OpenCloudOS-Kernel/fs/xfs/xfs_iops.c

1321 lines
34 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#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_inode.h"
#include "xfs_acl.h"
#include "xfs_quota.h"
xfs: Set up infrastructure for log attribute replay Currently attributes are modified directly across one or more transactions. But they are not logged or replayed in the event of an error. The goal of log attr replay is to enable logging and replaying of attribute operations using the existing delayed operations infrastructure. This will later enable the attributes to become part of larger multi part operations that also must first be recorded to the log. This is mostly of interest in the scheme of parent pointers which would need to maintain an attribute containing parent inode information any time an inode is moved, created, or removed. Parent pointers would then be of interest to any feature that would need to quickly derive an inode path from the mount point. Online scrub, nfs lookups and fs grow or shrink operations are all features that could take advantage of this. This patch adds two new log item types for setting or removing attributes as deferred operations. The xfs_attri_log_item will log an intent to set or remove an attribute. The corresponding xfs_attrd_log_item holds a reference to the xfs_attri_log_item and is freed once the transaction is done. Both log items use a generic xfs_attr_log_format structure that contains the attribute name, value, flags, inode, and an op_flag that indicates if the operations is a set or remove. [dchinner: added extra little bits needed for intent whiteouts] Signed-off-by: Allison Henderson <allison.henderson@oracle.com> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Dave Chinner <david@fromorbit.com>
2022-05-04 10:41:02 +08:00
#include "xfs_da_format.h"
#include "xfs_da_btree.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"
#include "xfs_dir2.h"
#include "xfs_iomap.h"
#include "xfs_error.h"
#include "xfs_ioctl.h"
#include "xfs_xattr.h"
#include <linux/posix_acl.h>
#include <linux/security.h>
#include <linux/iversion.h>
#include <linux/fiemap.h>
/*
* Directories have different lock order w.r.t. mmap_lock 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_lock 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++) {
struct xfs_da_args args = {
.dp = ip,
.attr_filter = XFS_ATTR_SECURE,
.name = xattr->name,
.namelen = strlen(xattr->name),
.value = xattr->value,
.valuelen = xattr->value_len,
};
error = xfs_attr_change(&args);
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).
*/
int
xfs_inode_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,
struct dentry *dentry)
{
namep->name = dentry->d_name.name;
namep->len = dentry->d_name.len;
namep->type = XFS_DIR3_FT_UNKNOWN;
}
static int
xfs_dentry_mode_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;
namep->type = xfs_mode_to_ftype(mode);
if (unlikely(namep->type == XFS_DIR3_FT_UNKNOWN))
return -EFSCORRUPTED;
return 0;
}
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_inode_init_security we must back out.
* ENOSPC can hit here, among other things.
*/
xfs_dentry_to_name(&teardown, dentry);
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
}
xfs: initialise attr fork on inode create When we allocate a new inode, we often need to add an attribute to the inode as part of the create. This can happen as a result of needing to add default ACLs or security labels before the inode is made visible to userspace. This is highly inefficient right now. We do the create transaction to allocate the inode, then we do an "add attr fork" transaction to modify the just created empty inode to set the inode fork offset to allow attributes to be stored, then we go and do the attribute creation. This means 3 transactions instead of 1 to allocate an inode, and this greatly increases the load on the CIL commit code, resulting in excessive contention on the CIL spin locks and performance degradation: 18.99% [kernel] [k] __pv_queued_spin_lock_slowpath 3.57% [kernel] [k] do_raw_spin_lock 2.51% [kernel] [k] __raw_callee_save___pv_queued_spin_unlock 2.48% [kernel] [k] memcpy 2.34% [kernel] [k] xfs_log_commit_cil The typical profile resulting from running fsmark on a selinux enabled filesytem is adds this overhead to the create path: - 15.30% xfs_init_security - 15.23% security_inode_init_security - 13.05% xfs_initxattrs - 12.94% xfs_attr_set - 6.75% xfs_bmap_add_attrfork - 5.51% xfs_trans_commit - 5.48% __xfs_trans_commit - 5.35% xfs_log_commit_cil - 3.86% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.70% xfs_trans_alloc 0.52% xfs_trans_reserve - 5.41% xfs_attr_set_args - 5.39% xfs_attr_set_shortform.constprop.0 - 4.46% xfs_trans_commit - 4.46% __xfs_trans_commit - 4.33% xfs_log_commit_cil - 2.74% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath 0.60% xfs_inode_item_format 0.90% xfs_attr_try_sf_addname - 1.99% selinux_inode_init_security - 1.02% security_sid_to_context_force - 1.00% security_sid_to_context_core - 0.92% sidtab_entry_to_string - 0.90% sidtab_sid2str_get 0.59% sidtab_sid2str_put.part.0 - 0.82% selinux_determine_inode_label - 0.77% security_transition_sid 0.70% security_compute_sid.part.0 And fsmark creation rate performance drops by ~25%. The key point to note here is that half the additional overhead comes from adding the attribute fork to the newly created inode. That's crazy, considering we can do this same thing at inode create time with a couple of lines of code and no extra overhead. So, if we know we are going to add an attribute immediately after creating the inode, let's just initialise the attribute fork inside the create transaction and chop that whole chunk of code out of the create fast path. This completely removes the performance drop caused by enabling SELinux, and the profile looks like: - 8.99% xfs_init_security - 9.00% security_inode_init_security - 6.43% xfs_initxattrs - 6.37% xfs_attr_set - 5.45% xfs_attr_set_args - 5.42% xfs_attr_set_shortform.constprop.0 - 4.51% xfs_trans_commit - 4.54% __xfs_trans_commit - 4.59% xfs_log_commit_cil - 2.67% _raw_spin_lock - 3.28% do_raw_spin_lock 3.08% __pv_queued_spin_lock_slowpath 0.66% xfs_inode_item_format - 0.90% xfs_attr_try_sf_addname - 0.60% xfs_trans_alloc - 2.35% selinux_inode_init_security - 1.25% security_sid_to_context_force - 1.21% security_sid_to_context_core - 1.19% sidtab_entry_to_string - 1.20% sidtab_sid2str_get - 0.86% sidtab_sid2str_put.part.0 - 0.62% _raw_spin_lock_irqsave - 0.77% do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.84% selinux_determine_inode_label - 0.83% security_transition_sid 0.86% security_compute_sid.part.0 Which indicates the XFS overhead of creating the selinux xattr has been halved. This doesn't fix the CIL lock contention problem, just means it's not a limiting factor for this workload. Lock contention in the security subsystems is going to be an issue soon, though... Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> [djwong: fix compilation error when CONFIG_SECURITY=n] Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Gao Xiang <hsiangkao@redhat.com>
2021-03-23 00:52:03 +08:00
/*
* Check to see if we are likely to need an extended attribute to be added to
* the inode we are about to allocate. This allows the attribute fork to be
* created during the inode allocation, reducing the number of transactions we
* need to do in this fast path.
*
* The security checks are optimistic, but not guaranteed. The two LSMs that
* require xattrs to be added here (selinux and smack) are also the only two
* LSMs that add a sb->s_security structure to the superblock. Hence if security
* is enabled and sb->s_security is set, we have a pretty good idea that we are
* going to be asked to add a security xattr immediately after allocating the
* xfs inode and instantiating the VFS inode.
