linux_old1/fs/super.c

1058 lines
24 KiB
C
Raw Normal View History

/*
* linux/fs/super.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* super.c contains code to handle: - mount structures
* - super-block tables
* - filesystem drivers list
* - mount system call
* - umount system call
* - ustat system call
*
* GK 2/5/95 - Changed to support mounting the root fs via NFS
*
* Added kerneld support: Jacques Gelinas and Bjorn Ekwall
* Added change_root: Werner Almesberger & Hans Lermen, Feb '96
* Added options to /proc/mounts:
* Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
* Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
* Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/acct.h>
#include <linux/blkdev.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/writeback.h> /* for the emergency remount stuff */
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
#include "internal.h"
LIST_HEAD(super_blocks);
DEFINE_SPINLOCK(sb_lock);
/**
* alloc_super - create new superblock
* @type: filesystem type superblock should belong to
*
* Allocates and initializes a new &struct super_block. alloc_super()
* returns a pointer new superblock or %NULL if allocation had failed.
*/
static struct super_block *alloc_super(struct file_system_type *type)
{
struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
static const struct super_operations default_op;
if (s) {
if (security_sb_alloc(s)) {
kfree(s);
s = NULL;
goto out;
}
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:38 +08:00
#ifdef CONFIG_SMP
s->s_files = alloc_percpu(struct list_head);
if (!s->s_files) {
security_sb_free(s);
kfree(s);
s = NULL;
goto out;
} else {
int i;
for_each_possible_cpu(i)
INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i));
}
#else
INIT_LIST_HEAD(&s->s_files);
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:38 +08:00
#endif
s->s_bdi = &default_backing_dev_info;
INIT_LIST_HEAD(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
fix soft lock up at NFS mount via per-SB LRU-list of unused dentries [Summary] Split LRU-list of unused dentries to one per superblock to avoid soft lock up during NFS mounts and remounting of any filesystem. Previously I posted here: http://lkml.org/lkml/2008/3/5/590 [Descriptions] - background dentry_unused is a list of dentries which are not referenced. dentry_unused grows up when references on directories or files are released. This list can be very long if there is huge free memory. - the problem When shrink_dcache_sb() is called, it scans all dentry_unused linearly under spin_lock(), and if dentry->d_sb is differnt from given superblock, scan next dentry. This scan costs very much if there are many entries, and very ineffective if there are many superblocks. IOW, When we need to shrink unused dentries on one dentry, but scans unused dentries on all superblocks in the system. For example, we scan 500 dentries to unmount a filesystem, but scans 1,000,000 or more unused dentries on other superblocks. In our case , At mounting NFS*, shrink_dcache_sb() is called to shrink unused dentries on NFS, but scans 100,000,000 unused dentries on superblocks in the system such as local ext3 filesystems. I hear NFS mounting took 1 min on some system in use. * : NFS uses virtual filesystem in rpc layer, so NFS is affected by this problem. 100,000,000 is possible number on large systems. Per-superblock LRU of unused dentried can reduce the cost in reasonable manner. - How to fix I found this problem is solved by David Chinner's "Per-superblock unused dentry LRU lists V3"(1), so I rebase it and add some fix to reclaim with fairness, which is in Andrew Morton's comments(2). 1) http://lkml.org/lkml/2006/5/25/318 2) http://lkml.org/lkml/2006/5/25/320 Split LRU-list of unused dentries to each superblocks. Then, NFS mounting will check dentries under a superblock instead of all. But this spliting will break LRU of dentry-unused. So, I've attempted to make reclaim unused dentrins with fairness by calculate number of dentries to scan on this sb based on following way number of dentries to scan on this sb = count * (number of dentries on this sb / number of dentries in the machine) - ToDo - I have to measuring performance number and do stress tests. - When unmount occurs during prune_dcache(), scanning on same superblock, It is unable to reach next superblock because it is gone away. We restart scannig superblock from first one, it causes unfairness of reclaim unused dentries on first superblock. But I think this happens very rarely. - Test Results Result on 6GB boxes with excessive unused dentries. Without patch: $ cat /proc/sys/fs/dentry-state 10181835 10180203 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m1.830s user 0m0.001s sys 0m1.653s With this patch: $ cat /proc/sys/fs/dentry-state 10236610 10234751 45 0 0 0 # mount -t nfs 10.124.60.70:/work/kernel-src nfs real 0m0.106s user 0m0.002s sys 0m0.032s [akpm@linux-foundation.org: fix comments] Signed-off-by: Kentaro Makita <k-makita@np.css.fujitsu.com> Cc: Neil Brown <neilb@suse.de> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Cc: David Chinner <dgc@sgi.com> Cc: "J. Bruce Fields" <bfields@fieldses.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:27:13 +08:00
