mirror/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge tag 'inode-refactor-6.11_2024-07-02' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into xfs-6.11-mergeB

Browse Source 
xfs: hoist inode operations to libxfs

This series hoists inode creation, renaming, and deletion operations to
libxfs in anticipation of the metadata inode directory feature, which
maintains a directory tree of metadata inodes.  This will be necessary
for further enhancements to the realtime feature, subvolume support.

There aren't supposed to be any functional changes in this intense
refactoring -- we just split the functions into pieces that are generic
and pieces that are specific to libxfs clients.  As a bonus, we can
remove various open-coded pieces of mkfs.xfs and xfs_repair when this
series gets to xfsprogs.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>

* tag 'inode-refactor-6.11_2024-07-02' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux:
  xfs: don't use the incore struct xfs_sb for offsets into struct xfs_dsb
  xfs: get rid of trivial rename helpers
  xfs: move dirent update hooks to xfs_dir2.c
  xfs: create libxfs helper to rename two directory entries
  xfs: create libxfs helper to exchange two directory entries
  xfs: create libxfs helper to remove an existing inode/name from a directory
  xfs: hoist inode free function to libxfs
  xfs: create libxfs helper to link an existing inode into a directory
  xfs: create libxfs helper to link a new inode into a directory
  xfs: separate the icreate logic around INIT_XATTRS
  xfs: hoist xfs_{bump,drop}link to libxfs
  xfs: hoist xfs_iunlink to libxfs
  xfs: wrap inode creation dqalloc calls
  xfs: push xfs_icreate_args creation out of xfs_create*
  xfs: hoist new inode initialization functions to libxfs
  xfs: split new inode creation into two pieces
  xfs: use xfs_trans_ichgtime to set times when allocating inode
  xfs: implement atime updates in xfs_trans_ichgtime
  xfs: pack icreate initialization parameters into a separate structure
  xfs: hoist project id get/set functions to libxfs
  xfs: hoist inode flag conversion functions to libxfs
  xfs: hoist extent size helpers to libxfs
  xfs: move inode copy-on-write predicates to xfs_inode.[ch]
  xfs: use consistent uid/gid when grabbing dquots for inodes
  xfs: verify buffer, inode, and dquot items every tx commit
This commit is contained in:
Chandan Babu R
2024-07-04 12:10:04 +05:30
parent 3ba3ab1f67 ac3a027516
commit 2f6ebd4cf5
28 changed files with 1946 additions and 1543 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
fs/xfs/Kconfig
View File

@@ -217,6 +217,18 @@ config XFS_DEBUG
Say N unless you are an XFS developer, or you play one on TV.
config XFS_DEBUG_EXPENSIVE
bool "XFS expensive debugging checks"
depends on XFS_FS && XFS_DEBUG
help
Say Y here to get an XFS build with expensive debugging checks
enabled. These checks may affect performance significantly.
Note that the resulting code will be HUGER and SLOWER, and probably
not useful unless you are debugging a particular problem.
Say N unless you are an XFS developer, or you play one on TV.
config XFS_ASSERT_FATAL
bool "XFS fatal asserts"
default y

1
fs/xfs/Makefile
View File

@@ -40,6 +40,7 @@ xfs-y += $(addprefix libxfs/, \
xfs_iext_tree.o \
xfs_inode_fork.o \
xfs_inode_buf.o \
xfs_inode_util.o \
xfs_log_rlimit.o \
xfs_ag_resv.o \
xfs_parent.o \

43
fs/xfs/libxfs/xfs_bmap.c
View File

@@ -39,6 +39,7 @@
#include "xfs_health.h"
#include "xfs_bmap_item.h"
#include "xfs_symlink_remote.h"
#include "xfs_inode_util.h"
struct kmem_cache *xfs_bmap_intent_cache;
@@ -6454,3 +6455,45 @@ xfs_bmap_query_all(
return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
}
/* Helper function to extract extent size hint from inode */
xfs_extlen_t
xfs_get_extsz_hint(
struct xfs_inode *ip)
{
/*
* No point in aligning allocations if we need to COW to actually
* write to them.
*/
if (xfs_is_always_cow_inode(ip))
return 0;
if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize)
return ip->i_extsize;
if (XFS_IS_REALTIME_INODE(ip) &&
ip->i_mount->m_sb.sb_rextsize > 1)
return ip->i_mount->m_sb.sb_rextsize;
return 0;
}
/*
* Helper function to extract CoW extent size hint from inode.
* Between the extent size hint and the CoW extent size hint, we
* return the greater of the two. If the value is zero (automatic),
* use the default size.
*/
xfs_extlen_t
xfs_get_cowextsz_hint(
struct xfs_inode *ip)
{
xfs_extlen_t a, b;
a = 0;
if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
a = ip->i_cowextsize;
b = xfs_get_extsz_hint(ip);
a = max(a, b);
if (a == 0)
return XFS_DEFAULT_COWEXTSZ_HINT;
return a;
}

3
fs/xfs/libxfs/xfs_bmap.h
View File

@@ -296,4 +296,7 @@ typedef int (*xfs_bmap_query_range_fn)(
int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
void *priv);
xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
#endif /* __XFS_BMAP_H__ */

