* along with this program; if not, write the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
+#include <linux/log2.h>
+
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
kmem_zone_t *xfs_ifork_zone;
kmem_zone_t *xfs_inode_zone;
-kmem_zone_t *xfs_icluster_zone;
/*
* Used in xfs_itruncate(). This is the maximum number of extents
}
#endif
+/*
+ * Find the buffer associated with the given inode map
+ * We do basic validation checks on the buffer once it has been
+ * retrieved from disk.
+ */
+STATIC int
+xfs_imap_to_bp(
+ xfs_mount_t *mp,
+ xfs_trans_t *tp,
+ xfs_imap_t *imap,
+ xfs_buf_t **bpp,
+ uint buf_flags,
+ uint imap_flags)
+{
+ int error;
+ int i;
+ int ni;
+ xfs_buf_t *bp;
+
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+ (int)imap->im_len, buf_flags, &bp);
+ if (error) {
+ if (error != EAGAIN) {
+ cmn_err(CE_WARN,
+ "xfs_imap_to_bp: xfs_trans_read_buf()returned "
+ "an error %d on %s. Returning error.",
+ error, mp->m_fsname);
+ } else {
+ ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+ }
+ return error;
+ }
+
+ /*
+ * Validate the magic number and version of every inode in the buffer
+ * (if DEBUG kernel) or the first inode in the buffer, otherwise.
+ */
+#ifdef DEBUG
+ ni = BBTOB(imap->im_len) >> mp->m_sb.sb_inodelog;
+#else /* usual case */
+ ni = 1;
+#endif
+
+ for (i = 0; i < ni; i++) {
+ int di_ok;
+ xfs_dinode_t *dip;
+
+ dip = (xfs_dinode_t *)xfs_buf_offset(bp,
+ (i << mp->m_sb.sb_inodelog));
+ di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
+ XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
+ if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
+ XFS_ERRTAG_ITOBP_INOTOBP,
+ XFS_RANDOM_ITOBP_INOTOBP))) {
+ if (imap_flags & XFS_IMAP_BULKSTAT) {
+ xfs_trans_brelse(tp, bp);
+ return XFS_ERROR(EINVAL);
+ }
+ XFS_CORRUPTION_ERROR("xfs_imap_to_bp",
+ XFS_ERRLEVEL_HIGH, mp, dip);
+#ifdef DEBUG
+ cmn_err(CE_PANIC,
+ "Device %s - bad inode magic/vsn "
+ "daddr %lld #%d (magic=%x)",
+ XFS_BUFTARG_NAME(mp->m_ddev_targp),
+ (unsigned long long)imap->im_blkno, i,
+ be16_to_cpu(dip->di_core.di_magic));
+#endif
+ xfs_trans_brelse(tp, bp);
+ return XFS_ERROR(EFSCORRUPTED);
+ }
+ }
+
+ xfs_inobp_check(mp, bp);
+
+ /*
+ * Mark the buffer as an inode buffer now that it looks good
+ */
+ XFS_BUF_SET_VTYPE(bp, B_FS_INO);
+
+ *bpp = bp;
+ return 0;
+}
+
/*
* This routine is called to map an inode number within a file
* system to the buffer containing the on-disk version of the
xfs_buf_t **bpp,
int *offset)
{
- int di_ok;
xfs_imap_t imap;
xfs_buf_t *bp;
int error;
- xfs_dinode_t *dip;
- /*
- * Call the space management code to find the location of the
- * inode on disk.
- */
imap.im_blkno = 0;
error = xfs_imap(mp, tp, ino, &imap, XFS_IMAP_LOOKUP);
- if (error != 0) {
- cmn_err(CE_WARN,
- "xfs_inotobp: xfs_imap() returned an "
- "error %d on %s. Returning error.", error, mp->m_fsname);
+ if (error)
return error;
- }
-
- /*
- * If the inode number maps to a block outside the bounds of the
- * file system then return NULL rather than calling read_buf
- * and panicing when we get an error from the driver.
