OpenCloudOS-Kernel/fs/xfs/xfs_ioctl.c

1630 lines
36 KiB
C
Raw Normal View History

/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_alloc.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_ioctl.h"
#include "xfs_rtalloc.h"
#include "xfs_itable.h"
#include "xfs_error.h"
#include "xfs_attr.h"
#include "xfs_bmap.h"
#include "xfs_buf_item.h"
#include "xfs_utils.h"
#include "xfs_dfrag.h"
#include "xfs_fsops.h"
#include "xfs_vnodeops.h"
#include "xfs_discard.h"
#include "xfs_quota.h"
#include "xfs_inode_item.h"
#include "xfs_export.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 <linux/capability.h>
#include <linux/dcache.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/exportfs.h>
/*
* xfs_find_handle maps from userspace xfs_fsop_handlereq structure to
* a file or fs handle.
*
* XFS_IOC_PATH_TO_FSHANDLE
* returns fs handle for a mount point or path within that mount point
* XFS_IOC_FD_TO_HANDLE
* returns full handle for a FD opened in user space
* XFS_IOC_PATH_TO_HANDLE
* returns full handle for a path
*/
int
xfs_find_handle(
unsigned int cmd,
xfs_fsop_handlereq_t *hreq)
{
int hsize;
xfs_handle_t handle;
struct inode *inode;
struct fd f = {0};
struct path path;
int error;
struct xfs_inode *ip;
if (cmd == XFS_IOC_FD_TO_HANDLE) {
f = fdget(hreq->fd);
if (!f.file)
return -EBADF;
inode = f.file->f_path.dentry->d_inode;
} else {
error = user_lpath((const char __user *)hreq->path, &path);
if (error)
return error;
inode = path.dentry->d_inode;
}
ip = XFS_I(inode);
/*
* We can only generate handles for inodes residing on a XFS filesystem,
* and only for regular files, directories or symbolic links.
*/
error = -EINVAL;
if (inode->i_sb->s_magic != XFS_SB_MAGIC)
goto out_put;
error = -EBADF;
if (!S_ISREG(inode->i_mode) &&
!S_ISDIR(inode->i_mode) &&
!S_ISLNK(inode->i_mode))
goto out_put;
memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t));
if (cmd == XFS_IOC_PATH_TO_FSHANDLE) {
/*
* This handle only contains an fsid, zero the rest.
*/
memset(&handle.ha_fid, 0, sizeof(handle.ha_fid));
hsize = sizeof(xfs_fsid_t);
} else {
int lock_mode;
lock_mode = xfs_ilock_map_shared(ip);
handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
sizeof(handle.ha_fid.fid_len);
handle.ha_fid.fid_pad = 0;
handle.ha_fid.fid_gen = ip->i_d.di_gen;
handle.ha_fid.fid_ino = ip->i_ino;
xfs_iunlock_map_shared(ip, lock_mode);
hsize = XFS_HSIZE(handle);
}
error = -EFAULT;
if (copy_to_user(hreq->ohandle, &handle, hsize) ||
copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32)))
goto out_put;
error = 0;
out_put:
if (cmd == XFS_IOC_FD_TO_HANDLE)
fdput(f);
else
path_put(&path);
return error;
}
/*
* No need to do permission checks on the various pathname components
* as the handle operations are privileged.
*/
STATIC int
xfs_handle_acceptable(
void *context,
struct dentry *dentry)
{
return 1;
}
/*
* Convert userspace handle data into a dentry.
*/
struct dentry *
xfs_handle_to_dentry(
struct file *parfilp,
void __user *uhandle,
u32 hlen)
{
xfs_handle_t handle;
struct xfs_fid64 fid;
/*
* Only allow handle opens under a directory.
*/
if (!S_ISDIR(parfilp->f_path.dentry->d_inode->i_mode))
return ERR_PTR(-ENOTDIR);
if (hlen != sizeof(xfs_handle_t))
return ERR_PTR(-EINVAL);
if (copy_from_user(&handle, uhandle, hlen))
return ERR_PTR(-EFAULT);
if (handle.ha_fid.fid_len !=
sizeof(handle.ha_fid) - sizeof(handle.ha_fid.fid_len))
return ERR_PTR(-EINVAL);
memset(&fid, 0, sizeof(struct fid));
fid.ino = handle.ha_fid.fid_ino;
fid.gen = handle.ha_fid.fid_gen;
return exportfs_decode_fh(parfilp->f_path.mnt, (struct fid *)&fid, 3,
FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG,
xfs_handle_acceptable, NULL);
}
STATIC struct dentry *
xfs_handlereq_to_dentry(
struct file *parfilp,
xfs_fsop_handlereq_t *hreq)
{
return xfs_handle_to_dentry(parfilp, hreq->ihandle, hreq->ihandlen);
}
int
xfs_open_by_handle(
struct file *parfilp,
xfs_fsop_handlereq_t *hreq)
{
const struct cred *cred = current_cred();
int error;
int fd;
int permflag;
struct file *filp;
struct inode *inode;
struct dentry *dentry;
fmode_t fmode;
struct path path;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
dentry = xfs_handlereq_to_dentry(parfilp, hreq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
inode = dentry->d_inode;
/* Restrict xfs_open_by_handle to directories & regular files. */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) {
error = -XFS_ERROR(EPERM);
goto out_dput;
}
#if BITS_PER_LONG != 32
hreq->oflags |= O_LARGEFILE;
#endif
permflag = hreq->oflags;
fmode = OPEN_FMODE(permflag);
if ((!(permflag & O_APPEND) || (permflag & O_TRUNC)) &&
(fmode & FMODE_WRITE) && IS_APPEND(inode)) {
error = -XFS_ERROR(EPERM);
goto out_dput;
}
if ((fmode & FMODE_WRITE) && IS_IMMUTABLE(inode)) {
error = -XFS_ERROR(EACCES);
goto out_dput;
}
/* Can't write directories. */
if (S_ISDIR(inode->i_mode) && (fmode & FMODE_WRITE)) {
error = -XFS_ERROR(EISDIR);
goto out_dput;
}
fd = get_unused_fd();
if (fd < 0) {
error = fd;
goto out_dput;
}
path.mnt = parfilp->f_path.mnt;
path.dentry = dentry;
filp = dentry_open(&path, hreq->oflags, cred);
dput(dentry);
if (IS_ERR(filp)) {
put_unused_fd(fd);
return PTR_ERR(filp);
}
if (S_ISREG(inode->i_mode)) {
filp->f_flags |= O_NOATIME;
filp->f_mode |= FMODE_NOCMTIME;
}
fd_install(fd, filp);
return fd;
out_dput:
dput(dentry);
return error;
}
/*
* This is a copy from fs/namei.c:vfs_readlink(), except for removing it's
* unused first argument.
