl(serial);
whdr.type = RXRPC_PACKET_TYPE_DATA;
whdr.flags = sp->hdr.flags;
whdr.userStatus = 0;
whdr.securityIndex = call->security_ix;
whdr._rsvd = htons(sp->hdr._rsvd);
whdr.serviceId = htons(call->service_id);
if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) &&
sp->hdr.seq == 1)
whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE;
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = skb->head;
iov[1].iov_len = skb->len;
len = iov[0].iov_len + iov[1].iov_len;
msg.msg_name = &call->peer->srx.transport;
msg.msg_namelen = call->peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
/* If our RTT cache needs working on, request an ACK. Also request
* ACKs if a DATA packet appears to have been lost.
*
* However, we mustn't request an ACK on the last reply packet of a
* service call, lest OpenAFS incorrectly send us an ACK with some
* soft-ACKs in it and then never follow up with a proper hard ACK.
*/
if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) ||
rxrpc_to_server(sp)
) &&
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
(call->peer->rtt_usage < 3 && sp->hdr.seq & 1) ||
ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000),
ktime_get_real())))
whdr.flags |= RXRPC_REQUEST_ACK;
if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
static int lose;
if ((lose++ & 7) == 7) {
ret = 0;
lost = true;
goto done;
}
}
_proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq);
/* send the packet with the don't fragment bit set if we currently
* think it's small enough */
if (iov[1].iov_len >= call->peer->maxdata)
goto send_fragmentable;
down_read(&conn->params.local->defrag_sem);
sp->hdr.serial = serial;
smp_wmb(); /* Set serial before timestamp */
skb->tstamp = ktime_get_real();
/* send the packet by UDP
* - returns -EMSGSIZE if UDP would have to fragment the packet
* to go out of the interface
* - in which case, we'll have processed the ICMP error
* message and update the peer record
*/
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
conn->params.peer->last_tx_at = ktime_get_seconds();
up_read(&conn->params.local->defrag_sem);
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_point_call_data_nofrag);
else
trace_rxrpc_tx_packet(call->debug_id, &whdr,
rxrpc_tx_point_call_data_nofrag);
rxrpc_tx_backoff(call, ret);
if (ret == -EMSGSIZE)
goto send_fragmentable;
done:
trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
retrans, lost);
if (ret >= 0) {
if (whdr.flags & RXRPC_REQUEST_ACK) {
call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
if (call->peer->rtt_usage > 1) {
unsigned long nowj = jiffies, ack_lost_at;
ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt);
if (ack_lost_at < 1)
ack_lost_at = 1;
ack_lost_at += nowj;
WRITE_ONCE(call->ack_lost_at, ack_lost_at);
rxrpc_reduce_call_timer(call, ack_lost_at, nowj,
rxrpc_timer_set_for_lost_ack);
}
}
if (sp->hdr.seq == 1 &&
!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER,
&call->flags)) {
unsigned long nowj = jiffies, expect_rx_by;
expect_rx_by = nowj + call->next_rx_timo;
WRITE_ONCE(call->expect_rx_by, expect_rx_by);
rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
rxrpc_timer_set_for_normal);
}
rxrpc_set_keepalive(call);
} else {
/* Cancel the call if the initial transmission fails,
* particularly if that's due to network routing issues that
* aren't going away anytime soon. The layer above can arrange
* the retransmission.
*/
if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags))
rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
RX_USER_ABORT, ret);
}
_leave(" = %d [%u]", ret, call->peer->maxdata);
return ret;
send_fragmentable:
/* attempt to send this message with fragmentation enabled */
_debug("send fragment");
down_write(&conn->params.local->defrag_sem);
sp->hdr.serial = serial;
smp_wmb(); /* Set serial before timestamp */
skb->tstamp = ktime_get_real();
switch (conn->params.local->srx.transport.family) {
case AF_INET6:
case AF_INET:
opt = IP_PMTUDISC_DONT;
kernel_setsockopt(conn->params.local->socket,
SOL_IP, IP_MTU_DISCOVER,
(char *)&opt, sizeof(opt));
ret = kernel_sendmsg(conn->params.local->socket, &msg,
iov, 2, len);
conn->params.peer->last_tx_at = ktime_get_seconds();
opt = IP_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket,
SOL_IP, IP_MTU_DISCOVER,
(char *)&opt, sizeof(opt));
break;
default:
BUG();
}
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
rxrpc_tx_point_call_data_frag);
else
trace_rxrpc_tx_packet(call->debug_id, &whdr,
rxrpc_tx_point_call_data_frag);
rxrpc_tx_backoff(call, ret);
up_write(&conn->params.local->defrag_sem);
goto done;
}
/*
* reject packets through the local endpoint
*/
void rxrpc_reject_packets(struct rxrpc_local *local)
{
struct sockaddr_rxrpc srx;
struct rxrpc_skb_priv *sp;
struct rxrpc_wire_header whdr;
struct sk_buff *skb;
struct msghdr msg;
struct kvec iov[2];
size_t size;
__be32 code;
int ret, ioc;
_enter("%d", local->debug_id);
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = &code;
iov[1].iov_len = sizeof(code);
msg.msg_name = &srx.transport;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
memset(&whdr, 0, sizeof(whdr));
while ((skb = skb_dequeue(&local->reject_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
sp = rxrpc_skb(skb);
switch (skb->mark) {
case RXRPC_SKB_MARK_REJECT_BUSY:
whdr.type = RXRPC_PACKET_TYPE_BUSY;
size = sizeof(whdr);
ioc = 1;
break;
case RXRPC_SKB_MARK_REJECT_ABORT:
whdr.type = RXRPC_PACKET_TYPE_ABORT;
code = htonl(skb->priority);
size = sizeof(whdr) + sizeof(code);
ioc = 2;
break;
default:
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
continue;
}
if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) {
msg.msg_namelen = srx.transport_len;
whdr.epoch = htonl(sp->hdr.epoch);
whdr.cid = htonl(sp->hdr.cid);
whdr.callNumber = htonl(sp->hdr.callNumber);
whdr.serviceId = htons(sp->hdr.serviceId);
whdr.flags = sp->hdr.flags;
whdr.flags ^= RXRPC_CLIENT_INITIATED;
whdr.flags &= RXRPC_CLIENT_INITIATED;
ret = kernel_sendmsg(local->socket, &msg,
iov, ioc, size);
if (ret < 0)
trace_rxrpc_tx_fail(local->debug_id, 0, ret,
rxrpc_tx_point_reject);
else
trace_rxrpc_tx_packet(local->debug_id, &whdr,
rxrpc_tx_point_reject);
}
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
}
_leave("");
}
/*
* Send a VERSION reply to a peer as a keepalive.
*/
void rxrpc_send_keepalive(struct rxrpc_peer *peer)
{
struct rxrpc_wire_header whdr;
struct msghdr msg;
struct kvec iov[2];
size_t len;
int ret;
_enter("");
msg.msg_name = &peer->srx.transport;
msg.msg_namelen = peer->srx.transport_len;
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
whdr.epoch = htonl(peer->local->rxnet->epoch);
whdr.cid = 0;
whdr.callNumber = 0;
whdr.seq = 0;
whdr.serial = 0;
whdr.type = RXRPC_PACKET_TYPE_VERSION; /* Not client-initiated */
whdr.flags = RXRPC_LAST_PACKET;
whdr.userStatus = 0;
whdr.securityIndex = 0;
whdr._rsvd = 0;
whdr.serviceId = 0;
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = (char *)rxrpc_keepalive_string;
iov[1].iov_len = sizeof(rxrpc_keepalive_string);
len = iov[0].iov_len + iov[1].iov_len;
_proto("Tx VERSION (keepalive)");
ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
if (ret < 0)
trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
rxrpc_tx_point_version_keepalive);
else
trace_rxrpc_tx_packet(peer->debug_id, &whdr,
rxrpc_tx_point_version_keepalive);
peer->last_tx_at = ktime_get_seconds();
_leave("");
}
+455
View File
@@ -0,0 +1,455 @@
/* Peer event handling, typically ICMP messages.
*
* 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.
*/
#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/icmp.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include "ar-internal.h"
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
static void rxrpc_distribute_error(struct rxrpc_peer *, int,
enum rxrpc_call_completion);
/*
* Find the peer associated with an ICMP packet.
*/
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
const struct sk_buff *skb,
struct sockaddr_rxrpc *srx)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
_enter("");
memset(srx, 0, sizeof(*srx));
srx->transport_type = local->srx.transport_type;
srx->transport_len = local->srx.transport_len;
srx->transport.family = local->srx.transport.family;
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
* versa?
*/
switch (srx->transport.family) {
case AF_INET:
srx->transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP");
memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6 on v4 sock");
memcpy(&srx->transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset + 12,
sizeof(struct in_addr));
break;
default:
memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
sizeof(struct in_addr));
break;
}
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
srx->transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
memcpy(&srx->transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
srx->transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
default:
memcpy(&srx->transport.sin6.sin6_addr,
&ipv6_hdr(skb)->saddr,
sizeof(struct in6_addr));
break;
}
break;
#endif
default:
BUG();
}
return rxrpc_lookup_peer_rcu(local, srx);
}
/*
* Handle an MTU/fragmentation problem.
*/
static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
{
u32 mtu = serr->ee.ee_info;
_net("Rx ICMP Fragmentation Needed (%d)", mtu);
/* wind down the local interface MTU */
if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
peer->if_mtu = mtu;
_net("I/F MTU %u", mtu);
}
if (mtu == 0) {
/* they didn't give us a size, estimate one */
mtu = peer->if_mtu;
if (mtu > 1500) {
mtu >>= 1;
if (mtu < 1500)
mtu = 1500;
} else {
mtu -= 100;
if (mtu < peer->hdrsize)
mtu = peer->hdrsize + 4;
}
}
if (mtu < peer->mtu) {
spin_lock_bh(&peer->lock);
peer->mtu = mtu;
peer->maxdata = peer->mtu - peer->hdrsize;
spin_unlock_bh(&peer->lock);
_net("Net MTU %u (maxdata %u)",
peer->mtu, peer->maxdata);
}
}
/*
* Handle an error received on the local endpoint.
