OpenCloudOS-Kernel/fs/ecryptfs/inode.c

1156 lines
32 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/**
* eCryptfs: Linux filesystem encryption layer
*
* Copyright (C) 1997-2004 Erez Zadok
* Copyright (C) 2001-2004 Stony Brook University
* Copyright (C) 2004-2007 International Business Machines Corp.
* Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
* Michael C. Thompsion <mcthomps@us.ibm.com>
*/
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/fs_stack.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/xattr.h>
#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
static struct dentry *lock_parent(struct dentry *dentry)
{
struct dentry *dir;
dir = dget_parent(dentry);
inode_lock_nested(d_inode(dir), I_MUTEX_PARENT);
return dir;
}
static void unlock_dir(struct dentry *dir)
{
inode_unlock(d_inode(dir));
dput(dir);
}
static int ecryptfs_inode_test(struct inode *inode, void *lower_inode)
{
return ecryptfs_inode_to_lower(inode) == lower_inode;
}
static int ecryptfs_inode_set(struct inode *inode, void *opaque)
{
struct inode *lower_inode = opaque;
ecryptfs_set_inode_lower(inode, lower_inode);
fsstack_copy_attr_all(inode, lower_inode);
/* i_size will be overwritten for encrypted regular files */
fsstack_copy_inode_size(inode, lower_inode);
inode->i_ino = lower_inode->i_ino;
inode->i_mapping->a_ops = &ecryptfs_aops;
if (S_ISLNK(inode->i_mode))
inode->i_op = &ecryptfs_symlink_iops;
else if (S_ISDIR(inode->i_mode))
inode->i_op = &ecryptfs_dir_iops;
else
inode->i_op = &ecryptfs_main_iops;
if (S_ISDIR(inode->i_mode))
inode->i_fop = &ecryptfs_dir_fops;
else if (special_file(inode->i_mode))
init_special_inode(inode, inode->i_mode, inode->i_rdev);
else
inode->i_fop = &ecryptfs_main_fops;
return 0;
}
static struct inode *__ecryptfs_get_inode(struct inode *lower_inode,
struct super_block *sb)
{
struct inode *inode;
if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb))
return ERR_PTR(-EXDEV);
if (!igrab(lower_inode))
return ERR_PTR(-ESTALE);
inode = iget5_locked(sb, (unsigned long)lower_inode,
ecryptfs_inode_test, ecryptfs_inode_set,
lower_inode);
if (!inode) {
iput(lower_inode);
return ERR_PTR(-EACCES);
}
if (!(inode->i_state & I_NEW))
iput(lower_inode);
return inode;
}
struct inode *ecryptfs_get_inode(struct inode *lower_inode,
struct super_block *sb)
{
struct inode *inode = __ecryptfs_get_inode(lower_inode, sb);
if (!IS_ERR(inode) && (inode->i_state & I_NEW))
unlock_new_inode(inode);
return inode;
}
/**
* ecryptfs_interpose
* @lower_dentry: Existing dentry in the lower filesystem
* @dentry: ecryptfs' dentry
* @sb: ecryptfs's super_block
*
* Interposes upper and lower dentries.
*
* Returns zero on success; non-zero otherwise
*/
static int ecryptfs_interpose(struct dentry *lower_dentry,
struct dentry *dentry, struct super_block *sb)
{
struct inode *inode = ecryptfs_get_inode(d_inode(lower_dentry), sb);
if (IS_ERR(inode))
return PTR_ERR(inode);
d_instantiate(dentry, inode);
return 0;
}
static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
struct inode *inode)
{
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
struct dentry *lower_dir_dentry;
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
struct inode *lower_dir_inode;
int rc;
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
lower_dir_inode = d_inode(lower_dir_dentry);
inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
dget(lower_dentry); // don't even try to make the lower negative
if (lower_dentry->d_parent != lower_dir_dentry)
rc = -EINVAL;
else if (d_unhashed(lower_dentry))
rc = -EINVAL;
else
rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
if (rc) {
printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
goto out_unlock;
}
fsstack_copy_attr_times(dir, lower_dir_inode);
set_nlink(inode, ecryptfs_inode_to_lower(inode)->i_nlink);
inode->i_ctime = dir->i_ctime;
out_unlock:
dput(lower_dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
inode_unlock(lower_dir_inode);
if (!rc)
d_drop(dentry);
return rc;
}
/**
* ecryptfs_do_create
* @directory_inode: inode of the new file's dentry's parent in ecryptfs
* @ecryptfs_dentry: New file's dentry in ecryptfs
* @mode: The mode of the new file
*
* Creates the underlying file and the eCryptfs inode which will link to
* it. It will also update the eCryptfs directory inode to mimic the
* stat of the lower directory inode.
*
* Returns the new eCryptfs inode on success; an ERR_PTR on error condition
*/
static struct inode *
ecryptfs_do_create(struct inode *directory_inode,
struct dentry *ecryptfs_dentry, umode_t mode)
{
int rc;
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
struct inode *inode;
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
rc = vfs_create(d_inode(lower_dir_dentry), lower_dentry, mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
inode = ERR_PTR(rc);
goto out_lock;
}
inode = __ecryptfs_get_inode(d_inode(lower_dentry),
directory_inode->i_sb);
if (IS_ERR(inode)) {
vfs_unlink(d_inode(lower_dir_dentry), lower_dentry, NULL);
goto out_lock;
}
fsstack_copy_attr_times(directory_inode, d_inode(lower_dir_dentry));
fsstack_copy_inode_size(directory_inode, d_inode(lower_dir_dentry));
out_lock:
unlock_dir(lower_dir_dentry);
return inode;
}
/**
* ecryptfs_initialize_file
*
* Cause the file to be changed from a basic empty file to an ecryptfs
* file with a header and first data page.