*/
STATIC int
do_readlink(
char __user *buffer,
int buflen,
const char *link)
{
int len;
len = PTR_ERR(link);
if (IS_ERR(link))
goto out;
len = strlen(link);
if (len > (unsigned) buflen)
len = buflen;
if (copy_to_user(buffer, link, len))
len = -EFAULT;
out:
return len;
}
int
xfs_readlink_by_handle(
struct file *parfilp,
xfs_fsop_handlereq_t *hreq)
{
struct dentry *dentry;
__u32 olen;
void *link;
int error;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
dentry = xfs_handlereq_to_dentry(parfilp, hreq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
/* Restrict this handle operation to symlinks only. */
if (!S_ISLNK(dentry->d_inode->i_mode)) {
error = -XFS_ERROR(EINVAL);
goto out_dput;
}
if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) {
error = -XFS_ERROR(EFAULT);
goto out_dput;
}
link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
if (!link) {
error = -XFS_ERROR(ENOMEM);
goto out_dput;
}
error = -xfs_readlink(XFS_I(dentry->d_inode), link);
if (error)
goto out_kfree;
error = do_readlink(hreq->ohandle, olen, link);
if (error)
goto out_kfree;
out_kfree:
kfree(link);
out_dput:
dput(dentry);
return error;
}
STATIC int
xfs_fssetdm_by_handle(
struct file *parfilp,
void __user *arg)
{
int error;
struct fsdmidata fsd;
xfs_fsop_setdm_handlereq_t dmhreq;
struct dentry *dentry;
if (!capable(CAP_MKNOD))
return -XFS_ERROR(EPERM);
if (copy_from_user(&dmhreq, arg, sizeof(xfs_fsop_setdm_handlereq_t)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(parfilp);
if (error)
return error;
dentry = xfs_handlereq_to_dentry(parfilp, &dmhreq.hreq);
if (IS_ERR(dentry)) {
mnt_drop_write_file(parfilp);
return PTR_ERR(dentry);
}
if (IS_IMMUTABLE(dentry->d_inode) || IS_APPEND(dentry->d_inode)) {
error = -XFS_ERROR(EPERM);
goto out;
}
if (copy_from_user(&fsd, dmhreq.data, sizeof(fsd))) {
error = -XFS_ERROR(EFAULT);
goto out;
}
error = -xfs_set_dmattrs(XFS_I(dentry->d_inode), fsd.fsd_dmevmask,
fsd.fsd_dmstate);
out:
mnt_drop_write_file(parfilp);
dput(dentry);
return error;
}
STATIC int
xfs_attrlist_by_handle(
struct file *parfilp,
void __user *arg)
{
int error = -ENOMEM;
attrlist_cursor_kern_t *cursor;
xfs_fsop_attrlist_handlereq_t al_hreq;
struct dentry *dentry;
char *kbuf;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (copy_from_user(&al_hreq, arg, sizeof(xfs_fsop_attrlist_handlereq_t)))
return -XFS_ERROR(EFAULT);
if (al_hreq.buflen > XATTR_LIST_MAX)
return -XFS_ERROR(EINVAL);
/*
* Reject flags, only allow namespaces.