*/
void rxrpc_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
struct sockaddr_rxrpc srx;
struct rxrpc_local *local = sk->sk_user_data;
struct rxrpc_peer *peer;
struct sk_buff *skb;
if (unlikely(!local))
return;
_enter("%p{%d}", sk, local->debug_id);
skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
return;
}
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
serr = SKB_EXT_ERR(skb);
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
_leave("UDP empty message");
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
return;
}
rcu_read_lock();
peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
_leave(" [no peer]");
return;
}
trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
serr->ee.ee_type == ICMP_DEST_UNREACH &&
serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
rxrpc_adjust_mtu(peer, serr);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
rxrpc_put_peer(peer);
_leave(" [MTU update]");
return;
}
rxrpc_store_error(peer, serr);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
rxrpc_put_peer(peer);
_leave("");
}
/*
* Map an error report to error codes on the peer record.
*/
static void rxrpc_store_error(struct rxrpc_peer *peer,
struct sock_exterr_skb *serr)
{
enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
struct sock_extended_err *ee;
int err;
_enter("");
ee = &serr->ee;
err = ee->ee_errno;
switch (ee->ee_origin) {
case SO_EE_ORIGIN_ICMP:
switch (ee->ee_type) {
case ICMP_DEST_UNREACH:
switch (ee->ee_code) {
case ICMP_NET_UNREACH:
_net("Rx Received ICMP Network Unreachable");
break;
case ICMP_HOST_UNREACH:
_net("Rx Received ICMP Host Unreachable");
break;
case ICMP_PORT_UNREACH:
_net("Rx Received ICMP Port Unreachable");
break;
case ICMP_NET_UNKNOWN:
_net("Rx Received ICMP Unknown Network");
break;
case ICMP_HOST_UNKNOWN:
_net("Rx Received ICMP Unknown Host");
break;
default:
_net("Rx Received ICMP DestUnreach code=%u",
ee->ee_code);
break;
}
break;
case ICMP_TIME_EXCEEDED:
_net("Rx Received ICMP TTL Exceeded");
break;
default:
_proto("Rx Received ICMP error { type=%u code=%u }",
ee->ee_type, ee->ee_code);
break;
}
break;
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
compl = RXRPC_CALL_LOCAL_ERROR;
break;
case SO_EE_ORIGIN_ICMP6:
default:
_proto("Rx Received error report { orig=%u }", ee->ee_origin);
break;
}
rxrpc_distribute_error(peer, err, compl);
}
/*
* Distribute an error that occurred on a peer.
*/
static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
enum rxrpc_call_completion compl)
{
struct rxrpc_call *call;
hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
rxrpc_see_call(call);
if (call->state < RXRPC_CALL_COMPLETE &&
rxrpc_set_call_completion(call, compl, 0, -error))
rxrpc_notify_socket(call);
}
}
/*
* Add RTT information to cache. This is called in softirq mode and has
* exclusive access to the peer RTT data.
*/
void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
ktime_t send_time, ktime_t resp_time)
{
struct rxrpc_peer *peer = call->peer;
s64 rtt;
u64 sum = peer->rtt_sum, avg;
u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
if (rtt < 0)
return;
spin_lock(&peer->rtt_input_lock);
/* Replace the oldest datum in the RTT buffer */
sum -= peer->rtt_cache[cursor];
sum += rtt;
peer->rtt_cache[cursor] = rtt;
peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
peer->rtt_sum = sum;
if (usage < RXRPC_RTT_CACHE_SIZE) {
usage++;
peer->rtt_usage = usage;
}
spin_unlock(&peer->rtt_input_lock);
/* Now recalculate the average */
if (usage == RXRPC_RTT_CACHE_SIZE) {
avg = sum / RXRPC_RTT_CACHE_SIZE;
} else {
avg = sum;
do_div(avg, usage);
}
/* Don't need to update this under lock */
peer->rtt = avg;
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
usage, avg);
}
/*
* Perform keep-alive pings.
*/
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
struct list_head *collector,
time64_t base,
u8 cursor)
{
struct rxrpc_peer *peer;
const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
time64_t keepalive_at;
int slot;
spin_lock_bh(&rxnet->peer_hash_lock);
while (!list_empty(collector)) {
peer = list_entry(collector->next,
struct rxrpc_peer, keepalive_link);
list_del_init(&peer->keepalive_link);
if (!rxrpc_get_peer_maybe(peer))
continue;
if (__rxrpc_use_local(peer->local)) {
spin_unlock_bh(&rxnet->peer_hash_lock);
keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
slot = keepalive_at - base;
_debug("%02x peer %u t=%d {%pISp}",
cursor, peer->debug_id, slot, &peer->srx.transport);
if (keepalive_at <= base ||
keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
rxrpc_send_keepalive(peer);
slot = RXRPC_KEEPALIVE_TIME;
}
/* A transmission to this peer occurred since last we
* examined it so put it into the appropriate future
* bucket.
*/
slot += cursor;
slot &= mask;
spin_lock_bh(&rxnet->peer_hash_lock);
list_add_tail(&peer->keepalive_link,
&rxnet->peer_keepalive[slot & mask]);
rxrpc_unuse_local(peer->local);
}
rxrpc_put_peer_locked(peer);
}
spin_unlock_bh(&rxnet->peer_hash_lock);
}
/*
* Perform keep-alive pings with VERSION packets to keep any NAT alive.
*/
void rxrpc_peer_keepalive_worker(struct work_struct *work)
{
struct rxrpc_net *rxnet =
container_of(work, struct rxrpc_net, peer_keepalive_work);
const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
time64_t base, now, delay;
u8 cursor, stop;
LIST_HEAD(collector);
now = ktime_get_seconds();
base = rxnet->peer_keepalive_base;
cursor = rxnet->peer_keepalive_cursor;
_enter("%lld,%u", base - now, cursor);
if (!rxnet->live)
return;
/* Remove to a temporary list all the peers that are currently lodged
* in expired buckets plus all new peers.
*
* Everything in the bucket at the cursor is processed this
* second; the bucket at cursor + 1 goes at now + 1s and so
* on...
*/
spin_lock_bh(&rxnet->peer_hash_lock);
list_splice_init(&rxnet->peer_keepalive_new, &collector);
stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
while (base <= now && (s8)(cursor - stop) < 0) {
list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
&collector);
base++;
cursor++;
}
base = now;
spin_unlock_bh(&rxnet->peer_hash_lock);
rxnet->peer_keepalive_base = base;
rxnet->peer_keepalive_cursor = cursor;
rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
ASSERT(list_empty(&collector));
/* Schedule the timer for the next occupied timeslot. */
cursor = rxnet->peer_keepalive_cursor;
stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
for (; (s8)(cursor - stop) < 0; cursor++) {
if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
break;
base++;
}
now = ktime_get_seconds();
delay = base - now;
if (delay < 1)
delay = 1;
delay *= HZ;
if (rxnet->live)
timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
_leave("");
}
+512
View File
@@ -0,0 +1,512 @@
/* RxRPC remote transport endpoint record management
*
* 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 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/slab.h>
#include <linux/hashtable.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/ip6_route.h>
#include "ar-internal.h"
/*
* Hash a peer key.
*/
static unsigned long rxrpc_peer_hash_key(struct rxrpc_local *local,
const struct sockaddr_rxrpc *srx)
{
const u16 *p;
unsigned int i, size;
unsigned long hash_key;
_enter("");
hash_key = (unsigned long)local / __alignof__(*local);
hash_key += srx->transport_type;
hash_key += srx->transport_len;
hash_key += srx->transport.family;
switch (srx->transport.family) {
case AF_INET:
hash_key += (u16 __force)srx->transport.sin.sin_port;
size = sizeof(srx->transport.sin.sin_addr);
p = (u16 *)&srx->transport.sin.sin_addr;
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
hash_key += (u16 __force)srx->transport.sin.sin_port;
size = sizeof(srx->transport.sin6.sin6_addr);
p = (u16 *)&srx->transport.sin6.sin6_addr;
break;
#endif
default:
WARN(1, "AF_RXRPC: Unsupported transport address family\n");
return 0;
}
/* Step through the peer address in 16-bit portions for speed */
for (i = 0; i < size; i += sizeof(*p), p++)
hash_key += *p;
_leave(" 0x%lx", hash_key);
return hash_key;
}
/*
* Compare a peer to a key. Return -ve, 0 or +ve to indicate less than, same
* or greater than.
*
* Unfortunately, the primitives in linux/hashtable.h don't allow for sorted
* buckets and mid-bucket insertion, so we don't make full use of this
* information at this point.
*/
static long rxrpc_peer_cmp_key(const struct rxrpc_peer *peer,
struct rxrpc_local *local,
const struct sockaddr_rxrpc *srx,
unsigned long hash_key)
{
long diff;
diff = ((peer->hash_key - hash_key) ?:
((unsigned long)peer->local - (unsigned long)local) ?:
(peer->srx.transport_type - srx->transport_type) ?:
(peer->srx.transport_len - srx->transport_len) ?:
(peer->srx.transport.family - srx->transport.family));
if (diff != 0)
return diff;
switch (srx->transport.family) {
case AF_INET:
return ((u16 __force)peer->srx.transport.sin.sin_port -
(u16 __force)srx->transport.sin.sin_port) ?:
memcmp(&peer->srx.transport.sin.sin_addr,
&srx->transport.sin.sin_addr,
sizeof(struct in_addr));
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
return ((u16 __force)peer->srx.transport.sin6.sin6_port -
(u16 __force)srx->transport.sin6.sin6_port) ?:
memcmp(&peer->srx.transport.sin6.sin6_addr,
&srx->transport.sin6.sin6_addr,
sizeof(struct in6_addr));
#endif
default:
BUG();
}
}
/*
* Look up a remote transport endpoint for the specified address using RCU.
*/
static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
struct rxrpc_local *local,
const struct sockaddr_rxrpc *srx,
unsigned long hash_key)
{
struct rxrpc_peer *peer;
struct rxrpc_net *rxnet = local->rxnet;
hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) {
if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 &&
atomic_read(&peer->usage) > 0)
return peer;
}
return NULL;
}
/*
* Look up a remote transport endpoint for the specified address using RCU.
