linux/net/tipc/msg.c
Ying Xue c93d3baa24 tipc: involve namespace infrastructure
Involve namespace infrastructure, make the "tipc_net_id" global
variable aware of per namespace, and rename it to "net_id". In
order that the conversion can be successfully done, an instance
of networking namespace must be passed to relevant functions,
allowing them to access the "net_id" variable of per namespace.

Signed-off-by: Ying Xue <ying.xue@windriver.com>
Tested-by: Tero Aho <Tero.Aho@coriant.com>
Reviewed-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-12 16:24:32 -05:00

489 lines
13 KiB
C

/*
* net/tipc/msg.c: TIPC message header routines
*
* Copyright (c) 2000-2006, 2014, Ericsson AB
* Copyright (c) 2005, 2010-2011, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the names of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* Alternatively, this software may be distributed under the terms of the
* GNU General Public License ("GPL") version 2 as published by the Free
* Software Foundation.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#include <net/sock.h>
#include "core.h"
#include "msg.h"
#include "addr.h"
#include "name_table.h"
#define MAX_FORWARD_SIZE 1024
static unsigned int align(unsigned int i)
{
return (i + 3) & ~3u;
}
/**
* tipc_buf_acquire - creates a TIPC message buffer
* @size: message size (including TIPC header)
*
* Returns a new buffer with data pointers set to the specified size.
*
* NOTE: Headroom is reserved to allow prepending of a data link header.
* There may also be unrequested tailroom present at the buffer's end.
*/
struct sk_buff *tipc_buf_acquire(u32 size)
{
struct sk_buff *skb;
unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;
skb = alloc_skb_fclone(buf_size, GFP_ATOMIC);
if (skb) {
skb_reserve(skb, BUF_HEADROOM);
skb_put(skb, size);
skb->next = NULL;
}
return skb;
}
void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, u32 hsize,
u32 destnode)
{
memset(m, 0, hsize);
msg_set_version(m);
msg_set_user(m, user);
msg_set_hdr_sz(m, hsize);
msg_set_size(m, hsize);
msg_set_prevnode(m, tipc_own_addr);
msg_set_type(m, type);
if (hsize > SHORT_H_SIZE) {
msg_set_orignode(m, tipc_own_addr);
msg_set_destnode(m, destnode);
}
}
struct sk_buff *tipc_msg_create(uint user, uint type, uint hdr_sz,
uint data_sz, u32 dnode, u32 onode,
u32 dport, u32 oport, int errcode)
{
struct tipc_msg *msg;
struct sk_buff *buf;
buf = tipc_buf_acquire(hdr_sz + data_sz);
if (unlikely(!buf))
return NULL;
msg = buf_msg(buf);
tipc_msg_init(msg, user, type, hdr_sz, dnode);
msg_set_size(msg, hdr_sz + data_sz);
msg_set_prevnode(msg, onode);
msg_set_origport(msg, oport);
msg_set_destport(msg, dport);
msg_set_errcode(msg, errcode);
if (hdr_sz > SHORT_H_SIZE) {
msg_set_orignode(msg, onode);
msg_set_destnode(msg, dnode);
}
return buf;
}
/* tipc_buf_append(): Append a buffer to the fragment list of another buffer
* @*headbuf: in: NULL for first frag, otherwise value returned from prev call
* out: set when successful non-complete reassembly, otherwise NULL
* @*buf: in: the buffer to append. Always defined
* out: head buf after successful complete reassembly, otherwise NULL
* Returns 1 when reassembly complete, otherwise 0
*/
int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
{
struct sk_buff *head = *headbuf;
struct sk_buff *frag = *buf;
struct sk_buff *tail;
struct tipc_msg *msg;
u32 fragid;
int delta;
bool headstolen;
if (!frag)
goto err;
msg = buf_msg(frag);
fragid = msg_type(msg);
frag->next = NULL;
skb_pull(frag, msg_hdr_sz(msg));
if (fragid == FIRST_FRAGMENT) {
if (unlikely(head))
goto err;
if (unlikely(skb_unclone(frag, GFP_ATOMIC)))
goto err;
head = *headbuf = frag;
skb_frag_list_init(head);
TIPC_SKB_CB(head)->tail = NULL;
*buf = NULL;
return 0;
}
if (!head)
goto err;
if (skb_try_coalesce(head, frag, &headstolen, &delta)) {
kfree_skb_partial(frag, headstolen);
} else {
tail = TIPC_SKB_CB(head)->tail;
if (!skb_has_frag_list(head))
skb_shinfo(head)->frag_list = frag;
else
tail->next = frag;
head->truesize += frag->truesize;
head->data_len += frag->len;