*/
if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE))
return -XFS_ERROR(EINVAL);
dentry = xfs_handlereq_to_dentry(parfilp, &al_hreq.hreq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
kbuf = kzalloc(al_hreq.buflen, GFP_KERNEL);
if (!kbuf)
goto out_dput;
cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
error = -xfs_attr_list(XFS_I(dentry->d_inode), kbuf, al_hreq.buflen,
al_hreq.flags, cursor);
if (error)
goto out_kfree;
if (copy_to_user(al_hreq.buffer, kbuf, al_hreq.buflen))
error = -EFAULT;
out_kfree:
kfree(kbuf);
out_dput:
dput(dentry);
return error;
}
int
xfs_attrmulti_attr_get(
struct inode *inode,
unsigned char *name,
unsigned char __user *ubuf,
__uint32_t *len,
__uint32_t flags)
{
unsigned char *kbuf;
int error = EFAULT;
if (*len > XATTR_SIZE_MAX)
return EINVAL;
kbuf = kmem_zalloc(*len, KM_SLEEP | KM_MAYFAIL);
if (!kbuf) {
kbuf = kmem_zalloc_large(*len);
if (!kbuf)
return ENOMEM;
}
error = xfs_attr_get(XFS_I(inode), name, kbuf, (int *)len, flags);
if (error)
goto out_kfree;
if (copy_to_user(ubuf, kbuf, *len))
error = EFAULT;
out_kfree:
if (is_vmalloc_addr(kbuf))
kmem_free_large(kbuf);
else
kmem_free(kbuf);
return error;
}
int
xfs_attrmulti_attr_set(
struct inode *inode,
unsigned char *name,
const unsigned char __user *ubuf,
__uint32_t len,
__uint32_t flags)
{
unsigned char *kbuf;
int error = EFAULT;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return EPERM;
if (len > XATTR_SIZE_MAX)
return EINVAL;
kbuf = memdup_user(ubuf, len);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
error = xfs_attr_set(XFS_I(inode), name, kbuf, len, flags);
return error;
}
int
xfs_attrmulti_attr_remove(
struct inode *inode,
unsigned char *name,
__uint32_t flags)
{
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return EPERM;
return xfs_attr_remove(XFS_I(inode), name, flags);
}
STATIC int
xfs_attrmulti_by_handle(
struct file *parfilp,
void __user *arg)
{
int error;
xfs_attr_multiop_t *ops;
xfs_fsop_attrmulti_handlereq_t am_hreq;
struct dentry *dentry;
unsigned int i, size;
unsigned char *attr_name;
if (!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (copy_from_user(&am_hreq, arg, sizeof(xfs_fsop_attrmulti_handlereq_t)))
return -XFS_ERROR(EFAULT);
/* overflow check */
if (am_hreq.opcount >= INT_MAX / sizeof(xfs_attr_multiop_t))
return -E2BIG;
dentry = xfs_handlereq_to_dentry(parfilp, &am_hreq.hreq);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
error = E2BIG;
size = am_hreq.opcount * sizeof(xfs_attr_multiop_t);
if (!size || size > 16 * PAGE_SIZE)
goto out_dput;
ops = memdup_user(am_hreq.ops, size);
if (IS_ERR(ops)) {
error = PTR_ERR(ops);
goto out_dput;
}
attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
if (!attr_name)
goto out_kfree_ops;
error = 0;
for (i = 0; i < am_hreq.opcount; i++) {
ops[i].am_error = strncpy_from_user((char *)attr_name,
ops[i].am_attrname, MAXNAMELEN);
if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
error = -ERANGE;
if (ops[i].am_error < 0)
break;
switch (ops[i].am_opcode) {
case ATTR_OP_GET:
ops[i].am_error = xfs_attrmulti_attr_get(
dentry->d_inode, attr_name,
ops[i].am_attrvalue, &ops[i].am_length,
ops[i].am_flags);
break;
case ATTR_OP_SET:
ops[i].am_error = mnt_want_write_file(parfilp);
if (ops[i].am_error)
break;
ops[i].am_error = xfs_attrmulti_attr_set(
dentry->d_inode, attr_name,
ops[i].am_attrvalue, ops[i].am_length,
ops[i].am_flags);
mnt_drop_write_file(parfilp);
break;
case ATTR_OP_REMOVE:
ops[i].am_error = mnt_want_write_file(parfilp);
if (ops[i].am_error)
break;
ops[i].am_error = xfs_attrmulti_attr_remove(
dentry->d_inode, attr_name,
ops[i].am_flags);
mnt_drop_write_file(parfilp);
break;
default:
ops[i].am_error = EINVAL;
}
}
if (copy_to_user(am_hreq.ops, ops, size))
error = XFS_ERROR(EFAULT);
kfree(attr_name);
out_kfree_ops:
kfree(ops);
out_dput:
dput(dentry);
return -error;
}
int
xfs_ioc_space(
struct xfs_inode *ip,
struct inode *inode,
struct file *filp,
int ioflags,
unsigned int cmd,
xfs_flock64_t *bf)
{
int attr_flags = 0;
int error;
/*
* Only allow the sys admin to reserve space unless
* unwritten extents are enabled.
*/
if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
!capable(CAP_SYS_ADMIN))
return -XFS_ERROR(EPERM);
if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
return -XFS_ERROR(EPERM);
if (!(filp->f_mode & FMODE_WRITE))
return -XFS_ERROR(EBADF);
if (!S_ISREG(inode->i_mode))
return -XFS_ERROR(EINVAL);
if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
attr_flags |= XFS_ATTR_NONBLOCK;
if (filp->f_flags & O_DSYNC)
attr_flags |= XFS_ATTR_SYNC;
if (ioflags & IO_INVIS)
attr_flags |= XFS_ATTR_DMI;
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
mnt_drop_write_file(filp);
return -error;
}
STATIC int
xfs_ioc_bulkstat(
xfs_mount_t *mp,
unsigned int cmd,
void __user *arg)
{
xfs_fsop_bulkreq_t bulkreq;
int count; /* # of records returned */
xfs_ino_t inlast; /* last inode number */
int done;
int error;
/* done = 1 if there are more stats to get and if bulkstat */
/* should be called again (unused here, but used in dmapi) */
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (XFS_FORCED_SHUTDOWN(mp))
return -XFS_ERROR(EIO);
if (copy_from_user(&bulkreq, arg, sizeof(xfs_fsop_bulkreq_t)))
return -XFS_ERROR(EFAULT);
if (copy_from_user(&inlast, bulkreq.lastip, sizeof(__s64)))
return -XFS_ERROR(EFAULT);
if ((count = bulkreq.icount) <= 0)
return -XFS_ERROR(EINVAL);
