2006-10-01 02:52:18 +08:00
|
|
|
/* fs/ internal definitions
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
|
|
|
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
|
|
|
*
|
|
|
|
|
* This program 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.
|
|
|
|
|
*/
|
|
|
|
|
|
fs: brlock vfsmount_lock
fs: brlock vfsmount_lock
Use a brlock for the vfsmount lock. It must be taken for write whenever
modifying the mount hash or associated fields, and may be taken for read when
performing mount hash lookups.
A new lock is added for the mnt-id allocator, so it doesn't need to take
the heavy vfsmount write-lock.
The number of atomics should remain the same for fastpath rlock cases, though
code would be slightly slower due to per-cpu access. Scalability is not not be
much improved in common cases yet, due to other locks (ie. dcache_lock) getting
in the way. However path lookups crossing mountpoints should be one case where
scalability is improved (currently requiring the global lock).
The slowpath is slower due to use of brlock. On a 64 core, 64 socket, 32 node
Altix system (high latency to remote nodes), a simple umount microbenchmark
(mount --bind mnt mnt2 ; umount mnt2 loop 1000 times), before this patch it
took 6.8s, afterwards took 7.1s, about 5% slower.
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:39 +08:00
|
|
|
#include <linux/lglock.h>
|
|
|
|
|
|
2006-08-31 18:55:23 +08:00
|
|
|
struct super_block;
|
2011-03-18 10:08:28 +08:00
|
|
|
struct file_system_type;
|
CRED: Make execve() take advantage of copy-on-write credentials
Make execve() take advantage of copy-on-write credentials, allowing it to set
up the credentials in advance, and then commit the whole lot after the point
of no return.
This patch and the preceding patches have been tested with the LTP SELinux
testsuite.
This patch makes several logical sets of alteration:
(1) execve().
The credential bits from struct linux_binprm are, for the most part,
replaced with a single credentials pointer (bprm->cred). This means that
all the creds can be calculated in advance and then applied at the point
of no return with no possibility of failure.
I would like to replace bprm->cap_effective with:
cap_isclear(bprm->cap_effective)
but this seems impossible due to special behaviour for processes of pid 1
(they always retain their parent's capability masks where normally they'd
be changed - see cap_bprm_set_creds()).
The following sequence of events now happens:
(a) At the start of do_execve, the current task's cred_exec_mutex is
locked to prevent PTRACE_ATTACH from obsoleting the calculation of
creds that we make.
(a) prepare_exec_creds() is then called to make a copy of the current
task's credentials and prepare it. This copy is then assigned to
bprm->cred.
This renders security_bprm_alloc() and security_bprm_free()
unnecessary, and so they've been removed.
(b) The determination of unsafe execution is now performed immediately
after (a) rather than later on in the code. The result is stored in
bprm->unsafe for future reference.
(c) prepare_binprm() is called, possibly multiple times.
(i) This applies the result of set[ug]id binaries to the new creds
attached to bprm->cred. Personality bit clearance is recorded,
but now deferred on the basis that the exec procedure may yet
fail.
(ii) This then calls the new security_bprm_set_creds(). This should
calculate the new LSM and capability credentials into *bprm->cred.
This folds together security_bprm_set() and parts of
security_bprm_apply_creds() (these two have been removed).
Anything that might fail must be done at this point.
(iii) bprm->cred_prepared is set to 1.
bprm->cred_prepared is 0 on the first pass of the security
calculations, and 1 on all subsequent passes. This allows SELinux
in (ii) to base its calculations only on the initial script and
not on the interpreter.
(d) flush_old_exec() is called to commit the task to execution. This
performs the following steps with regard to credentials:
(i) Clear pdeath_signal and set dumpable on certain circumstances that
may not be covered by commit_creds().
(ii) Clear any bits in current->personality that were deferred from
(c.i).
(e) install_exec_creds() [compute_creds() as was] is called to install the
new credentials. This performs the following steps with regard to
credentials:
(i) Calls security_bprm_committing_creds() to apply any security
requirements, such as flushing unauthorised files in SELinux, that
must be done before the credentials are changed.
This is made up of bits of security_bprm_apply_creds() and
security_bprm_post_apply_creds(), both of which have been removed.
This function is not allowed to fail; anything that might fail
must have been done in (c.ii).
(ii) Calls commit_creds() to apply the new credentials in a single
assignment (more or less). Possibly pdeath_signal and dumpable
should be part of struct creds.
(iii) Unlocks the task's cred_replace_mutex, thus allowing
PTRACE_ATTACH to take place.
(iv) Clears The bprm->cred pointer as the credentials it was holding
are now immutable.
(v) Calls security_bprm_committed_creds() to apply any security
alterations that must be done after the creds have been changed.
SELinux uses this to flush signals and signal handlers.
