UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs 

Pull vfs updates from Al Viro:
 "In this one:

   - d_move fixes (Eric Biederman)

   - UFS fixes (me; locking is mostly sane now, a bunch of bugs in error
     handling ought to be fixed)

   - switch of sb_writers to percpu rwsem (Oleg Nesterov)

   - superblock scalability (Josef Bacik and Dave Chinner)

   - swapon(2) race fix (Hugh Dickins)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (65 commits)
  vfs: Test for and handle paths that are unreachable from their mnt_root
  dcache: Reduce the scope of i_lock in d_splice_alias
  dcache: Handle escaped paths in prepend_path
  mm: fix potential data race in SyS_swapon
  inode: don't softlockup when evicting inodes
  inode: rename i_wb_list to i_io_list
  sync: serialise per-superblock sync operations
  inode: convert inode_sb_list_lock to per-sb
  inode: add hlist_fake to avoid the inode hash lock in evict
  writeback: plug writeback at a high level
  change sb_writers to use percpu_rw_semaphore
  shift percpu_counter_destroy() into destroy_super_work()
  percpu-rwsem: kill CONFIG_PERCPU_RWSEM
  percpu-rwsem: introduce percpu_rwsem_release() and percpu_rwsem_acquire()
  percpu-rwsem: introduce percpu_down_read_trylock()
  document rwsem_release() in sb_wait_write()
  fix the broken lockdep logic in __sb_start_write()
  introduce __sb_writers_{acquired,release}() helpers
  ufs_inode_get{frag,block}(): get rid of 'phys' argument
  ufs_getfrag_block(): tidy up a bit
  ...
This commit is contained in:
Linus Torvalds 2015-09-05 20:34:28 -07:00
parent bd77966994 397d425dc2
commit 7d9071a095
29 changed files with 936 additions and 1119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
arch/Kconfig
View File

@ -93,7 +93,6 @@ config KPROBES_ON_FTRACE
config UPROBES
def_bool n
select PERCPU_RWSEM
help
Uprobes is the user-space counterpart to kprobes: they
enable instrumentation applications (such as 'perf probe')

12
fs/block_dev.c
View File

@ -1769,7 +1769,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
struct inode *inode, *old_inode = NULL;
spin_lock(&inode_sb_list_lock);
spin_lock(&blockdev_superblock->s_inode_list_lock);
list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
struct address_space *mapping = inode->i_mapping;
@ -1781,13 +1781,13 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&blockdev_superblock->s_inode_list_lock);
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
* inode_sb_list_lock. We cannot iput the inode now as we can
* s_inode_list_lock We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
* inode_sb_list_lock. So we keep the reference and iput it
* s_inode_list_lock. So we keep the reference and iput it
* later.
*/
iput(old_inode);
@ -1795,8 +1795,8 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
func(I_BDEV(inode), arg);
spin_lock(&inode_sb_list_lock);
spin_lock(&blockdev_superblock->s_inode_list_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&blockdev_superblock->s_inode_list_lock);
iput(old_inode);
}

8
fs/btrfs/transaction.c
View File

@ -1640,9 +1640,7 @@ static void do_async_commit(struct work_struct *work)
* Tell lockdep about it.
*/
if (ac->newtrans->type & __TRANS_FREEZABLE)
rwsem_acquire_read(
&ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
0, 1, _THIS_IP_);
__sb_writers_acquired(ac->root->fs_info->sb, SB_FREEZE_FS);
current->journal_info = ac->newtrans;
@ -1681,9 +1679,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
* async commit thread will be the one to unlock it.
*/
if (ac->newtrans->type & __TRANS_FREEZABLE)
rwsem_release(
&root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
1, _THIS_IP_);
__sb_writers_release(root->fs_info->sb, SB_FREEZE_FS);
schedule_work(&ac->work);

14
fs/dcache.c
View File

@ -2718,7 +2718,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
* This helper attempts to cope with remotely renamed directories
*
* It assumes that the caller is already holding
* dentry->d_parent->d_inode->i_mutex, inode->i_lock and rename_lock
* dentry->d_parent->d_inode->i_mutex, and rename_lock
*
* Note: If ever the locking in lock_rename() changes, then please
* remember to update this too...
@ -2744,7 +2744,6 @@ out_unalias:
__d_move(alias, dentry, false);
ret = 0;
out_err:
spin_unlock(&inode->i_lock);
if (m2)
mutex_unlock(m2);
if (m1)
@ -2790,10 +2789,11 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
if (S_ISDIR(inode->i_mode)) {
struct dentry *new = __d_find_any_alias(inode);
if (unlikely(new)) {
/* The reference to new ensures it remains an alias */
spin_unlock(&inode->i_lock);
write_seqlock(&rename_lock);
if (unlikely(d_ancestor(new, dentry))) {
write_sequnlock(&rename_lock);
spin_unlock(&inode->i_lock);
dput(new);
new = ERR_PTR(-ELOOP);
pr_warn_ratelimited(
@ -2812,7 +2812,6 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
} else {
__d_move(new, dentry, false);
write_sequnlock(&rename_lock);
spin_unlock(&inode->i_lock);
security_d_instantiate(new, inode);
}
iput(inode);
@ -2926,6 +2925,13 @@ restart:
if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
/* Escaped? */
if (dentry != vfsmnt->mnt_root) {
bptr = *buffer;
blen = *buflen;
error = 3;
break;
}
/* Global root? */
if (mnt != parent) {
dentry = ACCESS_ONCE(mnt->mnt_mountpoint);

10
fs/drop_caches.c
View File

@ -17,7 +17,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
{
struct inode *inode, *toput_inode = NULL;
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@ -27,13 +27,15 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
invalidate_mapping_pages(inode->i_mapping, 0, -1);
iput(toput_inode);
toput_inode = inode;
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
iput(toput_inode);
}

