linux/fs/xfs/xfs_xattr.c

349 lines
8.4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2008 Christoph Hellwig.
* Portions Copyright (C) 2000-2008 Silicon Graphics, Inc.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_da_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
#include "xfs_acl.h"
#include "xfs_log.h"
#include "xfs_xattr.h"
#include "xfs_quota.h"
#include <linux/posix_acl_xattr.h>
/*
* Get permission to use log-assisted atomic exchange of file extents.
xfs: only clear log incompat flags at clean unmount While reviewing the online fsck patchset, someone spied the xfs_swapext_can_use_without_log_assistance function and wondered why we go through this inverted-bitmask dance to avoid setting the XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT feature. (The same principles apply to the logged extended attribute update feature bit in the since-merged LARP series.) The reason for this dance is that xfs_add_incompat_log_feature is an expensive operation -- it forces the log, pushes the AIL, and then if nobody's beaten us to it, sets the feature bit and issues a synchronous write of the primary superblock. That could be a one-time cost amortized over the life of the filesystem, but the log quiesce and cover operations call xfs_clear_incompat_log_features to remove feature bits opportunistically. On a moderately loaded filesystem this leads to us cycling those bits on and off over and over, which hurts performance. Why do we clear the log incompat bits? Back in ~2020 I think Dave and I had a conversation on IRC[2] about what the log incompat bits represent. IIRC in that conversation we decided that the log incompat bits protect unrecovered log items so that old kernels won't try to recover them and barf. Since a clean log has no protected log items, we could clear the bits at cover/quiesce time. As Dave Chinner pointed out in the thread, clearing log incompat bits at unmount time has positive effects for golden root disk image generator setups, since the generator could be running a newer kernel than what gets written to the golden image -- if there are log incompat fields set in the golden image that was generated by a newer kernel/OS image builder then the provisioning host cannot mount the filesystem even though the log is clean and recovery is unnecessary to mount the filesystem. Given that it's expensive to set log incompat bits, we really only want to do that once per bit per mount. Therefore, I propose that we only clear log incompat bits as part of writing a clean unmount record. Do this by adding an operational state flag to the xfs mount that guards whether or not the feature bit clearing can actually take place. This eliminates the l_incompat_users rwsem that we use to protect a log cleaning operation from clearing a feature bit that a frontend thread is trying to set -- this lock adds another way to fail w.r.t. locking. For the swapext series, I shard that into multiple locks just to work around the lockdep complaints, and that's fugly. Link: https://lore.kernel.org/linux-xfs/20240131230043.GA6180@frogsfrogsfrogs/ Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2024-04-15 21:54:06 +00:00
* Callers must not be running any transactions or hold any ILOCKs.
*/
static inline int
xfs_attr_grab_log_assist(
struct xfs_mount *mp)
{
int error = 0;
xfs: only clear log incompat flags at clean unmount While reviewing the online fsck patchset, someone spied the xfs_swapext_can_use_without_log_assistance function and wondered why we go through this inverted-bitmask dance to avoid setting the XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT feature. (The same principles apply to the logged extended attribute update feature bit in the since-merged LARP series.) The reason for this dance is that xfs_add_incompat_log_feature is an expensive operation -- it forces the log, pushes the AIL, and then if nobody's beaten us to it, sets the feature bit and issues a synchronous write of the primary superblock. That could be a one-time cost amortized over the life of the filesystem, but the log quiesce and cover operations call xfs_clear_incompat_log_features to remove feature bits opportunistically. On a moderately loaded filesystem this leads to us cycling those bits on and off over and over, which hurts performance. Why do we clear the log incompat bits? Back in ~2020 I think Dave and I had a conversation on IRC[2] about what the log incompat bits represent. IIRC in that conversation we decided that the log incompat bits protect unrecovered log items so that old kernels won't try to recover them and barf. Since a clean log has no protected log items, we could clear the bits at cover/quiesce time. As Dave Chinner pointed out in the thread, clearing log incompat bits at unmount time has positive effects for golden root disk image generator setups, since the generator could be running a newer kernel than what gets written to the golden image -- if there are log incompat fields set in the golden image that was generated by a newer kernel/OS image builder then the provisioning host cannot mount the filesystem even though the log is clean and recovery is unnecessary to mount the filesystem. Given that it's expensive to set log incompat bits, we really only want to do that once per bit per mount. Therefore, I propose that we only clear log incompat bits as part of writing a clean unmount record. Do this by adding an operational state flag to the xfs mount that guards whether or not the feature bit clearing can actually take place. This eliminates the l_incompat_users rwsem that we use to protect a log cleaning operation from clearing a feature bit that a frontend thread is trying to set -- this lock adds another way to fail w.r.t. locking. For the swapext series, I shard that into multiple locks just to work around the lockdep complaints, and that's fugly. Link: https://lore.kernel.org/linux-xfs/20240131230043.GA6180@frogsfrogsfrogs/ Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2024-04-15 21:54:06 +00:00
/* xattr update log intent items are already enabled */
if (xfs_is_using_logged_xattrs(mp))
return 0;
/*
* Check if the filesystem featureset is new enough to set this log
* incompat feature bit. Strictly speaking, the minimum requirement is
* a V5 filesystem for the superblock field, but we'll require rmap
* or reflink to avoid having to deal with really old kernels.
