diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-08-18 09:35:08 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-08-18 09:35:08 -0700 |
commit | 145c3ae46b37993b0debb0b3da6256daea4a6ec5 (patch) | |
tree | 0dbff382ce36b23b3d2dbff87d3eaab73a07a2a4 | |
parent | 81ca03a0e2ea0207b2df80e0edcf4c775c07a505 (diff) | |
parent | 99b7db7b8ffd6bb755eb0a175596421a0b581cb2 (diff) |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
fs: brlock vfsmount_lock
fs: scale files_lock
lglock: introduce special lglock and brlock spin locks
tty: fix fu_list abuse
fs: cleanup files_lock locking
fs: remove extra lookup in __lookup_hash
fs: fs_struct rwlock to spinlock
apparmor: use task path helpers
fs: dentry allocation consolidation
fs: fix do_lookup false negative
mbcache: Limit the maximum number of cache entries
hostfs ->follow_link() braino
hostfs: dumb (and usually harmless) tpyo - strncpy instead of strlcpy
remove SWRITE* I/O types
kill BH_Ordered flag
vfs: update ctime when changing the file's permission by setfacl
cramfs: only unlock new inodes
fix reiserfs_evict_inode end_writeback second call
43 files changed, 797 insertions, 450 deletions
diff --git a/drivers/char/pty.c b/drivers/char/pty.c index ad46eae1f9bb..c350d01716bd 100644 --- a/drivers/char/pty.c +++ b/drivers/char/pty.c @@ -675,8 +675,8 @@ static int ptmx_open(struct inode *inode, struct file *filp) } set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */ - filp->private_data = tty; - file_move(filp, &tty->tty_files); + + tty_add_file(tty, filp); retval = devpts_pty_new(inode, tty->link); if (retval) diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index 0350c42375a2..949067a0bd47 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -136,6 +136,9 @@ LIST_HEAD(tty_drivers); /* linked list of tty drivers */ DEFINE_MUTEX(tty_mutex); EXPORT_SYMBOL(tty_mutex); +/* Spinlock to protect the tty->tty_files list */ +DEFINE_SPINLOCK(tty_files_lock); + static ssize_t tty_read(struct file *, char __user *, size_t, loff_t *); static ssize_t tty_write(struct file *, const char __user *, size_t, loff_t *); ssize_t redirected_tty_write(struct file *, const char __user *, @@ -185,6 +188,41 @@ void free_tty_struct(struct tty_struct *tty) kfree(tty); } +static inline struct tty_struct *file_tty(struct file *file) +{ + return ((struct tty_file_private *)file->private_data)->tty; +} + +/* Associate a new file with the tty structure */ +void tty_add_file(struct tty_struct *tty, struct file *file) +{ + struct tty_file_private *priv; + + /* XXX: must implement proper error handling in callers */ + priv = kmalloc(sizeof(*priv), GFP_KERNEL|__GFP_NOFAIL); + + priv->tty = tty; + priv->file = file; + file->private_data = priv; + + spin_lock(&tty_files_lock); + list_add(&priv->list, &tty->tty_files); + spin_unlock(&tty_files_lock); +} + +/* Delete file from its tty */ +void tty_del_file(struct file *file) +{ + struct tty_file_private *priv = file->private_data; + + spin_lock(&tty_files_lock); + list_del(&priv->list); + spin_unlock(&tty_files_lock); + file->private_data = NULL; + kfree(priv); +} + + #define TTY_NUMBER(tty) ((tty)->index + (tty)->driver->name_base) /** @@ -235,11 +273,11 @@ static int check_tty_count(struct tty_struct *tty, const char *routine) struct list_head *p; int count = 0; - file_list_lock(); + spin_lock(&tty_files_lock); list_for_each(p, &tty->tty_files) { count++; } - file_list_unlock(); + spin_unlock(&tty_files_lock); if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_SLAVE && tty->link && tty->link->count) @@ -497,6 +535,7 @@ void __tty_hangup(struct tty_struct *tty) struct file *cons_filp = NULL; struct file *filp, *f = NULL; struct task_struct *p; + struct tty_file_private *priv; int closecount = 0, n; unsigned long flags; int refs = 0; @@ -506,7 +545,7 @@ void __tty_hangup(struct tty_struct *tty) spin_lock(&redirect_lock); - if (redirect && redirect->private_data == tty) { + if (redirect && file_tty(redirect) == tty) { f = redirect; redirect = NULL; } @@ -519,9 +558,10 @@ void __tty_hangup(struct tty_struct *tty) workqueue with the lock held */ check_tty_count(tty, "tty_hangup"); - file_list_lock(); + spin_lock(&tty_files_lock); /* This breaks for file handles being sent over AF_UNIX sockets ? */ - list_for_each_entry(filp, &tty->tty_files, f_u.fu_list) { + list_for_each_entry(priv, &tty->tty_files, list) { + filp = priv->file; if (filp->f_op->write == redirected_tty_write) cons_filp = filp; if (filp->f_op->write != tty_write) @@ -530,7 +570,7 @@ void __tty_hangup(struct tty_struct *tty) __tty_fasync(-1, filp, 0); /* can't block */ filp->f_op = &hung_up_tty_fops; } - file_list_unlock(); + spin_unlock(&tty_files_lock); tty_ldisc_hangup(tty); @@ -889,12 +929,10 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { int i; - struct tty_struct *tty; - struct inode *inode; + struct inode *inode = file->f_path.dentry->d_inode; + struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; - tty = file->private_data; - inode = file->f_path.dentry->d_inode; if (tty_paranoia_check(tty, inode, "tty_read")) return -EIO; if (!tty || (test_bit(TTY_IO_ERROR, &tty->flags))) @@ -1065,12 +1103,11 @@ void tty_write_message(struct tty_struct *tty, char *msg) static ssize_t tty_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct tty_struct *tty; struct inode *inode = file->f_path.dentry->d_inode; + struct tty_struct *tty = file_tty(file); + struct tty_ldisc *ld; ssize_t ret; - struct tty_ldisc *ld; - tty = file->private_data; if (tty_paranoia_check(tty, inode, "tty_write")) return -EIO; if (!tty || !tty->ops->write || @@ -1424,9 +1461,9 @@ static void release_one_tty(struct work_struct *work) tty_driver_kref_put(driver); module_put(driver->owner); - file_list_lock(); + spin_lock(&tty_files_lock); list_del_init(&tty->tty_files); - file_list_unlock(); + spin_unlock(&tty_files_lock); put_pid(tty->pgrp); put_pid(tty->session); @@ -1507,13 +1544,13 @@ static void release_tty(struct tty_struct *tty, int idx) int tty_release(struct inode *inode, struct file *filp) { - struct tty_struct *tty, *o_tty; + struct tty_struct *tty = file_tty(filp); + struct tty_struct *o_tty; int pty_master, tty_closing, o_tty_closing, do_sleep; int devpts; int idx; char buf[64]; - tty = filp->private_data; if (tty_paranoia_check(tty, inode, "tty_release_dev")) return 0; @@ -1671,8 +1708,7 @@ int tty_release(struct inode *inode, struct file *filp) * - do_tty_hangup no longer sees this file descriptor as * something that needs to be handled for hangups. */ - file_kill(filp); - filp->private_data = NULL; + tty_del_file(filp); /* * Perform some housekeeping before deciding whether to return. @@ -1839,8 +1875,8 @@ got_driver: return PTR_ERR(tty); } - filp->private_data = tty; - file_move(filp, &tty->tty_files); + tty_add_file(tty, filp); + check_tty_count(tty, "tty_open"); if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) @@ -1916,11 +1952,10 @@ got_driver: static unsigned int tty_poll(struct file *filp, poll_table *wait) { - struct tty_struct *tty; + struct tty_struct *tty = file_tty(filp); struct tty_ldisc *ld; int ret = 0; - tty = filp->private_data; if (tty_paranoia_check(tty, filp->f_path.dentry->d_inode, "tty_poll")) return 0; @@ -1933,11 +1968,10 @@ static unsigned int tty_poll(struct file *filp, poll_table *wait) static int __tty_fasync(int fd, struct file *filp, int on) { - struct tty_struct *tty; + struct tty_struct *tty = file_tty(filp); unsigned long flags; int retval = 0; - tty = filp->private_data; if (tty_paranoia_check(tty, filp->f_path.dentry->d_inode, "tty_fasync")) goto out; @@ -2491,13 +2525,13 @@ EXPORT_SYMBOL(tty_pair_get_pty); */ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct tty_struct *tty, *real_tty; + struct tty_struct *tty = file_tty(file); + struct tty_struct *real_tty; void __user *p = (void __user *)arg; int retval; struct tty_ldisc *ld; struct inode *inode = file->f_dentry->d_inode; - tty = file->private_data; if (tty_paranoia_check(tty, inode, "tty_ioctl")) return -EINVAL; @@ -2619,7 +2653,7 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file->f_dentry->d_inode; - struct tty_struct *tty = file->private_data; + struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; int retval = -ENOIOCTLCMD; @@ -2711,7 +2745,7 @@ void __do_SAK(struct tty_struct *tty) if (!filp) continue; if (filp->f_op->read == tty_read && - filp->private_data == tty) { + file_tty(filp) == tty) { printk(KERN_NOTICE "SAK: killed process %d" " (%s): fd#%d opened to the tty\n", task_pid_nr(p), p->comm, i); diff --git a/drivers/staging/pohmelfs/path_entry.c b/drivers/staging/pohmelfs/path_entry.c index cdc4dd50d638..8ec83d2dffb7 100644 --- a/drivers/staging/pohmelfs/path_entry.c +++ b/drivers/staging/pohmelfs/path_entry.c @@ -44,9 +44,9 @@ int pohmelfs_construct_path_string(struct pohmelfs_inode *pi, void *data, int le return -ENOENT; } - read_lock(¤t->fs->lock); + spin_lock(¤t->fs->lock); path.mnt = mntget(current->fs->root.mnt); - read_unlock(¤t->fs->lock); + spin_unlock(¤t->fs->lock); path.dentry = d; @@ -91,9 +91,9 @@ int pohmelfs_path_length(struct pohmelfs_inode *pi) return -ENOENT; } - read_lock(¤t->fs->lock); + spin_lock(¤t->fs->lock); root = dget(current->fs->root.dentry); - read_unlock(¤t->fs->lock); + spin_unlock(¤t->fs->lock); spin_lock(&dcache_lock); diff --git a/fs/buffer.c b/fs/buffer.c index 50efa339e051..3e7dca279d1c 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -770,11 +770,12 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) spin_unlock(lock); /* * Ensure any pending I/O completes so that - * ll_rw_block() actually writes the current - * contents - it is a noop if I/O is still in - * flight on potentially older contents. + * write_dirty_buffer() actually writes the + * current contents - it is a noop if I/O is + * still in flight on potentially older + * contents. */ - ll_rw_block(SWRITE_SYNC_PLUG, 1, &bh); + write_dirty_buffer(bh, WRITE_SYNC_PLUG); /* * Kick off IO for the previous mapping. Note @@ -2912,13 +2913,6 @@ int submit_bh(int rw, struct buffer_head * bh) BUG_ON(buffer_unwritten(bh)); /* - * Mask in barrier bit for a write (could be either a WRITE or a - * WRITE_SYNC - */ - if (buffer_ordered(bh) && (rw & WRITE)) - rw |= WRITE_BARRIER; - - /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (rw & WRITE)) @@ -2956,22 +2950,21 @@ EXPORT_SYMBOL(submit_bh); /** * ll_rw_block: low-level access to block devices (DEPRECATED) - * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead) + * @rw: whether to %READ or %WRITE or maybe %READA (readahead) * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * * ll_rw_block() takes an array of pointers to &struct buffer_heads, and * requests an I/O operation on them, either a %READ or a %WRITE. The third - * %SWRITE is like %WRITE only we make sure that the *current* data in buffers - * are sent to disk. The fourth %READA option is described in the documentation - * for generic_make_request() which ll_rw_block() calls. + * %READA option is described in the documentation for generic_make_request() + * which ll_rw_block() calls. * * This function drops any buffer that it cannot get a lock on (with the - * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be - * clean when doing a write request, and any buffer that appears to be - * up-to-date when doing read request. Further it marks as clean buffers that - * are processed for writing (the buffer cache won't assume that they are - * actually clean until the buffer gets unlocked). + * BH_Lock state bit), any