linux/fs/xfs/xfs_iops.c

1327 lines
34 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#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_mount.h"
#include "xfs_da_format.h"
#include "xfs_inode.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_acl.h"
#include "xfs_quota.h"
#include "xfs_error.h"
#include "xfs_attr.h"
#include "xfs_trans.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>
2009-12-15 07:14:59 +08:00
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_trans_space.h"
#include <linux/capability.h>
#include <linux/xattr.h>
#include <linux/namei.h>
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/fiemap.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
/*
* Directories have different lock order w.r.t. mmap_sem compared to regular
* files. This is due to readdir potentially triggering page faults on a user
* buffer inside filldir(), and this happens with the ilock on the directory
* held. For regular files, the lock order is the other way around - the
* mmap_sem is taken during the page fault, and then we lock the ilock to do
* block mapping. Hence we need a different class for the directory ilock so
* that lockdep can tell them apart.
*/
static struct lock_class_key xfs_nondir_ilock_class;
static struct lock_class_key xfs_dir_ilock_class;
static int
xfs_initxattrs(
struct inode *inode,
const struct xattr *xattr_array,
void *fs_info)
{
const struct xattr *xattr;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
error = xfs_attr_set(ip, xattr->name, xattr->value,
xattr->value_len, ATTR_SECURE);
if (error < 0)
break;
}
return error;
}
/*
* Hook in SELinux. This is not quite correct yet, what we really need
* here (as we do for default ACLs) is a mechanism by which creation of
* these attrs can be journalled at inode creation time (along with the
* inode, of course, such that log replay can't cause these to be lost).
*/
STATIC int
xfs_init_security(
struct inode *inode,
struct inode *dir,
const struct qstr *qstr)
{
return security_inode_init_security(inode, dir, qstr,
&xfs_initxattrs, NULL);
}
static void
xfs_dentry_to_name(
struct xfs_name *namep,
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
struct dentry *dentry,
int mode)
{
namep->name = dentry->d_name.name;
namep->len = dentry->d_name.len;
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
namep->type = xfs_mode_to_ftype[(mode & S_IFMT) >> S_SHIFT];
}
STATIC void
xfs_cleanup_inode(
struct inode *dir,
struct inode *inode,
struct dentry *dentry)
{
struct xfs_name teardown;
/* Oh, the horror.
* If we can't add the ACL or we fail in
* xfs_init_security we must back out.
* ENOSPC can hit here, among other things.
*/
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&teardown, dentry, 0);
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
}
STATIC int
xfs_generic_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev,
bool tmpfile) /* unnamed file */
{
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))
return -EINVAL;
rdev = sysv_encode_dev(rdev);
} else {
rdev = 0;
}
error = posix_acl_create(dir, &mode, &default_acl, &acl);
if (error)
return error;
if (!tmpfile) {
xfs_dentry_to_name(&name, dentry, mode);
error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
} else {
error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
#ifdef CONFIG_XFS_POSIX_ACL
if (default_acl) {
error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
if (error)
goto out_cleanup_inode;
}
if (acl) {
error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
if (error)
goto out_cleanup_inode;
}
#endif
if (tmpfile)
d_tmpfile(dentry, inode);
else
d_instantiate(dentry, inode);
out_free_acl:
if (default_acl)
posix_acl_release(default_acl);
if (acl)
posix_acl_release(acl);
return error;
out_cleanup_inode:
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
iput(inode);
goto out_free_acl;
}
STATIC int
xfs_vn_mknod(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev)
{
return xfs_generic_create(dir, dentry, mode, rdev, false);
}
STATIC int
xfs_vn_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool flags)
{
return xfs_vn_mknod(dir, dentry, mode, 0);
}
STATIC int
xfs_vn_mkdir(
struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
}
STATIC struct dentry *
xfs_vn_lookup(
struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct xfs_inode *cip;
struct xfs_name name;
int error;
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&name, dentry, 0);
error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
if (unlikely(error)) {
if (unlikely(error != -ENOENT))
return ERR_PTR(error);
d_add(dentry, NULL);
return NULL;
}
return d_splice_alias(VFS_I(cip), dentry);
}
STATIC struct dentry *
xfs_vn_ci_lookup(
struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct xfs_inode *ip;
struct xfs_name xname;
struct xfs_name ci_name;
struct qstr dname;
int error;
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&xname, dentry, 0);
error = xfs_lookup(XFS_I(dir), &xname, &ip, &ci_name);
if (unlikely(error)) {
if (unlikely(error != -ENOENT))
return ERR_PTR(error);
/*
* call d_add(dentry, NULL) here when d_drop_negative_children
* is called in xfs_vn_mknod (ie. allow negative dentries
* with CI filesystems).