*
* Returns zero on success
*/
int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
struct inode *ecryptfs_inode)
{
struct ecryptfs_crypt_stat *crypt_stat =
&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
int rc = 0;
if (S_ISDIR(ecryptfs_inode->i_mode)) {
ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
goto out;
}
ecryptfs_printk(KERN_DEBUG, "Initializing crypto context\n");
rc = ecryptfs_new_file_context(ecryptfs_inode);
if (rc) {
ecryptfs_printk(KERN_ERR, "Error creating new file "
"context; rc = [%d]\n", rc);
goto out;
}
rc = ecryptfs_get_lower_file(ecryptfs_dentry, ecryptfs_inode);
if (rc) {
printk(KERN_ERR "%s: Error attempting to initialize "
"the lower file for the dentry with name "
"[%pd]; rc = [%d]\n", __func__,
ecryptfs_dentry, rc);
goto out;
}
rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
if (rc)
printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
ecryptfs_put_lower_file(ecryptfs_inode);
out:
return rc;
}
/**
* ecryptfs_create
* @dir: The inode of the directory in which to create the file.
* @dentry: The eCryptfs dentry
* @mode: The mode of the new file.
*
* Creates a new file.
*
* Returns zero on success; non-zero on error condition
*/
static int
ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
umode_t mode, bool excl)
{
struct inode *ecryptfs_inode;
int rc;
ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry,
mode);
if (IS_ERR(ecryptfs_inode)) {
ecryptfs_printk(KERN_WARNING, "Failed to create file in"
"lower filesystem\n");
rc = PTR_ERR(ecryptfs_inode);
goto out;
}
/* At this point, a file exists on "disk"; we need to make sure
* that this on disk file is prepared to be an ecryptfs file */
rc = ecryptfs_initialize_file(ecryptfs_dentry, ecryptfs_inode);
if (rc) {
ecryptfs_do_unlink(directory_inode, ecryptfs_dentry,
ecryptfs_inode);
iget_failed(ecryptfs_inode);
goto out;
}
d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
out:
return rc;
}
static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
{
struct ecryptfs_crypt_stat *crypt_stat;
int rc;
rc = ecryptfs_get_lower_file(dentry, inode);
if (rc) {
printk(KERN_ERR "%s: Error attempting to initialize "
"the lower file for the dentry with name "
"[%pd]; rc = [%d]\n", __func__,
dentry, rc);
return rc;
}
crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
/* TODO: lock for crypt_stat comparison */
if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
ecryptfs_set_default_sizes(crypt_stat);
rc = ecryptfs_read_and_validate_header_region(inode);
ecryptfs_put_lower_file(inode);
if (rc) {
rc = ecryptfs_read_and_validate_xattr_region(dentry, inode);
if (!rc)
crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
}
/* Must return 0 to allow non-eCryptfs files to be looked up, too */
return 0;
}
/**
* ecryptfs_lookup_interpose - Dentry interposition for a lookup
*/
static struct dentry *ecryptfs_lookup_interpose(struct dentry *dentry,
struct dentry *lower_dentry)
{
struct path *path = ecryptfs_dentry_to_lower_path(dentry->d_parent);
struct inode *inode, *lower_inode;
struct ecryptfs_dentry_info *dentry_info;
int rc = 0;
dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
if (!dentry_info) {
dput(lower_dentry);
return ERR_PTR(-ENOMEM);
}
fsstack_copy_attr_atime(d_inode(dentry->d_parent),
d_inode(path->dentry));
BUG_ON(!d_count(lower_dentry));
ecryptfs_set_dentry_private(dentry, dentry_info);
dentry_info->lower_path.mnt = mntget(path->mnt);
dentry_info->lower_path.dentry = lower_dentry;
/*
* negative dentry can go positive under us here - its parent is not
* locked. That's OK and that could happen just as we return from
* ecryptfs_lookup() anyway. Just need to be careful and fetch
* ->d_inode only once - it's not stable here.
*/
lower_inode = READ_ONCE(lower_dentry->d_inode);
if (!lower_inode) {
/* We want to add because we couldn't find in lower */
d_add(dentry, NULL);
return NULL;
}
inode = __ecryptfs_get_inode(lower_inode, dentry->d_sb);
if (IS_ERR(inode)) {
printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n",
__func__, PTR_ERR(inode));
return ERR_CAST(inode);
}
if (S_ISREG(inode->i_mode)) {
rc = ecryptfs_i_size_read(dentry, inode);
if (rc) {
make_bad_inode(inode);
return ERR_PTR(rc);
}
}
if (inode->i_state & I_NEW)
unlock_new_inode(inode);
return d_splice_alias(inode, dentry);
}
/**
* ecryptfs_lookup
* @ecryptfs_dir_inode: The eCryptfs directory inode
* @ecryptfs_dentry: The eCryptfs dentry that we are looking up
* @flags: lookup flags
*
* Find a file on disk. If the file does not exist, then we'll add it to the
* dentry cache and continue on to read it from the disk.