head->len += frag->len;
TIPC_SKB_CB(head)->tail = frag;
}
if (fragid == LAST_FRAGMENT) {
*buf = head;
TIPC_SKB_CB(head)->tail = NULL;
*headbuf = NULL;
return 1;
}
*buf = NULL;
return 0;
err:
pr_warn_ratelimited("Unable to build fragment list\n");
kfree_skb(*buf);
kfree_skb(*headbuf);
*buf = *headbuf = NULL;
return 0;
}
/**
* tipc_msg_build - create buffer chain containing specified header and data
* @mhdr: Message header, to be prepended to data
* @m: User message
* @offset: Posision in iov to start copying from
* @dsz: Total length of user data
* @pktmax: Max packet size that can be used
* @list: Buffer or chain of buffers to be returned to caller
*
* Returns message data size or errno: -ENOMEM, -EFAULT
*/
int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
int dsz, int pktmax, struct sk_buff_head *list)
{
int mhsz = msg_hdr_sz(mhdr);
int msz = mhsz + dsz;
int pktno = 1;
int pktsz;
int pktrem = pktmax;
int drem = dsz;
struct tipc_msg pkthdr;
struct sk_buff *skb;
char *pktpos;
int rc;
msg_set_size(mhdr, msz);
/* No fragmentation needed? */
if (likely(msz <= pktmax)) {
skb = tipc_buf_acquire(msz);
if (unlikely(!skb))
return -ENOMEM;
skb_orphan(skb);
__skb_queue_tail(list, skb);
skb_copy_to_linear_data(skb, mhdr, mhsz);
pktpos = skb->data + mhsz;
if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset,
dsz))
return dsz;
rc = -EFAULT;
goto error;
}
/* Prepare reusable fragment header */
tipc_msg_init(&pkthdr, MSG_FRAGMENTER, FIRST_FRAGMENT,
INT_H_SIZE, msg_destnode(mhdr));
msg_set_size(&pkthdr, pktmax);
msg_set_fragm_no(&pkthdr, pktno);
/* Prepare first fragment */
skb = tipc_buf_acquire(pktmax);
if (!skb)
return -ENOMEM;
skb_orphan(skb);
__skb_queue_tail(list, skb);
pktpos = skb->data;
skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
pktpos += INT_H_SIZE;
pktrem -= INT_H_SIZE;
skb_copy_to_linear_data_offset(skb, INT_H_SIZE, mhdr, mhsz);
pktpos += mhsz;
pktrem -= mhsz;
do {
if (drem < pktrem)
pktrem = drem;
if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) {
rc = -EFAULT;
goto error;
}
drem -= pktrem;
offset += pktrem;
if (!drem)
break;
/* Prepare new fragment: */
if (drem < (pktmax - INT_H_SIZE))
pktsz = drem + INT_H_SIZE;
else
pktsz = pktmax;
skb = tipc_buf_acquire(pktsz);
if (!skb) {
rc = -ENOMEM;
goto error;
}
skb_orphan(skb);
__skb_queue_tail(list, skb);
msg_set_type(&pkthdr, FRAGMENT);
msg_set_size(&pkthdr, pktsz);
msg_set_fragm_no(&pkthdr, ++pktno);
skb_copy_to_linear_data(skb, &pkthdr, INT_H_SIZE);
pktpos = skb->data + INT_H_SIZE;
pktrem = pktsz - INT_H_SIZE;
} while (1);
msg_set_type(buf_msg(skb), LAST_FRAGMENT);
return dsz;
error:
__skb_queue_purge(list);
__skb_queue_head_init(list);
return rc;
}
/**
* tipc_msg_bundle(): Append contents of a buffer to tail of an existing one
* @list: the buffer chain of the existing buffer ("bundle")
* @skb: buffer to be appended
* @mtu: max allowable size for the bundle buffer
* Consumes buffer if successful
* Returns true if bundling could be performed, otherwise false
*/
bool tipc_msg_bundle(struct sk_buff_head *list, struct sk_buff *skb, u32 mtu)
{
struct sk_buff *bskb = skb_peek_tail(list);
struct tipc_msg *bmsg = buf_msg(bskb);
struct tipc_msg *msg = buf_msg(skb);
unsigned int bsz = msg_size(bmsg);
unsigned int msz = msg_size(msg);
u32 start = align(bsz);
u32 max = mtu - INT_H_SIZE;
u32 pad = start - bsz;
if (likely(msg_user(msg) == MSG_FRAGMENTER))
return false;
if (unlikely(msg_user(msg) == CHANGEOVER_PROTOCOL))
return false;
if (unlikely(msg_user(msg) == BCAST_PROTOCOL))
return false;
if (likely(msg_user(bmsg) != MSG_BUNDLER))
return false;
if (likely(!TIPC_SKB_CB(bskb)->bundling))
return false;
if (unlikely(skb_tailroom(bskb) < (pad + msz)))
return false;
if (unlikely(max < (start + msz)))
return false;
skb_put(bskb, pad + msz);
skb_copy_to_linear_data_offset(bskb, start, skb->data, msz);
msg_set_size(bmsg, start + msz);
msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
kfree_skb(skb);
return true;
}
/**
* tipc_msg_make_bundle(): Create bundle buf and append message to its tail
* @list: the buffer chain