buffer that appears to be clean when doing a write + * request, and any buffer that appears to be up-to-date when doing read + * request. Further it marks as clean buffers that are processed for + * writing (the buffer cache won't assume that they are actually clean + * until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if approriate), unlocks the buffer and wakes @@ -2987,20 +2980,13 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; - if (rw == SWRITE || rw == SWRITE_SYNC || rw == SWRITE_SYNC_PLUG) - lock_buffer(bh); - else if (!trylock_buffer(bh)) + if (!trylock_buffer(bh)) continue; - - if (rw == WRITE || rw == SWRITE || rw == SWRITE_SYNC || - rw == SWRITE_SYNC_PLUG) { + if (rw == WRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; get_bh(bh); - if (rw == SWRITE_SYNC) - submit_bh(WRITE_SYNC, bh); - else - submit_bh(WRITE, bh); + submit_bh(WRITE, bh); continue; } } else { @@ -3016,12 +3002,25 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) } EXPORT_SYMBOL(ll_rw_block); +void write_dirty_buffer(struct buffer_head *bh, int rw) +{ + lock_buffer(bh); + if (!test_clear_buffer_dirty(bh)) { + unlock_buffer(bh); + return; + } + bh->b_end_io = end_buffer_write_sync; + get_bh(bh); + submit_bh(rw, bh); +} +EXPORT_SYMBOL(write_dirty_buffer); + /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ -int sync_dirty_buffer(struct buffer_head *bh) +int __sync_dirty_buffer(struct buffer_head *bh, int rw) { int ret = 0; @@ -3030,7 +3029,7 @@ int sync_dirty_buffer(struct buffer_head *bh) if (test_clear_buffer_dirty(bh)) { get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(WRITE_SYNC, bh); + ret = submit_bh(rw, bh); wait_on_buffer(bh); if (buffer_eopnotsupp(bh)) { clear_buffer_eopnotsupp(bh); @@ -3043,6 +3042,12 @@ int sync_dirty_buffer(struct buffer_head *bh) } return ret; } +EXPORT_SYMBOL(__sync_dirty_buffer); + +int sync_dirty_buffer(struct buffer_head *bh) +{ + return __sync_dirty_buffer(bh, WRITE_SYNC); +} EXPORT_SYMBOL(sync_dirty_buffer); /* diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index a53b130b366c..1e7a33028d33 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -80,7 +80,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, } } else { inode = iget_locked(sb, CRAMINO(cramfs_inode)); - if (inode) { + if (inode && (inode->i_state & I_NEW)) { setup_inode(inode, cramfs_inode); unlock_new_inode(inode); } diff --git a/fs/dcache.c b/fs/dcache.c index 4d13bf50b7b1..83293be48149 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1332,31 +1332,13 @@ EXPORT_SYMBOL(d_add_ci); * d_lookup - search for a dentry * @parent: parent dentry * @name: qstr of name we wish to find + * Returns: dentry, or NULL * - * Searches the children of the parent dentry for the name in question. If - * the dentry is found its reference count is incremented and the dentry - * is returned. The caller must use dput to free the entry when it has - * finished using it. %NULL is returned on failure. - * - * __d_lookup is dcache_lock free. The hash list is protected using RCU. - * Memory barriers are used while updating and doing lockless traversal. - * To avoid races with d_move while rename is happening, d_lock is used. - * - * Overflows in memcmp(), while d_move, are avoided by keeping the length - * and name pointer in one structure pointed by d_qstr. - * - * rcu_read_lock() and rcu_read_unlock() are used to disable preemption while - * lookup is going on. - * - * The dentry unused LRU is not updated even if lookup finds the required dentry - * in there. It is updated in places such as prune_dcache, shrink_dcache_sb, - * select_parent and __dget_locked. This laziness saves lookup from dcache_lock - * acquisition. - * - * d_lookup() is protected against the concurrent renames in some unrelated - * directory using the seqlockt_t rename_lock. + * d_lookup searches the