*/
xfs: only clear log incompat flags at clean unmount While reviewing the online fsck patchset, someone spied the xfs_swapext_can_use_without_log_assistance function and wondered why we go through this inverted-bitmask dance to avoid setting the XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT feature. (The same principles apply to the logged extended attribute update feature bit in the since-merged LARP series.) The reason for this dance is that xfs_add_incompat_log_feature is an expensive operation -- it forces the log, pushes the AIL, and then if nobody's beaten us to it, sets the feature bit and issues a synchronous write of the primary superblock. That could be a one-time cost amortized over the life of the filesystem, but the log quiesce and cover operations call xfs_clear_incompat_log_features to remove feature bits opportunistically. On a moderately loaded filesystem this leads to us cycling those bits on and off over and over, which hurts performance. Why do we clear the log incompat bits? Back in ~2020 I think Dave and I had a conversation on IRC[2] about what the log incompat bits represent. IIRC in that conversation we decided that the log incompat bits protect unrecovered log items so that old kernels won't try to recover them and barf. Since a clean log has no protected log items, we could clear the bits at cover/quiesce time. As Dave Chinner pointed out in the thread, clearing log incompat bits at unmount time has positive effects for golden root disk image generator setups, since the generator could be running a newer kernel than what gets written to the golden image -- if there are log incompat fields set in the golden image that was generated by a newer kernel/OS image builder then the provisioning host cannot mount the filesystem even though the log is clean and recovery is unnecessary to mount the filesystem. Given that it's expensive to set log incompat bits, we really only want to do that once per bit per mount. Therefore, I propose that we only clear log incompat bits as part of writing a clean unmount record. Do this by adding an operational state flag to the xfs mount that guards whether or not the feature bit clearing can actually take place. This eliminates the l_incompat_users rwsem that we use to protect a log cleaning operation from clearing a feature bit that a frontend thread is trying to set -- this lock adds another way to fail w.r.t. locking. For the swapext series, I shard that into multiple locks just to work around the lockdep complaints, and that's fugly. Link: https://lore.kernel.org/linux-xfs/20240131230043.GA6180@frogsfrogsfrogs/ Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2024-04-15 21:54:06 +00:00
if (!xfs_has_reflink(mp) && !xfs_has_rmapbt(mp))
return -EOPNOTSUPP;
/* Enable log-assisted xattrs. */
error = xfs_add_incompat_log_feature(mp,
XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);
if (error)
xfs: only clear log incompat flags at clean unmount While reviewing the online fsck patchset, someone spied the xfs_swapext_can_use_without_log_assistance function and wondered why we go through this inverted-bitmask dance to avoid setting the XFS_SB_FEAT_INCOMPAT_LOG_SWAPEXT feature. (The same principles apply to the logged extended attribute update feature bit in the since-merged LARP series.) The reason for this dance is that xfs_add_incompat_log_feature is an expensive operation -- it forces the log, pushes the AIL, and then if nobody's beaten us to it, sets the feature bit and issues a synchronous write of the primary superblock. That could be a one-time cost amortized over the life of the filesystem, but the log quiesce and cover operations call xfs_clear_incompat_log_features to remove feature bits opportunistically. On a moderately loaded filesystem this leads to us cycling those bits on and off over and over, which hurts performance. Why do we clear the log incompat bits? Back in ~2020 I think Dave and I had a conversation on IRC[2] about what the log incompat bits represent. IIRC in that conversation we decided that the log incompat bits protect unrecovered log items so that old kernels won't try to recover