kernel_optimize_test/fs/kernfs/inode.c
Johannes Weiner 91b0abe36a mm + fs: store shadow entries in page cache
Reclaim will be leaving shadow entries in the page cache radix tree upon
evicting the real page.  As those pages are found from the LRU, an
iput() can lead to the inode being freed concurrently.  At this point,
reclaim must no longer install shadow pages because the inode freeing
code needs to ensure the page tree is really empty.

Add an address_space flag, AS_EXITING, that the inode freeing code sets
under the tree lock before doing the final truncate.  Reclaim will check
for this flag before installing shadow pages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-04-03 16:21:01 -07:00

378 lines
8.7 KiB
C

/*
* fs/kernfs/inode.c - kernfs inode implementation
*
* Copyright (c) 2001-3 Patrick Mochel
* Copyright (c) 2007 SUSE Linux Products GmbH
* Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org>
*
* This file is released under the GPLv2.
*/
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include "kernfs-internal.h"
static const struct address_space_operations kernfs_aops = {
.readpage = simple_readpage,
.write_begin = simple_write_begin,
.write_end = simple_write_end,
};
static struct backing_dev_info kernfs_bdi = {
.name = "kernfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
static const struct inode_operations kernfs_iops = {
.permission = kernfs_iop_permission,
.setattr = kernfs_iop_setattr,
.getattr = kernfs_iop_getattr,
.setxattr = kernfs_iop_setxattr,
.removexattr = kernfs_iop_removexattr,
.getxattr = kernfs_iop_getxattr,
.listxattr = kernfs_iop_listxattr,
};
void __init kernfs_inode_init(void)
{
if (bdi_init(&kernfs_bdi))
panic("failed to init kernfs_bdi");
}
static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)
{
struct iattr *iattrs;
if (kn->iattr)
return kn->iattr;
kn->iattr = kzalloc(sizeof(struct kernfs_iattrs), GFP_KERNEL);
if (!kn->iattr)
return NULL;
iattrs = &kn->iattr->ia_iattr;
/* assign default attributes */
iattrs->ia_mode = kn->mode;
iattrs->ia_uid = GLOBAL_ROOT_UID;
iattrs->ia_gid = GLOBAL_ROOT_GID;
iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME;
simple_xattrs_init(&kn->iattr->xattrs);
return kn->iattr;
}
static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
{
struct kernfs_iattrs *attrs;
struct iattr *iattrs;
unsigned int ia_valid = iattr->ia_valid;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
iattrs = &attrs->ia_iattr;
if (ia_valid & ATTR_UID)
iattrs->ia_uid = iattr->ia_uid;
if (ia_valid & ATTR_GID)
iattrs->ia_gid = iattr->ia_gid;
if (ia_valid & ATTR_ATIME)
iattrs->ia_atime = iattr->ia_atime;
if (ia_valid & ATTR_MTIME)
iattrs->ia_mtime = iattr->ia_mtime;
if (ia_valid & ATTR_CTIME)
iattrs->ia_ctime = iattr->ia_ctime;
if (ia_valid & ATTR_MODE) {
umode_t mode = iattr->ia_mode;
iattrs->ia_mode = kn->mode = mode;
}
return 0;
}
/**
* kernfs_setattr - set iattr on a node
* @kn: target node
* @iattr: iattr to set
*
* Returns 0 on success, -errno on failure.
*/
int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
{
int ret;
mutex_lock(&kernfs_mutex);
ret = __kernfs_setattr(kn, iattr);
mutex_unlock(&kernfs_mutex);
return ret;
}
int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
struct kernfs_node *kn = dentry->d_fsdata;
int error;
if (!kn)
return -EINVAL;
mutex_lock(&kernfs_mutex);
error = inode_change_ok(inode, iattr);
if (error)
goto out;
error = __kernfs_setattr(kn, iattr);
if (error)
goto out;
/* this ignores size changes */
setattr_copy(inode, iattr);
out:
mutex_unlock(&kernfs_mutex);
return error;
}
static int kernfs_node_setsecdata(struct kernfs_node *kn, void **secdata,
u32 *secdata_len)
{
struct kernfs_iattrs *attrs;
void *old_secdata;
size_t old_secdata_len;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
old_secdata = attrs->ia_secdata;
old_secdata_len = attrs->ia_secdata_len;
attrs->ia_secdata = *secdata;
attrs->ia_secdata_len = *secdata_len;
*secdata = old_secdata;
*secdata_len = old_secdata_len;
return 0;
}
int kernfs_iop_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct kernfs_node *kn = dentry->d_fsdata;
struct kernfs_iattrs *attrs;
void *secdata;
int error;
u32 secdata_len = 0;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
error = security_inode_setsecurity(dentry->d_inode, suffix,