*/
static inline bool
xfs_create_need_xattr(
struct inode *dir,
struct posix_acl *default_acl,
struct posix_acl *acl)
{
if (acl)
return true;
if (default_acl)
return true;
#if IS_ENABLED(CONFIG_SECURITY)
if (dir->i_sb->s_security)
return true;
#endif
return false;
}
STATIC int
xfs_generic_create(
struct user_namespace *mnt_userns,
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;
} else {
rdev = 0;
}
error = posix_acl_create(dir, &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);
if (unlikely(error))
goto out_free_acl;
if (!tmpfile) {
error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
xfs: initialise attr fork on inode create When we allocate a new inode, we often need to add an attribute to the inode as part of the create. This can happen as a result of needing to add default ACLs or security labels before the inode is made visible to userspace. This is highly inefficient right now. We do the create transaction to allocate the inode, then we do an "add attr fork" transaction to modify the just created empty inode to set the inode fork offset to allow attributes to be stored, then we go and do the attribute creation. This means 3 transactions instead of 1 to allocate an inode, and this greatly increases the load on the CIL commit code, resulting in excessive contention on the CIL spin locks and performance degradation: 18.99% [kernel] [k] __pv_queued_spin_lock_slowpath 3.57% [kernel] [k] do_raw_spin_lock 2.51% [kernel] [k] __raw_callee_save___pv_queued_spin_unlock 2.48% [kernel] [k] memcpy 2.34% [kernel] [k] xfs_log_commit_cil The typical profile resulting from running fsmark on a selinux enabled filesytem is adds this overhead to the create path: - 15.30% xfs_init_security - 15.23% security_inode_init_security - 13.05% xfs_initxattrs - 12.94% xfs_attr_set - 6.75% xfs_bmap_add_attrfork - 5.51% xfs_trans_commit - 5.48% __xfs_trans_commit - 5.35% xfs_log_commit_cil - 3.86% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.70% xfs_trans_alloc 0.52% xfs_trans_reserve - 5.41% xfs_attr_set_args - 5.39% xfs_attr_set_shortform.constprop.0 - 4.46% xfs_trans_commit - 4.46% __xfs_trans_commit - 4.33% xfs_log_commit_cil - 2.74% _raw_spin_lock - do_raw_spin_lock __pv_queued_spin_lock_slowpath 0.60% xfs_inode_item_format 0.90% xfs_attr_try_sf_addname - 1.99% selinux_inode_init_security - 1.02% security_sid_to_context_force - 1.00% security_sid_to_context_core - 0.92% sidtab_entry_to_string - 0.90% sidtab_sid2str_get 0.59% sidtab_sid2str_put.part.0 - 0.82% selinux_determine_inode_label - 0.77% security_transition_sid 0.70% security_compute_sid.part.0 And fsmark creation rate performance drops by ~25%. The key point to note here is that half the additional overhead comes from adding the attribute fork to the newly created inode. That's crazy, considering we can do this same thing at inode create time with a couple of lines of code and no extra overhead. So, if we know we are going to add an attribute immediately after creating the inode, let's just initialise the attribute fork inside the create transaction and chop that whole chunk of code out of the create fast path. This completely removes the performance drop caused by enabling SELinux, and the profile looks like: - 8.99% xfs_init_security - 9.00% security_inode_init_security - 6.43% xfs_initxattrs - 6.37% xfs_attr_set - 5.45% xfs_attr_set_args - 5.42% xfs_attr_set_shortform.constprop.0 - 4.51% xfs_trans_commit - 4.54% __xfs_trans_commit - 4.59% xfs_log_commit_cil - 2.67% _raw_spin_lock - 3.28% do_raw_spin_lock 3.08% __pv_queued_spin_lock_slowpath 0.66% xfs_inode_item_format - 0.90% xfs_attr_try_sf_addname - 0.60% xfs_trans_alloc - 2.35% selinux_inode_init_security - 1.25% security_sid_to_context_force - 1.21% security_sid_to_context_core - 1.19% sidtab_entry_to_string - 1.20% sidtab_sid2str_get - 0.86% sidtab_sid2str_put.part.0 - 0.62% _raw_spin_lock_irqsave - 0.77% do_raw_spin_lock __pv_queued_spin_lock_slowpath - 0.84% selinux_determine_inode_label - 0.83% security_transition_sid 0.86% security_compute_sid.part.0 Which indicates the XFS overhead of creating the selinux xattr has been halved. This doesn't fix the CIL lock contention problem, just means it's not a limiting factor for this workload. Lock contention in the security subsystems is going to be an issue soon, though... Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> [djwong: fix compilation error when CONFIG_SECURITY=n] Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Gao Xiang <hsiangkao@redhat.com>
2021-03-23 00:52:03 +08:00
xfs_create_need_xattr(dir, default_acl, acl),
&ip);
} else {
error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
}
if (unlikely(error))
goto out_free_acl;
inode = VFS_I(ip);
error = xfs_inode_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
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;
}
xfs_setup_iops(ip);
if (tmpfile) {
/*
* The VFS requires that any inode fed to d_tmpfile must have
* nlink == 1 so that it can decrement the nlink in d_tmpfile.
* However, we created the temp file with nlink == 0 because
* we're not allowed to put an inode with nlink > 0 on the
* unlinked list. Therefore we have to set nlink to 1 so that
* d_tmpfile can immediately set it back to zero.
*/
set_nlink(inode, 1);
d_tmpfile(dentry, inode);
} else
d_instantiate(dentry, inode);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
xfs_finish_inode_setup(ip);
out_free_acl:
posix_acl_release(default_acl);
posix_acl_release(acl);
return error;
out_cleanup_inode:
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
xfs_finish_inode_setup(ip);
if (!tmpfile)
xfs_cleanup_inode(dir, inode, dentry);
xfs_irele(ip);
goto out_free_acl;
}
STATIC int
xfs_vn_mknod(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
dev_t rdev)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, false);
}
STATIC int
xfs_vn_create(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode,
bool flags)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, false);
}
STATIC int
xfs_vn_mkdir(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0,
false);
}
STATIC struct dentry *
xfs_vn_lookup(
struct inode *dir,
struct dentry *dentry,
unsigned int flags)
{
struct inode *inode;
struct xfs_inode *cip;
struct xfs_name name;
int error;
if (dentry->d_name.len >= MAXNAMELEN)
return ERR_PTR(-ENAMETOOLONG);
xfs_dentry_to_name(&name, dentry);
error = xfs_lookup(XFS_I(dir), &name, &cip, NULL);
if (likely(!error))
inode = VFS_I(cip);
else if (likely(error == -ENOENT))
inode = NULL;
else
