linux_dsm_epyc7002/fs/xattr.c

985 lines
23 KiB
C
Raw Normal View History

/*
File: fs/xattr.c
Extended attribute handling.
Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
Copyright (C) 2001 SGI - Silicon Graphics, Inc <linux-xfs@oss.sgi.com>
Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*/
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/evm.h>
#include <linux/syscalls.h>
#include <linux/export.h>
#include <linux/fsnotify.h>
#include <linux/audit.h>
#include <linux/vmalloc.h>
2012-02-08 09:52:57 +07:00
#include <linux/posix_acl_xattr.h>
#include <asm/uaccess.h>
/*
* Check permissions for extended attribute access. This is a bit complicated
* because different namespaces have very different rules.
*/
static int
xattr_permission(struct inode *inode, const char *name, int mask)
{
/*
* We can never set or remove an extended attribute on a read-only
* filesystem or on an immutable / append-only inode.
*/
if (mask & MAY_WRITE) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
/*
* No restriction for security.* and system.* from the VFS. Decision
* on these is left to the underlying filesystem / security module.
*/
if (!strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return 0;
/*
* The trusted.* namespace can only be accessed by privileged users.
*/
if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
if (!capable(CAP_SYS_ADMIN))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
return 0;
}
/*
* In the user.* namespace, only regular files and directories can have
* extended attributes. For sticky directories, only the owner and
* privileged users can write attributes.
*/
if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
(mask & MAY_WRITE) && !inode_owner_or_capable(inode))
return -EPERM;
}
return inode_permission(inode, mask);
}
/**
* __vfs_setxattr_noperm - perform setxattr operation without performing
* permission checks.
*
* @dentry - object to perform setxattr on
* @name - xattr name to set
* @value - value to set @name to
* @size - size of @value
* @flags - flags to pass into filesystem operations
*
* returns the result of the internal setxattr or setsecurity operations.
*
* This function requires the caller to lock the inode's i_mutex before it
* is executed. It also assumes that the caller will make the appropriate
* permission checks.
*/
int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
int error = -EOPNOTSUPP;
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
if (issec)
inode->i_flags &= ~S_NOSEC;
if (inode->i_op->setxattr) {
error = inode->i_op->setxattr(dentry, name, value, size, flags);
if (!error) {
fsnotify_xattr(dentry);
security_inode_post_setxattr(dentry, name, value,
size, flags);
}
Cache xattr security drop check for write v2 Some recent benchmarking on btrfs showed that a major scaling bottleneck on large systems on btrfs is currently the xattr lookup on every write. Why xattr lookup on every write I hear you ask? write wants to drop suid and security related xattrs that could set o capabilities for executables. To do that it currently looks up security.capability on EVERY write (even for non executables) to decide whether to drop it or not. In btrfs this causes an additional tree walk, hitting some per file system locks and quite bad scalability. In a simple read workload on a 8S system I saw over 90% CPU time in spinlocks related to that. Chris Mason tells me this is also a problem in ext4, where it hits the global mbcache lock. This patch adds a simple per inode to avoid this problem. We only do the lookup once per file and then if there is no xattr cache the decision. All xattr changes clear the flag. I also used the same flag to avoid the suid check, although that one is pretty cheap. A file system can also set this flag when it creates the inode, if it has a cheap way to do so. This is done for some common file systems in followon patches. With this patch a major part of the lock contention disappears for btrfs. Some testing on smaller systems didn't show significant performance changes, but at least it helps the larger systems and is generally more efficient. v2: Rename is_sgid. add file system helper. Cc: chris.mason@oracle.com Cc: josef@redhat.com Cc: viro@zeniv.linux.org.uk Cc: agruen@linbit.com Cc: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2011-05-28 22:25:51 +07:00
} else if (issec) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
error = security_inode_setsecurity(inode, suffix, value,
size, flags);
if (!error)
fsnotify_xattr(dentry);
}
return error;
}
int
vfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(inode, name, MAY_WRITE);
if (error)
return error;
inode_lock(inode);
error = security_inode_setxattr(dentry, name, value, size, flags);
if (error)
goto out;
error = __vfs_setxattr_noperm(dentry, name, value, size, flags);
out:
inode_unlock(inode);
return error;
}
EXPORT_SYMBOL_GPL(vfs_setxattr);
ssize_t
xattr_getsecurity(struct inode *inode, const char *name, void *value,
size_t size)
{
void *buffer = NULL;
ssize_t len;
if (!value || !size) {
len = security_inode_getsecurity(inode, name, &buffer, false);
goto out_noalloc;
}
len = security_inode_getsecurity(inode, name, &buffer, true);
if (len < 0)
return len;
if (size < len) {
len = -ERANGE;
goto out;
}
memcpy(value, buffer, len);
out:
security_release_secctx(buffer, len);
out_noalloc:
return len;
}
EXPORT_SYMBOL_GPL(xattr_getsecurity);
/*
* vfs_getxattr_alloc - allocate memory, if necessary, before calling getxattr
*
* Allocate memory, if not already allocated, or re-allocate correct size,
* before retrieving the extended attribute.
