linux/net/rxrpc/ar-local.c

409 lines
9.8 KiB
C
Raw Normal View History

/* 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.
*/
#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/udp.h>
#include <linux/ip.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";
static LIST_HEAD(rxrpc_locals);
DEFINE_RWLOCK(rxrpc_local_lock);
static DECLARE_RWSEM(rxrpc_local_sem);
static DECLARE_WAIT_QUEUE_HEAD(rxrpc_local_wq);
static void rxrpc_destroy_local(struct work_struct *work);
static void rxrpc_process_local_events(struct work_struct *work);
/*
* allocate a new local
*/
static
struct rxrpc_local *rxrpc_alloc_local(struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL);
if (local) {
INIT_WORK(&local->destroyer, &rxrpc_destroy_local);
INIT_WORK(&local->acceptor, &rxrpc_accept_incoming_calls);
INIT_WORK(&local->rejecter, &rxrpc_reject_packets);
INIT_WORK(&local->event_processor, &rxrpc_process_local_events);
INIT_LIST_HEAD(&local->services);
INIT_LIST_HEAD(&local->link);
init_rwsem(&local->defrag_sem);
skb_queue_head_init(&local->accept_queue);
skb_queue_head_init(&local->reject_queue);
skb_queue_head_init(&local->event_queue);
spin_lock_init(&local->lock);
rwlock_init(&local->services_lock);
atomic_set(&local->usage, 1);
local->debug_id = atomic_inc_return(&rxrpc_debug_id);
memcpy(&local->srx, srx, sizeof(*srx));
}
_leave(" = %p", local);
return local;
}
/*
* create the local socket
* - must be called with rxrpc_local_sem writelocked
*/
static int rxrpc_create_local(struct rxrpc_local *local)
{
struct sock *sock;
int ret, opt;
_enter("%p{%d}", local, local->srx.transport_type);
/* create a socket to represent the local endpoint */
ret = sock_create_kern(PF_INET, local->srx.transport_type, IPPROTO_UDP,
&local->socket);
if (ret < 0) {
_leave(" = %d [socket]", ret);
return ret;
}
/* 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");
goto error;
}
}
/* 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;
}
write_lock_bh(&rxrpc_local_lock);
list_add(&local->link, &rxrpc_locals);
write_unlock_bh(&rxrpc_local_lock);
/* set the socket up */
sock = local->socket->sk;
sock->sk_user_data = local;
sock->sk_data_ready = rxrpc_data_ready;
sock->sk_error_report = rxrpc_UDP_error_report;
_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;
}
/*
* create a new local endpoint using the specified UDP address
*/
struct rxrpc_local *rxrpc_lookup_local(struct sockaddr_rxrpc *srx)
{
struct rxrpc_local *local;
int ret;
_enter("{%d,%u,%pI4+%hu}",
srx->transport_type,
srx->transport.family,
&srx->transport.sin.sin_addr,
ntohs(srx->transport.sin.sin_port));
down_write(&rxrpc_local_sem);
/* see if we have a suitable local local endpoint already */
read_lock_bh(&rxrpc_local_lock);
list_for_each_entry(local, &rxrpc_locals, link) {
_debug("CMP {%d,%u,%pI4+%hu}",
local->srx.transport_type,
local->srx.transport.family,
&local->srx.transport.sin.sin_addr,
ntohs(local->srx.transport.sin.sin_port));
if (local->srx.transport_type != srx->transport_type ||
local->srx.transport.family != srx->transport.family)
continue;
switch (srx->transport.family) {
case AF_INET:
if (local->srx.transport.sin.sin_port !=
srx->transport.sin.sin_port)
continue;
if (memcmp(&local->srx.transport.sin.sin_addr,
&srx->transport.sin.sin_addr,
sizeof(struct in_addr)) != 0)
continue;
goto found_local;
default:
BUG();
}
}
read_unlock_bh(&rxrpc_local_lock);
/* we didn't find one, so we need to create one */
local = rxrpc_alloc_local(srx);
if (!local) {
up_write(&rxrpc_local_sem);
return ERR_PTR(-ENOMEM);
}
ret = rxrpc_create_local(local);
if (ret < 0) {
up_write(&rxrpc_local_sem);
kfree(local);
_leave(" = %d", ret);
return ERR_PTR(ret);
}
up_write(&rxrpc_local_sem);
_net("LOCAL new %d {%d,%u,%pI4+%hu}",
local->debug_id,
local->srx.transport_type,
local->srx.transport.family,
&local->srx.transport.sin.sin_addr,
ntohs(local->srx.transport.sin.sin_port));
_leave(" = %p [new]", local);
return local;
found_local:
rxrpc_get_local(local);
read_unlock_bh(&rxrpc_local_lock);
