* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*/
-#include <linux/config.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
+#include <linux/fdtable.h>
#include <linux/init.h>
#include <linux/module.h>
-#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/security.h>
+#include <linux/ima.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
/* public. Not pretty! */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);
+/* SLAB cache for file structures */
+static struct kmem_cache *filp_cachep __read_mostly;
+
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
static inline void file_free_rcu(struct rcu_head *head)
{
- struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
+ struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
+
+ put_cred(f->f_cred);
kmem_cache_free(filp_cachep, f);
}
static inline void file_free(struct file *f)
{
percpu_counter_dec(&nr_files);
+ file_check_state(f);
call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}
/* Find an unused file structure and return a pointer to it.
* Returns NULL, if there are no more free file structures or
* we run out of memory.
+ *
+ * Be very careful using this. You are responsible for
+ * getting write access to any mount that you might assign
+ * to this filp, if it is opened for write. If this is not
+ * done, you will imbalance int the mount's writer count
+ * and a warning at __fput() time.
*/
struct file *get_empty_filp(void)
{
- struct task_struct *tsk;
+ const struct cred *cred = current_cred();
static int old_max;
struct file * f;
* percpu_counters are inaccurate. Do an expensive check before
* we go and fail.
*/
- if (percpu_counter_sum(&nr_files) >= files_stat.max_files)
+ if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
goto over;
}
- f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
+ f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
if (f == NULL)
goto fail;
percpu_counter_inc(&nr_files);
- memset(f, 0, sizeof(*f));
if (security_file_alloc(f))
goto fail_sec;
- tsk = current;
INIT_LIST_HEAD(&f->f_u.fu_list);
- atomic_set(&f->f_count, 1);
+ atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
- f->f_uid = tsk->fsuid;
- f->f_gid = tsk->fsgid;
+ f->f_cred = get_cred(cred);
+ spin_lock_init(&f->f_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
EXPORT_SYMBOL(get_empty_filp);
-void fastcall fput(struct file *file)
+/**
+ * alloc_file - allocate and initialize a 'struct file'
+ * @mnt: the vfsmount on which the file will reside
+ * @dentry: the dentry representing the new file
+ * @mode: the mode with which the new file will be opened
+ * @fop: the 'struct file_operations' for the new file
+ *
+ * Use this instead of get_empty_filp() to get a new
+ * 'struct file'. Do so because of the same initialization
+ * pitfalls reasons listed for init_file(). This is a
+ * preferred interface to using init_file().
+ *
+ * If all the callers of init_file() are eliminated, its
+ * code should be moved into this function.
+ */
+struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
+ fmode_t mode, const struct file_operations *fop)
+{
+ struct file *file;
+
+ file = get_empty_filp();
+ if (!file)
+ return NULL;
+
+ init_file(file, mnt, dentry, mode, fop);
+ return file;
+}
+EXPORT_SYMBOL(alloc_file);
+
+/**
+ * init_file - initialize a 'struct file'
+ * @file: the already allocated 'struct file' to initialized
+ * @mnt: the vfsmount on which the file resides
+ * @dentry: the dentry representing this file
+ * @mode: the mode the file is opened with
+ * @fop: the 'struct file_operations' for this file
+ *
+ * Use this instead of setting the members directly. Doing so
+ * avoids making mistakes like forgetting the mntget() or
+ * forgetting to take a write on the mnt.
+ *
+ * Note: This is a crappy interface. It is here to make
+ * merging with the existing users of get_empty_filp()
+ * who have complex failure logic easier. All users
+ * of this should be moving to alloc_file().
+ */
+int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
+ fmode_t mode, const struct file_operations *fop)
+{
+ int error = 0;
+ file->f_path.dentry = dentry;
+ file->f_path.mnt = mntget(mnt);
+ file->f_mapping = dentry->d_inode->i_mapping;
+ file->f_mode = mode;
+ file->f_op = fop;
+
+ /*
+ * These mounts don't really matter in practice
+ * for r/o bind mounts. They aren't userspace-
+ * visible. We do this for consistency, and so
+ * that we can do debugging checks at __fput()
+ */
+ if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+ file_take_write(file);
+ error = mnt_clone_write(mnt);
+ WARN_ON(error);
+ }
+ return error;
+}
+EXPORT_SYMBOL(init_file);
+
+void fput(struct file *file)
{
- if (atomic_dec_and_test(&file->f_count))
+ if (atomic_long_dec_and_test(&file->f_count))
__fput(file);
}
EXPORT_SYMBOL(fput);
+/**
+ * drop_file_write_access - give up ability to write to a file
+ * @file: the file to which we will stop writing
+ *
+ * This is a central place which will give up the ability
+ * to write to @file, along with access to write through
+ * its vfsmount.