(f) If an error occurs before (d.i), bprm_free() will call abort_creds()
to destroy the proposed new credentials and will then unlock
cred_replace_mutex. No changes to the credentials will have been
made.
(2) LSM interface.
A number of functions have been changed, added or removed:
(*) security_bprm_alloc(), ->bprm_alloc_security()
(*) security_bprm_free(), ->bprm_free_security()
Removed in favour of preparing new credentials and modifying those.
(*) security_bprm_apply_creds(), ->bprm_apply_creds()
(*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds()
Removed; split between security_bprm_set_creds(),
security_bprm_committing_creds() and security_bprm_committed_creds().
(*) security_bprm_set(), ->bprm_set_security()
Removed; folded into security_bprm_set_creds().
(*) security_bprm_set_creds(), ->bprm_set_creds()
New. The new credentials in bprm->creds should be checked and set up
as appropriate. bprm->cred_prepared is 0 on the first call, 1 on the
second and subsequent calls.
(*) security_bprm_committing_creds(), ->bprm_committing_creds()
(*) security_bprm_committed_creds(), ->bprm_committed_creds()
New. Apply the security effects of the new credentials. This
includes closing unauthorised files in SELinux. This function may not
fail. When the former is called, the creds haven't yet been applied
to the process; when the latter is called, they have.
The former may access bprm->cred, the latter may not.
(3) SELinux.
SELinux has a number of changes, in addition to those to support the LSM
interface changes mentioned above:
(a) The bprm_security_struct struct has been removed in favour of using
the credentials-under-construction approach.
(c) flush_unauthorized_files() now takes a cred pointer and passes it on
to inode_has_perm(), file_has_perm() and dentry_open().
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: James Morris <jmorris@namei.org>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 07:39:24 +08:00
|
|
|
struct linux_binprm;
|
2009-03-30 07:00:13 +08:00
|
|
|
struct path;
|
2011-11-25 07:22:03 +08:00
|
|
|
struct mount;
|
2006-08-31 18:55:23 +08:00
|
|
|
|
2006-10-01 02:52:18 +08:00
|
|
|
/*
|
|
|
|
|
* block_dev.c
|
|
|
|
|
*/
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#ifdef CONFIG_BLOCK
|
2006-10-01 02:52:18 +08:00
|
|
|
extern void __init bdev_cache_init(void);
|
|
|
|
|
|
2009-04-27 22:43:51 +08:00
|
|
|
extern int __sync_blockdev(struct block_device *bdev, int wait);
|
|
|
|
|
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#else
|
2006-08-31 18:55:23 +08:00
|
|
|
static inline void bdev_cache_init(void)
|
|
|
|
|
{
|
|
|
|
|
}
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
|
2009-04-27 22:43:51 +08:00
|
|
|
static inline int __sync_blockdev(struct block_device *bdev, int wait)
|
|
|
|
|
{
|
|
|
|
|
return 0;
|
|
|
|
|
}
|
[PATCH] BLOCK: Make it possible to disable the block layer [try #6]
Make it possible to disable the block layer. Not all embedded devices require
it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require
the block layer to be present.
This patch does the following:
(*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev
support.
(*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls
an item that uses the block layer. This includes:
(*) Block I/O tracing.
(*) Disk partition code.
(*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS.
(*) The SCSI layer. As far as I can tell, even SCSI chardevs use the
block layer to do scheduling. Some drivers that use SCSI facilities -
such as USB storage - end up disabled indirectly from this.
(*) Various block-based device drivers, such as IDE and the old CDROM
drivers.
(*) MTD blockdev handling and FTL.
(*) JFFS - which uses set_bdev_super(), something it could avoid doing by
taking a leaf out of JFFS2's book.
(*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and
linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is,
however, still used in places, and so is still available.
(*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and
parts of linux/fs.h.
(*) Makes a number of files in fs/ contingent on CONFIG_BLOCK.
(*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK.
(*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK
is not enabled.
(*) fs/no-block.c is created to hold out-of-line stubs and things that are
required when CONFIG_BLOCK is not set:
(*) Default blockdev file operations (to give error ENODEV on opening).
(*) Makes some /proc changes:
(*) /proc/devices does not list any blockdevs.
(*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK.
(*) Makes some compat ioctl handling contingent on CONFIG_BLOCK.
(*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if
given command other than Q_SYNC or if a special device is specified.
(*) In init/do_mounts.c, no reference is made to the blockdev routines if
CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2.
(*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return
error ENOSYS by way of cond_syscall if so).
(*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if
CONFIG_BLOCK is not set, since they can't then happen.