*/
static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
struct dentry *ecryptfs_dentry,
unsigned int flags)
{
char *encrypted_and_encoded_name = NULL;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *lower_dir_dentry, *lower_dentry;
const char *name = ecryptfs_dentry->d_name.name;
size_t len = ecryptfs_dentry->d_name.len;
struct dentry *res;
int rc = 0;
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
rc = ecryptfs_encrypt_and_encode_filename(
&encrypted_and_encoded_name, &len,
mount_crypt_stat, name, len);
if (rc) {
printk(KERN_ERR "%s: Error attempting to encrypt and encode "
"filename; rc = [%d]\n", __func__, rc);
return ERR_PTR(rc);
}
name = encrypted_and_encoded_name;
}
lower_dentry = lookup_one_len_unlocked(name, lower_dir_dentry, len);
if (IS_ERR(lower_dentry)) {
ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
"[%ld] on lower_dentry = [%s]\n", __func__,
PTR_ERR(lower_dentry),
name);
res = ERR_CAST(lower_dentry);
} else {
res = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry);
}
kfree(encrypted_and_encoded_name);
return res;
}
static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry)
{
struct dentry *lower_old_dentry;
struct dentry *lower_new_dentry;
struct dentry *lower_dir_dentry;
u64 file_size_save;
int rc;
file_size_save = i_size_read(d_inode(old_dentry));
lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
dget(lower_old_dentry);
dget(lower_new_dentry);
lower_dir_dentry = lock_parent(lower_new_dentry);
rc = vfs_link(lower_old_dentry, d_inode(lower_dir_dentry),
lower_new_dentry, NULL);
if (rc || d_really_is_negative(lower_new_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
if (rc)
goto out_lock;
fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
set_nlink(d_inode(old_dentry),
ecryptfs_inode_to_lower(d_inode(old_dentry))->i_nlink);
i_size_write(d_inode(new_dentry), file_size_save);
out_lock:
unlock_dir(lower_dir_dentry);
dput(lower_new_dentry);
dput(lower_old_dentry);
return rc;
}
static int ecryptfs_unlink(struct inode *dir, struct dentry *dentry)
{
return ecryptfs_do_unlink(dir, dentry, d_inode(dentry));
}
static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
const char *symname)
{
int rc;
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
char *encoded_symname;
size_t encoded_symlen;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
dget(lower_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
mount_crypt_stat = &ecryptfs_superblock_to_private(
dir->i_sb)->mount_crypt_stat;
rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname,
&encoded_symlen,
mount_crypt_stat, symname,
strlen(symname));
if (rc)
goto out_lock;
rc = vfs_symlink(d_inode(lower_dir_dentry), lower_dentry,
encoded_symname);
kfree(encoded_symname);
if (rc || d_really_is_negative(lower_dentry))
goto out_lock;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out_lock;
fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
out_lock:
unlock_dir(lower_dir_dentry);
dput(lower_dentry);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int rc;
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
rc = vfs_mkdir(d_inode(lower_dir_dentry), lower_dentry, mode);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
set_nlink(dir, d_inode(lower_dir_dentry)->i_nlink);
out:
unlock_dir(lower_dir_dentry);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
{
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
struct inode *lower_dir_inode;
int rc;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
lower_dir_dentry = ecryptfs_dentry_to_lower(dentry->d_parent);
lower_dir_inode = d_inode(lower_dir_dentry);
inode_lock_nested(lower_dir_inode, I_MUTEX_PARENT);
dget(lower_dentry); // don't even try to make the lower negative
if (lower_dentry->d_parent != lower_dir_dentry)
rc = -EINVAL;
else if (d_unhashed(lower_dentry))
rc = -EINVAL;
else
rc = vfs_rmdir(lower_dir_inode, lower_dentry);
if (!rc) {
clear_nlink(d_inode(dentry));
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
fsstack_copy_attr_times(dir, lower_dir_inode);
set_nlink(dir, lower_dir_inode->i_nlink);
}
dput(lower_dentry);
inode_unlock(lower_dir_inode);
if (!rc)
d_drop(dentry);
return rc;
}
static int
ecryptfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
int rc;
struct dentry *lower_dentry;
struct dentry *lower_dir_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_dir_dentry = lock_parent(lower_dentry);
rc = vfs_mknod(d_inode(lower_dir_dentry), lower_dentry, mode, dev);
if (rc || d_really_is_negative(lower_dentry))
goto out;
rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
if (rc)
goto out;
fsstack_copy_attr_times(dir, d_inode(lower_dir_dentry));
fsstack_copy_inode_size(dir, d_inode(lower_dir_dentry));
out:
unlock_dir(lower_dir_dentry);
if (d_really_is_negative(dentry))
d_drop(dentry);
return rc;
}
static int
ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
int rc;
struct dentry *lower_old_dentry;
struct dentry *lower_new_dentry;
struct dentry *lower_old_dir_dentry;
struct dentry *lower_new_dir_dentry;
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
struct dentry *trap;
struct inode *target_inode;
if (flags)
return -EINVAL;
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
