mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-23 04:34:11 +08:00
e9c15badbb
The kernel uses internal mounts created by kern_mount() and populated with files with no lookup path by alloc_file_pseudo() for a variety of reasons. An example of such a mount is for anonymous pipes. For pipes, every vfs_write() regardless of filesystem, calls fsnotify_modify() to notify of any changes which incurs a small amount of overhead in fsnotify even when there are no watchers. It can also trigger for reads and readv and writev, it was simply vfs_write() that was noticed first. A patch is pending that reduces, but does not eliminate, the overhead of fsnotify but for files that cannot be looked up via a path, even that small overhead is unnecessary. The user API for all notification subsystems (inotify, fanotify, ...) is based on the pathname and a dirfd and proc entries appear to be the only visible representation of the files. Proc does not have the same pathname as the internal entry and the proc inode is not the same as the internal inode so even if fanotify is used on a file under /proc/XX/fd, no useful events are notified. This patch changes alloc_file_pseudo() to always opt out of fsnotify by setting FMODE_NONOTIFY flag so that no check is made for fsnotify watchers on pseudo files. This should be safe as the underlying helper for the dentry is d_alloc_pseudo() which explicitly states that no lookups are ever performed meaning that fanotify should have nothing useful to attach to. The test motivating this was "perf bench sched messaging --pipe". On a single-socket machine using threads the difference of the patch was as follows. 5.7.0 5.7.0 vanilla nofsnotify-v1r1 Amean 1 1.3837 ( 0.00%) 1.3547 ( 2.10%) Amean 3 3.7360 ( 0.00%) 3.6543 ( 2.19%) Amean 5 5.8130 ( 0.00%) 5.7233 * 1.54%* Amean 7 8.1490 ( 0.00%) 7.9730 * 2.16%* Amean 12 14.6843 ( 0.00%) 14.1820 ( 3.42%) Amean 18 21.8840 ( 0.00%) 21.7460 ( 0.63%) Amean 24 28.8697 ( 0.00%) 29.1680 ( -1.03%) Amean 30 36.0787 ( 0.00%) 35.2640 * 2.26%* Amean 32 38.0527 ( 0.00%) 38.1223 ( -0.18%) The difference is small but in some cases it's outside the noise so while marginal, there is still some small benefit to ignoring fsnotify for files allocated via alloc_file_pseudo() in some cases. Link: https://lore.kernel.org/r/20200615121358.GF3183@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Reviewed-by: Amir Goldstein <amir73il@gmail.com> Signed-off-by: Jan Kara <jack@suse.cz>
402 lines
10 KiB
C
402 lines
10 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* 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/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)
|
|
{
|
|
security_file_free(f);
|
|
if (!(f->f_mode & FMODE_NOACCOUNT))
|
|
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 *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 *buffer, size_t *lenp, loff_t *ppos)
|
|
{
|
|
return -ENOSYS;
|
|
}
|
|
#endif
|
|
|
|
static struct file *__alloc_file(int flags, const struct cred *cred)
|
|
{
|
|
struct file *f;
|
|
int error;
|
|
|
|
f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
|
|
if (unlikely(!f))
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
f->f_cred = get_cred(cred);
|
|
error = security_file_alloc(f);
|
|
if (unlikely(error)) {
|
|
file_free_rcu(&f->f_u.fu_rcuhead);
|
|
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_flags = flags;
|
|
f->f_mode = OPEN_FMODE(flags);
|
|
/* f->f_version: 0 */
|
|
|
|
return f;
|
|
}
|
|
|
|
/* 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 *alloc_empty_file(int flags, const struct cred *cred)
|
|
{
|
|
static long old_max;
|
|
struct file *f;
|
|
|
|
/*
|
|
* 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 = __alloc_file(flags, cred);
|
|
if (!IS_ERR(f))
|
|
percpu_counter_inc(&nr_files);
|
|
|
|
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);
|
|
}
|
|
|
|
/*
|
|
* Variant of alloc_empty_file() that doesn't check and modify nr_files.
|
|
*
|
|
* Should not be used unless there's a very good reason to do so.