*/
struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local,
const struct sockaddr_rxrpc *srx)
{
struct rxrpc_peer *peer;
unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
if (peer) {
_net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport);
_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
}
return peer;
}
/*
* assess the MTU size for the network interface through which this peer is
* reached
*/
static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx,
struct rxrpc_peer *peer)
{
struct net *net = sock_net(&rx->sk);
struct dst_entry *dst;
struct rtable *rt;
struct flowi fl;
struct flowi4 *fl4 = &fl.u.ip4;
#ifdef CONFIG_AF_RXRPC_IPV6
struct flowi6 *fl6 = &fl.u.ip6;
#endif
peer->if_mtu = 1500;
memset(&fl, 0, sizeof(fl));
switch (peer->srx.transport.family) {
case AF_INET:
rt = ip_route_output_ports(
net, fl4, NULL,
peer->srx.transport.sin.sin_addr.s_addr, 0,
htons(7000), htons(7001), IPPROTO_UDP, 0, 0);
if (IS_ERR(rt)) {
_leave(" [route err %ld]", PTR_ERR(rt));
return;
}
dst = &rt->dst;
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
fl6->flowi6_iif = LOOPBACK_IFINDEX;
fl6->flowi6_scope = RT_SCOPE_UNIVERSE;
fl6->flowi6_proto = IPPROTO_UDP;
memcpy(&fl6->daddr, &peer->srx.transport.sin6.sin6_addr,
sizeof(struct in6_addr));
fl6->fl6_dport = htons(7001);
fl6->fl6_sport = htons(7000);
dst = ip6_route_output(net, NULL, fl6);
if (dst->error) {
_leave(" [route err %d]", dst->error);
return;
}
break;
#endif
default:
BUG();
}
peer->if_mtu = dst_mtu(dst);
dst_release(dst);
_leave(" [if_mtu %u]", peer->if_mtu);
}
/*
* Allocate a peer.
*/
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
{
struct rxrpc_peer *peer;
_enter("");
peer = kzalloc(sizeof(struct rxrpc_peer), gfp);
if (peer) {
atomic_set(&peer->usage, 1);
peer->local = rxrpc_get_local(local);
INIT_HLIST_HEAD(&peer->error_targets);
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
spin_lock_init(&peer->lock);
spin_lock_init(&peer->rtt_input_lock);
peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
if (RXRPC_TX_SMSS > 2190)
peer->cong_cwnd = 2;
else if (RXRPC_TX_SMSS > 1095)
peer->cong_cwnd = 3;
else
peer->cong_cwnd = 4;
}
_leave(" = %p", peer);
return peer;
}
/*
* Initialise peer record.
*/
static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer,
unsigned long hash_key)
{
peer->hash_key = hash_key;
rxrpc_assess_MTU_size(rx, peer);
peer->mtu = peer->if_mtu;
peer->rtt_last_req = ktime_get_real();
switch (peer->srx.transport.family) {
case AF_INET:
peer->hdrsize = sizeof(struct iphdr);
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
peer->hdrsize = sizeof(struct ipv6hdr);
break;
#endif
default:
BUG();
}
switch (peer->srx.transport_type) {
case SOCK_DGRAM:
peer->hdrsize += sizeof(struct udphdr);
break;
default:
BUG();
}
peer->hdrsize += sizeof(struct rxrpc_wire_header);
peer->maxdata = peer->mtu - peer->hdrsize;
}
/*
* Set up a new peer.
*/
static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx,
struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
unsigned long hash_key,
gfp_t gfp)
{
struct rxrpc_peer *peer;
_enter("");
peer = rxrpc_alloc_peer(local, gfp);
if (peer) {
memcpy(&peer->srx, srx, sizeof(*srx));
rxrpc_init_peer(rx, peer, hash_key);
}
_leave(" = %p", peer);
return peer;
}
/*
* Set up a new incoming peer. There shouldn't be any other matching peers
* since we've already done a search in the list from the non-reentrant context
* (the data_ready handler) that is the only place we can add new peers.
*/
void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local,
struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx);
rxrpc_init_peer(rx, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
spin_unlock(&rxnet->peer_hash_lock);
}
/*
* obtain a remote transport endpoint for the specified address
*/
struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx,
struct rxrpc_local *local,
struct sockaddr_rxrpc *srx, gfp_t gfp)
{
struct rxrpc_peer *peer, *candidate;
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key = rxrpc_peer_hash_key(local, srx);
_enter("{%pISp}", &srx->transport);
/* search the peer list first */
rcu_read_lock();
peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
rcu_read_unlock();
if (!peer) {
/* The peer is not yet present in hash - create a candidate
* for a new record and then redo the search.
*/
candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp);
if (!candidate) {
_leave(" = NULL [nomem]");
return NULL;
}
spin_lock_bh(&rxnet->peer_hash_lock);
/* Need to check that we aren't racing with someone else */
peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
hash_add_rcu(rxnet->peer_hash,
&candidate->hash_link, hash_key);
list_add_tail(&candidate->keepalive_link,
&rxnet->peer_keepalive_new);
}
spin_unlock_bh(&rxnet->peer_hash_lock);
if (peer)
kfree(candidate);
else
peer = candidate;
}
_net("PEER %d {%pISp}", peer->debug_id, &peer->srx.transport);
_leave(" = %p {u=%d}", peer, atomic_read(&peer->usage));
return peer;
}
/*
* Get a ref on a peer record.
*/
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
int n;
n = atomic_inc_return(&peer->usage);
trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here);
return peer;
}
/*
* Get a ref on a peer record unless its usage has already reached 0.
*/
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
if (peer) {
int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
if (n > 0)
trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here);
else
peer = NULL;
}
return peer;
}
/*
* Discard a peer record.
*/
static void __rxrpc_put_peer(struct rxrpc_peer *peer)
{
struct rxrpc_net *rxnet = peer->local->rxnet;
ASSERT(hlist_empty(&peer->error_targets));
spin_lock_bh(&rxnet->peer_hash_lock);
hash_del_rcu(&peer->hash_link);
list_del_init(&peer->keepalive_link);
spin_unlock_bh(&rxnet->peer_hash_lock);
rxrpc_put_local(peer->local);
kfree_rcu(peer, rcu);
}
/*
* Drop a ref on a peer record.
*/
void rxrpc_put_peer(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
unsigned int debug_id;
int n;
if (peer) {
debug_id = peer->debug_id;
n = atomic_dec_return(&peer->usage);
trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
if (n == 0)
__rxrpc_put_peer(peer);
}
}
/*
* Drop a ref on a peer record where the caller already holds the
* peer_hash_lock.
*/
void rxrpc_put_peer_locked(struct rxrpc_peer *peer)
{
const void *here = __builtin_return_address(0);
unsigned int debug_id = peer->debug_id;
int n;
n = atomic_dec_return(&peer->usage);
trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here);
if (n == 0) {
hash_del_rcu(&peer->hash_link);
list_del_init(&peer->keepalive_link);
rxrpc_put_local(peer->local);
kfree_rcu(peer, rcu);
}
}
/*
* Make sure all peer records have been discarded.
*/
void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet)
{
struct rxrpc_peer *peer;
int i;
for (i = 0; i < HASH_SIZE(rxnet->peer_hash); i++) {
if (hlist_empty(&rxnet->peer_hash[i]))
continue;
hlist_for_each_entry(peer, &rxnet->peer_hash[i], hash_link) {
pr_err("Leaked peer %u {%u} %pISp\n",
peer->debug_id,
atomic_read(&peer->usage),
&peer->srx.transport);
}
}
}
/**
* rxrpc_kernel_get_peer - Get the peer address of a call
* @sock: The socket on which the call is in progress.
* @call: The call to query
* @_srx: Where to place the result
*
* Get the address of the remote peer in a call.
*/
void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call,
struct sockaddr_rxrpc *_srx)
{
*_srx = call->peer->srx;
}
EXPORT_SYMBOL(rxrpc_kernel_get_peer);
/**
* rxrpc_kernel_get_rtt - Get a call's peer RTT
* @sock: The socket on which the call is in progress.
* @call: The call to query
*
* Get the call's peer RTT.
*/
u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call)
{
return call->peer->rtt;
}
EXPORT_SYMBOL(rxrpc_kernel_get_rtt);
+214
View File
@@ -0,0 +1,214 @@
/* /proc/net/ support for AF_RXRPC
*
* 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.