INIT_LIST_HEAD(&s->s_dentry_lru);
init_rwsem(&s->s_umount);
mutex_init(&s->s_lock);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
/*
* The locking rules for s_lock are up to the
* filesystem. For example ext3fs has different
* lock ordering than usbfs:
*/
lockdep_set_class(&s->s_lock, &type->s_lock_key);
fs/super.c: add lockdep annotation to s_umount Li Zefan said: Thread 1: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 cat /mnt/cpus > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } Thread 2: for ((; ;)) { mount -t cpuset xxx /mnt > /dev/null 2>&1 umount /mnt > /dev/null 2>&1 } (Note: It is irrelevant which cgroup subsys is used.) After a while a lockdep warning showed up: ============================================= [ INFO: possible recursive locking detected ] 2.6.28 #479 --------------------------------------------- mount/13554 is trying to acquire lock: (&type->s_umount_key#19){--..}, at: [<c049d888>] sget+0x5e/0x321 but task is already holding lock: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 other info that might help us debug this: 1 lock held by mount/13554: #0: (&type->s_umount_key#19){--..}, at: [<c049da0c>] sget+0x1e2/0x321 stack backtrace: Pid: 13554, comm: mount Not tainted 2.6.28-mc #479 Call Trace: [<c044ad2e>] validate_chain+0x4c6/0xbbd [<c044ba9b>] __lock_acquire+0x676/0x700 [<c044bb82>] lock_acquire+0x5d/0x7a [<c049d888>] ? sget+0x5e/0x321 [<c061b9b8>] down_write+0x34/0x50 [<c049d888>] ? sget+0x5e/0x321 [<c049d888>] sget+0x5e/0x321 [<c045a2e7>] ? cgroup_set_super+0x0/0x3e [<c045959f>] ? cgroup_test_super+0x0/0x2f [<c045bcea>] cgroup_get_sb+0x98/0x2e7 [<c045cfb6>] cpuset_get_sb+0x4a/0x5f [<c049dfa4>] vfs_kern_mount+0x40/0x7b [<c049e02d>] do_kern_mount+0x37/0xbf [<c04af4a0>] do_mount+0x5c3/0x61a [<c04addd2>] ? copy_mount_options+0x2c/0x111 [<c04af560>] sys_mount+0x69/0xa0 [<c0403251>] sysenter_do_call+0x12/0x31 The cause is after alloc_super() and then retry, an old entry in list fs_supers is found, so grab_super(old) is called, but both functions hold s_umount lock: struct super_block *sget(...) { ... retry: spin_lock(&sb_lock); if (test) { list_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (!grab_super(old)) <--- 2nd: down_write(&old->s_umount); goto retry; if (s) destroy_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type); <--- 1th: down_write(&s->s_umount) if (!s) return ERR_PTR(-ENOMEM); goto retry; } ... } It seems like a false positive, and seems like VFS but not cgroup needs to be fixed. Peter said: We can simply put the new s_umount instance in a but lockdep doesn't particularly cares about subclass order. If there's any issue with the callers of sget() assuming the s_umount lock being of sublcass 0, then there is another annotation we can use to fix that, but lets not bother with that if this is sufficient. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12673 Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Li Zefan <lizf@cn.fujitsu.com> Reported-by: Li Zefan <lizf@cn.fujitsu.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Paul Menage <menage@google.com> Cc: Arjan van de Ven <arjan@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-02-19 06:48:30 +08:00
/*
* sget() can have s_umount recursion.
*
* When it cannot find a suitable sb, it allocates a new
* one (this one), and tries again to find a suitable old
* one.
*
* In case that succeeds, it will acquire the s_umount
* lock of the old one. Since these are clearly distrinct
* locks, and this object isn't exposed yet, there's no
* risk of deadlocks.
*
* Annotate this by putting this lock in a different
* subclass.
*/
down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
s->s_count = 1;
atomic_set(&s->s_active, 1);
mutex_init(&s->s_vfs_rename_mutex);
vfs: add lockdep annotation to s_vfs_rename_key for ecryptfs > ============================================= > [ INFO: possible recursive locking detected ] > 2.6.31-2-generic #14~rbd3 > --------------------------------------------- > firefox-3.5/4162 is trying to acquire lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > but task is already holding lock: > (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > > other info that might help us debug this: > 3 locks held by firefox-3.5/4162: > #0: (&s->s_vfs_rename_mutex){+.+.+.}, at: [<ffffffff81139d31>] lock_rename+0x41/0xf0 > #1: (&sb->s_type->i_mutex_key#11/1){+.+.+.}, at: [<ffffffff81139d5a>] lock_rename+0x6a/0xf0 > #2: (&sb->s_type->i_mutex_key#11/2){+.+.+.