/*
 * Copyright (c) 2000-2001 Christoph Hellwig.
 * 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,
 *    without modification.
 * 2. The name of the author may not 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").
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 */

/* 
 * Veritas filesystem driver - object location table support.
 */
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/kernel.h>

#include "vxfs.h"
#include "vxfs_olt.h"
#include "vxfs_extern.h"


static inline void
vxfs_get_fshead(struct vxfs_oltfshead *fshp, struct vxfs_sb_info *infp)
{
	BUG_ON(infp->vsi_fshino);
	infp->vsi_fshino = fs32_to_cpu(infp, fshp->olt_fsino[0]);
}

static inline void
vxfs_get_ilist(struct vxfs_oltilist *ilistp, struct vxfs_sb_info *infp)
{
	BUG_ON(infp->vsi_iext);
	infp->vsi_iext = fs32_to_cpu(infp, ilistp->olt_iext[0]);
}

static inline u_long
vxfs_oblock(struct super_block *sbp, daddr_t block, u_long bsize)
{
	BUG_ON(sbp->s_blocksize % bsize);
	return (block * (sbp->s_blocksize / bsize));
}


/**
 * vxfs_read_olt - read olt
 * @sbp:	superblock of the filesystem
 * @bsize:	blocksize of the filesystem
 *
 * Description:
 *   vxfs_read_olt reads the olt of the filesystem described by @sbp
 *   into main memory and does some basic setup.
 *
 * Returns:
 *   Zero on success, else a negative error code.
 */
int
vxfs_read_olt(struct super_block *sbp, u_long bsize)
{
	struct vxfs_sb_info	*infp = VXFS_SBI(sbp);
	struct buffer_head	*bp;
	struct vxfs_olt		*op;
	char			*oaddr, *eaddr;

	bp = sb_bread(sbp, vxfs_oblock(sbp, infp->vsi_oltext, bsize));
	if (!bp || !bp->b_data)
		goto fail;

	op = (struct vxfs_olt *)bp->b_data;
	if (fs32_to_cpu(infp, op->olt_magic) != VXFS_OLT_MAGIC) {
		printk(KERN_NOTICE "vxfs: ivalid olt magic number\n");
		goto fail;
	}

	/*
	 * It is in theory possible that vsi_oltsize is > 1.
	 * I've not seen any such filesystem yet and I'm lazy..  --hch
	 */
	if (infp->vsi_oltsize > 1) {
		printk(KERN_NOTICE "vxfs: oltsize > 1 detected.\n");
		printk(KERN_NOTICE "vxfs: please notify hch@infradead.org\n");
		goto fail;
	}

	oaddr = bp->b_data + fs32_to_cpu(infp, op->olt_size);
	eaddr = bp->b_data + (infp->vsi_oltsize * sbp->s_blocksize);

	while (oaddr < eaddr) {
		struct vxfs_oltcommon	*ocp =
			(struct vxfs_oltcommon *)oaddr;
		
		switch (fs32_to_cpu(infp, ocp->olt_type)) {
		case VXFS_OLT_FSHEAD:
			vxfs_get_fshead((struct vxfs_oltfshead *)oaddr, infp);
			break;
		case VXFS_OLT_ILIST:
			vxfs_get_ilist((struct vxfs_oltilist *)oaddr, infp);
			break;
		}

		oaddr += fs32_to_cpu(infp, ocp->olt_size);
	}

	brelse(bp);
	return (infp->vsi_fshino && infp->vsi_iext) ? 0 : -EINVAL;

