mirror of
https://github.com/torvalds/linux.git
synced 2024-11-14 08:02:07 +00:00
b3e19d924b
The problem that this patch aims to fix is vfsmount refcounting scalability. We need to take a reference on the vfsmount for every successful path lookup, which often go to the same mount point. The fundamental difficulty is that a "simple" reference count can never be made scalable, because any time a reference is dropped, we must check whether that was the last reference. To do that requires communication with all other CPUs that may have taken a reference count. We can make refcounts more scalable in a couple of ways, involving keeping distributed counters, and checking for the global-zero condition less frequently. - check the global sum once every interval (this will delay zero detection for some interval, so it's probably a showstopper for vfsmounts). - keep a local count and only taking the global sum when local reaches 0 (this is difficult for vfsmounts, because we can't hold preempt off for the life of a reference, so a counter would need to be per-thread or tied strongly to a particular CPU which requires more locking). - keep a local difference of increments and decrements, which allows us to sum the total difference and hence find the refcount when summing all CPUs. Then, keep a single integer "long" refcount for slow and long lasting references, and only take the global sum of local counters when the long refcount is 0. This last scheme is what I implemented here. Attached mounts and process root and working directory references are "long" references, and everything else is a short reference. This allows scalable vfsmount references during path walking over mounted subtrees and unattached (lazy umounted) mounts with processes still running in them. This results in one fewer atomic op in the fastpath: mntget is now just a per-CPU inc, rather than an atomic inc; and mntput just requires a spinlock and non-atomic decrement in the common case. However code is otherwise bigger and heavier, so single threaded performance is basically a wash. Signed-off-by: Nick Piggin <npiggin@kernel.dk>
112 lines
2.6 KiB
C
112 lines
2.6 KiB
C
/* fs/ internal definitions
|
|
*
|
|
* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
|
|
#include <linux/lglock.h>
|
|
|
|
struct super_block;
|
|
struct linux_binprm;
|
|
struct path;
|
|
|
|
/*
|
|
* block_dev.c
|
|
*/
|
|
#ifdef CONFIG_BLOCK
|
|
extern struct super_block *blockdev_superblock;
|
|
extern void __init bdev_cache_init(void);
|
|
|
|
static inline int sb_is_blkdev_sb(struct super_block *sb)
|
|
{
|
|
return sb == blockdev_superblock;
|
|
}
|
|
|
|
extern int __sync_blockdev(struct block_device *bdev, int wait);
|
|
|
|
#else
|
|
static inline void bdev_cache_init(void)
|
|
{
|
|
}
|
|
|
|
static inline int sb_is_blkdev_sb(struct super_block *sb)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline int __sync_blockdev(struct block_device *bdev, int wait)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* char_dev.c
|
|
*/
|
|
extern void __init chrdev_init(void);
|
|
|
|
/*
|
|
* exec.c
|
|
*/
|
|
extern int check_unsafe_exec(struct linux_binprm *);
|
|
|
|
/*
|
|
* namespace.c
|
|
*/
|
|
extern int copy_mount_options(const void __user *, unsigned long *);
|
|
extern int copy_mount_string(const void __user *, char **);
|
|
|
|
extern void free_vfsmnt(struct vfsmount *);
|
|
extern struct vfsmount *alloc_vfsmnt(const char *);
|
|
extern unsigned int mnt_get_count(struct vfsmount *mnt);
|
|
extern struct vfsmount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
|
|
extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
|
|
struct vfsmount *);
|
|
extern void release_mounts(struct list_head *);
|
|
extern void umount_tree(struct vfsmount *, int, struct list_head *);
|
|
extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
|
|
|
|
extern void __init mnt_init(void);
|
|
|
|
DECLARE_BRLOCK(vfsmount_lock);
|
|
|
|
|
|
/*
|
|
* fs_struct.c
|
|
*/
|
|
extern void chroot_fs_refs(struct path *, struct path *);
|
|
|
|
/*
|
|
* file_table.c
|
|
*/
|
|
extern void file_sb_list_add(struct file *f, struct super_block *sb);
|
|
extern void file_sb_list_del(struct file *f);
|
|
extern void mark_files_ro(struct super_block *);
|
|
extern struct file *get_empty_filp(void);
|
|
|
|
/*
|
|
* super.c
|
|
*/
|
|
extern int do_remount_sb(struct super_block *, int, void *, int);
|
|
extern void __put_super(struct super_block *sb);
|
|
extern void put_super(struct super_block *sb);
|
|
|
|
/*
|
|
* open.c
|
|
*/
|
|
struct nameidata;
|
|
extern struct file *nameidata_to_filp(struct nameidata *);
|
|
extern void release_open_intent(struct nameidata *);
|
|
|
|
/*
|
|
* inode.c
|
|
*/
|
|
extern int get_nr_dirty_inodes(void);
|
|
extern void evict_inodes(struct super_block *);
|
|
extern int invalidate_inodes(struct super_block *);
|