*/
return NULL;
}
/* if exact match, just splice and exit */
if (!ci_name.name)
return d_splice_alias(VFS_I(ip), dentry);
/* else case-insensitive match... */
dname.name = ci_name.name;
dname.len = ci_name.len;
dentry = d_add_ci(dentry, VFS_I(ip), &dname);
kmem_free(ci_name.name);
return dentry;
}
STATIC int
xfs_vn_link(
struct dentry *old_dentry,
struct inode *dir,
struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
struct xfs_name name;
int error;
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&name, dentry, inode->i_mode);
error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
if (unlikely(error))
return error;
ihold(inode);
d_instantiate(dentry, inode);
return 0;
}
STATIC int
xfs_vn_unlink(
struct inode *dir,
struct dentry *dentry)
{
struct xfs_name name;
int error;
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&name, dentry, 0);
error = xfs_remove(XFS_I(dir), &name, XFS_I(dentry->d_inode));
if (error)
return error;
/*
* With unlink, the VFS makes the dentry "negative": no inode,
* but still hashed. This is incompatible with case-insensitive
* mode, so invalidate (unhash) the dentry in CI-mode.
*/
if (xfs_sb_version_hasasciici(&XFS_M(dir->i_sb)->m_sb))
d_invalidate(dentry);
return 0;
}
STATIC int
xfs_vn_symlink(
struct inode *dir,
struct dentry *dentry,
const char *symname)
{
struct inode *inode;
struct xfs_inode *cip = NULL;
struct xfs_name name;
int error;
umode_t mode;
mode = S_IFLNK |
(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&name, dentry, mode);
error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
if (unlikely(error))
goto out;
inode = VFS_I(cip);
error = xfs_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
d_instantiate(dentry, inode);
return 0;
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
iput(inode);
out:
return error;
}
STATIC int
xfs_vn_rename(
struct inode *odir,
struct dentry *odentry,
struct inode *ndir,
struct dentry *ndentry)
{
struct inode *new_inode = ndentry->d_inode;
struct xfs_name oname;
struct xfs_name nname;
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
xfs_dentry_to_name(&oname, odentry, 0);
xfs_dentry_to_name(&nname, ndentry, odentry->d_inode->i_mode);
return xfs_rename(XFS_I(odir), &oname, XFS_I(odentry->d_inode),
XFS_I(ndir), &nname, new_inode ?
xfs: Add read-only support for dirent filetype field Add support for the file type field in directory entries so that readdir can return the type of the inode the dirent points to to userspace without first having to read the inode off disk. The encoding of the type field is a single byte that is added to the end of the directory entry name length. For all intents and purposes, it appends a "hidden" byte to the name field which contains the type information. As the directory entry is already of dynamic size, helpers are already required to access and decode the direct entry structures. Hence the relevent extraction and iteration helpers are updated to understand the hidden byte. Helpers for reading and writing the filetype field from the directory entries are also added. Only the read helpers are used by this patch. It also adds all the code necessary to read the type information out of the dirents on disk. Further we add the superblock feature bit and helpers to indicate that we understand the on-disk format change. This is not a compatible change - existing kernels cannot read the new format successfully - so an incompatible feature flag is added. We don't yet allow filesystems to mount with this flag yet - that will be added once write support is added. Finally, the code to take the type from the VFS, convert it to an XFS on-disk type and put it into the xfs_name structures passed around is added, but the directory code does not use this field yet. That will be in the next patch. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Mark Tinguely <tinguely@sgi.com> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-08-12 18:50:09 +08:00
XFS_I(new_inode) : NULL);
}
/*
* careful here - this function can get called recursively, so
* we need to be very careful about how much stack we use.
* uio is kmalloced for this reason...