up_write(&rxrpc_local_sem);
_net("LOCAL old %d {%d,%u,%pI4+%hu}",
local->debug_id,
local->srx.transport_type,
local->srx.transport.family,
&local->srx.transport.sin.sin_addr,
ntohs(local->srx.transport.sin.sin_port));
_leave(" = %p [reuse]", local);
return local;
}
/*
* release a local endpoint
*/
void rxrpc_put_local(struct rxrpc_local *local)
{
_enter("%p{u=%d}", local, atomic_read(&local->usage));
ASSERTCMP(atomic_read(&local->usage), >, 0);
/* to prevent a race, the decrement and the dequeue must be effectively
* atomic */
write_lock_bh(&rxrpc_local_lock);
if (unlikely(atomic_dec_and_test(&local->usage))) {
_debug("destroy local");
[AF_RXRPC]: Add an interface to the AF_RXRPC module for the AFS filesystem to use Add an interface to the AF_RXRPC module so that the AFS filesystem module can more easily make use of the services available. AFS still opens a socket but then uses the action functions in lieu of sendmsg() and registers an intercept functions to grab messages before they're queued on the socket Rx queue. This permits AFS (or whatever) to: (1) Avoid the overhead of using the recvmsg() call. (2) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (3) Avoid calling request_key() at the point of issue of a call or opening of a socket. This is done instead by AFS at the point of open(), unlink() or other VFS operation and the key handed through. (4) Request the use of something other than GFP_KERNEL to allocate memory. Furthermore: (*) The socket buffer markings used by RxRPC are made available for AFS so that it can interpret the cooked RxRPC messages itself. (*) rxgen (un)marshalling abort codes are made available. The following documentation for the kernel interface is added to Documentation/networking/rxrpc.txt: ========================= AF_RXRPC KERNEL INTERFACE ========================= The AF_RXRPC module also provides an interface for use by in-kernel utilities such as the AFS filesystem. This permits such a utility to: (1) Use different keys directly on individual client calls on one socket rather than having to open a whole slew of sockets, one for each key it might want to use. (2) Avoid having RxRPC call request_key() at the point of issue of a call or opening of a socket. Instead the utility is responsible for requesting a key at the appropriate point. AFS, for instance, would do this during VFS operations such as open() or unlink(). The key is then handed through when the call is initiated. (3) Request the use of something other than GFP_KERNEL to allocate memory. (4) Avoid the overhead of using the recvmsg() call. RxRPC messages can be intercepted before they get put into the socket Rx queue and the socket buffers manipulated directly. To use the RxRPC facility, a kernel utility must still open an AF_RXRPC socket, bind an addess as appropriate and listen if it's to be a server socket, but then it passes this to the kernel interface functions. The kernel interface functions are as follows: (*) Begin a new client call. struct rxrpc_call * rxrpc_kernel_begin_call(struct socket *sock, struct sockaddr_rxrpc *srx, struct key *key, unsigned long user_call_ID, gfp_t gfp); This allocates the infrastructure to make a new RxRPC call and assigns call and connection numbers. The call will be made on the UDP port that the socket is bound to. The call will go to the destination address of a connected client socket unless an alternative is supplied (srx is non-NULL). If a key is supplied then this will be used to secure the call instead of the key bound to the socket with the RXRPC_SECURITY_KEY sockopt. Calls secured in this way will still share connections if at all possible. The user_call_ID is equivalent to that supplied to sendmsg() in the control data buffer. It is entirely feasible to use this to point to a kernel data structure. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) End a client call. void rxrpc_kernel_end_call(struct rxrpc_call *call); This is used to end a previously begun call. The user_call_ID is expunged from AF_RXRPC's knowledge and will not be seen again in association with the specified call. (*) Send data through a call. int rxrpc_kernel_send_data(struct rxrpc_call *call, struct msghdr *msg, size_t len); This is used to supply either the request part of a client call or the reply part of a server call. msg.msg_iovlen and msg.msg_iov specify the data buffers to be used. msg_iov may not be NULL and must point exclusively to in-kernel virtual addresses. msg.msg_flags may be given MSG_MORE if there will be subsequent data sends for this call. The msg must not specify a destination address, control data or any flags other than MSG_MORE. len is the total amount of data to transmit. (*) Abort a call. void rxrpc_kernel_abort_call(struct rxrpc_call *call, u32 abort_code); This is used to abort a call if it's still in an abortable state. The abort code specified will be placed in the ABORT message sent. (*) Intercept received RxRPC messages. typedef void (*rxrpc_interceptor_t)(struct sock *sk, unsigned long user_call_ID, struct sk_buff *skb); void rxrpc_kernel_intercept_rx_messages(struct socket *sock, rxrpc_interceptor_t interceptor); This installs an interceptor function on the specified AF_RXRPC socket. All messages that would otherwise wind up in the socket's Rx queue are then diverted to this function. Note that care must be taken to process the messages in the right order to maintain DATA message sequentiality. The interceptor function itself is provided with the address of the socket and handling the incoming message, the ID assigned by the kernel utility to the call and the socket buffer containing the message. The skb->mark field indicates the type of message: MARK MEANING =============================== ======================================= RXRPC_SKB_MARK_DATA Data message RXRPC_SKB_MARK_FINAL_ACK Final ACK received for an incoming call RXRPC_SKB_MARK_BUSY Client call rejected as server busy RXRPC_SKB_MARK_REMOTE_ABORT Call aborted by peer RXRPC_SKB_MARK_NET_ERROR Network error detected RXRPC_SKB_MARK_LOCAL_ERROR Local error encountered RXRPC_SKB_MARK_NEW_CALL New incoming call awaiting acceptance The remote abort message can be probed with rxrpc_kernel_get_abort_code(). The two error messages can be probed with rxrpc_kernel_get_error_number(). A new call can be accepted with rxrpc_kernel_accept_call(). Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a data message has been used up, rxrpc_kernel_data_delivered() should be called on it.. Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose of. It is possible to get extra refs on all types of message for later freeing, but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. struct rxrpc_call * rxrpc_kernel_accept_call(struct socket *sock, unsigned long user_call_ID); This is used to accept an incoming call and to assign it a call ID. This function is similar to rxrpc_kernel_begin_call() and calls accepted must be ended in the same way. If this function is successful, an opaque reference to the RxRPC call is returned. The caller now holds a reference on this and it must be properly ended. (*) Reject an incoming call. int rxrpc_kernel_reject_call(struct socket *sock); This is used to reject the first incoming call on the socket's queue with a BUSY message. -ENODATA is returned if there were no incoming calls. Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). (*) Record the delivery of a data message and free it. void rxrpc_kernel_data_delivered(struct sk_buff *skb); This is used to record a data message as having been delivered and to update the ACK state for the call. The socket buffer will be freed. (*) Free a message. void rxrpc_kernel_free_skb(struct sk_buff *skb); This is used to free a non-DATA socket buffer intercepted from an AF_RXRPC socket. (*) Determine if a data message is the last one on a call. bool rxrpc_kernel_is_data_last(struct sk_buff *skb); This is used to determine if a socket buffer holds the last data