#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
-#include "xfs_dir.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
-#include "xfs_dir_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_itable.h"
#include "xfs_dfrag.h"
#include "xfs_error.h"
-#include "xfs_mac.h"
#include "xfs_rw.h"
+#include "xfs_vnodeops.h"
+#include "xfs_trace.h"
+
+
+static int xfs_swap_extents(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
+ xfs_swapext_t *sxp);
/*
- * Syssgi interface for swapext
+ * ioctl interface for swapext
*/
int
xfs_swapext(
- xfs_swapext_t __user *sxu)
+ xfs_swapext_t *sxp)
{
- xfs_swapext_t *sxp;
- xfs_inode_t *ip=NULL, *tip=NULL;
- xfs_mount_t *mp;
- struct file *fp = NULL, *tfp = NULL;
- bhv_vnode_t *vp, *tvp;
+ xfs_inode_t *ip, *tip;
+ struct file *file, *tmp_file;
int error = 0;
- sxp = kmem_alloc(sizeof(xfs_swapext_t), KM_MAYFAIL);
- if (!sxp) {
- error = XFS_ERROR(ENOMEM);
- goto error0;
+ /* Pull information for the target fd */
+ file = fget((int)sxp->sx_fdtarget);
+ if (!file) {
+ error = XFS_ERROR(EINVAL);
+ goto out;
}
- if (copy_from_user(sxp, sxu, sizeof(xfs_swapext_t))) {
- error = XFS_ERROR(EFAULT);
- goto error0;
+ if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND)) {
+ error = XFS_ERROR(EBADF);
+ goto out_put_file;
}
- /* Pull information for the target fd */
- if (((fp = fget((int)sxp->sx_fdtarget)) == NULL) ||
- ((vp = vn_from_inode(fp->f_dentry->d_inode)) == NULL)) {
+ tmp_file = fget((int)sxp->sx_fdtmp);
+ if (!tmp_file) {
error = XFS_ERROR(EINVAL);
- goto error0;
+ goto out_put_file;
}
- ip = xfs_vtoi(vp);
- if (ip == NULL) {
+ if (!(tmp_file->f_mode & FMODE_WRITE) ||
+ (tmp_file->f_flags & O_APPEND)) {
error = XFS_ERROR(EBADF);
- goto error0;
+ goto out_put_tmp_file;
}
- if (((tfp = fget((int)sxp->sx_fdtmp)) == NULL) ||
- ((tvp = vn_from_inode(tfp->f_dentry->d_inode)) == NULL)) {
+ if (IS_SWAPFILE(file->f_path.dentry->d_inode) ||
+ IS_SWAPFILE(tmp_file->f_path.dentry->d_inode)) {
error = XFS_ERROR(EINVAL);
- goto error0;
+ goto out_put_tmp_file;
}
- tip = xfs_vtoi(tvp);
- if (tip == NULL) {
- error = XFS_ERROR(EBADF);
- goto error0;
- }
+ ip = XFS_I(file->f_path.dentry->d_inode);
+ tip = XFS_I(tmp_file->f_path.dentry->d_inode);
if (ip->i_mount != tip->i_mount) {
- error = XFS_ERROR(EINVAL);
- goto error0;
+ error = XFS_ERROR(EINVAL);
+ goto out_put_tmp_file;
}
if (ip->i_ino == tip->i_ino) {
- error = XFS_ERROR(EINVAL);
- goto error0;
+ error = XFS_ERROR(EINVAL);
+ goto out_put_tmp_file;
}
- mp = ip->i_mount;
-
- if (XFS_FORCED_SHUTDOWN(mp)) {
- error = XFS_ERROR(EIO);
- goto error0;
+ if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
+ error = XFS_ERROR(EIO);
+ goto out_put_tmp_file;
}
- error = XFS_SWAP_EXTENTS(mp, &ip->i_iocore, &tip->i_iocore, sxp);
+ error = xfs_swap_extents(ip, tip, sxp);
+
+ out_put_tmp_file:
+ fput(tmp_file);
+ out_put_file:
+ fput(file);
+ out:
+ return error;
+}
+
+/*
+ * We need to check that the format of the data fork in the temporary inode is
+ * valid for the target inode before doing the swap. This is not a problem with
+ * attr1 because of the fixed fork offset, but attr2 has a dynamically sized
+ * data fork depending on the space the attribute fork is taking so we can get
+ * invalid formats on the target inode.
+ *
+ * E.g. target has space for 7 extents in extent format, temp inode only has
+ * space for 6. If we defragment down to 7 extents, then the tmp format is a
+ * btree, but when swapped it needs to be in extent format. Hence we can't just
+ * blindly swap data forks on attr2 filesystems.
+ *
+ * Note that we check the swap in both directions so that we don't end up with
+ * a corrupt temporary inode, either.
+ *
+ * Note that fixing the way xfs_fsr sets up the attribute fork in the source
+ * inode will prevent this situation from occurring, so all we do here is
+ * reject and log the attempt. basically we are putting the responsibility on
+ * userspace to get this right.