661
fs/xfs/libxfs/xfs_dir2.c
View File

@@ -19,6 +19,11 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_health.h"
#include "xfs_bmap_btree.h"
#include "xfs_trans_space.h"
#include "xfs_parent.h"
#include "xfs_ag.h"
#include "xfs_ialloc.h"
const struct xfs_name xfs_name_dotdot = {
.name = (const unsigned char *)"..",
@@ -584,9 +589,9 @@ xfs_dir_replace(
*/
int
xfs_dir_canenter(
xfs_trans_t *tp,
xfs_inode_t *dp,
struct xfs_name *name) /* name of entry to add */
struct xfs_trans *tp,
struct xfs_inode *dp,
const struct xfs_name *name) /* name of entry to add */
{
return xfs_dir_createname(tp, dp, name, 0, 0);
}
@@ -756,3 +761,653 @@ xfs_dir2_compname(
return xfs_ascii_ci_compname(args, name, len);
return xfs_da_compname(args, name, len);
}
#ifdef CONFIG_XFS_LIVE_HOOKS
/*
* Use a static key here to reduce the overhead of directory live update hooks.
* If the compiler supports jump labels, the static branch will be replaced by
* a nop sled when there are no hook users. Online fsck is currently the only
* caller, so this is a reasonable tradeoff.
*
* Note: Patching the kernel code requires taking the cpu hotplug lock. Other
* parts of the kernel allocate memory with that lock held, which means that
* XFS callers cannot hold any locks that might be used by memory reclaim or
* writeback when calling the static_branch_{inc,dec} functions.
*/
DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch);
void
xfs_dir_hook_disable(void)
{
xfs_hooks_switch_off(&xfs_dir_hooks_switch);
}
void
xfs_dir_hook_enable(void)
{
xfs_hooks_switch_on(&xfs_dir_hooks_switch);
}
/* Call hooks for a directory update relating to a child dirent update. */
inline void
xfs_dir_update_hook(
struct xfs_inode *dp,
struct xfs_inode *ip,
int delta,
const struct xfs_name *name)
{
if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) {
struct xfs_dir_update_params p = {
.dp = dp,
.ip = ip,
.delta = delta,
.name = name,
};
struct xfs_mount *mp = ip->i_mount;
xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p);
}
}
/* Call the specified function during a directory update. */
int
xfs_dir_hook_add(
struct xfs_mount *mp,
struct xfs_dir_hook *hook)
{
return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook);
}
/* Stop calling the specified function during a directory update. */
void
xfs_dir_hook_del(
struct xfs_mount *mp,
struct xfs_dir_hook *hook)
{
xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook);
}
/* Configure directory update hook functions. */
void
xfs_dir_hook_setup(
struct xfs_dir_hook *hook,
notifier_fn_t mod_fn)
{
xfs_hook_setup(&hook->dirent_hook, mod_fn);
}
#endif /* CONFIG_XFS_LIVE_HOOKS */
/*
* Given a directory @dp, a newly allocated inode @ip, and a @name, link @ip
* into @dp under the given @name. If @ip is a directory, it will be
* initialized. Both inodes must have the ILOCK held and the transaction must
* have sufficient blocks reserved.
*/
int
xfs_dir_create_child(
struct xfs_trans *tp,
unsigned int resblks,
struct xfs_dir_update *du)
{
struct xfs_inode *dp = du->dp;
const struct xfs_name *name = du->name;
struct xfs_inode *ip = du->ip;
int error;
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
if (error) {
ASSERT(error != -ENOSPC);
return error;
}
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
if (S_ISDIR(VFS_I(ip)->i_mode)) {
error = xfs_dir_init(tp, ip, dp);
if (error)
return error;
xfs_bumplink(tp, dp);
}
/*
* If we have parent pointers, we need to add the attribute containing
* the parent information now.
*/
if (du->ppargs) {
error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
if (error)
return error;
}
xfs_dir_update_hook(dp, ip, 1, name);
return 0;
}
/*
* Given a directory @dp, an existing non-directory inode @ip, and a @name,
* link @ip into @dp under the given @name. Both inodes must have the ILOCK
* held.
*/
int
xfs_dir_add_child(
struct xfs_trans *tp,
unsigned int resblks,
struct xfs_dir_update *du)
{
struct xfs_inode *dp = du->dp;
const struct xfs_name *name = du->name;
struct xfs_inode *ip = du->ip;
struct xfs_mount *mp = tp->t_mountp;
int error;
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
ASSERT(!S_ISDIR(VFS_I(ip)->i_mode));
if (!resblks) {
error = xfs_dir_canenter(tp, dp, name);
if (error)
return error;
}
/*
* Handle initial link state of O_TMPFILE inode
*/
if (VFS_I(ip)->i_nlink == 0) {
struct xfs_perag *pag;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
error = xfs_iunlink_remove(tp, pag, ip);
xfs_perag_put(pag);
if (error)
return error;
}
error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
if (error)
return error;
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
xfs_bumplink(tp, ip);
/*
* If we have parent pointers, we now need to add the parent record to
* the attribute fork of the inode. If this is the initial parent
* attribute, we need to create it correctly, otherwise we can just add
* the parent to the inode.
*/
if (du->ppargs) {
error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
if (error)
return error;
}
xfs_dir_update_hook(dp, ip, 1, name);
return 0;
}
/*
* Given a directory @dp, a child @ip, and a @name, remove the (@name, @ip)
* entry from the directory. Both inodes must have the ILOCK held.
*/
int
xfs_dir_remove_child(
struct xfs_trans *tp,
unsigned int resblks,
struct xfs_dir_update *du)
{
struct xfs_inode *dp = du->dp;
const struct xfs_name *name = du->name;
struct xfs_inode *ip = du->ip;
int error;
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
/*
* If we're removing a directory perform some additional validation.
*/
if (S_ISDIR(VFS_I(ip)->i_mode)) {
ASSERT(VFS_I(ip)->i_nlink >= 2);
if (VFS_I(ip)->i_nlink != 2)
return -ENOTEMPTY;
if (!xfs_dir_isempty(ip))
return -ENOTEMPTY;
/* Drop the link from ip's "..". */
error = xfs_droplink(tp, dp);
if (error)
return error;
/* Drop the "." link from ip to self. */
error = xfs_droplink(tp, ip);
if (error)
return error;
/*
* Point the unlinked child directory's ".." entry to the root
* directory to eliminate back-references to inodes that may
* get freed before the child directory is closed. If the fs
* gets shrunk, this can lead to dirent inode validation errors.
*/
if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) {
error = xfs_dir_replace(tp, ip, &xfs_name_dotdot,
tp->t_mountp->m_sb.sb_rootino, 0);
if (error)
return error;
}
} else {
/*
* When removing a non-directory we need to log the parent
* inode here. For a directory this is done implicitly
* by the xfs_droplink call for the ".." entry.
*/
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
}
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/* Drop the link from dp to ip. */
error = xfs_droplink(tp, ip);
if (error)
return error;
error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
if (error) {
ASSERT(error != -ENOENT);
return error;
}
/* Remove parent pointer. */
if (du->ppargs) {
error = xfs_parent_removename(tp, du->ppargs, dp, name, ip);
if (error)
return error;
}
xfs_dir_update_hook(dp, ip, -1, name);
return 0;
}
/*
* Exchange the entry (@name1, @ip1) in directory @dp1 with the entry (@name2,
* @ip2) in directory @dp2, and update '..' @ip1 and @ip2's entries as needed.
* @ip1 and @ip2 need not be of the same type.
*
* All inodes must have the ILOCK held, and both entries must already exist.
*/
int
xfs_dir_exchange_children(
struct xfs_trans *tp,
struct xfs_dir_update *du1,
struct xfs_dir_update *du2,
unsigned int spaceres)
{
struct xfs_inode *dp1 = du1->dp;
const struct xfs_name *name1 = du1->name;
struct xfs_inode *ip1 = du1->ip;
struct xfs_inode *dp2 = du2->dp;
const struct xfs_name *name2 = du2->name;
struct xfs_inode *ip2 = du2->ip;
int ip1_flags = 0;
int ip2_flags = 0;
int dp2_flags = 0;
int error;
/* Swap inode number for dirent in first parent */
error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
if (error)
return error;
/* Swap inode number for dirent in second parent */
error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
if (error)
return error;
/*
* If we're renaming one or more directories across different parents,
* update the respective ".." entries (and link counts) to match the new
* parents.
*/
if (dp1 != dp2) {
dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
if (S_ISDIR(VFS_I(ip2)->i_mode)) {
error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
dp1->i_ino, spaceres);
if (error)
return error;
/* transfer ip2 ".." reference to dp1 */
if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
error = xfs_droplink(tp, dp2);
if (error)
return error;
xfs_bumplink(tp, dp1);
}
/*
* Although ip1 isn't changed here, userspace needs
* to be warned about the change, so that applications
* relying on it (like backup ones), will properly
* notify the change
*/
ip1_flags |= XFS_ICHGTIME_CHG;
ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
}
if (S_ISDIR(VFS_I(ip1)->i_mode)) {
error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
dp2->i_ino, spaceres);
if (error)
return error;
/* transfer ip1 ".." reference to dp2 */
if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
error = xfs_droplink(tp, dp1);
if (error)
return error;
xfs_bumplink(tp, dp2);
}
/*
* Although ip2 isn't changed here, userspace needs
* to be warned about the change, so that applications
* relying on it (like backup ones), will properly
* notify the change
*/
ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
ip2_flags |= XFS_ICHGTIME_CHG;
}
}
if (ip1_flags) {
xfs_trans_ichgtime(tp, ip1, ip1_flags);
xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
}
if (ip2_flags) {
xfs_trans_ichgtime(tp, ip2, ip2_flags);
xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
}
if (dp2_flags) {
xfs_trans_ichgtime(tp, dp2, dp2_flags);
xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
}
xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
/* Schedule parent pointer replacements */
if (du1->ppargs) {
error = xfs_parent_replacename(tp, du1->ppargs, dp1, name1,
dp2, name2, ip1);
if (error)
return error;
}
if (du2->ppargs) {
error = xfs_parent_replacename(tp, du2->ppargs, dp2, name2,
dp1, name1, ip2);
if (error)
return error;
}
/*
* Inform our hook clients that we've finished an exchange operation as
* follows: removed the source and target files from their directories;
* added the target to the source directory; and added the source to
* the target directory. All inodes are locked, so it's ok to model a
* rename this way so long as we say we deleted entries before we add
* new ones.
*/
xfs_dir_update_hook(dp1, ip1, -1, name1);
xfs_dir_update_hook(dp2, ip2, -1, name2);
xfs_dir_update_hook(dp1, ip2, 1, name1);
xfs_dir_update_hook(dp2, ip1, 1, name2);
return 0;
}
/*
* Given an entry (@src_name, @src_ip) in directory @src_dp, make the entry
* @target_name in directory @target_dp point to @src_ip and remove the
* original entry, cleaning up everything left behind.
*
* Cleanup involves dropping a link count on @target_ip, and either removing
* the (@src_name, @src_ip) entry from @src_dp or simply replacing the entry
* with (@src_name, @wip) if a whiteout inode @wip is supplied.
*
* All inodes must have the ILOCK held. We assume that if @src_ip is a
* directory then its '..' doesn't already point to @target_dp, and that @wip
* is a freshly allocated whiteout.
*/
int
xfs_dir_rename_children(
struct xfs_trans *tp,
struct xfs_dir_update *du_src,
struct xfs_dir_update *du_tgt,
unsigned int spaceres,
struct xfs_dir_update *du_wip)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_inode *src_dp = du_src->dp;
const struct xfs_name *src_name = du_src->name;
struct xfs_inode *src_ip = du_src->ip;
struct xfs_inode *target_dp = du_tgt->dp;
const struct xfs_name *target_name = du_tgt->name;
struct xfs_inode *target_ip = du_tgt->ip;
bool new_parent = (src_dp != target_dp);
bool src_is_directory;
int error;
src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
/*
* Check for expected errors before we dirty the transaction
* so we can return an error without a transaction abort.
*/
if (target_ip == NULL) {
/*
* If there's no space reservation, check the entry will
* fit before actually inserting it.
*/
if (!spaceres) {
error = xfs_dir_canenter(tp, target_dp, target_name);
if (error)
return error;
}
} else {
/*
* If target exists and it's a directory, check that whether
* it can be destroyed.
*/
if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
(!xfs_dir_isempty(target_ip) ||
(VFS_I(target_ip)->i_nlink > 2)))
return -EEXIST;
}
/*
* Directory entry creation below may acquire the AGF. Remove
* the whiteout from the unlinked list first to preserve correct
* AGI/AGF locking order. This dirties the transaction so failures
* after this point will abort and log recovery will clean up the
* mess.
*
* For whiteouts, we need to bump the link count on the whiteout
* inode. After this point, we have a real link, clear the tmpfile
* state flag from the inode so it doesn't accidentally get misused
* in future.
*/
if (du_wip->ip) {
struct xfs_perag *pag;
ASSERT(VFS_I(du_wip->ip)->i_nlink == 0);
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, du_wip->ip->i_ino));
error = xfs_iunlink_remove(tp, pag, du_wip->ip);
xfs_perag_put(pag);
if (error)
return error;
xfs_bumplink(tp, du_wip->ip);
}
/*
* Set up the target.
*/
if (target_ip == NULL) {
/*
* If target does not exist and the rename crosses
* directories, adjust the target directory link count
* to account for the ".." reference from the new entry.
*/
error = xfs_dir_createname(tp, target_dp, target_name,
src_ip->i_ino, spaceres);
if (error)
return error;
xfs_trans_ichgtime(tp, target_dp,
XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
if (new_parent && src_is_directory) {
xfs_bumplink(tp, target_dp);
}
} else { /* target_ip != NULL */
/*
* Link the source inode under the target name.
* If the source inode is a directory and we are moving
* it across directories, its ".." entry will be
* inconsistent until we replace that down below.
*
* In case there is already an entry with the same
* name at the destination directory, remove it first.
*/
error = xfs_dir_replace(tp, target_dp, target_name,
src_ip->i_ino, spaceres);
if (error)
return error;
xfs_trans_ichgtime(tp, target_dp,
XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
/*
* Decrement the link count on the target since the target
* dir no longer points to it.
*/
error = xfs_droplink(tp, target_ip);
if (error)
return error;
if (src_is_directory) {
/*
* Drop the link from the old "." entry.
*/
error = xfs_droplink(tp, target_ip);
if (error)
return error;
}
} /* target_ip != NULL */
/*
* Remove the source.
*/
if (new_parent && src_is_directory) {
/*
* Rewrite the ".." entry to point to the new
* directory.
*/
error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
target_dp->i_ino, spaceres);
ASSERT(error != -EEXIST);
if (error)
return error;
}
/*
* We always want to hit the ctime on the source inode.
*
* This isn't strictly required by the standards since the source
* inode isn't really being changed, but old unix file systems did
* it and some incremental backup programs won't work without it.
*/
xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);
/*
* Adjust the link count on src_dp. This is necessary when
* renaming a directory, either within one parent when
* the target existed, or across two parent directories.
*/
if (src_is_directory && (new_parent || target_ip != NULL)) {
/*
* Decrement link count on src_directory since the
* entry that's moved no longer points to it.
*/
error = xfs_droplink(tp, src_dp);
if (error)
return error;
}
/*
* For whiteouts, we only need to update the source dirent with the
* inode number of the whiteout inode rather than removing it
* altogether.
*/
if (du_wip->ip)
error = xfs_dir_replace(tp, src_dp, src_name, du_wip->ip->i_ino,
spaceres);
else
error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
spaceres);
if (error)
return error;
xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
if (new_parent)
xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
/* Schedule parent pointer updates. */
if (du_wip->ppargs) {
error = xfs_parent_addname(tp, du_wip->ppargs, src_dp,
src_name, du_wip->ip);
if (error)
return error;
}
if (du_src->ppargs) {
error = xfs_parent_replacename(tp, du_src->ppargs, src_dp,
src_name, target_dp, target_name, src_ip);
if (error)
return error;
}
if (du_tgt->ppargs) {
error = xfs_parent_removename(tp, du_tgt->ppargs, target_dp,
target_name, target_ip);
if (error)
return error;
}
/*
* Inform our hook clients that we've finished a rename operation as
* follows: removed the source and target files from their directories;
* that we've added the source to the target directory; and finally
* that we've added the whiteout, if there was one. All inodes are
* locked, so it's ok to model a rename this way so long as we say we
* deleted entries before we add new ones.
*/
if (target_ip)
xfs_dir_update_hook(target_dp, target_ip, -1, target_name);
xfs_dir_update_hook(src_dp, src_ip, -1, src_name);
xfs_dir_update_hook(target_dp, src_ip, 1, target_name);
if (du_wip->ip)
xfs_dir_update_hook(src_dp, du_wip->ip, 1, src_name);
return 0;
}