}, at: [<ffffffff81139d6f>] lock_rename+0x7f/0xf0 > > stack backtrace: > Pid: 4162, comm: firefox-3.5 Tainted: G C 2.6.31-2-generic #14~rbd3 > Call Trace: > [<ffffffff8108ae74>] print_deadlock_bug+0xf4/0x100 > [<ffffffff8108ce26>] validate_chain+0x4c6/0x750 > [<ffffffff8108d2e7>] __lock_acquire+0x237/0x430 > [<ffffffff8108d585>] lock_acquire+0xa5/0x150 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff815526ad>] __mutex_lock_common+0x4d/0x3d0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff81139d31>] ? lock_rename+0x41/0xf0 > [<ffffffff8120eaf9>] ? ecryptfs_rename+0x99/0x170 > [<ffffffff81552b36>] mutex_lock_nested+0x46/0x60 > [<ffffffff81139d31>] lock_rename+0x41/0xf0 > [<ffffffff8120eb2a>] ecryptfs_rename+0xca/0x170 > [<ffffffff81139a9e>] vfs_rename_dir+0x13e/0x160 > [<ffffffff8113ac7e>] vfs_rename+0xee/0x290 > [<ffffffff8113c212>] ? __lookup_hash+0x102/0x160 > [<ffffffff8113d512>] sys_renameat+0x252/0x280 > [<ffffffff81133eb4>] ? cp_new_stat+0xe4/0x100 > [<ffffffff8101316a>] ? sysret_check+0x2e/0x69 > [<ffffffff8108c34d>] ? trace_hardirqs_on_caller+0x14d/0x190 > [<ffffffff8113d55b>] sys_rename+0x1b/0x20 > [<ffffffff81013132>] system_call_fastpath+0x16/0x1b The trace above is totally reproducible by doing a cross-directory rename on an ecryptfs directory. The issue seems to be that sys_renameat() does lock_rename() then calls into the filesystem; if the filesystem is ecryptfs, then ecryptfs_rename() again does lock_rename() on the lower filesystem, and lockdep can't tell that the two s_vfs_rename_mutexes are different. It seems an annotation like the following is sufficient to fix this (it does get rid of the lockdep trace in my simple tests); however I would like to make sure I'm not misunderstanding the locking, hence the CC list... Signed-off-by: Roland Dreier <rdreier@cisco.com> Cc: Tyler Hicks <tyhicks@linux.vnet.ibm.com> Cc: Dustin Kirkland <kirkland@canonical.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-04-28 05:23:57 +08:00
lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
mutex_init(&s->s_dquot.dqio_mutex);
mutex_init(&s->s_dquot.dqonoff_mutex);
init_rwsem(&s->s_dquot.dqptr_sem);
init_waitqueue_head(&s->s_wait_unfrozen);
s->s_maxbytes = MAX_NON_LFS;
s->s_op = &default_op;
s->s_time_gran = 1000000000;
}
out:
return s;
}
/**
* destroy_super - frees a superblock
* @s: superblock to free
*
* Frees a superblock.
*/
static inline void destroy_super(struct super_block *s)
{
fs: scale files_lock fs: scale files_lock Improve scalability of files_lock by adding per-cpu, per-sb files lists, protected with an lglock. The lglock provides fast access to the per-cpu lists to add and remove files. It also provides a snapshot of all the per-cpu lists (although this is very slow). One difficulty with this approach is that a file can be removed from the list by another CPU. We must track which per-cpu list the file is on with a new variale in the file struct (packed into a hole on 64-bit archs). Scalability could suffer if files are frequently removed from different cpu's list. However loads with frequent removal of files imply short interval between adding and removing the files, and the scheduler attempts to avoid moving processes too far away. Also, even in the case of cross-CPU removal, the hardware has much more opportunity to parallelise cacheline transfers with N cachelines than with 1. A worst-case test of 1 CPU allocating files subsequently being freed by N CPUs degenerates to contending on a single lock, which is no worse than before. When more than one CPU are allocating files, even if they are always freed by different CPUs, there will be more parallelism than the single-lock case. Testing results: On a 2 socket, 8 core opteron, I measure the number of times the lock is taken to remove the file, the number of times it is removed by the same CPU that added it, and the number of times it is removed by the same node that added it. Booting: locks= 25049 cpu-hits= 23174 (92.5%) node-hits= 23945 (95.6%) kbuild -j16 locks=2281913 cpu-hits=2208126 (96.8%) node-hits=2252674 (98.7%) dbench 64 locks=4306582 cpu-hits=4287247 (99.6%) node-hits=4299527 (99.8%) So a file is removed from the same CPU it was added by over 90% of the time. It remains within the same node 95% of the time. Tim Chen ran some numbers for a 64 thread Nehalem system performing a compile. throughput 2.6.34-rc2 24.5 +patch 24.9 us sys idle IO wait (in %) 2.6.34-rc2 51.25 28.25 17.25 3.25 +patch 53.75 18.5 19 8.75 So significantly less CPU time spent in kernel code, higher idle time and slightly higher throughput. Single threaded performance difference was within the noise of microbenchmarks. That is not to say penalty does not exist, the code is larger and more memory accesses required so it will be slightly slower. Cc: linux-kernel@vger.kernel.org Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Signed-off-by: Nick Piggin <npiggin@kernel.dk> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2010-08-18 02:37:38 +08:00
#ifdef CONFIG_SMP
free_percpu(s->s_files);
#endif
security_sb_free(s);
kfree(s->s_subtype);
kfree(s->s_options);
kfree(s);
}
/* Superblock refcounting */
/*
* Drop a superblock's refcount. The caller must hold sb_lock.
*/
void __put_super(struct super_block *sb)
{
if (!--sb->s_count) {
list_del_init(&sb->s_list);
destroy_super(sb);
}
}
/**
* put_super - drop a temporary reference to superblock
* @sb: superblock in question
*
* Drops a temporary reference, frees superblock if there's no
* references left.