*/
STATIC void *
xfs_vn_follow_link(
struct dentry *dentry,
struct nameidata *nd)
{
char *link;
int error = -ENOMEM;
link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
if (!link)
goto out_err;
error = xfs_readlink(XFS_I(dentry->d_inode), link);
if (unlikely(error))
goto out_kfree;
nd_set_link(nd, link);
return NULL;
out_kfree:
kfree(link);
out_err:
nd_set_link(nd, ERR_PTR(error));
return NULL;
}
STATIC int
xfs_vn_getattr(
struct vfsmount *mnt,
struct dentry *dentry,
struct kstat *stat)
{
struct inode *inode = dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
trace_xfs_getattr(ip);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = ip->i_d.di_mode;
stat->nlink = ip->i_d.di_nlink;
stat->uid = inode->i_uid;
stat->gid = inode->i_gid;
stat->ino = ip->i_ino;
stat->atime = inode->i_atime;
2009-10-07 04:29:26 +08:00
stat->mtime = inode->i_mtime;
stat->ctime = inode->i_ctime;
stat->blocks =
XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
if (XFS_IS_REALTIME_INODE(ip)) {
/*
* If the file blocks are being allocated from a
* realtime volume, then return the inode's realtime
* extent size or the realtime volume's extent size.
*/
stat->blksize =
xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
} else
stat->blksize = xfs_preferred_iosize(mp);
stat->rdev = 0;
break;
}
return 0;
}
static void
xfs_setattr_mode(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
umode_t mode = iattr->ia_mode;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ip->i_d.di_mode &= S_IFMT;
ip->i_d.di_mode |= mode & ~S_IFMT;
inode->i_mode &= S_IFMT;
inode->i_mode |= mode & ~S_IFMT;
}
static void
xfs_setattr_time(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct inode *inode = VFS_I(ip);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
if (iattr->ia_valid & ATTR_ATIME) {
inode->i_atime = iattr->ia_atime;
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
}
if (iattr->ia_valid & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (iattr->ia_valid & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
}
int
xfs_setattr_nonsize(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
xfs_mount_t *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_trans_t *tp;
int error;
kuid_t uid = GLOBAL_ROOT_UID, iuid = GLOBAL_ROOT_UID;
kgid_t gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *olddquot1 = NULL, *olddquot2 = NULL;
trace_xfs_setattr(ip);
/* If acls are being inherited, we already have this checked */
if (!(flags & XFS_ATTR_NOACL)) {
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
}
ASSERT((mask & ATTR_SIZE) == 0);
/*
* If disk quotas is on, we make sure that the dquots do exist on disk,
* before we start any other transactions. Trying to do this later
* is messy. We don't care to take a readlock to look at the ids
* in inode here, because we can't hold it across the trans_reserve.
* If the IDs do change before we take the ilock, we're covered
* because the i_*dquot fields will get updated anyway.
*/
if (XFS_IS_QUOTA_ON(mp) && (mask & (ATTR_UID|ATTR_GID))) {
uint qflags = 0;
if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
uid = iattr->ia_uid;
qflags |= XFS_QMOPT_UQUOTA;
} else {
uid = inode->i_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
gid = iattr->ia_gid;
qflags |= XFS_QMOPT_GQUOTA;
} else {
gid = inode->i_gid;
}
/*
* We take a reference when we initialize udqp and gdqp,
* so it is important that we never blindly double trip on
* the same variable. See xfs_create() for an example.
*/
ASSERT(udqp == NULL);
ASSERT(gdqp == NULL);
error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid),
xfs_kgid_to_gid(gid),
xfs_get_projid(ip),
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
}
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
if (error)
goto out_dqrele;
xfs_ilock(ip, XFS_ILOCK_EXCL);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* These IDs could have changed since we last looked at them.
* But, we're assured that if the ownership did change
* while we didn't have the inode locked, inode's dquot(s)
* would have changed also.
*/
iuid = inode->i_uid;
igid = inode->i_gid;
gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
/*
* Do a quota reservation only if uid/gid is actually
* going to change.
*/
if (XFS_IS_QUOTA_RUNNING(mp) &&
((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) ||
(XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) {
ASSERT(tp);
error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
NULL, capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (error) /* out of quota */
goto out_trans_cancel;
}
}
xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (!uid_eq(iuid, uid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
ASSERT(mask & ATTR_UID);
ASSERT(udqp);
olddquot1 = xfs_qm_vop_chown(tp, ip,
&ip->i_udquot, udqp);
}
ip->i_d.di_uid = xfs_kuid_to_uid(uid);
inode->i_uid = uid;
}
if (!gid_eq(igid, gid)) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
!XFS_IS_PQUOTA_ON(mp));
ASSERT(mask & ATTR_GID);
ASSERT(gdqp);
olddquot2 = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
ip->i_d.di_gid = xfs_kgid_to_gid(gid);
inode->i_gid = gid;
}
}
if (mask & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot1);
xfs_qm_dqrele(olddquot2);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
if (error)
return error;
/*
* XXX(hch): Updating the ACL entries is not atomic vs the i_mode
* update. We could avoid this with linked transactions
* and passing down the transaction pointer all the way
* to attr_set. No previous user of the generic
* Posix ACL code seems to care about this issue either.