inode = ERR_PTR(error);
return d_splice_alias(inode, 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_dentry_to_name(&xname, dentry);
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 = d_inode(old_dentry);
struct xfs_name name;
int error;
error = xfs_dentry_mode_to_name(&name, dentry, inode->i_mode);
if (unlikely(error))
return error;
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_dentry_to_name(&name, dentry);
error = xfs_remove(XFS_I(dir), &name, XFS_I(d_inode(dentry)));
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_has_asciici(XFS_M(dir->i_sb)))
d_invalidate(dentry);
return 0;
}
STATIC int
xfs_vn_symlink(
struct user_namespace *mnt_userns,
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);
error = xfs_dentry_mode_to_name(&name, dentry, mode);
if (unlikely(error))
goto out;
error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip);
if (unlikely(error))
goto out;
inode = VFS_I(cip);
error = xfs_inode_init_security(inode, dir, &dentry->d_name);
if (unlikely(error))
goto out_cleanup_inode;
xfs_setup_iops(cip);
d_instantiate(dentry, inode);
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
xfs_finish_inode_setup(cip);
return 0;
out_cleanup_inode:
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
xfs_finish_inode_setup(cip);
xfs_cleanup_inode(dir, inode, dentry);
xfs_irele(cip);
out:
return error;
}
STATIC int
xfs_vn_rename(
struct user_namespace *mnt_userns,
struct inode *odir,
struct dentry *odentry,
struct inode *ndir,
struct dentry *ndentry,
unsigned int flags)
{
struct inode *new_inode = d_inode(ndentry);
int omode = 0;
int error;
struct xfs_name oname;
struct xfs_name nname;
xfs: add RENAME_WHITEOUT support Whiteouts are used by overlayfs - it has a crazy convention that a whiteout is a character device inode with a major:minor of 0:0. Because it's not documented anywhere, here's an example of what RENAME_WHITEOUT does on ext4: # echo foo > /mnt/scratch/foo # echo bar > /mnt/scratch/bar # ls -l /mnt/scratch total 24 -rw-r--r-- 1 root root 4 Feb 11 20:22 bar -rw-r--r-- 1 root root 4 Feb 11 20:22 foo drwx------ 2 root root 16384 Feb 11 20:18 lost+found # src/renameat2 -w /mnt/scratch/foo /mnt/scratch/bar # ls -l /mnt/scratch total 20 -rw-r--r-- 1 root root 4 Feb 11 20:22 bar c--------- 1 root root 0, 0 Feb 11 20:23 foo drwx------ 2 root root 16384 Feb 11 20:18 lost+found # cat /mnt/scratch/bar foo # In XFS rename terms, the operation that has been done is that source (foo) has been moved to the target (bar), which is like a nomal rename operation, but rather than the source being removed, it have been replaced with a whiteout. We can't allocate whiteout inodes within the rename transaction due to allocation being a multi-commit transaction: rename needs to be a single, atomic commit. Hence we have several options here, form most efficient to least efficient: - use DT_WHT in the target dirent and do no whiteout inode allocation. The main issue with this approach is that we need hooks in lookup to create a virtual chardev inode to present to userspace and in places where we might need to modify the dirent e.g. unlink. Overlayfs also needs to be taught about DT_WHT. Most invasive change, lowest overhead. - create a special whiteout inode in the root directory (e.g. a ".wino" dirent) and then hardlink every new whiteout to it. This means we only need to create a single whiteout inode, and rename simply creates a hardlink to it. We can use DT_WHT for these, though using DT_CHR means we won't have to modify overlayfs, nor anything in userspace. Downside is we have to look up the whiteout inode on every operation and create it if it doesn't exist. - copy ext4: create a special whiteout chardev inode for every whiteout. This is more complex than the above options because of the lack of atomicity between inode creation and the rename operation, requiring us to create a tmpfile inode and then linking it into the directory structure during the rename. At least with a tmpfile inode crashes between the create and rename doesn't leave unreferenced inodes or directory pollution around. By far the simplest thing to do in the short term is to copy ext4. While it is the most inefficient way of supporting whiteouts, but as an initial implementation we can simply reuse existing functions and add a small amount of extra code the the rename operation. When we get full whiteout support in the VFS (via the dentry cache) we can then look to supporting DT_WHT method outlined as the first method of supporting whiteouts. But until then, we'll stick with what overlayfs expects us to be: dumb and stupid. Signed-off-by: Dave Chinner <dchinner@redhat.com>
2015-03-25 11:08:08 +08:00
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
/* if we are exchanging files, we need to set i_mode of both files */
if (flags & RENAME_EXCHANGE)
omode = d_inode(ndentry)->i_mode;
error = xfs_dentry_mode_to_name(&oname, odentry, omode);
if (omode && unlikely(error))
return error;
error = xfs_dentry_mode_to_name(&nname, ndentry,
d_inode(odentry)->i_mode);
if (unlikely(error))
return error;
return xfs_rename(mnt_userns, XFS_I(odir), &oname,
XFS_I(d_inode(odentry)), XFS_I(ndir), &nname,
new_inode ? XFS_I(new_inode) : NULL, flags);
}
/*
* 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 const char *
xfs_vn_get_link(
struct dentry *dentry,
struct inode *inode,
struct delayed_call *done)
{
char *link;
int error = -ENOMEM;
if (!dentry)
return ERR_PTR(-ECHILD);
link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL);
if (!link)
goto out_err;
error = xfs_readlink(XFS_I(d_inode(dentry)), link);
if (unlikely(error))
goto out_kfree;
set_delayed_call(done, kfree_link, link);
return link;
out_kfree:
kfree(link);
out_err:
return ERR_PTR(error);
}
static uint32_t
xfs_stat_blksize(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
/*
* If the file blocks are being allocated from a realtime volume, then
* always return the realtime extent size.
*/
if (XFS_IS_REALTIME_INODE(ip))
return XFS_FSB_TO_B(mp, xfs_get_extsz_hint(ip));
/*
* Allow large block sizes to be reported to userspace programs if the
* "largeio" mount option is used.
*
* If compatibility mode is specified, simply return the basic unit of
* caching so that we don't get inefficient read/modify/write I/O from
* user apps. Otherwise....
*
* If the underlying volume is a stripe, then return the stripe width in
* bytes as the recommended I/O size. It is not a stripe and we've set a
* default buffered I/O size, return that, otherwise return the compat
* default.