49
fs/xfs/libxfs/xfs_dir2.h
View File

@@ -74,7 +74,7 @@ extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
const struct xfs_name *name, xfs_ino_t inum,
xfs_extlen_t tot);
extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_name *name);
const struct xfs_name *name);
int xfs_dir_lookup_args(struct xfs_da_args *args);
int xfs_dir_createname_args(struct xfs_da_args *args);
@@ -309,4 +309,51 @@ static inline unsigned char xfs_ascii_ci_xfrm(unsigned char c)
return c;
}
struct xfs_dir_update_params {
const struct xfs_inode *dp;
const struct xfs_inode *ip;
const struct xfs_name *name;
int delta;
};
#ifdef CONFIG_XFS_LIVE_HOOKS
void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip,
int delta, const struct xfs_name *name);
struct xfs_dir_hook {
struct xfs_hook dirent_hook;
};
void xfs_dir_hook_disable(void);
void xfs_dir_hook_enable(void);
int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook);
void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook);
void xfs_dir_hook_setup(struct xfs_dir_hook *hook, notifier_fn_t mod_fn);
#else
# define xfs_dir_update_hook(dp, ip, delta, name) ((void)0)
#endif /* CONFIG_XFS_LIVE_HOOKS */
struct xfs_parent_args;
struct xfs_dir_update {
struct xfs_inode *dp;
const struct xfs_name *name;
struct xfs_inode *ip;
struct xfs_parent_args *ppargs;
};
int xfs_dir_create_child(struct xfs_trans *tp, unsigned int resblks,
struct xfs_dir_update *du);
int xfs_dir_add_child(struct xfs_trans *tp, unsigned int resblks,
struct xfs_dir_update *du);
int xfs_dir_remove_child(struct xfs_trans *tp, unsigned int resblks,
struct xfs_dir_update *du);
int xfs_dir_exchange_children(struct xfs_trans *tp, struct xfs_dir_update *du1,
struct xfs_dir_update *du2, unsigned int spaceres);
int xfs_dir_rename_children(struct xfs_trans *tp, struct xfs_dir_update *du_src,
struct xfs_dir_update *du_tgt, unsigned int spaceres,
struct xfs_dir_update *du_wip);
#endif /* __XFS_DIR2_H__ */

9
fs/xfs/libxfs/xfs_format.h
View File

@@ -90,8 +90,7 @@ struct xfs_ifork;
#define XFSLABEL_MAX 12
/*
* Superblock - in core version. Must match the ondisk version below.
* Must be padded to 64 bit alignment.
* Superblock - in core version. Must be padded to 64 bit alignment.
*/
typedef struct xfs_sb {
uint32_t sb_magicnum; /* magic number == XFS_SB_MAGIC */
@@ -178,10 +177,8 @@ typedef struct xfs_sb {
/* must be padded to 64 bit alignment */
} xfs_sb_t;
#define XFS_SB_CRC_OFF offsetof(struct xfs_sb, sb_crc)
/*
* Superblock - on disk version. Must match the in core version above.
* Superblock - on disk version.
* Must be padded to 64 bit alignment.
*/
struct xfs_dsb {
@@ -265,6 +262,8 @@ struct xfs_dsb {
/* must be padded to 64 bit alignment */
};
#define XFS_SB_CRC_OFF offsetof(struct xfs_dsb, sb_crc)
/*
* Misc. Flags - warning - these will be cleared by xfs_repair unless
* a feature bit is set when the flag is used.

15
fs/xfs/libxfs/xfs_ialloc.c
View File

@@ -1946,6 +1946,21 @@ retry:
}
return -ENOSPC;
}
/*
* Protect against obviously corrupt allocation btree records. Later
* xfs_iget checks will catch re-allocation of other active in-memory
* and on-disk inodes. If we don't catch reallocating the parent inode
* here we will deadlock in xfs_iget() so we have to do these checks
* first.
*/
if (ino == parent || !xfs_verify_dir_ino(mp, ino)) {
xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
XFS_SICK_AG_INOBT);
return -EFSCORRUPTED;
}
*new_ino = ino;
return 0;
}