value, size, flags);
if (error)
return error;
error = security_inode_getsecctx(dentry->d_inode,
&secdata, &secdata_len);
if (error)
return error;
mutex_lock(&kernfs_mutex);
error = kernfs_node_setsecdata(kn, &secdata, &secdata_len);
mutex_unlock(&kernfs_mutex);
if (secdata)
security_release_secctx(secdata, secdata_len);
return error;
} else if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
return simple_xattr_set(&attrs->xattrs, name, value, size,
flags);
}
return -EINVAL;
}
int kernfs_iop_removexattr(struct dentry *dentry, const char *name)
{
struct kernfs_node *kn = dentry->d_fsdata;
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
return simple_xattr_remove(&attrs->xattrs, name);
}
ssize_t kernfs_iop_getxattr(struct dentry *dentry, const char *name, void *buf,
size_t size)
{
struct kernfs_node *kn = dentry->d_fsdata;
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
return simple_xattr_get(&attrs->xattrs, name, buf, size);
}
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
{
struct kernfs_node *kn = dentry->d_fsdata;
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
if (!attrs)
return -ENOMEM;
return simple_xattr_list(&attrs->xattrs, buf, size);
}
static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
{
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
}
static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
{
inode->i_uid = iattr->ia_uid;
inode->i_gid = iattr->ia_gid;
inode->i_atime = iattr->ia_atime;
inode->i_mtime = iattr->ia_mtime;
inode->i_ctime = iattr->ia_ctime;
}
static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
{
struct kernfs_iattrs *attrs = kn->iattr;
inode->i_mode = kn->mode;
if (attrs) {
/*
* kernfs_node has non-default attributes get them from
* persistent copy in kernfs_node.
*/
set_inode_attr(inode, &attrs->ia_iattr);
security_inode_notifysecctx(inode, attrs->ia_secdata,
attrs->ia_secdata_len);
}
if (kernfs_type(kn) == KERNFS_DIR)
set_nlink(inode, kn->dir.subdirs + 2);
}
int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
struct kstat *stat)
{
struct kernfs_node *kn = dentry->d_fsdata;
struct inode *inode = dentry->d_inode;
mutex_lock(&kernfs_mutex);
kernfs_refresh_inode(kn, inode);
mutex_unlock(&kernfs_mutex);
generic_fillattr(inode, stat);
return 0;
}
static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
{
kernfs_get(kn);
inode->i_private = kn;
inode->i_mapping->a_ops = &kernfs_aops;
inode->i_mapping->backing_dev_info = &kernfs_bdi;
inode->i_op = &kernfs_iops;
set_default_inode_attr(inode, kn->mode);
kernfs_refresh_inode(kn, inode);
/* initialize inode according to type */
switch (kernfs_type(kn)) {
case KERNFS_DIR:
inode->i_op = &kernfs_dir_iops;
inode->i_fop = &kernfs_dir_fops;
break;
case KERNFS_FILE:
inode->i_size = kn->attr.size;
inode->i_fop = &kernfs_file_fops;
break;
case KERNFS_LINK:
inode->i_op = &kernfs_symlink_iops;
break;
default:
BUG();
}
unlock_new_inode(inode);
}
/**
* kernfs_get_inode - get inode for kernfs_node
* @sb: super block
* @kn: kernfs_node to allocate inode for
*
* Get inode for @kn. If such inode doesn't exist, a new inode is
* allocated and basics are initialized. New inode is returned
* locked.
*
* LOCKING:
* Kernel thread context (may sleep).
*
* RETURNS:
* Pointer to allocated inode on success, NULL on failure.
*/
struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
{
struct inode *inode;
inode = iget_locked(sb, kn->ino);
if (inode && (inode->i_state & I_NEW))
kernfs_init_inode(kn, inode);
return inode;
}
/*
* The kernfs_node serves as both an inode and a directory entry for
* kernfs. To prevent the kernfs inode numbers from being freed
* prematurely we take a reference to kernfs_node from the kernfs inode. A
* super_operations.evict_inode() implementation is needed to drop that
* reference upon inode destruction.
*/
void kernfs_evict_inode(struct inode *inode)
{
struct kernfs_node *kn = inode->i_private;
truncate_inode_pages_final(&inode->i_data);
clear_inode(inode);
kernfs_put(kn);
}
int kernfs_iop_permission(struct inode *inode, int mask)
{
struct kernfs_node *kn;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
kn = inode->i_private;
mutex_lock(&kernfs_mutex);
kernfs_refresh_inode(kn, inode);
mutex_unlock(&kernfs_mutex);
return generic_permission(inode, mask);
}