- */
- if ((imap.im_blkno + imap.im_len) >
- XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
- cmn_err(CE_WARN,
- "xfs_inotobp: inode number (%llu + %d) maps to a block outside the bounds "
- "of the file system %s. Returning EINVAL.",
- (unsigned long long)imap.im_blkno,
- imap.im_len, mp->m_fsname);
- return XFS_ERROR(EINVAL);
- }
- /*
- * Read in the buffer. If tp is NULL, xfs_trans_read_buf() will
- * default to just a read_buf() call.
- */
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
- (int)imap.im_len, XFS_BUF_LOCK, &bp);
-
- if (error) {
- cmn_err(CE_WARN,
- "xfs_inotobp: xfs_trans_read_buf() returned an "
- "error %d on %s. Returning error.", error, mp->m_fsname);
+ error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, 0);
+ if (error)
return error;
- }
- dip = (xfs_dinode_t *)xfs_buf_offset(bp, 0);
- di_ok =
- be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
- XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
- if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP,
- XFS_RANDOM_ITOBP_INOTOBP))) {
- XFS_CORRUPTION_ERROR("xfs_inotobp", XFS_ERRLEVEL_LOW, mp, dip);
- xfs_trans_brelse(tp, bp);
- cmn_err(CE_WARN,
- "xfs_inotobp: XFS_TEST_ERROR() returned an "
- "error on %s. Returning EFSCORRUPTED.", mp->m_fsname);
- return XFS_ERROR(EFSCORRUPTED);
- }
- xfs_inobp_check(mp, bp);
-
- /*
- * Set *dipp to point to the on-disk inode in the buffer.
- */
*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
*bpp = bp;
*offset = imap.im_boffset;
xfs_dinode_t **dipp,
xfs_buf_t **bpp,
xfs_daddr_t bno,
- uint imap_flags)
+ uint imap_flags,
+ uint buf_flags)
{
xfs_imap_t imap;
xfs_buf_t *bp;
int error;
- int i;
- int ni;
if (ip->i_blkno == (xfs_daddr_t)0) {
- /*
- * Call the space management code to find the location of the
- * inode on disk.
- */
imap.im_blkno = bno;
- if ((error = xfs_imap(mp, tp, ip->i_ino, &imap,
- XFS_IMAP_LOOKUP | imap_flags)))
+ error = xfs_imap(mp, tp, ip->i_ino, &imap,
+ XFS_IMAP_LOOKUP | imap_flags);
+ if (error)
return error;
- /*
- * If the inode number maps to a block outside the bounds
- * of the file system then return NULL rather than calling
- * read_buf and panicing when we get an error from the
- * driver.
- */
- if ((imap.im_blkno + imap.im_len) >
- XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
-#ifdef DEBUG
- xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
- "(imap.im_blkno (0x%llx) "
- "+ imap.im_len (0x%llx)) > "
- " XFS_FSB_TO_BB(mp, "
- "mp->m_sb.sb_dblocks) (0x%llx)",
- (unsigned long long) imap.im_blkno,
- (unsigned long long) imap.im_len,
- XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
-#endif /* DEBUG */
- return XFS_ERROR(EINVAL);
- }
-
/*
* Fill in the fields in the inode that will be used to
* map the inode to its buffer from now on.
}
ASSERT(bno == 0 || bno == imap.im_blkno);
- /*
- * Read in the buffer. If tp is NULL, xfs_trans_read_buf() will
- * default to just a read_buf() call.
- */
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap.im_blkno,
- (int)imap.im_len, XFS_BUF_LOCK, &bp);
- if (error) {
-#ifdef DEBUG
- xfs_fs_cmn_err(CE_ALERT, mp, "xfs_itobp: "
- "xfs_trans_read_buf() returned error %d, "
- "imap.im_blkno 0x%llx, imap.im_len 0x%llx",
- error, (unsigned long long) imap.im_blkno,
- (unsigned long long) imap.im_len);
-#endif /* DEBUG */
+ error = xfs_imap_to_bp(mp, tp, &imap, &bp, buf_flags, imap_flags);
+ if (error)
return error;
- }
-
- /*
- * Validate the magic number and version of every inode in the buffer
- * (if DEBUG kernel) or the first inode in the buffer, otherwise.