749
fs/xfs/libxfs/xfs_inode_util.c Normal file
View File

@@ -0,0 +1,749 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#include <linux/iversion.h>
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_inode_util.h"
#include "xfs_trans.h"
#include "xfs_ialloc.h"
#include "xfs_health.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_ag.h"
#include "xfs_iunlink_item.h"
#include "xfs_inode_item.h"
uint16_t
xfs_flags2diflags(
struct xfs_inode *ip,
unsigned int xflags)
{
/* can't set PREALLOC this way, just preserve it */
uint16_t di_flags =
(ip->i_diflags & XFS_DIFLAG_PREALLOC);
if (xflags & FS_XFLAG_IMMUTABLE)
di_flags |= XFS_DIFLAG_IMMUTABLE;
if (xflags & FS_XFLAG_APPEND)
di_flags |= XFS_DIFLAG_APPEND;
if (xflags & FS_XFLAG_SYNC)
di_flags |= XFS_DIFLAG_SYNC;
if (xflags & FS_XFLAG_NOATIME)
di_flags |= XFS_DIFLAG_NOATIME;
if (xflags & FS_XFLAG_NODUMP)
di_flags |= XFS_DIFLAG_NODUMP;
if (xflags & FS_XFLAG_NODEFRAG)
di_flags |= XFS_DIFLAG_NODEFRAG;
if (xflags & FS_XFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
if (S_ISDIR(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (xflags & FS_XFLAG_NOSYMLINKS)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
if (xflags & FS_XFLAG_EXTSZINHERIT)
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
if (xflags & FS_XFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_REALTIME)
di_flags |= XFS_DIFLAG_REALTIME;
if (xflags & FS_XFLAG_EXTSIZE)
di_flags |= XFS_DIFLAG_EXTSIZE;
}
return di_flags;
}
uint64_t
xfs_flags2diflags2(
struct xfs_inode *ip,
unsigned int xflags)
{
uint64_t di_flags2 =
(ip->i_diflags2 & (XFS_DIFLAG2_REFLINK |
XFS_DIFLAG2_BIGTIME |
XFS_DIFLAG2_NREXT64));
if (xflags & FS_XFLAG_DAX)
di_flags2 |= XFS_DIFLAG2_DAX;
if (xflags & FS_XFLAG_COWEXTSIZE)
di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
return di_flags2;
}
uint32_t
xfs_ip2xflags(
struct xfs_inode *ip)
{
uint32_t flags = 0;
if (ip->i_diflags & XFS_DIFLAG_ANY) {
if (ip->i_diflags & XFS_DIFLAG_REALTIME)
flags |= FS_XFLAG_REALTIME;
if (ip->i_diflags & XFS_DIFLAG_PREALLOC)
flags |= FS_XFLAG_PREALLOC;
if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
flags |= FS_XFLAG_IMMUTABLE;
if (ip->i_diflags & XFS_DIFLAG_APPEND)
flags |= FS_XFLAG_APPEND;
if (ip->i_diflags & XFS_DIFLAG_SYNC)
flags |= FS_XFLAG_SYNC;
if (ip->i_diflags & XFS_DIFLAG_NOATIME)
flags |= FS_XFLAG_NOATIME;
if (ip->i_diflags & XFS_DIFLAG_NODUMP)
flags |= FS_XFLAG_NODUMP;
if (ip->i_diflags & XFS_DIFLAG_RTINHERIT)
flags |= FS_XFLAG_RTINHERIT;
if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT)
flags |= FS_XFLAG_PROJINHERIT;
if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS)
flags |= FS_XFLAG_NOSYMLINKS;
if (ip->i_diflags & XFS_DIFLAG_EXTSIZE)
flags |= FS_XFLAG_EXTSIZE;
if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)
flags |= FS_XFLAG_EXTSZINHERIT;
if (ip->i_diflags & XFS_DIFLAG_NODEFRAG)
flags |= FS_XFLAG_NODEFRAG;
if (ip->i_diflags & XFS_DIFLAG_FILESTREAM)
flags |= FS_XFLAG_FILESTREAM;
}
if (ip->i_diflags2 & XFS_DIFLAG2_ANY) {
if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
flags |= FS_XFLAG_DAX;
if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
flags |= FS_XFLAG_COWEXTSIZE;
}
if (xfs_inode_has_attr_fork(ip))
flags |= FS_XFLAG_HASATTR;
return flags;
}
prid_t
xfs_get_initial_prid(struct xfs_inode *dp)
{
if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT)
return dp->i_projid;
/* Assign to the root project by default. */
return 0;
}
/* Propagate di_flags from a parent inode to a child inode. */
static inline void
xfs_inode_inherit_flags(
struct xfs_inode *ip,
const struct xfs_inode *pip)
{
unsigned int di_flags = 0;
xfs_failaddr_t failaddr;
umode_t mode = VFS_I(ip)->i_mode;
if (S_ISDIR(mode)) {
if (pip->i_diflags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
ip->i_extsize = pip->i_extsize;
}
if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(mode)) {
if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
xfs_has_realtime(ip->i_mount))
di_flags |= XFS_DIFLAG_REALTIME;
if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
ip->i_extsize = pip->i_extsize;
}
}
if ((pip->i_diflags & XFS_DIFLAG_NOATIME) &&
xfs_inherit_noatime)
di_flags |= XFS_DIFLAG_NOATIME;
if ((pip->i_diflags & XFS_DIFLAG_NODUMP) &&
xfs_inherit_nodump)
di_flags |= XFS_DIFLAG_NODUMP;
if ((pip->i_diflags & XFS_DIFLAG_SYNC) &&
xfs_inherit_sync)
di_flags |= XFS_DIFLAG_SYNC;
if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) &&
xfs_inherit_nosymlinks)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) &&
xfs_inherit_nodefrag)
di_flags |= XFS_DIFLAG_NODEFRAG;
if (pip->i_diflags & XFS_DIFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
ip->i_diflags |= di_flags;
/*
* Inode verifiers on older kernels only check that the extent size
* hint is an integer multiple of the rt extent size on realtime files.
* They did not check the hint alignment on a directory with both
* rtinherit and extszinherit flags set. If the misaligned hint is
* propagated from a directory into a new realtime file, new file
* allocations will fail due to math errors in the rt allocator and/or
* trip the verifiers. Validate the hint settings in the new file so
* that we don't let broken hints propagate.
*/
failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize,
VFS_I(ip)->i_mode, ip->i_diflags);
if (failaddr) {
ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
XFS_DIFLAG_EXTSZINHERIT);
ip->i_extsize = 0;
}
}
/* Propagate di_flags2 from a parent inode to a child inode. */
static inline void
xfs_inode_inherit_flags2(
struct xfs_inode *ip,
const struct xfs_inode *pip)
{
xfs_failaddr_t failaddr;
if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
ip->i_cowextsize = pip->i_cowextsize;
}
if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
ip->i_diflags2 |= XFS_DIFLAG2_DAX;
/* Don't let invalid cowextsize hints propagate. */
failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2);
if (failaddr) {
ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
ip->i_cowextsize = 0;
}
}
/*
* If we need to create attributes immediately after allocating the inode,
* initialise an empty attribute fork right now. We use the default fork offset
* for attributes here as we don't know exactly what size or how many
* attributes we might be adding. We can do this safely here because we know
* the data fork is completely empty and this saves us from needing to run a
* separate transaction to set the fork offset in the immediate future.
*
* If we have parent pointers and the caller hasn't told us that the file will
* never be linked into a directory tree, we /must/ create the attr fork.
*/
static inline bool
xfs_icreate_want_attrfork(
struct xfs_mount *mp,
const struct xfs_icreate_args *args)
{
if (args->flags & XFS_ICREATE_INIT_XATTRS)
return true;
if (!(args->flags & XFS_ICREATE_UNLINKABLE) && xfs_has_parent(mp))
return true;
return false;
}
/* Initialise an inode's attributes. */
void
xfs_inode_init(
struct xfs_trans *tp,
const struct xfs_icreate_args *args,
struct xfs_inode *ip)
{
struct xfs_inode *pip = args->pip;
struct inode *dir = pip ? VFS_I(pip) : NULL;
struct xfs_mount *mp = tp->t_mountp;
struct inode *inode = VFS_I(ip);
unsigned int flags;
int times = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG |
XFS_ICHGTIME_ACCESS;
if (args->flags & XFS_ICREATE_TMPFILE)
set_nlink(inode, 0);
else if (S_ISDIR(args->mode))
set_nlink(inode, 2);
else
set_nlink(inode, 1);
inode->i_rdev = args->rdev;
if (!args->idmap || pip == NULL) {
/* creating a tree root, sb rooted, or detached file */
inode->i_uid = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
ip->i_projid = 0;
inode->i_mode = args->mode;
} else {
/* creating a child in the directory tree */
if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) {
inode_fsuid_set(inode, args->idmap);
inode->i_gid = dir->i_gid;
inode->i_mode = args->mode;
} else {
inode_init_owner(args->idmap, inode, dir, args->mode);
}
/*
* If the group ID of the new file does not match the effective
* group ID or one of the supplementary group IDs, the S_ISGID
* bit is cleared (and only if the irix_sgid_inherit
* compatibility variable is set).
*/
if (irix_sgid_inherit && (inode->i_mode & S_ISGID) &&
!vfsgid_in_group_p(i_gid_into_vfsgid(args->idmap, inode)))
inode->i_mode &= ~S_ISGID;
ip->i_projid = pip ? xfs_get_initial_prid(pip) : 0;
}
ip->i_disk_size = 0;
ip->i_df.if_nextents = 0;
ASSERT(ip->i_nblocks == 0);
ip->i_extsize = 0;
ip->i_diflags = 0;
if (xfs_has_v3inodes(mp)) {
inode_set_iversion(inode, 1);
ip->i_cowextsize = 0;
times |= XFS_ICHGTIME_CREATE;
}
xfs_trans_ichgtime(tp, ip, times);
flags = XFS_ILOG_CORE;
switch (args->mode & S_IFMT) {
case S_IFIFO:
case S_IFCHR:
case S_IFBLK:
case S_IFSOCK:
ip->i_df.if_format = XFS_DINODE_FMT_DEV;
flags |= XFS_ILOG_DEV;
break;
case S_IFREG:
case S_IFDIR:
if (pip && (pip->i_diflags & XFS_DIFLAG_ANY))
xfs_inode_inherit_flags(ip, pip);
if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY))
xfs_inode_inherit_flags2(ip, pip);
fallthrough;
case S_IFLNK:
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
ip->i_df.if_bytes = 0;
ip->i_df.if_data = NULL;
break;
default:
ASSERT(0);
}
if (xfs_icreate_want_attrfork(mp, args)) {
ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
if (!xfs_has_attr(mp)) {
spin_lock(&mp->m_sb_lock);
xfs_add_attr(mp);
spin_unlock(&mp->m_sb_lock);
xfs_log_sb(tp);
}
}
xfs_trans_log_inode(tp, ip, flags);
}
/*
* In-Core Unlinked List Lookups
* =============================
*
* Every inode is supposed to be reachable from some other piece of metadata
* with the exception of the root directory. Inodes with a connection to a
* file descriptor but not linked from anywhere in the on-disk directory tree
* are collectively known as unlinked inodes, though the filesystem itself
* maintains links to these inodes so that on-disk metadata are consistent.
*
