Merge branch 'work.dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull dcache_readdir() fixes from Al Viro: "The couple of patches you'd been OK with; no hlist conversion yet, and cursors are still in the list of children" [ Al is referring to future work to avoid some nasty O(n**2) behavior with the readdir cursors when you have lots of concurrent readdirs. This is just a fix for a race with a trivial cleanup - Linus ] * 'work.dcache' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: libfs: take cursors out of list when moving past the end of directory Fix the locking in dcache_readdir() and friends
This commit is contained in:
commit
ad338d0543
129
fs/libfs.c
129
fs/libfs.c
|
@ -89,58 +89,45 @@ int dcache_dir_close(struct inode *inode, struct file *file)
|
|||
EXPORT_SYMBOL(dcache_dir_close);
|
||||
|
||||
/* parent is locked at least shared */
|
||||
static struct dentry *next_positive(struct dentry *parent,
|
||||
struct list_head *from,
|
||||
int count)
|
||||
/*
|
||||
* Returns an element of siblings' list.
|
||||
* We are looking for <count>th positive after <p>; if
|
||||
* found, dentry is grabbed and returned to caller.
|
||||
* If no such element exists, NULL is returned.
|
||||
*/
|
||||
static struct dentry *scan_positives(struct dentry *cursor,
|
||||
struct list_head *p,
|
||||
loff_t count,
|
||||
struct dentry *last)
|
||||
{
|
||||
unsigned *seq = &parent->d_inode->i_dir_seq, n;
|
||||
struct dentry *res;
|
||||
struct list_head *p;
|
||||
bool skipped;
|
||||
int i;
|
||||
struct dentry *dentry = cursor->d_parent, *found = NULL;
|
||||
|
||||
retry:
|
||||
i = count;
|
||||
skipped = false;
|
||||
n = smp_load_acquire(seq) & ~1;
|
||||
res = NULL;
|
||||
rcu_read_lock();
|
||||
for (p = from->next; p != &parent->d_subdirs; p = p->next) {
|
||||
spin_lock(&dentry->d_lock);
|
||||
while ((p = p->next) != &dentry->d_subdirs) {
|
||||
struct dentry *d = list_entry(p, struct dentry, d_child);
|
||||
if (!simple_positive(d)) {
|
||||
skipped = true;
|
||||
} else if (!--i) {
|
||||
res = d;
|
||||
// we must at least skip cursors, to avoid livelocks
|
||||
if (d->d_flags & DCACHE_DENTRY_CURSOR)
|
||||
continue;
|
||||
if (simple_positive(d) && !--count) {
|
||||
spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
|
||||
if (simple_positive(d))
|
||||
found = dget_dlock(d);
|
||||
spin_unlock(&d->d_lock);
|
||||
if (likely(found))
|
||||
break;
|
||||
count = 1;
|
||||
}
|
||||
if (need_resched()) {
|
||||
list_move(&cursor->d_child, p);
|
||||
p = &cursor->d_child;
|
||||
spin_unlock(&dentry->d_lock);
|
||||
cond_resched();
|
||||
spin_lock(&dentry->d_lock);
|
||||
}
|
||||
}
|
||||
rcu_read_unlock();
|
||||
if (skipped) {
|
||||
smp_rmb();
|
||||
if (unlikely(*seq != n))
|
||||
goto retry;
|
||||
}
|
||||
return res;
|
||||
}
|
||||
|
||||
static void move_cursor(struct dentry *cursor, struct list_head *after)
|
||||
{
|
||||
struct dentry *parent = cursor->d_parent;
|
||||
unsigned n, *seq = &parent->d_inode->i_dir_seq;
|
||||