*/
writeback: switch to per-bdi threads for flushing data This gets rid of pdflush for bdi writeout and kupdated style cleaning. pdflush writeout suffers from lack of locality and also requires more threads to handle the same workload, since it has to work in a non-blocking fashion against each queue. This also introduces lumpy behaviour and potential request starvation, since pdflush can be starved for queue access if others are accessing it. A sample ffsb workload that does random writes to files is about 8% faster here on a simple SATA drive during the benchmark phase. File layout also seems a LOT more smooth in vmstat: r b swpd free buff cache si so bi bo in cs us sy id wa 0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42 0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44 1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37 0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58 0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34 0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37 0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44 0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38 0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41 0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45 where vanilla tends to fluctuate a lot in the creation phase: r b swpd free buff cache si so bi bo in cs us sy id wa 1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36 1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51 0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40 0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37 1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41 0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49 0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36 1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43 0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39 1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45 1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34 0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54 A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A SSD based writeback test on XFS performs over 20% better as well, with the throughput being very stable around 1GB/sec, where pdflush only manages 750MB/sec and fluctuates wildly while doing so. Random buffered writes to many files behave a lot better as well, as does random mmap'ed writes. A separate thread is added to sync the super blocks. In the long term, adding sync_supers_bdi() functionality could get rid of this thread again. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-09-09 15:08:54 +08:00
void put_super(struct super_block *sb)
{
spin_lock(&sb_lock);
__put_super(sb);
spin_unlock(&sb_lock);
}
/**
* deactivate_locked_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Drops an active reference to superblock, converting it into a temprory
* one if there is no other active references left. In that case we
* tell fs driver to shut it down and drop the temporary reference we
* had just acquired.
*
* Caller holds exclusive lock on superblock; that lock is released.
*/
void deactivate_locked_super(struct super_block *s)
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
fs->kill_sb(s);
/*
* We need to call rcu_barrier so all the delayed rcu free
* inodes are flushed before we release the fs module.
*/
rcu_barrier();
put_filesystem(fs);
put_super(s);
} else {
up_write(&s->s_umount);
}
}
EXPORT_SYMBOL(deactivate_locked_super);
/**
* deactivate_super - drop an active reference to superblock
* @s: superblock to deactivate
*
* Variant of deactivate_locked_super(), except that superblock is *not*
* locked by caller. If we are going to drop the final active reference,
* lock will be acquired prior to that.
*/
void deactivate_super(struct super_block *s)
{
if (!atomic_add_unless(&s->s_active, -1, 1)) {
down_write(&s->s_umount);
deactivate_locked_super(s);
}
}
EXPORT_SYMBOL(deactivate_super);
/**
* grab_super - acquire an active reference
* @s: reference we are trying to make active
*
* Tries to acquire an active reference. grab_super() is used when we
* had just found a superblock in super_blocks or fs_type->fs_supers
* and want to turn it into a full-blown active reference. grab_super()
* is called with sb_lock held and drops it. Returns 1 in case of
* success, 0 if we had failed (superblock contents was already dead or
* dying when grab_super() had been called).
*/
static int grab_super(struct super_block *s) __releases(sb_lock)
{
if (atomic_inc_not_zero(&s->s_active)) {
spin_unlock(&sb_lock);
return 1;
}
/* it's going away */
s->s_count++;
spin_unlock(&sb_lock);
/* wait for it to die */
down_write(&s->s_umount);
up_write(&s->s_umount);
put_super(s);
return 0;
}
/*
* Superblock locking. We really ought to get rid of these two.
*/
void lock_super(struct super_block * sb)
{
get_fs_excl();
mutex_lock(&sb->s_lock);
}
void unlock_super(struct super_block * sb)
{
put_fs_excl();
mutex_unlock(&sb->s_lock);
}
EXPORT_SYMBOL(lock_super);
EXPORT_SYMBOL(unlock_super);
/**
* generic_shutdown_super - common helper for ->kill_sb()
* @sb: superblock to kill
*
* generic_shutdown_super() does all fs-independent work on superblock
* shutdown. Typical ->kill_sb() should pick all fs-specific objects
* that need destruction out of superblock, call generic_shutdown_super()
* and release aforementioned objects. Note: dentries and inodes _are_
* taken care of and do not need specific handling.
[PATCH] VFS: Destroy the dentries contributed by a superblock on unmounting The attached patch destroys all the dentries attached to a superblock in one go by: (1) Destroying the tree rooted at s_root. (2) Destroying every entry in the anon list, one at a time. (3) Each entry in the anon list has its subtree consumed from the leaves inwards. This reduces the amount of work generic_shutdown_super() does, and avoids iterating through the dentry_unused list. Note that locking is almost entirely absent in the shrink_dcache_for_umount*() functions added by this patch. This is because: (1) at the point the filesystem calls generic_shutdown_super(), it is not permitted to further touch the superblock's set of dentries, and nor may it remove aliases from inodes; (2) the dcache memory shrinker now skips dentries that are being unmounted; and (3) the superblock no longer has any external references through which the VFS can reach it. Given these points, the only locking we need to do is when we remove dentries from the unused list and the name hashes, which we do a directory's worth at a time. We also don't need to guard against reference counts going to zero unexpectedly and removing bits of the tree we're working on as nothing else can call dput(). A cut down version of dentry_iput() has been folded into shrink_dcache_for_umount_subtree() function. Apart from not needing to unlock things, it also doesn't need to check for inotify watches. In this version of the patch, the complaint about a dentry still being in use has been expanded from a single BUG_ON() and now gives much more information. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: NeilBrown <neilb@suse.de> Acked-by: Ian Kent <raven@themaw.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-11 16:22:19 +08:00
*
* Upon calling this function, the filesystem may no longer alter or
* rearrange the set of dentries belonging to this super_block, nor may it
* change the attachments of dentries to inodes.