*/
if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
error = posix_acl_chmod(inode, inode->i_mode);
if (error)
return error;
}
return 0;
out_trans_cancel:
xfs_trans_cancel(tp, 0);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (newsize > oldsize) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
return error;
}
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
xfs: truncate_setsize should be outside transactions truncate_setsize() removes pages from the page cache, and hence requires page locks to be held. It is not valid to lock a page cache page inside a transaction context as we can hold page locks when we we reserve space for a transaction. If we do, then we expose an ABBA deadlock between log space reservation and page locks. That is, both the write path and writeback lock a page, then start a transaction for block allocation, which means they can block waiting for a log reservation with the page lock held. If we hold a log reservation and then do something that locks a page (e.g. truncate_setsize in xfs_setattr_size) then that page lock can block on the page locked and waiting for a log reservation. If the transaction that is waiting for the page lock is the only active transaction in the system that can free log space via a commit, then writeback will never make progress and so log space will never free up. This issue with xfs_setattr_size() was introduced back in 2010 by commit fa9b227 ("xfs: new truncate sequence") which moved the page cache truncate from outside the transaction context (what was xfs_itruncate_data()) to inside the transaction context as a call to truncate_setsize(). The reason truncate_setsize() was located where in this place was that we can't shouldn't change the file size until after we are in the transaction context and the operation will either succeed or shut down the filesystem on failure. However, block_truncate_page() already modifies the file contents before we enter the transaction context, so we can't really fulfill this guarantee in any way. Hence we may as well ensure that on success or failure, the in-memory inode and data is truncated away and that the application cleans up the mess appropriately. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-05-07 06:05:45 +08:00
/*
* Do all the page cache truncate work outside the transaction context
* as the "lock" order is page lock->log space reservation. i.e.
* locking pages inside the transaction can ABBA deadlock with
* writeback. We have to do the VFS inode size update before we truncate
* the pagecache, however, to avoid racing with page faults beyond the
* new EOF they are not serialised against truncate operations except by
* page locks and size updates.
*
* Hence we are in a situation where a truncate can fail with ENOMEM
* from xfs_trans_reserve(), but having already truncated the in-memory
* version of the file (i.e. made user visible changes). There's not
* much we can do about this, except to hope that the caller sees ENOMEM
* and retries the truncate operation.
*/
error = block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
xfs: truncate_setsize should be outside transactions truncate_setsize() removes pages from the page cache, and hence requires page locks to be held. It is not valid to lock a page cache page inside a transaction context as we can hold page locks when we we reserve space for a transaction. If we do, then we expose an ABBA deadlock between log space reservation and page locks. That is, both the write path and writeback lock a page, then start a transaction for block allocation, which means they can block waiting for a log reservation with the page lock held. If we hold a log reservation and then do something that locks a page (e.g. truncate_setsize in xfs_setattr_size) then that page lock can block on the page locked and waiting for a log reservation. If the transaction that is waiting for the page lock is the only active transaction in the system that can free log space via a commit, then writeback will never make progress and so log space will never free up. This issue with xfs_setattr_size() was introduced back in 2010 by commit fa9b227 ("xfs: new truncate sequence") which moved the page cache truncate from outside the transaction context (what was xfs_itruncate_data()) to inside the transaction context as a call to truncate_setsize(). The reason truncate_setsize() was located where in this place was that we can't shouldn't change the file size until after we are in the transaction context and the operation will either succeed or shut down the filesystem on failure. However, block_truncate_page() already modifies the file contents before we enter the transaction context, so we can't really fulfill this guarantee in any way. Hence we may as well ensure that on success or failure, the in-memory inode and data is truncated away and that the application cleans up the mess appropriately. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-05-07 06:05:45 +08:00
truncate_setsize(inode, newsize);
xfs: flush entire last page of old EOF on truncate up On a sub-page sized filesystem, truncating a mapped region down leaves us in a world of hurt. We truncate the pagecache, zeroing the newly unused tail, then punch blocks out from under the page. If we then truncate the file back up immediately, we expose that unmapped hole to a dirty page mapped into the user application, and that's where it all goes wrong. In truncating the page cache, we avoid unmapping the tail page of the cache because it still contains valid data. The problem is that it also contains a hole after the truncate, but nobody told the mm subsystem that. Therefore, if the page is dirty before the truncate, we'll never get a .page_mkwrite callout after we extend the file and the application writes data into the hole on the page. Hence when we come to writing that region of the page, it has no blocks and no delayed allocation reservation and hence we toss the data away. This patch adds code to the truncate up case to solve it, by ensuring the partial page at the old EOF is always cleaned after we do any zeroing and move the EOF upwards. We can't actually serialise the page writeback and truncate against page faults (yes, that problem AGAIN) so this is really just a best effort and assumes it is extremely unlikely that someone is concurrently writing to the page at the EOF while extending the file. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2014-09-23 20:55:00 +08:00
/*
* The "we can't serialise against page faults" pain gets worse.