lower_old_dir_dentry = ecryptfs_dentry_to_lower(old_dentry->d_parent);
lower_new_dir_dentry = ecryptfs_dentry_to_lower(new_dentry->d_parent);
lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
target_inode = d_inode(new_dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
trap = lock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
dget(lower_new_dentry);
rc = -EINVAL;
if (lower_old_dentry->d_parent != lower_old_dir_dentry)
goto out_lock;
if (lower_new_dentry->d_parent != lower_new_dir_dentry)
goto out_lock;
if (d_unhashed(lower_old_dentry) || d_unhashed(lower_new_dentry))
goto out_lock;
/* source should not be ancestor of target */
if (trap == lower_old_dentry)
goto out_lock;
/* target should not be ancestor of source */
if (trap == lower_new_dentry) {
rc = -ENOTEMPTY;
goto out_lock;
}
rc = vfs_rename(d_inode(lower_old_dir_dentry), lower_old_dentry,
d_inode(lower_new_dir_dentry), lower_new_dentry,
NULL, 0);
if (rc)
goto out_lock;
if (target_inode)
fsstack_copy_attr_all(target_inode,
ecryptfs_inode_to_lower(target_inode));
fsstack_copy_attr_all(new_dir, d_inode(lower_new_dir_dentry));
if (new_dir != old_dir)
fsstack_copy_attr_all(old_dir, d_inode(lower_old_dir_dentry));
out_lock:
dput(lower_new_dentry);
ecryptfs: fix unlink and rmdir in face of underlying fs modifications A problem similar to the one caught in commit 74dd7c97ea2a ("ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()") exists for unlink/rmdir as well. Instead of playing with dget_parent() of underlying dentry of victim and hoping it's the same as underlying dentry of our directory, do the following: * find the underlying dentry of victim * find the underlying directory of victim's parent (stable since the victim is ecryptfs dentry and inode of its parent is held exclusive by the caller). * lock the inode of dentry underlying the victim's parent * check that underlying dentry of victim is still hashed and has the right parent - it can be moved, but it can't be moved to/from the directory we are holding exclusive. So while ->d_parent itself might not be stable, the result of comparison is. If the check passes, everything is fine - underlying directory is locked, underlying victim is still a child of that directory and we can go ahead and feed them to vfs_unlink(). As in the current mainline we need to pin the underlying dentry of victim, so that it wouldn't go negative under us, but that's the only temporary reference that needs to be grabbed there. Underlying dentry of parent won't go away (it's pinned by the parent, which is held by caller), so there's no need to grab it. The same problem (with the same solution) exists for rmdir. Moreover, rename gets simpler and more robust with the same "don't bother with dget_parent()" approach. Fixes: 74dd7c97ea2 "ecryptfs_rename(): verify that lower dentries are still OK after lock_rename()" Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2019-11-04 01:07:15 +08:00
unlock_rename(lower_old_dir_dentry, lower_new_dir_dentry);
return rc;
}
static char *ecryptfs_readlink_lower(struct dentry *dentry, size_t *bufsiz)
{
DEFINE_DELAYED_CALL(done);
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
const char *link;
char *buf;
int rc;
link = vfs_get_link(lower_dentry, &done);
if (IS_ERR(link))
return ERR_CAST(link);
rc = ecryptfs_decode_and_decrypt_filename(&buf, bufsiz, dentry->d_sb,
link, strlen(link));
do_delayed_call(&done);
if (rc)
return ERR_PTR(rc);
return buf;
}
static const char *ecryptfs_get_link(struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
size_t len;
char *buf;
if (!dentry)
return ERR_PTR(-ECHILD);
buf = ecryptfs_readlink_lower(dentry, &len);
if (IS_ERR(buf))
return buf;
fsstack_copy_attr_atime(d_inode(dentry),
d_inode(ecryptfs_dentry_to_lower(dentry)));
buf[len] = '\0';
set_delayed_call(done, kfree_link, buf);
return buf;
}
/**
* upper_size_to_lower_size
* @crypt_stat: Crypt_stat associated with file
* @upper_size: Size of the upper file
*
* Calculate the required size of the lower file based on the
* specified size of the upper file. This calculation is based on the
* number of headers in the underlying file and the extent size.
*
* Returns Calculated size of the lower file.
*/
static loff_t
upper_size_to_lower_size(struct ecryptfs_crypt_stat *crypt_stat,
loff_t upper_size)
{
loff_t lower_size;
lower_size = ecryptfs_lower_header_size(crypt_stat);
if (upper_size != 0) {
loff_t num_extents;
num_extents = upper_size >> crypt_stat->extent_shift;
if (upper_size & ~crypt_stat->extent_mask)
num_extents++;
lower_size += (num_extents * crypt_stat->extent_size);
}
return lower_size;
}
/**
* truncate_upper
* @dentry: The ecryptfs layer dentry
* @ia: Address of the ecryptfs inode's attributes
* @lower_ia: Address of the lower inode's attributes
*
* Function to handle truncations modifying the size of the file. Note
* that the file sizes are interpolated. When expanding, we are simply
* writing strings of 0's out. When truncating, we truncate the upper
* inode and update the lower_ia according to the page index
* interpolations. If ATTR_SIZE is set in lower_ia->ia_valid upon return,
* the caller must use lower_ia in a call to notify_change() to perform
* the truncation of the lower inode.