*/
if (xfs_has_large_iosize(mp)) {
if (mp->m_swidth)
return XFS_FSB_TO_B(mp, mp->m_swidth);
if (xfs_has_allocsize(mp))
return 1U << mp->m_allocsize_log;
}
return PAGE_SIZE;
}
STATIC int
xfs_vn_getattr(
struct user_namespace *mnt_userns,
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
const struct path *path,
struct kstat *stat,
u32 request_mask,
unsigned int query_flags)
{
statx: Add a system call to make enhanced file info available Add a system call to make extended file information available, including file creation and some attribute flags where available through the underlying filesystem. The getattr inode operation is altered to take two additional arguments: a u32 request_mask and an unsigned int flags that indicate the synchronisation mode. This change is propagated to the vfs_getattr*() function. Functions like vfs_stat() are now inline wrappers around new functions vfs_statx() and vfs_statx_fd() to reduce stack usage. ======== OVERVIEW ======== The idea was initially proposed as a set of xattrs that could be retrieved with getxattr(), but the general preference proved to be for a new syscall with an extended stat structure. A number of requests were gathered for features to be included. The following have been included: (1) Make the fields a consistent size on all arches and make them large. (2) Spare space, request flags and information flags are provided for future expansion. (3) Better support for the y2038 problem [Arnd Bergmann] (tv_sec is an __s64). (4) Creation time: The SMB protocol carries the creation time, which could be exported by Samba, which will in turn help CIFS make use of FS-Cache as that can be used for coherency data (stx_btime). This is also specified in NFSv4 as a recommended attribute and could be exported by NFSD [Steve French]. (5) Lightweight stat: Ask for just those details of interest, and allow a netfs (such as NFS) to approximate anything not of interest, possibly without going to the server [Trond Myklebust, Ulrich Drepper, Andreas Dilger] (AT_STATX_DONT_SYNC). (6) Heavyweight stat: Force a netfs to go to the server, even if it thinks its cached attributes are up to date [Trond Myklebust] (AT_STATX_FORCE_SYNC). And the following have been left out for future extension: (7) Data version number: Could be used by userspace NFS servers [Aneesh Kumar]. Can also be used to modify fill_post_wcc() in NFSD which retrieves i_version directly, but has just called vfs_getattr(). It could get it from the kstat struct if it used vfs_xgetattr() instead. (There's disagreement on the exact semantics of a single field, since not all filesystems do this the same way). (8) BSD stat compatibility: Including more fields from the BSD stat such as creation time (st_btime) and inode generation number (st_gen) [Jeremy Allison, Bernd Schubert]. (9) Inode generation number: Useful for FUSE and userspace NFS servers [Bernd Schubert]. (This was asked for but later deemed unnecessary with the open-by-handle capability available and caused disagreement as to whether it's a security hole or not). (10) Extra coherency data may be useful in making backups [Andreas Dilger]. (No particular data were offered, but things like last backup timestamp, the data version number and the DOS archive bit would come into this category). (11) Allow the filesystem to indicate what it can/cannot provide: A filesystem can now say it doesn't support a standard stat feature if that isn't available, so if, for instance, inode numbers or UIDs don't exist or are fabricated locally... (This requires a separate system call - I have an fsinfo() call idea for this). (12) Store a 16-byte volume ID in the superblock that can be returned in struct xstat [Steve French]. (Deferred to fsinfo). (13) Include granularity fields in the time data to indicate the granularity of each of the times (NFSv4 time_delta) [Steve French]. (Deferred to fsinfo). (14) FS_IOC_GETFLAGS value. These could be translated to BSD's st_flags. Note that the Linux IOC flags are a mess and filesystems such as Ext4 define flags that aren't in linux/fs.h, so translation in the kernel may be a necessity (or, possibly, we provide the filesystem type too). (Some attributes are made available in stx_attributes, but the general feeling was that the IOC flags were to ext[234]-specific and shouldn't be exposed through statx this way). (15) Mask of features available on file (eg: ACLs, seclabel) [Brad Boyer, Michael Kerrisk]. (Deferred, probably to fsinfo. Finding out if there's an ACL or seclabal might require extra filesystem operations). (16) Femtosecond-resolution timestamps [Dave Chinner]. (A __reserved field has been left in the statx_timestamp struct for this - if there proves to be a need). (17) A set multiple attributes syscall to go with this. =============== NEW SYSTEM CALL =============== The new system call is: int ret = statx(int dfd, const char *filename, unsigned int flags, unsigned int mask, struct statx *buffer); The dfd, filename and flags parameters indicate the file to query, in a similar way to fstatat(). There is no equivalent of lstat() as that can be emulated with statx() by passing AT_SYMLINK_NOFOLLOW in flags. There is also no equivalent of fstat() as that can be emulated by passing a NULL filename to statx() with the fd of interest in dfd. Whether or not statx() synchronises the attributes with the backing store can be controlled by OR'ing a value into the flags argument (this typically only affects network filesystems): (1) AT_STATX_SYNC_AS_STAT tells statx() to behave as stat() does in this respect. (2) AT_STATX_FORCE_SYNC will require a network filesystem to synchronise its attributes with the server - which might require data writeback to occur to get the timestamps correct. (3) AT_STATX_DONT_SYNC will suppress synchronisation with the server in a network filesystem. The resulting values should be considered approximate. mask is a bitmask indicating the fields in struct statx that are of interest to the caller. The user should set this to STATX_BASIC_STATS to get the basic set returned by stat(). It should be noted that asking for more information may entail extra I/O operations. buffer points to the destination for the data. This must be 256 bytes in size. ====================== MAIN ATTRIBUTES RECORD ====================== The following structures are defined in which to return the main attribute set: struct statx_timestamp { __s64 tv_sec; __s32 tv_nsec; __s32 __reserved; }; struct statx { __u32 stx_mask; __u32 stx_blksize; __u64 stx_attributes; __u32 stx_nlink; __u32 stx_uid; __u32 stx_gid; __u16 stx_mode; __u16 __spare0[1]; __u64 stx_ino; __u64 stx_size; __u64 stx_blocks; __u64 __spare1[1]; struct statx_timestamp stx_atime; struct statx_timestamp stx_btime; struct statx_timestamp stx_ctime; struct statx_timestamp stx_mtime; __u32 stx_rdev_major; __u32 stx_rdev_minor; __u32 stx_dev_major; __u32 stx_dev_minor; __u64 __spare2[14]; }; The defined bits in request_mask and stx_mask are: STATX_TYPE Want/got stx_mode & S_IFMT STATX_MODE Want/got stx_mode & ~S_IFMT STATX_NLINK Want/got stx_nlink STATX_UID Want/got stx_uid STATX_GID Want/got stx_gid STATX_ATIME Want/got stx_atime{,_ns} STATX_MTIME Want/got stx_mtime{,_ns} STATX_CTIME Want/got stx_ctime{,_ns} STATX_INO Want/got stx_ino STATX_SIZE Want/got stx_size STATX_BLOCKS Want/got stx_blocks STATX_BASIC_STATS [The stuff in the normal stat struct] STATX_BTIME Want/got stx_btime{,_ns} STATX_ALL [All currently available stuff] stx_btime is the file creation time, stx_mask is a bitmask indicating the data provided and __spares*[] are where as-yet undefined fields can be placed. Time fields are structures with separate seconds and nanoseconds fields plus a reserved field in case we want to add even finer resolution. Note that times will be negative if before 1970; in such a case, the nanosecond fields will also be negative if not zero. The bits defined in the stx_attributes field convey information about a file, how it is accessed, where it is and what it does. The following attributes map to FS_*_FL flags and are the same numerical value: STATX_ATTR_COMPRESSED File is compressed by the fs STATX_ATTR_IMMUTABLE File is marked immutable STATX_ATTR_APPEND File is append-only STATX_ATTR_NODUMP File is not to be dumped STATX_ATTR_ENCRYPTED File requires key to decrypt in fs Within the kernel, the supported flags are listed by: KSTAT_ATTR_FS_IOC_FLAGS [Are any other IOC flags of sufficient general interest to be exposed through this interface?] New flags include: STATX_ATTR_AUTOMOUNT Object is an automount trigger These are for the use of GUI tools that might want to mark files specially, depending on what they are. Fields in struct statx come in a number of classes: (0) stx_dev_*, stx_blksize. These are local system information and are always available. (1) stx_mode, stx_nlinks, stx_uid, stx_gid, stx_[amc]time, stx_ino, stx_size, stx_blocks. These will be returned whether the caller asks for them or not. The corresponding bits in stx_mask will be set to indicate whether they actually have valid values. If the caller didn't ask for them, then they may be approximated. For example, NFS won't waste any time updating them from the server, unless as a byproduct of updating something requested. If the values don't actually exist for the underlying object (such as UID or GID on a DOS file), then the bit won't be set in the stx_mask, even if the caller asked for the value. In such a case, the returned value will be a fabrication. Note that there are instances where the type might not be valid, for instance Windows reparse points. (2) stx_rdev_*. This will be set only if stx_mode indicates we're looking at a blockdev or a chardev, otherwise will be 0. (3) stx_btime. Similar to (1), except this will be set to 0 if it doesn't exist. ======= TESTING ======= The following test program can be used to test the statx system call: samples/statx/test-statx.c Just compile and run, passing it paths to the files you want to examine. The file is built automatically if CONFIG_SAMPLES is enabled. Here's some example output. Firstly, an NFS directory that crosses to another FSID. Note that the AUTOMOUNT attribute is set because transiting this directory will cause d_automount to be invoked by the VFS. [root@andromeda ~]# /tmp/test-statx -A /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:26 Inode: 1703937 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Attributes: 0000000000001000 (-------- -------- -------- -------- -------- -------- ---m---- --------) Secondly, the result of automounting on that directory. [root@andromeda ~]# /tmp/test-statx /warthog/data statx(/warthog/data) = 0 results=7ff Size: 4096 Blocks: 8 IO Block: 1048576 directory Device: 00:27 Inode: 2 Links: 125 Access: (3777/drwxrwxrwx) Uid: 0 Gid: 4041 Access: 2016-11-24 09:02:12.219699527+0000 Modify: 2016-11-17 10:44:36.225653653+0000 Change: 2016-11-17 10:44:36.225653653+0000 Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2017-02-01 00:46:22 +08:00
struct inode *inode = d_inode(path->dentry);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
trace_xfs_getattr(ip);
if (xfs_is_shutdown(mp))
return -EIO;
stat->size = XFS_ISIZE(ip);
stat->dev = inode->i_sb->s_dev;
stat->mode = inode->i_mode;
stat->nlink = inode->i_nlink;
stat->uid = i_uid_into_mnt(mnt_userns, inode);
stat->gid = i_gid_into_mnt(mnt_userns, inode);
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_nblocks + ip->i_delayed_blks);
if (xfs_has_v3inodes(mp)) {
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
stat->btime = ip->i_crtime;
}
}
/*
* Note: If you add another clause to set an attribute flag, please
* update attributes_mask below.