*
* If the file is mapped then we have to clean the page at the old EOF
* when extending the file. Extending the file can expose changes the
* underlying page mapping (e.g. from beyond EOF to a hole or
* unwritten), and so on the next attempt to write to that page we need
* to remap it for write. i.e. we need .page_mkwrite() to be called.
* Hence we need to clean the page to clean the pte and so a new write
* fault will be triggered appropriately.
*
* If we do it before we change the inode size, then we can race with a
* page fault that maps the page with exactly the same problem. If we do
* it after we change the file size, then a new page fault can come in
* and allocate space before we've run the rest of the truncate
* transaction. That's kinda grotesque, but it's better than have data
* over a hole, and so that's the lesser evil that has been chosen here.
*
* The real solution, however, is to have some mechanism for locking out
* page faults while a truncate is in progress.
*/
if (newsize > oldsize && mapping_mapped(VFS_I(ip)->i_mapping)) {
error = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
round_down(oldsize, PAGE_CACHE_SIZE),
round_up(oldsize, PAGE_CACHE_SIZE) - 1);
if (error)
return error;
}
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
STATIC int
xfs_vn_setattr(
struct dentry *dentry,
struct iattr *iattr)
{
struct xfs_inode *ip = XFS_I(dentry->d_inode);
int error;
if (iattr->ia_valid & ATTR_SIZE) {
xfs_ilock(ip, XFS_IOLOCK_EXCL);
error = xfs_setattr_size(ip, iattr);
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
} else {
error = xfs_setattr_nonsize(ip, iattr, 0);
}
return error;
}
STATIC int
xfs_vn_update_time(
struct inode *inode,
struct timespec *now,
int flags)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
int error;
trace_xfs_update_time(ip);
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (flags & S_CTIME) {
inode->i_ctime = *now;
ip->i_d.di_ctime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_ctime.t_nsec = (__int32_t)now->tv_nsec;
}
if (flags & S_MTIME) {
inode->i_mtime = *now;
ip->i_d.di_mtime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_mtime.t_nsec = (__int32_t)now->tv_nsec;
}
if (flags & S_ATIME) {
inode->i_atime = *now;
ip->i_d.di_atime.t_sec = (__int32_t)now->tv_sec;
ip->i_d.di_atime.t_nsec = (__int32_t)now->tv_nsec;
}
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_TIMESTAMP);
return xfs_trans_commit(tp, 0);
}
#define XFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
/*
* Call fiemap helper to fill in user data.
* Returns positive errors to xfs_getbmap.
