Revision 9230a0b65b47fe6856c4468ec0175c4987e5bede authored by Dave Chinner on 20 November 2018, 06:50:08 UTC, committed by Darrick J. Wong on 21 November 2018, 18:10:53 UTC
Long saga. There have been days spent following this through dead end
after dead end in multi-GB event traces. This morning, after writing
a trace-cmd wrapper that enabled me to be more selective about XFS
trace points, I discovered that I could get just enough essential
tracepoints enabled that there was a 50:50 chance the fsx config
would fail at ~115k ops. If it didn't fail at op 115547, I stopped
fsx at op 115548 anyway.

That gave me two traces - one where the problem manifested, and one
where it didn't. After refining the traces to have the necessary
information, I found that in the failing case there was a real
extent in the COW fork compared to an unwritten extent in the
working case.

Walking back through the two traces to the point where the CWO fork
extents actually diverged, I found that the bad case had an extra
unwritten extent in it. This is likely because the bug it led me to
had triggered multiple times in those 115k ops, leaving stray
COW extents around. What I saw was a COW delalloc conversion to an
unwritten extent (as they should always be through
xfs_iomap_write_allocate()) resulted in a /written extent/:

xfs_writepage:        dev 259:0 ino 0x83 pgoff 0x17000 size 0x79a00 offset 0 length 0
xfs_iext_remove:      dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/2 offset 32 block 152 count 20 flag 1 caller xfs_bmap_add_extent_delay_real
xfs_bmap_pre_update:  dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/1 offset 1 block 4503599627239429 count 31 flag 0 caller xfs_bmap_add_extent_delay_real
xfs_bmap_post_update: dev 259:0 ino 0x83 state RC|LF|RF|COW cur 0xffff888247b899c0/1 offset 1 block 121 count 51 flag 0 caller xfs_bmap_add_ex

Basically, Cow fork before:

	0 1            32          52
	+H+DDDDDDDDDDDD+UUUUUUUUUUU+
	   PREV		RIGHT

COW delalloc conversion allocates:

	  1	       32
	  +uuuuuuuuuuuu+
	  NEW

And the result according to the xfs_bmap_post_update trace was:

	0 1            32          52
	+H+wwwwwwwwwwwwwwwwwwwwwwww+
	   PREV

Which is clearly wrong - it should be a merged unwritten extent,
not an unwritten extent.

That lead me to look at the LEFT_FILLING|RIGHT_FILLING|RIGHT_CONTIG
case in xfs_bmap_add_extent_delay_real(), and sure enough, there's
the bug.

It takes the old delalloc extent (PREV) and adds the length of the
RIGHT extent to it, takes the start block from NEW, removes the
RIGHT extent and then updates PREV with the new extent.

What it fails to do is update PREV.br_state. For delalloc, this is
always XFS_EXT_NORM, while in this case we are converting the
delayed allocation to unwritten, so it needs to be updated to
XFS_EXT_UNWRITTEN. This LF|RF|RC case does not do this, and so
the resultant extent is always written.

And that's the bug I've been chasing for a week - a bmap btree bug,
not a reflink/dedupe/copy_file_range bug, but a BMBT bug introduced
with the recent in core extent tree scalability enhancements.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
1 parent 2c30717
Raw File
msg.c
/*
 * net/tipc/msg.c: TIPC message header routines
 *
 * Copyright (c) 2000-2006, 2014-2015, 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
#define BUF_HEADROOM (LL_MAX_HEADER + 48)
#define BUF_TAILROOM 16

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, gfp_t gfp)
{
	struct sk_buff *skb;
	unsigned int buf_size = (BUF_HEADROOM + size + 3) & ~3u;

	skb = alloc_skb_fclone(buf_size, gfp);
	if (skb) {
		skb_reserve(skb, BUF_HEADROOM);
		skb_put(skb, size);
		skb->next = NULL;
	}
	return skb;
}

void tipc_msg_init(u32 own_node, struct tipc_msg *m, u32 user, u32 type,
		   u32 hsize, u32 dnode)
{
	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, own_node);
	msg_set_type(m, type);
	if (hsize > SHORT_H_SIZE) {
		msg_set_orignode(m, own_node);
		msg_set_destnode(m, dnode);
	}
}