72
fs/fs-writeback.c
View File

@ -88,7 +88,7 @@ unsigned int dirtytime_expire_interval = 12 * 60 * 60;
static inline struct inode *wb_inode(struct list_head *head)
{
return list_entry(head, struct inode, i_wb_list);
return list_entry(head, struct inode, i_io_list);
}
/*
@ -125,22 +125,22 @@ static void wb_io_lists_depopulated(struct bdi_writeback *wb)
}
/**
* inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
* inode_io_list_move_locked - move an inode onto a bdi_writeback IO list
* @inode: inode to be moved
* @wb: target bdi_writeback
* @head: one of @wb->b_{dirty|io|more_io}
*
* Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
* Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io.
* Returns %true if @inode is the first occupant of the !dirty_time IO
* lists; otherwise, %false.
*/
static bool inode_wb_list_move_locked(struct inode *inode,
static bool inode_io_list_move_locked(struct inode *inode,
struct bdi_writeback *wb,
struct list_head *head)
{
assert_spin_locked(&wb->list_lock);
list_move(&inode->i_wb_list, head);
list_move(&inode->i_io_list, head);
/* dirty_time doesn't count as dirty_io until expiration */
if (head != &wb->b_dirty_time)
@ -151,19 +151,19 @@ static bool inode_wb_list_move_locked(struct inode *inode,
}
/**
* inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
* inode_io_list_del_locked - remove an inode from its bdi_writeback IO list
* @inode: inode to be removed
* @wb: bdi_writeback @inode is being removed from
*
* Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
* clear %WB_has_dirty_io if all are empty afterwards.
*/
static void inode_wb_list_del_locked(struct inode *inode,
static void inode_io_list_del_locked(struct inode *inode,
struct bdi_writeback *wb)
{
assert_spin_locked(&wb->list_lock);
list_del_init(&inode->i_wb_list);
list_del_init(&inode->i_io_list);
wb_io_lists_depopulated(wb);
}
@ -351,7 +351,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
/*
* Once I_FREEING is visible under i_lock, the eviction path owns
* the inode and we shouldn't modify ->i_wb_list.
* the inode and we shouldn't modify ->i_io_list.
*/
if (unlikely(inode->i_state & I_FREEING))
goto skip_switch;
@ -390,16 +390,16 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
* is always correct including from ->b_dirty_time. The transfer
* preserves @inode->dirtied_when ordering.
*/
if (!list_empty(&inode->i_wb_list)) {
if (!list_empty(&inode->i_io_list)) {
struct inode *pos;
inode_wb_list_del_locked(inode, old_wb);
inode_io_list_del_locked(inode, old_wb);
inode->i_wb = new_wb;
list_for_each_entry(pos, &new_wb->b_dirty, i_wb_list)
list_for_each_entry(pos, &new_wb->b_dirty, i_io_list)
if (time_after_eq(inode->dirtied_when,
pos->dirtied_when))
break;
inode_wb_list_move_locked(inode, new_wb, pos->i_wb_list.prev);
inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev);
} else {
inode->i_wb = new_wb;
}
@ -961,12 +961,12 @@ void wb_start_background_writeback(struct bdi_writeback *wb)
/*
* Remove the inode from the writeback list it is on.
*/
void inode_wb_list_del(struct inode *inode)
void inode_io_list_del(struct inode *inode)
{
struct bdi_writeback *wb;
wb = inode_to_wb_and_lock_list(inode);
inode_wb_list_del_locked(inode, wb);
inode_io_list_del_locked(inode, wb);
spin_unlock(&wb->list_lock);
}
@ -988,7 +988,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
inode_wb_list_move_locked(inode, wb, &wb->b_dirty);
inode_io_list_move_locked(inode, wb, &wb->b_dirty);
}
/*
@ -996,7 +996,7 @@ static void redirty_tail(struct inode *inode, struct bdi_writeback *wb)
*/
static void requeue_io(struct inode *inode, struct bdi_writeback *wb)
{
inode_wb_list_move_locked(inode, wb, &wb->b_more_io);
inode_io_list_move_locked(inode, wb, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@ -1055,7 +1055,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
if (older_than_this &&
inode_dirtied_after(inode, *older_than_this))
break;
list_move(&inode->i_wb_list, &tmp);
list_move(&inode->i_io_list, &tmp);
moved++;
if (flags & EXPIRE_DIRTY_ATIME)
set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
@ -1078,7 +1078,7 @@ static int move_expired_inodes(struct list_head *delaying_queue,
list_for_each_prev_safe(pos, node, &tmp) {
inode = wb_inode(pos);
if (inode->i_sb == sb)
list_move(&inode->i_wb_list, dispatch_queue);
list_move(&inode->i_io_list, dispatch_queue);
}
}
out:
@ -1232,10 +1232,10 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
redirty_tail(inode, wb);
} else if (inode->i_state & I_DIRTY_TIME) {
inode->dirtied_when = jiffies;
inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
inode_io_list_move_locked(inode, wb, &wb->b_dirty_time);
} else {
/* The inode is clean. Remove from writeback lists. */
inode_wb_list_del_locked(inode, wb);
inode_io_list_del_locked(inode, wb);
}
}
@ -1378,7 +1378,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
* touch it. See comment above for explanation.
*/
if (!(inode->i_state & I_DIRTY_ALL))
inode_wb_list_del_locked(inode, wb);
inode_io_list_del_locked(inode, wb);
spin_unlock(&wb->list_lock);
inode_sync_complete(inode);
out:
@ -1439,7 +1439,9 @@ static long writeback_sb_inodes(struct super_block *sb,
unsigned long start_time = jiffies;
long write_chunk;
long wrote = 0; /* count both pages and inodes */
struct blk_plug plug;
blk_start_plug(&plug);
while (!list_empty(&wb->b_io)) {
struct inode *inode = wb_inode(wb->b_io.prev);
@ -1537,6 +1539,7 @@ static long writeback_sb_inodes(struct super_block *sb,
break;
}
}
blk_finish_plug(&plug);
return wrote;
}
@ -2088,7 +2091,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
else
dirty_list = &wb->b_dirty_time;
wakeup_bdi = inode_wb_list_move_locked(inode, wb,
wakeup_bdi = inode_io_list_move_locked(inode, wb,
dirty_list);
spin_unlock(&wb->list_lock);
@ -2111,6 +2114,15 @@ out_unlock_inode:
}
EXPORT_SYMBOL(__mark_inode_dirty);
/*
* The @s_sync_lock is used to serialise concurrent sync operations
* to avoid lock contention problems with concurrent wait_sb_inodes() calls.
* Concurrent callers will block on the s_sync_lock rather than doing contending
* walks. The queueing maintains sync(2) required behaviour as all the IO that
* has been issued up to the time this function is enter is guaranteed to be
* completed by the time we have gained the lock and waited for all IO that is
* in progress regardless of the order callers are granted the lock.
*/
static void wait_sb_inodes(struct super_block *sb)
{
struct inode *inode, *old_inode = NULL;
@ -2121,7 +2133,8 @@ static void wait_sb_inodes(struct super_block *sb)
*/
WARN_ON(!rwsem_is_locked(&sb->s_umount));
spin_lock(&inode_sb_list_lock);
mutex_lock(&sb->s_sync_lock);
spin_lock(&sb->s_inode_list_lock);
/*
* Data integrity sync. Must wait for all pages under writeback,
@ -2141,14 +2154,14 @@ static void wait_sb_inodes(struct super_block *sb)
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
* inode_sb_list_lock. We cannot iput the inode now as we can
* s_inode_list_lock. We cannot iput the inode now as we can
* be holding the last reference and we cannot iput it under
* inode_sb_list_lock. So we keep the reference and iput it
* s_inode_list_lock. So we keep the reference and iput it
* later.
*/
iput(old_inode);
@ -2158,10 +2171,11 @@ static void wait_sb_inodes(struct super_block *sb)
cond_resched();
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
iput(old_inode);
mutex_unlock(&sb->s_sync_lock);
}
static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,

50
fs/inode.c
View File

@ -28,16 +28,16 @@
* inode->i_state, inode->i_hash, __iget()
* Inode LRU list locks protect:
* inode->i_sb->s_inode_lru, inode->i_lru
* inode_sb_list_lock protects:
* sb->s_inodes, inode->i_sb_list
* inode->i_sb->s_inode_list_lock protects:
* inode->i_sb->s_inodes, inode->i_sb_list
* bdi->wb.list_lock protects:
* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_wb_list
* bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list
* inode_hash_lock protects:
* inode_hashtable, inode->i_hash
*
* Lock ordering:
*
* inode_sb_list_lock
* inode->i_sb->s_inode_list_lock
* inode->i_lock
* Inode LRU list locks
*
@ -45,7 +45,7 @@
* inode->i_lock
*
* inode_hash_lock
* inode_sb_list_lock
* inode->i_sb->s_inode_list_lock
* inode->i_lock
*
* iunique_lock
@ -57,8 +57,6 @@ static unsigned int i_hash_shift __read_mostly;
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
/*
* Empty aops. Can be used for the cases where the user does not
* define any of the address_space operations.
@ -359,7 +357,7 @@ void inode_init_once(struct inode *inode)
memset(inode, 0, sizeof(*inode));
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_devices);
INIT_LIST_HEAD(&inode->i_wb_list);
INIT_LIST_HEAD(&inode->i_io_list);
INIT_LIST_HEAD(&inode->i_lru);
address_space_init_once(&inode->i_data);
i_size_ordered_init(inode);
@ -426,18 +424,18 @@ static void inode_lru_list_del(struct inode *inode)
*/
void inode_sb_list_add(struct inode *inode)
{
spin_lock(&inode_sb_list_lock);
spin_lock(&inode->i_sb->s_inode_list_lock);
list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&inode->i_sb->s_inode_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);
static inline void inode_sb_list_del(struct inode *inode)
{
if (!list_empty(&inode->i_sb_list)) {
spin_lock(&inode_sb_list_lock);
spin_lock(&inode->i_sb->s_inode_list_lock);
list_del_init(&inode->i_sb_list);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&inode->i_sb->s_inode_list_lock);
}
}
@ -527,8 +525,8 @@ static void evict(struct inode *inode)
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(!list_empty(&inode->i_lru));
if (!list_empty(&inode->i_wb_list))
inode_wb_list_del(inode);
if (!list_empty(&inode->i_io_list))
inode_io_list_del(inode);
inode_sb_list_del(inode);
@ -577,6 +575,7 @@ static void dispose_list(struct list_head *head)
list_del_init(&inode->i_lru);
evict(inode);
cond_resched();
}
}
@ -594,7 +593,8 @@ void evict_inodes(struct super_block *sb)
struct inode *inode, *next;
LIST_HEAD(dispose);
spin_lock(&inode_sb_list_lock);
again:
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
if (atomic_read(&inode->i_count))
continue;
@ -609,8 +609,20 @@ void evict_inodes(struct super_block *sb)
inode_lru_list_del(inode);
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
/*
* We can have a ton of inodes to evict at unmount time given
* enough memory, check to see if we need to go to sleep for a
* bit so we don't livelock.
*/
if (need_resched()) {
spin_unlock(&sb->s_inode_list_lock);
cond_resched();
dispose_list(&dispose);
goto again;
}
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
dispose_list(&dispose);
}
@ -631,7 +643,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
struct inode *inode, *next;
LIST_HEAD(dispose);
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
@ -654,7 +666,7 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty)
spin_unlock(&inode->i_lock);
list_add(&inode->i_lru, &dispose);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
dispose_list(&dispose);
@ -890,7 +902,7 @@ struct inode *new_inode(struct super_block *sb)
{
struct inode *inode;
spin_lock_prefetch(&inode_sb_list_lock);
spin_lock_prefetch(&sb->s_inode_list_lock);
inode = new_inode_pseudo(sb);
if (inode)

