#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/fs.h>
#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>
+#include <linux/atomic.h>
+
+#include "internal.h"
/* sysctl tunables... */
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;
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);
}
/*
* Return the total number of open files in the system
*/
-static int get_nr_files(void)
+static long get_nr_files(void)
{
return percpu_counter_read_positive(&nr_files);
}
/*
* Return the maximum number of open files in the system
*/
-int get_max_files(void)
+unsigned long get_max_files(void)
{
return files_stat.max_files;
}
* Handle nr_files sysctl
*/
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(ctl_table *table, int write, struct file *filp,
+int proc_nr_files(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
- return proc_dointvec(table, write, filp, buffer, lenp, ppos);
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#else
-int proc_nr_files(ctl_table *table, int write, struct file *filp,
+int proc_nr_files(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
/* 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;
- static int old_max;
+ const struct cred *cred = current_cred();
+ static long old_max;
struct file * f;
/*
goto fail;
percpu_counter_inc(&nr_files);
+ f->f_cred = get_cred(cred);
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;
+ spin_lock_init(&f->f_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
over:
/* Ran out of filps - report that */
if (get_nr_files() > old_max) {
- printk(KERN_INFO "VFS: file-max limit %d reached\n",
- get_max_files());
+ pr_info("VFS: file-max limit %lu reached\n", get_max_files());
old_max = get_nr_files();
}
goto fail;
return NULL;
}
-EXPORT_SYMBOL(get_empty_filp);
-
/**
* alloc_file - allocate and initialize a 'struct file'
* @mnt: the vfsmount on which the file will reside
* 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,
- mode_t mode, const struct file_operations *fop)
+struct file *alloc_file(struct path *path, fmode_t mode,
+ const struct file_operations *fop)
{
struct file *file;
- struct path;
file = get_empty_filp();
if (!file)
return NULL;
- init_file(file, mnt, dentry, mode, fop);
+ file->f_path = *path;
+ file->f_mapping = path->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(path->dentry->d_inode->i_mode)) {
+ file_take_write(file);
+ WARN_ON(mnt_clone_write(path->mnt));
+ }
+ if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+ i_readcount_inc(path->dentry->d_inode);
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.
+ * drop_file_write_access - give up ability to write to a file
+ * @file: the file to which we will stop writing
*
- * 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().
+ * This is a central place which will give up the ability
+ * to write to @file, along with access to write through
+ * its vfsmount.
*/
-int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
- mode_t mode, const struct file_operations *fop)
+void drop_file_write_access(struct file *file)
{
- 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;
- return error;
-}
-EXPORT_SYMBOL(init_file);
+ struct vfsmount *mnt = file->f_path.mnt;
+ struct dentry *dentry = file->f_path.dentry;
+ struct inode *inode = dentry->d_inode;
-void fastcall fput(struct file *file)
-{
- if (atomic_dec_and_test(&file->f_count))
- __fput(file);
-}
+ put_write_access(inode);
-EXPORT_SYMBOL(fput);
+ 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.
+/* the real guts of fput() - releasing the last reference to file
*/
-void fastcall __fput(struct file *file)
+static void __fput(struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
struct vfsmount *mnt = file->f_path.mnt;
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(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL))
+ ima_file_free(file);
+ if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
+ !(file->f_mode & FMODE_PATH))) {
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_sb_list_del(file);
+ if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+ i_readcount_dec(inode);
+ if (file->f_mode & FMODE_WRITE)
+ drop_file_write_access(file);
file->f_path.dentry = NULL;
file->f_path.mnt = NULL;
file_free(file);
mntput(mnt);
}
-struct file fastcall *fget(unsigned int fd)
+void fput(struct file *file)
+{
+ if (atomic_long_dec_and_test(&file->f_count))
+ __fput(file);
+}
+
+EXPORT_SYMBOL(fput);
+
+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)) {
- /* File object ref couldn't be taken */
- rcu_read_unlock();
- return NULL;
- }
+ /* File object ref couldn't be taken */
+ if (file->f_mode & FMODE_PATH ||
+ !atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
}
rcu_read_unlock();
EXPORT_SYMBOL(fget);
+struct file *fget_raw(unsigned int fd)
+{
+ struct file *file;
+ struct files_struct *files = current->files;
+
+ rcu_read_lock();
+ file = fcheck_files(files, fd);
+ if (file) {
+ /* File object ref couldn't be taken */
+ if (!atomic_long_inc_not_zero(&file->f_count))
+ file = NULL;
+ }
+ rcu_read_unlock();
+
+ return file;
+}
+
+EXPORT_SYMBOL(fget_raw);
+
/*
- * Lightweight file lookup - no refcnt increment if fd table isn't shared.