*
* Returns the result of alloc, if failed, or the getxattr operation.
*/
ssize_t
vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value,
size_t xattr_size, gfp_t flags)
{
struct inode *inode = dentry->d_inode;
char *value = *xattr_value;
int error;
error = xattr_permission(inode, name, MAY_READ);
if (error)
return error;
if (!inode->i_op->getxattr)
return -EOPNOTSUPP;
error = inode->i_op->getxattr(dentry, name, NULL, 0);
if (error < 0)
return error;
if (!value || (error > xattr_size)) {
value = krealloc(*xattr_value, error + 1, flags);
if (!value)
return -ENOMEM;
memset(value, 0, error + 1);
}
error = inode->i_op->getxattr(dentry, name, value, error);
*xattr_value = value;
return error;
}
ssize_t
vfs_getxattr(struct dentry *dentry, const char *name, void *value, size_t size)
{
struct inode *inode = dentry->d_inode;
int error;
error = xattr_permission(inode, name, MAY_READ);
if (error)
return error;
error = security_inode_getxattr(dentry, name);
if (error)
return error;
if (!strncmp(name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN)) {
const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
int ret = xattr_getsecurity(inode, suffix, value, size);
/*
* Only overwrite the return value if a security module
* is actually active.
*/
if (ret == -EOPNOTSUPP)
goto nolsm;
return ret;
}
nolsm:
if (inode->i_op->getxattr)
error = inode->i_op->getxattr(dentry, name, value, size);
else
error = -EOPNOTSUPP;
return error;
}
EXPORT_SYMBOL_GPL(vfs_getxattr);
ssize_t
vfs_listxattr(struct dentry *d, char *list, size_t size)
{
ssize_t error;
error = security_inode_listxattr(d);
if (error)
return error;
error = -EOPNOTSUPP;
if (d->d_inode->i_op->listxattr) {
error = d->d_inode->i_op->listxattr(d, list, size);
} else {
error = security_inode_listsecurity(d->d_inode, list, size);
if (size && error > size)
error = -ERANGE;
}
return error;
}
EXPORT_SYMBOL_GPL(vfs_listxattr);
int
vfs_removexattr(struct dentry *dentry, const char *name)
{
struct inode *inode = dentry->d_inode;
int error;
if (!inode->i_op->removexattr)
return -EOPNOTSUPP;
error = xattr_permission(inode, name, MAY_WRITE);
if (error)
return error;
inode_lock(inode);
error = security_inode_removexattr(dentry, name);
if (error)
goto out;
error = inode->i_op->removexattr(dentry, name);
if (!error) {
fsnotify_xattr(dentry);
evm_inode_post_removexattr(dentry, name);
}
out:
inode_unlock(inode);
return error;
}
EXPORT_SYMBOL_GPL(vfs_removexattr);
/*
* Extended attribute SET operations
*/
static long
setxattr(struct dentry *d, const char __user *name, const void __user *value,
size_t size, int flags)
{
int error;
void *kvalue = NULL;
char kname[XATTR_NAME_MAX + 1];
if (flags & ~(XATTR_CREATE|XATTR_REPLACE))
return -EINVAL;
error = strncpy_from_user(kname, name, sizeof(kname));
if (error == 0 || error == sizeof(kname))
error = -ERANGE;
if (error < 0)
return error;
if (size) {
if (size > XATTR_SIZE_MAX)
return -E2BIG;
kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!kvalue) {
kvalue = vmalloc(size);
if (!kvalue)
return -ENOMEM;
}
if (copy_from_user(kvalue, value, size)) {
error = -EFAULT;
goto out;
}
2012-02-08 09:52:57 +07:00
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
posix_acl_fix_xattr_from_user(kvalue, size);
}
error = vfs_setxattr(d, kname, kvalue, size, flags);
out:
kvfree(kvalue);
return error;
}
static int path_setxattr(const char __user *pathname,
const char __user *name, const void __user *value,
size_t size, int flags, unsigned int lookup_flags)
{
struct path path;
int error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = mnt_want_write(path.mnt);
if (!error) {
error = setxattr(path.dentry, name, value, size, flags);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattr(pathname, name, value, size, flags, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
const char __user *, name, const void __user *, value,
size_t, size, int, flags)
{
return path_setxattr(pathname, name, value, size, flags, 0);
}
SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
const void __user *,value, size_t, size, int, flags)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
error = setxattr(f.file->f_path.dentry, name, value, size, flags);
mnt_drop_write_file(f.file);
}
fdput(f);
return error;
}
/*
* Extended attribute GET operations
*/
static ssize_t
getxattr(struct dentry *d, const char __user *name, void __user *value,
size_t size)
{
ssize_t error;
void *kvalue = NULL;
char kname[XATTR_NAME_MAX + 1];
error = strncpy_from_user(kname, name, sizeof(kname));
if (error == 0 || error == sizeof(kname))
error = -ERANGE;
if (error < 0)
return error;