*
* Returns zero on success; non-zero otherwise
*/
static int truncate_upper(struct dentry *dentry, struct iattr *ia,
struct iattr *lower_ia)
{
int rc = 0;
struct inode *inode = d_inode(dentry);
struct ecryptfs_crypt_stat *crypt_stat;
loff_t i_size = i_size_read(inode);
loff_t lower_size_before_truncate;
loff_t lower_size_after_truncate;
if (unlikely((ia->ia_size == i_size))) {
lower_ia->ia_valid &= ~ATTR_SIZE;
return 0;
}
rc = ecryptfs_get_lower_file(dentry, inode);
if (rc)
return rc;
crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
/* Switch on growing or shrinking file */
if (ia->ia_size > i_size) {
char zero[] = { 0x00 };
lower_ia->ia_valid &= ~ATTR_SIZE;
/* Write a single 0 at the last position of the file;
* this triggers code that will fill in 0's throughout
* the intermediate portion of the previous end of the
* file and the new and of the file */
rc = ecryptfs_write(inode, zero,
(ia->ia_size - 1), 1);
} else { /* ia->ia_size < i_size_read(inode) */
/* We're chopping off all the pages down to the page
* in which ia->ia_size is located. Fill in the end of
* that page from (ia->ia_size & ~PAGE_MASK) to
* PAGE_SIZE with zeros. */
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 20:29:47 +08:00
size_t num_zeros = (PAGE_SIZE
- (ia->ia_size & ~PAGE_MASK));
if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
truncate_setsize(inode, ia->ia_size);
lower_ia->ia_size = ia->ia_size;
lower_ia->ia_valid |= ATTR_SIZE;
goto out;
}
if (num_zeros) {
char *zeros_virt;
zeros_virt = kzalloc(num_zeros, GFP_KERNEL);
if (!zeros_virt) {
rc = -ENOMEM;
goto out;
}
rc = ecryptfs_write(inode, zeros_virt,
ia->ia_size, num_zeros);
kfree(zeros_virt);
if (rc) {
printk(KERN_ERR "Error attempting to zero out "
"the remainder of the end page on "
"reducing truncate; rc = [%d]\n", rc);
goto out;
}
}
truncate_setsize(inode, ia->ia_size);
rc = ecryptfs_write_inode_size_to_metadata(inode);
if (rc) {
printk(KERN_ERR "Problem with "
"ecryptfs_write_inode_size_to_metadata; "
"rc = [%d]\n", rc);
goto out;
}
/* We are reducing the size of the ecryptfs file, and need to
* know if we need to reduce the size of the lower file. */
lower_size_before_truncate =
upper_size_to_lower_size(crypt_stat, i_size);
lower_size_after_truncate =
upper_size_to_lower_size(crypt_stat, ia->ia_size);
if (lower_size_after_truncate < lower_size_before_truncate) {
lower_ia->ia_size = lower_size_after_truncate;
lower_ia->ia_valid |= ATTR_SIZE;
} else
lower_ia->ia_valid &= ~ATTR_SIZE;
}
out:
ecryptfs_put_lower_file(inode);
return rc;
}
eCryptfs: Check inode changes in setattr Most filesystems call inode_change_ok() very early in ->setattr(), but eCryptfs didn't call it at all. It allowed the lower filesystem to make the call in its ->setattr() function. Then, eCryptfs would copy the appropriate inode attributes from the lower inode to the eCryptfs inode. This patch changes that and actually calls inode_change_ok() on the eCryptfs inode, fairly early in ecryptfs_setattr(). Ideally, the call would happen earlier in ecryptfs_setattr(), but there are some possible inode initialization steps that must happen first. Since the call was already being made on the lower inode, the change in functionality should be minimal, except for the case of a file extending truncate call. In that case, inode_newsize_ok() was never being called on the eCryptfs inode. Rather than inode_newsize_ok() catching maximum file size errors early on, eCryptfs would encrypt zeroed pages and write them to the lower filesystem until the lower filesystem's write path caught the error in generic_write_checks(). This patch introduces a new function, called ecryptfs_inode_newsize_ok(), which checks if the new lower file size is within the appropriate limits when the truncate operation will be growing the lower file. In summary this change prevents eCryptfs truncate operations (and the resulting page encryptions), which would exceed the lower filesystem limits or FSIZE rlimits, from ever starting. Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Li Wang <liwang@nudt.edu.cn> Cc: <stable@vger.kernel.org>
2012-01-20 10:33:44 +08:00
static int ecryptfs_inode_newsize_ok(struct inode *inode, loff_t offset)
{
struct ecryptfs_crypt_stat *crypt_stat;
loff_t lower_oldsize, lower_newsize;
crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
lower_oldsize = upper_size_to_lower_size(crypt_stat,
i_size_read(inode));
lower_newsize = upper_size_to_lower_size(crypt_stat, offset);
if (lower_newsize > lower_oldsize) {
/*
* The eCryptfs inode and the new *lower* size are mixed here
* because we may not have the lower i_mutex held and/or it may
* not be appropriate to call inode_newsize_ok() with inodes
* from other filesystems.
*/
return inode_newsize_ok(inode, lower_newsize);
}
return 0;
}
/**
* ecryptfs_truncate
* @dentry: The ecryptfs layer dentry
* @new_length: The length to expand the file to
*
* Simple function that handles the truncation of an eCryptfs inode and
* its corresponding lower inode.