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, GFP_ATOMIC);
	if (unlikely(!buf))
		return NULL;

	msg = buf_msg(buf);
	tipc_msg_init(onode, msg, user, type, hdr_sz, dnode);
	msg_set_size(msg, hdr_sz + data_sz);
	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 = NULL;
	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;
		*buf = NULL;
		TIPC_SKB_CB(head)->tail = NULL;
		if (skb_is_nonlinear(head)) {
			skb_walk_frags(head, tail) {
				TIPC_SKB_CB(head)->tail = tail;
			}
		} else {
			skb_frag_list_init(head);
		}
		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) {
		TIPC_SKB_CB(head)->validated = false;
		if (unlikely(!tipc_msg_validate(&head)))
			goto err;
		*buf = head;
		TIPC_SKB_CB(head)->tail = NULL;
		*headbuf = NULL;
		return 1;
	}
	*buf = NULL;
	return 0;
err:
	kfree_skb(*buf);
	kfree_skb(*headbuf);
	*buf = *headbuf = NULL;
	return 0;
}

/* tipc_msg_validate - validate basic format of received message
 *
 * This routine ensures a TIPC message has an acceptable header, and at least
 * as much data as the header indicates it should.  The routine also ensures
 * that the entire message header is stored in the main fragment of the message
 * buffer, to simplify future access to message header fields.
 *
 * Note: Having extra info present in the message header or data areas is OK.
 * TIPC will ignore the excess, under the assumption that it is optional info
 * introduced by a later release of the protocol.
 */
bool tipc_msg_validate(struct sk_buff **_skb)
{
	struct sk_buff *skb = *_skb;
	struct tipc_msg *hdr;
	int msz, hsz;

	/* Ensure that flow control ratio condition is satisfied */
	if (unlikely(skb->truesize / buf_roundup_len(skb) >= 4)) {
		skb = skb_copy_expand(skb, BUF_HEADROOM, 0, GFP_ATOMIC);
		if (!skb)
			return false;
		kfree_skb(*_skb);
		*_skb = skb;
	}

	if (unlikely(TIPC_SKB_CB(skb)->validated))
		return true;
	if (unlikely(!pskb_may_pull(skb, MIN_H_SIZE)))
		return false;

	hsz = msg_hdr_sz(buf_msg(skb));
	if (unlikely(hsz < MIN_H_SIZE) || (hsz > MAX_H_SIZE))
		return false;
	if (unlikely(!pskb_may_pull(skb, hsz)))
		return false;

	hdr = buf_msg(skb);
	if (unlikely(msg_version(hdr) != TIPC_VERSION))
		return false;

	msz = msg_size(hdr);
	if (unlikely(msz < hsz))
		return false;
	if (unlikely((msz - hsz) > TIPC_MAX_USER_MSG_SIZE))
		return false;
	if (unlikely(skb->len < msz))
		return false;

	TIPC_SKB_CB(skb)->validated = true;
	return true;
}

/**
 * tipc_msg_build - create buffer chain containing specified header and data
 * @mhdr: Message header, to be prepended to data
 * @m: User message
 * @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
 *
 * Note that the recursive call we are making here is safe, since it can
 * logically go only one further level down.
 *
 * 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);
	struct tipc_msg pkthdr;
	int msz = mhsz + dsz;
	int pktrem = pktmax;
	struct sk_buff *skb;
	int drem = dsz;
	int pktno = 1;
	char *pktpos;
	int pktsz;
	int rc;

	msg_set_size(mhdr, msz);

	/* No fragmentation needed? */
	if (likely(msz <= pktmax)) {
		skb = tipc_buf_acquire(msz, GFP_KERNEL);

		/* Fall back to smaller MTU if node local message */
		if (unlikely(!skb)) {
			if (pktmax != MAX_MSG_SIZE)
				return -ENOMEM;
			rc = tipc_msg_build(mhdr, m, offset, dsz, FB_MTU, list);
			if (rc != dsz)
				return rc;
			if (tipc_msg_assemble(list))
				return dsz;
			return -ENOMEM;
		}
		skb_orphan(skb);
		__skb_queue_tail(list, skb);
		skb_copy_to_linear_data(skb, mhdr, mhsz);
		pktpos = skb->data + mhsz;
		if (copy_from_iter_full(pktpos, dsz, &m->msg_iter))
			return dsz;
		rc = -EFAULT;
		goto error;
	}