|
|
*/
|
|
struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
|
|
{
|
|
struct file *f = __alloc_file(flags, cred);
|
|
|
|
if (!IS_ERR(f))
|
|
f->f_mode |= FMODE_NOACCOUNT;
|
|
|
|
return f;
|
|
}
|
|
|
|
/**
|
|
* alloc_file - allocate and initialize a 'struct file'
|
|
*
|
|
* @path: the (dentry, vfsmount) pair for the new file
|
|
* @flags: O_... flags with which the new file will be opened
|
|
* @fop: the 'struct file_operations' for the new file
|
|
*/
|
|
static struct file *alloc_file(const struct path *path, int flags,
|
|
const struct file_operations *fop)
|
|
{
|
|
struct file *file;
|
|
|
|
file = alloc_empty_file(flags, current_cred());
|
|
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);
|
|
file->f_sb_err = file_sample_sb_err(file);
|
|
if ((file->f_mode & FMODE_READ) &&
|
|
likely(fop->read || fop->read_iter))
|
|
file->f_mode |= FMODE_CAN_READ;
|
|
if ((file->f_mode & FMODE_WRITE) &&
|
|
likely(fop->write || fop->write_iter))
|
|
file->f_mode |= FMODE_CAN_WRITE;
|
|
file->f_mode |= FMODE_OPENED;
|
|
file->f_op = fop;
|
|
if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
|
|
i_readcount_inc(path->dentry->d_inode);
|
|
return file;
|
|
}
|
|
|
|
struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
|
|
const char *name, int flags,
|
|
const struct file_operations *fops)
|
|
{
|
|
static const struct dentry_operations anon_ops = {
|
|
.d_dname = simple_dname
|
|
};
|
|
struct qstr this = QSTR_INIT(name, strlen(name));
|
|
struct path path;
|
|
struct file *file;
|
|
|
|
path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
|
|
if (!path.dentry)
|
|
return ERR_PTR(-ENOMEM);
|
|
if (!mnt->mnt_sb->s_d_op)
|
|
d_set_d_op(path.dentry, &anon_ops);
|
|
path.mnt = mntget(mnt);
|
|
d_instantiate(path.dentry, inode);
|
|
file = alloc_file(&path, flags | FMODE_NONOTIFY, fops);
|
|
if (IS_ERR(file)) {
|
|
ihold(inode);
|
|
path_put(&path);
|
|
}
|
|
return file;
|
|
}
|
|
EXPORT_SYMBOL(alloc_file_pseudo);
|
|
|
|
struct file *alloc_file_clone(struct file *base, int flags,
|
|
const struct file_operations *fops)
|
|
{
|
|
struct file *f = alloc_file(&base->f_path, flags, fops);
|
|
if (!IS_ERR(f)) {
|
|
path_get(&f->f_path);
|
|
f->f_mapping = base->f_mapping;
|
|
}
|
|
return f;
|
|
}
|
|
|
|
/* 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;
|
|
fmode_t mode = file->f_mode;
|
|
|
|
if (unlikely(!(file->f_mode & FMODE_OPENED)))
|
|
goto out;
|
|
|
|
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);
|
|
|
|
ima_file_free(file);
|
|
if (unlikely(file->f_flags & FASYNC)) {
|
|
if (file->f_op->fasync)
|
|
file->f_op->fasync(-1, file, 0);
|
|
}
|
|
if (file->f_op->release)
|
|
file->f_op->release(inode, file);
|
|
if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
|
|
!(mode & FMODE_PATH))) {
|
|
cdev_put(inode->i_cdev);
|
|
}
|
|
fops_put(file->f_op);
|
|
put_pid(file->f_owner.pid);
|
|
if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
|
|
i_readcount_dec(inode);
|
|
if (mode & FMODE_WRITER) {
|
|
put_write_access(inode);
|
|
__mnt_drop_write(mnt);
|
|
}
|
|
dput(dentry);
|
|
if (unlikely(mode & FMODE_NEED_UNMOUNT))
|
|
dissolve_on_fput(mnt);
|
|
mntput(mnt);
|
|
out:
|
|
file_free(file);
|
|
}
|
|
|
|
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 file *f, *t;
|
|
|
|
llist_for_each_entry_safe(f, t, node, f_u.fu_llist)
|
|
__fput(f);
|
|
}
|
|
|
|
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);
|
|
}
|
|
EXPORT_SYMBOL_GPL(flush_delayed_fput);
|
|
|
|
static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
|
|
|
|
void fput_many(struct file *file, unsigned int refs)
|
|
{
|
|
if (atomic_long_sub_and_test(refs, &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);
|
|
}
|
|
}
|
|
|
|
void fput(struct file *file)
|
|
{
|
|
fput_many(file, 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 __init files_init(void)
|
|
{
|
|
filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
|
|
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, 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 nr_pages = totalram_pages();
|
|
unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2;
|
|
|
|
memreserve = min(memreserve, nr_pages - 1);
|
|
n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
|
|
|
|
files_stat.max_files = max_t(unsigned long, n, NR_FILE);
|
|
}
|