*/
void generic_shutdown_super(struct super_block *sb)
{
const struct super_operations *sop = sb->s_op;
[PATCH] VFS: Destroy the dentries contributed by a superblock on unmounting The attached patch destroys all the dentries attached to a superblock in one go by: (1) Destroying the tree rooted at s_root. (2) Destroying every entry in the anon list, one at a time. (3) Each entry in the anon list has its subtree consumed from the leaves inwards. This reduces the amount of work generic_shutdown_super() does, and avoids iterating through the dentry_unused list. Note that locking is almost entirely absent in the shrink_dcache_for_umount*() functions added by this patch. This is because: (1) at the point the filesystem calls generic_shutdown_super(), it is not permitted to further touch the superblock's set of dentries, and nor may it remove aliases from inodes; (2) the dcache memory shrinker now skips dentries that are being unmounted; and (3) the superblock no longer has any external references through which the VFS can reach it. Given these points, the only locking we need to do is when we remove dentries from the unused list and the name hashes, which we do a directory's worth at a time. We also don't need to guard against reference counts going to zero unexpectedly and removing bits of the tree we're working on as nothing else can call dput(). A cut down version of dentry_iput() has been folded into shrink_dcache_for_umount_subtree() function. Apart from not needing to unlock things, it also doesn't need to check for inotify watches. In this version of the patch, the complaint about a dentry still being in use has been expanded from a single BUG_ON() and now gives much more information. Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: NeilBrown <neilb@suse.de> Acked-by: Ian Kent <raven@themaw.net> Cc: Trond Myklebust <trond.myklebust@fys.uio.no> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-11 16:22:19 +08:00
if (sb->s_root) {
shrink_dcache_for_umount(sb);
sync_filesystem(sb);
get_fs_excl();
sb->s_flags &= ~MS_ACTIVE;
fsnotify_unmount_inodes(&sb->s_inodes);
evict_inodes(sb);
if (sop->put_super)
sop->put_super(sb);
if (!list_empty(&sb->s_inodes)) {
printk("VFS: Busy inodes after unmount of %s. "
"Self-destruct in 5 seconds. Have a nice day...\n",
sb->s_id);
}
put_fs_excl();
}
spin_lock(&sb_lock);
/* should be initialized for __put_super_and_need_restart() */
list_del_init(&sb->s_instances);
spin_unlock(&sb_lock);
up_write(&sb->s_umount);
}
EXPORT_SYMBOL(generic_shutdown_super);
/**
* sget - find or create a superblock
* @type: filesystem type superblock should belong to
* @test: comparison callback
* @set: setup callback
* @data: argument to each of them
*/
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
void *data)
{
struct super_block *s = NULL;
struct super_block *old;
int err;
retry:
spin_lock(&sb_lock);
if (test) {
list_for_each_entry(old, &type->fs_supers, s_instances) {
if (!test(old, data))
continue;
if (!grab_super(old))
goto retry;
if (s) {
up_write(&s->s_umount);
destroy_super(s);
s = NULL;
}
down_write(&old->s_umount);
if (unlikely(!(old->s_flags & MS_BORN))) {
deactivate_locked_super(old);
goto retry;
}
return old;
}
}
if (!s) {
spin_unlock(&sb_lock);
s = alloc_super(type);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
}
err = set(s, data);
if (err) {
spin_unlock(&sb_lock);
up_write(&s->s_umount);
destroy_super(s);
return ERR_PTR(err);
}
s->s_type = type;
strlcpy(s->s_id, type->name, sizeof(s->s_id));
list_add_tail(&s->s_list, &super_blocks);
list_add(&s->s_instances, &type->fs_supers);
spin_unlock(&sb_lock);
get_filesystem(type);
return s;
}
EXPORT_SYMBOL(sget);
void drop_super(struct super_block *sb)
{
up_read(&sb->s_umount);
put_super(sb);
}
EXPORT_SYMBOL(drop_super);
/**
* sync_supers - helper for periodic superblock writeback
*
* Call the write_super method if present on all dirty superblocks in
* the system. This is for the periodic writeback used by most older
* filesystems. For data integrity superblock writeback use
* sync_filesystems() instead.
*
* Note: check the dirty flag before waiting, so we don't
* hold up the sync while mounting a device. (The newly
* mounted device won't need syncing.)
*/
void sync_supers(void)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
if (sb->s_op->write_super && sb->s_dirt) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
if (sb->s_root && sb->s_dirt)
sb->s_op->write_super(sb);
up_read(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
/**
* iterate_supers - call function for all active superblocks
* @f: function to call
* @arg: argument to pass to it
*
* Scans the superblock list and calls given function, passing it
* locked superblock and given argument.
*/
void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
if (sb->s_root)
f(sb, arg);
up_read(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
}
/**
* get_super - get the superblock of a device
* @bdev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device given. %NULL is returned if no match is found.