*/
STATIC int
xfs_fiemap_format(
void **arg,
struct getbmapx *bmv,
int *full)
{
int error;
struct fiemap_extent_info *fieinfo = *arg;
u32 fiemap_flags = 0;
u64 logical, physical, length;
/* Do nothing for a hole */
if (bmv->bmv_block == -1LL)
return 0;
logical = BBTOB(bmv->bmv_offset);
physical = BBTOB(bmv->bmv_block);
length = BBTOB(bmv->bmv_length);
if (bmv->bmv_oflags & BMV_OF_PREALLOC)
fiemap_flags |= FIEMAP_EXTENT_UNWRITTEN;
else if (bmv->bmv_oflags & BMV_OF_DELALLOC) {
fiemap_flags |= (FIEMAP_EXTENT_DELALLOC |
FIEMAP_EXTENT_UNKNOWN);
physical = 0; /* no block yet */
}
if (bmv->bmv_oflags & BMV_OF_LAST)
fiemap_flags |= FIEMAP_EXTENT_LAST;
error = fiemap_fill_next_extent(fieinfo, logical, physical,
length, fiemap_flags);
if (error > 0) {
error = 0;
*full = 1; /* user array now full */
}
return error;
}
STATIC int
xfs_vn_fiemap(
struct inode *inode,
struct fiemap_extent_info *fieinfo,
u64 start,
u64 length)
{
xfs_inode_t *ip = XFS_I(inode);
struct getbmapx bm;
int error;
error = fiemap_check_flags(fieinfo, XFS_FIEMAP_FLAGS);
if (error)
return error;
/* Set up bmap header for xfs internal routine */
bm.bmv_offset = BTOBBT(start);
/* Special case for whole file */
if (length == FIEMAP_MAX_OFFSET)
bm.bmv_length = -1LL;
else
bm.bmv_length = BTOBB(start + length) - bm.bmv_offset;
/* We add one because in getbmap world count includes the header */
bm.bmv_count = !fieinfo->fi_extents_max ? MAXEXTNUM :
fieinfo->fi_extents_max + 1;
bm.bmv_count = min_t(__s32, bm.bmv_count,
(PAGE_SIZE * 16 / sizeof(struct getbmapx)));
bm.bmv_iflags = BMV_IF_PREALLOC | BMV_IF_NO_HOLES;
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
bm.bmv_iflags |= BMV_IF_ATTRFORK;
if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
bm.bmv_iflags |= BMV_IF_DELALLOC;
error = xfs_getbmap(ip, &bm, xfs_fiemap_format, fieinfo);
if (error)
return error;
return 0;
}
STATIC int
xfs_vn_tmpfile(
struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
return xfs_generic_create(dir, dentry, mode, 0, true);
}
static const struct inode_operations xfs_inode_operations = {
.get_acl = xfs_get_acl,
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.fiemap = xfs_vn_fiemap,
.update_time = xfs_vn_update_time,
};
static const struct inode_operations xfs_dir_inode_operations = {
.create = xfs_vn_create,
.lookup = xfs_vn_lookup,
.link = xfs_vn_link,
.unlink = xfs_vn_unlink,
.symlink = xfs_vn_symlink,
.mkdir = xfs_vn_mkdir,
/*
* Yes, XFS uses the same method for rmdir and unlink.
*
* There are some subtile differences deeper in the code,
* but we use S_ISDIR to check for those.
*/
.rmdir = xfs_vn_unlink,
.mknod = xfs_vn_mknod,
.rename = xfs_vn_rename,
.get_acl = xfs_get_acl,
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
};
static const struct inode_operations xfs_dir_ci_inode_operations = {
.create = xfs_vn_create,
.lookup = xfs_vn_ci_lookup,
.link = xfs_vn_link,
.unlink = xfs_vn_unlink,
.symlink = xfs_vn_symlink,
.mkdir = xfs_vn_mkdir,
/*
* Yes, XFS uses the same method for rmdir and unlink.
*
* There are some subtile differences deeper in the code,
* but we use S_ISDIR to check for those.