- * No validation is done here in userspace (xfs_repair).
- */
-#if !defined(__KERNEL__)
- ni = 0;
-#elif defined(DEBUG)
- ni = BBTOB(imap.im_len) >> mp->m_sb.sb_inodelog;
-#else /* usual case */
- ni = 1;
-#endif
- for (i = 0; i < ni; i++) {
- int di_ok;
- xfs_dinode_t *dip;
-
- dip = (xfs_dinode_t *)xfs_buf_offset(bp,
- (i << mp->m_sb.sb_inodelog));
- di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
- XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
- if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
- XFS_ERRTAG_ITOBP_INOTOBP,
- XFS_RANDOM_ITOBP_INOTOBP))) {
- if (imap_flags & XFS_IMAP_BULKSTAT) {
- xfs_trans_brelse(tp, bp);
- return XFS_ERROR(EINVAL);
- }
-#ifdef DEBUG
- cmn_err(CE_ALERT,
- "Device %s - bad inode magic/vsn "
- "daddr %lld #%d (magic=%x)",
- XFS_BUFTARG_NAME(mp->m_ddev_targp),
- (unsigned long long)imap.im_blkno, i,
- be16_to_cpu(dip->di_core.di_magic));
-#endif
- XFS_CORRUPTION_ERROR("xfs_itobp", XFS_ERRLEVEL_HIGH,
- mp, dip);
- xfs_trans_brelse(tp, bp);
- return XFS_ERROR(EFSCORRUPTED);
- }
+ if (!bp) {
+ ASSERT(buf_flags & XFS_BUF_TRYLOCK);
+ ASSERT(tp == NULL);
+ *bpp = NULL;
+ return EAGAIN;
}
- xfs_inobp_check(mp, bp);
-
- /*
- * Mark the buffer as an inode buffer now that it looks good
- */
- XFS_BUF_SET_VTYPE(bp, B_FS_INO);
-
- /*
- * Set *dipp to point to the on-disk inode in the buffer.
- */
*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
*bpp = bp;
return 0;
xfs_icdinode_t *dic = &ip->i_d;
return _xfs_dic2xflags(dic->di_flags) |
- (XFS_CFORK_Q(dic) ? XFS_XFLAG_HASATTR : 0);
+ (XFS_IFORK_Q(ip) ? XFS_XFLAG_HASATTR : 0);
}
uint
xfs_dic2xflags(
- xfs_dinode_core_t *dic)
+ xfs_dinode_t *dip)
{
+ xfs_dinode_core_t *dic = &dip->di_core;
+
return _xfs_dic2xflags(be16_to_cpu(dic->di_flags)) |
- (XFS_CFORK_Q_DISK(dic) ? XFS_XFLAG_HASATTR : 0);
+ (XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
}
/*
* return NULL as well. Set i_blkno to 0 so that xfs_itobp() will
* know that this is a new incore inode.
*/
- error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags);
+ error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags, XFS_BUF_LOCK);
if (error) {
kmem_zone_free(xfs_inode_zone, ip);
return error;
* Initialize inode's trace buffers.
* Do this before xfs_iformat in case it adds entries.
*/
-#ifdef XFS_VNODE_TRACE
- ip->i_trace = ktrace_alloc(VNODE_TRACE_SIZE, KM_SLEEP);
+#ifdef XFS_INODE_TRACE
+ ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_SLEEP);
#endif
#ifdef XFS_BMAP_TRACE
ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_SLEEP);
* the inode version number now. This way we only do the conversion
* here rather than here and in the flush/logging code.