[XFS] 971064 Various fixups for xfs_bulkstat(). - sanity check for NULL user buffer in xfs_ioc_bulkstat[_compat]() - remove the special case for XFS_IOC_FSBULKSTAT with count == 1. This special case causes bulkstat to fail because the special case uses xfs_bulkstat_single() instead of xfs_bulkstat() and the two functions have different semantics. xfs_bulkstat() will return the next inode after the one supplied while skipping internal inodes (ie quota inodes). xfs_bulkstate_single() will only lookup the inode supplied and return an error if it is an internal inode. - in xfs_bulkstat(), need to initialise 'lastino' to the inode supplied so in cases were we return without examining any inodes the scan wont restart back at zero. - sanity check for valid *ubcountp values. Cannot sanity check for valid ubuffer here because some users of xfs_bulkstat() don't supply a buffer. - checks against 'ubleft' (the space left in the user's buffer) should be against 'statstruct_size' which is the supplied minimum object size. The mixture of checks against statstruct_size and 0 was one of the reasons we were skipping inodes. - if the formatter function returns BULKSTAT_RV_NOTHING and an error and the error is not ENOENT or EINVAL then we need to abort the scan. ENOENT is for inodes that are no longer valid and we just skip them. EINVAL is returned if we try to lookup an internal inode so we skip them too. For a DMF scan if the inode and DMF attribute cannot fit into the space left in the user's buffer it would return ERANGE. We didn't handle this error and skipped the inode. We would continue to skip inodes until one fitted into the user's buffer or we completed the scan. - put back the recalculation of agino (that got removed with the last fix) at the end of the while loop. This is because the code at the start of the loop expects agino to be the last inode examined if it is non-zero. - if we found some inodes but then encountered an error, return success this time and the error next time. If the formatter aborted with ENOMEM we will now return this error but only if we couldn't read any inodes. Previously if we encountered ENOMEM without reading any inodes we returned a zero count and no error which falsely indicated the scan was complete. SGI-PV: 973431 SGI-Modid: xfs-linux-melb:xfs-kern:30089a Signed-off-by: Lachlan McIlroy <lachlan@sgi.com> Signed-off-by: David Chinner <dgc@sgi.com>
2007-11-23 13:30:32 +08:00
if (bulkreq.ubuffer == NULL)
return -XFS_ERROR(EINVAL);
if (cmd == XFS_IOC_FSINUMBERS)
error = xfs_inumbers(mp, &inlast, &count,
bulkreq.ubuffer, xfs_inumbers_fmt);
else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE)
error = xfs_bulkstat_single(mp, &inlast,
bulkreq.ubuffer, &done);
[XFS] 971064 Various fixups for xfs_bulkstat(). - sanity check for NULL user buffer in xfs_ioc_bulkstat[_compat]() - remove the special case for XFS_IOC_FSBULKSTAT with count == 1. This special case causes bulkstat to fail because the special case uses xfs_bulkstat_single() instead of xfs_bulkstat() and the two functions have different semantics. xfs_bulkstat() will return the next inode after the one supplied while skipping internal inodes (ie quota inodes). xfs_bulkstate_single() will only lookup the inode supplied and return an error if it is an internal inode. - in xfs_bulkstat(), need to initialise 'lastino' to the inode supplied so in cases were we return without examining any inodes the scan wont restart back at zero. - sanity check for valid *ubcountp values. Cannot sanity check for valid ubuffer here because some users of xfs_bulkstat() don't supply a buffer. - checks against 'ubleft' (the space left in the user's buffer) should be against 'statstruct_size' which is the supplied minimum object size. The mixture of checks against statstruct_size and 0 was one of the reasons we were skipping inodes. - if the formatter function returns BULKSTAT_RV_NOTHING and an error and the error is not ENOENT or EINVAL then we need to abort the scan. ENOENT is for inodes that are no longer valid and we just skip them. EINVAL is returned if we try to lookup an internal inode so we skip them too. For a DMF scan if the inode and DMF attribute cannot fit into the space left in the user's buffer it would return ERANGE. We didn't handle this error and skipped the inode. We would continue to skip inodes until one fitted into the user's buffer or we completed the scan. - put back the recalculation of agino (that got removed with the last fix) at the end of the while loop. This is because the code at the start of the loop expects agino to be the last inode examined if it is non-zero. - if we found some inodes but then encountered an error, return success this time and the error next time. If the formatter aborted with ENOMEM we will now return this error but only if we couldn't read any inodes. Previously if we encountered ENOMEM without reading any inodes we returned a zero count and no error which falsely indicated the scan was complete. SGI-PV: 973431 SGI-Modid: xfs-linux-melb:xfs-kern:30089a Signed-off-by: Lachlan McIlroy <lachlan@sgi.com> Signed-off-by: David Chinner <dgc@sgi.com>
2007-11-23 13:30:32 +08:00
else /* XFS_IOC_FSBULKSTAT */
error = xfs_bulkstat(mp, &inlast, &count, xfs_bulkstat_one,
sizeof(xfs_bstat_t), bulkreq.ubuffer,
&done);
if (error)
return -error;
if (bulkreq.ocount != NULL) {
if (copy_to_user(bulkreq.lastip, &inlast,
sizeof(xfs_ino_t)))
return -XFS_ERROR(EFAULT);
if (copy_to_user(bulkreq.ocount, &count, sizeof(count)))
return -XFS_ERROR(EFAULT);
}
return 0;
}
STATIC int
xfs_ioc_fsgeometry_v1(
xfs_mount_t *mp,
void __user *arg)
{
xfs_fsop_geom_t fsgeo;
int error;
error = xfs_fs_geometry(mp, &fsgeo, 3);
if (error)
return -error;
/*
* Caller should have passed an argument of type
* xfs_fsop_geom_v1_t. This is a proper subset of the
* xfs_fsop_geom_t that xfs_fs_geometry() fills in.