Signed-Off-By: David Howells <dhowells@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
|
|
|
#endif
|
2006-08-30 02:06:07 +08:00
|
|
|
|
2006-10-01 02:52:18 +08:00
|
|
|
/*
|
|
|
|
|
* char_dev.c
|
|
|
|
|
*/
|
|
|
|
|
extern void __init chrdev_init(void);
|
|
|
|
|
|
2012-06-25 19:55:46 +08:00
|
|
|
/*
|
|
|
|
|
* namei.c
|
|
|
|
|
*/
|
|
|
|
|
extern int __inode_permission(struct inode *, int);
|
|
|
|
|
|
2006-10-01 02:52:18 +08:00
|
|
|
/*
|
|
|
|
|
* namespace.c
|
|
|
|
|
*/
|
|
|
|
|
extern int copy_mount_options(const void __user *, unsigned long *);
|
fs: fix overflow in sys_mount() for in-kernel calls
sys_mount() reads/copies a whole page for its "type" parameter. When
do_mount_root() passes a kernel address that points to an object which is
smaller than a whole page, copy_mount_options() will happily go past this
memory object, possibly dereferencing "wild" pointers that could be in any
state (hence the kmemcheck warning, which shows that parts of the next
page are not even allocated).
(The likelihood of something going wrong here is pretty low -- first of
all this only applies to kernel calls to sys_mount(), which are mostly
found in the boot code. Secondly, I guess if the page was not mapped,
exact_copy_from_user() _would_ in fact handle it correctly because of its
access_ok(), etc. checks.)
But it is much nicer to avoid the dubious reads altogether, by stopping as
soon as we find a NUL byte. Is there a good reason why we can't do
something like this, using the already existing strndup_from_user()?
[akpm@linux-foundation.org: make copy_mount_string() static]
[AV: fix compat mount breakage, which involves undoing akpm's change above]
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: al <al@dizzy.pdmi.ras.ru>
2009-09-19 04:05:45 +08:00
|
|
|
extern int copy_mount_string(const void __user *, char **);
|
2008-03-23 03:48:17 +08:00
|
|
|
|
2011-03-21 22:28:58 +08:00
|
|
|
extern struct vfsmount *lookup_mnt(struct path *);
|
2011-01-17 14:35:23 +08:00
|
|
|
extern int finish_automount(struct vfsmount *, struct path *);
|
2008-03-23 03:48:17 +08:00
|
|
|
|
2011-11-21 19:11:31 +08:00
|
|
|
extern int sb_prepare_remount_readonly(struct super_block *);
|
2011-01-15 11:30:21 +08:00
|
|
|
|
2008-03-23 03:48:17 +08:00
|
|
|
extern void __init mnt_init(void);
|
2009-03-30 07:00:13 +08:00
|
|
|
|
2012-05-08 12:02:24 +08:00
|
|
|
extern struct lglock vfsmount_lock;
|
fs: brlock vfsmount_lock
fs: brlock vfsmount_lock
Use a brlock for the vfsmount lock. It must be taken for write whenever
modifying the mount hash or associated fields, and may be taken for read when
performing mount hash lookups.
A new lock is added for the mnt-id allocator, so it doesn't need to take
the heavy vfsmount write-lock.
The number of atomics should remain the same for fastpath rlock cases, though
code would be slightly slower due to per-cpu access. Scalability is not not be
much improved in common cases yet, due to other locks (ie. dcache_lock) getting
in the way. However path lookups crossing mountpoints should be one case where
scalability is improved (currently requiring the global lock).
The slowpath is slower due to use of brlock. On a 64 core, 64 socket, 32 node
Altix system (high latency to remote nodes), a simple umount microbenchmark
(mount --bind mnt mnt2 ; umount mnt2 loop 1000 times), before this patch it
took 6.8s, afterwards took 7.1s, about 5% slower.
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:39 +08:00
|
|
|
|
2012-06-12 22:20:35 +08:00
|
|
|
extern int __mnt_want_write(struct vfsmount *);
|
|
|
|
|
extern int __mnt_want_write_file(struct file *);
|
|
|
|
|
extern void __mnt_drop_write(struct vfsmount *);
|
|
|
|
|
extern void __mnt_drop_write_file(struct file *);
|
2010-02-05 15:01:14 +08:00
|
|
|
|
2009-03-30 07:00:13 +08:00
|
|
|
/*
|
|
|
|
|
* fs_struct.c
|
|
|
|
|
*/
|
2013-03-02 12:51:07 +08:00
|
|
|
extern void chroot_fs_refs(const struct path *, const struct path *);
|
2009-04-26 18:25:56 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* file_table.c
|
|
|
|
|
*/
|
tty: fix fu_list abuse
tty: fix fu_list abuse
tty code abuses fu_list, which causes a bug in remount,ro handling.
If a tty device node is opened on a filesystem, then the last link to the inode
removed, the filesystem will be allowed to be remounted readonly. This is
because fs_may_remount_ro does not find the 0 link tty inode on the file sb
list (because the tty code incorrectly removed it to use for its own purpose).
This can result in a filesystem with errors after it is marked "clean".