message to be received for a call (true will be returned if it does, false if not). The data message will be part of the reply on a client call and the request on an incoming call. In the latter case there will be more messages, but in the former case there will not. (*) Get the abort code from an abort message. u32 rxrpc_kernel_get_abort_code(struct sk_buff *skb); This is used to extract the abort code from a remote abort message. (*) Get the error number from a local or network error message. int rxrpc_kernel_get_error_number(struct sk_buff *skb); This is used to extract the error number from a message indicating either a local error occurred or a network error occurred. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-26 22:50:17 +00:00
rxrpc_queue_work(&local->destroyer);
}
write_unlock_bh(&rxrpc_local_lock);
_leave("");
}
/*
* destroy a local endpoint
*/
static void rxrpc_destroy_local(struct work_struct *work)
{
struct rxrpc_local *local =
container_of(work, struct rxrpc_local, destroyer);
_enter("%p{%d}", local, atomic_read(&local->usage));
down_write(&rxrpc_local_sem);
write_lock_bh(&rxrpc_local_lock);
if (atomic_read(&local->usage) > 0) {
write_unlock_bh(&rxrpc_local_lock);
up_read(&rxrpc_local_sem);
_leave(" [resurrected]");
return;
}
list_del(&local->link);
local->socket->sk->sk_user_data = NULL;
write_unlock_bh(&rxrpc_local_lock);
downgrade_write(&rxrpc_local_sem);
ASSERT(list_empty(&local->services));
ASSERT(!work_pending(&local->acceptor));
ASSERT(!work_pending(&local->rejecter));
ASSERT(!work_pending(&local->event_processor));
/* finish cleaning up the local descriptor */
rxrpc_purge_queue(&local->accept_queue);
rxrpc_purge_queue(&local->reject_queue);
rxrpc_purge_queue(&local->event_queue);
kernel_sock_shutdown(local->socket, SHUT_RDWR);
sock_release(local->socket);
up_read(&rxrpc_local_sem);
_net("DESTROY LOCAL %d", local->debug_id);
kfree(local);
if (list_empty(&rxrpc_locals))
wake_up_all(&rxrpc_local_wq);
_leave("");
}
/*
* preemptively destroy all local local endpoint rather than waiting for
* them to be destroyed
*/
void __exit rxrpc_destroy_all_locals(void)
{
DECLARE_WAITQUEUE(myself,current);
_enter("");
/* we simply have to wait for them to go away */
if (!list_empty(&rxrpc_locals)) {
set_current_state(TASK_UNINTERRUPTIBLE);
add_wait_queue(&rxrpc_local_wq, &myself);
while (!list_empty(&rxrpc_locals)) {
schedule();
set_current_state(TASK_UNINTERRUPTIBLE);
}
remove_wait_queue(&rxrpc_local_wq, &myself);
set_current_state(TASK_RUNNING);
}
_leave("");
}
/*
* Reply to a version request
*/
static void rxrpc_send_version_request(struct rxrpc_local *local,
struct rxrpc_header *hdr,
struct sk_buff *skb)
{
struct sockaddr_in sin;
struct msghdr msg;
struct kvec iov[2];
size_t len;
int ret;
_enter("");
sin.sin_family = AF_INET;
sin.sin_port = udp_hdr(skb)->source;
sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
msg.msg_name = &sin;
msg.msg_namelen = sizeof(sin);
msg.msg_control = NULL;
msg.msg_controllen = 0;
msg.msg_flags = 0;
hdr->seq = 0;
hdr->serial = 0;
hdr->type = RXRPC_PACKET_TYPE_VERSION;
hdr->flags = RXRPC_LAST_PACKET | (~hdr->flags & RXRPC_CLIENT_INITIATED);
hdr->userStatus = 0;
hdr->_rsvd = 0;
iov[0].iov_base = hdr;
iov[0].iov_len = sizeof(*hdr);
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)
_debug("sendmsg failed: %d", ret);
_leave("");
}
/*
* Process event packets targetted at a local endpoint.
*/
static void rxrpc_process_local_events(struct work_struct *work)
{
struct rxrpc_local *local = container_of(work, struct rxrpc_local, event_processor);
struct sk_buff *skb;
char v;
_enter("");
atomic_inc(&local->usage);
while ((skb = skb_dequeue(&local->event_queue))) {
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
kdebug("{%d},{%u}", local->debug_id, sp->hdr.type);
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
if (skb_copy_bits(skb, 0, &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_put_local(local);
rxrpc_free_skb(skb);
}
rxrpc_put_local(local);
_leave("");
}