them and barf. Since a clean log has no protected log items, we could clear the bits at cover/quiesce time. As Dave Chinner pointed out in the thread, clearing log incompat bits at unmount time has positive effects for golden root disk image generator setups, since the generator could be running a newer kernel than what gets written to the golden image -- if there are log incompat fields set in the golden image that was generated by a newer kernel/OS image builder then the provisioning host cannot mount the filesystem even though the log is clean and recovery is unnecessary to mount the filesystem. Given that it's expensive to set log incompat bits, we really only want to do that once per bit per mount. Therefore, I propose that we only clear log incompat bits as part of writing a clean unmount record. Do this by adding an operational state flag to the xfs mount that guards whether or not the feature bit clearing can actually take place. This eliminates the l_incompat_users rwsem that we use to protect a log cleaning operation from clearing a feature bit that a frontend thread is trying to set -- this lock adds another way to fail w.r.t. locking. For the swapext series, I shard that into multiple locks just to work around the lockdep complaints, and that's fugly. Link: https://lore.kernel.org/linux-xfs/20240131230043.GA6180@frogsfrogsfrogs/ Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Dave Chinner <dchinner@redhat.com>
2024-04-15 21:54:06 +00:00
return error;
xfs_set_using_logged_xattrs(mp);
xfs_warn_mount(mp, XFS_OPSTATE_WARNED_LARP,
"EXPERIMENTAL logged extended attributes feature in use. Use at your own risk!");
return 0;
}
xfs: fix TOCTOU race involving the new logged xattrs control knob I found a race involving the larp control knob, aka the debugging knob that lets developers enable logging of extended attribute updates: Thread 1 Thread 2 echo 0 > /sys/fs/xfs/debug/larp setxattr(REPLACE) xfs_has_larp (returns false) xfs_attr_set echo 1 > /sys/fs/xfs/debug/larp xfs_attr_defer_replace xfs_attr_init_replace_state xfs_has_larp (returns true) xfs_attr_init_remove_state <oops, wrong DAS state!> This isn't a particularly severe problem right now because xattr logging is only enabled when CONFIG_XFS_DEBUG=y, and developers *should* know what they're doing. However, the eventual intent is that callers should be able to ask for the assistance of the log in persisting xattr updates. This capability might not be required for /all/ callers, which means that dynamic control must work correctly. Once an xattr update has decided whether or not to use logged xattrs, it needs to stay in that mode until the end of the operation regardless of what subsequent parallel operations might do. Therefore, it is an error to continue sampling xfs_globals.larp once xfs_attr_change has made a decision about larp, and it was not correct for me to have told Allison that ->create_intent functions can sample the global log incompat feature bitfield to decide to elide a log item. Instead, create a new op flag for the xfs_da_args structure, and convert all other callers of xfs_has_larp and xfs_sb_version_haslogxattrs within the attr update state machine to look for the operations flag. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
2022-06-06 01:51:22 +00:00
static inline bool
xfs_attr_want_log_assist(
struct xfs_mount *mp)
{
#ifdef DEBUG
/* Logged xattrs require a V5 super for log_incompat */
return xfs_has_crc(mp) && xfs_globals.larp;
#else
return false;
#endif
}
/*
* Set or remove an xattr, having grabbed the appropriate logging resources
* prior to calling libxfs. Callers of this function are only required to
* initialize the inode, attr_filter, name, namelen, value, and valuelen fields
* of @args.
*/
int
xfs_attr_change(
struct xfs_da_args *args,
enum xfs_attr_update op)
{
struct xfs_mount *mp = args->dp->i_mount;
int error;
if (xfs_is_shutdown(mp))
return -EIO;
error = xfs_qm_dqattach(args->dp);
if (error)
return error;
/*
* We have no control over the attribute names that userspace passes us
* to remove, so we have to allow the name lookup prior to attribute
* removal to fail as well.