*/
- if (XFS_SB_VERSION_HASNLINK(&tp->t_mountp->m_sb) &&
+ if (xfs_sb_version_hasnlink(&tp->t_mountp->m_sb) &&
ip->i_d.di_version == XFS_DINODE_VERSION_1) {
ip->i_d.di_version = XFS_DINODE_VERSION_2;
/*
ip->i_d.di_extsize = pip->i_d.di_extsize;
}
} else if ((mode & S_IFMT) == S_IFREG) {
- if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) {
+ if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
di_flags |= XFS_DIFLAG_REALTIME;
- ip->i_iocore.io_flags |= XFS_IOCORE_RT;
- }
if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
di_flags |= XFS_DIFLAG_EXTSIZE;
ip->i_d.di_extsize = pip->i_d.di_extsize;
if ((ip->i_d.di_mode & S_IFMT) != S_IFREG)
return;
- if (ip->i_d.di_flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_EXTSIZE))
+ if (XFS_IS_REALTIME_INODE(ip))
+ return;
+
+ if (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
return;
nimaps = 2;
xfs_fileoff_t size_last_block;
int error;
- ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE | MR_ACCESS));
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED));
mp = ip->i_mount;
/*
bhv_vnode_t *vp;
int error = 0;
- ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT((new_size == 0) || (new_size <= ip->i_size));
ASSERT((flags == XFS_ITRUNC_DEFINITE) ||
(flags == XFS_ITRUNC_MAYBE));
}
/*
- * Shrink the file to the given new_size. The new
- * size must be smaller than the current size.
- * This will free up the underlying blocks
- * in the removed range after a call to xfs_itruncate_start()
- * or xfs_atruncate_start().
+ * Shrink the file to the given new_size. The new size must be smaller than
+ * the current size. This will free up the underlying blocks in the removed
+ * range after a call to xfs_itruncate_start() or xfs_atruncate_start().
*
- * The transaction passed to this routine must have made
- * a permanent log reservation of at least XFS_ITRUNCATE_LOG_RES.
- * This routine may commit the given transaction and
- * start new ones, so make sure everything involved in
- * the transaction is tidy before calling here.
- * Some transaction will be returned to the caller to be
- * committed. The incoming transaction must already include
- * the inode, and both inode locks must be held exclusively.
- * The inode must also be "held" within the transaction. On
- * return the inode will be "held" within the returned transaction.
- * This routine does NOT require any disk space to be reserved
- * for it within the transaction.
+ * The transaction passed to this routine must have made a permanent log
+ * reservation of at least XFS_ITRUNCATE_LOG_RES. This routine may commit the
+ * given transaction and start new ones, so make sure everything involved in
+ * the transaction is tidy before calling here. Some transaction will be
+ * returned to the caller to be committed. The incoming transaction must
+ * already include the inode, and both inode locks must be held exclusively.
+ * The inode must also be "held" within the transaction. On return the inode
+ * will be "held" within the returned transaction. This routine does NOT
+ * require any disk space to be reserved for it within the transaction.
*
- * The fork parameter must be either xfs_attr_fork or xfs_data_fork,
- * and it indicates the fork which is to be truncated. For the
- * attribute fork we only support truncation to size 0.
+ * The fork parameter must be either xfs_attr_fork or xfs_data_fork, and it
+ * indicates the fork which is to be truncated. For the attribute fork we only
+ * support truncation to size 0.
*
- * We use the sync parameter to indicate whether or not the first
- * transaction we perform might have to be synchronous. For the attr fork,
- * it needs to be so if the unlink of the inode is not yet known to be
- * permanent in the log. This keeps us from freeing and reusing the
- * blocks of the attribute fork before the unlink of the inode becomes
- * permanent.
+ * We use the sync parameter to indicate whether or not the first transaction
+ * we perform might have to be synchronous. For the attr fork, it needs to be
+ * so if the unlink of the inode is not yet known to be permanent in the log.