*/
#include <linux/module.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = {
[RXRPC_CONN_UNUSED] = "Unused ",
[RXRPC_CONN_CLIENT] = "Client ",
[RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc",
[RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ",
[RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ",
[RXRPC_CONN_SERVICE] = "SvSecure",
[RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort",
[RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort",
};
/*
* generate a list of extant and dead calls in /proc/net/rxrpc_calls
*/
static void *rxrpc_call_seq_start(struct seq_file *seq, loff_t *_pos)
__acquires(rcu)
__acquires(rxnet->call_lock)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
rcu_read_lock();
read_lock(&rxnet->call_lock);
return seq_list_start_head(&rxnet->calls, *_pos);
}
static void *rxrpc_call_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
return seq_list_next(v, &rxnet->calls, pos);
}
static void rxrpc_call_seq_stop(struct seq_file *seq, void *v)
__releases(rxnet->call_lock)
__releases(rcu)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
read_unlock(&rxnet->call_lock);
rcu_read_unlock();
}
static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
{
struct rxrpc_local *local;
struct rxrpc_sock *rx;
struct rxrpc_peer *peer;
struct rxrpc_call *call;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
unsigned long timeout = 0;
rxrpc_seq_t tx_hard_ack, rx_hard_ack;
char lbuff[50], rbuff[50];
if (v == &rxnet->calls) {
seq_puts(seq,
"Proto Local "
" Remote "
" SvID ConnID CallID End Use State Abort "
" DebugId TxSeq TW RxSeq RW RxSerial RxTimo\n");
return 0;
}
call = list_entry(v, struct rxrpc_call, link);
rx = rcu_dereference(call->socket);
if (rx) {
local = READ_ONCE(rx->local);
if (local)
sprintf(lbuff, "%pISpc", &local->srx.transport);
else
strcpy(lbuff, "no_local");
} else {
strcpy(lbuff, "no_socket");
}
peer = call->peer;
if (peer)
sprintf(rbuff, "%pISpc", &peer->srx.transport);
else
strcpy(rbuff, "no_connection");
if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
timeout = READ_ONCE(call->expect_rx_by);
timeout -= jiffies;
}
tx_hard_ack = READ_ONCE(call->tx_hard_ack);
rx_hard_ack = READ_ONCE(call->rx_hard_ack);
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %08x %s %3u"
" %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n",
lbuff,
rbuff,
call->service_id,
call->cid,
call->call_id,
rxrpc_is_service_call(call) ? "Svc" : "Clt",
atomic_read(&call->usage),
rxrpc_call_states[call->state],
call->abort_code,
call->debug_id,
tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack,
rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack,
call->rx_serial,
timeout);
return 0;
}
const struct seq_operations rxrpc_call_seq_ops = {
.start = rxrpc_call_seq_start,
.next = rxrpc_call_seq_next,
.stop = rxrpc_call_seq_stop,
.show = rxrpc_call_seq_show,
};
/*
* generate a list of extant virtual connections in /proc/net/rxrpc_conns
*/
static void *rxrpc_connection_seq_start(struct seq_file *seq, loff_t *_pos)
__acquires(rxnet->conn_lock)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
read_lock(&rxnet->conn_lock);
return seq_list_start_head(&rxnet->conn_proc_list, *_pos);
}
static void *rxrpc_connection_seq_next(struct seq_file *seq, void *v,
loff_t *pos)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
return seq_list_next(v, &rxnet->conn_proc_list, pos);
}
static void rxrpc_connection_seq_stop(struct seq_file *seq, void *v)
__releases(rxnet->conn_lock)
{
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
read_unlock(&rxnet->conn_lock);
}
static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
{
struct rxrpc_connection *conn;
struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
char lbuff[50], rbuff[50];
if (v == &rxnet->conn_proc_list) {
seq_puts(seq,
"Proto Local "
" Remote "
" SvID ConnID End Use State Key "
" Serial ISerial\n"
);
return 0;
}
conn = list_entry(v, struct rxrpc_connection, proc_link);
if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) {
strcpy(lbuff, "no_local");
strcpy(rbuff, "no_connection");
goto print;
}
sprintf(lbuff, "%pISpc", &conn->params.local->srx.transport);
sprintf(rbuff, "%pISpc", &conn->params.peer->srx.transport);
print:
seq_printf(seq,
"UDP %-47.47s %-47.47s %4x %08x %s %3u"
" %s %08x %08x %08x %08x %08x %08x %08x\n",
lbuff,
rbuff,
conn->service_id,
conn->proto.cid,
rxrpc_conn_is_service(conn) ? "Svc" : "Clt",
atomic_read(&conn->usage),
rxrpc_conn_states[conn->state],
key_serial(conn->params.key),
atomic_read(&conn->serial),
conn->hi_serial,
conn->channels[0].call_id,
conn->channels[1].call_id,
conn->channels[2].call_id,
conn->channels[3].call_id);
return 0;
}
const struct seq_operations rxrpc_connection_seq_ops = {
.start = rxrpc_connection_seq_start,
.next = rxrpc_connection_seq_next,
.stop = rxrpc_connection_seq_stop,
.show = rxrpc_connection_seq_show,
};
+181
View File
@@ -0,0 +1,181 @@
/* packet.h: Rx packet layout and definitions
*
* Copyright (C) 2002, 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.
*/
#ifndef _LINUX_RXRPC_PACKET_H
#define _LINUX_RXRPC_PACKET_H
typedef u32 rxrpc_seq_t; /* Rx message sequence number */
typedef u32 rxrpc_serial_t; /* Rx message serial number */
typedef __be32 rxrpc_seq_net_t; /* on-the-wire Rx message sequence number */
typedef __be32 rxrpc_serial_net_t; /* on-the-wire Rx message serial number */
/*****************************************************************************/
/*
* on-the-wire Rx packet header
* - all multibyte fields should be in network byte order
*/
struct rxrpc_wire_header {
__be32 epoch; /* client boot timestamp */
#define RXRPC_RANDOM_EPOCH 0x80000000 /* Random if set, date-based if not */
__be32 cid; /* connection and channel ID */
#define RXRPC_MAXCALLS 4 /* max active calls per conn */
#define RXRPC_CHANNELMASK (RXRPC_MAXCALLS-1) /* mask for channel ID */
#define RXRPC_CIDMASK (~RXRPC_CHANNELMASK) /* mask for connection ID */
#define RXRPC_CIDSHIFT ilog2(RXRPC_MAXCALLS) /* shift for connection ID */
#define RXRPC_CID_INC (1 << RXRPC_CIDSHIFT) /* connection ID increment */
__be32 callNumber; /* call ID (0 for connection-level packets) */
__be32 seq; /* sequence number of pkt in call stream */
__be32 serial; /* serial number of pkt sent to network */
uint8_t type; /* packet type */
#define RXRPC_PACKET_TYPE_DATA 1 /* data */
#define RXRPC_PACKET_TYPE_ACK 2 /* ACK */
#define RXRPC_PACKET_TYPE_BUSY 3 /* call reject */
#define RXRPC_PACKET_TYPE_ABORT 4 /* call/connection abort */
#define RXRPC_PACKET_TYPE_ACKALL 5 /* ACK all outstanding packets on call */
#define RXRPC_PACKET_TYPE_CHALLENGE 6 /* connection security challenge (SRVR->CLNT) */
#define RXRPC_PACKET_TYPE_RESPONSE 7 /* connection secutity response (CLNT->SRVR) */
#define RXRPC_PACKET_TYPE_DEBUG 8 /* debug info request */
#define RXRPC_PACKET_TYPE_PARAMS 9 /* Parameter negotiation (unspec'd, ignore) */
#define RXRPC_PACKET_TYPE_10 10 /* Ignored */
#define RXRPC_PACKET_TYPE_11 11 /* Ignored */
#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */
uint8_t flags; /* packet flags */
#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */
#define RXRPC_REQUEST_ACK 0x02 /* request an unconditional ACK of this packet */
#define RXRPC_LAST_PACKET 0x04 /* the last packet from this side for this call */
#define RXRPC_MORE_PACKETS 0x08 /* more packets to come */
#define RXRPC_JUMBO_PACKET 0x20 /* [DATA] this is a jumbo packet */
#define RXRPC_SLOW_START_OK 0x20 /* [ACK] slow start supported */
uint8_t userStatus; /* app-layer defined status */
#define RXRPC_USERSTATUS_SERVICE_UPGRADE 0x01 /* AuriStor service upgrade request */
uint8_t securityIndex; /* security protocol ID */
union {
__be16 _rsvd; /* reserved */
__be16 cksum; /* kerberos security checksum */
};
__be16 serviceId; /* service ID */
} __packed;
/*****************************************************************************/
/*
* jumbo packet secondary header
* - can be mapped to read header by:
* - new_serial = serial + 1
* - new_seq = seq + 1
* - new_flags = j_flags
* - new__rsvd = j__rsvd
* - duplicating all other fields
*/
struct rxrpc_jumbo_header {
uint8_t flags; /* packet flags (as per rxrpc_header) */
uint8_t pad;
union {
__be16 _rsvd; /* reserved */
__be16 cksum; /* kerberos security checksum */
};
};
#define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */
#define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header))
/*****************************************************************************/
/*
* on-the-wire Rx ACK packet data payload
* - all multibyte fields should be in network byte order
*/
struct rxrpc_ackpacket {
__be16 bufferSpace; /* number of packet buffers available */
__be16 maxSkew; /* diff between serno being ACK'd and highest serial no
* received */
__be32 firstPacket; /* sequence no of first ACK'd packet in attached list */
__be32 previousPacket; /* sequence no of previous packet received */
__be32 serial; /* serial no of packet that prompted this ACK */
uint8_t reason; /* reason for ACK */
#define RXRPC_ACK_REQUESTED 1 /* ACK was requested on packet */
#define RXRPC_ACK_DUPLICATE 2 /* duplicate packet received */
#define RXRPC_ACK_OUT_OF_SEQUENCE 3 /* out of sequence packet received */
#define RXRPC_ACK_EXCEEDS_WINDOW 4 /* packet received beyond end of ACK window */
#define RXRPC_ACK_NOSPACE 5 /* packet discarded due to lack of buffer space */
#define RXRPC_ACK_PING 6 /* keep alive ACK */
#define RXRPC_ACK_PING_RESPONSE 7 /* response to RXRPC_ACK_PING */
#define RXRPC_ACK_DELAY 8 /* nothing happened since received packet */
#define RXRPC_ACK_IDLE 9 /* ACK due to fully received ACK window */
#define RXRPC_ACK__INVALID 10 /* Representation of invalid ACK reason */
uint8_t nAcks; /* number of ACKs */
#define RXRPC_MAXACKS 255
uint8_t acks[0]; /* list of ACK/NAKs */
#define RXRPC_ACK_TYPE_NACK 0
#define RXRPC_ACK_TYPE_ACK 1
} __packed;
/* Some ACKs refer to specific packets and some are general and can be updated. */
#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \
(1 << RXRPC_ACK_PING_RESPONSE) | \
(1 << RXRPC_ACK_DELAY) | \
(1 << RXRPC_ACK_IDLE))
/*
* ACK packets can have a further piece of information tagged on the end
*/
struct rxrpc_ackinfo {
__be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */
__be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */
__be32 rwind; /* Rx window size (packets) [AFS 3.4] */
__be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */
};
/*****************************************************************************/
/*
* Kerberos security type-2 challenge packet
*/
struct rxkad_challenge {
__be32 version; /* version of this challenge type */
__be32 nonce; /* encrypted random number */
__be32 min_level; /* minimum security level */
__be32 __padding; /* padding to 8-byte boundary */
} __packed;
/*****************************************************************************/
/*
* Kerberos security type-2 response packet
*/
struct rxkad_response {
__be32 version; /* version of this response type */
__be32 __pad;
/* encrypted bit of the response */
struct {
__be32 epoch; /* current epoch */
__be32 cid; /* parent connection ID */
__be32 checksum; /* checksum */
__be32 securityIndex; /* security type */
__be32 call_id[4]; /* encrypted call IDs */
__be32 inc_nonce; /* challenge nonce + 1 */
__be32 level; /* desired level */
} encrypted;
__be32 kvno; /* Kerberos key version number */
__be32 ticket_len; /* Kerberos ticket length */
} __packed;
#endif /* _LINUX_RXRPC_PACKET_H */
+718
View File
@@ -0,0 +1,718 @@
/* RxRPC recvmsg() implementation
*
* 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/net.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"
/*
* Post a call for attention by the socket or kernel service. Further
* notifications are suppressed by putting recvmsg_link on a dummy queue.