* XFS implements a per-AG on-disk hash table of unlinked inodes. The AGI
* header contains a number of buckets that point to an inode, and each inode
* record has a pointer to the next inode in the hash chain. This
* singly-linked list causes scaling problems in the iunlink remove function
* because we must walk that list to find the inode that points to the inode
* being removed from the unlinked hash bucket list.
*
* Hence we keep an in-memory double linked list to link each inode on an
* unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer
* based lists would require having 64 list heads in the perag, one for each
* list. This is expensive in terms of memory (think millions of AGs) and cache
* misses on lookups. Instead, use the fact that inodes on the unlinked list
* must be referenced at the VFS level to keep them on the list and hence we
* have an existence guarantee for inodes on the unlinked list.
*
* Given we have an existence guarantee, we can use lockless inode cache lookups
* to resolve aginos to xfs inodes. This means we only need 8 bytes per inode
* for the double linked unlinked list, and we don't need any extra locking to
* keep the list safe as all manipulations are done under the AGI buffer lock.
* Keeping the list up to date does not require memory allocation, just finding
* the XFS inode and updating the next/prev unlinked list aginos.
*/
/*
* Update the prev pointer of the next agino. Returns -ENOLINK if the inode
* is not in cache.
*/
static int
xfs_iunlink_update_backref(
struct xfs_perag *pag,
xfs_agino_t prev_agino,
xfs_agino_t next_agino)
{
struct xfs_inode *ip;
/* No update necessary if we are at the end of the list. */
if (next_agino == NULLAGINO)
return 0;
ip = xfs_iunlink_lookup(pag, next_agino);
if (!ip)
return -ENOLINK;
ip->i_prev_unlinked = prev_agino;
return 0;
}
/*
* Point the AGI unlinked bucket at an inode and log the results. The caller
* is responsible for validating the old value.
*/
STATIC int
xfs_iunlink_update_bucket(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_buf *agibp,
unsigned int bucket_index,
xfs_agino_t new_agino)
{
struct xfs_agi *agi = agibp->b_addr;
xfs_agino_t old_value;
int offset;
ASSERT(xfs_verify_agino_or_null(pag, new_agino));
old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index,
old_value, new_agino);
/*
* We should never find the head of the list already set to the value
* passed in because either we're adding or removing ourselves from the
* head of the list.
*/
if (old_value == new_agino) {
xfs_buf_mark_corrupt(agibp);
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
return -EFSCORRUPTED;
}
agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
offset = offsetof(struct xfs_agi, agi_unlinked) +
(sizeof(xfs_agino_t) * bucket_index);
xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1);
return 0;
}
static int
xfs_iunlink_insert_inode(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_buf *agibp,
struct xfs_inode *ip)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_agi *agi = agibp->b_addr;
xfs_agino_t next_agino;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
int error;
/*
* Get the index into the agi hash table for the list this inode will
* go on. Make sure the pointer isn't garbage and that this inode
* isn't already on the list.
*/
next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
if (next_agino == agino ||
!xfs_verify_agino_or_null(pag, next_agino)) {
xfs_buf_mark_corrupt(agibp);
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
return -EFSCORRUPTED;
}
/*
* Update the prev pointer in the next inode to point back to this
* inode.
*/
error = xfs_iunlink_update_backref(pag, agino, next_agino);
if (error == -ENOLINK)
error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino);
if (error)
return error;
if (next_agino != NULLAGINO) {
/*
* There is already another inode in the bucket, so point this
* inode to the current head of the list.
*/
error = xfs_iunlink_log_inode(tp, ip, pag, next_agino);
if (error)
return error;
ip->i_next_unlinked = next_agino;
}
/* Point the head of the list to point to this inode. */
ip->i_prev_unlinked = NULLAGINO;
return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino);
}
/*
* This is called when the inode's link count has gone to 0 or we are creating
* a tmpfile via O_TMPFILE. The inode @ip must have nlink == 0.
*
* We place the on-disk inode on a list in the AGI. It will be pulled from this
* list when the inode is freed.
*/
int
xfs_iunlink(
struct xfs_trans *tp,
struct xfs_inode *ip)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_perag *pag;
struct xfs_buf *agibp;
int error;
ASSERT(VFS_I(ip)->i_nlink == 0);
ASSERT(VFS_I(ip)->i_mode != 0);
trace_xfs_iunlink(ip);
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
/* Get the agi buffer first. It ensures lock ordering on the list. */
error = xfs_read_agi(pag, tp, 0, &agibp);
if (error)
goto out;
error = xfs_iunlink_insert_inode(tp, pag, agibp, ip);
out:
xfs_perag_put(pag);
return error;
}
static int
xfs_iunlink_remove_inode(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_buf *agibp,
struct xfs_inode *ip)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_agi *agi = agibp->b_addr;
xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
xfs_agino_t head_agino;
short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
int error;
trace_xfs_iunlink_remove(ip);
/*
* Get the index into the agi hash table for the list this inode will
* go on. Make sure the head pointer isn't garbage.
*/
head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
if (!xfs_verify_agino(pag, head_agino)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
agi, sizeof(*agi));
xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
return -EFSCORRUPTED;
}
/*
* Set our inode's next_unlinked pointer to NULL and then return
* the old pointer value so that we can update whatever was previous
* to us in the list to point to whatever was next in the list.
*/
error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO);
if (error)
return error;
/*
* Update the prev pointer in the next inode to point back to previous
* inode in the chain.
*/
error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked,
ip->i_next_unlinked);
if (error == -ENOLINK)
error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked,
ip->i_next_unlinked);
if (error)
return error;
if (head_agino != agino) {
struct xfs_inode *prev_ip;
prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked);
if (!prev_ip) {
xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
error = xfs_iunlink_log_inode(tp, prev_ip, pag,
ip->i_next_unlinked);
prev_ip->i_next_unlinked = ip->i_next_unlinked;
} else {
/* Point the head of the list to the next unlinked inode. */
error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index,
ip->i_next_unlinked);
}
ip->i_next_unlinked = NULLAGINO;
ip->i_prev_unlinked = 0;
return error;
}
/*
* Pull the on-disk inode from the AGI unlinked list.
*/
int
xfs_iunlink_remove(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_inode *ip)
{
struct xfs_buf *agibp;
int error;
trace_xfs_iunlink_remove(ip);
/* Get the agi buffer first. It ensures lock ordering on the list. */
error = xfs_read_agi(pag, tp, 0, &agibp);
if (error)
return error;
return xfs_iunlink_remove_inode(tp, pag, agibp, ip);
}
/*
* Decrement the link count on an inode & log the change. If this causes the
* link count to go to zero, move the inode to AGI unlinked list so that it can
* be freed when the last active reference goes away via xfs_inactive().
*/
int
xfs_droplink(
struct xfs_trans *tp,
struct xfs_inode *ip)
{
struct inode *inode = VFS_I(ip);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
if (inode->i_nlink == 0) {
xfs_info_ratelimited(tp->t_mountp,
"Inode 0x%llx link count dropped below zero. Pinning link count.",
ip->i_ino);
set_nlink(inode, XFS_NLINK_PINNED);
}
if (inode->i_nlink != XFS_NLINK_PINNED)
drop_nlink(inode);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (inode->i_nlink)
return 0;
return xfs_iunlink(tp, ip);
}
/*
* Increment the link count on an inode & log the change.
*/
void
xfs_bumplink(
struct xfs_trans *tp,
struct xfs_inode *ip)
{
struct inode *inode = VFS_I(ip);
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
if (inode->i_nlink == XFS_NLINK_PINNED - 1)
xfs_info_ratelimited(tp->t_mountp,
"Inode 0x%llx link count exceeded maximum. Pinning link count.",
ip->i_ino);
if (inode->i_nlink != XFS_NLINK_PINNED)
inc_nlink(inode);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
/* Free an inode in the ondisk index and zero it out. */
int
xfs_inode_uninit(
struct xfs_trans *tp,
struct xfs_perag *pag,
struct xfs_inode *ip,
struct xfs_icluster *xic)
{
struct xfs_mount *mp = ip->i_mount;
int error;
/*
* Free the inode first so that we guarantee that the AGI lock is going
* to be taken before we remove the inode from the unlinked list. This
* makes the AGI lock -> unlinked list modification order the same as
* used in O_TMPFILE creation.
*/
error = xfs_difree(tp, pag, ip->i_ino, xic);
if (error)
return error;
error = xfs_iunlink_remove(tp, pag, ip);
if (error)
return error;
/*
* Free any local-format data sitting around before we reset the
* data fork to extents format. Note that the attr fork data has
* already been freed by xfs_attr_inactive.
*/
if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
kfree(ip->i_df.if_data);
ip->i_df.if_data = NULL;
ip->i_df.if_bytes = 0;
}
VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
ip->i_diflags = 0;
ip->i_diflags2 = mp->m_ino_geo.new_diflags2;
ip->i_forkoff = 0; /* mark the attr fork not in use */
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
/*
* Bump the generation count so no one will be confused
* by reincarnations of this inode.
*/
VFS_I(ip)->i_generation++;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return 0;
}