*/
struct super_block *get_super(struct block_device *bdev)
{
struct super_block *sb;
if (!bdev)
return NULL;
spin_lock(&sb_lock);
rescan:
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
if (sb->s_bdev == bdev) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
/* still alive? */
if (sb->s_root)
return sb;
up_read(&sb->s_umount);
/* nope, got unmounted */
spin_lock(&sb_lock);
__put_super(sb);
goto rescan;
}
}
spin_unlock(&sb_lock);
return NULL;
}
EXPORT_SYMBOL(get_super);
/**
* get_active_super - get an active reference to the superblock of a device
* @bdev: device to get the superblock for
*
* Scans the superblock list and finds the superblock of the file system
* mounted on the device given. Returns the superblock with an active
* reference or %NULL if none was found.
*/
struct super_block *get_active_super(struct block_device *bdev)
{
struct super_block *sb;
if (!bdev)
return NULL;
restart:
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
if (sb->s_bdev == bdev) {
if (grab_super(sb)) /* drops sb_lock */
return sb;
else
goto restart;
}
}
spin_unlock(&sb_lock);
return NULL;
}
struct super_block *user_get_super(dev_t dev)
{
struct super_block *sb;
spin_lock(&sb_lock);
rescan:
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
if (sb->s_dev == dev) {
sb->s_count++;
spin_unlock(&sb_lock);
down_read(&sb->s_umount);
/* still alive? */
if (sb->s_root)
return sb;
up_read(&sb->s_umount);
/* nope, got unmounted */
spin_lock(&sb_lock);
__put_super(sb);
goto rescan;
}
}
spin_unlock(&sb_lock);
return NULL;
}
/**
* do_remount_sb - asks filesystem to change mount options.
* @sb: superblock in question
* @flags: numeric part of options
* @data: the rest of options
* @force: whether or not to force the change
*
* Alters the mount options of a mounted file system.
*/
int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
{
int retval;
int remount_ro;
if (sb->s_frozen != SB_UNFROZEN)
return -EBUSY;
[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
if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
return -EACCES;
[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
if (flags & MS_RDONLY)
acct_auto_close(sb);
shrink_dcache_sb(sb);
sync_filesystem(sb);
2009-12-22 08:28:53 +08:00
remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
/* If we are remounting RDONLY and current sb is read/write,
make sure there are no rw files opened */
2009-12-22 08:28:53 +08:00
if (remount_ro) {
if (force)
mark_files_ro(sb);
else if (!fs_may_remount_ro(sb))
return -EBUSY;
}
if (sb->s_op->remount_fs) {
retval = sb->s_op->remount_fs(sb, &flags, data);
if (retval)
return retval;
}
sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
2009-12-22 08:28:53 +08:00
/*
* Some filesystems modify their metadata via some other path than the
* bdev buffer cache (eg. use a private mapping, or directories in
* pagecache, etc). Also file data modifications go via their own
* mappings. So If we try to mount readonly then copy the filesystem
* from bdev, we could get stale data, so invalidate it to give a best
* effort at coherency.
*/
if (remount_ro && sb->s_bdev)
invalidate_bdev(sb->s_bdev);
return 0;
}
static void do_emergency_remount(struct work_struct *work)
{
struct super_block *sb, *p = NULL;
spin_lock(&sb_lock);
list_for_each_entry(sb, &super_blocks, s_list) {
if (list_empty(&sb->s_instances))
continue;
sb->s_count++;
spin_unlock(&sb_lock);
down_write(&sb->s_umount);
if (sb->s_root && sb->s_bdev && !(sb->s_flags & MS_RDONLY)) {
/*
* What lock protects sb->s_flags??
*/
do_remount_sb(sb, MS_RDONLY, NULL, 1);
}
up_write(&sb->s_umount);
spin_lock(&sb_lock);
if (p)
__put_super(p);
p = sb;
}
if (p)
__put_super(p);
spin_unlock(&sb_lock);
kfree(work);
printk("Emergency Remount complete\n");
}
void emergency_remount(void)
{
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_emergency_remount);
schedule_work(work);
}
}
/*
* Unnamed block devices are dummy devices used by virtual
* filesystems which don't use real block-devices. -- jrs
*/
static DEFINE_IDA(unnamed_dev_ida);
static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
static int unnamed_dev_start = 0; /* don't bother trying below it */
int set_anon_super(struct super_block *s, void *data)
{
int dev;
int error;
retry:
if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0)
return -ENOMEM;
spin_lock(&unnamed_dev_lock);
error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev);
if (!error)
unnamed_dev_start = dev + 1;
spin_unlock(&unnamed_dev_lock);
if (error == -EAGAIN)
/* We raced and lost with another CPU. */
goto retry;
else if (error)
return -EAGAIN;
if ((dev & MAX_ID_MASK) == (1 << MINORBITS)) {
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, dev);
if (unnamed_dev_start > dev)
unnamed_dev_start = dev;
spin_unlock(&unnamed_dev_lock);
return -EMFILE;
}
s->s_dev = MKDEV(0, dev & MINORMASK);
s->s_bdi = &noop_backing_dev_info;
return 0;
}
EXPORT_SYMBOL(set_anon_super);
void kill_anon_super(struct super_block *sb)
{
int slot = MINOR(sb->s_dev);
generic_shutdown_super(sb);
spin_lock(&unnamed_dev_lock);
ida_remove(&unnamed_dev_ida, slot);
if (slot < unnamed_dev_start)
unnamed_dev_start = slot;
spin_unlock(&unnamed_dev_lock);
}
EXPORT_SYMBOL(kill_anon_super);
void kill_litter_super(struct super_block *sb)
{
if (sb->s_root)
d_genocide(sb->s_root);
kill_anon_super(sb);