*/
void rxrpc_notify_socket(struct rxrpc_call *call)
{
struct rxrpc_sock *rx;
struct sock *sk;
_enter("%d", call->debug_id);
if (!list_empty(&call->recvmsg_link))
return;
rcu_read_lock();
rx = rcu_dereference(call->socket);
sk = &rx->sk;
if (rx && sk->sk_state < RXRPC_CLOSE) {
if (call->notify_rx) {
spin_lock_bh(&call->notify_lock);
call->notify_rx(sk, call, call->user_call_ID);
spin_unlock_bh(&call->notify_lock);
} else {
write_lock_bh(&rx->recvmsg_lock);
if (list_empty(&call->recvmsg_link)) {
rxrpc_get_call(call, rxrpc_call_got);
list_add_tail(&call->recvmsg_link, &rx->recvmsg_q);
}
write_unlock_bh(&rx->recvmsg_lock);
if (!sock_flag(sk, SOCK_DEAD)) {
_debug("call %ps", sk->sk_data_ready);
sk->sk_data_ready(sk);
}
}
}
rcu_read_unlock();
_leave("");
}
/*
* Pass a call terminating message to userspace.
*/
static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg)
{
u32 tmp = 0;
int ret;
switch (call->completion) {
case RXRPC_CALL_SUCCEEDED:
ret = 0;
if (rxrpc_is_service_call(call))
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ACK, 0, &tmp);
break;
case RXRPC_CALL_REMOTELY_ABORTED:
tmp = call->abort_code;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp);
break;
case RXRPC_CALL_LOCALLY_ABORTED:
tmp = call->abort_code;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_ABORT, 4, &tmp);
break;
case RXRPC_CALL_NETWORK_ERROR:
tmp = -call->error;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NET_ERROR, 4, &tmp);
break;
case RXRPC_CALL_LOCAL_ERROR:
tmp = -call->error;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp);
break;
default:
pr_err("Invalid terminal call state %u\n", call->state);
BUG();
break;
}
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack,
call->rx_pkt_offset, call->rx_pkt_len, ret);
return ret;
}
/*
* Pass back notification of a new call. The call is added to the
* to-be-accepted list. This means that the next call to be accepted might not
* be the last call seen awaiting acceptance, but unless we leave this on the
* front of the queue and block all other messages until someone gives us a
* user_ID for it, there's not a lot we can do.
*/
static int rxrpc_recvmsg_new_call(struct rxrpc_sock *rx,
struct rxrpc_call *call,
struct msghdr *msg, int flags)
{
int tmp = 0, ret;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &tmp);
if (ret == 0 && !(flags & MSG_PEEK)) {
_debug("to be accepted");
write_lock_bh(&rx->recvmsg_lock);
list_del_init(&call->recvmsg_link);
write_unlock_bh(&rx->recvmsg_lock);
rxrpc_get_call(call, rxrpc_call_got);
write_lock(&rx->call_lock);
list_add_tail(&call->accept_link, &rx->to_be_accepted);
write_unlock(&rx->call_lock);
}
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_to_be_accepted, 1, 0, 0, ret);
return ret;
}
/*
* End the packet reception phase.
*/
static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
{
_enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]);
trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top);
ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
rxrpc_propose_ack_terminal_ack);
//rxrpc_send_ack_packet(call, false, NULL);
}
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
__rxrpc_call_completed(call);
write_unlock_bh(&call->state_lock);
break;
case RXRPC_CALL_SERVER_RECV_REQUEST:
call->tx_phase = true;
call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
call->expect_req_by = jiffies + MAX_JIFFY_OFFSET;
write_unlock_bh(&call->state_lock);
rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true,
rxrpc_propose_ack_processing_op);
break;
default:
write_unlock_bh(&call->state_lock);
break;
}
}
/*
* Discard a packet we've used up and advance the Rx window by one.
*/
static void rxrpc_rotate_rx_window(struct rxrpc_call *call)
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
u8 flags;
int ix;
_enter("%d", call->debug_id);
hard_ack = call->rx_hard_ack;
top = smp_load_acquire(&call->rx_top);
ASSERT(before(hard_ack, top));
hard_ack++;
ix = hard_ack & RXRPC_RXTX_BUFF_MASK;
skb = call->rxtx_buffer[ix];
rxrpc_see_skb(skb, rxrpc_skb_rx_rotated);
sp = rxrpc_skb(skb);
flags = sp->hdr.flags;
serial = sp->hdr.serial;
if (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO)
serial += (call->rxtx_annotations[ix] & RXRPC_RX_ANNO_JUMBO) - 1;
call->rxtx_buffer[ix] = NULL;
call->rxtx_annotations[ix] = 0;
/* Barrier against rxrpc_input_data(). */
smp_store_release(&call->rx_hard_ack, hard_ack);
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
_debug("%u,%u,%02x", hard_ack, top, flags);
trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack);
if (flags & RXRPC_LAST_PACKET) {
rxrpc_end_rx_phase(call, serial);
} else {
/* Check to see if there's an ACK that needs sending. */
if (after_eq(hard_ack, call->ackr_consumed + 2) ||
after_eq(top, call->ackr_seen + 2) ||
(hard_ack == top && after(hard_ack, call->ackr_consumed)))
rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial,
true, true,
rxrpc_propose_ack_rotate_rx);
if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY)
rxrpc_send_ack_packet(call, false, NULL);
}
}
/*
* Decrypt and verify a (sub)packet. The packet's length may be changed due to
* padding, but if this is the case, the packet length will be resident in the
* socket buffer. Note that we can't modify the master skb info as the skb may
* be the home to multiple subpackets.
*/
static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
u8 annotation,
unsigned int offset, unsigned int len)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
rxrpc_seq_t seq = sp->hdr.seq;
u16 cksum = sp->hdr.cksum;
_enter("");
/* For all but the head jumbo subpacket, the security checksum is in a
* jumbo header immediately prior to the data.
*/
if ((annotation & RXRPC_RX_ANNO_JUMBO) > 1) {
__be16 tmp;
if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0)
BUG();
cksum = ntohs(tmp);
seq += (annotation & RXRPC_RX_ANNO_JUMBO) - 1;
}
return call->conn->security->verify_packet(call, skb, offset, len,
seq, cksum);
}
/*
* Locate the data within a packet. This is complicated by:
*
* (1) An skb may contain a jumbo packet - so we have to find the appropriate
* subpacket.
*
* (2) The (sub)packets may be encrypted and, if so, the encrypted portion
* contains an extra header which includes the true length of the data,
* excluding any encrypted padding.
*/
static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
u8 *_annotation,
unsigned int *_offset, unsigned int *_len)
{
unsigned int offset = sizeof(struct rxrpc_wire_header);
unsigned int len;
int ret;
u8 annotation = *_annotation;
/* Locate the subpacket */
len = skb->len - offset;
if ((annotation & RXRPC_RX_ANNO_JUMBO) > 0) {
offset += (((annotation & RXRPC_RX_ANNO_JUMBO) - 1) *
RXRPC_JUMBO_SUBPKTLEN);
len = (annotation & RXRPC_RX_ANNO_JLAST) ?
skb->len - offset : RXRPC_JUMBO_SUBPKTLEN;
}
if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) {
ret = rxrpc_verify_packet(call, skb, annotation, offset, len);
if (ret < 0)
return ret;
*_annotation |= RXRPC_RX_ANNO_VERIFIED;
}
*_offset = offset;
*_len = len;
call->conn->security->locate_data(call, skb, _offset, _len);
return 0;
}
/*
* Deliver messages to a call. This keeps processing packets until the buffer
* is filled and we find either more DATA (returns 0) or the end of the DATA
* (returns 1). If more packets are required, it returns -EAGAIN.