*/
if (copy_to_user(arg, &fsgeo, sizeof(xfs_fsop_geom_v1_t)))
return -XFS_ERROR(EFAULT);
return 0;
}
STATIC int
xfs_ioc_fsgeometry(
xfs_mount_t *mp,
void __user *arg)
{
xfs_fsop_geom_t fsgeo;
int error;
error = xfs_fs_geometry(mp, &fsgeo, 4);
if (error)
return -error;
if (copy_to_user(arg, &fsgeo, sizeof(fsgeo)))
return -XFS_ERROR(EFAULT);
return 0;
}
/*
* Linux extended inode flags interface.
*/
STATIC unsigned int
xfs_merge_ioc_xflags(
unsigned int flags,
unsigned int start)
{
unsigned int xflags = start;
if (flags & FS_IMMUTABLE_FL)
xflags |= XFS_XFLAG_IMMUTABLE;
else
xflags &= ~XFS_XFLAG_IMMUTABLE;
if (flags & FS_APPEND_FL)
xflags |= XFS_XFLAG_APPEND;
else
xflags &= ~XFS_XFLAG_APPEND;
if (flags & FS_SYNC_FL)
xflags |= XFS_XFLAG_SYNC;
else
xflags &= ~XFS_XFLAG_SYNC;
if (flags & FS_NOATIME_FL)
xflags |= XFS_XFLAG_NOATIME;
else
xflags &= ~XFS_XFLAG_NOATIME;
if (flags & FS_NODUMP_FL)
xflags |= XFS_XFLAG_NODUMP;
else
xflags &= ~XFS_XFLAG_NODUMP;
return xflags;
}
STATIC unsigned int
xfs_di2lxflags(
__uint16_t di_flags)
{
unsigned int flags = 0;
if (di_flags & XFS_DIFLAG_IMMUTABLE)
flags |= FS_IMMUTABLE_FL;
if (di_flags & XFS_DIFLAG_APPEND)
flags |= FS_APPEND_FL;
if (di_flags & XFS_DIFLAG_SYNC)
flags |= FS_SYNC_FL;
if (di_flags & XFS_DIFLAG_NOATIME)
flags |= FS_NOATIME_FL;
if (di_flags & XFS_DIFLAG_NODUMP)
flags |= FS_NODUMP_FL;
return flags;
}
STATIC int
xfs_ioc_fsgetxattr(
xfs_inode_t *ip,
int attr,
void __user *arg)
{
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
xfs_ilock(ip, XFS_ILOCK_SHARED);
fa.fsx_xflags = xfs_ip2xflags(ip);
fa.fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
fa.fsx_projid = xfs_get_projid(ip);
if (attr) {
if (ip->i_afp) {
if (ip->i_afp->if_flags & XFS_IFEXTENTS)
fa.fsx_nextents = ip->i_afp->if_bytes /
sizeof(xfs_bmbt_rec_t);
else
fa.fsx_nextents = ip->i_d.di_anextents;
} else
fa.fsx_nextents = 0;
} else {
if (ip->i_df.if_flags & XFS_IFEXTENTS)
fa.fsx_nextents = ip->i_df.if_bytes /
sizeof(xfs_bmbt_rec_t);
else
fa.fsx_nextents = ip->i_d.di_nextents;
}
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (copy_to_user(arg, &fa, sizeof(fa)))
return -EFAULT;
return 0;
}
STATIC void
xfs_set_diflags(
struct xfs_inode *ip,
unsigned int xflags)
{
unsigned int di_flags;
/* can't set PREALLOC this way, just preserve it */
di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
if (xflags & XFS_XFLAG_IMMUTABLE)
di_flags |= XFS_DIFLAG_IMMUTABLE;
if (xflags & XFS_XFLAG_APPEND)
di_flags |= XFS_DIFLAG_APPEND;
if (xflags & XFS_XFLAG_SYNC)
di_flags |= XFS_DIFLAG_SYNC;
if (xflags & XFS_XFLAG_NOATIME)
di_flags |= XFS_DIFLAG_NOATIME;
if (xflags & XFS_XFLAG_NODUMP)
di_flags |= XFS_DIFLAG_NODUMP;
if (xflags & XFS_XFLAG_PROJINHERIT)
di_flags |= XFS_DIFLAG_PROJINHERIT;
if (xflags & XFS_XFLAG_NODEFRAG)
di_flags |= XFS_DIFLAG_NODEFRAG;
if (xflags & XFS_XFLAG_FILESTREAM)
di_flags |= XFS_DIFLAG_FILESTREAM;
if (S_ISDIR(ip->i_d.di_mode)) {
if (xflags & XFS_XFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_RTINHERIT;
if (xflags & XFS_XFLAG_NOSYMLINKS)
di_flags |= XFS_DIFLAG_NOSYMLINKS;
if (xflags & XFS_XFLAG_EXTSZINHERIT)
di_flags |= XFS_DIFLAG_EXTSZINHERIT;
} else if (S_ISREG(ip->i_d.di_mode)) {
if (xflags & XFS_XFLAG_REALTIME)
di_flags |= XFS_DIFLAG_REALTIME;
if (xflags & XFS_XFLAG_EXTSIZE)
di_flags |= XFS_DIFLAG_EXTSIZE;
}
ip->i_d.di_flags = di_flags;
}
STATIC void
xfs_diflags_to_linux(
struct xfs_inode *ip)
{
struct inode *inode = VFS_I(ip);
unsigned int xflags = xfs_ip2xflags(ip);
if (xflags & XFS_XFLAG_IMMUTABLE)
inode->i_flags |= S_IMMUTABLE;
else
inode->i_flags &= ~S_IMMUTABLE;
if (xflags & XFS_XFLAG_APPEND)
inode->i_flags |= S_APPEND;
else
inode->i_flags &= ~S_APPEND;
if (xflags & XFS_XFLAG_SYNC)
inode->i_flags |= S_SYNC;
else
inode->i_flags &= ~S_SYNC;
if (xflags & XFS_XFLAG_NOATIME)
inode->i_flags |= S_NOATIME;
else
inode->i_flags &= ~S_NOATIME;
}
#define FSX_PROJID 1
#define FSX_EXTSIZE 2
#define FSX_XFLAGS 4
#define FSX_NONBLOCK 8
STATIC int
xfs_ioctl_setattr(
xfs_inode_t *ip,
struct fsxattr *fa,
int mask)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_trans *tp;
unsigned int lock_flags = 0;
struct xfs_dquot *udqp = NULL;
struct xfs_dquot *gdqp = NULL;
struct xfs_dquot *olddquot = NULL;
int code;
trace_xfs_ioctl_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
/*
* Disallow 32bit project ids when projid32bit feature is not enabled.