+ */
+void drop_file_write_access(struct file *file)
+{
+ struct vfsmount *mnt = file->f_path.mnt;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
+
+ put_write_access(inode);
+
+ if (special_file(inode->i_mode))
+ return;
+ if (file_check_writeable(file) != 0)
+ return;
+ mnt_drop_write(mnt);
+ file_release_write(file);
+}
+EXPORT_SYMBOL_GPL(drop_file_write_access);
+
/* __fput is called from task context when aio completion releases the last
* last use of a struct file *. Do not use otherwise.
*/
-void fastcall __fput(struct file *file)
+void __fput(struct file *file)
{
- struct dentry *dentry = file->f_dentry;
- struct vfsmount *mnt = file->f_vfsmnt;
+ struct dentry *dentry = file->f_path.dentry;
+ struct vfsmount *mnt = file->f_path.mnt;
struct inode *inode = dentry->d_inode;
might_sleep();
eventpoll_release(file);
locks_remove_flock(file);
+ if (unlikely(file->f_flags & FASYNC)) {
+ if (file->f_op && file->f_op->fasync)
+ file->f_op->fasync(-1, file, 0);
+ }
if (file->f_op && file->f_op->release)
file->f_op->release(inode, file);
security_file_free(file);
- if (unlikely(inode->i_cdev != NULL))
+ ima_file_free(file);
+ if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL))
cdev_put(inode->i_cdev);
fops_put(file->f_op);
- if (file->f_mode & FMODE_WRITE)
- put_write_access(inode);
+ put_pid(file->f_owner.pid);
file_kill(file);
- file->f_dentry = NULL;
- file->f_vfsmnt = NULL;
+ if (file->f_mode & FMODE_WRITE)
+ drop_file_write_access(file);
+ file->f_path.dentry = NULL;
+ file->f_path.mnt = NULL;
file_free(file);
dput(dentry);
mntput(mnt);
}
-struct file fastcall *fget(unsigned int fd)
+struct file *fget(unsigned int fd)
{
struct file *file;
struct files_struct *files = current->files;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- if (!atomic_inc_not_zero(&file->f_count)) {
+ if (!atomic_long_inc_not_zero(&file->f_count)) {
/* File object ref couldn't be taken */
rcu_read_unlock();
return NULL;
* and a flag is returned to be passed to the corresponding fput_light().
* There must not be a cloning between an fget_light/fput_light pair.
*/
-struct file fastcall *fget_light(unsigned int fd, int *fput_needed)
+struct file *fget_light(unsigned int fd, int *fput_needed)
{
struct file *file;
struct files_struct *files = current->files;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- if (atomic_inc_not_zero(&file->f_count))
+ if (atomic_long_inc_not_zero(&file->f_count))
*fput_needed = 1;
else
/* Didn't get the reference, someone's freed */
void put_filp(struct file *file)
{
- if (atomic_dec_and_test(&file->f_count)) {
+ if (atomic_long_dec_and_test(&file->f_count)) {
security_file_free(file);
file_kill(file);
file_free(file);
int fs_may_remount_ro(struct super_block *sb)
{
- struct list_head *p;
+ struct file *file;
/* Check that no files are currently opened for writing. */
file_list_lock();
- list_for_each(p, &sb->s_files) {
- struct file *file = list_entry(p, struct file, f_u.fu_list);
- struct inode *inode = file->f_dentry->d_inode;
+ list_for_each_entry(file, &sb->s_files, f_u.fu_list) {
+ struct inode *inode = file->f_path.dentry->d_inode;
/* File with pending delete? */
if (inode->i_nlink == 0)
return 0;
}
+/**
+ * mark_files_ro - mark all files read-only
+ * @sb: superblock in question
+ *
+ * All files are marked read-only. We don't care about pending
+ * delete files so this should be used in 'force' mode only.
+ */
+void mark_files_ro(struct super_block *sb)
+{
+ struct file *f;
+
+retry:
+ file_list_lock();
+ list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
+ struct vfsmount *mnt;
+ if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
+ continue;
+ if (!file_count(f))
+ continue;
+ if (!(f->f_mode & FMODE_WRITE))
+ continue;
+ f->f_mode &= ~FMODE_WRITE;
+ if (file_check_writeable(f) != 0)
+ continue;
+ file_release_write(f);
+ mnt = mntget(f->f_path.mnt);
+ file_list_unlock();
+ /*
+ * This can sleep, so we can't hold
+ * the file_list_lock() spinlock.
+ */
+ mnt_drop_write(mnt);
+ mntput(mnt);
+ goto retry;
+ }
+ file_list_unlock();
+}
+
void __init files_init(unsigned long mempages)
{
int n;
- /* One file with associated inode and dcache is very roughly 1K.
+
+ filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+
+ /*
+ * One file with associated inode and dcache is very roughly 1K.
* Per default don't use more than 10% of our memory for files.
*/
if (files_stat.max_files < NR_FILE)
files_stat.max_files = NR_FILE;
files_defer_init();
- percpu_counter_init(&nr_files);
+ percpu_counter_init(&nr_files, 0);
}