}
EXPORT_SYMBOL(kill_litter_super);
static int ns_test_super(struct super_block *sb, void *data)
{
return sb->s_fs_info == data;
}
static int ns_set_super(struct super_block *sb, void *data)
{
sb->s_fs_info = data;
return set_anon_super(sb, NULL);
}
struct dentry *mount_ns(struct file_system_type *fs_type, int flags,
void *data, int (*fill_super)(struct super_block *, void *, int))
{
struct super_block *sb;
sb = sget(fs_type, ns_test_super, ns_set_super, data);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!sb->s_root) {
int err;
sb->s_flags = flags;
err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (err) {
deactivate_locked_super(sb);
return ERR_PTR(err);
}
sb->s_flags |= MS_ACTIVE;
}
return dget(sb->s_root);
}
EXPORT_SYMBOL(mount_ns);
[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
static int set_bdev_super(struct super_block *s, void *data)
{
s->s_bdev = data;
s->s_dev = s->s_bdev->bd_dev;
/*
* We set the bdi here to the queue backing, file systems can
* overwrite this in ->fill_super()
*/
s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
return 0;
}
static int test_bdev_super(struct super_block *s, void *data)
{
return (void *)s->s_bdev == data;
}
struct dentry *mount_bdev(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
struct block_device *bdev;
struct super_block *s;
fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
if (!(flags & MS_RDONLY))
mode |= FMODE_WRITE;
bdev = blkdev_get_by_path(dev_name, mode, fs_type);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
/*
* once the super is inserted into the list by sget, s_umount
* will protect the lockfs code from trying to start a snapshot
* while we are mounting
*/
mutex_lock(&bdev->bd_fsfreeze_mutex);
if (bdev->bd_fsfreeze_count > 0) {
mutex_unlock(&bdev->bd_fsfreeze_mutex);
error = -EBUSY;
goto error_bdev;
}
s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s))
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
goto error_s;
if (s->s_root) {
if ((flags ^ s->s_flags) & MS_RDONLY) {
deactivate_locked_super(s);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error = -EBUSY;
goto error_bdev;
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
/*
* s_umount nests inside bd_mutex during
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
* __invalidate_device(). blkdev_put() acquires
* bd_mutex and can't be called under s_umount. Drop
* s_umount temporarily. This is safe as we're
* holding an active reference.
*/
up_write(&s->s_umount);
blkdev_put(bdev, mode);
down_write(&s->s_umount);
} else {
char b[BDEVNAME_SIZE];
s->s_flags = flags;
s->s_mode = mode;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(bdev));
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
goto error;
}
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
s->s_flags |= MS_ACTIVE;
bdev->bd_super = s;
}
return dget(s->s_root);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error_s:
error = PTR_ERR(s);
error_bdev:
blkdev_put(bdev, mode);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error:
return ERR_PTR(error);
}
EXPORT_SYMBOL(mount_bdev);
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
fmode_t mode = sb->s_mode;
bdev->bd_super = NULL;
generic_shutdown_super(sb);
sync_blockdev(bdev);
WARN_ON_ONCE(!(mode & FMODE_EXCL));
block: make blkdev_get/put() handle exclusive access Over time, block layer has accumulated a set of APIs dealing with bdev open, close, claim and release. * blkdev_get/put() are the primary open and close functions. * bd_claim/release() deal with exclusive open. * open/close_bdev_exclusive() are combination of open and claim and the other way around, respectively. * bd_link/unlink_disk_holder() to create and remove holder/slave symlinks. * open_by_devnum() wraps bdget() + blkdev_get(). The interface is a bit confusing and the decoupling of open and claim makes it impossible to properly guarantee exclusive access as in-kernel open + claim sequence can disturb the existing exclusive open even before the block layer knows the current open if for another exclusive access. Reorganize the interface such that, * blkdev_get() is extended to include exclusive access management. @holder argument is added and, if is @FMODE_EXCL specified, it will gain exclusive access atomically w.r.t. other exclusive accesses. * blkdev_put() is similarly extended. It now takes @mode argument and if @FMODE_EXCL is set, it releases an exclusive access. Also, when the last exclusive claim is released, the holder/slave symlinks are removed automatically. * bd_claim/release() and close_bdev_exclusive() are no longer necessary and either made static or removed. * bd_link_disk_holder() remains the same but bd_unlink_disk_holder() is no longer necessary and removed. * open_bdev_exclusive() becomes a simple wrapper around lookup_bdev() and blkdev_get(). It also has an unexpected extra bdev_read_only() test which probably should be moved into blkdev_get(). * open_by_devnum() is modified to take @holder argument and pass it to blkdev_get(). Most of bdev open/close operations are unified into blkdev_get/put() and most exclusive accesses are tested atomically at the open time (as it should). This cleans up code and removes some, both valid and invalid, but unnecessary all the same, corner cases. open_bdev_exclusive() and open_by_devnum() can use further cleanup - rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop special features. Well, let's leave them for another day. Most conversions are straight-forward. drbd conversion is a bit more involved as there was some reordering, but the logic should stay the same. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Brown <neilb@suse.de> Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> Acked-by: Mike Snitzer <snitzer@redhat.com> Acked-by: Philipp Reisner <philipp.reisner@linbit.com> Cc: Peter Osterlund <petero2@telia.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com> Cc: Alex Elder <aelder@sgi.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: dm-devel@redhat.com Cc: drbd-dev@lists.linbit.com Cc: Leo Chen <leochen@broadcom.com> Cc: Scott Branden <sbranden@broadcom.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com> Cc: Joern Engel <joern@logfs.org> Cc: reiserfs-devel@vger.kernel.org Cc: Alexander Viro <viro@zeniv.linux.org.uk>
2010-11-13 18:55:17 +08:00
blkdev_put(bdev, mode | FMODE_EXCL);
}
EXPORT_SYMBOL(kill_block_super);
[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
struct dentry *mount_nodev(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
int error;
struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
s->s_flags = flags;
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= MS_ACTIVE;
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_nodev);
static int compare_single(struct super_block *s, void *p)
{
return 1;
}
struct dentry *mount_single(struct file_system_type *fs_type,
int flags, void *data,
int (*fill_super)(struct super_block *, void *, int))
{
struct super_block *s;
int error;
s = sget(fs_type, compare_single, set_anon_super, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
if (!s->s_root) {
s->s_flags = flags;
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
return ERR_PTR(error);
}
s->s_flags |= MS_ACTIVE;
} else {
do_remount_sb(s, flags, data, 0);
}
return dget(s->s_root);
}
EXPORT_SYMBOL(mount_single);
struct dentry *
mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
{
struct dentry *root;
struct super_block *sb;
char *secdata = NULL;
int error = -ENOMEM;
if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
secdata = alloc_secdata();
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
if (!secdata)
goto out;
error = security_sb_copy_data(data, secdata);
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
if (error)
goto out_free_secdata;
}
root = type->mount(type, flags, name, data);
if (IS_ERR(root)) {
error = PTR_ERR(root);
goto out_free_secdata;
}
sb = root->d_sb;
BUG_ON(!sb);
WARN_ON(!sb->s_bdi);
WARN_ON(sb->s_bdi == &default_backing_dev_info);
sb->s_flags |= MS_BORN;
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
error = security_sb_kern_mount(sb, flags, secdata);
if (error)
goto out_sb;
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
/*
* filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
* but s_maxbytes was an unsigned long long for many releases. Throw
* this warning for a little while to try and catch filesystems that
* violate this rule. This warning should be either removed or
* converted to a BUG() in 2.6.34.
*/
WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
"negative value (%lld)\n", type->name, sb->s_maxbytes);
up_write(&sb->s_umount);
free_secdata(secdata);
return root;
out_sb:
dput(root);
deactivate_locked_super(sb);
out_free_secdata:
free_secdata(secdata);
out:
[PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Cc: Nathan Scott <nathans@sgi.com> Cc: Roland Dreier <rolandd@cisco.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 17:02:57 +08:00
return ERR_PTR(error);
}
/**
* freeze_super - lock the filesystem and force it into a consistent state
* @sb: the super to lock
*
* Syncs the super to make sure the filesystem is consistent and calls the fs's
* freeze_fs. Subsequent calls to this without first thawing the fs will return
* -EBUSY.
*/
int freeze_super(struct super_block *sb)
{
int ret;
atomic_inc(&sb->s_active);
down_write(&sb->s_umount);
if (sb->s_frozen) {
deactivate_locked_super(sb);
return -EBUSY;
}
if (sb->s_flags & MS_RDONLY) {
sb->s_frozen = SB_FREEZE_TRANS;
smp_wmb();
up_write(&sb->s_umount);
return 0;
}
sb->s_frozen = SB_FREEZE_WRITE;
smp_wmb();
sync_filesystem(sb);
sb->s_frozen = SB_FREEZE_TRANS;
smp_wmb();
sync_blockdev(sb->s_bdev);
if (sb->s_op->freeze_fs) {
ret = sb->s_op->freeze_fs(sb);
if (ret) {
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_frozen = SB_UNFROZEN;
deactivate_locked_super(sb);
return ret;
}
}
up_write(&sb->s_umount);
return 0;
}
EXPORT_SYMBOL(freeze_super);
/**
* thaw_super -- unlock filesystem
* @sb: the super to thaw
*
* Unlocks the filesystem and marks it writeable again after freeze_super().
*/
int thaw_super(struct super_block *sb)
{
int error;
down_write(&sb->s_umount);
if (sb->s_frozen == SB_UNFROZEN) {
up_write(&sb->s_umount);
return -EINVAL;
}
if (sb->s_flags & MS_RDONLY)
goto out;
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
if (error) {
printk(KERN_ERR
"VFS:Filesystem thaw failed\n");
sb->s_frozen = SB_FREEZE_TRANS;
up_write(&sb->s_umount);
return error;
}
}
out:
sb->s_frozen = SB_UNFROZEN;
smp_wmb();
wake_up(&sb->s_wait_unfrozen);
deactivate_locked_super(sb);
return 0;
}
EXPORT_SYMBOL(thaw_super);