*
* Returns zero on success; non-zero otherwise
*/
int ecryptfs_truncate(struct dentry *dentry, loff_t new_length)
{
struct iattr ia = { .ia_valid = ATTR_SIZE, .ia_size = new_length };
struct iattr lower_ia = { .ia_valid = 0 };
int rc;
rc = ecryptfs_inode_newsize_ok(d_inode(dentry), new_length);
eCryptfs: Check inode changes in setattr Most filesystems call inode_change_ok() very early in ->setattr(), but eCryptfs didn't call it at all. It allowed the lower filesystem to make the call in its ->setattr() function. Then, eCryptfs would copy the appropriate inode attributes from the lower inode to the eCryptfs inode. This patch changes that and actually calls inode_change_ok() on the eCryptfs inode, fairly early in ecryptfs_setattr(). Ideally, the call would happen earlier in ecryptfs_setattr(), but there are some possible inode initialization steps that must happen first. Since the call was already being made on the lower inode, the change in functionality should be minimal, except for the case of a file extending truncate call. In that case, inode_newsize_ok() was never being called on the eCryptfs inode. Rather than inode_newsize_ok() catching maximum file size errors early on, eCryptfs would encrypt zeroed pages and write them to the lower filesystem until the lower filesystem's write path caught the error in generic_write_checks(). This patch introduces a new function, called ecryptfs_inode_newsize_ok(), which checks if the new lower file size is within the appropriate limits when the truncate operation will be growing the lower file. In summary this change prevents eCryptfs truncate operations (and the resulting page encryptions), which would exceed the lower filesystem limits or FSIZE rlimits, from ever starting. Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Li Wang <liwang@nudt.edu.cn> Cc: <stable@vger.kernel.org>
2012-01-20 10:33:44 +08:00
if (rc)
return rc;
rc = truncate_upper(dentry, &ia, &lower_ia);
if (!rc && lower_ia.ia_valid & ATTR_SIZE) {
struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
inode_lock(d_inode(lower_dentry));
rc = notify_change(lower_dentry, &lower_ia, NULL);
inode_unlock(d_inode(lower_dentry));
}
return rc;
}
static int
ecryptfs_permission(struct inode *inode, int mask)
{
return inode_permission(ecryptfs_inode_to_lower(inode), mask);
}
/**
* ecryptfs_setattr
* @dentry: dentry handle to the inode to modify
* @ia: Structure with flags of what to change and values
*
* Updates the metadata of an inode. If the update is to the size
* i.e. truncation, then ecryptfs_truncate will handle the size modification
* of both the ecryptfs inode and the lower inode.
*
* All other metadata changes will be passed right to the lower filesystem,
* and we will just update our inode to look like the lower.
*/
static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
{
int rc = 0;
struct dentry *lower_dentry;
struct iattr lower_ia;
struct inode *inode;
struct inode *lower_inode;
struct ecryptfs_crypt_stat *crypt_stat;
crypt_stat = &ecryptfs_inode_to_private(d_inode(dentry))->crypt_stat;
if (!(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED)) {
rc = ecryptfs_init_crypt_stat(crypt_stat);
if (rc)
return rc;
}
inode = d_inode(dentry);
lower_inode = ecryptfs_inode_to_lower(inode);
lower_dentry = ecryptfs_dentry_to_lower(dentry);
mutex_lock(&crypt_stat->cs_mutex);
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 20:02:35 +08:00
if (d_is_dir(dentry))
crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
VFS: (Scripted) Convert S_ISLNK/DIR/REG(dentry->d_inode) to d_is_*(dentry) Convert the following where appropriate: (1) S_ISLNK(dentry->d_inode) to d_is_symlink(dentry). (2) S_ISREG(dentry->d_inode) to d_is_reg(dentry). (3) S_ISDIR(dentry->d_inode) to d_is_dir(dentry). This is actually more complicated than it appears as some calls should be converted to d_can_lookup() instead. The difference is whether the directory in question is a real dir with a ->lookup op or whether it's a fake dir with a ->d_automount op. In some circumstances, we can subsume checks for dentry->d_inode not being NULL into this, provided we the code isn't in a filesystem that expects d_inode to be NULL if the dirent really *is* negative (ie. if we're going to use d_inode() rather than d_backing_inode() to get the inode pointer). Note that the dentry type field may be set to something other than DCACHE_MISS_TYPE when d_inode is NULL in the case of unionmount, where the VFS manages the fall-through from a negative dentry to a lower layer. In such a case, the dentry type of the negative union dentry is set to the same as the type of the lower dentry. However, if you know d_inode is not NULL at the call site, then you can use the d_is_xxx() functions even in a filesystem. There is one further complication: a 0,0 chardev dentry may be labelled DCACHE_WHITEOUT_TYPE rather than DCACHE_SPECIAL_TYPE. Strictly, this was intended for special directory entry types that don't have attached inodes. The following perl+coccinelle script was used: use strict; my @callers; open($fd, 'git grep -l \'S_IS[A-Z].*->d_inode\' |') || die "Can't grep for S_ISDIR and co. callers"; @callers = <$fd>; close($fd); unless (@callers) { print "No matches\n"; exit(0); } my @cocci = ( '@@', 'expression E;', '@@', '', '- S_ISLNK(E->d_inode->i_mode)', '+ d_is_symlink(E)', '', '@@', 'expression E;', '@@', '', '- S_ISDIR(E->d_inode->i_mode)', '+ d_is_dir(E)', '', '@@', 'expression E;', '@@', '', '- S_ISREG(E->d_inode->i_mode)', '+ d_is_reg(E)' ); my $coccifile = "tmp.sp.cocci"; open($fd, ">$coccifile") || die $coccifile; print($fd "$_\n") || die $coccifile foreach (@cocci); close($fd); foreach my $file (@callers) { chomp $file; print "Processing ", $file, "\n"; system("spatch", "--sp-file", $coccifile, $file, "--in-place", "--no-show-diff") == 0 || die "spatch failed"; } [AV: overlayfs parts skipped] Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2015-01-29 20:02:35 +08:00
