/* * mft.h - Defines for mft record handling in NTFS Linux kernel driver. * Part of the Linux-NTFS project. * * Copyright (c) 2001-2004 Anton Altaparmakov * * This program/include file 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. * * This program/include file is distributed in the hope that it will be * useful, but WITHOUT ANY WARRANTY; without even the implied warranty * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program (in the main directory of the Linux-NTFS * distribution in the file COPYING); if not, write to the Free Software * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef _LINUX_NTFS_MFT_H #define _LINUX_NTFS_MFT_H #include #include #include #include "inode.h" extern MFT_RECORD *map_mft_record(ntfs_inode *ni); extern void unmap_mft_record(ntfs_inode *ni); extern MFT_RECORD *map_extent_mft_record(ntfs_inode *base_ni, MFT_REF mref, ntfs_inode **ntfs_ino); static inline void unmap_extent_mft_record(ntfs_inode *ni) { unmap_mft_record(ni); return; } #ifdef NTFS_RW /** * flush_dcache_mft_record_page - flush_dcache_page() for mft records * @ni: ntfs inode structure of mft record * * Call flush_dcache_page() for the page in which an mft record resides. * * This must be called every time an mft record is modified, just after the * modification. */ static inline void flush_dcache_mft_record_page(ntfs_inode *ni) { flush_dcache_page(ni->page); } extern void __mark_mft_record_dirty(ntfs_inode *ni); /** * mark_mft_record_dirty - set the mft record and the page containing it dirty * @ni: ntfs inode describing the mapped mft record * * Set the mapped (extent) mft record of the (base or extent) ntfs inode @ni, * as well as the page containing the mft record, dirty. Also, mark the base * vfs inode dirty. This ensures that any changes to the mft record are * written out to disk. * * NOTE: Do not do anything if the mft record is already marked dirty. */ static inline void mark_mft_record_dirty(ntfs_inode *ni) { if (!NInoTestSetDirty(ni)) __mark_mft_record_dirty(ni); } extern int ntfs_sync_mft_mirror(ntfs_volume *vol, const unsigned long mft_no, MFT_RECORD *m, int sync); extern int write_mft_record_nolock(ntfs_inode *ni, MFT_RECORD *m, int sync); /** * write_mft_record - write out a mapped (extent) mft record * @ni: ntfs inode describing the mapped (extent) mft record * @m: mapped (extent) mft record to write * @sync: if true, wait for i/o completion * * This is just a wrapper for write_mft_record_nolock() (see mft.c), which * locks the page for the duration of the write. This ensures that there are * no race conditions between writing the mft record via the dirty inode code * paths and via the page cache write back code paths or between writing * neighbouring mft records residing in the same page. * * Locking the page also serializes us against ->readpage() if the page is not * uptodate. * * On success, clean the mft record and return 0. On error, leave the mft * record dirty and return -errno. */ static inline int write_mft_record(ntfs_inode *ni, MFT_RECORD *m, int sync) { struct page *page = ni->page; int err; BUG_ON(!page); lock_page(page); err = write_mft_record_nolock(ni, m, sync); unlock_page(page); return err; } extern bool ntfs_may_write_mft_record(ntfs_volume *vol, const unsigned long mft_no, const MFT_RECORD *m, ntfs_inode **locked_ni); extern ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, const int mode, ntfs_inode *base_ni, MFT_RECORD **mrec); extern int ntfs_extent_mft_record_free(ntfs_inode *ni, MFT_RECORD *m); #endif /* NTFS_RW */ #endif /* _LINUX_NTFS_MFT_H */ option value='25'>25space:mode:
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /security/keys/encrypted-keys/Makefile
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
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+
Diffstat (limited to 'security/keys/encrypted-keys/Makefile')