3
fs/internal.h
View File

@ -112,14 +112,13 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
/*
* inode.c
*/
extern spinlock_t inode_sb_list_lock;
extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc);
extern void inode_add_lru(struct inode *inode);
/*
* fs-writeback.c
*/
extern void inode_wb_list_del(struct inode *inode);
extern void inode_io_list_del(struct inode *inode);
extern long get_nr_dirty_inodes(void);
extern void evict_inodes(struct super_block *);

27
fs/namei.c
View File

@ -560,6 +560,24 @@ static int __nd_alloc_stack(struct nameidata *nd)
return 0;
}
/**
* path_connected - Verify that a path->dentry is below path->mnt.mnt_root
* @path: nameidate to verify
*
* Rename can sometimes move a file or directory outside of a bind
* mount, path_connected allows those cases to be detected.
*/
static bool path_connected(const struct path *path)
{
struct vfsmount *mnt = path->mnt;
/* Only bind mounts can have disconnected paths */
if (mnt->mnt_root == mnt->mnt_sb->s_root)
return true;
return is_subdir(path->dentry, mnt->mnt_root);
}
static inline int nd_alloc_stack(struct nameidata *nd)
{
if (likely(nd->depth != EMBEDDED_LEVELS))
@ -1296,6 +1314,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
return -ECHILD;
nd->path.dentry = parent;
nd->seq = seq;
if (unlikely(!path_connected(&nd->path)))
return -ENOENT;
break;
} else {
struct mount *mnt = real_mount(nd->path.mnt);
@ -1396,7 +1416,7 @@ static void follow_mount(struct path *path)
}
}
static void follow_dotdot(struct nameidata *nd)
static int follow_dotdot(struct nameidata *nd)
{
if (!nd->root.mnt)
set_root(nd);
@ -1412,6 +1432,8 @@ static void follow_dotdot(struct nameidata *nd)
/* rare case of legitimate dget_parent()... */
nd->path.dentry = dget_parent(nd->path.dentry);
dput(old);
if (unlikely(!path_connected(&nd->path)))
return -ENOENT;
break;
}
if (!follow_up(&nd->path))
@ -1419,6 +1441,7 @@ static void follow_dotdot(struct nameidata *nd)
}
follow_mount(&nd->path);
nd->inode = nd->path.dentry->d_inode;
return 0;
}
/*
@ -1634,7 +1657,7 @@ static inline int handle_dots(struct nameidata *nd, int type)
if (nd->flags & LOOKUP_RCU) {
return follow_dotdot_rcu(nd);
} else
follow_dotdot(nd);
return follow_dotdot(nd);
}
return 0;
}

20
fs/notify/inode_mark.c
View File

@ -143,17 +143,17 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
/**
* fsnotify_unmount_inodes - an sb is unmounting. handle any watched inodes.
* @list: list of inodes being unmounted (sb->s_inodes)
* @sb: superblock being unmounted.
*
* Called during unmount with no locks held, so needs to be safe against
* concurrent modifiers. We temporarily drop inode_sb_list_lock and CAN block.
* concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
*/
void fsnotify_unmount_inodes(struct list_head *list)
void fsnotify_unmount_inodes(struct super_block *sb)
{
struct inode *inode, *next_i, *need_iput = NULL;
spin_lock(&inode_sb_list_lock);
list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry_safe(inode, next_i, &sb->s_inodes, i_sb_list) {
struct inode *need_iput_tmp;
/*
@ -189,7 +189,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
spin_unlock(&inode->i_lock);
/* In case the dropping of a reference would nuke next_i. */
while (&next_i->i_sb_list != list) {
while (&next_i->i_sb_list != &sb->s_inodes) {
spin_lock(&next_i->i_lock);
if (!(next_i->i_state & (I_FREEING | I_WILL_FREE)) &&
atomic_read(&next_i->i_count)) {
@ -204,12 +204,12 @@ void fsnotify_unmount_inodes(struct list_head *list)
}
/*
* We can safely drop inode_sb_list_lock here because either
* We can safely drop s_inode_list_lock here because either
* we actually hold references on both inode and next_i or
* end of list. Also no new inodes will be added since the
* umount has begun.
*/
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
if (need_iput_tmp)
iput(need_iput_tmp);
@ -221,7 +221,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
iput(inode);
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
}

16
fs/quota/dquot.c
View File

@ -928,7 +928,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
int reserved = 0;
#endif
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
spin_lock(&inode->i_lock);
if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
@ -939,7 +939,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
}
__iget(inode);
spin_unlock(&inode->i_lock);
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
#ifdef CONFIG_QUOTA_DEBUG
if (unlikely(inode_get_rsv_space(inode) > 0))
@ -951,15 +951,15 @@ static void add_dquot_ref(struct super_block *sb, int type)
/*
* We hold a reference to 'inode' so it couldn't have been
* removed from s_inodes list while we dropped the
* inode_sb_list_lock We cannot iput the inode now as we can be
* s_inode_list_lock. We cannot iput the inode now as we can be
* holding the last reference and we cannot iput it under
* inode_sb_list_lock. So we keep the reference and iput it
* s_inode_list_lock. So we keep the reference and iput it
* later.
*/
old_inode = inode;
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
iput(old_inode);
#ifdef CONFIG_QUOTA_DEBUG
@ -1028,7 +1028,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
struct inode *inode;
int reserved = 0;
spin_lock(&inode_sb_list_lock);
spin_lock(&sb->s_inode_list_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
/*
* We have to scan also I_NEW inodes because they can already
@ -1044,7 +1044,7 @@ static void remove_dquot_ref(struct super_block *sb, int type,
}
spin_unlock(&dq_data_lock);
}
spin_unlock(&inode_sb_list_lock);
spin_unlock(&sb->s_inode_list_lock);
#ifdef CONFIG_QUOTA_DEBUG
if (reserved) {
printk(KERN_WARNING "VFS (%s): Writes happened after quota"