*/
static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
struct msghdr *msg, struct iov_iter *iter,
size_t len, int flags, size_t *_offset)
{
struct rxrpc_skb_priv *sp;
struct sk_buff *skb;
rxrpc_seq_t hard_ack, top, seq;
size_t remain;
bool last;
unsigned int rx_pkt_offset, rx_pkt_len;
int ix, copy, ret = -EAGAIN, ret2;
if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) &&
call->ackr_reason)
rxrpc_send_ack_packet(call, false, NULL);
rx_pkt_offset = call->rx_pkt_offset;
rx_pkt_len = call->rx_pkt_len;
if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) {
seq = call->rx_hard_ack;
ret = 1;
goto done;
}
/* Barriers against rxrpc_input_data(). */
hard_ack = call->rx_hard_ack;
seq = hard_ack + 1;
while (top = smp_load_acquire(&call->rx_top),
before_eq(seq, top)
) {
ix = seq & RXRPC_RXTX_BUFF_MASK;
skb = call->rxtx_buffer[ix];
if (!skb) {
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq,
rx_pkt_offset, rx_pkt_len, 0);
break;
}
smp_rmb();
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
sp = rxrpc_skb(skb);
if (!(flags & MSG_PEEK))
trace_rxrpc_receive(call, rxrpc_receive_front,
sp->hdr.serial, seq);
if (msg)
sock_recv_timestamp(msg, sock->sk, skb);
if (rx_pkt_offset == 0) {
ret2 = rxrpc_locate_data(call, skb,
&call->rxtx_annotations[ix],
&rx_pkt_offset, &rx_pkt_len);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq,
rx_pkt_offset, rx_pkt_len, ret2);
if (ret2 < 0) {
ret = ret2;
goto out;
}
} else {
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq,
rx_pkt_offset, rx_pkt_len, 0);
}
/* We have to handle short, empty and used-up DATA packets. */
remain = len - *_offset;
copy = rx_pkt_len;
if (copy > remain)
copy = remain;
if (copy > 0) {
ret2 = skb_copy_datagram_iter(skb, rx_pkt_offset, iter,
copy);
if (ret2 < 0) {
ret = ret2;
goto out;
}
/* handle piecemeal consumption of data packets */
rx_pkt_offset += copy;
rx_pkt_len -= copy;
*_offset += copy;
}
if (rx_pkt_len > 0) {
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq,
rx_pkt_offset, rx_pkt_len, 0);
ASSERTCMP(*_offset, ==, len);
ret = 0;
break;
}
/* The whole packet has been transferred. */
last = sp->hdr.flags & RXRPC_LAST_PACKET;
if (!(flags & MSG_PEEK))
rxrpc_rotate_rx_window(call);
rx_pkt_offset = 0;
rx_pkt_len = 0;
if (last) {
ASSERTCMP(seq, ==, READ_ONCE(call->rx_top));
ret = 1;
goto out;
}
seq++;
}
out:
if (!(flags & MSG_PEEK)) {
call->rx_pkt_offset = rx_pkt_offset;
call->rx_pkt_len = rx_pkt_len;
}
done:
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq,
rx_pkt_offset, rx_pkt_len, ret);
if (ret == -EAGAIN)
set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags);
return ret;
}
/*
* Receive a message from an RxRPC socket
* - we need to be careful about two or more threads calling recvmsg
* simultaneously
*/
int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
int flags)
{
struct rxrpc_call *call;
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct list_head *l;
size_t copied = 0;
long timeo;
int ret;
DEFINE_WAIT(wait);
trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0);
if (flags & (MSG_OOB | MSG_TRUNC))
return -EOPNOTSUPP;
timeo = sock_rcvtimeo(&rx->sk, flags & MSG_DONTWAIT);
try_again:
lock_sock(&rx->sk);
/* Return immediately if a client socket has no outstanding calls */
if (RB_EMPTY_ROOT(&rx->calls) &&
list_empty(&rx->recvmsg_q) &&
rx->sk.sk_state != RXRPC_SERVER_LISTENING) {
release_sock(&rx->sk);
return -EAGAIN;
}
if (list_empty(&rx->recvmsg_q)) {
ret = -EWOULDBLOCK;
if (timeo == 0) {
call = NULL;
goto error_no_call;
}
release_sock(&rx->sk);
/* Wait for something to happen */
prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait,
TASK_INTERRUPTIBLE);
ret = sock_error(&rx->sk);
if (ret)
goto wait_error;
if (list_empty(&rx->recvmsg_q)) {
if (signal_pending(current))
goto wait_interrupted;
trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait,
0, 0, 0, 0);
timeo = schedule_timeout(timeo);
}
finish_wait(sk_sleep(&rx->sk), &wait);
goto try_again;
}
/* Find the next call and dequeue it if we're not just peeking. If we
* do dequeue it, that comes with a ref that we will need to release.
*/
write_lock_bh(&rx->recvmsg_lock);
l = rx->recvmsg_q.next;
call = list_entry(l, struct rxrpc_call, recvmsg_link);
if (!(flags & MSG_PEEK))
list_del_init(&call->recvmsg_link);
else
rxrpc_get_call(call, rxrpc_call_got);
write_unlock_bh(&rx->recvmsg_lock);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0);
/* We're going to drop the socket lock, so we need to lock the call
* against interference by sendmsg.
*/
if (!mutex_trylock(&call->user_mutex)) {
ret = -EWOULDBLOCK;
if (flags & MSG_DONTWAIT)
goto error_requeue_call;
ret = -ERESTARTSYS;
if (mutex_lock_interruptible(&call->user_mutex) < 0)
goto error_requeue_call;
}
release_sock(&rx->sk);
if (test_bit(RXRPC_CALL_RELEASED, &call->flags))
BUG();
if (test_bit(RXRPC_CALL_HAS_USERID, &call->flags)) {
if (flags & MSG_CMSG_COMPAT) {
unsigned int id32 = call->user_call_ID;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
sizeof(unsigned int), &id32);
} else {
unsigned long idl = call->user_call_ID;
ret = put_cmsg(msg, SOL_RXRPC, RXRPC_USER_CALL_ID,
sizeof(unsigned long), &idl);
}
if (ret < 0)
goto error_unlock_call;
}
if (msg->msg_name && call->peer) {
struct sockaddr_rxrpc *srx = msg->msg_name;
size_t len = sizeof(call->peer->srx);
memcpy(msg->msg_name, &call->peer->srx, len);
srx->srx_service = call->service_id;
msg->msg_namelen = len;
}
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_SERVER_ACCEPTING:
ret = rxrpc_recvmsg_new_call(rx, call, msg, flags);
break;
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len,
flags, &copied);
if (ret == -EAGAIN)
ret = 0;
if (after(call->rx_top, call->rx_hard_ack) &&
call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK])
rxrpc_notify_socket(call);
break;
default:
ret = 0;
break;
}
if (ret < 0)
goto error_unlock_call;
if (call->state == RXRPC_CALL_COMPLETE) {
ret = rxrpc_recvmsg_term(call, msg);
if (ret < 0)
goto error_unlock_call;
if (!(flags & MSG_PEEK))
rxrpc_release_call(rx, call);
msg->msg_flags |= MSG_EOR;
ret = 1;
}
if (ret == 0)
msg->msg_flags |= MSG_MORE;
else
msg->msg_flags &= ~MSG_MORE;
ret = copied;
error_unlock_call:
mutex_unlock(&call->user_mutex);
rxrpc_put_call(call, rxrpc_call_put);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
return ret;
error_requeue_call:
if (!(flags & MSG_PEEK)) {
write_lock_bh(&rx->recvmsg_lock);
list_add(&call->recvmsg_link, &rx->recvmsg_q);
write_unlock_bh(&rx->recvmsg_lock);
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0);
} else {
rxrpc_put_call(call, rxrpc_call_put);
}
error_no_call:
release_sock(&rx->sk);
error_trace:
trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret);
return ret;
wait_interrupted:
ret = sock_intr_errno(timeo);
wait_error:
finish_wait(sk_sleep(&rx->sk), &wait);
call = NULL;
goto error_trace;
}
/**
* rxrpc_kernel_recv_data - Allow a kernel service to receive data/info
* @sock: The socket that the call exists on
* @call: The call to send data through
* @iter: The buffer to receive into
* @want_more: True if more data is expected to be read
* @_abort: Where the abort code is stored if -ECONNABORTED is returned
* @_service: Where to store the actual service ID (may be upgraded)
*
* Allow a kernel service to receive data and pick up information about the
* state of a call. Returns 0 if got what was asked for and there's more
* available, 1 if we got what was asked for and we're at the end of the data
* and -EAGAIN if we need more data.
*
* Note that we may return -EAGAIN to drain empty packets at the end of the
* data, even if we've already copied over the requested data.
*
* *_abort should also be initialised to 0.
*/
int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
struct iov_iter *iter,
bool want_more, u32 *_abort, u16 *_service)
{
size_t offset = 0;
int ret;
_enter("{%d,%s},%zu,%d",
call->debug_id, rxrpc_call_states[call->state],
iov_iter_count(iter), want_more);
ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING);
mutex_lock(&call->user_mutex);
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_RECV_REPLY:
case RXRPC_CALL_SERVER_RECV_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
iov_iter_count(iter), 0,
&offset);
if (ret < 0)
goto out;
/* We can only reach here with a partially full buffer if we
* have reached the end of the data. We must otherwise have a
* full buffer or have been given -EAGAIN.
*/
if (ret == 1) {
if (iov_iter_count(iter) > 0)
goto short_data;
if (!want_more)
goto read_phase_complete;
ret = 0;
goto out;
}
if (!want_more)
goto excess_data;
goto out;
case RXRPC_CALL_COMPLETE:
goto call_complete;
default:
ret = -EINPROGRESS;
goto out;
}
read_phase_complete:
ret = 1;
out:
switch (call->ackr_reason) {
case RXRPC_ACK_IDLE:
break;
case RXRPC_ACK_DELAY:
if (ret != -EAGAIN)
break;
/* Fall through */
default:
rxrpc_send_ack_packet(call, false, NULL);
}
if (_service)
*_service = call->service_id;
mutex_unlock(&call->user_mutex);
_leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort);
return ret;
short_data:
trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data"));
ret = -EBADMSG;
goto out;
excess_data:
trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data"));
ret = -EMSGSIZE;
goto out;
call_complete:
*_abort = call->abort_code;
ret = call->error;
if (call->completion == RXRPC_CALL_SUCCEEDED) {
ret = 1;
if (iov_iter_count(iter) > 0)
ret = -ECONNRESET;
}
goto out;
}
EXPORT_SYMBOL(rxrpc_kernel_recv_data);
+1260
View File
File diff suppressed because it is too large. Load diff
+166
View File
@@ -0,0 +1,166 @@
/* RxRPC security 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.
