2007-04-26 16:48:28 -06:00
|
|
|
/* 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.
|
|
|
|
*/
|
|
|
|
|
2016-06-02 13:08:52 -06:00
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
|
2007-04-26 16:48:28 -06:00
|
|
|
#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"
|
|
|
|
|
|
|
|
/*
|
|
|
|
* set up for the ACK at the end of the receive phase when we discard the final
|
|
|
|
* receive phase data packet
|
|
|
|
* - called with softirqs disabled
|
|
|
|
*/
|
|
|
|
static void rxrpc_request_final_ACK(struct rxrpc_call *call)
|
|
|
|
{
|
|
|
|
/* the call may be aborted before we have a chance to ACK it */
|
|
|
|
write_lock(&call->state_lock);
|
|
|
|
|
|
|
|
switch (call->state) {
|
|
|
|
case RXRPC_CALL_CLIENT_RECV_REPLY:
|
|
|
|
call->state = RXRPC_CALL_CLIENT_FINAL_ACK;
|
|
|
|
_debug("request final ACK");
|
|
|
|
|
|
|
|
/* get an extra ref on the call for the final-ACK generator to
|
|
|
|
* release */
|
|
|
|
rxrpc_get_call(call);
|
2016-03-04 08:53:46 -07:00
|
|
|
set_bit(RXRPC_CALL_EV_ACK_FINAL, &call->events);
|
2007-04-26 16:48:28 -06:00
|
|
|
if (try_to_del_timer_sync(&call->ack_timer) >= 0)
|
[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 16:50:17 -06:00
|
|
|
rxrpc_queue_call(call);
|
2007-04-26 16:48:28 -06:00
|
|
|
break;
|
|
|
|
|
|
|
|
case RXRPC_CALL_SERVER_RECV_REQUEST:
|
|
|
|
call->state = RXRPC_CALL_SERVER_ACK_REQUEST;
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
write_unlock(&call->state_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* drop the bottom ACK off of the call ACK window and advance the window
|
|
|
|
*/
|
|
|
|
static void rxrpc_hard_ACK_data(struct rxrpc_call *call,
|
|
|
|
struct rxrpc_skb_priv *sp)
|
|
|
|
{
|
|
|
|
int loop;
|
|
|
|
u32 seq;
|
|
|
|
|
|
|
|
spin_lock_bh(&call->lock);
|
|
|
|
|
2016-03-04 08:53:46 -07:00
|
|
|
_debug("hard ACK #%u", sp->hdr.seq);
|
2007-04-26 16:48:28 -06:00
|
|
|
|
|
|
|
for (loop = 0; loop < RXRPC_ACKR_WINDOW_ASZ; loop++) {
|
|
|
|
call->ackr_window[loop] >>= 1;
|
|
|
|
call->ackr_window[loop] |=
|
|
|
|
call->ackr_window[loop + 1] << (BITS_PER_LONG - 1);
|
|
|
|
}
|
|
|
|
|
2016-03-04 08:53:46 -07:00
|
|
|
seq = sp->hdr.seq;
|
2007-04-26 16:48:28 -06:00
|
|
|
ASSERTCMP(seq, ==, call->rx_data_eaten + 1);
|
|
|
|
call->rx_data_eaten = seq;
|
|
|
|
|
|
|
|
if (call->ackr_win_top < UINT_MAX)
|
|
|
|
call->ackr_win_top++;
|
|
|
|
|
|
|
|
ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE,
|
|
|
|
call->rx_data_post, >=, call->rx_data_recv);
|
|
|
|
ASSERTIFCMP(call->state <= RXRPC_CALL_COMPLETE,
|
|
|
|
call->rx_data_recv, >=, call->rx_data_eaten);
|
|
|
|
|
|
|
|
if (sp->hdr.flags & RXRPC_LAST_PACKET) {
|
|
|
|
rxrpc_request_final_ACK(call);
|
|
|
|
} else if (atomic_dec_and_test(&call->ackr_not_idle) &&
|
|
|
|
test_and_clear_bit(RXRPC_CALL_TX_SOFT_ACK, &call->flags)) {
|
2014-02-07 11:58:44 -07:00
|
|
|
/* We previously soft-ACK'd some received packets that have now
|
|
|
|
* been consumed, so send a hard-ACK if no more packets are
|
|
|
|
* immediately forthcoming to allow the transmitter to free up
|
|
|
|
* its Tx bufferage.
|
|
|
|
*/
|
2007-04-26 16:48:28 -06:00
|
|
|
_debug("send Rx idle ACK");
|
|
|
|
__rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, sp->hdr.serial,
|
2014-02-07 11:58:45 -07:00
|
|
|
false);
|
2007-04-26 16:48:28 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
spin_unlock_bh(&call->lock);
|
|
|
|
}
|
|
|
|
|
rxrpc: Fix races between skb free, ACK generation and replying
Inside the kafs filesystem it is possible to occasionally have a call
processed and terminated before we've had a chance to check whether we need
to clean up the rx queue for that call because afs_send_simple_reply() ends
the call when it is done, but this is done in a workqueue item that might
happen to run to completion before afs_deliver_to_call() completes.