*/
if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (ip->i_diflags & XFS_DIFLAG_APPEND)
stat->attributes |= STATX_ATTR_APPEND;
if (ip->i_diflags & XFS_DIFLAG_NODUMP)
stat->attributes |= STATX_ATTR_NODUMP;
stat->attributes_mask |= (STATX_ATTR_IMMUTABLE |
STATX_ATTR_APPEND |
STATX_ATTR_NODUMP);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
stat->blksize = BLKDEV_IOSIZE;
stat->rdev = inode->i_rdev;
break;
default:
stat->blksize = xfs_stat_blksize(ip);
stat->rdev = 0;
break;
}
return 0;
}
static int
xfs_vn_change_ok(
struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
struct xfs_mount *mp = XFS_I(d_inode(dentry))->i_mount;
if (xfs_is_readonly(mp))
return -EROFS;
if (xfs_is_shutdown(mp))
return -EIO;
return setattr_prepare(mnt_userns, dentry, iattr);
}
/*
* Set non-size attributes of an inode.
*
* Caution: The caller of this function is responsible for calling
* setattr_prepare() or otherwise verifying the change is fine.
*/
static int
xfs_setattr_nonsize(
struct user_namespace *mnt_userns,
struct xfs_inode *ip,
struct iattr *iattr)
{
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;
kgid_t gid = GLOBAL_ROOT_GID;
struct xfs_dquot *udqp = NULL, *gdqp = NULL;
struct xfs_dquot *old_udqp = NULL, *old_gdqp = NULL;
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)) {
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 22:14:54 +08:00
uid = from_vfsuid(mnt_userns, i_user_ns(inode),
iattr->ia_vfsuid);
qflags |= XFS_QMOPT_UQUOTA;
} else {
uid = inode->i_uid;
}
if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 22:14:54 +08:00
gid = from_vfsgid(mnt_userns, i_user_ns(inode),
iattr->ia_vfsgid);
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, uid, gid, ip->i_projid,
qflags, &udqp, &gdqp, NULL);
if (error)
return error;
}
error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL,
has_capability_noaudit(current, CAP_FOWNER), &tp);
if (error)
goto out_dqrele;
/*
* Register quota modifications in the transaction. Must be the owner
* or privileged. 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.
*/
if (XFS_IS_UQUOTA_ON(mp) &&
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 22:14:54 +08:00
i_uid_needs_update(mnt_userns, iattr, inode)) {
ASSERT(udqp);
old_udqp = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp);
}
if (XFS_IS_GQUOTA_ON(mp) &&
attr: port attribute changes to new types Now that we introduced new infrastructure to increase the type safety for filesystems supporting idmapped mounts port the first part of the vfs over to them. This ports the attribute changes codepaths to rely on the new better helpers using a dedicated type. Before this change we used to take a shortcut and place the actual values that would be written to inode->i_{g,u}id into struct iattr. This had the advantage that we moved idmappings mostly out of the picture early on but it made reasoning about changes more difficult than it should be. The filesystem was never explicitly told that it dealt with an idmapped mount. The transition to the value that needed to be stored in inode->i_{g,u}id appeared way too early and increased the probability of bugs in various codepaths. We know place the same value in struct iattr no matter if this is an idmapped mount or not. The vfs will only deal with type safe vfs{g,u}id_t. This makes it massively safer to perform permission checks as the type will tell us what checks we need to perform and what helpers we need to use. Fileystems raising FS_ALLOW_IDMAP can't simply write ia_vfs{g,u}id to inode->i_{g,u}id since they are different types. Instead they need to use the dedicated vfs{g,u}id_to_k{g,u}id() helpers that map the vfs{g,u}id into the filesystem. The other nice effect is that filesystems like overlayfs don't need to care about idmappings explicitly anymore and can simply set up struct iattr accordingly directly. Link: https://lore.kernel.org/lkml/CAHk-=win6+ahs1EwLkcq8apqLi_1wXFWbrPf340zYEhObpz4jA@mail.gmail.com [1] Link: https://lore.kernel.org/r/20220621141454.2914719-9-brauner@kernel.org Cc: Seth Forshee <sforshee@digitalocean.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Al Viro <viro@zeniv.linux.org.uk> CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee <sforshee@digitalocean.com> Signed-off-by: Christian Brauner (Microsoft) <brauner@kernel.org>
2022-06-21 22:14:54 +08:00
i_gid_needs_update(mnt_userns, iattr, inode)) {
ASSERT(xfs_has_pquotino(mp) || !XFS_IS_PQUOTA_ON(mp));
ASSERT(gdqp);
old_gdqp = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp);
}
xfs: use setattr_copy to set vfs inode attributes Filipe Manana pointed out that XFS' behavior w.r.t. setuid/setgid revocation isn't consistent with btrfs[1] or ext4. Those two filesystems use the VFS function setattr_copy to convey certain attributes from struct iattr into the VFS inode structure. Andrey Zhadchenko reported[2] that XFS uses the wrong user namespace to decide if it should clear setgid and setuid on a file attribute update. This is a second symptom of the problem that Filipe noticed. XFS, on the other hand, open-codes setattr_copy in xfs_setattr_mode, xfs_setattr_nonsize, and xfs_setattr_time. Regrettably, setattr_copy is /not/ a simple copy function; it contains additional logic to clear the setgid bit when setting the mode, and XFS' version no longer matches. The VFS implements its own setuid/setgid stripping logic, which establishes consistent behavior. It's a tad unfortunate that it's scattered across notify_change, should_remove_suid, and setattr_copy but XFS should really follow the Linux VFS. Adapt XFS to use the VFS functions and get rid of the old functions. [1] https://lore.kernel.org/fstests/CAL3q7H47iNQ=Wmk83WcGB-KBJVOEtR9+qGczzCeXJ9Y2KCV25Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-xfs/20220221182218.748084-1-andrey.zhadchenko@virtuozzo.com/ Fixes: 7fa294c8991c ("userns: Allow chown and setgid preservation") Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christian Brauner <brauner@kernel.org>
2022-03-09 02:51:16 +08:00
setattr_copy(mnt_userns, inode, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (xfs_has_wsync(mp))
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(old_udqp);
xfs_qm_dqrele(old_gdqp);
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) {
error = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
if (error)
return error;
}
return 0;
out_dqrele:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return error;
}
/*
* Truncate file. Must have write permission and not be a directory.
