linux/fs/anon_inodes.c
Nick Piggin b3e19d924b fs: scale mntget/mntput
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>
2011-01-07 17:50:33 +11:00

244 lines
6.4 KiB
C

/*
* fs/anon_inodes.c
*
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
*
* Thanks to Arnd Bergmann for code review and suggestions.
* More changes for Thomas Gleixner suggestions.
*
*/
#include <linux/cred.h>
#include <linux/file.h>
#include <linux/poll.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/magic.h>
#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
static struct vfsmount *anon_inode_mnt __read_mostly;
static struct inode *anon_inode_inode;
static const struct file_operations anon_inode_fops;
static struct dentry *anon_inodefs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_pseudo(fs_type, "anon_inode:", NULL, ANON_INODE_FS_MAGIC);
}
/*
* anon_inodefs_dname() is called from d_path().
*/
static char *anon_inodefs_dname(struct dentry *dentry, char *buffer, int buflen)
{
return dynamic_dname(dentry, buffer, buflen, "anon_inode:%s",
dentry->d_name.name);
}
static struct file_system_type anon_inode_fs_type = {
.name = "anon_inodefs",
.mount = anon_inodefs_mount,
.kill_sb = kill_anon_super,
};
static const struct dentry_operations anon_inodefs_dentry_operations = {
.d_dname = anon_inodefs_dname,
};
/*
* nop .set_page_dirty method so that people can use .page_mkwrite on
* anon inodes.
*/
static int anon_set_page_dirty(struct page *page)
{
return 0;
};
static const struct address_space_operations anon_aops = {
.set_page_dirty = anon_set_page_dirty,
};
/**
* anon_inode_getfd - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
* of the file
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
* All the files created with anon_inode_getfile() will share a single inode,
* hence saving memory and avoiding code duplication for the file/inode/dentry
* setup. Returns the newly created file* or an error pointer.
*/
struct file *anon_inode_getfile(const char *name,
const struct file_operations *fops,
void *priv, int flags)
{
struct qstr this;
struct path path;
struct file *file;
int error;
if (IS_ERR(anon_inode_inode))
return ERR_PTR(-ENODEV);
if (fops->owner && !try_module_get(fops->owner))
return ERR_PTR(-ENOENT);
/*
* Link the inode to a directory entry by creating a unique name
* using the inode sequence number.
*/
error = -ENOMEM;
this.name = name;
this.len = strlen(name);
this.hash = 0;
path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
if (!path.dentry)
goto err_module;
path.mnt = mntget(anon_inode_mnt);
/*
* We know the anon_inode inode count is always greater than zero,
* so ihold() is safe.
*/
ihold(anon_inode_inode);
d_set_d_op(path.dentry, &anon_inodefs_dentry_operations);
d_instantiate(path.dentry, anon_inode_inode);
error = -ENFILE;
file = alloc_file(&path, OPEN_FMODE(flags), fops);
if (!file)
goto err_dput;
file->f_mapping = anon_inode_inode->i_mapping;
file->f_pos = 0;
file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
file->f_version = 0;
file->private_data = priv;
return file;
err_dput:
path_put(&path);
err_module:
module_put(fops->owner);
return ERR_PTR(error);
}
EXPORT_SYMBOL_GPL(anon_inode_getfile);
/**
* anon_inode_getfd - creates a new file instance by hooking it up to an
* anonymous inode, and a dentry that describe the "class"
* of the file
*
* @name: [in] name of the "class" of the new file
* @fops: [in] file operations for the new file
* @priv: [in] private data for the new file (will be file's private_data)
* @flags: [in] flags
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
* All the files created with anon_inode_getfd() will share a single inode,
* hence saving memory and avoiding code duplication for the file/inode/dentry
* setup. Returns new descriptor or an error code.
*/
int anon_inode_getfd(const char *name, const struct file_operations *fops,
void *priv, int flags)
{
int error, fd;
struct file *file;
error = get_unused_fd_flags(flags);
if (error < 0)
return error;
fd = error;
file = anon_inode_getfile(name, fops, priv, flags);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_put_unused_fd;
}
fd_install(fd, file);
return fd;
err_put_unused_fd:
put_unused_fd(fd);
return error;
}
EXPORT_SYMBOL_GPL(anon_inode_getfd);
/*
* A single inode exists for all anon_inode files. Contrary to pipes,
* anon_inode inodes have no associated per-instance data, so we need
* only allocate one of them.
*/
static struct inode *anon_inode_mkinode(void)
{
struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
if (!inode)
return ERR_PTR(-ENOMEM);
inode->i_ino = get_next_ino();
inode->i_fop = &anon_inode_fops;
inode->i_mapping->a_ops = &anon_aops;
/*
* Mark the inode dirty from the very beginning,
* that way it will never be moved to the dirty
* list because mark_inode_dirty() will think
* that it already _is_ on the dirty list.
*/
inode->i_state = I_DIRTY;
inode->i_mode = S_IRUSR | S_IWUSR;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
inode->i_flags |= S_PRIVATE;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
return inode;
}
static int __init anon_inode_init(void)
{
int error;
error = register_filesystem(&anon_inode_fs_type);
if (error)
goto err_exit;
anon_inode_mnt = kern_mount(&anon_inode_fs_type);
if (IS_ERR(anon_inode_mnt)) {
error = PTR_ERR(anon_inode_mnt);
goto err_unregister_filesystem;
}
anon_inode_inode = anon_inode_mkinode();
if (IS_ERR(anon_inode_inode)) {
error = PTR_ERR(anon_inode_inode);
goto err_mntput;
}
return 0;
err_mntput:
mntput_long(anon_inode_mnt);
err_unregister_filesystem:
unregister_filesystem(&anon_inode_fs_type);
err_exit:
panic(KERN_ERR "anon_inode_init() failed (%d)\n", error);
}
fs_initcall(anon_inode_init);