+ * This keeps us from freeing and reusing the blocks of the attribute fork
+ * before the unlink of the inode becomes permanent.
*
- * For the data fork, we normally have to run synchronously if we're
- * being called out of the inactive path or we're being called
- * out of the create path where we're truncating an existing file.
- * Either way, the truncate needs to be sync so blocks don't reappear
- * in the file with altered data in case of a crash. wsync filesystems
- * can run the first case async because anything that shrinks the inode
- * has to run sync so by the time we're called here from inactive, the
- * inode size is permanently set to 0.
+ * For the data fork, we normally have to run synchronously if we're being
+ * called out of the inactive path or we're being called out of the create path
+ * where we're truncating an existing file. Either way, the truncate needs to
+ * be sync so blocks don't reappear in the file with altered data in case of a
+ * crash. wsync filesystems can run the first case async because anything that
+ * shrinks the inode has to run sync so by the time we're called here from
+ * inactive, the inode size is permanently set to 0.
*
- * Calls from the truncate path always need to be sync unless we're
- * in a wsync filesystem and the file has already been unlinked.
+ * Calls from the truncate path always need to be sync unless we're in a wsync
+ * filesystem and the file has already been unlinked.
*
- * The caller is responsible for correctly setting the sync parameter.
- * It gets too hard for us to guess here which path we're being called
- * out of just based on inode state.
+ * The caller is responsible for correctly setting the sync parameter. It gets
+ * too hard for us to guess here which path we're being called out of just
+ * based on inode state.
+ *
+ * If we get an error, we must return with the inode locked and linked into the
+ * current transaction. This keeps things simple for the higher level code,
+ * because it always knows that the inode is locked and held in the transaction
+ * that returns to it whether errors occur or not. We don't mark the inode
+ * dirty on error so that transactions can be easily aborted if possible.
*/
int
xfs_itruncate_finish(
xfs_bmap_free_t free_list;
int error;
- ASSERT(ismrlocked(&ip->i_iolock, MR_UPDATE) != 0);
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE) != 0);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
ASSERT((new_size == 0) || (new_size <= ip->i_size));
ASSERT(*tp != NULL);
ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
* runs.
*/
XFS_BMAP_INIT(&free_list, &first_block);
- error = XFS_BUNMAPI(mp, ntp, &ip->i_iocore,
+ error = xfs_bunmapi(ntp, ip,
first_unmap_block, unmap_len,
XFS_BMAPI_AFLAG(fork) |
(sync ? 0 : XFS_BMAPI_ASYNC),
*/
error = xfs_bmap_finish(tp, &free_list, &committed);
ntp = *tp;
+ if (committed) {
+ /* link the inode into the next xact in the chain */
+ xfs_trans_ijoin(ntp, ip,
+ XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+ xfs_trans_ihold(ntp, ip);
+ }
+
if (error) {
/*
- * If the bmap finish call encounters an error,
- * return to the caller where the transaction
- * can be properly aborted. We just need to
- * make sure we're not holding any resources
- * that we were not when we came in.
+ * If the bmap finish call encounters an error, return
+ * to the caller where the transaction can be properly
+ * aborted. We just need to make sure we're not
+ * holding any resources that we were not when we came
+ * in.
*
- * Aborting from this point might lose some
- * blocks in the file system, but oh well.
+ * Aborting from this point might lose some blocks in
+ * the file system, but oh well.
*/
xfs_bmap_cancel(&free_list);
- if (committed) {
- /*
- * If the passed in transaction committed
- * in xfs_bmap_finish(), then we want to
- * add the inode to this one before returning.
- * This keeps things simple for the higher
- * level code, because it always knows that
- * the inode is locked and held in the
- * transaction that returns to it whether
- * errors occur or not. We don't mark the
- * inode dirty so that this transaction can
- * be easily aborted if possible.
- */
- xfs_trans_ijoin(ntp, ip,
- XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- xfs_trans_ihold(ntp, ip);
- }
return error;
}
if (committed) {
/*
- * The first xact was committed,
- * so add the inode to the new one.