*
* Caution: The caller of this function is responsible for calling
* setattr_prepare() or otherwise verifying the change is fine.
*/
STATIC int
xfs_setattr_size(
struct user_namespace *mnt_userns,
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;
bool did_zeroing = false;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|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_df.if_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(mnt_userns, ip, iattr);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip);
if (error)
return error;
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
/*
* File data changes must be complete before we start the transaction to
* modify the inode. 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.
*
* Start with zeroing any data beyond EOF that we may expose on file
* extension, or zeroing out the rest of the block on a downward
* truncate.
*/
if (newsize > oldsize) {
trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
error = xfs_zero_range(ip, oldsize, newsize - oldsize,
&did_zeroing);
} else {
xfs: flush new eof page on truncate to avoid post-eof corruption It is possible to expose non-zeroed post-EOF data in XFS if the new EOF page is dirty, backed by an unwritten block and the truncate happens to race with writeback. iomap_truncate_page() will not zero the post-EOF portion of the page if the underlying block is unwritten. The subsequent call to truncate_setsize() will, but doesn't dirty the page. Therefore, if writeback happens to complete after iomap_truncate_page() (so it still sees the unwritten block) but before truncate_setsize(), the cached page becomes inconsistent with the on-disk block. A mapped read after the associated page is reclaimed or invalidated exposes non-zero post-EOF data. For example, consider the following sequence when run on a kernel modified to explicitly flush the new EOF page within the race window: $ xfs_io -fc "falloc 0 4k" -c fsync /mnt/file $ xfs_io -c "pwrite 0 4k" -c "truncate 1k" /mnt/file ... $ xfs_io -c "mmap 0 4k" -c "mread -v 1k 8" /mnt/file 00000400: 00 00 00 00 00 00 00 00 ........ $ umount /mnt/; mount <dev> /mnt/ $ xfs_io -c "mmap 0 4k" -c "mread -v 1k 8" /mnt/file 00000400: cd cd cd cd cd cd cd cd ........ Update xfs_setattr_size() to explicitly flush the new EOF page prior to the page truncate to ensure iomap has the latest state of the underlying block. Fixes: 68a9f5e7007c ("xfs: implement iomap based buffered write path") Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2020-10-30 05:30:48 +08:00
/*
* iomap won't detect a dirty page over an unwritten block (or a
* cow block over a hole) and subsequently skips zeroing the
* newly post-EOF portion of the page. Flush the new EOF to
* convert the block before the pagecache truncate.
*/
error = filemap_write_and_wait_range(inode->i_mapping, newsize,
newsize);
if (error)
return error;
error = xfs_truncate_page(ip, newsize, &did_zeroing);
}
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
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
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
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), 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.
xfs: truncate pagecache before writeback in xfs_setattr_size() On truncate down, if new size is not block size aligned, we zero the rest of block to avoid exposing stale data to user, and iomap_truncate_page() skips zeroing if the range is already in unwritten state or a hole. Then we writeback from on-disk i_size to the new size if this range hasn't been written to disk yet, and truncate page cache beyond new EOF and set in-core i_size. The problem is that we could write data between di_size and newsize before removing the page cache beyond newsize, as the extents may still be in unwritten state right after a buffer write. As such, the page of data that newsize lies in has not been zeroed by page cache invalidation before it is written, and xfs_do_writepage() hasn't triggered it's "zero data beyond EOF" case because we haven't updated in-core i_size yet. Then a subsequent mmap read could see non-zeros past EOF. I occasionally see this in fsx runs in fstests generic/112, a simplified fsx operation sequence is like (assuming 4k block size xfs): fallocate 0x0 0x1000 0x0 keep_size write 0x0 0x1000 0x0 truncate 0x0 0x800 0x1000 punch_hole 0x0 0x800 0x800 mapread 0x0 0x800 0x800 where fallocate allocates unwritten extent but doesn't update i_size, buffer write populates the page cache and extent is still unwritten, truncate skips zeroing page past new EOF and writes the page to disk, punch_hole invalidates the page cache, at last mapread reads the block back and sees non-zero beyond EOF. Fix it by moving truncate_setsize() to before writeback so the page cache invalidation zeros the partial page at the new EOF. This also triggers "zero data beyond EOF" in xfs_do_writepage() at writeback time, because newsize has been set and page straddles the newsize. Also fixed the wrong 'end' param of filemap_write_and_wait_range() call while we're at it, the 'end' is inclusive and should be 'newsize - 1'. Suggested-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Eryu Guan <eguan@redhat.com> Acked-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-11-02 12:43:50 +08:00
*
* And we update in-core i_size and truncate page cache beyond newsize
* before writeback the [i_disk_size, newsize] range, so we're
* guaranteed not to write stale data past the new EOF on truncate down.
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: truncate pagecache before writeback in xfs_setattr_size() On truncate down, if new size is not block size aligned, we zero the rest of block to avoid exposing stale data to user, and iomap_truncate_page() skips zeroing if the range is already in unwritten state or a hole. Then we writeback from on-disk i_size to the new size if this range hasn't been written to disk yet, and truncate page cache beyond new EOF and set in-core i_size. The problem is that we could write data between di_size and newsize before removing the page cache beyond newsize, as the extents may still be in unwritten state right after a buffer write. As such, the page of data that newsize lies in has not been zeroed by page cache invalidation before it is written, and xfs_do_writepage() hasn't triggered it's "zero data beyond EOF" case because we haven't updated in-core i_size yet. Then a subsequent mmap read could see non-zeros past EOF. I occasionally see this in fsx runs in fstests generic/112, a simplified fsx operation sequence is like (assuming 4k block size xfs): fallocate 0x0 0x1000 0x0 keep_size write 0x0 0x1000 0x0 truncate 0x0 0x800 0x1000 punch_hole 0x0 0x800 0x800 mapread 0x0 0x800 0x800 where fallocate allocates unwritten extent but doesn't update i_size, buffer write populates the page cache and extent is still unwritten, truncate skips zeroing page past new EOF and writes the page to disk, punch_hole invalidates the page cache, at last mapread reads the block back and sees non-zero beyond EOF. Fix it by moving truncate_setsize() to before writeback so the page cache invalidation zeros the partial page at the new EOF. This also triggers "zero data beyond EOF" in xfs_do_writepage() at writeback time, because newsize has been set and page straddles the newsize. Also fixed the wrong 'end' param of filemap_write_and_wait_range() call while we're at it, the 'end' is inclusive and should be 'newsize - 1'. Suggested-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Eryu Guan <eguan@redhat.com> Acked-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-11-02 12:43:50 +08:00
/*
* 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. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
(newsize > ip->i_disk_size && oldsize != ip->i_disk_size)) {