+ */
+static int
+xfs_swap_extents_check_format(
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip) /* tmp inode */
+{
- error0:
- if (fp != NULL)
- fput(fp);
- if (tfp != NULL)
- fput(tfp);
+ /* Should never get a local format */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
+ tip->i_d.di_format == XFS_DINODE_FMT_LOCAL)
+ return EINVAL;
- if (sxp != NULL)
- kmem_free(sxp, sizeof(xfs_swapext_t));
+ /*
+ * if the target inode has less extents that then temporary inode then
+ * why did userspace call us?
+ */
+ if (ip->i_d.di_nextents < tip->i_d.di_nextents)
+ return EINVAL;
- return error;
+ /*
+ * if the target inode is in extent form and the temp inode is in btree
+ * form then we will end up with the target inode in the wrong format
+ * as we already know there are less extents in the temp inode.
+ */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
+ return EINVAL;
+
+ /* Check temp in extent form to max in target */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max)
+ return EINVAL;
+
+ /* Check target in extent form to max in temp */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max)
+ return EINVAL;
+
+ /*
+ * If we are in a btree format, check that the temp root block will fit
+ * in the target and that it has enough extents to be in btree format
+ * in the target.
+ *
+ * Note that we have to be careful to allow btree->extent conversions
+ * (a common defrag case) which will occur when the temp inode is in
+ * extent format...
+ */
+ if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ ((XFS_IFORK_BOFF(ip) &&
+ tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip)) ||
+ XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <= ip->i_df.if_ext_max))
+ return EINVAL;
+
+ /* Reciprocal target->temp btree format checks */
+ if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
+ ((XFS_IFORK_BOFF(tip) &&
+ ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip)) ||
+ XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <= tip->i_df.if_ext_max))
+ return EINVAL;
+
+ return 0;
}
-int
+static int
xfs_swap_extents(
- xfs_inode_t *ip,
- xfs_inode_t *tip,
+ xfs_inode_t *ip, /* target inode */
+ xfs_inode_t *tip, /* tmp inode */
xfs_swapext_t *sxp)
{
xfs_mount_t *mp;
- xfs_inode_t *ips[2];
xfs_trans_t *tp;
xfs_bstat_t *sbp = &sxp->sx_stat;
- bhv_vnode_t *vp, *tvp;
xfs_ifork_t *tempifp, *ifp, *tifp;
int ilf_fields, tilf_fields;
- static uint lock_flags = XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL;
int error = 0;
int aforkblks = 0;
int taforkblks = 0;
__uint64_t tmp;
- char locked = 0;
mp = ip->i_mount;
tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
if (!tempifp) {
error = XFS_ERROR(ENOMEM);
- goto error0;
+ goto out;
}
sbp = &sxp->sx_stat;
- vp = XFS_ITOV(ip);
- tvp = XFS_ITOV(tip);
-
- /* Lock in i_ino order */
- if (ip->i_ino < tip->i_ino) {
- ips[0] = ip;
- ips[1] = tip;
- } else {
- ips[0] = tip;
- ips[1] = ip;
- }
-
- xfs_lock_inodes(ips, 2, 0, lock_flags);
- locked = 1;
- /* Check permissions */
- error = xfs_iaccess(ip, S_IWUSR, NULL);
- if (error)
- goto error0;
-
- error = xfs_iaccess(tip, S_IWUSR, NULL);
- if (error)
- goto error0;
+ /*
+ * we have to do two separate lock calls here to keep lockdep
+ * happy. If we try to get all the locks in one call, lock will
+ * report false positives when we drop the ILOCK and regain them
+ * below.
+ */
+ xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/* Verify that both files have the same format */
if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
error = XFS_ERROR(EINVAL);
- goto error0;
+ goto out_unlock;
}
/* Verify both files are either real-time or non-realtime */
- if ((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) !=
- (tip->i_d.di_flags & XFS_DIFLAG_REALTIME)) {
- error = XFS_ERROR(EINVAL);
- goto error0;
- }
-
- /* Should never get a local format */
- if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
- tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+ if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
error = XFS_ERROR(EINVAL);
- goto error0;
+ goto out_unlock;
}
- if (VN_CACHED(tvp) != 0) {
- xfs_inval_cached_trace(&tip->i_iocore, 0, -1, 0, -1);
- bhv_vop_flushinval_pages(tvp, 0, -1, FI_REMAPF_LOCKED);
+ if (VN_CACHED(VFS_I(tip)) != 0) {
+ error = xfs_flushinval_pages(tip, 0, -1,
+ FI_REMAPF_LOCKED);
+ if (error)
+ goto out_unlock;
}
/* Verify O_DIRECT for ftmp */
- if (VN_CACHED(tvp) != 0) {
+ if (VN_CACHED(VFS_I(tip)) != 0) {
error = XFS_ERROR(EINVAL);
- goto error0;
+ goto out_unlock;
}
/* Verify all data are being swapped */
sxp->sx_length != ip->i_d.di_size ||
sxp->sx_length != tip->i_d.di_size) {
error = XFS_ERROR(EFAULT);
- goto error0;
+ goto out_unlock;
}
- /*
- * If the target has extended attributes, the tmp file
- * must also in order to ensure the correct data fork
- * format.