175
fs/super.c
View File

@ -135,6 +135,24 @@ static unsigned long super_cache_count(struct shrinker *shrink,
return total_objects;
}
static void destroy_super_work(struct work_struct *work)
{
struct super_block *s = container_of(work, struct super_block,
destroy_work);
int i;
for (i = 0; i < SB_FREEZE_LEVELS; i++)
percpu_free_rwsem(&s->s_writers.rw_sem[i]);
kfree(s);
}
static void destroy_super_rcu(struct rcu_head *head)
{
struct super_block *s = container_of(head, struct super_block, rcu);
INIT_WORK(&s->destroy_work, destroy_super_work);
schedule_work(&s->destroy_work);
}
/**
* destroy_super - frees a superblock
* @s: superblock to free
@ -143,16 +161,13 @@ static unsigned long super_cache_count(struct shrinker *shrink,
*/
static void destroy_super(struct super_block *s)
{
int i;
list_lru_destroy(&s->s_dentry_lru);
list_lru_destroy(&s->s_inode_lru);
for (i = 0; i < SB_FREEZE_LEVELS; i++)
percpu_counter_destroy(&s->s_writers.counter[i]);
security_sb_free(s);
WARN_ON(!list_empty(&s->s_mounts));
kfree(s->s_subtype);
kfree(s->s_options);
kfree_rcu(s, rcu);
call_rcu(&s->rcu, destroy_super_rcu);
}
/**
@ -178,19 +193,19 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
goto fail;
for (i = 0; i < SB_FREEZE_LEVELS; i++) {
if (percpu_counter_init(&s->s_writers.counter[i], 0,
GFP_KERNEL) < 0)
if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
sb_writers_name[i],
&type->s_writers_key[i]))
goto fail;
lockdep_init_map(&s->s_writers.lock_map[i], sb_writers_name[i],
&type->s_writers_key[i], 0);
}
init_waitqueue_head(&s->s_writers.wait);
init_waitqueue_head(&s->s_writers.wait_unfrozen);
s->s_bdi = &noop_backing_dev_info;
s->s_flags = flags;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
mutex_init(&s->s_sync_lock);
INIT_LIST_HEAD(&s->s_inodes);
spin_lock_init(&s->s_inode_list_lock);
if (list_lru_init_memcg(&s->s_dentry_lru))
goto fail;
@ -399,7 +414,7 @@ void generic_shutdown_super(struct super_block *sb)
sync_filesystem(sb);
sb->s_flags &= ~MS_ACTIVE;
fsnotify_unmount_inodes(&sb->s_inodes);
fsnotify_unmount_inodes(sb);
evict_inodes(sb);
@ -1146,72 +1161,46 @@ out:
*/
void __sb_end_write(struct super_block *sb, int level)
{
percpu_counter_dec(&sb->s_writers.counter[level-1]);
/*
* Make sure s_writers are updated before we wake up waiters in
* freeze_super().
*/
smp_mb();
if (waitqueue_active(&sb->s_writers.wait))
wake_up(&sb->s_writers.wait);
rwsem_release(&sb->s_writers.lock_map[level-1], 1, _RET_IP_);
percpu_up_read(sb->s_writers.rw_sem + level-1);
}
EXPORT_SYMBOL(__sb_end_write);
#ifdef CONFIG_LOCKDEP
/*
* We want lockdep to tell us about possible deadlocks with freezing but
* it's it bit tricky to properly instrument it. Getting a freeze protection
* works as getting a read lock but there are subtle problems. XFS for example
* gets freeze protection on internal level twice in some cases, which is OK
* only because we already hold a freeze protection also on higher level. Due
* to these cases we have to tell lockdep we are doing trylock when we
* already hold a freeze protection for a higher freeze level.
*/
static void acquire_freeze_lock(struct super_block *sb, int level, bool trylock,
unsigned long ip)
{
int i;
if (!trylock) {
for (i = 0; i < level - 1; i++)
if (lock_is_held(&sb->s_writers.lock_map[i])) {
trylock = true;
break;
}
}
rwsem_acquire_read(&sb->s_writers.lock_map[level-1], 0, trylock, ip);
}
#endif
/*
* This is an internal function, please use sb_start_{write,pagefault,intwrite}
* instead.
*/
int __sb_start_write(struct super_block *sb, int level, bool wait)
{
retry:
if (unlikely(sb->s_writers.frozen >= level)) {
if (!wait)
return 0;
wait_event(sb->s_writers.wait_unfrozen,
sb->s_writers.frozen < level);
}
bool force_trylock = false;
int ret = 1;
#ifdef CONFIG_LOCKDEP
acquire_freeze_lock(sb, level, !wait, _RET_IP_);
#endif
percpu_counter_inc(&sb->s_writers.counter[level-1]);
/*
* Make sure counter is updated before we check for frozen.
* freeze_super() first sets frozen and then checks the counter.
* We want lockdep to tell us about possible deadlocks with freezing
* but it's it bit tricky to properly instrument it. Getting a freeze
* protection works as getting a read lock but there are subtle
* problems. XFS for example gets freeze protection on internal level
* twice in some cases, which is OK only because we already hold a
* freeze protection also on higher level. Due to these cases we have
* to use wait == F (trylock mode) which must not fail.
*/
smp_mb();
if (unlikely(sb->s_writers.frozen >= level)) {
__sb_end_write(sb, level);
goto retry;
if (wait) {
int i;
for (i = 0; i < level - 1; i++)
if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
force_trylock = true;
break;
}
}
return 1;
#endif
if (wait && !force_trylock)
percpu_down_read(sb->s_writers.rw_sem + level-1);
else
ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);
WARN_ON(force_trylock & !ret);
return ret;
}
EXPORT_SYMBOL(__sb_start_write);
@ -1221,37 +1210,33 @@ EXPORT_SYMBOL(__sb_start_write);
* @level: type of writers we wait for (normal vs page fault)
*
* This function waits until there are no writers of given type to given file
* system. Caller of this function should make sure there can be no new writers
* of type @level before calling this function. Otherwise this function can
* livelock.
* system.
*/
static void sb_wait_write(struct super_block *sb, int level)
{
s64 writers;
percpu_down_write(sb->s_writers.rw_sem + level-1);
/*
* We just cycle-through lockdep here so that it does not complain
* about returning with lock to userspace
* We are going to return to userspace and forget about this lock, the
* ownership goes to the caller of thaw_super() which does unlock.
*
* FIXME: we should do this before return from freeze_super() after we
* called sync_filesystem(sb) and s_op->freeze_fs(sb), and thaw_super()
* should re-acquire these locks before s_op->unfreeze_fs(sb). However
* this leads to lockdep false-positives, so currently we do the early
* release right after acquire.
*/
rwsem_acquire(&sb->s_writers.lock_map[level-1], 0, 0, _THIS_IP_);
rwsem_release(&sb->s_writers.lock_map[level-1], 1, _THIS_IP_);
percpu_rwsem_release(sb->s_writers.rw_sem + level-1, 0, _THIS_IP_);
}
do {
DEFINE_WAIT(wait);
static void sb_freeze_unlock(struct super_block *sb)
{
int level;
/*
* We use a barrier in prepare_to_wait() to separate setting
* of frozen and checking of the counter
*/
prepare_to_wait(&sb->s_writers.wait, &wait,
TASK_UNINTERRUPTIBLE);
for (level = 0; level < SB_FREEZE_LEVELS; ++level)
percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
writers = percpu_counter_sum(&sb->s_writers.counter[level-1]);
if (writers)
schedule();
finish_wait(&sb->s_writers.wait, &wait);
} while (writers);
for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
percpu_up_write(sb->s_writers.rw_sem + level);
}
/**
@ -1310,20 +1295,14 @@ int freeze_super(struct super_block *sb)
return 0;
}
/* From now on, no new normal writers can start */
sb->s_writers.frozen = SB_FREEZE_WRITE;
smp_wmb();
/* Release s_umount to preserve sb_start_write -> s_umount ordering */
up_write(&sb->s_umount);
sb_wait_write(sb, SB_FREEZE_WRITE);
down_write(&sb->s_umount);
/* Now we go and block page faults... */
down_write(&sb->s_umount);
sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
smp_wmb();
sb_wait_write(sb, SB_FREEZE_PAGEFAULT);
/* All writers are done so after syncing there won't be dirty data */
@ -1331,7 +1310,6 @@ int freeze_super(struct super_block *sb)
/* Now wait for internal filesystem counter */
sb->s_writers.frozen = SB_FREEZE_FS;
smp_wmb();
sb_wait_write(sb, SB_FREEZE_FS);
if (sb->s_op->freeze_fs) {
@ -1340,7 +1318,7 @@ int freeze_super(struct super_block *sb)
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_writers.frozen = SB_UNFROZEN;
smp_wmb();
sb_freeze_unlock(sb);
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return ret;
@ -1372,8 +1350,10 @@ int thaw_super(struct super_block *sb)
return -EINVAL;
}
if (sb->s_flags & MS_RDONLY)
if (sb->s_flags & MS_RDONLY) {
sb->s_writers.frozen = SB_UNFROZEN;
goto out;
}
if (sb->s_op->unfreeze_fs) {
error = sb->s_op->unfreeze_fs(sb);
@ -1385,12 +1365,11 @@ int thaw_super(struct super_block *sb)
}
}
out:
sb->s_writers.frozen = SB_UNFROZEN;
smp_wmb();
sb_freeze_unlock(sb);
out:
wake_up(&sb->s_writers.wait_unfrozen);
deactivate_locked_super(sb);
return 0;
}
EXPORT_SYMBOL(thaw_super);

2
fs/ufs/Makefile
View File

@ -5,5 +5,5 @@
obj-$(CONFIG_UFS_FS) += ufs.o
ufs-objs := balloc.o cylinder.o dir.o file.o ialloc.o inode.o \
namei.o super.o symlink.o truncate.o util.o
namei.o super.o symlink.o util.o
ccflags-$(CONFIG_UFS_DEBUG) += -DDEBUG

4
fs/ufs/balloc.c
View File

@ -417,7 +417,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
if (oldcount == 0) {
result = ufs_alloc_fragments (inode, cgno, goal, count, err);
if (result) {
write_seqlock(&UFS_I(inode)->meta_lock);
ufs_cpu_to_data_ptr(sb, p, result);
write_sequnlock(&UFS_I(inode)->meta_lock);
*err = 0;
UFS_I(inode)->i_lastfrag =
max(UFS_I(inode)->i_lastfrag, fragment + count);
@ -473,7 +475,9 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
ufs_change_blocknr(inode, fragment - oldcount, oldcount,
uspi->s_sbbase + tmp,
uspi->s_sbbase + result, locked_page);
write_seqlock(&UFS_I(inode)->meta_lock);
ufs_cpu_to_data_ptr(sb, p, result);
write_sequnlock(&UFS_I(inode)->meta_lock);
*err = 0;
UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
fragment + count);

948
fs/ufs/inode.c
View File

File diff suppressed because it is too large Load Diff

36
fs/ufs/super.c
View File

@ -94,22 +94,6 @@
#include "swab.h"
#include "util.h"
void lock_ufs(struct super_block *sb)
{
struct ufs_sb_info *sbi = UFS_SB(sb);
mutex_lock(&sbi->mutex);
sbi->mutex_owner = current;
}
void unlock_ufs(struct super_block *sb)
{
struct ufs_sb_info *sbi = UFS_SB(sb);
sbi->mutex_owner = NULL;
mutex_unlock(&sbi->mutex);
}
static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation)
{
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
@ -694,7 +678,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
struct ufs_super_block_third * usb3;
unsigned flags;
lock_ufs(sb);
mutex_lock(&UFS_SB(sb)->s_lock);
UFSD("ENTER\n");
@ -714,7 +697,6 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
UFSD("EXIT\n");
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
}
@ -758,7 +740,6 @@ static void ufs_put_super(struct super_block *sb)
ubh_brelse_uspi (sbi->s_uspi);
kfree (sbi->s_uspi);
mutex_destroy(&sbi->mutex);
kfree (sbi);
sb->s_fs_info = NULL;
UFSD("EXIT\n");
@ -801,7 +782,6 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
mutex_init(&sbi->mutex);
mutex_init(&sbi->s_lock);
spin_lock_init(&sbi->work_lock);
INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
@ -1257,7 +1237,6 @@ magic_found:
return 0;
failed:
mutex_destroy(&sbi->mutex);
if (ubh)
ubh_brelse_uspi (uspi);
kfree (uspi);
@ -1280,7 +1259,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
unsigned flags;
sync_filesystem(sb);
lock_ufs(sb);
mutex_lock(&UFS_SB(sb)->s_lock);
uspi = UFS_SB(sb)->s_uspi;
flags = UFS_SB(sb)->s_flags;
@ -1296,7 +1274,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
ufs_set_opt (new_mount_opt, ONERROR_LOCK);
if (!ufs_parse_options (data, &new_mount_opt)) {
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
if (!(new_mount_opt & UFS_MOUNT_UFSTYPE)) {
@ -1304,14 +1281,12 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
pr_err("ufstype can't be changed during remount\n");
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
UFS_SB(sb)->s_mount_opt = new_mount_opt;
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
}
@ -1335,7 +1310,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
#ifndef CONFIG_UFS_FS_WRITE
pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
#else
if (ufstype != UFS_MOUNT_UFSTYPE_SUN &&
@ -1345,13 +1319,11 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
pr_err("this ufstype is read-only supported\n");
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EINVAL;
}
if (!ufs_read_cylinder_structures(sb)) {
pr_err("failed during remounting\n");
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return -EPERM;
}
sb->s_flags &= ~MS_RDONLY;
@ -1359,7 +1331,6 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
}
UFS_SB(sb)->s_mount_opt = new_mount_opt;
mutex_unlock(&UFS_SB(sb)->s_lock);
unlock_ufs(sb);
return 0;
}
@ -1391,8 +1362,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct ufs_super_block_third *usb3;
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
lock_ufs(sb);
mutex_lock(&UFS_SB(sb)->s_lock);
usb3 = ubh_get_usb_third(uspi);
if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) {
@ -1413,7 +1383,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
unlock_ufs(sb);
mutex_unlock(&UFS_SB(sb)->s_lock);
return 0;
}
@ -1429,6 +1399,8 @@ static struct inode *ufs_alloc_inode(struct super_block *sb)
return NULL;
ei->vfs_inode.i_version = 1;
seqlock_init(&ei->meta_lock);
mutex_init(&ei->truncate_mutex);
return &ei->vfs_inode;
}