Taking idea from Christoph's initial patch, allocate a tty private struct
at file->private_data and put our required list fields in there, linking
file and tty. This makes tty nodes behave the same way as other device nodes
and avoid meddling with the vfs, and avoids this bug.
The error handling is not trivial in the tty code, so for this bugfix, I take
the simple approach of using __GFP_NOFAIL and don't worry about memory errors.
This is not a problem because our allocator doesn't fail small allocs as a rule
anyway. So proper error handling is left as an exercise for tty hackers.
[ Arguably filesystem's device inode would ideally be divorced from the
driver's pseudo inode when it is opened, but in practice it's not clear whether
that will ever be worth implementing. ]
Cc: linux-kernel@vger.kernel.org
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:36 +08:00
|
|
|
extern void file_sb_list_add(struct file *f, struct super_block *sb);
|
|
|
|
|
extern void file_sb_list_del(struct file *f);
|
2009-04-26 18:25:56 +08:00
|
|
|
extern void mark_files_ro(struct super_block *);
|
2009-12-05 04:47:36 +08:00
|
|
|
extern struct file *get_empty_filp(void);
|
2009-05-07 15:12:29 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* super.c
|
|
|
|
|
*/
|
|
|
|
|
extern int do_remount_sb(struct super_block *, int, void *, int);
|
2011-07-08 12:14:41 +08:00
|
|
|
extern bool grab_super_passive(struct super_block *sb);
|
2011-03-18 10:08:28 +08:00
|
|
|
extern struct dentry *mount_fs(struct file_system_type *,
|
|
|
|
|
int, const char *, void *);
|
2012-01-03 11:28:36 +08:00
|
|
|
extern struct super_block *user_get_super(dev_t);
|
2009-12-19 23:10:39 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* open.c
|
|
|
|
|
*/
|
2011-02-24 06:44:09 +08:00
|
|
|
struct open_flags {
|
|
|
|
|
int open_flag;
|
2011-11-22 03:59:34 +08:00
|
|
|
umode_t mode;
|
2011-02-24 06:44:09 +08:00
|
|
|
int acc_mode;
|
|
|
|
|
int intent;
|
|
|
|
|
};
|
2012-10-11 04:43:10 +08:00
|
|
|
extern struct file *do_filp_open(int dfd, struct filename *pathname,
|
|
|
|
|
const struct open_flags *op, int flags);
|
2011-03-12 01:08:24 +08:00
|
|
|
extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
|
|
|
|
|
const char *, const struct open_flags *, int lookup_flags);
|
2010-10-24 23:13:10 +08:00
|
|
|
|
2011-01-29 21:13:26 +08:00
|
|
|
extern long do_handle_open(int mountdirfd,
|
|
|
|
|
struct file_handle __user *ufh, int open_flag);
|
2012-05-21 23:30:15 +08:00
|
|
|
extern int open_check_o_direct(struct file *f);
|
2011-01-29 21:13:26 +08:00
|
|
|
|
2010-10-24 23:13:10 +08:00
|
|
|
/*
|
|
|
|
|
* inode.c
|
|
|
|
|
*/
|
2011-03-22 19:23:40 +08:00
|
|
|
extern spinlock_t inode_sb_list_lock;
|
2012-11-27 08:29:51 +08:00
|
|
|
extern void inode_add_lru(struct inode *inode);
|
2011-03-22 19:23:40 +08:00
|
|
|
|
2011-03-22 19:23:41 +08:00
|
|
|
/*
|
|
|
|
|
* fs-writeback.c
|
|
|
|
|
*/
|
|
|
|
|
extern void inode_wb_list_del(struct inode *inode);
|
|
|
|
|
|
2010-10-23 17:03:02 +08:00
|
|
|
extern int get_nr_dirty_inodes(void);
|
2010-10-29 17:49:13 +08:00
|
|
|
extern void evict_inodes(struct super_block *);
|
2011-02-24 14:25:47 +08:00
|
|
|
extern int invalidate_inodes(struct super_block *, bool);
|
2011-07-08 03:03:58 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* dcache.c
|
|
|
|
|
*/
|
|
|
|
|
extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
|
2013-03-21 01:19:30 +08:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* read_write.c
|
|
|
|
|
*/
|
|
|
|
|
extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
|
2013-03-12 21:58:10 +08:00
|
|
|
|
2013-06-20 22:58:36 +08:00
|
|
|
/*
|
|
|
|
|
* splice.c
|
|
|
|
|
*/
|
|
|
|
|
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
|
|
|
|
|
loff_t *opos, size_t len, unsigned int flags);
|
|
|
|
|
|
2013-03-12 21:58:10 +08:00
|
|
|
/*
|
|
|
|
|
* pipe.c
|
|
|
|
|
*/
|
|
|
|
|
extern const struct file_operations pipefifo_fops;
|