62
fs/xfs/libxfs/xfs_inode_util.h Normal file
View File

@@ -0,0 +1,62 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_INODE_UTIL_H__
#define __XFS_INODE_UTIL_H__
struct xfs_icluster;
uint16_t xfs_flags2diflags(struct xfs_inode *ip, unsigned int xflags);
uint64_t xfs_flags2diflags2(struct xfs_inode *ip, unsigned int xflags);
uint32_t xfs_dic2xflags(struct xfs_inode *ip);
uint32_t xfs_ip2xflags(struct xfs_inode *ip);
prid_t xfs_get_initial_prid(struct xfs_inode *dp);
/*
* File creation context.
*
* Due to our only partial reliance on the VFS to propagate uid and gid values
* according to accepted Unix behaviors, callers must initialize idmap to the
* correct idmapping structure to get the correct inheritance behaviors when
* XFS_MOUNT_GRPID is set.
*
* To create files detached from the directory tree (e.g. quota inodes), set
* idmap to NULL. To create a tree root, set pip to NULL.
*/
struct xfs_icreate_args {
struct mnt_idmap *idmap;
struct xfs_inode *pip; /* parent inode or null */
dev_t rdev;
umode_t mode;
#define XFS_ICREATE_TMPFILE (1U << 0) /* create an unlinked file */
#define XFS_ICREATE_INIT_XATTRS (1U << 1) /* will set xattrs immediately */
#define XFS_ICREATE_UNLINKABLE (1U << 2) /* cannot link into dir tree */
uint16_t flags;
};
/*
* Flags for xfs_trans_ichgtime().
*/
#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
#define XFS_ICHGTIME_ACCESS 0x8 /* last access timestamp */
void xfs_trans_ichgtime(struct xfs_trans *tp, struct xfs_inode *ip, int flags);
void xfs_inode_init(struct xfs_trans *tp, const struct xfs_icreate_args *args,
struct xfs_inode *ip);
int xfs_inode_uninit(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_inode *ip, struct xfs_icluster *xic);
int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_inode *ip);
int xfs_droplink(struct xfs_trans *tp, struct xfs_inode *ip);
void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip);
#endif /* __XFS_INODE_UTIL_H__ */

1
fs/xfs/libxfs/xfs_ondisk.h
View File

@@ -85,6 +85,7 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t, 12);
*/
XFS_CHECK_OFFSET(struct xfs_dsb, sb_crc, 224);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen, 0);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen, 2);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval, 3);

7
fs/xfs/libxfs/xfs_shared.h
View File

@@ -177,13 +177,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_REFC_BTREE_REF 1
#define XFS_SSB_REF 0
/*
* Flags for xfs_trans_ichgtime().
*/
#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
/* Computed inode geometry for the filesystem. */
struct xfs_ino_geometry {
/* Maximum inode count in this filesystem. */

2
fs/xfs/libxfs/xfs_trans_inode.c
View File

@@ -68,6 +68,8 @@ xfs_trans_ichgtime(
inode_set_mtime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CHG)
inode_set_ctime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_ACCESS)
inode_set_atime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CREATE)
ip->i_crtime = tv;
}

1
fs/xfs/scrub/common.c
View File

@@ -26,6 +26,7 @@
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_dir2_priv.h"
#include "xfs_dir2.h"
#include "xfs_attr.h"
#include "xfs_reflink.h"
#include "xfs_ag.h"

21
fs/xfs/scrub/tempfile.c
View File

@@ -40,11 +40,16 @@ xrep_tempfile_create(
struct xfs_scrub *sc,
uint16_t mode)
{
struct xfs_icreate_args args = {
.pip = sc->mp->m_rootip,
.mode = mode,
.flags = XFS_ICREATE_TMPFILE | XFS_ICREATE_UNLINKABLE,
};
struct xfs_mount *mp = sc->mp;
struct xfs_trans *tp = NULL;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *pdqp = NULL;
struct xfs_dquot *udqp;
struct xfs_dquot *gdqp;
struct xfs_dquot *pdqp;
struct xfs_trans_res *tres;
struct xfs_inode *dp = mp->m_rootip;
xfs_ino_t ino;
@@ -65,8 +70,7 @@ xrep_tempfile_create(
* inode should be completely root owned so that we don't fail due to
* quota limits.
*/
error = xfs_qm_vop_dqalloc(dp, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
XFS_QMOPT_QUOTALL, &udqp, &gdqp, &pdqp);
error = xfs_icreate_dqalloc(&args, &udqp, &gdqp, &pdqp);
if (error)
return error;
@@ -87,14 +91,11 @@ xrep_tempfile_create(
error = xfs_dialloc(&tp, dp->i_ino, mode, &ino);
if (error)
goto out_trans_cancel;
error = xfs_init_new_inode(&nop_mnt_idmap, tp, dp, ino, mode, 0, 0,
0, false, &sc->tempip);
error = xfs_icreate(tp, ino, &args, &sc->tempip);
if (error)
goto out_trans_cancel;
/* Change the ownership of the inode to root. */
VFS_I(sc->tempip)->i_uid = GLOBAL_ROOT_UID;
VFS_I(sc->tempip)->i_gid = GLOBAL_ROOT_GID;
/* We don't touch file data, so drop the realtime flags. */
sc->tempip->i_diflags &= ~(XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT);
xfs_trans_log_inode(tp, sc->tempip, XFS_ILOG_CORE);

4
fs/xfs/xfs.h
View File

@@ -10,6 +10,10 @@
#define DEBUG 1
#endif
#ifdef CONFIG_XFS_DEBUG_EXPENSIVE
#define DEBUG_EXPENSIVE 1
#endif
#ifdef CONFIG_XFS_ASSERT_FATAL
#define XFS_ASSERT_FATAL 1
#endif

32
fs/xfs/xfs_buf_item.c
View File

@@ -22,6 +22,7 @@
#include "xfs_trace.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_error.h"
struct kmem_cache *xfs_buf_item_cache;
@@ -781,8 +782,39 @@ xfs_buf_item_committed(
return lsn;
}
#ifdef DEBUG_EXPENSIVE
static int
xfs_buf_item_precommit(
struct xfs_trans *tp,
struct xfs_log_item *lip)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
struct xfs_mount *mp = bp->b_mount;
xfs_failaddr_t fa;
if (!bp->b_ops || !bp->b_ops->verify_struct)
return 0;
if (bip->bli_flags & XFS_BLI_STALE)
return 0;
fa = bp->b_ops->verify_struct(bp);
if (fa) {
xfs_buf_verifier_error(bp, -EFSCORRUPTED, bp->b_ops->name,
bp->b_addr, BBTOB(bp->b_length), fa);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
ASSERT(fa == NULL);
}
return 0;
}
#else
# define xfs_buf_item_precommit NULL
#endif
static const struct xfs_item_ops xfs_buf_item_ops = {
.iop_size = xfs_buf_item_size,
.iop_precommit = xfs_buf_item_precommit,
.iop_format = xfs_buf_item_format,
.iop_pin = xfs_buf_item_pin,
.iop_unpin = xfs_buf_item_unpin,

31
fs/xfs/xfs_dquot_item.c
View File

@@ -17,6 +17,7 @@
#include "xfs_trans_priv.h"
#include "xfs_qm.h"
#include "xfs_log.h"
#include "xfs_error.h"
static inline struct xfs_dq_logitem *DQUOT_ITEM(struct xfs_log_item *lip)
{
@@ -193,8 +194,38 @@ xfs_qm_dquot_logitem_committing(
return xfs_qm_dquot_logitem_release(lip);
}
#ifdef DEBUG_EXPENSIVE
static int
xfs_qm_dquot_logitem_precommit(
struct xfs_trans *tp,
struct xfs_log_item *lip)
{
struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot;
struct xfs_mount *mp = dqp->q_mount;
struct xfs_disk_dquot ddq = { };
xfs_failaddr_t fa;
xfs_dquot_to_disk(&ddq, dqp);
fa = xfs_dquot_verify(mp, &ddq, dqp->q_id);
if (fa) {
XFS_CORRUPTION_ERROR("Bad dquot during logging",
XFS_ERRLEVEL_LOW, mp, &ddq, sizeof(ddq));
xfs_alert(mp,
"Metadata corruption detected at %pS, dquot 0x%x",
fa, dqp->q_id);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
ASSERT(fa == NULL);
}
return 0;
}
#else
# define xfs_qm_dquot_logitem_precommit NULL
#endif
static const struct xfs_item_ops xfs_dquot_item_ops = {
.iop_size = xfs_qm_dquot_logitem_size,
.iop_precommit = xfs_qm_dquot_logitem_precommit,
.iop_format = xfs_qm_dquot_logitem_format,
.iop_pin = xfs_qm_dquot_logitem_pin,
.iop_unpin = xfs_qm_dquot_logitem_unpin,