- * You can use this only if it is guranteed that the current task already
- * holds a refcnt to that file. That check has to be done at fget() only
- * 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.
+ * Lightweight file lookup - no refcnt increment if fd table isn't shared.
+ *
+ * You can use this instead of fget if you satisfy all of the following
+ * conditions:
+ * 1) You must call fput_light before exiting the syscall and returning control
+ * to userspace (i.e. you cannot remember the returned struct file * after
+ * returning to userspace).
+ * 2) You must not call filp_close on the returned struct file * in between
+ * calls to fget_light and fput_light.
+ * 3) You must not clone the current task in between the calls to fget_light
+ * and fput_light.
+ *
+ * The fput_needed flag returned by fget_light should be passed to the
+ * corresponding fput_light.
*/
-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;
*fput_needed = 0;
- if (likely((atomic_read(&files->count) == 1))) {
+ if (atomic_read(&files->count) == 1) {
file = fcheck_files(files, fd);
+ if (file && (file->f_mode & FMODE_PATH))
+ file = NULL;
} else {
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
- if (atomic_inc_not_zero(&file->f_count))
+ if (!(file->f_mode & FMODE_PATH) &&
+ atomic_long_inc_not_zero(&file->f_count))
*fput_needed = 1;
else
/* Didn't get the reference, someone's freed */
return file;
}
+struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+{
+ struct file *file;
+ struct files_struct *files = current->files;
+
+ *fput_needed = 0;
+ if (atomic_read(&files->count) == 1) {
+ file = fcheck_files(files, fd);
+ } else {
+ rcu_read_lock();
+ file = fcheck_files(files, fd);
+ if (file) {
+ if (atomic_long_inc_not_zero(&file->f_count))
+ *fput_needed = 1;
+ else
+ /* Didn't get the reference, someone's freed */
+ file = NULL;
+ }
+ rcu_read_unlock();
+ }
+
+ return file;
+}
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_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);
+}
+
+/**
+ * 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);
}
-void file_kill(struct file *file)
+/**
+ * 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
+
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);
+ lg_global_lock(files_lglock);
+ do_file_list_for_each_entry(sb, file) {
struct inode *inode = file->f_path.dentry->d_inode;
/* File with pending delete? */
/* Writeable file? */
if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE))
goto too_bad;
- }
- file_list_unlock();
+ } while_file_list_for_each_entry;
+ lg_global_unlock(files_lglock);
return 1; /* Tis' cool bro. */
too_bad:
- file_list_unlock();
+ lg_global_unlock(files_lglock);
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:
+ lg_global_lock(files_lglock);
+ do_file_list_for_each_entry(sb, f) {
+ 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;
+ spin_lock(&f->f_lock);
+ f->f_mode &= ~FMODE_WRITE;
+ spin_unlock(&f->f_lock);
+ if (file_check_writeable(f) != 0)
+ continue;
+ file_release_write(f);
+ mnt = mntget(f->f_path.mnt);
+ /* This can sleep, so we can't hold the spinlock. */
+ lg_global_unlock(files_lglock);
+ mnt_drop_write(mnt);
+ mntput(mnt);
+ goto retry;
+ } while_file_list_for_each_entry;
+ lg_global_unlock(files_lglock);
+}
+
void __init files_init(unsigned long mempages)
{
- int n;
- /* One file with associated inode and dcache is very roughly 1K.
+ unsigned long n;
+
+ 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.
*/
n = (mempages * (PAGE_SIZE / 1024)) / 10;
- files_stat.max_files = n;
- if (files_stat.max_files < NR_FILE)
- files_stat.max_files = NR_FILE;
+ files_stat.max_files = max_t(unsigned long, n, NR_FILE);
files_defer_init();
+ lg_lock_init(files_lglock);
percpu_counter_init(&nr_files, 0);
}