*/
args->op_flags = XFS_DA_OP_OKNOENT;
xfs: fix TOCTOU race involving the new logged xattrs control knob I found a race involving the larp control knob, aka the debugging knob that lets developers enable logging of extended attribute updates: Thread 1 Thread 2 echo 0 > /sys/fs/xfs/debug/larp setxattr(REPLACE) xfs_has_larp (returns false) xfs_attr_set echo 1 > /sys/fs/xfs/debug/larp xfs_attr_defer_replace xfs_attr_init_replace_state xfs_has_larp (returns true) xfs_attr_init_remove_state <oops, wrong DAS state!> This isn't a particularly severe problem right now because xattr logging is only enabled when CONFIG_XFS_DEBUG=y, and developers *should* know what they're doing. However, the eventual intent is that callers should be able to ask for the assistance of the log in persisting xattr updates. This capability might not be required for /all/ callers, which means that dynamic control must work correctly. Once an xattr update has decided whether or not to use logged xattrs, it needs to stay in that mode until the end of the operation regardless of what subsequent parallel operations might do. Therefore, it is an error to continue sampling xfs_globals.larp once xfs_attr_change has made a decision about larp, and it was not correct for me to have told Allison that ->create_intent functions can sample the global log incompat feature bitfield to decide to elide a log item. Instead, create a new op flag for the xfs_da_args structure, and convert all other callers of xfs_has_larp and xfs_sb_version_haslogxattrs within the attr update state machine to look for the operations flag. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
2022-06-06 01:51:22 +00:00
if (xfs_attr_want_log_assist(mp)) {
error = xfs_attr_grab_log_assist(mp);
if (error)
return error;
xfs: fix TOCTOU race involving the new logged xattrs control knob I found a race involving the larp control knob, aka the debugging knob that lets developers enable logging of extended attribute updates: Thread 1 Thread 2 echo 0 > /sys/fs/xfs/debug/larp setxattr(REPLACE) xfs_has_larp (returns false) xfs_attr_set echo 1 > /sys/fs/xfs/debug/larp xfs_attr_defer_replace xfs_attr_init_replace_state xfs_has_larp (returns true) xfs_attr_init_remove_state <oops, wrong DAS state!> This isn't a particularly severe problem right now because xattr logging is only enabled when CONFIG_XFS_DEBUG=y, and developers *should* know what they're doing. However, the eventual intent is that callers should be able to ask for the assistance of the log in persisting xattr updates. This capability might not be required for /all/ callers, which means that dynamic control must work correctly. Once an xattr update has decided whether or not to use logged xattrs, it needs to stay in that mode until the end of the operation regardless of what subsequent parallel operations might do. Therefore, it is an error to continue sampling xfs_globals.larp once xfs_attr_change has made a decision about larp, and it was not correct for me to have told Allison that ->create_intent functions can sample the global log incompat feature bitfield to decide to elide a log item. Instead, create a new op flag for the xfs_da_args structure, and convert all other callers of xfs_has_larp and xfs_sb_version_haslogxattrs within the attr update state machine to look for the operations flag. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
2022-06-06 01:51:22 +00:00
args->op_flags |= XFS_DA_OP_LOGGED;
}
args->owner = args->dp->i_ino;
args->geo = mp->m_attr_geo;
args->whichfork = XFS_ATTR_FORK;
xfs_attr_sethash(args);
/*
* Some xattrs must be resistant to allocation failure at ENOSPC, e.g.
* creating an inode with ACLs or security attributes requires the
* allocation of the xattr holding that information to succeed. Hence
* we allow xattrs in the VFS TRUSTED, SYSTEM, POSIX_ACL and SECURITY
* (LSM xattr) namespaces to dip into the reserve block pool to allow
* manipulation of these xattrs when at ENOSPC. These VFS xattr
* namespaces translate to the XFS_ATTR_ROOT and XFS_ATTR_SECURE on-disk
* namespaces.
*
* For most of these cases, these special xattrs will fit in the inode
* itself and so consume no extra space or only require temporary extra
* space while an overwrite is being made. Hence the use of the reserved
* pool is largely to avoid the worst case reservation from preventing
* the xattr from being created at ENOSPC.