- */
- if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
- error = XFS_ERROR(EINVAL);
- goto error0;
+ trace_xfs_swap_extent_before(ip, 0);
+ trace_xfs_swap_extent_before(tip, 1);
+
+ /* check inode formats now that data is flushed */
+ error = xfs_swap_extents_check_format(ip, tip);
+ if (error) {
+ xfs_fs_cmn_err(CE_NOTE, mp,
+ "%s: inode 0x%llx format is incompatible for exchanging.",
+ __FILE__, ip->i_ino);
+ goto out_unlock;
}
/*
* process that the file was not changed out from
* under it.
*/
- if ((sbp->bs_ctime.tv_sec != ip->i_d.di_ctime.t_sec) ||
- (sbp->bs_ctime.tv_nsec != ip->i_d.di_ctime.t_nsec) ||
- (sbp->bs_mtime.tv_sec != ip->i_d.di_mtime.t_sec) ||
- (sbp->bs_mtime.tv_nsec != ip->i_d.di_mtime.t_nsec)) {
+ if ((sbp->bs_ctime.tv_sec != VFS_I(ip)->i_ctime.tv_sec) ||
+ (sbp->bs_ctime.tv_nsec != VFS_I(ip)->i_ctime.tv_nsec) ||
+ (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
+ (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
error = XFS_ERROR(EBUSY);
- goto error0;
+ goto out_unlock;
}
/* We need to fail if the file is memory mapped. Once we have tossed
* vop_read (or write in the case of autogrow) they block on the iolock
* until we have switched the extents.
*/
- if (VN_MAPPED(vp)) {
+ if (VN_MAPPED(VFS_I(ip))) {
error = XFS_ERROR(EBUSY);
- goto error0;
+ goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
* fields change.
*/
- bhv_vop_toss_pages(vp, 0, -1, FI_REMAPF);
+ xfs_tosspages(ip, 0, -1, FI_REMAPF);
tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
if ((error = xfs_trans_reserve(tp, 0,
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
xfs_iunlock(tip, XFS_IOLOCK_EXCL);
xfs_trans_cancel(tp, 0);
- locked = 0;
- goto error0;
+ goto out;
}
- xfs_lock_inodes(ips, 2, 0, XFS_ILOCK_EXCL);
+ xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
/*
* Count the number of extended attribute blocks
if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
- if (error) {
- xfs_trans_cancel(tp, 0);
- goto error0;
- }
+ if (error)
+ goto out_trans_cancel;
}
if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
(tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
&taforkblks);
- if (error) {
- xfs_trans_cancel(tp, 0);
- goto error0;
- }
+ if (error)
+ goto out_trans_cancel;
}
/*
*tifp = *tempifp; /* struct copy */
/*
+ * Fix the in-memory data fork values that are dependent on the fork
+ * offset in the inode. We can't assume they remain the same as attr2
+ * has dynamic fork offsets.
+ */
+ ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+ tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
+ (uint)sizeof(xfs_bmbt_rec_t);
+
+ /*
* Fix the on-disk inode values
*/
tmp = (__uint64_t)ip->i_d.di_nblocks;
break;
}
- /*
- * Increment vnode ref counts since xfs_trans_commit &
- * xfs_trans_cancel will both unlock the inodes and
- * decrement the associated ref counts.
- */
- VN_HOLD(vp);
- VN_HOLD(tvp);
- xfs_trans_ijoin(tp, ip, lock_flags);
- xfs_trans_ijoin(tp, tip, lock_flags);
+ IHOLD(ip);
+ xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+ IHOLD(tip);
+ xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_log_inode(tp, ip, ilf_fields);
xfs_trans_log_inode(tp, tip, tilf_fields);
* If this is a synchronous mount, make sure that the
* transaction goes to disk before returning to the user.
*/
- if (mp->m_flags & XFS_MOUNT_WSYNC) {
+ if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
- }
- error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT, NULL);
- locked = 0;
+ error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT);
- error0:
- if (locked) {
- xfs_iunlock(ip, lock_flags);
- xfs_iunlock(tip, lock_flags);
- }
- if (tempifp != NULL)
- kmem_free(tempifp, sizeof(xfs_ifork_t));
+ trace_xfs_swap_extent_after(ip, 0);
+ trace_xfs_swap_extent_after(tip, 1);
+out:
+ kmem_free(tempifp);
return error;
+
+out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ goto out;
+
+out_trans_cancel:
+ xfs_trans_cancel(tp, 0);
+ goto out_unlock;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff