/*
* 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.
*
*/
#ifndef _VXFS_DIR_H_
#define _VXFS_DIR_H_
/*
* Veritas filesystem driver - directory structure.
*
* This file contains the definition of the vxfs directory format.
*/
/*
* VxFS directory block header.
*
* This entry is the head of every filesystem block in a directory.
* It is used for free space management and additionally includes
* a hash for speeding up directory search (lookup).
*
* The hash may be empty and in fact we do not use it all in the
* Linux driver for now.
*/
struct vxfs_dirblk {
__fs16 d_free; /* free space in dirblock */
__fs16 d_nhash; /* no of hash chains */
__fs16 d_hash[1]; /* hash chain */
};
/*
* VXFS_NAMELEN is the maximum length of the d_name field
* of an VxFS directory entry.
*/
#define VXFS_NAMELEN 256
/*
* VxFS directory entry.
*/
struct vxfs_direct {
__fs32 d_ino; /* inode number */
__fs16 d_reclen; /* record length */
__fs16 d_namelen; /* d_name length */
__fs16 d_hashnext; /* next hash entry */
char d_name[VXFS_NAMELEN]; /* name */
};
/*
* VXFS_DIRPAD defines the directory entry boundaries, is _must_ be
* a multiple of four.
* VXFS_NAMEMIN is the length of a directory entry with a NULL d_name.
* VXFS_DIRROUND is an internal macros that rounds a length to a value
* usable for directory sizes.
* VXFS_DIRLEN calculates the directory entry size for an entry with
* a d_name with size len.
*/
#define VXFS_DIRPAD 4
#define VXFS_NAMEMIN offsetof(struct vxfs_direct, d_name)
#define VXFS_DIRROUND(len) ((VXFS_DIRPAD + (len) - 1) & ~(VXFS_DIRPAD -1))
#define VXFS_DIRLEN(len) (VXFS_DIRROUND(VXFS_NAMEMIN + (len)))
/*
* VXFS_DIRBLKOV is the overhead of a specific dirblock.
*/
#define VXFS_DIRBLKOV(sbi, dbp) \
((sizeof(short) * fs16_to_cpu(sbi, dbp->d_nhash)) + 4)
#endif /* _VXFS_DIR_H_ */
dc3341'>crypto
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return
"true" IFF they acquire a reference. But the return value from
atomic_long_inc_not_zero() is a long and may have high bits set,
e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines
is bool so the reference may actually be acquired but the routines
return "false" which results in a reference leak since the caller
assumes it does not need to do a corresponding percpu_ref_put().
This was seen when performing CPU hotplug during I/O, as hangs in
blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start)
raced with percpu_ref_tryget (blk_mq_timeout_work).
Sample stack trace:
__switch_to+0x2c0/0x450
__schedule+0x2f8/0x970
schedule+0x48/0xc0
blk_mq_freeze_queue_wait+0x94/0x120
blk_mq_queue_reinit_work+0xb8/0x180
blk_mq_queue_reinit_prepare+0x84/0xa0
cpuhp_invoke_callback+0x17c/0x600
cpuhp_up_callbacks+0x58/0x150
_cpu_up+0xf0/0x1c0
do_cpu_up+0x120/0x150
cpu_subsys_online+0x64/0xe0
device_online+0xb4/0x120
online_store+0xb4/0xc0
dev_attr_store+0x68/0xa0
sysfs_kf_write+0x80/0xb0
kernfs_fop_write+0x17c/0x250
__vfs_write+0x6c/0x1e0
vfs_write+0xd0/0x270
SyS_write+0x6c/0x110
system_call+0x38/0xe0
Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS,
and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests.
However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0
and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set.
The fix is to make the tryget routines use an actual boolean internally instead
of the atomic long result truncated to a int.
Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints
Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751
Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com>
Reviewed-by: Jens Axboe <axboe@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints")
Cc: stable@vger.kernel.org # v3.18+