xfs: truncate pagecache before writeback in xfs_setattr_size() On truncate down, if new size is not block size aligned, we zero the rest of block to avoid exposing stale data to user, and iomap_truncate_page() skips zeroing if the range is already in unwritten state or a hole. Then we writeback from on-disk i_size to the new size if this range hasn't been written to disk yet, and truncate page cache beyond new EOF and set in-core i_size. The problem is that we could write data between di_size and newsize before removing the page cache beyond newsize, as the extents may still be in unwritten state right after a buffer write. As such, the page of data that newsize lies in has not been zeroed by page cache invalidation before it is written, and xfs_do_writepage() hasn't triggered it's "zero data beyond EOF" case because we haven't updated in-core i_size yet. Then a subsequent mmap read could see non-zeros past EOF. I occasionally see this in fsx runs in fstests generic/112, a simplified fsx operation sequence is like (assuming 4k block size xfs): fallocate 0x0 0x1000 0x0 keep_size write 0x0 0x1000 0x0 truncate 0x0 0x800 0x1000 punch_hole 0x0 0x800 0x800 mapread 0x0 0x800 0x800 where fallocate allocates unwritten extent but doesn't update i_size, buffer write populates the page cache and extent is still unwritten, truncate skips zeroing page past new EOF and writes the page to disk, punch_hole invalidates the page cache, at last mapread reads the block back and sees non-zero beyond EOF. Fix it by moving truncate_setsize() to before writeback so the page cache invalidation zeros the partial page at the new EOF. This also triggers "zero data beyond EOF" in xfs_do_writepage() at writeback time, because newsize has been set and page straddles the newsize. Also fixed the wrong 'end' param of filemap_write_and_wait_range() call while we're at it, the 'end' is inclusive and should be 'newsize - 1'. Suggested-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Eryu Guan <eguan@redhat.com> Acked-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-11-02 12:43:50 +08:00
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_disk_size, newsize - 1);
xfs: truncate pagecache before writeback in xfs_setattr_size() On truncate down, if new size is not block size aligned, we zero the rest of block to avoid exposing stale data to user, and iomap_truncate_page() skips zeroing if the range is already in unwritten state or a hole. Then we writeback from on-disk i_size to the new size if this range hasn't been written to disk yet, and truncate page cache beyond new EOF and set in-core i_size. The problem is that we could write data between di_size and newsize before removing the page cache beyond newsize, as the extents may still be in unwritten state right after a buffer write. As such, the page of data that newsize lies in has not been zeroed by page cache invalidation before it is written, and xfs_do_writepage() hasn't triggered it's "zero data beyond EOF" case because we haven't updated in-core i_size yet. Then a subsequent mmap read could see non-zeros past EOF. I occasionally see this in fsx runs in fstests generic/112, a simplified fsx operation sequence is like (assuming 4k block size xfs): fallocate 0x0 0x1000 0x0 keep_size write 0x0 0x1000 0x0 truncate 0x0 0x800 0x1000 punch_hole 0x0 0x800 0x800 mapread 0x0 0x800 0x800 where fallocate allocates unwritten extent but doesn't update i_size, buffer write populates the page cache and extent is still unwritten, truncate skips zeroing page past new EOF and writes the page to disk, punch_hole invalidates the page cache, at last mapread reads the block back and sees non-zero beyond EOF. Fix it by moving truncate_setsize() to before writeback so the page cache invalidation zeros the partial page at the new EOF. This also triggers "zero data beyond EOF" in xfs_do_writepage() at writeback time, because newsize has been set and page straddles the newsize. Also fixed the wrong 'end' param of filemap_write_and_wait_range() call while we're at it, the 'end' is inclusive and should be 'newsize - 1'. Suggested-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Eryu Guan <eguan@redhat.com> Acked-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
2017-11-02 12:43:50 +08:00
if (error)
return error;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
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_time(inode);
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_disk_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_cancel;
/*
* 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);
}
xfs: use setattr_copy to set vfs inode attributes Filipe Manana pointed out that XFS' behavior w.r.t. setuid/setgid revocation isn't consistent with btrfs[1] or ext4. Those two filesystems use the VFS function setattr_copy to convey certain attributes from struct iattr into the VFS inode structure. Andrey Zhadchenko reported[2] that XFS uses the wrong user namespace to decide if it should clear setgid and setuid on a file attribute update. This is a second symptom of the problem that Filipe noticed. XFS, on the other hand, open-codes setattr_copy in xfs_setattr_mode, xfs_setattr_nonsize, and xfs_setattr_time. Regrettably, setattr_copy is /not/ a simple copy function; it contains additional logic to clear the setgid bit when setting the mode, and XFS' version no longer matches. The VFS implements its own setuid/setgid stripping logic, which establishes consistent behavior. It's a tad unfortunate that it's scattered across notify_change, should_remove_suid, and setattr_copy but XFS should really follow the Linux VFS. Adapt XFS to use the VFS functions and get rid of the old functions. [1] https://lore.kernel.org/fstests/CAL3q7H47iNQ=Wmk83WcGB-KBJVOEtR9+qGczzCeXJ9Y2KCV25Q@mail.gmail.com/ [2] https://lore.kernel.org/linux-xfs/20220221182218.748084-1-andrey.zhadchenko@virtuozzo.com/ Fixes: 7fa294c8991c ("userns: Allow chown and setgid preservation") Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christian Brauner <brauner@kernel.org>
2022-03-09 02:51:16 +08:00
ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID)));
setattr_copy(mnt_userns, inode, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (xfs_has_wsync(mp))
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
int
xfs_vn_setattr_size(
struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
struct xfs_inode *ip = XFS_I(d_inode(dentry));
int error;
trace_xfs_setattr(ip);
error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
if (error)
return error;
return xfs_setattr_size(mnt_userns, ip, iattr);
}
STATIC int
xfs_vn_setattr(
struct user_namespace *mnt_userns,
struct dentry *dentry,
struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
struct xfs_inode *ip = XFS_I(inode);
int error;
if (iattr->ia_valid & ATTR_SIZE) {
uint iolock;
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
xfs: prepare xfs_break_layouts() for another layout type When xfs is operating as the back-end of a pNFS block server, it prevents collisions between local and remote operations by requiring a lease to be held for remotely accessed blocks. Local filesystem operations break those leases before writing or mutating the extent map of the file. A similar mechanism is needed to prevent operations on pinned dax mappings, like device-DMA, from colliding with extent unmap operations. BREAK_WRITE and BREAK_UNMAP are introduced as two distinct levels of layout breaking. Layouts are broken in the BREAK_WRITE case to ensure that layout-holders do not collide with local writes. Additionally, layouts are broken in the BREAK_UNMAP case to make sure the layout-holder has a consistent view of the file's extent map. While BREAK_WRITE breaks can be satisfied be recalling FL_LAYOUT leases, BREAK_UNMAP breaks additionally require waiting for busy dax-pages to go idle while holding XFS_MMAPLOCK_EXCL. After this refactoring xfs_break_layouts() becomes the entry point for coordinating both types of breaks. Finally, xfs_break_leased_layouts() becomes just the BREAK_WRITE handler. Note that the unlock tracking is needed in a follow on change. That will coordinate retrying either break handler until both successfully test for a lease break while maintaining the lock state. Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: "Darrick J. Wong" <darrick.wong@oracle.com> Reported-by: Dave Chinner <david@fromorbit.com> Reported-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2018-03-21 05:42:38 +08:00