Further, it is possible for rxrpc_kernel_send_data() to be called to send a
reply before the last request-phase data skb is released. The rxrpc skb
destructor is where the ACK processing is done and the call state is
advanced upon release of the last skb. ACK generation is also deferred to
a work item because it's possible that the skb destructor is not called in
a context where kernel_sendmsg() can be invoked.
To this end, the following changes are made:
(1) kernel_rxrpc_data_consumed() is added. This should be called whenever
an skb is emptied so as to crank the ACK and call states. This does
not release the skb, however. kernel_rxrpc_free_skb() must now be
called to achieve that. These together replace
rxrpc_kernel_data_delivered().
(2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed().
This makes afs_deliver_to_call() easier to work as the skb can simply
be discarded unconditionally here without trying to work out what the
return value of the ->deliver() function means.
The ->deliver() functions can, via afs_data_complete(),
afs_transfer_reply() and afs_extract_data() mark that an skb has been
consumed (thereby cranking the state) without the need to
conditionally free the skb to make sure the state is correct on an
incoming call for when the call processor tries to send the reply.
(3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it
has finished with a packet and MSG_PEEK isn't set.
(4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data().
Because of this, we no longer need to clear the destructor and put the
call before we free the skb in cases where we don't want the ACK/call
state to be cranked.
(5) The ->deliver() call-type callbacks are made to return -EAGAIN rather
than 0 if they expect more data (afs_extract_data() returns -EAGAIN to
the delivery function already), and the caller is now responsible for
producing an abort if that was the last packet.
(6) There are many bits of unmarshalling code where:
ret = afs_extract_data(call, skb, last, ...);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
default: return ret;
}
is to be found. As -EAGAIN can now be passed back to the caller, we
now just return if ret < 0:
ret = afs_extract_data(call, skb, last, ...);
if (ret < 0)
return ret;
(7) Checks for trailing data and empty final data packets has been
consolidated as afs_data_complete(). So:
if (skb->len > 0)
return -EBADMSG;
if (!last)
return 0;
becomes:
ret = afs_data_complete(call, skb, last);
if (ret < 0)
return ret;
(8) afs_transfer_reply() now checks the amount of data it has against the
amount of data desired and the amount of data in the skb and returns
an error to induce an abort if we don't get exactly what we want.
Without these changes, the following oops can occasionally be observed,
particularly if some printks are inserted into the delivery path:
general protection fault: 0000 [#1] SMP
Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc]
CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G E 4.7.0-fsdevel+ #1303
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Workqueue: kafsd afs_async_workfn [kafs]
task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000
RIP: 0010:[<ffffffff8108fd3c>] [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1
RSP: 0018:ffff88040c073bc0 EFLAGS: 00010002
RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710
RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f
FS: 0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0
Stack:
0000000000000006 000000000be04930 0000000000000000 ffff880400000000
ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446
ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38
Call Trace:
[<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74
[<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1
[<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189
[<ffffffff810915f4>] lock_acquire+0x122/0x1b6
[<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff814c928f>] skb_dequeue+0x18/0x61
[<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs]
[<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs]
[<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs]
[<ffffffff81063a3a>] process_one_work+0x29d/0x57c
[<ffffffff81064ac2>] worker_thread+0x24a/0x385
[<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0
[<ffffffff810696f5>] kthread+0xf3/0xfb
[<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40
[<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-03 07:11:40 -06:00
|
|
|
/**
|
|
|
|
* rxrpc_kernel_data_consumed - Record consumption of data message
|
|
|
|
* @call: The call to which the message pertains.
|
|
|
|
* @skb: Message holding data
|
|
|
|
*
|
|
|
|
* Record the consumption of a data message and generate an ACK if appropriate.
|
|
|
|
* The call state is shifted if this was the final packet. The caller must be
|
|
|
|
* in process context with no spinlocks held.
|
|
|
|
*
|
|
|
|
* TODO: Actually generate the ACK here rather than punting this to the
|
|
|
|
* workqueue.