523
fs/ufs/truncate.c
View File

@ -1,523 +0,0 @@
/*
* linux/fs/ufs/truncate.c
*
* Copyright (C) 1998
* Daniel Pirkl <daniel.pirkl@email.cz>
* Charles University, Faculty of Mathematics and Physics
*
* from
*
* linux/fs/ext2/truncate.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* from
*
* linux/fs/minix/truncate.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*/
/*
* Real random numbers for secure rm added 94/02/18
* Idea from Pierre del Perugia <delperug@gla.ecoledoc.ibp.fr>
*/
/*
* Adoptation to use page cache and UFS2 write support by
* Evgeniy Dushistov <dushistov@mail.ru>, 2006-2007
*/
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/fcntl.h>
#include <linux/time.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/sched.h>
#include "ufs_fs.h"
#include "ufs.h"
#include "swab.h"
#include "util.h"
/*
* Secure deletion currently doesn't work. It interacts very badly
* with buffers shared with memory mappings, and for that reason
* can't be done in the truncate() routines. It should instead be
* done separately in "release()" before calling the truncate routines
* that will release the actual file blocks.
*
* Linus
*/
#define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift)
#define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift)
static int ufs_trunc_direct(struct inode *inode)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
struct super_block * sb;
struct ufs_sb_private_info * uspi;
void *p;
u64 frag1, frag2, frag3, frag4, block1, block2;
unsigned frag_to_free, free_count;
unsigned i, tmp;
int retry;
UFSD("ENTER: ino %lu\n", inode->i_ino);
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
frag_to_free = 0;
free_count = 0;
retry = 0;
frag1 = DIRECT_FRAGMENT;
frag4 = min_t(u64, UFS_NDIR_FRAGMENT, ufsi->i_lastfrag);
frag2 = ((frag1 & uspi->s_fpbmask) ? ((frag1 | uspi->s_fpbmask) + 1) : frag1);
frag3 = frag4 & ~uspi->s_fpbmask;
block1 = block2 = 0;
if (frag2 > frag3) {
frag2 = frag4;
frag3 = frag4 = 0;
} else if (frag2 < frag3) {
block1 = ufs_fragstoblks (frag2);
block2 = ufs_fragstoblks (frag3);
}
UFSD("ino %lu, frag1 %llu, frag2 %llu, block1 %llu, block2 %llu,"
" frag3 %llu, frag4 %llu\n", inode->i_ino,
(unsigned long long)frag1, (unsigned long long)frag2,
(unsigned long long)block1, (unsigned long long)block2,
(unsigned long long)frag3, (unsigned long long)frag4);
if (frag1 >= frag2)
goto next1;
/*
* Free first free fragments
*/
p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag1));
tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp )
ufs_panic (sb, "ufs_trunc_direct", "internal error");
frag2 -= frag1;
frag1 = ufs_fragnum (frag1);
ufs_free_fragments(inode, tmp + frag1, frag2);
mark_inode_dirty(inode);
frag_to_free = tmp + frag1;
next1:
/*
* Free whole blocks
*/
for (i = block1 ; i < block2; i++) {
p = ufs_get_direct_data_ptr(uspi, ufsi, i);
tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp)
continue;
ufs_data_ptr_clear(uspi, p);
if (free_count == 0) {
frag_to_free = tmp;
free_count = uspi->s_fpb;
} else if (free_count > 0 && frag_to_free == tmp - free_count)
free_count += uspi->s_fpb;
else {
ufs_free_blocks (inode, frag_to_free, free_count);
frag_to_free = tmp;
free_count = uspi->s_fpb;
}
mark_inode_dirty(inode);
}
if (free_count > 0)
ufs_free_blocks (inode, frag_to_free, free_count);
if (frag3 >= frag4)
goto next3;
/*
* Free last free fragments
*/
p = ufs_get_direct_data_ptr(uspi, ufsi, ufs_fragstoblks(frag3));
tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp )
ufs_panic(sb, "ufs_truncate_direct", "internal error");
frag4 = ufs_fragnum (frag4);
ufs_data_ptr_clear(uspi, p);
ufs_free_fragments (inode, tmp, frag4);
mark_inode_dirty(inode);
next3:
UFSD("EXIT: ino %lu\n", inode->i_ino);
return retry;
}
static int ufs_trunc_indirect(struct inode *inode, u64 offset, void *p)
{
struct super_block * sb;
struct ufs_sb_private_info * uspi;
struct ufs_buffer_head * ind_ubh;
void *ind;
u64 tmp, indirect_block, i, frag_to_free;
unsigned free_count;
int retry;
UFSD("ENTER: ino %lu, offset %llu, p: %p\n",
inode->i_ino, (unsigned long long)offset, p);
BUG_ON(!p);
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
frag_to_free = 0;
free_count = 0;
retry = 0;
tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp)
return 0;
ind_ubh = ubh_bread(sb, tmp, uspi->s_bsize);
if (tmp != ufs_data_ptr_to_cpu(sb, p)) {
ubh_brelse (ind_ubh);
return 1;
}
if (!ind_ubh) {
ufs_data_ptr_clear(uspi, p);
return 0;
}
indirect_block = (DIRECT_BLOCK > offset) ? (DIRECT_BLOCK - offset) : 0;
for (i = indirect_block; i < uspi->s_apb; i++) {
ind = ubh_get_data_ptr(uspi, ind_ubh, i);
tmp = ufs_data_ptr_to_cpu(sb, ind);
if (!tmp)
continue;
ufs_data_ptr_clear(uspi, ind);
ubh_mark_buffer_dirty(ind_ubh);
if (free_count == 0) {
frag_to_free = tmp;
free_count = uspi->s_fpb;
} else if (free_count > 0 && frag_to_free == tmp - free_count)
free_count += uspi->s_fpb;
else {
ufs_free_blocks (inode, frag_to_free, free_count);
frag_to_free = tmp;
free_count = uspi->s_fpb;
}
mark_inode_dirty(inode);
}
if (free_count > 0) {
ufs_free_blocks (inode, frag_to_free, free_count);
}
for (i = 0; i < uspi->s_apb; i++)
if (!ufs_is_data_ptr_zero(uspi,
ubh_get_data_ptr(uspi, ind_ubh, i)))
break;
if (i >= uspi->s_apb) {
tmp = ufs_data_ptr_to_cpu(sb, p);
ufs_data_ptr_clear(uspi, p);
ufs_free_blocks (inode, tmp, uspi->s_fpb);
mark_inode_dirty(inode);
ubh_bforget(ind_ubh);
ind_ubh = NULL;
}
if (IS_SYNC(inode) && ind_ubh && ubh_buffer_dirty(ind_ubh))
ubh_sync_block(ind_ubh);
ubh_brelse (ind_ubh);
UFSD("EXIT: ino %lu\n", inode->i_ino);
return retry;
}
static int ufs_trunc_dindirect(struct inode *inode, u64 offset, void *p)
{
struct super_block * sb;
struct ufs_sb_private_info * uspi;
struct ufs_buffer_head *dind_bh;
u64 i, tmp, dindirect_block;
void *dind;
int retry = 0;
UFSD("ENTER: ino %lu\n", inode->i_ino);
sb = inode->i_sb;
uspi = UFS_SB(sb)->s_uspi;
dindirect_block = (DIRECT_BLOCK > offset)
? ((DIRECT_BLOCK - offset) >> uspi->s_apbshift) : 0;
retry = 0;
tmp = ufs_data_ptr_to_cpu(sb, p);
if (!tmp)
return 0;
dind_bh = ubh_bread(sb, tmp, uspi->s_bsize);
if (tmp != ufs_data_ptr_to_cpu(sb, p)) {
ubh_brelse (dind_bh);
return 1;
}
if (!dind_bh) {
ufs_data_ptr_clear(uspi, p);
return 0;
}
for (i = dindirect_block ; i < uspi->s_apb ; i++) {
dind = ubh_get_data_ptr(uspi, dind_bh, i);
tmp = ufs_data_ptr_to_cpu(sb, dind);
if (!tmp)
continue;
retry |= ufs_trunc_indirect (inode, offset + (i << uspi->s_apbshift), dind);
ubh_mark_buffer_dirty(dind_bh);
}
for (i = 0; i < uspi->s_apb; i++)
if (!ufs_is_data_ptr_zero(uspi,
ubh_get_data_ptr(uspi, dind_bh, i)))
break;
if (i >= uspi->s_apb) {
tmp = ufs_data_ptr_to_cpu(sb, p);
ufs_data_ptr_clear(uspi, p);
ufs_free_blocks(inode, tmp, uspi->s_fpb);
mark_inode_dirty(inode);
ubh_bforget(dind_bh);
dind_bh = NULL;
}
if (IS_SYNC(inode) && dind_bh && ubh_buffer_dirty(dind_bh))
ubh_sync_block(dind_bh);
ubh_brelse (dind_bh);
UFSD("EXIT: ino %lu\n", inode->i_ino);
return retry;
}
static int ufs_trunc_tindirect(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
struct ufs_inode_info *ufsi = UFS_I(inode);
struct ufs_buffer_head * tind_bh;
u64 tindirect_block, tmp, i;
void *tind, *p;
int retry;
UFSD("ENTER: ino %lu\n", inode->i_ino);
retry = 0;
tindirect_block = (DIRECT_BLOCK > (UFS_NDADDR + uspi->s_apb + uspi->s_2apb))
? ((DIRECT_BLOCK - UFS_NDADDR - uspi->s_apb - uspi->s_2apb) >> uspi->s_2apbshift) : 0;
p = ufs_get_direct_data_ptr(uspi, ufsi, UFS_TIND_BLOCK);
if (!(tmp = ufs_data_ptr_to_cpu(sb, p)))
return 0;
tind_bh = ubh_bread (sb, tmp, uspi->s_bsize);
if (tmp != ufs_data_ptr_to_cpu(sb, p)) {
ubh_brelse (tind_bh);
return 1;
}
if (!tind_bh) {
ufs_data_ptr_clear(uspi, p);
return 0;
}
for (i = tindirect_block ; i < uspi->s_apb ; i++) {
tind = ubh_get_data_ptr(uspi, tind_bh, i);
retry |= ufs_trunc_dindirect(inode, UFS_NDADDR +
uspi->s_apb + ((i + 1) << uspi->s_2apbshift), tind);
ubh_mark_buffer_dirty(tind_bh);
}
for (i = 0; i < uspi->s_apb; i++)
if (!ufs_is_data_ptr_zero(uspi,
ubh_get_data_ptr(uspi, tind_bh, i)))
break;
if (i >= uspi->s_apb) {
tmp = ufs_data_ptr_to_cpu(sb, p);
ufs_data_ptr_clear(uspi, p);
ufs_free_blocks(inode, tmp, uspi->s_fpb);
mark_inode_dirty(inode);
ubh_bforget(tind_bh);
tind_bh = NULL;
}
if (IS_SYNC(inode) && tind_bh && ubh_buffer_dirty(tind_bh))
ubh_sync_block(tind_bh);
ubh_brelse (tind_bh);
UFSD("EXIT: ino %lu\n", inode->i_ino);
return retry;
}
static int ufs_alloc_lastblock(struct inode *inode)
{
int err = 0;
struct super_block *sb = inode->i_sb;
struct address_space *mapping = inode->i_mapping;
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
unsigned i, end;
sector_t lastfrag;
struct page *lastpage;
struct buffer_head *bh;
u64 phys64;
lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift;
if (!lastfrag)
goto out;
lastfrag--;
lastpage = ufs_get_locked_page(mapping, lastfrag >>
(PAGE_CACHE_SHIFT - inode->i_blkbits));
if (IS_ERR(lastpage)) {
err = -EIO;
goto out;
}
end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1);
bh = page_buffers(lastpage);
for (i = 0; i < end; ++i)
bh = bh->b_this_page;
err = ufs_getfrag_block(inode, lastfrag, bh, 1);
if (unlikely(err))
goto out_unlock;
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
/*
* we do not zeroize fragment, because of
* if it maped to hole, it already contains zeroes
*/
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
set_page_dirty(lastpage);
}
if (lastfrag >= UFS_IND_FRAGMENT) {
end = uspi->s_fpb - ufs_fragnum(lastfrag) - 1;
phys64 = bh->b_blocknr + 1;
for (i = 0; i < end; ++i) {
bh = sb_getblk(sb, i + phys64);
lock_buffer(bh);
memset(bh->b_data, 0, sb->s_blocksize);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
unlock_buffer(bh);
sync_dirty_buffer(bh);
brelse(bh);
}
}
out_unlock:
ufs_put_locked_page(lastpage);
out:
return err;
}
int ufs_truncate(struct inode *inode, loff_t old_i_size)
{
struct ufs_inode_info *ufsi = UFS_I(inode);
struct super_block *sb = inode->i_sb;
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
int retry, err = 0;
UFSD("ENTER: ino %lu, i_size: %llu, old_i_size: %llu\n",
inode->i_ino, (unsigned long long)i_size_read(inode),
(unsigned long long)old_i_size);
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return -EINVAL;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return -EPERM;
err = ufs_alloc_lastblock(inode);
if (err) {
i_size_write(inode, old_i_size);
goto out;
}
block_truncate_page(inode->i_mapping, inode->i_size, ufs_getfrag_block);
while (1) {
retry = ufs_trunc_direct(inode);
retry |= ufs_trunc_indirect(inode, UFS_IND_BLOCK,
ufs_get_direct_data_ptr(uspi, ufsi,
UFS_IND_BLOCK));
retry |= ufs_trunc_dindirect(inode, UFS_IND_BLOCK + uspi->s_apb,
ufs_get_direct_data_ptr(uspi, ufsi,
UFS_DIND_BLOCK));
retry |= ufs_trunc_tindirect (inode);
if (!retry)
break;
if (IS_SYNC(inode) && (inode->i_state & I_DIRTY))
ufs_sync_inode (inode);
yield();
}
inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
ufsi->i_lastfrag = DIRECT_FRAGMENT;
mark_inode_dirty(inode);
out:
UFSD("EXIT: err %d\n", err);
return err;
}
int ufs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
unsigned int ia_valid = attr->ia_valid;
int error;
error = inode_change_ok(inode, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
loff_t old_i_size = inode->i_size;
/* XXX(truncate): truncate_setsize should be called last */
truncate_setsize(inode, attr->ia_size);
lock_ufs(inode->i_sb);
error = ufs_truncate(inode, old_i_size);
unlock_ufs(inode->i_sb);
if (error)
return error;
}
setattr_copy(inode, attr);
mark_inode_dirty(inode);
return 0;
}
const struct inode_operations ufs_file_inode_operations = {
.setattr = ufs_setattr,
};

