linux-stable/fs/xfs/xfs_acl.c

295 lines
6.4 KiB
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2008, Christoph Hellwig
* All Rights Reserved.
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_attr.h"
xfs: event tracing support Convert the old xfs tracing support that could only be used with the out of tree kdb and xfsidbg patches to use the generic event tracer. To use it make sure CONFIG_EVENT_TRACING is enabled and then enable all xfs trace channels by: echo 1 > /sys/kernel/debug/tracing/events/xfs/enable or alternatively enable single events by just doing the same in one event subdirectory, e.g. echo 1 > /sys/kernel/debug/tracing/events/xfs/xfs_ihold/enable or set more complex filters, etc. In Documentation/trace/events.txt all this is desctribed in more detail. To reads the events do a cat /sys/kernel/debug/tracing/trace Compared to the last posting this patch converts the tracing mostly to the one tracepoint per callsite model that other users of the new tracing facility also employ. This allows a very fine-grained control of the tracing, a cleaner output of the traces and also enables the perf tool to use each tracepoint as a virtual performance counter, allowing us to e.g. count how often certain workloads git various spots in XFS. Take a look at http://lwn.net/Articles/346470/ for some examples. Also the btree tracing isn't included at all yet, as it will require additional core tracing features not in mainline yet, I plan to deliver it later. And the really nice thing about this patch is that it actually removes many lines of code while adding this nice functionality: fs/xfs/Makefile | 8 fs/xfs/linux-2.6/xfs_acl.c | 1 fs/xfs/linux-2.6/xfs_aops.c | 52 - fs/xfs/linux-2.6/xfs_aops.h | 2 fs/xfs/linux-2.6/xfs_buf.c | 117 +-- fs/xfs/linux-2.6/xfs_buf.h | 33 fs/xfs/linux-2.6/xfs_fs_subr.c | 3 fs/xfs/linux-2.6/xfs_ioctl.c | 1 fs/xfs/linux-2.6/xfs_ioctl32.c | 1 fs/xfs/linux-2.6/xfs_iops.c | 1 fs/xfs/linux-2.6/xfs_linux.h | 1 fs/xfs/linux-2.6/xfs_lrw.c | 87 -- fs/xfs/linux-2.6/xfs_lrw.h | 45 - fs/xfs/linux-2.6/xfs_super.c | 104 --- fs/xfs/linux-2.6/xfs_super.h | 7 fs/xfs/linux-2.6/xfs_sync.c | 1 fs/xfs/linux-2.6/xfs_trace.c | 75 ++ fs/xfs/linux-2.6/xfs_trace.h | 1369 +++++++++++++++++++++++++++++++++++++++++ fs/xfs/linux-2.6/xfs_vnode.h | 4 fs/xfs/quota/xfs_dquot.c | 110 --- fs/xfs/quota/xfs_dquot.h | 21 fs/xfs/quota/xfs_qm.c | 40 - fs/xfs/quota/xfs_qm_syscalls.c | 4 fs/xfs/support/ktrace.c | 323 --------- fs/xfs/support/ktrace.h | 85 -- fs/xfs/xfs.h | 16 fs/xfs/xfs_ag.h | 14 fs/xfs/xfs_alloc.c | 230 +----- fs/xfs/xfs_alloc.h | 27 fs/xfs/xfs_alloc_btree.c | 1 fs/xfs/xfs_attr.c | 107 --- fs/xfs/xfs_attr.h | 10 fs/xfs/xfs_attr_leaf.c | 14 fs/xfs/xfs_attr_sf.h | 40 - fs/xfs/xfs_bmap.c | 507 +++------------ fs/xfs/xfs_bmap.h | 49 - fs/xfs/xfs_bmap_btree.c | 6 fs/xfs/xfs_btree.c | 5 fs/xfs/xfs_btree_trace.h | 17 fs/xfs/xfs_buf_item.c | 87 -- fs/xfs/xfs_buf_item.h | 20 fs/xfs/xfs_da_btree.c | 3 fs/xfs/xfs_da_btree.h | 7 fs/xfs/xfs_dfrag.c | 2 fs/xfs/xfs_dir2.c | 8 fs/xfs/xfs_dir2_block.c | 20 fs/xfs/xfs_dir2_leaf.c | 21 fs/xfs/xfs_dir2_node.c | 27 fs/xfs/xfs_dir2_sf.c | 26 fs/xfs/xfs_dir2_trace.c | 216 ------ fs/xfs/xfs_dir2_trace.h | 72 -- fs/xfs/xfs_filestream.c | 8 fs/xfs/xfs_fsops.c | 2 fs/xfs/xfs_iget.c | 111 --- fs/xfs/xfs_inode.c | 67 -- fs/xfs/xfs_inode.h | 76 -- fs/xfs/xfs_inode_item.c | 5 fs/xfs/xfs_iomap.c | 85 -- fs/xfs/xfs_iomap.h | 8 fs/xfs/xfs_log.c | 181 +---- fs/xfs/xfs_log_priv.h | 20 fs/xfs/xfs_log_recover.c | 1 fs/xfs/xfs_mount.c | 2 fs/xfs/xfs_quota.h | 8 fs/xfs/xfs_rename.c | 1 fs/xfs/xfs_rtalloc.c | 1 fs/xfs/xfs_rw.c | 3 fs/xfs/xfs_trans.h | 47 + fs/xfs/xfs_trans_buf.c | 62 - fs/xfs/xfs_vnodeops.c | 8 70 files changed, 2151 insertions(+), 2592 deletions(-) Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Alex Elder <aelder@sgi.com>
2009-12-14 23:14:59 +00:00
#include "xfs_trace.h"
#include "xfs_error.h"
#include "xfs_acl.h"
#include "xfs_trans.h"
#include "xfs_xattr.h"
#include <linux/posix_acl_xattr.h>
/*
* Locking scheme:
* - all ACL updates are protected by inode->i_mutex, which is taken before
* calling into this file.