*/
return xfs_attr_set(args, op,
args->attr_filter & (XFS_ATTR_ROOT | XFS_ATTR_SECURE));
}
static int
xfs_xattr_get(const struct xattr_handler *handler, struct dentry *unused,
struct inode *inode, const char *name, void *value, size_t size)
{
struct xfs_da_args args = {
.dp = XFS_I(inode),
.attr_filter = handler->flags,
.name = name,
.namelen = strlen(name),
.value = value,
.valuelen = size,
};
int error;
if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
return -EIO;
error = xfs_attr_get(&args);
if (error)
return error;
return args.valuelen;
}
static inline enum xfs_attr_update
xfs_xattr_flags_to_op(
int flags,
const void *value)
{
if (!value)
return XFS_ATTRUPDATE_REMOVE;
if (flags & XATTR_CREATE)
return XFS_ATTRUPDATE_CREATE;
if (flags & XATTR_REPLACE)
return XFS_ATTRUPDATE_REPLACE;
return XFS_ATTRUPDATE_UPSERT;
}
static int
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:27 +00:00
xfs_xattr_set(const struct xattr_handler *handler,
struct mnt_idmap *idmap, struct dentry *unused,
acl: handle idmapped mounts The posix acl permission checking helpers determine whether a caller is privileged over an inode according to the acls associated with the inode. Add helpers that make it possible to handle acls on idmapped mounts. The vfs and the filesystems targeted by this first iteration make use of posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to translate basic posix access and default permissions such as the ACL_USER and ACL_GROUP type according to the initial user namespace (or the superblock's user namespace) to and from the caller's current user namespace. Adapt these two helpers to handle idmapped mounts whereby we either map from or into the mount's user namespace depending on in which direction we're translating. Similarly, cap_convert_nscap() is used by the vfs to translate user namespace and non-user namespace aware filesystem capabilities from the superblock's user namespace to the caller's user namespace. Enable it to handle idmapped mounts by accounting for the mount's user namespace. In addition the fileystems targeted in the first iteration of this patch series make use of the posix_acl_chmod() and, posix_acl_update_mode() helpers. Both helpers perform permission checks on the target inode. Let them handle idmapped mounts. These two helpers are called when posix acls are set by the respective filesystems to handle this case we extend the ->set() method to take an additional user namespace argument to pass the mount's user namespace down. Link: https://lore.kernel.org/r/20210121131959.646623-9-christian.brauner@ubuntu.com Cc: Christoph Hellwig <hch@lst.de> Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:27 +00:00
struct inode *inode, const char *name, const void *value,
size_t size, int flags)
{
struct xfs_da_args args = {
.dp = XFS_I(inode),
.attr_filter = handler->flags,
.name = name,
.namelen = strlen(name),
.value = (void *)value,
.valuelen = size,
};
xfs: invalidate cached acl if set directly via xattr ACLs are stored as extended attributes of the inode to which they apply. XFS converts the standard "system.posix_acl_[access|default]" attribute names used to control ACLs to "trusted.SGI_ACL_[FILE|DEFAULT]" as stored on-disk. These xattrs are directly exposed in on-disk format via getxattr/setxattr, without any ACL aware code in the path to perform validation, etc. This is partly historical and supports backup/restore applications such as xfsdump to back up and restore the binary blob that represents ACLs as-is. Andreas reports that the ACLs observed via the getfacl interface is not consistent when ACLs are set directly via the setxattr path. This occurs because the ACLs are cached in-core against the inode and the xattr path has no knowledge that the operation relates to ACLs. Update the xattr set codepath to trap writes of the special XFS ACL attributes and invalidate the associated cached ACL when this occurs. This ensures that the correct ACLs are used on a subsequent operation through the actual ACL interface. Note that this does not update or add support for setting the ACL xattrs directly beyond the restore use case that requires a correctly formatted binary blob and to restore a consistent i_mode at the same time. It is still possible for a root user to set an invalid or inconsistent (with i_mode) ACL blob on-disk and potentially cause corruption. [ With fixes from Andreas Gruenbacher. ] Reported-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:40:59 +00:00
int error;
error = xfs_attr_change(&args, xfs_xattr_flags_to_op(flags, value));
if (!error && (handler->flags & XFS_ATTR_ROOT))
xfs_forget_acl(inode, name);
