linux-hardened/fs/file_table.c
Jeff Layton 5660e13d2f fs: new infrastructure for writeback error handling and reporting
Most filesystems currently use mapping_set_error and
filemap_check_errors for setting and reporting/clearing writeback errors
at the mapping level. filemap_check_errors is indirectly called from
most of the filemap_fdatawait_* functions and from
filemap_write_and_wait*. These functions are called from all sorts of
contexts to wait on writeback to finish -- e.g. mostly in fsync, but
also in truncate calls, getattr, etc.

The non-fsync callers are problematic. We should be reporting writeback
errors during fsync, but many places spread over the tree clear out
errors before they can be properly reported, or report errors at
nonsensical times.

If I get -EIO on a stat() call, there is no reason for me to assume that
it is because some previous writeback failed. The fact that it also
clears out the error such that a subsequent fsync returns 0 is a bug,
and a nasty one since that's potentially silent data corruption.

This patch adds a small bit of new infrastructure for setting and
reporting errors during address_space writeback. While the above was my
original impetus for adding this, I think it's also the case that
current fsync semantics are just problematic for userland. Most
applications that call fsync do so to ensure that the data they wrote
has hit the backing store.

In the case where there are multiple writers to the file at the same
time, this is really hard to determine. The first one to call fsync will
see any stored error, and the rest get back 0. The processes with open
fds may not be associated with one another in any way. They could even
be in different containers, so ensuring coordination between all fsync
callers is not really an option.

One way to remedy this would be to track what file descriptor was used
to dirty the file, but that's rather cumbersome and would likely be
slow. However, there is a simpler way to improve the semantics here
without incurring too much overhead.

This set adds an errseq_t to struct address_space, and a corresponding
one is added to struct file. Writeback errors are recorded in the
mapping's errseq_t, and the one in struct file is used as the "since"
value.

This changes the semantics of the Linux fsync implementation such that
applications can now use it to determine whether there were any
writeback errors since fsync(fd) was last called (or since the file was
opened in the case of fsync having never been called).

Note that those writeback errors may have occurred when writing data
that was dirtied via an entirely different fd, but that's the case now
with the current mapping_set_error/filemap_check_error infrastructure.
This will at least prevent you from getting a false report of success.

The new behavior is still consistent with the POSIX spec, and is more
reliable for application developers. This patch just adds some basic
infrastructure for doing this, and ensures that the f_wb_err "cursor"
is properly set when a file is opened. Later patches will change the
existing code to use this new infrastructure for reporting errors at
fsync time.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
2017-07-06 07:02:25 -04:00