*/
STATIC struct posix_acl *
xfs_acl_from_disk(
struct xfs_mount *mp,
const struct xfs_acl *aclp,
int len,
int max_entries)
{
struct posix_acl_entry *acl_e;
struct posix_acl *acl;
const struct xfs_acl_entry *ace;
unsigned int count, i;
if (len < sizeof(*aclp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp,
len);
return ERR_PTR(-EFSCORRUPTED);
}
count = be32_to_cpu(aclp->acl_cnt);
if (count > max_entries || XFS_ACL_SIZE(count) != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, aclp,
len);
return ERR_PTR(-EFSCORRUPTED);
}
acl = posix_acl_alloc(count, GFP_KERNEL);
if (!acl)
return ERR_PTR(-ENOMEM);
for (i = 0; i < count; i++) {
acl_e = &acl->a_entries[i];
ace = &aclp->acl_entry[i];
/*
* The tag is 32 bits on disk and 16 bits in core.
*
* Because every access to it goes through the core
* format first this is not a problem.
*/
acl_e->e_tag = be32_to_cpu(ace->ae_tag);
acl_e->e_perm = be16_to_cpu(ace->ae_perm);
switch (acl_e->e_tag) {
case ACL_USER:
acl_e->e_uid = make_kuid(&init_user_ns,
be32_to_cpu(ace->ae_id));
break;
case ACL_GROUP:
acl_e->e_gid = make_kgid(&init_user_ns,
be32_to_cpu(ace->ae_id));
break;
case ACL_USER_OBJ:
case ACL_GROUP_OBJ:
case ACL_MASK:
case ACL_OTHER:
break;
default:
goto fail;
}
}
return acl;
fail:
posix_acl_release(acl);
return ERR_PTR(-EINVAL);
}
STATIC void
xfs_acl_to_disk(struct xfs_acl *aclp, const struct posix_acl *acl)
{
const struct posix_acl_entry *acl_e;
struct xfs_acl_entry *ace;
int i;
aclp->acl_cnt = cpu_to_be32(acl->a_count);
for (i = 0; i < acl->a_count; i++) {
ace = &aclp->acl_entry[i];
acl_e = &acl->a_entries[i];
ace->ae_tag = cpu_to_be32(acl_e->e_tag);
switch (acl_e->e_tag) {
case ACL_USER:
ace->ae_id = cpu_to_be32(
from_kuid(&init_user_ns, acl_e->e_uid));
break;
case ACL_GROUP:
ace->ae_id = cpu_to_be32(
from_kgid(&init_user_ns, acl_e->e_gid));
break;
default:
ace->ae_id = cpu_to_be32(ACL_UNDEFINED_ID);
break;
}
ace->ae_perm = cpu_to_be16(acl_e->e_perm);
}
}
struct posix_acl *
xfs_get_acl(struct inode *inode, int type, bool rcu)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct posix_acl *acl = NULL;
struct xfs_da_args args = {
.dp = ip,
.attr_filter = XFS_ATTR_ROOT,
.valuelen = XFS_ACL_MAX_SIZE(mp),
};
int error;
if (rcu)
return ERR_PTR(-ECHILD);
trace_xfs_get_acl(ip);
switch (type) {
case ACL_TYPE_ACCESS:
args.name = SGI_ACL_FILE;
break;
case ACL_TYPE_DEFAULT:
args.name = SGI_ACL_DEFAULT;
break;
default:
BUG();
}
args.namelen = strlen(args.name);
/*
* If the attribute doesn't exist make sure we have a negative cache
* entry, for any other error assume it is transient.