*/
#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/udp.h>
#include <linux/crypto.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <keys/rxrpc-type.h>
#include "ar-internal.h"
static const struct rxrpc_security *rxrpc_security_types[] = {
[RXRPC_SECURITY_NONE] = &rxrpc_no_security,
#ifdef CONFIG_RXKAD
[RXRPC_SECURITY_RXKAD] = &rxkad,
#endif
};
int __init rxrpc_init_security(void)
{
int i, ret;
for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) {
if (rxrpc_security_types[i]) {
ret = rxrpc_security_types[i]->init();
if (ret < 0)
goto failed;
}
}
return 0;
failed:
for (i--; i >= 0; i--)
if (rxrpc_security_types[i])
rxrpc_security_types[i]->exit();
return ret;
}
void rxrpc_exit_security(void)
{
int i;
for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++)
if (rxrpc_security_types[i])
rxrpc_security_types[i]->exit();
}
/*
* look up an rxrpc security module
*/
static const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
{
if (security_index >= ARRAY_SIZE(rxrpc_security_types))
return NULL;
return rxrpc_security_types[security_index];
}
/*
* initialise the security on a client connection
*/
int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
{
const struct rxrpc_security *sec;
struct rxrpc_key_token *token;
struct key *key = conn->params.key;
int ret;
_enter("{%d},{%x}", conn->debug_id, key_serial(key));
if (!key)
return 0;
ret = key_validate(key);
if (ret < 0)
return ret;
token = key->payload.data[0];
if (!token)
return -EKEYREJECTED;
sec = rxrpc_security_lookup(token->security_index);
if (!sec)
return -EKEYREJECTED;
conn->security = sec;
ret = conn->security->init_connection_security(conn);
if (ret < 0) {
conn->security = &rxrpc_no_security;
return ret;
}
_leave(" = 0");
return 0;
}
/*
* initialise the security on a server connection
*/
int rxrpc_init_server_conn_security(struct rxrpc_connection *conn)
{
const struct rxrpc_security *sec;
struct rxrpc_local *local = conn->params.local;
struct rxrpc_sock *rx;
struct key *key;
key_ref_t kref;
char kdesc[5 + 1 + 3 + 1];
_enter("");
sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix);
sec = rxrpc_security_lookup(conn->security_ix);
if (!sec) {
_leave(" = -ENOKEY [lookup]");
return -ENOKEY;
}
/* find the service */
read_lock(&local->services_lock);
rx = rcu_dereference_protected(local->service,
lockdep_is_held(&local->services_lock));
if (rx && (rx->srx.srx_service == conn->service_id ||
rx->second_service == conn->service_id))
goto found_service;
/* the service appears to have died */
read_unlock(&local->services_lock);
_leave(" = -ENOENT");
return -ENOENT;
found_service:
if (!rx->securities) {
read_unlock(&local->services_lock);
_leave(" = -ENOKEY");
return -ENOKEY;
}
/* look through the service's keyring */
kref = keyring_search(make_key_ref(rx->securities, 1UL),
&key_type_rxrpc_s, kdesc);
if (IS_ERR(kref)) {
read_unlock(&local->services_lock);
_leave(" = %ld [search]", PTR_ERR(kref));
return PTR_ERR(kref);
}
key = key_ref_to_ptr(kref);
read_unlock(&local->services_lock);
conn->server_key = key;
conn->security = sec;
_leave(" = 0");
return 0;
}
+855
View File
@@ -0,0 +1,855 @@
/* 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 <linux/sched/signal.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
/*
* 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 (call->tx_top - call->tx_hard_ack <
min_t(unsigned int, call->tx_winsize,
call->cong_cwnd + call->cong_extra))
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_nonintr(struct rxrpc_sock *rx,
struct rxrpc_call *call)
{
rxrpc_seq_t tx_start, tx_win;
signed long rtt2, timeout;
u64 rtt;
rtt = READ_ONCE(call->peer->rtt);
rtt2 = nsecs_to_jiffies64(rtt) * 2;
if (rtt2 < 2)
rtt2 = 2;
timeout = rtt2;
tx_start = READ_ONCE(call->tx_hard_ack);
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
tx_win = READ_ONCE(call->tx_hard_ack);
if (call->tx_top - tx_win <
min_t(unsigned int, call->tx_winsize,
call->cong_cwnd + call->cong_extra))
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 = rtt2;
tx_start = tx_win;
}
trace_rxrpc_transmit(call, rxrpc_transmit_wait);
timeout = schedule_timeout(timeout);
}
}
/*
* 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);
if (waitall)
ret = rxrpc_wait_for_tx_window_nonintr(rx, call);
else
ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo);
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
*/
static void 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;
set_bit(RXRPC_CALL_TX_LASTQ, &call->flags);
}
/* 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;
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;
/* Fall through */
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);
rxrpc_notify_socket(call);
goto out;
}
_debug("need instant resend %d", ret);
rxrpc_instant_resend(call, ix);
} else {
unsigned long now = jiffies, resend_at;
if (call->peer->rtt_usage > 1)
resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2);
else
resend_at = rxrpc_resend_timeout;
if (resend_at < 1)
resend_at = 1;
resend_at += now;
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_tx_freed);
_leave("");
}
/*
* 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_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, NULL);
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,
msg->msg_flags & MSG_WAITALL);
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;
if (call->tx_total_len != -1)
call->tx_total_len -= copy;
}
/* 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)
skb_put_zero(skb, 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(rx, call, skb,
!msg_data_left(msg) && !more,
notify_end_tx);
skb = NULL;
}
/* Check for the far side aborting the call or a network error
* occurring. If this happens, save any packet that was under
* construction so that in the case of a network error, the
* call can be retried or redirected.
*/
if (call->state == RXRPC_CALL_COMPLETE) {
ret = call->error;
goto out;
}
} while (msg_data_left(msg) > 0);
success:
ret = copied;
out:
call->tx_pending = skb;
_leave(" = %d", ret);
return ret;
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);
}
got_user_ID = true;
break;
case RXRPC_ABORT:
if (p->command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
p->command = RXRPC_CMD_SEND_ABORT;
if (len != sizeof(p->abort_code))
return -EINVAL;
p->abort_code = *(unsigned int *)CMSG_DATA(cmsg);
if (p->abort_code == 0)
return -EINVAL;
break;
case RXRPC_ACCEPT:
if (p->command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
p->command = RXRPC_CMD_ACCEPT;
if (len != 0)
return -EINVAL;
break;
case RXRPC_EXCLUSIVE_CALL:
p->exclusive = true;
if (len != 0)
return -EINVAL;
break;
case RXRPC_UPGRADE_SERVICE:
p->upgrade = true;
if (len != 0)
return -EINVAL;
break;
case RXRPC_TX_LENGTH:
if (p->call.tx_total_len != -1 || len != sizeof(__s64))
return -EINVAL;
p->call.tx_total_len = *(__s64 *)CMSG_DATA(cmsg);
if (p->call.tx_total_len < 0)
return -EINVAL;
break;
case RXRPC_SET_CALL_TIMEOUT:
if (len & 3 || len < 4 || len > 12)
return -EINVAL;
memcpy(&p->call.timeouts, CMSG_DATA(cmsg), len);
p->call.nr_timeouts = len / 4;
if (p->call.timeouts.hard > INT_MAX / HZ)
return -ERANGE;
if (p->call.nr_timeouts >= 2 && p->call.timeouts.idle > 60 * 60 * 1000)
return -ERANGE;
if (p->call.nr_timeouts >= 3 && p->call.timeouts.normal > 60 * 60 * 1000)
return -ERANGE;
break;
default:
return -EINVAL;
}
}
if (!got_user_ID)
return -EINVAL;
if (p->call.tx_total_len != -1 && p->command != RXRPC_CMD_SEND_DATA)
return -EINVAL;
_leave(" = 0");
return 0;
}
/*
* Create a new client call for sendmsg().
* - 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.
*/
static struct rxrpc_call *
rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
struct rxrpc_send_params *p)
__releases(&rx->sk.sk_lock.slock)
__acquires(&call->user_mutex)
{
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) {
release_sock(&rx->sk);
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 | p->exclusive;
cp.upgrade = p->upgrade;
cp.service_id = srx->srx_service;
call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL,
atomic_inc_return(&rxrpc_debug_id));
/* The socket is now unlocked */
rxrpc_put_peer(cp.peer);
_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)
__releases(&rx->sk.sk_lock.slock)
__releases(&call->user_mutex)
{
enum rxrpc_call_state state;
struct rxrpc_call *call;
unsigned long now, j;
int ret;
struct rxrpc_send_params p = {
.call.tx_total_len = -1,
.call.user_call_ID = 0,
.call.nr_timeouts = 0,
.abort_code = 0,
.command = RXRPC_CMD_SEND_DATA,
.exclusive = false,
.upgrade = false,
};
_enter("");
ret = rxrpc_sendmsg_cmsg(msg, &p);
if (ret < 0)
goto error_release_sock;
if (p.command == RXRPC_CMD_ACCEPT) {
ret = -EINVAL;
if (rx->sk.sk_state != RXRPC_SERVER_LISTENING)
goto error_release_sock;
call = rxrpc_accept_call(rx, p.call.user_call_ID, NULL);
/* The socket is now unlocked. */
if (IS_ERR(call))
return PTR_ERR(call);
ret = 0;
goto out_put_unlock;
}
call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID);
if (!call) {
ret = -EBADSLT;
if (p.command != RXRPC_CMD_SEND_DATA)
goto error_release_sock;
call = rxrpc_new_client_call_for_sendmsg(rx, msg, &p);
/* The socket is now unlocked... */
if (IS_ERR(call))
return PTR_ERR(call);
/* ... and we have the call lock. */
ret = 0;
if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE)
goto out_put_unlock;
} else {
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_UNINITIALISED:
case RXRPC_CALL_CLIENT_AWAIT_CONN:
case RXRPC_CALL_SERVER_PREALLOC:
case RXRPC_CALL_SERVER_SECURING:
case RXRPC_CALL_SERVER_ACCEPTING:
rxrpc_put_call(call, rxrpc_call_put);
ret = -EBUSY;
goto error_release_sock;
default:
break;
}
ret = mutex_lock_interruptible(&call->user_mutex);
release_sock(&rx->sk);
if (ret < 0) {
ret = -ERESTARTSYS;
goto error_put;
}
if (p.call.tx_total_len != -1) {
ret = -EINVAL;
if (call->tx_total_len != -1 ||
call->tx_pending ||
call->tx_top != 0)
goto error_put;
call->tx_total_len = p.call.tx_total_len;
}
}
switch (p.call.nr_timeouts) {
case 3:
j = msecs_to_jiffies(p.call.timeouts.normal);
if (p.call.timeouts.normal > 0 && j == 0)
j = 1;
WRITE_ONCE(call->next_rx_timo, j);
/* Fall through */
case 2:
j = msecs_to_jiffies(p.call.timeouts.idle);
if (p.call.timeouts.idle > 0 && j == 0)
j = 1;
WRITE_ONCE(call->next_req_timo, j);
/* Fall through */
case 1:
if (p.call.timeouts.hard > 0) {
j = msecs_to_jiffies(p.call.timeouts.hard);
now = jiffies;
j += now;
WRITE_ONCE(call->expect_term_by, j);
rxrpc_reduce_call_timer(call, j, now,
rxrpc_timer_set_for_hard);
}
break;
}
state = READ_ONCE(call->state);
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, state, call->conn);
if (state >= RXRPC_CALL_COMPLETE) {
/* it's too late for this call */
ret = -ESHUTDOWN;
} else if (p.command == RXRPC_CMD_SEND_ABORT) {
ret = 0;
if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED))
ret = rxrpc_send_abort_packet(call);
} else if (p.command != RXRPC_CMD_SEND_DATA) {
ret = -EINVAL;
} else if (rxrpc_is_client_call(call) &&
state != RXRPC_CALL_CLIENT_SEND_REQUEST) {
/* request phase complete for this client call */
ret = -EPROTO;
} else if (rxrpc_is_service_call(call) &&
state != RXRPC_CALL_SERVER_ACK_REQUEST &&
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, NULL);
}
out_put_unlock:
mutex_unlock(&call->user_mutex);
error_put:
rxrpc_put_call(call, rxrpc_call_put);
_leave(" = %d", ret);
return ret;
error_release_sock:
release_sock(&rx->sk);
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
* @notify_end_tx: Notification that the last packet is queued.