|
|
|
|
*/
|
|
|
|
void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
|
|
|
|
|
|
|
|
_enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq);
|
|
|
|
|
|
|
|
ASSERTCMP(sp->call, ==, call);
|
|
|
|
ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA);
|
|
|
|
|
|
|
|
/* TODO: Fix the sequence number tracking */
|
|
|
|
ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv);
|
|
|
|
ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1);
|
|
|
|
ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten);
|
|
|
|
|
|
|
|
call->rx_data_recv = sp->hdr.seq;
|
|
|
|
rxrpc_hard_ACK_data(call, sp);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(rxrpc_kernel_data_consumed);
|
|
|
|
|
2007-04-26 16:48:28 -06:00
|
|
|
/*
|
rxrpc: Fix races between skb free, ACK generation and replying
Inside the kafs filesystem it is possible to occasionally have a call
processed and terminated before we've had a chance to check whether we need
to clean up the rx queue for that call because afs_send_simple_reply() ends
the call when it is done, but this is done in a workqueue item that might
happen to run to completion before afs_deliver_to_call() completes.
Further, it is possible for rxrpc_kernel_send_data() to be called to send a
reply before the last request-phase data skb is released. The rxrpc skb
destructor is where the ACK processing is done and the call state is
advanced upon release of the last skb. ACK generation is also deferred to
a work item because it's possible that the skb destructor is not called in
a context where kernel_sendmsg() can be invoked.
To this end, the following changes are made:
(1) kernel_rxrpc_data_consumed() is added. This should be called whenever
an skb is emptied so as to crank the ACK and call states. This does
not release the skb, however. kernel_rxrpc_free_skb() must now be
called to achieve that. These together replace
rxrpc_kernel_data_delivered().
(2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed().
This makes afs_deliver_to_call() easier to work as the skb can simply
be discarded unconditionally here without trying to work out what the
return value of the ->deliver() function means.
The ->deliver() functions can, via afs_data_complete(),
afs_transfer_reply() and afs_extract_data() mark that an skb has been
consumed (thereby cranking the state) without the need to
conditionally free the skb to make sure the state is correct on an
incoming call for when the call processor tries to send the reply.
(3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it
has finished with a packet and MSG_PEEK isn't set.
(4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data().
Because of this, we no longer need to clear the destructor and put the
call before we free the skb in cases where we don't want the ACK/call
state to be cranked.
(5) The ->deliver() call-type callbacks are made to return -EAGAIN rather
than 0 if they expect more data (afs_extract_data() returns -EAGAIN to
the delivery function already), and the caller is now responsible for
producing an abort if that was the last packet.
(6) There are many bits of unmarshalling code where:
ret = afs_extract_data(call, skb, last, ...);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
default: return ret;
}
is to be found. As -EAGAIN can now be passed back to the caller, we
now just return if ret < 0:
ret = afs_extract_data(call, skb, last, ...);
if (ret < 0)
return ret;
(7) Checks for trailing data and empty final data packets has been
consolidated as afs_data_complete(). So:
if (skb->len > 0)
return -EBADMSG;
if (!last)
return 0;
becomes:
ret = afs_data_complete(call, skb, last);
if (ret < 0)
return ret;
(8) afs_transfer_reply() now checks the amount of data it has against the
amount of data desired and the amount of data in the skb and returns
an error to induce an abort if we don't get exactly what we want.
Without these changes, the following oops can occasionally be observed,
particularly if some printks are inserted into the delivery path:
general protection fault: 0000 [#1] SMP
Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc]
CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G E 4.7.0-fsdevel+ #1303
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Workqueue: kafsd afs_async_workfn [kafs]
task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000
RIP: 0010:[<ffffffff8108fd3c>] [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1
RSP: 0018:ffff88040c073bc0 EFLAGS: 00010002
RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710
RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f
FS: 0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0
Stack:
0000000000000006 000000000be04930 0000000000000000 ffff880400000000
ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446
ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38
Call Trace:
[<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74
[<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1
[<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189
[<ffffffff810915f4>] lock_acquire+0x122/0x1b6
[<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff814c928f>] skb_dequeue+0x18/0x61
[<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs]
[<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs]
[<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs]
[<ffffffff81063a3a>] process_one_work+0x29d/0x57c
[<ffffffff81064ac2>] worker_thread+0x24a/0x385
[<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0
[<ffffffff810696f5>] kthread+0xf3/0xfb
[<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40
[<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-03 07:11:40 -06:00
|
|
|
* Destroy a packet that has an RxRPC control buffer
|
2007-04-26 16:48:28 -06:00
|
|
|
*/
|
|
|
|
void rxrpc_packet_destructor(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
|
|
|
|
struct rxrpc_call *call = sp->call;
|
|
|
|
|
|
|
|
_enter("%p{%p}", skb, call);
|
|
|
|
|
|
|
|
if (call) {
|
rxrpc: Fix races between skb free, ACK generation and replying
Inside the kafs filesystem it is possible to occasionally have a call
processed and terminated before we've had a chance to check whether we need
to clean up the rx queue for that call because afs_send_simple_reply() ends
the call when it is done, but this is done in a workqueue item that might
happen to run to completion before afs_deliver_to_call() completes.