	/* Prepare reusable fragment header */
	tipc_msg_init(msg_prevnode(mhdr), &pkthdr, MSG_FRAGMENTER,
		      FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(mhdr));
	msg_set_size(&pkthdr, pktmax);
	msg_set_fragm_no(&pkthdr, pktno);
	msg_set_importance(&pkthdr, msg_importance(mhdr));

	/* Prepare first fragment */
	skb = tipc_buf_acquire(pktmax, GFP_KERNEL);
	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 (!copy_from_iter_full(pktpos, pktrem, &m->msg_iter)) {
			rc = -EFAULT;
			goto error;
		}
		drem -= 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, GFP_KERNEL);
		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
 * @skb: the buffer to append to ("bundle")
 * @msg:  message 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 *skb, struct tipc_msg *msg, u32 mtu)
{
	struct tipc_msg *bmsg;
	unsigned int bsz;
	unsigned int msz = msg_size(msg);
	u32 start, pad;
	u32 max = mtu - INT_H_SIZE;

	if (likely(msg_user(msg) == MSG_FRAGMENTER))
		return false;
	if (!skb)
		return false;
	bmsg = buf_msg(skb);
	bsz = msg_size(bmsg);
	start = align(bsz);
	pad = start - bsz;

	if (unlikely(msg_user(msg) == TUNNEL_PROTOCOL))
		return false;
	if (unlikely(msg_user(msg) == BCAST_PROTOCOL))
		return false;
	if (unlikely(msg_user(bmsg) != MSG_BUNDLER))
		return false;
	if (unlikely(skb_tailroom(skb) < (pad + msz)))
		return false;
	if (unlikely(max < (start + msz)))
		return false;
	if ((msg_importance(msg) < TIPC_SYSTEM_IMPORTANCE) &&
	    (msg_importance(bmsg) == TIPC_SYSTEM_IMPORTANCE))
		return false;

	skb_put(skb, pad + msz);
	skb_copy_to_linear_data_offset(skb, start, msg, msz);
	msg_set_size(bmsg, start + msz);
	msg_set_msgcnt(bmsg, msg_msgcnt(bmsg) + 1);
	return true;
}

/**
 *  tipc_msg_extract(): extract bundled inner packet from buffer
 *  @skb: buffer to be extracted from.
 *  @iskb: extracted inner buffer, to be returned
 *  @pos: position in outer message of msg to be extracted.
 *        Returns position of next msg
 *  Consumes outer buffer when last packet extracted
 *  Returns true when when there is an extracted buffer, otherwise false
 */
bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
{
	struct tipc_msg *hdr, *ihdr;
	int imsz;

	*iskb = NULL;
	if (unlikely(skb_linearize(skb)))
		goto none;

	hdr = buf_msg(skb);
	if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE)))
		goto none;

	ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos);
	imsz = msg_size(ihdr);

	if ((*pos + imsz) > msg_data_sz(hdr))
		goto none;

	*iskb = tipc_buf_acquire(imsz, GFP_ATOMIC);
	if (!*iskb)
		goto none;

	skb_copy_to_linear_data(*iskb, ihdr, imsz);
	if (unlikely(!tipc_msg_validate(iskb)))
		goto none;

	*pos += align(imsz);
	return true;
none:
	kfree_skb(skb);
	kfree_skb(*iskb);
	*iskb = NULL;
	return false;
}

/**
 * tipc_msg_make_bundle(): Create bundle buf and append message to its tail
 * @list: the buffer chain, where head is the buffer to replace/append
 * @skb: buffer to be created, appended to and returned in case of success
 * @msg: message to be appended
 * @mtu: max allowable size for the bundle buffer, inclusive header
 * @dnode: destination node for message. (Not always present in header)
 * Returns true if success, otherwise false
 */
bool tipc_msg_make_bundle(struct sk_buff **skb,  struct tipc_msg *msg,
			  u32 mtu, u32 dnode)
{
	struct sk_buff *_skb;
	struct tipc_msg *bmsg;
	u32 msz = msg_size(msg);
	u32 max = mtu - INT_H_SIZE;

	if (msg_user(msg) == MSG_FRAGMENTER)
		return false;
	if (msg_user(msg) == TUNNEL_PROTOCOL)
		return false;
	if (msg_user(msg) == BCAST_PROTOCOL)
		return false;
	if (msz > (max / 2))
		return false;