*/
error = xfs_attr_get(&args);
if (!error) {
acl = xfs_acl_from_disk(mp, args.value, args.valuelen,
XFS_ACL_MAX_ENTRIES(mp));
} else if (error != -ENOATTR) {
acl = ERR_PTR(error);
}
kvfree(args.value);
return acl;
}
int
__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_da_args args = {
.dp = ip,
.attr_filter = XFS_ATTR_ROOT,
};
int error;
switch (type) {
case ACL_TYPE_ACCESS:
args.name = SGI_ACL_FILE;
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
args.name = SGI_ACL_DEFAULT;
break;
default:
return -EINVAL;
}
args.namelen = strlen(args.name);
if (acl) {
args.valuelen = XFS_ACL_SIZE(acl->a_count);
args.value = kvzalloc(args.valuelen, GFP_KERNEL);
if (!args.value)
return -ENOMEM;
xfs_acl_to_disk(args.value, acl);
error = xfs_attr_change(&args, XFS_ATTRUPDATE_UPSERT);
kvfree(args.value);
} else {
error = xfs_attr_change(&args, XFS_ATTRUPDATE_REMOVE);
/*
* If the attribute didn't exist to start with that's fine.
*/
if (error == -ENOATTR)
error = 0;
}
if (!error)
set_cached_acl(inode, type, acl);
return error;
}
static int
xfs_acl_set_mode(
struct inode *inode,
umode_t mode)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
inode->i_mode = mode;
inode_set_ctime_current(inode);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (xfs_has_wsync(mp))
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp);
}
int
xfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
struct posix_acl *acl, int type)
{
umode_t mode;
bool set_mode = false;
int error = 0;
fs: pass dentry to set acl method The current way of setting and getting posix acls through the generic xattr interface is error prone and type unsafe. The vfs needs to interpret and fixup posix acls before storing or reporting it to userspace. Various hacks exist to make this work. The code is hard to understand and difficult to maintain in it's current form. Instead of making this work by hacking posix acls through xattr handlers we are building a dedicated posix acl api around the get and set inode operations. This removes a lot of hackiness and makes the codepaths easier to maintain. A lot of background can be found in [1]. Since some filesystem rely on the dentry being available to them when setting posix acls (e.g., 9p and cifs) they cannot rely on set acl inode operation. But since ->set_acl() is required in order to use the generic posix acl xattr handlers filesystems that do not implement this inode operation cannot use the handler and need to implement their own dedicated posix acl handlers. Update the ->set_acl() inode method to take a dentry argument. This allows all filesystems to rely on ->set_acl(). As far as I can tell all codepaths can be switched to rely on the dentry instead of just the inode. Note that the original motivation for passing the dentry separate from the inode instead of just the dentry in the xattr handlers was because of security modules that call security_d_instantiate(). This hook is called during d_instantiate_new(), d_add(), __d_instantiate_anon(), and d_splice_alias() to initialize the inode's security context and possibly to set security.* xattrs. Since this only affects security.* xattrs this is completely irrelevant for posix acls. Link: https://lore.kernel.org/all/20220801145520.1532837-1-brauner@kernel.org [1] Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-09-23 08:29:39 +00:00
struct inode *inode = d_inode(dentry);
if (!acl)
goto set_acl;
error = -E2BIG;
if (acl->a_count > XFS_ACL_MAX_ENTRIES(XFS_M(inode->i_sb)))
return error;
if (type == ACL_TYPE_ACCESS) {
error = posix_acl_update_mode(idmap, inode, &mode, &acl);
if (error)
return error;
set_mode = true;
}
set_acl:
/*
* We set the mode after successfully updating the ACL xattr because the
* xattr update can fail at ENOSPC and we don't want to change the mode
* if the ACL update hasn't been applied.
*/
error = __xfs_set_acl(inode, acl, type);
if (!error && set_mode && mode != inode->i_mode)
error = xfs_acl_set_mode(inode, mode);
return error;
}
/*
* Invalidate any cached ACLs if the user has bypassed the ACL interface.
* We don't validate the content whatsoever so it is caller responsibility to
* provide data in valid format and ensure i_mode is consistent.
*/
void
xfs_forget_acl(
struct inode *inode,
const char *name)
{
if (!strcmp(name, SGI_ACL_FILE))
forget_cached_acl(inode, ACL_TYPE_ACCESS);
else if (!strcmp(name, SGI_ACL_DEFAULT))
forget_cached_acl(inode, ACL_TYPE_DEFAULT);
}