if (size) {
if (size > XATTR_SIZE_MAX)
size = XATTR_SIZE_MAX;
kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
if (!kvalue) {
kvalue = vmalloc(size);
if (!kvalue)
return -ENOMEM;
}
}
error = vfs_getxattr(d, kname, kvalue, size);
if (error > 0) {
2012-02-08 09:52:57 +07:00
if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) ||
(strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0))
posix_acl_fix_xattr_to_user(kvalue, size);
if (size && copy_to_user(value, kvalue, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_SIZE_MAX) {
/* The file system tried to returned a value bigger
than XATTR_SIZE_MAX bytes. Not possible. */
error = -E2BIG;
}
kvfree(kvalue);
return error;
}
static ssize_t path_getxattr(const char __user *pathname,
const char __user *name, void __user *value,
size_t size, unsigned int lookup_flags)
{
struct path path;
ssize_t error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = getxattr(path.dentry, name, value, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattr(pathname, name, value, size, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
const char __user *, name, void __user *, value, size_t, size)
{
return path_getxattr(pathname, name, value, size, 0);
}
SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name,
void __user *, value, size_t, size)
{
struct fd f = fdget(fd);
ssize_t error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = getxattr(f.file->f_path.dentry, name, value, size);
fdput(f);
return error;
}
/*
* Extended attribute LIST operations
*/
static ssize_t
listxattr(struct dentry *d, char __user *list, size_t size)
{
ssize_t error;
char *klist = NULL;
if (size) {
if (size > XATTR_LIST_MAX)
size = XATTR_LIST_MAX;
klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL);
if (!klist) {
klist = vmalloc(size);
if (!klist)
return -ENOMEM;
}
}
error = vfs_listxattr(d, klist, size);
if (error > 0) {
if (size && copy_to_user(list, klist, error))
error = -EFAULT;
} else if (error == -ERANGE && size >= XATTR_LIST_MAX) {
/* The file system tried to returned a list bigger
than XATTR_LIST_MAX bytes. Not possible. */
error = -E2BIG;
}
kvfree(klist);
return error;
}
static ssize_t path_listxattr(const char __user *pathname, char __user *list,
size_t size, unsigned int lookup_flags)
{
struct path path;
ssize_t error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = listxattr(path.dentry, list, size);
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattr(pathname, list, size, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
size_t, size)
{
return path_listxattr(pathname, list, size, 0);
}
SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
{
struct fd f = fdget(fd);
ssize_t error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = listxattr(f.file->f_path.dentry, list, size);
fdput(f);
return error;
}
/*
* Extended attribute REMOVE operations
*/
static long
removexattr(struct dentry *d, const char __user *name)
{
int error;
char kname[XATTR_NAME_MAX + 1];
error = strncpy_from_user(kname, name, sizeof(kname));
if (error == 0 || error == sizeof(kname))
error = -ERANGE;
if (error < 0)
return error;
return vfs_removexattr(d, kname);
}
static int path_removexattr(const char __user *pathname,
const char __user *name, unsigned int lookup_flags)
{
struct path path;
int error;
retry:
error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
if (error)
return error;
error = mnt_want_write(path.mnt);
if (!error) {
error = removexattr(path.dentry, name);
mnt_drop_write(path.mnt);
}
path_put(&path);
if (retry_estale(error, lookup_flags)) {
lookup_flags |= LOOKUP_REVAL;
goto retry;
}
return error;
}
SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattr(pathname, name, LOOKUP_FOLLOW);
}
SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
const char __user *, name)
{
return path_removexattr(pathname, name, 0);
}
SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
{
struct fd f = fdget(fd);
int error = -EBADF;
if (!f.file)
return error;
audit_file(f.file);
error = mnt_want_write_file(f.file);
if (!error) {
error = removexattr(f.file->f_path.dentry, name);
mnt_drop_write_file(f.file);
}
fdput(f);
return error;
}
static const char *
strcmp_prefix(const char *a, const char *a_prefix)
{
while (*a_prefix && *a == *a_prefix) {
a++;
a_prefix++;
}
return *a_prefix ? NULL : a;
}
/*
* In order to implement different sets of xattr operations for each xattr
* prefix with the generic xattr API, a filesystem should create a
* null-terminated array of struct xattr_handler (one for each prefix) and
* hang a pointer to it off of the s_xattr field of the superblock.