xfs: invalidate cached acl if set directly via xattr ACLs are stored as extended attributes of the inode to which they apply. XFS converts the standard "system.posix_acl_[access|default]" attribute names used to control ACLs to "trusted.SGI_ACL_[FILE|DEFAULT]" as stored on-disk. These xattrs are directly exposed in on-disk format via getxattr/setxattr, without any ACL aware code in the path to perform validation, etc. This is partly historical and supports backup/restore applications such as xfsdump to back up and restore the binary blob that represents ACLs as-is. Andreas reports that the ACLs observed via the getfacl interface is not consistent when ACLs are set directly via the setxattr path. This occurs because the ACLs are cached in-core against the inode and the xattr path has no knowledge that the operation relates to ACLs. Update the xattr set codepath to trap writes of the special XFS ACL attributes and invalidate the associated cached ACL when this occurs. This ensures that the correct ACLs are used on a subsequent operation through the actual ACL interface. Note that this does not update or add support for setting the ACL xattrs directly beyond the restore use case that requires a correctly formatted binary blob and to restore a consistent i_mode at the same time. It is still possible for a root user to set an invalid or inconsistent (with i_mode) ACL blob on-disk and potentially cause corruption. [ With fixes from Andreas Gruenbacher. ] Reported-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-11-03 01:40:59 +00:00
return error;
}
static const struct xattr_handler xfs_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
.flags = 0, /* no flags implies user namespace */
.get = xfs_xattr_get,
.set = xfs_xattr_set,
};
static const struct xattr_handler xfs_xattr_trusted_handler = {
.prefix = XATTR_TRUSTED_PREFIX,
.flags = XFS_ATTR_ROOT,
.get = xfs_xattr_get,
.set = xfs_xattr_set,
};
static const struct xattr_handler xfs_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.flags = XFS_ATTR_SECURE,
.get = xfs_xattr_get,
.set = xfs_xattr_set,
};
const struct xattr_handler * const xfs_xattr_handlers[] = {
&xfs_xattr_user_handler,
&xfs_xattr_trusted_handler,
&xfs_xattr_security_handler,
NULL
};
static void
__xfs_xattr_put_listent(
struct xfs_attr_list_context *context,
char *prefix,
int prefix_len,
unsigned char *name,
int namelen)
{
char *offset;
int arraytop;
if (context->count < 0 || context->seen_enough)
return;
if (!context->buffer)
goto compute_size;
arraytop = context->count + prefix_len + namelen + 1;
if (arraytop > context->firstu) {
context->count = -1; /* insufficient space */
context->seen_enough = 1;
return;
}
offset = context->buffer + context->count;
memcpy(offset, prefix, prefix_len);
offset += prefix_len;
strncpy(offset, (char *)name, namelen); /* real name */
offset += namelen;
*offset = '\0';
compute_size:
context->count += prefix_len + namelen + 1;
return;
}
static void
xfs_xattr_put_listent(
struct xfs_attr_list_context *context,
int flags,
unsigned char *name,
int namelen,
void *value,
int valuelen)
{
char *prefix;
int prefix_len;
ASSERT(context->count >= 0);
/* Don't expose private xattr namespaces. */
if (flags & XFS_ATTR_PRIVATE_NSP_MASK)
return;
if (flags & XFS_ATTR_ROOT) {
#ifdef CONFIG_XFS_POSIX_ACL
if (namelen == SGI_ACL_FILE_SIZE &&
strncmp(name, SGI_ACL_FILE,
SGI_ACL_FILE_SIZE) == 0) {
__xfs_xattr_put_listent(
context, XATTR_SYSTEM_PREFIX,
XATTR_SYSTEM_PREFIX_LEN,
XATTR_POSIX_ACL_ACCESS,
strlen(XATTR_POSIX_ACL_ACCESS));
} else if (namelen == SGI_ACL_DEFAULT_SIZE &&
strncmp(name, SGI_ACL_DEFAULT,
SGI_ACL_DEFAULT_SIZE) == 0) {
__xfs_xattr_put_listent(
context, XATTR_SYSTEM_PREFIX,
XATTR_SYSTEM_PREFIX_LEN,
XATTR_POSIX_ACL_DEFAULT,
strlen(XATTR_POSIX_ACL_DEFAULT));
}
#endif
/*
* Only show root namespace entries if we are actually allowed to
* see them.
*/
if (!capable(CAP_SYS_ADMIN))
return;
prefix = XATTR_TRUSTED_PREFIX;
prefix_len = XATTR_TRUSTED_PREFIX_LEN;
} else if (flags & XFS_ATTR_SECURE) {
prefix = XATTR_SECURITY_PREFIX;
prefix_len = XATTR_SECURITY_PREFIX_LEN;
} else {
prefix = XATTR_USER_PREFIX;
prefix_len = XATTR_USER_PREFIX_LEN;
}
__xfs_xattr_put_listent(context, prefix, prefix_len, name,
namelen);
return;
}
ssize_t
xfs_vn_listxattr(
struct dentry *dentry,
char *data,
size_t size)
{
struct xfs_attr_list_context context;
struct inode *inode = d_inode(dentry);
int error;
if (xfs_ifork_zapped(XFS_I(inode), XFS_ATTR_FORK))
return -EIO;
/*
* First read the regular on-disk attributes.
*/
memset(&context, 0, sizeof(context));
context.dp = XFS_I(inode);
context.resynch = 1;
context.buffer = size ? data : NULL;
context.bufsize = size;
context.firstu = context.bufsize;
context.put_listent = xfs_xattr_put_listent;
error = xfs_attr_list(&context);
if (error)
return error;
if (context.count < 0)
return -ERANGE;
return context.count;
}