*/
if ((mask & FSX_PROJID) && (fa->fsx_projid > (__uint16_t)-1) &&
!xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
return XFS_ERROR(EINVAL);
/*
* 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 & FSX_PROJID)) {
code = xfs_qm_vop_dqalloc(ip, ip->i_d.di_uid,
ip->i_d.di_gid, fa->fsx_projid,
XFS_QMOPT_PQUOTA, &udqp, &gdqp);
if (code)
return code;
}
/*
* For the other attributes, we acquire the inode lock and
* first do an error checking pass.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
code = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
if (code)
goto error_return;
lock_flags = XFS_ILOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* CAP_FOWNER overrides the following restrictions:
*
* The user ID of the calling process must be equal
* to the file owner ID, except in cases where the
* CAP_FSETID capability is applicable.
*/
if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
/*
* Do a quota reservation only if projid is actually going to change.
*/
if (mask & FSX_PROJID) {
if (XFS_IS_QUOTA_RUNNING(mp) &&
XFS_IS_PQUOTA_ON(mp) &&
xfs_get_projid(ip) != fa->fsx_projid) {
ASSERT(tp);
code = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
capable(CAP_FOWNER) ?
XFS_QMOPT_FORCE_RES : 0);
if (code) /* out of quota */
goto error_return;
}
}
if (mask & FSX_EXTSIZE) {
/*
* Can't change extent size if any extents are allocated.
*/
if (ip->i_d.di_nextents &&
((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) !=
fa->fsx_extsize)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* Extent size must be a multiple of the appropriate block
* size, if set at all. It must also be smaller than the
* maximum extent size supported by the filesystem.
*
* Also, for non-realtime files, limit the extent size hint to
* half the size of the AGs in the filesystem so alignment
* doesn't result in extents larger than an AG.
*/
if (fa->fsx_extsize != 0) {
xfs_extlen_t size;
xfs_fsblock_t extsize_fsb;
extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
if (extsize_fsb > MAXEXTLEN) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
if (XFS_IS_REALTIME_INODE(ip) ||
((mask & FSX_XFLAGS) &&
(fa->fsx_xflags & XFS_XFLAG_REALTIME))) {
size = mp->m_sb.sb_rextsize <<
mp->m_sb.sb_blocklog;
} else {
size = mp->m_sb.sb_blocksize;
if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
if (fa->fsx_extsize % size) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
}
if (mask & FSX_XFLAGS) {
/*
* Can't change realtime flag if any extents are allocated.
*/
if ((ip->i_d.di_nextents || ip->i_delayed_blks) &&
(XFS_IS_REALTIME_INODE(ip)) !=
(fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
code = XFS_ERROR(EINVAL); /* EFBIG? */
goto error_return;
}
/*
* If realtime flag is set then must have realtime data.
*/
if ((fa->fsx_xflags & XFS_XFLAG_REALTIME)) {
if ((mp->m_sb.sb_rblocks == 0) ||
(mp->m_sb.sb_rextsize == 0) ||
(ip->i_d.di_extsize % mp->m_sb.sb_rextsize)) {
code = XFS_ERROR(EINVAL);
goto error_return;
}
}
/*
* Can't modify an immutable/append-only file unless
* we have appropriate permission.
*/
if ((ip->i_d.di_flags &
(XFS_DIFLAG_IMMUTABLE|XFS_DIFLAG_APPEND) ||
(fa->fsx_xflags &
(XFS_XFLAG_IMMUTABLE | XFS_XFLAG_APPEND))) &&
!capable(CAP_LINUX_IMMUTABLE)) {
code = XFS_ERROR(EPERM);
goto error_return;
}
}
xfs_trans_ijoin(tp, ip, 0);
/*
* Change file ownership. Must be the owner or privileged.
*/
if (mask & FSX_PROJID) {
/*
* CAP_FSETID overrides the following restrictions:
*
* The set-user-ID and set-group-ID bits of a file will be
* cleared upon successful return from chown()
*/
if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
!capable(CAP_FSETID))
ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
/*
* Change the ownerships and register quota modifications
* in the transaction.
*/
if (xfs_get_projid(ip) != fa->fsx_projid) {
if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
olddquot = xfs_qm_vop_chown(tp, ip,
&ip->i_gdquot, gdqp);
}
xfs_set_projid(ip, fa->fsx_projid);
/*
* We may have to rev the inode as well as
* the superblock version number since projids didn't
* exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
*/
if (ip->i_d.di_version == 1)
xfs_bump_ino_vers2(tp, ip);
}
}
if (mask & FSX_EXTSIZE)
ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
if (mask & FSX_XFLAGS) {
xfs_set_diflags(ip, fa->fsx_xflags);
xfs_diflags_to_linux(ip);
}
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
/*
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
* This is slightly sub-optimal in that truncates require
* two sync transactions instead of one for wsync filesystems.