fail:
	brelse(bp);
	return -EINVAL;
}
</option><option value='1'>ignore</option></select></td></tr><tr><td class='label'>mode:</td><td class='ctrl'><select name='dt' onchange='this.form.submit();'><option value='0' selected='selected'>unified</option><option value='1'>ssdiff</option><option value='2'>stat only</option></select></td></tr><tr><td/><td class='ctrl'><noscript><input type='submit' value='reload'/></noscript></td></tr></table></form></div><table summary='commit info' class='commit-info'>
<tr><th>author</th><td>Maxim Patlasov &lt;mpatlasov@virtuozzo.com&gt;</td><td class='right'>2016-12-12 14:32:44 -0800</td></tr>
<tr><th>committer</th><td>Chris Mason &lt;clm@fb.com&gt;</td><td class='right'>2016-12-13 11:01:30 -0800</td></tr>
<tr><th>commit</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/net/nfc?id=2939e1a86f758b55cdba73e29397dd3d94df13bc'>2939e1a86f758b55cdba73e29397dd3d94df13bc</a> (<a href='/cgit.cgi/linux/net-next.git/patch/net/nfc?id=2939e1a86f758b55cdba73e29397dd3d94df13bc'>patch</a>)</td></tr>
<tr><th>tree</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/tree/?id=2939e1a86f758b55cdba73e29397dd3d94df13bc'>6024381b6fe04ed125c7bb6b613d3c3d3bf2b983</a> /<a href='/cgit.cgi/linux/net-next.git/tree/net/nfc?id=2939e1a86f758b55cdba73e29397dd3d94df13bc'>net/nfc</a></td></tr>
<tr><th>parent</th><td colspan='2' class='oid'><a href='/cgit.cgi/linux/net-next.git/commit/net/nfc?id=5f52a2c512a55500349aa261e469d099ede0f256'>5f52a2c512a55500349aa261e469d099ede0f256</a> (<a href='/cgit.cgi/linux/net-next.git/diff/net/nfc?id=2939e1a86f758b55cdba73e29397dd3d94df13bc&amp;id2=5f52a2c512a55500349aa261e469d099ede0f256'>diff</a>)</td></tr></table>
<div class='commit-subject'>btrfs: limit async_work allocation and worker func duration</div><div class='commit-msg'>Problem statement: unprivileged user who has read-write access to more than
one btrfs subvolume may easily consume all kernel memory (eventually
triggering oom-killer).

Reproducer (./mkrmdir below essentially loops over mkdir/rmdir):

[root@kteam1 ~]# cat prep.sh

DEV=/dev/sdb
mkfs.btrfs -f $DEV
mount $DEV /mnt
for i in `seq 1 16`
do
	mkdir /mnt/$i
	btrfs subvolume create /mnt/SV_$i
	ID=`btrfs subvolume list /mnt |grep "SV_$i$" |cut -d ' ' -f 2`
	mount -t btrfs -o subvolid=$ID $DEV /mnt/$i
	chmod a+rwx /mnt/$i
done

[root@kteam1 ~]# sh prep.sh

[maxim@kteam1 ~]$ for i in `seq 1 16`; do ./mkrmdir /mnt/$i 2000 2000 &amp; done

[root@kteam1 ~]# for i in `seq 1 4`; do grep "kmalloc-128" /proc/slabinfo | grep -v dma; sleep 60; done
kmalloc-128        10144  10144    128   32    1 : tunables    0    0    0 : slabdata    317    317      0
kmalloc-128       9992352 9992352    128   32    1 : tunables    0    0    0 : slabdata 312261 312261      0
kmalloc-128       24226752 24226752    128   32    1 : tunables    0    0    0 : slabdata 757086 757086      0
kmalloc-128       42754240 42754240    128   32    1 : tunables    0    0    0 : slabdata 1336070 1336070      0

The huge numbers above come from insane number of async_work-s allocated
and queued by btrfs_wq_run_delayed_node.

The problem is caused by btrfs_wq_run_delayed_node() queuing more and more
works if the number of delayed items is above BTRFS_DELAYED_BACKGROUND. The
worker func (btrfs_async_run_delayed_root) processes at least
BTRFS_DELAYED_BATCH items (if they are present in the list). So, the machinery
works as expected while the list is almost empty. As soon as it is getting
bigger, worker func starts to process more than one item at a time, it takes
longer, and the chances to have async_works queued more than needed is getting
higher.

The problem above is worsened by another flaw of delayed-inode implementation:
if async_work was queued in a throttling branch (number of items &gt;=
BTRFS_DELAYED_WRITEBACK), corresponding worker func won't quit until
the number of items &lt; BTRFS_DELAYED_BACKGROUND / 2. So, it is possible that
the func occupies CPU infinitely (up to 30sec in my experiments): while the
func is trying to drain the list, the user activity may add more and more
items to the list.

The patch fixes both problems in straightforward way: refuse queuing too
many works in btrfs_wq_run_delayed_node and bail out of worker func if
at least BTRFS_DELAYED_WRITEBACK items are processed.

Changed in v2: remove support of thresh == NO_THRESHOLD.

Signed-off-by: Maxim Patlasov &lt;mpatlasov@virtuozzo.com&gt;
Signed-off-by: Chris Mason &lt;clm@fb.com&gt;
Cc: stable@vger.kernel.org # v3.15+
</div><div class='diffstat-header'><a href='/cgit.cgi/linux/net-next.git/diff/?id=2939e1a86f758b55cdba73e29397dd3d94df13bc'>Diffstat</a> (limited to 'net/nfc')</div><table summary='diffstat' class='diffstat'>