error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
if (error) {
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
return error;
}
error = xfs_vn_setattr_size(mnt_userns, dentry, iattr);
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
} else {
trace_xfs_setattr(ip);
error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
if (!error)
error = xfs_setattr_nonsize(mnt_userns, ip, iattr);
}
return error;
}
STATIC int
xfs_vn_update_time(
struct inode *inode,
vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com> Cc: <anton@tuxera.com> Cc: <balbi@kernel.org> Cc: <bfields@fieldses.org> Cc: <darrick.wong@oracle.com> Cc: <dhowells@redhat.com> Cc: <dsterba@suse.com> Cc: <dwmw2@infradead.org> Cc: <hch@lst.de> Cc: <hirofumi@mail.parknet.co.jp> Cc: <hubcap@omnibond.com> Cc: <jack@suse.com> Cc: <jaegeuk@kernel.org> Cc: <jaharkes@cs.cmu.edu> Cc: <jslaby@suse.com> Cc: <keescook@chromium.org> Cc: <mark@fasheh.com> Cc: <miklos@szeredi.hu> Cc: <nico@linaro.org> Cc: <reiserfs-devel@vger.kernel.org> Cc: <richard@nod.at> Cc: <sage@redhat.com> Cc: <sfrench@samba.org> Cc: <swhiteho@redhat.com> Cc: <tj@kernel.org> Cc: <trond.myklebust@primarydata.com> Cc: <tytso@mit.edu> Cc: <viro@zeniv.linux.org.uk>
2018-05-09 10:36:02 +08:00
struct timespec64 *now,
int flags)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
int log_flags = XFS_ILOG_TIMESTAMP;
struct xfs_trans *tp;
int error;
trace_xfs_update_time(ip);
if (inode->i_sb->s_flags & SB_LAZYTIME) {
if (!((flags & S_VERSION) &&
inode_maybe_inc_iversion(inode, false)))
return generic_update_time(inode, now, flags);
/* Capture the iversion update that just occurred */
log_flags |= XFS_ILOG_CORE;
}
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
if (error)
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (flags & S_CTIME)
inode->i_ctime = *now;
if (flags & S_MTIME)
inode->i_mtime = *now;
if (flags & S_ATIME)
inode->i_atime = *now;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, log_flags);
return xfs_trans_commit(tp);
}
STATIC int
xfs_vn_fiemap(
struct inode *inode,
struct fiemap_extent_info *fieinfo,
u64 start,
u64 length)
{
int error;
xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED);
if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
error = iomap_fiemap(inode, fieinfo, start, length,
&xfs_xattr_iomap_ops);
} else {
error = iomap_fiemap(inode, fieinfo, start, length,
&xfs_read_iomap_ops);
}
xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
return error;
}
STATIC int
xfs_vn_tmpfile(
struct user_namespace *mnt_userns,
struct inode *dir,
struct dentry *dentry,
umode_t mode)
{
return xfs_generic_create(mnt_userns, 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,
.listxattr = xfs_vn_listxattr,
.fiemap = xfs_vn_fiemap,
.update_time = xfs_vn_update_time,
.fileattr_get = xfs_fileattr_get,
.fileattr_set = xfs_fileattr_set,
};
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,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
.fileattr_get = xfs_fileattr_get,
.fileattr_set = xfs_fileattr_set,
};
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,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
.tmpfile = xfs_vn_tmpfile,
.fileattr_get = xfs_fileattr_get,
.fileattr_set = xfs_fileattr_set,
};
static const struct inode_operations xfs_symlink_inode_operations = {
.get_link = xfs_vn_get_link,
.getattr = xfs_vn_getattr,
.setattr = xfs_vn_setattr,
.listxattr = xfs_vn_listxattr,
.update_time = xfs_vn_update_time,
};
/* Figure out if this file actually supports DAX. */
static bool
xfs_inode_supports_dax(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
/* Only supported on regular files. */
if (!S_ISREG(VFS_I(ip)->i_mode))
return false;
/* Only supported on non-reflinked files. */
if (xfs_is_reflink_inode(ip))
return false;
/* Block size must match page size */
if (mp->m_sb.sb_blocksize != PAGE_SIZE)
return false;
/* Device has to support DAX too. */
return xfs_inode_buftarg(ip)->bt_daxdev != NULL;
}
static bool
xfs_inode_should_enable_dax(
struct xfs_inode *ip)
{
if (!IS_ENABLED(CONFIG_FS_DAX))
return false;
if (xfs_has_dax_never(ip->i_mount))
return false;
if (!xfs_inode_supports_dax(ip))
return false;
if (xfs_has_dax_always(ip->i_mount))
return true;
if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
return true;
return false;
}
void
xfs_diflags_to_iflags(
struct xfs_inode *ip,
bool init)
{
struct inode *inode = VFS_I(ip);
unsigned int xflags = xfs_ip2xflags(ip);
unsigned int flags = 0;
ASSERT(!(IS_DAX(inode) && init));
if (xflags & FS_XFLAG_IMMUTABLE)
flags |= S_IMMUTABLE;
if (xflags & FS_XFLAG_APPEND)
flags |= S_APPEND;
if (xflags & FS_XFLAG_SYNC)
flags |= S_SYNC;
if (xflags & FS_XFLAG_NOATIME)
flags |= S_NOATIME;
if (init && xfs_inode_should_enable_dax(ip))
flags |= S_DAX;
/*
* S_DAX can only be set during inode initialization and is never set by
* the VFS, so we cannot mask off S_DAX in i_flags.
*/
inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC | S_NOATIME);
inode->i_flags |= flags;
}
/*
* Initialize the Linux inode.
*
xfs: inodes are new until the dentry cache is set up Al Viro noticed a generic set of issues to do with filehandle lookup racing with dentry cache setup. They involve a filehandle lookup occurring while an inode is being created and the filehandle lookup racing with the dentry creation for the real file. This can lead to multiple dentries for the one path being instantiated. There are a host of other issues around this same set of paths. The underlying cause is that file handle lookup only waits on inode cache instantiation rather than full dentry cache instantiation. XFS is mostly immune to the problems discovered due to it's own internal inode cache, but there are a couple of corner cases where races can happen. We currently clear the XFS_INEW flag when the inode is fully set up after insertion into the cache. Newly allocated inodes are inserted locked and so aren't usable until the allocation transaction commits. This, however, occurs before the dentry and security information is fully initialised and hence the inode is unlocked and available for lookups to find too early. To solve the problem, only clear the XFS_INEW flag for newly created inodes once the dentry is fully instantiated. This means lookups will retry until the XFS_INEW flag is removed from the inode and hence avoids the race conditions in questions. THis also means that xfs_create(), xfs_create_tmpfile() and xfs_symlink() need to finish the setup of the inode in their error paths if we had allocated the inode but failed later in the creation process. xfs_symlink(), in particular, needed a lot of help to make it's error handling match that of xfs_create(). Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
2015-02-23 19:38:08 +08:00
* When reading existing inodes from disk this is called directly from xfs_iget,
* when creating a new inode it is called from xfs_init_new_inode after setting
* up the inode. These callers have different criteria for clearing XFS_INEW, so
* leave it up to the caller to deal with unlocking the inode appropriately.
*/
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 */
inode_fake_hash(inode);
i_size_write(inode, ip->i_disk_size);
xfs_diflags_to_iflags(ip, true);
if (S_ISDIR(inode->i_mode)) {
/*
* We set the i_rwsem class here to avoid potential races with
* lockdep_annotate_inode_mutex_key() reinitialising the lock
* after a filehandle lookup has already found the inode in
* cache before it has been unlocked via unlock_new_inode().
*/
lockdep_set_class(&inode->i_rwsem,
&inode->i_sb->s_type->i_mutex_dir_key);
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
} else {
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
}
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_inode_has_attr_fork(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
}
void
xfs_setup_iops(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
if (IS_DAX(inode))
inode->i_mapping->a_ops = &xfs_dax_aops;
else
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
if (xfs_has_asciici(XFS_M(inode->i_sb)))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
}