13
fs/ufs/ufs.h
View File

@ -24,8 +24,6 @@ struct ufs_sb_info {
unsigned s_cgno[UFS_MAX_GROUP_LOADED];
unsigned short s_cg_loaded;
unsigned s_mount_opt;
struct mutex mutex;
struct task_struct *mutex_owner;
struct super_block *sb;
int work_queued; /* non-zero if the delayed work is queued */
struct delayed_work sync_work; /* FS sync delayed work */
@ -46,6 +44,8 @@ struct ufs_inode_info {
__u32 i_oeftflag;
__u16 i_osync;
__u64 i_lastfrag;
seqlock_t meta_lock;
struct mutex truncate_mutex;
__u32 i_dir_start_lookup;
struct inode vfs_inode;
};
@ -122,7 +122,7 @@ extern struct inode *ufs_iget(struct super_block *, unsigned long);
extern int ufs_write_inode (struct inode *, struct writeback_control *);
extern int ufs_sync_inode (struct inode *);
extern void ufs_evict_inode (struct inode *);
extern int ufs_getfrag_block (struct inode *inode, sector_t fragment, struct buffer_head *bh_result, int create);
extern int ufs_setattr(struct dentry *dentry, struct iattr *attr);
/* namei.c */
extern const struct file_operations ufs_dir_operations;
@ -140,10 +140,6 @@ void ufs_mark_sb_dirty(struct super_block *sb);
extern const struct inode_operations ufs_fast_symlink_inode_operations;
extern const struct inode_operations ufs_symlink_inode_operations;
/* truncate.c */
extern int ufs_truncate (struct inode *, loff_t);
extern int ufs_setattr(struct dentry *dentry, struct iattr *attr);
static inline struct ufs_sb_info *UFS_SB(struct super_block *sb)
{
return sb->s_fs_info;
@ -170,7 +166,4 @@ static inline u32 ufs_dtogd(struct ufs_sb_private_info * uspi, u64 b)
return do_div(b, uspi->s_fpg);
}
extern void lock_ufs(struct super_block *sb);
extern void unlock_ufs(struct super_block *sb);
#endif /* _UFS_UFS_H */

6
fs/xfs/xfs_aops.c
View File

@ -119,8 +119,7 @@ xfs_setfilesize_trans_alloc(
* We may pass freeze protection with a transaction. So tell lockdep
* we released it.
*/
rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
1, _THIS_IP_);
__sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
/*
* We hand off the transaction to the completion thread now, so
* clear the flag here.
@ -171,8 +170,7 @@ xfs_setfilesize_ioend(
* Similarly for freeze protection.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
0, 1, _THIS_IP_);
__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
}