Further, it is possible for rxrpc_kernel_send_data() to be called to send a
reply before the last request-phase data skb is released. The rxrpc skb
destructor is where the ACK processing is done and the call state is
advanced upon release of the last skb. ACK generation is also deferred to
a work item because it's possible that the skb destructor is not called in
a context where kernel_sendmsg() can be invoked.
To this end, the following changes are made:
(1) kernel_rxrpc_data_consumed() is added. This should be called whenever
an skb is emptied so as to crank the ACK and call states. This does
not release the skb, however. kernel_rxrpc_free_skb() must now be
called to achieve that. These together replace
rxrpc_kernel_data_delivered().
(2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed().
This makes afs_deliver_to_call() easier to work as the skb can simply
be discarded unconditionally here without trying to work out what the
return value of the ->deliver() function means.
The ->deliver() functions can, via afs_data_complete(),
afs_transfer_reply() and afs_extract_data() mark that an skb has been
consumed (thereby cranking the state) without the need to
conditionally free the skb to make sure the state is correct on an
incoming call for when the call processor tries to send the reply.
(3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it
has finished with a packet and MSG_PEEK isn't set.
(4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data().
Because of this, we no longer need to clear the destructor and put the
call before we free the skb in cases where we don't want the ACK/call
state to be cranked.
(5) The ->deliver() call-type callbacks are made to return -EAGAIN rather
than 0 if they expect more data (afs_extract_data() returns -EAGAIN to
the delivery function already), and the caller is now responsible for
producing an abort if that was the last packet.
(6) There are many bits of unmarshalling code where:
ret = afs_extract_data(call, skb, last, ...);
switch (ret) {
case 0: break;
case -EAGAIN: return 0;
default: return ret;
}
is to be found. As -EAGAIN can now be passed back to the caller, we
now just return if ret < 0:
ret = afs_extract_data(call, skb, last, ...);
if (ret < 0)
return ret;
(7) Checks for trailing data and empty final data packets has been
consolidated as afs_data_complete(). So:
if (skb->len > 0)
return -EBADMSG;
if (!last)
return 0;
becomes:
ret = afs_data_complete(call, skb, last);
if (ret < 0)
return ret;
(8) afs_transfer_reply() now checks the amount of data it has against the
amount of data desired and the amount of data in the skb and returns
an error to induce an abort if we don't get exactly what we want.
Without these changes, the following oops can occasionally be observed,
particularly if some printks are inserted into the delivery path:
general protection fault: 0000 [#1] SMP
Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc]
CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G E 4.7.0-fsdevel+ #1303
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Workqueue: kafsd afs_async_workfn [kafs]
task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000
RIP: 0010:[<ffffffff8108fd3c>] [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1
RSP: 0018:ffff88040c073bc0 EFLAGS: 00010002
RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710
RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f
FS: 0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0
Stack:
0000000000000006 000000000be04930 0000000000000000 ffff880400000000
ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446
ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38
Call Trace:
[<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74
[<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1
[<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189
[<ffffffff810915f4>] lock_acquire+0x122/0x1b6
[<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49
[<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
[<ffffffff814c928f>] skb_dequeue+0x18/0x61
[<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs]
[<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs]
[<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs]
[<ffffffff81063a3a>] process_one_work+0x29d/0x57c
[<ffffffff81064ac2>] worker_thread+0x24a/0x385
[<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0
[<ffffffff810696f5>] kthread+0xf3/0xfb
[<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40
[<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-03 07:11:40 -06:00
|
|
|
if (atomic_dec_return(&call->skb_count) < 0)
|
|
|
|
BUG();
|
2007-04-26 16:48:28 -06:00
|
|
|
rxrpc_put_call(call);
|
|
|
|
sp->call = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (skb->sk)
|
|
|
|
sock_rfree(skb);
|
|
|
|
_leave("");
|
|
|
|
}
|
[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 16:50:17 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* rxrpc_kernel_free_skb - Free an RxRPC socket buffer
|
|
|
|
* @skb: The socket buffer to be freed
|
|
|
|
*
|
|
|
|
* Let RxRPC free its own socket buffer, permitting it to maintain debug
|
|
|
|
* accounting.
|
|
|
|
*/
|
|
|
|
void rxrpc_kernel_free_skb(struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
rxrpc_free_skb(skb);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(rxrpc_kernel_free_skb);
|