else if (d_is_reg(dentry)
&& (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)
|| !(crypt_stat->flags & ECRYPTFS_KEY_VALID))) {
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
mount_crypt_stat = &ecryptfs_superblock_to_private(
dentry->d_sb)->mount_crypt_stat;
rc = ecryptfs_get_lower_file(dentry, inode);
if (rc) {
mutex_unlock(&crypt_stat->cs_mutex);
goto out;
}
rc = ecryptfs_read_metadata(dentry);
ecryptfs_put_lower_file(inode);
if (rc) {
if (!(mount_crypt_stat->flags
& ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED)) {
rc = -EIO;
printk(KERN_WARNING "Either the lower file "
"is not in a valid eCryptfs format, "
"or the key could not be retrieved. "
"Plaintext passthrough mode is not "
"enabled; returning -EIO\n");
mutex_unlock(&crypt_stat->cs_mutex);
goto out;
}
rc = 0;
crypt_stat->flags &= ~(ECRYPTFS_I_SIZE_INITIALIZED
| ECRYPTFS_ENCRYPTED);
}
}
mutex_unlock(&crypt_stat->cs_mutex);
eCryptfs: Check inode changes in setattr Most filesystems call inode_change_ok() very early in ->setattr(), but eCryptfs didn't call it at all. It allowed the lower filesystem to make the call in its ->setattr() function. Then, eCryptfs would copy the appropriate inode attributes from the lower inode to the eCryptfs inode. This patch changes that and actually calls inode_change_ok() on the eCryptfs inode, fairly early in ecryptfs_setattr(). Ideally, the call would happen earlier in ecryptfs_setattr(), but there are some possible inode initialization steps that must happen first. Since the call was already being made on the lower inode, the change in functionality should be minimal, except for the case of a file extending truncate call. In that case, inode_newsize_ok() was never being called on the eCryptfs inode. Rather than inode_newsize_ok() catching maximum file size errors early on, eCryptfs would encrypt zeroed pages and write them to the lower filesystem until the lower filesystem's write path caught the error in generic_write_checks(). This patch introduces a new function, called ecryptfs_inode_newsize_ok(), which checks if the new lower file size is within the appropriate limits when the truncate operation will be growing the lower file. In summary this change prevents eCryptfs truncate operations (and the resulting page encryptions), which would exceed the lower filesystem limits or FSIZE rlimits, from ever starting. Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Li Wang <liwang@nudt.edu.cn> Cc: <stable@vger.kernel.org>
2012-01-20 10:33:44 +08:00
rc = setattr_prepare(dentry, ia);
eCryptfs: Check inode changes in setattr Most filesystems call inode_change_ok() very early in ->setattr(), but eCryptfs didn't call it at all. It allowed the lower filesystem to make the call in its ->setattr() function. Then, eCryptfs would copy the appropriate inode attributes from the lower inode to the eCryptfs inode. This patch changes that and actually calls inode_change_ok() on the eCryptfs inode, fairly early in ecryptfs_setattr(). Ideally, the call would happen earlier in ecryptfs_setattr(), but there are some possible inode initialization steps that must happen first. Since the call was already being made on the lower inode, the change in functionality should be minimal, except for the case of a file extending truncate call. In that case, inode_newsize_ok() was never being called on the eCryptfs inode. Rather than inode_newsize_ok() catching maximum file size errors early on, eCryptfs would encrypt zeroed pages and write them to the lower filesystem until the lower filesystem's write path caught the error in generic_write_checks(). This patch introduces a new function, called ecryptfs_inode_newsize_ok(), which checks if the new lower file size is within the appropriate limits when the truncate operation will be growing the lower file. In summary this change prevents eCryptfs truncate operations (and the resulting page encryptions), which would exceed the lower filesystem limits or FSIZE rlimits, from ever starting. Signed-off-by: Tyler Hicks <tyhicks@canonical.com> Reviewed-by: Li Wang <liwang@nudt.edu.cn> Cc: <stable@vger.kernel.org>
2012-01-20 10:33:44 +08:00
if (rc)
goto out;
if (ia->ia_valid & ATTR_SIZE) {
rc = ecryptfs_inode_newsize_ok(inode, ia->ia_size);
if (rc)
goto out;
}
memcpy(&lower_ia, ia, sizeof(lower_ia));
if (ia->ia_valid & ATTR_FILE)
lower_ia.ia_file = ecryptfs_file_to_lower(ia->ia_file);
if (ia->ia_valid & ATTR_SIZE) {
rc = truncate_upper(dentry, ia, &lower_ia);
if (rc < 0)
goto out;
}
/*
* mode change is for clearing setuid/setgid bits. Allow lower fs
* to interpret this in its own way.