1483
fs/xfs/xfs_inode.c
View File

File diff suppressed because it is too large Load Diff

70
fs/xfs/xfs_inode.h
View File

@@ -8,6 +8,7 @@
#include "xfs_inode_buf.h"
#include "xfs_inode_fork.h"
#include "xfs_inode_util.h"
/*
* Kernel only inode definitions
@@ -270,15 +271,6 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned long flags)
return ret;
}
static inline prid_t
xfs_get_initial_prid(struct xfs_inode *dp)
{
if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT)
return dp->i_projid;
return XFS_PROJID_DEFAULT;
}
static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
{
return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
@@ -292,6 +284,13 @@ static inline bool xfs_is_metadata_inode(struct xfs_inode *ip)
xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
}
bool xfs_is_always_cow_inode(struct xfs_inode *ip);
static inline bool xfs_is_cow_inode(struct xfs_inode *ip)
{
return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip);
}
/*
* Check if an inode has any data in the COW fork. This might be often false
* even for inodes with the reflink flag when there is no pending COW operation.
@@ -517,12 +516,9 @@ int xfs_release(struct xfs_inode *ip);
int xfs_inactive(struct xfs_inode *ip);
int xfs_lookup(struct xfs_inode *dp, const struct xfs_name *name,
struct xfs_inode **ipp, struct xfs_name *ci_name);
int xfs_create(struct mnt_idmap *idmap,
struct xfs_inode *dp, struct xfs_name *name,
umode_t mode, dev_t rdev, bool need_xattr,
struct xfs_inode **ipp);
int xfs_create_tmpfile(struct mnt_idmap *idmap,
struct xfs_inode *dp, umode_t mode, bool init_xattrs,
int xfs_create(const struct xfs_icreate_args *iargs,
struct xfs_name *name, struct xfs_inode **ipp);
int xfs_create_tmpfile(const struct xfs_icreate_args *iargs,
struct xfs_inode **ipp);
int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
struct xfs_inode *ip);
@@ -542,7 +538,6 @@ void xfs_assert_ilocked(struct xfs_inode *, uint);
uint xfs_ilock_data_map_shared(struct xfs_inode *);
uint xfs_ilock_attr_map_shared(struct xfs_inode *);
uint xfs_ip2xflags(struct xfs_inode *);
int xfs_ifree(struct xfs_trans *, struct xfs_inode *);
int xfs_itruncate_extents_flags(struct xfs_trans **,
struct xfs_inode *, int, xfs_fsize_t, int);
@@ -556,13 +551,8 @@ int xfs_iflush_cluster(struct xfs_buf *);
void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode,
struct xfs_inode *ip1, uint ip1_mode);
xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
int xfs_init_new_inode(struct mnt_idmap *idmap, struct xfs_trans *tp,
struct xfs_inode *pip, xfs_ino_t ino, umode_t mode,
xfs_nlink_t nlink, dev_t rdev, prid_t prid, bool init_xattrs,
struct xfs_inode **ipp);
int xfs_icreate(struct xfs_trans *tp, xfs_ino_t ino,
const struct xfs_icreate_args *args, struct xfs_inode **ipp);
static inline int
xfs_itruncate_extents(
@@ -616,18 +606,15 @@ extern struct kmem_cache *xfs_inode_cache;
bool xfs_inode_needs_inactive(struct xfs_inode *ip);
int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_inode *ip);
struct xfs_inode *xfs_iunlink_lookup(struct xfs_perag *pag, xfs_agino_t agino);
int xfs_iunlink_reload_next(struct xfs_trans *tp, struct xfs_buf *agibp,
xfs_agino_t prev_agino, xfs_agino_t next_agino);
void xfs_end_io(struct work_struct *work);
int xfs_ilock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
void xfs_iunlock2_io_mmap(struct xfs_inode *ip1, struct xfs_inode *ip2);
void xfs_iunlock2_remapping(struct xfs_inode *ip1, struct xfs_inode *ip2);
int xfs_droplink(struct xfs_trans *tp, struct xfs_inode *ip);
void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip);
void xfs_lock_inodes(struct xfs_inode **ips, int inodes, uint lock_mode);
void xfs_sort_inodes(struct xfs_inode **i_tab, unsigned int num_inodes);
@@ -645,29 +632,8 @@ void xfs_inode_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_filblks_t *dblocks, xfs_filblks_t *rblocks);
unsigned int xfs_inode_alloc_unitsize(struct xfs_inode *ip);
struct xfs_dir_update_params {
const struct xfs_inode *dp;
const struct xfs_inode *ip;
const struct xfs_name *name;
int delta;
};
#ifdef CONFIG_XFS_LIVE_HOOKS
void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip,
int delta, const struct xfs_name *name);
struct xfs_dir_hook {
struct xfs_hook dirent_hook;
};
void xfs_dir_hook_disable(void);
void xfs_dir_hook_enable(void);
int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook);
void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook);
void xfs_dir_hook_setup(struct xfs_dir_hook *hook, notifier_fn_t mod_fn);
#else
# define xfs_dir_update_hook(dp, ip, delta, name) ((void)0)
#endif /* CONFIG_XFS_LIVE_HOOKS */
int xfs_icreate_dqalloc(const struct xfs_icreate_args *args,
struct xfs_dquot **udqpp, struct xfs_dquot **gdqpp,
struct xfs_dquot **pdqpp);
#endif /* __XFS_INODE_H__ */

32
fs/xfs/xfs_inode_item.c
View File

@@ -37,6 +37,36 @@ xfs_inode_item_sort(
return INODE_ITEM(lip)->ili_inode->i_ino;
}
#ifdef DEBUG_EXPENSIVE
static void
xfs_inode_item_precommit_check(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_dinode *dip;
xfs_failaddr_t fa;
dip = kzalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | GFP_NOFS);
if (!dip) {
ASSERT(dip != NULL);
return;
}
xfs_inode_to_disk(ip, dip, 0);
xfs_dinode_calc_crc(mp, dip);
fa = xfs_dinode_verify(mp, ip->i_ino, dip);
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
sizeof(*dip), fa);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
ASSERT(fa == NULL);
}
kfree(dip);
}
#else
# define xfs_inode_item_precommit_check(ip) ((void)0)
#endif
/*
* Prior to finally logging the inode, we have to ensure that all the
* per-modification inode state changes are applied. This includes VFS inode
@@ -169,6 +199,8 @@ xfs_inode_item_precommit(
iip->ili_fields |= (flags | iip->ili_last_fields);
spin_unlock(&iip->ili_lock);
xfs_inode_item_precommit_check(ip);
/*
* We are done with the log item transaction dirty state, so clear it so
* that it doesn't pollute future transactions.

60
fs/xfs/xfs_ioctl.c
View File

@@ -469,66 +469,6 @@ xfs_fileattr_get(
return 0;
}
STATIC uint16_t
xfs_flags2diflags(
struct xfs_inode *ip,
unsigned int xflags)
{
/* can't set PREALLOC this way, just preserve it */
uint16_t di_flags =
(ip->i_diflags & XFS_DIFLAG_PREALLOC);
if (xflags & FS_XFLAG_IMMUTABLE)
di_flags |= XFS_DIFLAG_IMMUTABLE;
if (xflags & FS_XFLAG_APPEND)
di_flags |= XFS_DIFLAG_APPEND;
if (xflags & FS_XFLAG_SYNC)
di_flags |= XFS_DIFLAG_SYNC;
if (xflags & FS_XFLAG_NOATIME)
di_flags |= XFS_DIFLAG_NOATIME;
if (xflags & FS_XFLAG_NODUMP)
di_flags |= XFS_DIFLAG_NODUMP;
if (xflags & FS_XFLAG_NODEFRAG)
di_flags |= XFS_DIFLAG_NODEFRAG;
if (xflags & FS_XFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
if (S_ISDIR(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (xflags & FS_XFLAG_NOSYMLINKS)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
if (xflags & FS_XFLAG_EXTSZINHERIT)
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
if (xflags & FS_XFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
} else if (S_ISREG(VFS_I(ip)->i_mode)) {
if (xflags & FS_XFLAG_REALTIME)
di_flags |= XFS_DIFLAG_REALTIME;
if (xflags & FS_XFLAG_EXTSIZE)
di_flags |= XFS_DIFLAG_EXTSIZE;
}
return di_flags;
}
STATIC uint64_t
xfs_flags2diflags2(
struct xfs_inode *ip,
unsigned int xflags)
{
uint64_t di_flags2 =
(ip->i_diflags2 & (XFS_DIFLAG2_REFLINK |
XFS_DIFLAG2_BIGTIME |
XFS_DIFLAG2_NREXT64));
if (xflags & FS_XFLAG_DAX)
di_flags2 |= XFS_DIFLAG2_DAX;
if (xflags & FS_XFLAG_COWEXTSIZE)
di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
return di_flags2;
}
static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,