*
* 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,
rxrpc_notify_end_tx_t notify_end_tx)
{
int ret;
_enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]);
ASSERTCMP(msg->msg_name, ==, NULL);
ASSERTCMP(msg->msg_control, ==, NULL);
mutex_lock(&call->user_mutex);
_debug("CALL %d USR %lx ST %d on CONN %p",
call->debug_id, call->user_call_ID, call->state, call->conn);
switch (READ_ONCE(call->state)) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
case RXRPC_CALL_SERVER_ACK_REQUEST:
case RXRPC_CALL_SERVER_SEND_REPLY:
ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len,
notify_end_tx);
break;
case RXRPC_CALL_COMPLETE:
read_lock_bh(&call->state_lock);
ret = call->error;
read_unlock_bh(&call->state_lock);
break;
default:
/* Request phase complete for this client call */
trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send"));
ret = -EPROTO;
break;
}
mutex_unlock(&call->user_mutex);
_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
* and return true if the call was aborted, false if it was already complete.
*/
bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call,
u32 abort_code, int error, const char *why)
{
bool aborted;
_enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why);
mutex_lock(&call->user_mutex);
aborted = rxrpc_abort_call(why, call, 0, abort_code, error);
if (aborted)
rxrpc_send_abort_packet(call);
mutex_unlock(&call->user_mutex);
return aborted;
}
EXPORT_SYMBOL(rxrpc_kernel_abort_call);
/**
* rxrpc_kernel_set_tx_length - Set the total Tx length on a call
* @sock: The socket the call is on
* @call: The call to be informed
* @tx_total_len: The amount of data to be transmitted for this call
*
* Allow a kernel service to set the total transmit length on a call. This
* allows buffer-to-packet encrypt-and-copy to be performed.
*
* This function is primarily for use for setting the reply length since the
* request length can be set when beginning the call.
*/
void rxrpc_kernel_set_tx_length(struct socket *sock, struct rxrpc_call *call,
s64 tx_total_len)
{
WARN_ON(call->tx_total_len != -1);
call->tx_total_len = tx_total_len;
}
EXPORT_SYMBOL(rxrpc_kernel_set_tx_length);
+99
View File
@@ -0,0 +1,99 @@
/* ar-skbuff.c: socket buffer destruction 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/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
#define select_skb_count(op) (op >= rxrpc_skb_tx_cleaned ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs)
/*
* Note the allocation or reception of a socket buffer.
*/
void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
int n = atomic_inc_return(select_skb_count(op));
trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
}
/*
* Note the re-emergence of a socket buffer from a queue or buffer.
*/
void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
if (skb) {
int n = atomic_read(select_skb_count(op));
trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
}
}
/*
* Note the addition of a ref on a socket buffer.
*/
void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
int n = atomic_inc_return(select_skb_count(op));
trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
skb_get(skb);
}
/*
* Note the destruction of a socket buffer.
*/
void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
if (skb) {
int n;
CHECK_SLAB_OKAY(&skb->users);
n = atomic_dec_return(select_skb_count(op));
trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
kfree_skb(skb);
}
}
/*
* Note the injected loss of a socket buffer.
*/
void rxrpc_lose_skb(struct sk_buff *skb, enum rxrpc_skb_trace op)
{
const void *here = __builtin_return_address(0);
if (skb) {
int n;
CHECK_SLAB_OKAY(&skb->users);
n = atomic_dec_return(select_skb_count(op));
trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here);
kfree_skb(skb);
}
}
/*
* Clear a queue of socket buffers.
*/
void rxrpc_purge_queue(struct sk_buff_head *list)
{
const void *here = __builtin_return_address(0);
struct sk_buff *skb;
while ((skb = skb_dequeue((list))) != NULL) {
int n = atomic_dec_return(select_skb_count(rxrpc_skb_rx_purged));
trace_rxrpc_skb(skb, rxrpc_skb_rx_purged,
refcount_read(&skb->users), n, here);
kfree_skb(skb);
}
}
+160
View File
@@ -0,0 +1,160 @@
/* sysctls for configuring RxRPC operating parameters
*
* Copyright (C) 2014 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.
*/
#include <linux/sysctl.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"
static struct ctl_table_header *rxrpc_sysctl_reg_table;
static const unsigned int one = 1;
static const unsigned int four = 4;
static const unsigned int thirtytwo = 32;
static const unsigned int n_65535 = 65535;
static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1;
static const unsigned long one_jiffy = 1;
static const unsigned long max_jiffies = MAX_JIFFY_OFFSET;
/*
* RxRPC operating parameters.
*
* See Documentation/networking/rxrpc.txt and the variable definitions for more
* information on the individual parameters.
*/
static struct ctl_table rxrpc_sysctl_table[] = {
/* Values measured in milliseconds but used in jiffies */
{
.procname = "req_ack_delay",
.data = &rxrpc_requested_ack_delay,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
{
.procname = "soft_ack_delay",
.data = &rxrpc_soft_ack_delay,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_ack_delay",
.data = &rxrpc_idle_ack_delay,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_conn_expiry",
.data = &rxrpc_conn_idle_client_expiry,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
{
.procname = "idle_conn_fast_expiry",
.data = &rxrpc_conn_idle_client_fast_expiry,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
{
.procname = "resend_timeout",
.data = &rxrpc_resend_timeout,
.maxlen = sizeof(unsigned long),
.mode = 0644,
.proc_handler = proc_doulongvec_ms_jiffies_minmax,
.extra1 = (void *)&one_jiffy,
.extra2 = (void *)&max_jiffies,
},
/* Non-time values */
{
.procname = "max_client_conns",
.data = &rxrpc_max_client_connections,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&rxrpc_reap_client_connections,
},
{
.procname = "reap_client_conns",
.data = &rxrpc_reap_client_connections,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&rxrpc_max_client_connections,
},
{
.procname = "max_backlog",
.data = &rxrpc_max_backlog,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&four,
.extra2 = (void *)&thirtytwo,
},
{
.procname = "rx_window_size",
.data = &rxrpc_rx_window_size,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&n_max_acks,
},
{
.procname = "rx_mtu",
.data = &rxrpc_rx_mtu,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&n_65535,
},
{
.procname = "rx_jumbo_max",
.data = &rxrpc_rx_jumbo_max,
.maxlen = sizeof(unsigned int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = (void *)&one,
.extra2 = (void *)&four,
},
{ }
};
int __init rxrpc_sysctl_init(void)
{
rxrpc_sysctl_reg_table = register_net_sysctl(&init_net, "net/rxrpc",
rxrpc_sysctl_table);
if (!rxrpc_sysctl_reg_table)
return -ENOMEM;
return 0;
}
void rxrpc_sysctl_exit(void)
{
if (rxrpc_sysctl_reg_table)
unregister_net_sysctl_table(rxrpc_sysctl_reg_table);
}
+59
View File
@@ -0,0 +1,59 @@
/* Utility routines
*
* Copyright (C) 2015 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.
*/
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/udp.h>
#include "ar-internal.h"
/*
* Fill out a peer address from a socket buffer containing a packet.
*/
int rxrpc_extract_addr_from_skb(struct rxrpc_local *local,
struct sockaddr_rxrpc *srx,
struct sk_buff *skb)
{
memset(srx, 0, sizeof(*srx));
switch (ntohs(skb->protocol)) {
case ETH_P_IP:
if (local->srx.transport.family == AF_INET6) {
srx->transport_type = SOCK_DGRAM;
srx->transport_len = sizeof(srx->transport.sin6);
srx->transport.sin6.sin6_family = AF_INET6;
srx->transport.sin6.sin6_port = udp_hdr(skb)->source;
srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
srx->transport.sin6.sin6_addr.s6_addr32[3] = ip_hdr(skb)->saddr;
} else {
srx->transport_type = SOCK_DGRAM;
srx->transport_len = sizeof(srx->transport.sin);
srx->transport.sin.sin_family = AF_INET;
srx->transport.sin.sin_port = udp_hdr(skb)->source;
srx->transport.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
}
return 0;
#ifdef CONFIG_AF_RXRPC_IPV6
case ETH_P_IPV6:
srx->transport_type = SOCK_DGRAM;
srx->transport_len = sizeof(srx->transport.sin6);
srx->transport.sin6.sin6_family = AF_INET6;
srx->transport.sin6.sin6_port = udp_hdr(skb)->source;
srx->transport.sin6.sin6_addr = ipv6_hdr(skb)->saddr;
return 0;
#endif
default:
pr_warn_ratelimited("AF_RXRPC: Unknown eth protocol %u\n",
ntohs(skb->protocol));
return -EAFNOSUPPORT;
}
}