children of the parent dentry for the name in + * question. If the dentry is found its reference count is incremented and the + * dentry is returned. The caller must use dput to free the entry when it has + * finished using it. %NULL is returned if the dentry does not exist. */ - struct dentry * d_lookup(struct dentry * parent, struct qstr * name) { struct dentry * dentry = NULL; @@ -1372,6 +1354,21 @@ struct dentry * d_lookup(struct dentry * parent, struct qstr * name) } EXPORT_SYMBOL(d_lookup); +/* + * __d_lookup - search for a dentry (racy) + * @parent: parent dentry + * @name: qstr of name we wish to find + * Returns: dentry, or NULL + * + * __d_lookup is like d_lookup, however it may (rarely) return a + * false-negative result due to unrelated rename activity. + * + * __d_lookup is slightly faster by avoiding rename_lock read seqlock, + * however it must be used carefully, eg. with a following d_lookup in + * the case of failure. + * + * __d_lookup callers must be commented. + */ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name) { unsigned int len = name->len; @@ -1382,6 +1379,19 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name) struct hlist_node *node; struct dentry *dentry; + /* + * The hash list is protected using RCU. + * + * Take d_lock when comparing a candidate dentry, to avoid races + * with d_move(). + * + * It is possible that concurrent renames can mess up our list + * walk here and result in missing our dentry, resulting in the + * false-negative result. d_lookup() protects against concurrent + * renames using rename_lock seqlock. + * + * See Documentation/vfs/dcache-locking.txt for more details. + */ rcu_read_lock(); hlist_for_each_entry_rcu(dentry, node, head, d_hash) { @@ -1396,8 +1406,8 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name) /* * Recheck the dentry after taking the lock - d_move may have - * changed things. Don't bother checking the hash because we're - * about to compare the whole name anyway. + * changed things. Don't bother checking the hash because + * we're about to compare the whole name anyway. */ if (dentry->d_parent != parent) goto next; @@ -1925,7 +1935,7 @@ static int prepend_path(const struct path *path, struct path *root, bool slash = false; int error = 0; - spin_lock(&vfsmount_lock); + br_read_lock(vfsmount_lock); while (dentry != root->dentry || vfsmnt != root->mnt) { struct dentry * parent; @@ -1954,7 +1964,7 @@ out: if (!error && !slash) error = prepend(buffer, buflen, "/", 1); - spin_unlock(&vfsmount_lock); + br_read_unlock(vfsmount_lock); return error; global_root: @@ -2292,11 +2302,12 @@ int path_is_under(struct path *path1, struct path *path2) struct vfsmount *mnt = path1->mnt; struct dentry *dentry = path1->dentry; int res; - spin_lock(&vfsmount_lock); + + br_read_lock(vfsmount_lock); if (mnt != path2->mnt) { for (;;) { if (mnt->mnt_parent == mnt) { - spin_unlock(&vfsmount_lock); + br_read_unlock(vfsmount_lock); return 0; } if (mnt->mnt_parent == path2->mnt) @@ -2306,7 +2317,7 @@ int path_is_under(struct path *path1, struct path *path2) dentry = mnt->mnt_mountpoint; } res = is_subdir(dentry, path2->dentry); - spin_unlock(&vfsmount_lock); + br_read_unlock(vfsmount_lock); return res; } EXPORT_SYMBOL(path_is_under); diff --git a/fs/exec.c b/fs/exec.c index 05c7d6b84df7..2d9455282744 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1118,7 +1118,7 @@ int check_unsafe_exec(struct linux_binprm *bprm) bprm->unsafe = tracehook_unsafe_exec(p); n_fs = 1; - write_lock(&p->fs->lock); + spin_lock(&p->fs->lock); rcu_read_lock(); for (t = next_thread(p); t != p; t = next_thread(t)) { if (t->fs == p->fs) @@ -1135,7 +1135,7 @@ int check_unsafe_exec(struct linux_binprm *bprm) res = 1; } } - write_unlock(&p->fs->lock); + spin_unlock(&p->fs->lock); return res; } diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 