*
* The generic_fooxattr() functions will use this list to dispatch xattr
* operations to the correct xattr_handler.
*/
#define for_each_xattr_handler(handlers, handler) \
for ((handler) = *(handlers)++; \
(handler) != NULL; \
(handler) = *(handlers)++)
/*
* Find the xattr_handler with the matching prefix.
*/
static const struct xattr_handler *
xattr_resolve_name(const struct xattr_handler **handlers, const char **name)
{
const struct xattr_handler *handler;
if (!*name)
return NULL;
for_each_xattr_handler(handlers, handler) {
const char *n;
n = strcmp_prefix(*name, xattr_prefix(handler));
if (n) {
if (!handler->prefix ^ !*n) {
if (*n)
continue;
return ERR_PTR(-EINVAL);
}
*name = n;
return handler;
}
}
return ERR_PTR(-EOPNOTSUPP);
}
/*
* Find the handler for the prefix and dispatch its get() operation.
*/
ssize_t
generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size)
{
const struct xattr_handler *handler;
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
return handler->get(handler, dentry, name, buffer, size);
}
/*
* Combine the results of the list() operation from every xattr_handler in the
* list.
*/
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr;
unsigned int size = 0;
if (!buffer) {
for_each_xattr_handler(handlers, handler) {
if (!handler->name ||
(handler->list && !handler->list(dentry)))
continue;
size += strlen(handler->name) + 1;
}
} else {
char *buf = buffer;
size_t len;
for_each_xattr_handler(handlers, handler) {
if (!handler->name ||
(handler->list && !handler->list(dentry)))
continue;
len = strlen(handler->name);
if (len + 1 > buffer_size)
return -ERANGE;
memcpy(buf, handler->name, len + 1);
buf += len + 1;
buffer_size -= len + 1;
}
size = buf - buffer;
}
return size;
}
/*
* Find the handler for the prefix and dispatch its set() operation.
*/
int
generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags)
{
const struct xattr_handler *handler;
if (size == 0)
value = ""; /* empty EA, do not remove */
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
return handler->set(handler, dentry, name, value, size, flags);
}
/*
* Find the handler for the prefix and dispatch its set() operation to remove
* any associated extended attribute.
*/
int
generic_removexattr(struct dentry *dentry, const char *name)
{
const struct xattr_handler *handler;
handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (IS_ERR(handler))
return PTR_ERR(handler);
return handler->set(handler, dentry, name, NULL, 0, XATTR_REPLACE);
}
EXPORT_SYMBOL(generic_getxattr);
EXPORT_SYMBOL(generic_listxattr);
EXPORT_SYMBOL(generic_setxattr);
EXPORT_SYMBOL(generic_removexattr);
/**
* xattr_full_name - Compute full attribute name from suffix
*
* @handler: handler of the xattr_handler operation
* @name: name passed to the xattr_handler operation
*
* The get and set xattr handler operations are called with the remainder of
* the attribute name after skipping the handler's prefix: for example, "foo"
* is passed to the get operation of a handler with prefix "user." to get
* attribute "user.foo". The full name is still "there" in the name though.
*
* Note: the list xattr handler operation when called from the vfs is passed a
* NULL name; some file systems use this operation internally, with varying
* semantics.
*/
const char *xattr_full_name(const struct xattr_handler *handler,
const char *name)
{
size_t prefix_len = strlen(xattr_prefix(handler));
return name - prefix_len;
}
EXPORT_SYMBOL(xattr_full_name);
/*
* Allocate new xattr and copy in the value; but leave the name to callers.