	_skb = tipc_buf_acquire(max, GFP_ATOMIC);
	if (!_skb)
		return false;

	skb_trim(_skb, INT_H_SIZE);
	bmsg = buf_msg(_skb);
	tipc_msg_init(msg_prevnode(msg), bmsg, MSG_BUNDLER, 0,
		      INT_H_SIZE, dnode);
	if (msg_isdata(msg))
		msg_set_importance(bmsg, TIPC_CRITICAL_IMPORTANCE);
	else
		msg_set_importance(bmsg, TIPC_SYSTEM_IMPORTANCE);
	msg_set_seqno(bmsg, msg_seqno(msg));
	msg_set_ack(bmsg, msg_ack(msg));
	msg_set_bcast_ack(bmsg, msg_bcast_ack(msg));
	tipc_msg_bundle(_skb, msg, mtu);
	*skb = _skb;
	return true;
}

/**
 * tipc_msg_reverse(): swap source and destination addresses and add error code
 * @own_node: originating node id for reversed message
 * @skb:  buffer containing message to be reversed; will be consumed
 * @err:  error code to be set in message, if any
 * Replaces consumed buffer with new one when successful
 * Returns true if success, otherwise false
 */
bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
{
	struct sk_buff *_skb = *skb;
	struct tipc_msg *_hdr, *hdr;
	int hlen, dlen;

	if (skb_linearize(_skb))
		goto exit;
	_hdr = buf_msg(_skb);
	dlen = min_t(uint, msg_data_sz(_hdr), MAX_FORWARD_SIZE);
	hlen = msg_hdr_sz(_hdr);

	if (msg_dest_droppable(_hdr))
		goto exit;
	if (msg_errcode(_hdr))
		goto exit;

	/* Never return SHORT header */
	if (hlen == SHORT_H_SIZE)
		hlen = BASIC_H_SIZE;

	/* Don't return data along with SYN+, - sender has a clone */
	if (msg_is_syn(_hdr) && err == TIPC_ERR_OVERLOAD)
		dlen = 0;

	/* Allocate new buffer to return */
	*skb = tipc_buf_acquire(hlen + dlen, GFP_ATOMIC);
	if (!*skb)
		goto exit;
	memcpy((*skb)->data, _skb->data, msg_hdr_sz(_hdr));
	memcpy((*skb)->data + hlen, msg_data(_hdr), dlen);

	/* Build reverse header in new buffer */
	hdr = buf_msg(*skb);
	msg_set_hdr_sz(hdr, hlen);
	msg_set_errcode(hdr, err);
	msg_set_non_seq(hdr, 0);
	msg_set_origport(hdr, msg_destport(_hdr));
	msg_set_destport(hdr, msg_origport(_hdr));
	msg_set_destnode(hdr, msg_prevnode(_hdr));
	msg_set_prevnode(hdr, own_node);
	msg_set_orignode(hdr, own_node);
	msg_set_size(hdr, hlen + dlen);
	skb_orphan(_skb);
	kfree_skb(_skb);
	return true;
exit:
	kfree_skb(_skb);
	*skb = NULL;
	return false;
}

bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy)
{
	struct sk_buff *skb, *_skb;

	skb_queue_walk(msg, skb) {
		_skb = skb_clone(skb, GFP_ATOMIC);
		if (!_skb) {
			__skb_queue_purge(cpy);
			pr_err_ratelimited("Failed to clone buffer chain\n");
			return false;
		}
		__skb_queue_tail(cpy, _skb);
	}
	return true;
}