1fa23f6ffba5..1736f2356388 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -250,7 +250,9 @@ int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs) { int i, err = 0; - ll_rw_block(SWRITE, nr_bhs, bhs); + for (i = 0; i < nr_bhs; i++) + write_dirty_buffer(bhs[i], WRITE); + for (i = 0; i < nr_bhs; i++) { wait_on_buffer(bhs[i]); if (buffer_eopnotsupp(bhs[i])) { diff --git a/fs/file_table.c b/fs/file_table.c index edecd36fed9b..a04bdd81c11c 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -20,7 +20,9 @@ #include <linux/cdev.h> #include <linux/fsnotify.h> #include <linux/sysctl.h> +#include <linux/lglock.h> #include <linux/percpu_counter.h> +#include <linux/percpu.h> #include <linux/ima.h> #include <asm/atomic.h> @@ -32,8 +34,8 @@ struct files_stat_struct files_stat = { .max_files = NR_FILE }; -/* public. Not pretty! */ -__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock); +DECLARE_LGLOCK(files_lglock); +DEFINE_LGLOCK(files_lglock); /* SLAB cache for file structures */ static struct kmem_cache *filp_cachep __read_mostly; @@ -249,7 +251,7 @@ static void __fput(struct file *file) cdev_put(inode->i_cdev); fops_put(file->f_op); put_pid(file->f_owner.pid); - file_kill(file); + file_sb_list_del(file); if (file->f_mode & FMODE_WRITE) drop_file_write_access(file); file->f_path.dentry = NULL; @@ -328,41 +330,107 @@ struct file *fget_light(unsigned int fd, int *fput_needed) return file; } - void put_filp(struct file *file) { if (atomic_long_dec_and_test(&file->f_count)) { security_file_free(file); - file_kill(file); + file_sb_list_del(file); file_free(file); } } -void file_move(struct file *file, struct list_head *list) +static inline int file_list_cpu(struct file *file) { - if (!list) - return; - file_list_lock(); - list_move(&file->f_u.fu_list, list); - file_list_unlock(); +#ifdef CONFIG_SMP + return file->f_sb_list_cpu; +#else + return smp_processor_id(); +#endif +} + +/* helper for file_sb_list_add to reduce ifdefs */ +static inline void __file_sb_list_add(struct file *file, struct super_block *sb) +{ + struct list_head *list; +#ifdef CONFIG_SMP + int cpu; + cpu = smp_processor_id(); + file->f_sb_list_cpu = cpu; + list = per_cpu_ptr(sb->s_files, cpu); +#else + list = &sb->s_files; +#endif + list_add(&file->f_u.fu_list, list); } -void file_kill(struct file *file) +/** + * file_sb_list_add - add a file to the sb's file list + * @file: file to add + * @sb: sb to add it to + * + * Use this function to associate a file with the superblock of the inode it + * refers to. + */ +void file_sb_list_add(struct file *file, struct super_block *sb) +{ + lg_local_lock(files_lglock); + __file_sb_list_add(file, sb); + lg_local_unlock(files_lglock); +} + +/** + * file_sb_list_del - remove a file from the sb's file list + * @file: file to remove + * @sb: sb to remove it from + * + * Use this function to remove a file from its superblock. + */ +void file_sb_list_del(struct file *file) { if (!list_empty(&file->f_u.fu_list)) { - file_list_lock(); + lg_local_lock_cpu(files_lglock, file_list_cpu(file)); list_del_init(&file->f_u.fu_list); - file_list_unlock(); + lg_local_unlock_cpu(files_lglock, file_list_cpu(file)); } } +#ifdef CONFIG_SMP + +/* + * These macros iterate all files on all CPUs for a given superblock. + * files_lglock must be held globally. + */ +#define do_file_list_for_each_entry(__sb, __file) \ +{ \ + int i; \ + for_each_possible_cpu(i) { \ + struct list_head *list; \ + list = per_cpu_ptr((__sb)->s_files, i); \ + list_for_each_entry((__file), list, f_u.fu_list) + +#define while_file_list_for_each_entry \ + } \ +} + +#else + +#define do_file_list_for_each_entry(__sb, __file) \ +{ \ + struct list_head *list; \ + list = &(sb)->s_files; \ + list_for_each_entry((__file), list, f_u.fu_list) + +#define while_file_list_for_each_entry \ +} + +#endif + |