* @skb: buffer to be appended and replaced
* @mtu: max allowable size for the bundle buffer, inclusive header
* @dnode: destination node for message. (Not always present in header)
* Replaces buffer if successful
* Returns true if success, otherwise false
*/
bool tipc_msg_make_bundle(struct sk_buff_head *list, struct sk_buff *skb,
u32 mtu, u32 dnode)
{
struct sk_buff *bskb;
struct tipc_msg *bmsg;
struct tipc_msg *msg = buf_msg(skb);
u32 msz = msg_size(msg);
u32 max = mtu - INT_H_SIZE;
if (msg_user(msg) == MSG_FRAGMENTER)
return false;
if (msg_user(msg) == CHANGEOVER_PROTOCOL)
return false;
if (msg_user(msg) == BCAST_PROTOCOL)
return false;
if (msz > (max / 2))
return false;
bskb = tipc_buf_acquire(max);
if (!bskb)
return false;
skb_trim(bskb, INT_H_SIZE);
bmsg = buf_msg(bskb);
tipc_msg_init(bmsg, MSG_BUNDLER, 0, INT_H_SIZE, dnode);
msg_set_seqno(bmsg, msg_seqno(msg));
msg_set_ack(bmsg, msg_ack(msg));
msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
TIPC_SKB_CB(bskb)->bundling = true;
__skb_queue_tail(list, bskb);
return tipc_msg_bundle(list, skb, mtu);
}
/**
* tipc_msg_reverse(): swap source and destination addresses and add error code
* @buf: buffer containing message to be reversed
* @dnode: return value: node where to send message after reversal
* @err: error code to be set in message
* Consumes buffer if failure
* Returns true if success, otherwise false
*/
bool tipc_msg_reverse(struct sk_buff *buf, u32 *dnode, int err)
{
struct tipc_msg *msg = buf_msg(buf);
uint imp = msg_importance(msg);
struct tipc_msg ohdr;
uint rdsz = min_t(uint, msg_data_sz(msg), MAX_FORWARD_SIZE);
if (skb_linearize(buf))
goto exit;
if (msg_dest_droppable(msg))
goto exit;
if (msg_errcode(msg))
goto exit;
memcpy(&ohdr, msg, msg_hdr_sz(msg));
imp = min_t(uint, imp + 1, TIPC_CRITICAL_IMPORTANCE);
if (msg_isdata(msg))
msg_set_importance(msg, imp);
msg_set_errcode(msg, err);
msg_set_origport(msg, msg_destport(&ohdr));
msg_set_destport(msg, msg_origport(&ohdr));
msg_set_prevnode(msg, tipc_own_addr);
if (!msg_short(msg)) {
msg_set_orignode(msg, msg_destnode(&ohdr));
msg_set_destnode(msg, msg_orignode(&ohdr));
}
msg_set_size(msg, msg_hdr_sz(msg) + rdsz);
skb_trim(buf, msg_size(msg));
skb_orphan(buf);
*dnode = msg_orignode(&ohdr);
return true;
exit:
kfree_skb(buf);
return false;
}
/**
* tipc_msg_eval: determine fate of message that found no destination
* @buf: the buffer containing the message.
* @dnode: return value: next-hop node, if message to be forwarded
* @err: error code to use, if message to be rejected
*
* Does not consume buffer
* Returns 0 (TIPC_OK) if message ok and we can try again, -TIPC error
* code if message to be rejected
*/
int tipc_msg_eval(struct sk_buff *buf, u32 *dnode)
{
struct tipc_msg *msg = buf_msg(buf);
u32 dport;
if (msg_type(msg) != TIPC_NAMED_MSG)
return -TIPC_ERR_NO_PORT;
if (skb_linearize(buf))
return -TIPC_ERR_NO_NAME;
if (msg_data_sz(msg) > MAX_FORWARD_SIZE)
return -TIPC_ERR_NO_NAME;
if (msg_reroute_cnt(msg) > 0)
return -TIPC_ERR_NO_NAME;
*dnode = addr_domain(msg_lookup_scope(msg));
dport = tipc_nametbl_translate(msg_nametype(msg),
msg_nameinst(msg),
dnode);
if (!dport)
return -TIPC_ERR_NO_NAME;
msg_incr_reroute_cnt(msg);
msg_set_destnode(msg, *dnode);
msg_set_destport(msg, dport);
return TIPC_OK;
}
/* tipc_msg_reassemble() - clone a buffer chain of fragments and
* reassemble the clones into one message
*/
struct sk_buff *tipc_msg_reassemble(struct sk_buff_head *list)
{
struct sk_buff *skb;
struct sk_buff *frag = NULL;
struct sk_buff *head = NULL;
int hdr_sz;
/* Copy header if single buffer */
if (skb_queue_len(list) == 1) {
skb = skb_peek(list);
hdr_sz = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb));
return __pskb_copy(skb, hdr_sz, GFP_ATOMIC);
}
/* Clone all fragments and reassemble */
skb_queue_walk(list, skb) {
frag = skb_clone(skb, GFP_ATOMIC);
if (!frag)
goto error;
frag->next = NULL;
if (tipc_buf_append(&head, &frag))
break;
if (!head)
goto error;
}
return frag;
error:
pr_warn("Failed do clone local mcast rcv buffer\n");
kfree_skb(head);
return NULL;
}