334 lines
8.6 KiB
C

/*
* linux/fs/file_table.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*/
#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/security.h>
#include <linux/cred.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/cdev.h>
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/task_work.h>
#include <linux/ima.h>
#include <linux/swap.h>
#include <linux/atomic.h>
#include "internal.h"
/* sysctl tunables... */
struct files_stat_struct files_stat = {
.max_files = NR_FILE
};
/* SLAB cache for file structures */
static struct kmem_cache *filp_cachep __read_mostly;
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
static void file_free_rcu(struct rcu_head *head)
{
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);
call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}
/*
* Return the total number of open files in the system
*/
static long get_nr_files(void)
{
return percpu_counter_read_positive(&nr_files);
}
/*
* Return the maximum number of open files in the system
*/
unsigned long get_max_files(void)
{
return files_stat.max_files;
}
EXPORT_SYMBOL_GPL(get_max_files);
/*
* Handle nr_files sysctl
*/
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
}
#else
int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
#endif
/* Find an unused file structure and return a pointer to it.
* Returns an error pointer if some error happend e.g. we over file
* structures limit, run out of memory or operation is not permitted.
*
* 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)
{
const struct cred *cred = current_cred();
static long old_max;
struct file *f;
int error;
/*
* Privileged users can go above max_files
*/
if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
/*
* percpu_counters are inaccurate. Do an expensive check before
* we go and fail.
*/
if (percpu_counter_sum_positive(&nr_files) >= files_stat.max_files)
goto over;
}
f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
if (unlikely(!f))
return ERR_PTR(-ENOMEM);
percpu_counter_inc(&nr_files);
f->f_cred = get_cred(cred);
error = security_file_alloc(f);
if (unlikely(error)) {
file_free(f);
return ERR_PTR(error);
}
atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
spin_lock_init(&f->f_lock);
mutex_init(&f->f_pos_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
over:
/* Ran out of filps - report that */
if (get_nr_files() > old_max) {
pr_info("VFS: file-max limit %lu reached\n", get_max_files());
old_max = get_nr_files();
}
return ERR_PTR(-ENFILE);
}
/**
* alloc_file - allocate and initialize a 'struct file'
*
* @path: the (dentry, vfsmount) pair for the new file
* @mode: the mode with which the new file will be opened
* @fop: the 'struct file_operations' for the new file
*/
struct file *alloc_file(const struct path *path, fmode_t mode,
const struct file_operations *fop)
{
struct file *file;
file = get_empty_filp();
if (IS_ERR(file))
return file;
file->f_path = *path;
file->f_inode = path->dentry->d_inode;
file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
if ((mode & FMODE_READ) &&
likely(fop->read || fop->read_iter))
mode |= FMODE_CAN_READ;
if ((mode & FMODE_WRITE) &&
likely(fop->write || fop->write_iter))
mode |= FMODE_CAN_WRITE;
file->f_mode = mode;
file->f_op = fop;
if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_inc(path->dentry->d_inode);
return file;
}
EXPORT_SYMBOL(alloc_file);
/* the real guts of fput() - releasing the last reference to file
*/
static void __fput(struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
struct vfsmount *mnt = file->f_path.mnt;
struct inode *inode = file->f_inode;
might_sleep();
fsnotify_close(file);
/*
* The function eventpoll_release() should be the first called
* in the file cleanup chain.
*/
eventpoll_release(file);
locks_remove_file(file);
if (unlikely(file->f_flags & FASYNC)) {
if (file->f_op->fasync)
file->f_op->fasync(-1, file, 0);
}
ima_file_free(file);
if (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 &&
!(file->f_mode & FMODE_PATH))) {
cdev_put(inode->i_cdev);
}
fops_put(file->f_op);
put_pid(file->f_owner.pid);
if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
i_readcount_dec(inode);
if (file->f_mode & FMODE_WRITER) {
put_write_access(inode);
__mnt_drop_write(mnt);
}
file->f_path.dentry = NULL;
file->f_path.mnt = NULL;
file->f_inode = NULL;
file_free(file);
dput(dentry);
mntput(mnt);
}
static LLIST_HEAD(delayed_fput_list);
static void delayed_fput(struct work_struct *unused)
{
struct llist_node *node = llist_del_all(&delayed_fput_list);
struct llist_node *next;
for (; node; node = next) {
next = llist_next(node);
__fput(llist_entry(node, struct file, f_u.fu_llist));
}
}
static void ____fput(struct callback_head *work)
{
__fput(container_of(work, struct file, f_u.fu_rcuhead));
}
/*
* If kernel thread really needs to have the final fput() it has done
* to complete, call this. The only user right now is the boot - we
* *do* need to make sure our writes to binaries on initramfs has
* not left us with opened struct file waiting for __fput() - execve()
* won't work without that. Please, don't add more callers without
* very good reasons; in particular, never call that with locks
* held and never call that from a thread that might need to do
* some work on any kind of umount.
*/
void flush_delayed_fput(void)
{
delayed_fput(NULL);
}
static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
void fput(struct file *file)
{
if (atomic_long_dec_and_test(&file->f_count)) {
struct task_struct *task = current;
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
init_task_work(&file->f_u.fu_rcuhead, ____fput);
if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
return;
/*
* After this task has run exit_task_work(),
* task_work_add() will fail. Fall through to delayed
* fput to avoid leaking *file.
*/
}
if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
schedule_delayed_work(&delayed_fput_work, 1);
}
}
/*
* synchronous analog of fput(); for kernel threads that might be needed
* in some umount() (and thus can't use flush_delayed_fput() without
* risking deadlocks), need to wait for completion of __fput() and know
* for this specific struct file it won't involve anything that would
* need them. Use only if you really need it - at the very least,
* don't blindly convert fput() by kernel thread to that.
*/
void __fput_sync(struct file *file)
{
if (atomic_long_dec_and_test(&file->f_count)) {
struct task_struct *task = current;
BUG_ON(!(task->flags & PF_KTHREAD));
__fput(file);
}
}
EXPORT_SYMBOL(fput);
void put_filp(struct file *file)
{
if (atomic_long_dec_and_test(&file->f_count)) {
security_file_free(file);
file_free(file);
}
}
void __init files_init(void)
{
filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
percpu_counter_init(&nr_files, 0, GFP_KERNEL);
}
/*
* One file with associated inode and dcache is very roughly 1K. Per default
* do not use more than 10% of our memory for files.
*/
void __init files_maxfiles_init(void)
{
unsigned long n;
unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
memreserve = min(memreserve, totalram_pages - 1);
n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
files_stat.max_files = max_t(unsigned long, n, NR_FILE);
}