*/
.rmdir = xfs_vn_unlink,
.mknod = xfs_vn_mknod,
.rename = xfs_vn_rename,
.get_acl = xfs_get_acl,
.set_acl = xfs_set_acl,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
};
static const struct inode_operations xfs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = xfs_vn_follow_link,
.put_link = kfree_put_link,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.removexattr = generic_removexattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
};
STATIC void
xfs_diflags_to_iflags(
struct inode *inode,
struct xfs_inode *ip)
{
if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
inode->i_flags |= S_IMMUTABLE;
else
inode->i_flags &= ~S_IMMUTABLE;
if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
inode->i_flags |= S_APPEND;
else
inode->i_flags &= ~S_APPEND;
if (ip->i_d.di_flags & XFS_DIFLAG_SYNC)
inode->i_flags |= S_SYNC;
else
inode->i_flags &= ~S_SYNC;
if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
else
inode->i_flags &= ~S_NOATIME;
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
xfs: prevent stack overflows from page cache allocation Page cache allocation doesn't always go through ->begin_write and hence we don't always get the opportunity to set the allocation context to GFP_NOFS. Failing to do this means we open up the direct relcaim stack to recurse into the filesystem and consume a significant amount of stack. On RHEL6.4 kernels we are seeing ra_submit() and generic_file_splice_read() from an nfsd context recursing into the filesystem via the inode cache shrinker and evicting inodes. This is causing truncation to be run (e.g EOF block freeing) and causing bmap btree block merges and free space btree block splits to occur. These btree manipulations are occurring with the call chain already 30 functions deep and hence there is not enough stack space to complete such operations. To avoid these specific overruns, we need to prevent the page cache allocation from recursing via direct reclaim. We can do that because the allocation functions take the allocation context from that which is stored in the mapping for the inode. We don't set that right now, so the default is GFP_HIGHUSER_MOVABLE, which is effectively a GFP_KERNEL context. We need it to be the equivalent of GFP_NOFS, so when we initialise an inode, set the mapping gfp mask appropriately. This makes the use of AOP_FLAG_NOFS redundant from other parts of the XFS IO path, so get rid of it. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-10-29 19:11:57 +08:00
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
/* make the inode look hashed for the writeback code */
hlist_add_fake(&inode->i_hash);
inode->i_mode = ip->i_d.di_mode;
set_nlink(inode, ip->i_d.di_nlink);
inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
break;
}
inode->i_generation = ip->i_d.di_gen;
i_size_write(inode, ip->i_d.di_size);
inode->i_atime.tv_sec = ip->i_d.di_atime.t_sec;
inode->i_atime.tv_nsec = ip->i_d.di_atime.t_nsec;
inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec;
inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec;
inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
xfs_diflags_to_iflags(inode, ip);
ip->d_ops = ip->i_mount->m_nondir_inode_ops;
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
xfs: abstract the differences in dir2/dir3 via an ops vector Lots of the dir code now goes through switches to determine what is the correct on-disk format to parse. It generally involves a "xfs_sbversion_hasfoo" check, deferencing the superblock version and feature fields and hence touching several cache lines per operation in the process. Some operations do multiple checks because they nest conditional operations and they don't pass the information in a direct fashion between each other. Hence, add an ops vector to the xfs_inode structure that is configured when the inode is initialised to point to all the correct decode and encoding operations. This will significantly reduce the branchiness and cacheline footprint of the directory object decoding and encoding. This is the first patch in a series of conversion patches. It will introduce the ops structure, the setup of it and add the first operation to the vector. Subsequent patches will convert directory ops one at a time to keep the changes simple and obvious. Just this patch shows the benefit of such an approach on code size. Just converting the two shortform dir operations as this patch does decreases the built binary size by ~1500 bytes: $ size fs/xfs/xfs.o.orig fs/xfs/xfs.o.p1 text data bss dec hex filename 794490 96802 1096 892388 d9de4 fs/xfs/xfs.o.orig 792986 96802 1096 890884 d9804 fs/xfs/xfs.o.p1 $ That's a significant decrease in the instruction cache footprint of the directory code for such a simple change, and indicates that this approach is definitely worth pursuing further. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-10-29 19:11:46 +08:00
ip->d_ops = ip->i_mount->m_dir_inode_ops;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
xfs: prevent stack overflows from page cache allocation Page cache allocation doesn't always go through ->begin_write and hence we don't always get the opportunity to set the allocation context to GFP_NOFS. Failing to do this means we open up the direct relcaim stack to recurse into the filesystem and consume a significant amount of stack. On RHEL6.4 kernels we are seeing ra_submit() and generic_file_splice_read() from an nfsd context recursing into the filesystem via the inode cache shrinker and evicting inodes. This is causing truncation to be run (e.g EOF block freeing) and causing bmap btree block merges and free space btree block splits to occur. These btree manipulations are occurring with the call chain already 30 functions deep and hence there is not enough stack space to complete such operations. To avoid these specific overruns, we need to prevent the page cache allocation from recursing via direct reclaim. We can do that because the allocation functions take the allocation context from that which is stored in the mapping for the inode. We don't set that right now, so the default is GFP_HIGHUSER_MOVABLE, which is effectively a GFP_KERNEL context. We need it to be the equivalent of GFP_NOFS, so when we initialise an inode, set the mapping gfp mask appropriately. This makes the use of AOP_FLAG_NOFS redundant from other parts of the XFS IO path, so get rid of it. Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Ben Myers <bpm@sgi.com>
2013-10-29 19:11:57 +08:00
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
/*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
if (!XFS_IFORK_Q(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}