* One for the truncate and one for the timestamps since we
* don't want to change the timestamps unless we're sure the
* truncate worked. Truncates are less than 1% of the laddis
* mix so this probably isn't worth the trouble to optimize.
*/
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
code = xfs_trans_commit(tp, 0);
xfs_iunlock(ip, lock_flags);
/*
* Release any dquot(s) the inode had kept before chown.
*/
xfs_qm_dqrele(olddquot);
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
return code;
error_return:
xfs_qm_dqrele(udqp);
xfs_qm_dqrele(gdqp);
xfs_trans_cancel(tp, 0);
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return code;
}
STATIC int
xfs_ioc_fssetxattr(
xfs_inode_t *ip,
struct file *filp,
void __user *arg)
{
struct fsxattr fa;
unsigned int mask;
int error;
if (copy_from_user(&fa, arg, sizeof(fa)))
return -EFAULT;
mask = FSX_XFLAGS | FSX_EXTSIZE | FSX_PROJID;
if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
mask |= FSX_NONBLOCK;
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_ioctl_setattr(ip, &fa, mask);
mnt_drop_write_file(filp);
return -error;
}
STATIC int
xfs_ioc_getxflags(
xfs_inode_t *ip,
void __user *arg)
{
unsigned int flags;
flags = xfs_di2lxflags(ip->i_d.di_flags);
if (copy_to_user(arg, &flags, sizeof(flags)))
return -EFAULT;
return 0;
}
STATIC int
xfs_ioc_setxflags(
xfs_inode_t *ip,
struct file *filp,
void __user *arg)
{
struct fsxattr fa;
unsigned int flags;
unsigned int mask;
int error;
if (copy_from_user(&flags, arg, sizeof(flags)))
return -EFAULT;
if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
FS_NOATIME_FL | FS_NODUMP_FL | \
FS_SYNC_FL))
return -EOPNOTSUPP;
mask = FSX_XFLAGS;
if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
mask |= FSX_NONBLOCK;
fa.fsx_xflags = xfs_merge_ioc_xflags(flags, xfs_ip2xflags(ip));
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_ioctl_setattr(ip, &fa, mask);
mnt_drop_write_file(filp);
return -error;
}
STATIC int
xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full)
{
struct getbmap __user *base = *ap;
/* copy only getbmap portion (not getbmapx) */
if (copy_to_user(base, bmv, sizeof(struct getbmap)))
return XFS_ERROR(EFAULT);
*ap += sizeof(struct getbmap);
return 0;
}
STATIC int
xfs_ioc_getbmap(
struct xfs_inode *ip,
int ioflags,
unsigned int cmd,
void __user *arg)
{
struct getbmapx bmx;
int error;
if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
return -XFS_ERROR(EFAULT);
if (bmx.bmv_count < 2)
return -XFS_ERROR(EINVAL);
bmx.bmv_iflags = (cmd == XFS_IOC_GETBMAPA ? BMV_IF_ATTRFORK : 0);
if (ioflags & IO_INVIS)
bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
error = xfs_getbmap(ip, &bmx, xfs_getbmap_format,
(struct getbmap *)arg+1);
if (error)
return -error;
/* copy back header - only size of getbmap */
if (copy_to_user(arg, &bmx, sizeof(struct getbmap)))
return -XFS_ERROR(EFAULT);
return 0;
}
STATIC int
xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full)
{
struct getbmapx __user *base = *ap;
if (copy_to_user(base, bmv, sizeof(struct getbmapx)))
return XFS_ERROR(EFAULT);
*ap += sizeof(struct getbmapx);
return 0;
}
STATIC int
xfs_ioc_getbmapx(
struct xfs_inode *ip,
void __user *arg)
{
struct getbmapx bmx;
int error;
if (copy_from_user(&bmx, arg, sizeof(bmx)))
return -XFS_ERROR(EFAULT);
if (bmx.bmv_count < 2)
return -XFS_ERROR(EINVAL);
if (bmx.bmv_iflags & (~BMV_IF_VALID))
return -XFS_ERROR(EINVAL);
error = xfs_getbmap(ip, &bmx, xfs_getbmapx_format,
(struct getbmapx *)arg+1);
if (error)
return -error;
/* copy back header */
if (copy_to_user(arg, &bmx, sizeof(struct getbmapx)))
return -XFS_ERROR(EFAULT);
return 0;
}
/*
* Note: some of the ioctl's return positive numbers as a
* byte count indicating success, such as readlink_by_handle.
* So we don't "sign flip" like most other routines. This means
* true errors need to be returned as a negative value.