33
include/linux/fs.h
View File

@ -1,7 +1,6 @@
#ifndef _LINUX_FS_H
#define _LINUX_FS_H
#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/kdev_t.h>
@ -30,6 +29,8 @@
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/blk_types.h>
#include <linux/workqueue.h>
#include <linux/percpu-rwsem.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
@ -636,7 +637,7 @@ struct inode {
unsigned long dirtied_time_when;
struct hlist_node i_hash;
struct list_head i_wb_list; /* backing dev IO list */
struct list_head i_io_list; /* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
struct bdi_writeback *i_wb; /* the associated cgroup wb */
@ -1281,16 +1282,9 @@ enum {
#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
struct sb_writers {
/* Counters for counting writers at each level */
struct percpu_counter counter[SB_FREEZE_LEVELS];
wait_queue_head_t wait; /* queue for waiting for
writers / faults to finish */
int frozen; /* Is sb frozen? */
wait_queue_head_t wait_unfrozen; /* queue for waiting for
sb to be thawed */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lockdep_map lock_map[SB_FREEZE_LEVELS];
#endif
int frozen; /* Is sb frozen? */
wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */
struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS];
};
struct super_block {
@ -1316,7 +1310,6 @@ struct super_block {
#endif
const struct xattr_handler **s_xattr;
struct list_head s_inodes; /* all inodes */
struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */
struct list_head s_mounts; /* list of mounts; _not_ for fs use */
struct block_device *s_bdev;
@ -1382,11 +1375,18 @@ struct super_block {
struct list_lru s_dentry_lru ____cacheline_aligned_in_smp;
struct list_lru s_inode_lru ____cacheline_aligned_in_smp;
struct rcu_head rcu;
struct work_struct destroy_work;
struct mutex s_sync_lock; /* sync serialisation lock */
/*
* Indicates how deep in a filesystem stack this SB is
*/
int s_stack_depth;
/* s_inode_list_lock protects s_inodes */
spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp;
struct list_head s_inodes; /* all inodes */
};
extern struct timespec current_fs_time(struct super_block *sb);
@ -1398,6 +1398,11 @@ extern struct timespec current_fs_time(struct super_block *sb);
void __sb_end_write(struct super_block *sb, int level);
int __sb_start_write(struct super_block *sb, int level, bool wait);
#define __sb_writers_acquired(sb, lev) \
percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
#define __sb_writers_release(sb, lev) \
percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
/**
* sb_end_write - drop write access to a superblock
* @sb: the super we wrote to
@ -2614,7 +2619,7 @@ static inline void insert_inode_hash(struct inode *inode)
extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
if (!inode_unhashed(inode))
if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
__remove_inode_hash(inode);
}

4
include/linux/fsnotify_backend.h
View File

@ -368,7 +368,7 @@ extern void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, un
extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group);
extern void fsnotify_get_mark(struct fsnotify_mark *mark);
extern void fsnotify_put_mark(struct fsnotify_mark *mark);
extern void fsnotify_unmount_inodes(struct list_head *list);
extern void fsnotify_unmount_inodes(struct super_block *sb);
/* put here because inotify does some weird stuff when destroying watches */
extern void fsnotify_init_event(struct fsnotify_event *event,
@ -404,7 +404,7 @@ static inline u32 fsnotify_get_cookie(void)
return 0;
}
static inline void fsnotify_unmount_inodes(struct list_head *list)
static inline void fsnotify_unmount_inodes(struct super_block *sb)
{}
#endif /* CONFIG_FSNOTIFY */

5
include/linux/list.h
View File

@ -672,6 +672,11 @@ static inline void hlist_add_fake(struct hlist_node *n)
n->pprev = &n->next;
}
static inline bool hlist_fake(struct hlist_node *h)
{
return h->pprev == &h->next;
}
/*
* Move a list from one list head to another. Fixup the pprev
* reference of the first entry if it exists.

20
include/linux/percpu-rwsem.h
View File

@ -16,6 +16,7 @@ struct percpu_rw_semaphore {
};
extern void percpu_down_read(struct percpu_rw_semaphore *);
extern int percpu_down_read_trylock(struct percpu_rw_semaphore *);
extern void percpu_up_read(struct percpu_rw_semaphore *);
extern void percpu_down_write(struct percpu_rw_semaphore *);
@ -31,4 +32,23 @@ extern void percpu_free_rwsem(struct percpu_rw_semaphore *);
__percpu_init_rwsem(brw, #brw, &rwsem_key); \
})
#define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem)
static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
lock_release(&sem->rw_sem.dep_map, 1, ip);
#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
if (!read)
sem->rw_sem.owner = NULL;
#endif
}
static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
bool read, unsigned long ip)
{
lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
}
#endif

1
init/Kconfig
View File

@ -927,7 +927,6 @@ config NUMA_BALANCING_DEFAULT_ENABLED
menuconfig CGROUPS
bool "Control Group support"
select KERNFS
select PERCPU_RWSEM
help
This option adds support for grouping sets of processes together, for
use with process control subsystems such as Cpusets, CFS, memory

3
kernel/locking/Makefile
View File

@ -1,5 +1,5 @@
obj-y += mutex.o semaphore.o rwsem.o
obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@ -24,6 +24,5 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
obj-$(CONFIG_PERCPU_RWSEM) += percpu-rwsem.o
obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o

13
kernel/locking/percpu-rwsem.c
View File

@ -88,6 +88,19 @@ void percpu_down_read(struct percpu_rw_semaphore *brw)
__up_read(&brw->rw_sem);
}
int percpu_down_read_trylock(struct percpu_rw_semaphore *brw)
{
if (unlikely(!update_fast_ctr(brw, +1))) {
if (!__down_read_trylock(&brw->rw_sem))
return 0;
atomic_inc(&brw->slow_read_ctr);
__up_read(&brw->rw_sem);
}
rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 1, _RET_IP_);
return 1;
}
void percpu_up_read(struct percpu_rw_semaphore *brw)
{
rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_);

3
lib/Kconfig
View File

@ -53,9 +53,6 @@ config GENERIC_IO
config STMP_DEVICE
bool
config PERCPU_RWSEM
bool
config ARCH_USE_CMPXCHG_LOCKREF
bool

8
mm/backing-dev.c
View File

@ -55,13 +55,13 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0;
spin_lock(&wb->list_lock);
list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
list_for_each_entry(inode, &wb->b_dirty, i_io_list)
nr_dirty++;
list_for_each_entry(inode, &wb->b_io, i_wb_list)
list_for_each_entry(inode, &wb->b_io, i_io_list)
nr_io++;
list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
list_for_each_entry(inode, &wb->b_more_io, i_io_list)
nr_more_io++;
list_for_each_entry(inode, &wb->b_dirty_time, i_wb_list)
list_for_each_entry(inode, &wb->b_dirty_time, i_io_list)
if (inode->i_state & I_DIRTY_TIME)
nr_dirty_time++;
spin_unlock(&wb->list_lock);

25
mm/swapfile.c
View File

@ -2143,11 +2143,10 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
if (S_ISBLK(inode->i_mode)) {
p->bdev = bdgrab(I_BDEV(inode));
error = blkdev_get(p->bdev,
FMODE_READ | FMODE_WRITE | FMODE_EXCL,
sys_swapon);
FMODE_READ | FMODE_WRITE | FMODE_EXCL, p);
if (error < 0) {
p->bdev = NULL;
return -EINVAL;
return error;
}
p->old_block_size = block_size(p->bdev);
error = set_blocksize(p->bdev, PAGE_SIZE);
@ -2348,7 +2347,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
struct filename *name;
struct file *swap_file = NULL;
struct address_space *mapping;
int i;
int prio;
int error;
union swap_header *swap_header;
@ -2388,19 +2386,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
p->swap_file = swap_file;
mapping = swap_file->f_mapping;
for (i = 0; i < nr_swapfiles; i++) {
struct swap_info_struct *q = swap_info[i];
if (q == p || !q->swap_file)
continue;
if (mapping == q->swap_file->f_mapping) {
error = -EBUSY;
goto bad_swap;
}
}
inode = mapping->host;
/* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */
error = claim_swapfile(p, inode);
if (unlikely(error))
@ -2433,6 +2420,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
goto bad_swap;
}
if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
int cpu;
p->flags |= SWP_SOLIDSTATE;
/*
* select a random position to start with to help wear leveling
@ -2451,9 +2440,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
error = -ENOMEM;
goto bad_swap;
}
for_each_possible_cpu(i) {
for_each_possible_cpu(cpu) {
struct percpu_cluster *cluster;
cluster = per_cpu_ptr(p->percpu_cluster, i);
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
cluster_set_null(&cluster->index);
}
}