/**
 * tipc_msg_lookup_dest(): try to find new destination for named message
 * @skb: the buffer containing the message.
 * @err: error code to be used by caller if lookup fails
 * Does not consume buffer
 * Returns true if a destination is found, false otherwise
 */
bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
{
	struct tipc_msg *msg = buf_msg(skb);
	u32 dport, dnode;
	u32 onode = tipc_own_addr(net);

	if (!msg_isdata(msg))
		return false;
	if (!msg_named(msg))
		return false;
	if (msg_errcode(msg))
		return false;
	*err = TIPC_ERR_NO_NAME;
	if (skb_linearize(skb))
		return false;
	msg = buf_msg(skb);
	if (msg_reroute_cnt(msg))
		return false;
	dnode = tipc_scope2node(net, msg_lookup_scope(msg));
	dport = tipc_nametbl_translate(net, msg_nametype(msg),
				       msg_nameinst(msg), &dnode);
	if (!dport)
		return false;
	msg_incr_reroute_cnt(msg);
	if (dnode != onode)
		msg_set_prevnode(msg, onode);
	msg_set_destnode(msg, dnode);
	msg_set_destport(msg, dport);
	*err = TIPC_OK;

	if (!skb_cloned(skb))
		return true;

	return true;
}

/* tipc_msg_assemble() - assemble chain of fragments into one message
 */
bool tipc_msg_assemble(struct sk_buff_head *list)
{
	struct sk_buff *skb, *tmp = NULL;

	if (skb_queue_len(list) == 1)
		return true;

	while ((skb = __skb_dequeue(list))) {
		skb->next = NULL;
		if (tipc_buf_append(&tmp, &skb)) {
			__skb_queue_tail(list, skb);
			return true;
		}
		if (!tmp)
			break;
	}
	__skb_queue_purge(list);
	__skb_queue_head_init(list);
	pr_warn("Failed do assemble buffer\n");
	return false;
}

/* tipc_msg_reassemble() - clone a buffer chain of fragments and
 *                         reassemble the clones into one message
 */
bool tipc_msg_reassemble(struct sk_buff_head *list, struct sk_buff_head *rcvq)
{
	struct sk_buff *skb, *_skb;
	struct sk_buff *frag = NULL;
	struct sk_buff *head = NULL;
	int hdr_len;

	/* Copy header if single buffer */
	if (skb_queue_len(list) == 1) {
		skb = skb_peek(list);
		hdr_len = skb_headroom(skb) + msg_hdr_sz(buf_msg(skb));
		_skb = __pskb_copy(skb, hdr_len, GFP_ATOMIC);
		if (!_skb)
			return false;
		__skb_queue_tail(rcvq, _skb);
		return true;
	}

	/* 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;
	}
	__skb_queue_tail(rcvq, frag);
	return true;
error:
	pr_warn("Failed do clone local mcast rcv buffer\n");
	kfree_skb(head);
	return false;
}

bool tipc_msg_pskb_copy(u32 dst, struct sk_buff_head *msg,
			struct sk_buff_head *cpy)
{
	struct sk_buff *skb, *_skb;

	skb_queue_walk(msg, skb) {
		_skb = pskb_copy(skb, GFP_ATOMIC);
		if (!_skb) {
			__skb_queue_purge(cpy);
			return false;
		}
		msg_set_destnode(buf_msg(_skb), dst);
		__skb_queue_tail(cpy, _skb);
	}
	return true;
}

/* tipc_skb_queue_sorted(); sort pkt into list according to sequence number
 * @list: list to be appended to
 * @seqno: sequence number of buffer to add
 * @skb: buffer to add
 */
void __tipc_skb_queue_sorted(struct sk_buff_head *list, u16 seqno,
			     struct sk_buff *skb)
{
	struct sk_buff *_skb, *tmp;

	if (skb_queue_empty(list) || less(seqno, buf_seqno(skb_peek(list)))) {
		__skb_queue_head(list, skb);
		return;
	}

	if (more(seqno, buf_seqno(skb_peek_tail(list)))) {
		__skb_queue_tail(list, skb);
		return;
	}

	skb_queue_walk_safe(list, _skb, tmp) {
		if (more(seqno, buf_seqno(_skb)))
			continue;
		if (seqno == buf_seqno(_skb))
			break;
		__skb_queue_before(list, _skb, skb);
		return;
	}
	kfree_skb(skb);
}

void tipc_skb_reject(struct net *net, int err, struct sk_buff *skb,
		     struct sk_buff_head *xmitq)
{
	if (tipc_msg_reverse(tipc_own_addr(net), &skb, err))
		__skb_queue_tail(xmitq, skb);
}
back to top