*/
struct simple_xattr *simple_xattr_alloc(const void *value, size_t size)
{
struct simple_xattr *new_xattr;
size_t len;
/* wrap around? */
len = sizeof(*new_xattr) + size;
if (len < sizeof(*new_xattr))
return NULL;
new_xattr = kmalloc(len, GFP_KERNEL);
if (!new_xattr)
return NULL;
new_xattr->size = size;
memcpy(new_xattr->value, value, size);
return new_xattr;
}
/*
* xattr GET operation for in-memory/pseudo filesystems
*/
int simple_xattr_get(struct simple_xattrs *xattrs, const char *name,
void *buffer, size_t size)
{
struct simple_xattr *xattr;
int ret = -ENODATA;
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
if (strcmp(name, xattr->name))
continue;
ret = xattr->size;
if (buffer) {
if (size < xattr->size)
ret = -ERANGE;
else
memcpy(buffer, xattr->value, xattr->size);
}
break;
}
spin_unlock(&xattrs->lock);
return ret;
}
/**
* simple_xattr_set - xattr SET operation for in-memory/pseudo filesystems
* @xattrs: target simple_xattr list
* @name: name of the extended attribute
* @value: value of the xattr. If %NULL, will remove the attribute.
* @size: size of the new xattr
* @flags: %XATTR_{CREATE|REPLACE}
*
* %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails
* with -EEXIST. If %XATTR_REPLACE is set, the xattr should exist;
* otherwise, fails with -ENODATA.
*
* Returns 0 on success, -errno on failure.
*/
int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,
const void *value, size_t size, int flags)
{
struct simple_xattr *xattr;
struct simple_xattr *new_xattr = NULL;
int err = 0;
/* value == NULL means remove */
if (value) {
new_xattr = simple_xattr_alloc(value, size);
if (!new_xattr)
return -ENOMEM;
new_xattr->name = kstrdup(name, GFP_KERNEL);
if (!new_xattr->name) {
kfree(new_xattr);
return -ENOMEM;
}
}
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
if (!strcmp(name, xattr->name)) {
if (flags & XATTR_CREATE) {
xattr = new_xattr;
err = -EEXIST;
} else if (new_xattr) {
list_replace(&xattr->list, &new_xattr->list);
} else {
list_del(&xattr->list);
}
goto out;
}
}
if (flags & XATTR_REPLACE) {
xattr = new_xattr;
err = -ENODATA;
} else {
list_add(&new_xattr->list, &xattrs->head);
xattr = NULL;
}
out:
spin_unlock(&xattrs->lock);
if (xattr) {
kfree(xattr->name);
kfree(xattr);
}
return err;
}
static bool xattr_is_trusted(const char *name)
{
return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
static int xattr_list_one(char **buffer, ssize_t *remaining_size,
const char *name)
{
size_t len = strlen(name) + 1;
if (*buffer) {
if (*remaining_size < len)
return -ERANGE;
memcpy(*buffer, name, len);
*buffer += len;
}
*remaining_size -= len;
return 0;
}
/*
* xattr LIST operation for in-memory/pseudo filesystems
*/
ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
char *buffer, size_t size)
{
bool trusted = capable(CAP_SYS_ADMIN);
struct simple_xattr *xattr;
ssize_t remaining_size = size;
int err = 0;
#ifdef CONFIG_FS_POSIX_ACL
if (inode->i_acl) {
err = xattr_list_one(&buffer, &remaining_size,
XATTR_NAME_POSIX_ACL_ACCESS);
if (err)
return err;
}
if (inode->i_default_acl) {
err = xattr_list_one(&buffer, &remaining_size,
XATTR_NAME_POSIX_ACL_DEFAULT);
if (err)
return err;
}
#endif
spin_lock(&xattrs->lock);
list_for_each_entry(xattr, &xattrs->head, list) {
/* skip "trusted." attributes for unprivileged callers */
if (!trusted && xattr_is_trusted(xattr->name))
continue;
err = xattr_list_one(&buffer, &remaining_size, xattr->name);
if (err)
break;
}
spin_unlock(&xattrs->lock);
return err ? err : size - remaining_size;
}
/*
* Adds an extended attribute to the list
*/
void simple_xattr_list_add(struct simple_xattrs *xattrs,
struct simple_xattr *new_xattr)
{
spin_lock(&xattrs->lock);
list_add(&new_xattr->list, &xattrs->head);
spin_unlock(&xattrs->lock);
}