spin_lock(&parent->d_lock);
|
||||
for (;;) {
|
||||
n = *seq;
|
||||
if (!(n & 1) && cmpxchg(seq, n, n + 1) == n)
|
||||
break;
|
||||
cpu_relax();
|
||||
}
|
||||
__list_del(cursor->d_child.prev, cursor->d_child.next);
|
||||
if (after)
|
||||
list_add(&cursor->d_child, after);
|
||||
else
|
||||
list_add_tail(&cursor->d_child, &parent->d_subdirs);
|
||||
smp_store_release(seq, n + 2);
|
||||
spin_unlock(&parent->d_lock);
|
||||
spin_unlock(&dentry->d_lock);
|
||||
dput(last);
|
||||
return found;
|
||||
}
|
||||
|
||||
loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
|
||||
|
@ -158,18 +145,26 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence)
|
|||
return -EINVAL;
|
||||
}
|
||||
if (offset != file->f_pos) {
|
||||
file->f_pos = offset;
|
||||
if (file->f_pos >= 2) {
|
||||
struct dentry *cursor = file->private_data;
|
||||
struct dentry *to;
|
||||
loff_t n = file->f_pos - 2;
|
||||
struct dentry *to = NULL;
|
||||
|
||||
inode_lock_shared(dentry->d_inode);
|
||||
to = next_positive(dentry, &dentry->d_subdirs, n);
|
||||
move_cursor(cursor, to ? &to->d_child : NULL);
|
||||
|
||||
if (offset > 2)
|
||||
to = scan_positives(cursor, &dentry->d_subdirs,
|
||||
offset - 2, NULL);
|
||||
spin_lock(&dentry->d_lock);
|
||||
if (to)
|
||||
list_move(&cursor->d_child, &to->d_child);
|
||||
else
|
||||
list_del_init(&cursor->d_child);
|
||||
spin_unlock(&dentry->d_lock);
|
||||
dput(to);
|
||||
|
||||
file->f_pos = offset;
|
||||
|
||||
inode_unlock_shared(dentry->d_inode);
|
||||
}
|
||||
}
|
||||
return offset;
|
||||
}
|
||||
EXPORT_SYMBOL(dcache_dir_lseek);
|
||||
|
@ -190,25 +185,35 @@ int dcache_readdir(struct file *file, struct dir_context *ctx)
|
|||
{
|
||||
struct dentry *dentry = file->f_path.dentry;
|
||||
struct dentry *cursor = file->private_data;
|
||||
struct list_head *p = &cursor->d_child;
|
||||
struct dentry *next;
|
||||
bool moved = false;
|
||||
struct list_head *anchor = &dentry->d_subdirs;
|
||||
struct dentry *next = NULL;
|
||||
struct list_head *p;
|
||||
|
||||
if (!dir_emit_dots(file, ctx))
|
||||
return 0;
|
||||
|
||||
if (ctx->pos == 2)
|
||||
p = &dentry->d_subdirs;
|
||||
while ((next = next_positive(dentry, p, 1)) != NULL) {
|
||||
p = anchor;
|
||||
else if (!list_empty(&cursor->d_child))
|
||||
p = &cursor->d_child;
|
||||
else
|
||||
return 0;
|
||||
|
||||
while ((next = scan_positives(cursor, p, 1, next)) != NULL) {
|
||||
if (!dir_emit(ctx, next->d_name.name, next->d_name.len,
|
||||
d_inode(next)->i_ino, dt_type(d_inode(next))))
|
||||
break;
|
||||
moved = true;
|
||||
p = &next->d_child;
|
||||
ctx->pos++;
|
||||
p = &next->d_child;
|
||||
}
|
||||
if (moved)
|
||||
move_cursor(cursor, p);
|
||||
spin_lock(&dentry->d_lock);
|
||||
if (next)
|
||||
list_move_tail(&cursor->d_child, &next->d_child);
|
||||
else
|
||||
list_del_init(&cursor->d_child);
|
||||
spin_unlock(&dentry->d_lock);
|
||||
dput(next);
|
||||
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL(dcache_readdir);
|
||||
|
|
Loading…
Reference in New Issue