*/
long
xfs_file_ioctl(
struct file *filp,
unsigned int cmd,
unsigned long p)
{
struct inode *inode = filp->f_path.dentry->d_inode;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
void __user *arg = (void __user *)p;
int ioflags = 0;
int error;
if (filp->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
trace_xfs_file_ioctl(ip);
switch (cmd) {
case FITRIM:
return xfs_ioc_trim(mp, arg);
case XFS_IOC_ALLOCSP:
case XFS_IOC_FREESP:
case XFS_IOC_RESVSP:
case XFS_IOC_UNRESVSP:
case XFS_IOC_ALLOCSP64:
case XFS_IOC_FREESP64:
case XFS_IOC_RESVSP64:
case XFS_IOC_UNRESVSP64:
case XFS_IOC_ZERO_RANGE: {
xfs_flock64_t bf;
if (copy_from_user(&bf, arg, sizeof(bf)))
return -XFS_ERROR(EFAULT);
return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
}
case XFS_IOC_DIOINFO: {
struct dioattr da;
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
da.d_mem = da.d_miniosz = 1 << target->bt_sshift;
da.d_maxiosz = INT_MAX & ~(da.d_miniosz - 1);
if (copy_to_user(arg, &da, sizeof(da)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSBULKSTAT_SINGLE:
case XFS_IOC_FSBULKSTAT:
case XFS_IOC_FSINUMBERS:
return xfs_ioc_bulkstat(mp, cmd, arg);
case XFS_IOC_FSGEOMETRY_V1:
return xfs_ioc_fsgeometry_v1(mp, arg);
case XFS_IOC_FSGEOMETRY:
return xfs_ioc_fsgeometry(mp, arg);
case XFS_IOC_GETVERSION:
return put_user(inode->i_generation, (int __user *)arg);
case XFS_IOC_FSGETXATTR:
return xfs_ioc_fsgetxattr(ip, 0, arg);
case XFS_IOC_FSGETXATTRA:
return xfs_ioc_fsgetxattr(ip, 1, arg);
2008-04-18 10:59:45 +08:00
case XFS_IOC_FSSETXATTR:
return xfs_ioc_fssetxattr(ip, filp, arg);
case XFS_IOC_GETXFLAGS:
2008-04-18 10:59:45 +08:00
return xfs_ioc_getxflags(ip, arg);
case XFS_IOC_SETXFLAGS:
2008-04-18 10:59:45 +08:00
return xfs_ioc_setxflags(ip, filp, arg);
case XFS_IOC_FSSETDM: {
struct fsdmidata dmi;
if (copy_from_user(&dmi, arg, sizeof(dmi)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_set_dmattrs(ip, dmi.fsd_dmevmask,
dmi.fsd_dmstate);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GETBMAP:
case XFS_IOC_GETBMAPA:
return xfs_ioc_getbmap(ip, ioflags, cmd, arg);
case XFS_IOC_GETBMAPX:
return xfs_ioc_getbmapx(ip, arg);
case XFS_IOC_FD_TO_HANDLE:
case XFS_IOC_PATH_TO_HANDLE:
case XFS_IOC_PATH_TO_FSHANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(hreq)))
return -XFS_ERROR(EFAULT);
return xfs_find_handle(cmd, &hreq);
}
case XFS_IOC_OPEN_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_open_by_handle(filp, &hreq);
}
case XFS_IOC_FSSETDM_BY_HANDLE:
return xfs_fssetdm_by_handle(filp, arg);
case XFS_IOC_READLINK_BY_HANDLE: {
xfs_fsop_handlereq_t hreq;
if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
return -XFS_ERROR(EFAULT);
return xfs_readlink_by_handle(filp, &hreq);
}
case XFS_IOC_ATTRLIST_BY_HANDLE:
return xfs_attrlist_by_handle(filp, arg);
case XFS_IOC_ATTRMULTI_BY_HANDLE:
return xfs_attrmulti_by_handle(filp, arg);
case XFS_IOC_SWAPEXT: {
struct xfs_swapext sxp;
if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_swapext(&sxp);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSCOUNTS: {
xfs_fsop_counts_t out;
error = xfs_fs_counts(mp, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_SET_RESBLKS: {
xfs_fsop_resblks_t inout;
__uint64_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -XFS_ERROR(EROFS);
if (copy_from_user(&inout, arg, sizeof(inout)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
/* input parameter is passed in resblks field of structure */
in = inout.resblks;
error = xfs_reserve_blocks(mp, &in, &inout);
mnt_drop_write_file(filp);
if (error)
return -error;
if (copy_to_user(arg, &inout, sizeof(inout)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_GET_RESBLKS: {
xfs_fsop_resblks_t out;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_reserve_blocks(mp, NULL, &out);
if (error)
return -error;
if (copy_to_user(arg, &out, sizeof(out)))
return -XFS_ERROR(EFAULT);
return 0;
}
case XFS_IOC_FSGROWFSDATA: {
xfs_growfs_data_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_data(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSLOG: {
xfs_growfs_log_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_log(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_FSGROWFSRT: {
xfs_growfs_rt_t in;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = mnt_want_write_file(filp);
if (error)
return error;
error = xfs_growfs_rt(mp, &in);
mnt_drop_write_file(filp);
return -error;
}
case XFS_IOC_GOINGDOWN: {
__uint32_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(in, (__uint32_t __user *)arg))
return -XFS_ERROR(EFAULT);
error = xfs_fs_goingdown(mp, in);
return -error;
}
case XFS_IOC_ERROR_INJECTION: {
xfs_error_injection_t in;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&in, arg, sizeof(in)))
return -XFS_ERROR(EFAULT);
error = xfs_errortag_add(in.errtag, mp);
return -error;
}
case XFS_IOC_ERROR_CLEARALL:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
error = xfs_errortag_clearall(mp, 1);
return -error;
case XFS_IOC_FREE_EOFBLOCKS: {
struct xfs_eofblocks eofb;
if (copy_from_user(&eofb, arg, sizeof(eofb)))
return -XFS_ERROR(EFAULT);
if (eofb.eof_version != XFS_EOFBLOCKS_VERSION)
return -XFS_ERROR(EINVAL);
if (eofb.eof_flags & ~XFS_EOF_FLAGS_VALID)
return -XFS_ERROR(EINVAL);
if (memchr_inv(&eofb.pad32, 0, sizeof(eofb.pad32)) ||
memchr_inv(eofb.pad64, 0, sizeof(eofb.pad64)))
return -XFS_ERROR(EINVAL);
error = xfs_icache_free_eofblocks(mp, &eofb);
return -error;
}
default:
return -ENOTTY;
}
}