*/
if (lower_ia.ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID))
lower_ia.ia_valid &= ~ATTR_MODE;
inode_lock(d_inode(lower_dentry));
rc = notify_change(lower_dentry, &lower_ia, NULL);
inode_unlock(d_inode(lower_dentry));
out:
fsstack_copy_attr_all(inode, lower_inode);
return rc;
}
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
struct dentry *dentry = path->dentry;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
int rc = 0;
mount_crypt_stat = &ecryptfs_superblock_to_private(
dentry->d_sb)->mount_crypt_stat;
generic_fillattr(d_inode(dentry), stat);
if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) {
char *target;
size_t targetsiz;
target = ecryptfs_readlink_lower(dentry, &targetsiz);
if (!IS_ERR(target)) {
kfree(target);
stat->size = targetsiz;
} else {
rc = PTR_ERR(target);
}
}
return rc;
}
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
static int ecryptfs_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
struct dentry *dentry = path->dentry;
struct kstat lower_stat;
int rc;
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat,
request_mask, flags);
if (!rc) {
fsstack_copy_attr_all(d_inode(dentry),
ecryptfs_inode_to_lower(d_inode(dentry)));
generic_fillattr(d_inode(dentry), stat);
stat->blocks = lower_stat.blocks;
}
return rc;
}
int
ecryptfs_setxattr(struct dentry *dentry, struct inode *inode,
const char *name, const void *value,
size_t size, int flags)
{
int rc;
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
if (!(d_inode(lower_dentry)->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
rc = vfs_setxattr(lower_dentry, name, value, size, flags);
if (!rc && inode)
fsstack_copy_attr_all(inode, d_inode(lower_dentry));
out:
return rc;
}
ssize_t
ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode,
const char *name, void *value, size_t size)
{
int rc;
if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
inode_lock(lower_inode);
rc = __vfs_getxattr(lower_dentry, lower_inode, name, value, size);
inode_unlock(lower_inode);
out:
return rc;
}
static ssize_t
ecryptfs_getxattr(struct dentry *dentry, struct inode *inode,
const char *name, void *value, size_t size)
{
return ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
ecryptfs_inode_to_lower(inode),
name, value, size);
}
static ssize_t
ecryptfs_listxattr(struct dentry *dentry, char *list, size_t size)
{
int rc = 0;
struct dentry *lower_dentry;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
if (!d_inode(lower_dentry)->i_op->listxattr) {
rc = -EOPNOTSUPP;
goto out;
}
inode_lock(d_inode(lower_dentry));
rc = d_inode(lower_dentry)->i_op->listxattr(lower_dentry, list, size);
inode_unlock(d_inode(lower_dentry));
out:
return rc;
}
static int ecryptfs_removexattr(struct dentry *dentry, struct inode *inode,
const char *name)
{
int rc;
struct dentry *lower_dentry;
struct inode *lower_inode;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_inode = ecryptfs_inode_to_lower(inode);
if (!(lower_inode->i_opflags & IOP_XATTR)) {
rc = -EOPNOTSUPP;
goto out;
}
inode_lock(lower_inode);
rc = __vfs_removexattr(lower_dentry, name);
inode_unlock(lower_inode);
out:
return rc;
}
const struct inode_operations ecryptfs_symlink_iops = {
.get_link = ecryptfs_get_link,
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.getattr = ecryptfs_getattr_link,
.listxattr = ecryptfs_listxattr,
};
const struct inode_operations ecryptfs_dir_iops = {
.create = ecryptfs_create,
.lookup = ecryptfs_lookup,
.link = ecryptfs_link,
.unlink = ecryptfs_unlink,
.symlink = ecryptfs_symlink,
.mkdir = ecryptfs_mkdir,
.rmdir = ecryptfs_rmdir,
.mknod = ecryptfs_mknod,
.rename = ecryptfs_rename,
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.listxattr = ecryptfs_listxattr,
};
const struct inode_operations ecryptfs_main_iops = {
.permission = ecryptfs_permission,
.setattr = ecryptfs_setattr,
.getattr = ecryptfs_getattr,
.listxattr = ecryptfs_listxattr,
};
static int ecryptfs_xattr_get(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, void *buffer, size_t size)
{
return ecryptfs_getxattr(dentry, inode, name, buffer, size);
}
static int ecryptfs_xattr_set(const struct xattr_handler *handler,
struct dentry *dentry, struct inode *inode,
const char *name, const void *value, size_t size,
int flags)
{
if (value)
return ecryptfs_setxattr(dentry, inode, name, value, size, flags);
else {
BUG_ON(flags != XATTR_REPLACE);
return ecryptfs_removexattr(dentry, inode, name);
}
}
static const struct xattr_handler ecryptfs_xattr_handler = {
.prefix = "", /* match anything */
.get = ecryptfs_xattr_get,
.set = ecryptfs_xattr_set,
};
const struct xattr_handler *ecryptfs_xattr_handlers[] = {
&ecryptfs_xattr_handler,
NULL
};