51
fs/xfs/xfs_iops.c
View File

@@ -26,6 +26,7 @@
#include "xfs_ioctl.h"
#include "xfs_xattr.h"
#include "xfs_file.h"
#include "xfs_bmap.h"
#include <linux/posix_acl.h>
#include <linux/security.h>
@@ -157,8 +158,6 @@ xfs_create_need_xattr(
if (dir->i_sb->s_security)
return true;
#endif
if (xfs_has_parent(XFS_I(dir)->i_mount))
return true;
return false;
}
@@ -172,49 +171,55 @@ xfs_generic_create(
dev_t rdev,
struct file *tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
struct xfs_icreate_args args = {
.idmap = idmap,
.pip = XFS_I(dir),
.rdev = rdev,
.mode = mode,
};
struct inode *inode;
struct xfs_inode *ip = NULL;
struct posix_acl *default_acl, *acl;
struct xfs_name name;
int error;
/*
* Irix uses Missed'em'V split, but doesn't want to see
* the upper 5 bits of (14bit) major.
*/
if (S_ISCHR(mode) || S_ISBLK(mode)) {
if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
if (S_ISCHR(args.mode) || S_ISBLK(args.mode)) {
if (unlikely(!sysv_valid_dev(args.rdev) ||
MAJOR(args.rdev) & ~0x1ff))
return -EINVAL;
} else {
rdev = 0;
args.rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
error = posix_acl_create(dir, &args.mode, &default_acl, &acl);
if (error)
return error;
/* Verify mode is valid also for tmpfile case */
error = xfs_dentry_mode_to_name(&name, dentry, mode);
error = xfs_dentry_mode_to_name(&name, dentry, args.mode);
if (unlikely(error))
goto out_free_acl;
if (!tmpfile) {
error = xfs_create(idmap, XFS_I(dir), &name, mode, rdev,
xfs_create_need_xattr(dir, default_acl, acl),
&ip);
if (xfs_create_need_xattr(dir, default_acl, acl))
args.flags |= XFS_ICREATE_INIT_XATTRS;
error = xfs_create(&args, &name, &ip);
} else {
bool init_xattrs = false;
args.flags |= XFS_ICREATE_TMPFILE;
/*
* If this temporary file will be linkable, set up the file
* with an attr fork to receive a parent pointer.
* If this temporary file will not be linkable, don't bother
* creating an attr fork to receive a parent pointer.
*/
if (!(tmpfile->f_flags & O_EXCL) &&
xfs_has_parent(XFS_I(dir)->i_mount))
init_xattrs = true;
if (tmpfile->f_flags & O_EXCL)
args.flags |= XFS_ICREATE_UNLINKABLE;
error = xfs_create_tmpfile(idmap, XFS_I(dir), mode,
init_xattrs, &ip);
error = xfs_create_tmpfile(&args, &ip);
}
if (unlikely(error))
goto out_free_acl;

2
fs/xfs/xfs_linux.h
View File

@@ -135,8 +135,6 @@ typedef __u32 xfs_nlink_t;
*/
#define __this_address ({ __label__ __here; __here: barrier(); &&__here; })
#define XFS_PROJID_DEFAULT 0
#define howmany(x, y) (((x)+((y)-1))/(y))
static inline void delay(long ticks)

7
fs/xfs/xfs_qm.c
View File

@@ -793,12 +793,15 @@ xfs_qm_qino_alloc(
return error;
if (need_alloc) {
struct xfs_icreate_args args = {
.mode = S_IFREG,
.flags = XFS_ICREATE_UNLINKABLE,
};
xfs_ino_t ino;
error = xfs_dialloc(&tp, 0, S_IFREG, &ino);
if (!error)
error = xfs_init_new_inode(&nop_mnt_idmap, tp, NULL, ino,
S_IFREG, 1, 0, 0, false, ipp);
error = xfs_icreate(tp, ino, &args, ipp);
if (error) {
xfs_trans_cancel(tp);
return error;

10
fs/xfs/xfs_reflink.h
View File

@@ -6,16 +6,6 @@
#ifndef __XFS_REFLINK_H
#define __XFS_REFLINK_H 1
static inline bool xfs_is_always_cow_inode(struct xfs_inode *ip)
{
return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount);
}
static inline bool xfs_is_cow_inode(struct xfs_inode *ip)
{
return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip);
}
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
struct xfs_bmbt_irec *irec, bool *shared);
int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,

70
fs/xfs/xfs_symlink.c
View File

@@ -90,19 +90,25 @@ xfs_symlink(
struct xfs_inode **ipp)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_icreate_args args = {
.idmap = idmap,
.pip = dp,
.mode = S_IFLNK | (mode & ~S_IFMT),
};
struct xfs_dir_update du = {
.dp = dp,
.name = link_name,
};
struct xfs_trans *tp = NULL;
struct xfs_inode *ip = NULL;
int error = 0;
int pathlen;
bool unlock_dp_on_error = false;
xfs_filblks_t fs_blocks;
prid_t prid;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *pdqp = NULL;
struct xfs_dquot *udqp;
struct xfs_dquot *gdqp;
struct xfs_dquot *pdqp;
uint resblks;
xfs_ino_t ino;
struct xfs_parent_args *ppargs;
*ipp = NULL;
@@ -119,15 +125,8 @@ xfs_symlink(
return -ENAMETOOLONG;
ASSERT(pathlen > 0);
prid = xfs_get_initial_prid(dp);
/*
* Make sure that we have allocated dquot(s) on disk.
*/
error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(idmap, &init_user_ns),
mapped_fsgid(idmap, &init_user_ns), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
/* Make sure that we have allocated dquot(s) on disk. */
error = xfs_icreate_dqalloc(&args, &udqp, &gdqp, &pdqp);
if (error)
return error;
@@ -143,7 +142,7 @@ xfs_symlink(
fs_blocks = xfs_symlink_blocks(mp, pathlen);
resblks = xfs_symlink_space_res(mp, link_name->len, fs_blocks);
error = xfs_parent_start(mp, &ppargs);
error = xfs_parent_start(mp, &du.ppargs);
if (error)
goto out_release_dquots;
@@ -168,9 +167,7 @@ xfs_symlink(
*/
error = xfs_dialloc(&tp, dp->i_ino, S_IFLNK, &ino);
if (!error)
error = xfs_init_new_inode(idmap, tp, dp, ino,
S_IFLNK | (mode & ~S_IFMT), 1, 0, prid,
xfs_has_parent(mp), &ip);
error = xfs_icreate(tp, ino, &args, &du.ip);
if (error)
goto out_trans_cancel;
@@ -186,33 +183,22 @@ xfs_symlink(
/*
* Also attach the dquot(s) to it, if applicable.
*/
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
xfs_qm_vop_create_dqattach(tp, du.ip, udqp, gdqp, pdqp);
resblks -= XFS_IALLOC_SPACE_RES(mp);
error = xfs_symlink_write_target(tp, ip, ip->i_ino, target_path,
error = xfs_symlink_write_target(tp, du.ip, du.ip->i_ino, target_path,
pathlen, fs_blocks, resblks);
if (error)
goto out_trans_cancel;
resblks -= fs_blocks;
i_size_write(VFS_I(ip), ip->i_disk_size);
i_size_write(VFS_I(du.ip), du.ip->i_disk_size);
/*
* Create the directory entry for the symlink.
*/
error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
error = xfs_dir_create_child(tp, resblks, &du);
if (error)
goto out_trans_cancel;
xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/* Add parent pointer for the new symlink. */
if (ppargs) {
error = xfs_parent_addname(tp, ppargs, dp, link_name, ip);
if (error)
goto out_trans_cancel;
}
xfs_dir_update_hook(dp, ip, 1, link_name);
/*
* If this is a synchronous mount, make sure that the
@@ -230,10 +216,10 @@ xfs_symlink(
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
*ipp = ip;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
*ipp = du.ip;
xfs_iunlock(du.ip, XFS_ILOCK_EXCL);
xfs_iunlock(dp, XFS_ILOCK_EXCL);
xfs_parent_finish(mp, ppargs);
xfs_parent_finish(mp, du.ppargs);
return 0;
out_trans_cancel:
@@ -244,13 +230,13 @@ out_release_inode:
* setup of the inode and release the inode. This prevents recursive
* transactions and deadlocks from xfs_inactive.
*/
if (ip) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_finish_inode_setup(ip);
xfs_irele(ip);
if (du.ip) {
xfs_iunlock(du.ip, XFS_ILOCK_EXCL);
xfs_finish_inode_setup(du.ip);
xfs_irele(du.ip);
}
out_parent:
xfs_parent_finish(mp, ppargs);
xfs_parent_finish(mp, du.ppargs);
out_release_dquots:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);

1
fs/xfs/xfs_trans.h
View File

@@ -224,7 +224,6 @@ void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *);
bool xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint);
void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);
void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint);
void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint,
uint);