- * Mark it dirty so it will be logged
- * and moved forward in the log as
- * part of every commit.
+ * Mark the inode dirty so it will be logged and
+ * moved forward in the log as part of every commit.
*/
- xfs_trans_ijoin(ntp, ip,
- XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
- xfs_trans_ihold(ntp, ip);
xfs_trans_log_inode(ntp, ip, XFS_ILOG_CORE);
}
+
ntp = xfs_trans_dup(ntp);
- (void) xfs_trans_commit(*tp, 0);
+ error = xfs_trans_commit(*tp, 0);
*tp = ntp;
- error = xfs_trans_reserve(ntp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
- XFS_TRANS_PERM_LOG_RES,
- XFS_ITRUNCATE_LOG_COUNT);
- /*
- * Add the inode being truncated to the next chained
- * transaction.
- */
+
+ /* link the inode into the next transaction in the chain */
xfs_trans_ijoin(ntp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
xfs_trans_ihold(ntp, ip);
+
+ if (!error)
+ error = xfs_trans_reserve(ntp, 0,
+ XFS_ITRUNCATE_LOG_RES(mp), 0,
+ XFS_TRANS_PERM_LOG_RES,
+ XFS_ITRUNCATE_LOG_COUNT);
if (error)
- return (error);
+ return error;
}
/*
* Only update the size in the case of the data fork, but
xfs_fsize_t new_size,
cred_t *credp)
{
- int error;
-
- ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
- ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
ASSERT(new_size > ip->i_size);
/*
* xfs_write_file() beyond the end of the file
* and any blocks between the old and new file sizes.
*/
- error = xfs_zero_eof(XFS_ITOV(ip), &ip->i_iocore, new_size,
- ip->i_size);
- return error;
+ return xfs_zero_eof(ip, new_size, ip->i_size);
}
/*
xfs_fsize_t new_size,
int change_flag)
{
- ASSERT(ismrlocked(&(ip->i_lock), MR_UPDATE) != 0);
- ASSERT(ismrlocked(&(ip->i_iolock), MR_UPDATE) != 0);
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
ASSERT(ip->i_transp == tp);
ASSERT(new_size > ip->i_size);
ASSERT(agi->agi_unlinked[bucket_index]);
ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino);
- error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
- if (error)
- return error;
-
- /*
- * Clear the on-disk di_nlink. This is to prevent xfs_bulkstat
- * from picking up this inode when it is reclaimed (its incore state
- * initialzed but not flushed to disk yet). The in-core di_nlink is
- * already cleared in xfs_droplink() and a corresponding transaction
- * logged. The hack here just synchronizes the in-core to on-disk
- * di_nlink value in advance before the actual inode sync to disk.
- * This is OK because the inode is already unlinked and would never
- * change its di_nlink again for this inode generation.
- * This is a temporary hack that would require a proper fix
- * in the future.
- */
- dip->di_core.di_nlink = 0;
-
if (be32_to_cpu(agi->agi_unlinked[bucket_index]) != NULLAGINO) {
/*
* There is already another inode in the bucket we need
* Here we put the head pointer into our next pointer,
* and then we fall through to point the head at us.
*/
+ error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+ if (error)
+ return error;
+
ASSERT(be32_to_cpu(dip->di_next_unlinked) == NULLAGINO);
/* both on-disk, don't endian flip twice */
dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
* of dealing with the buffer when there is no need to
* change it.
*/
- error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
+ error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
if (error) {
cmn_err(CE_WARN,
"xfs_iunlink_remove: xfs_itobp() returned an error %d on %s. Returning error.",
* Now last_ibp points to the buffer previous to us on
* the unlinked list. Pull us from the list.
*/
- error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0);
+ error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
if (error) {
cmn_err(CE_WARN,
"xfs_iunlink_remove: xfs_itobp() returned an error %d on %s. Returning error.",
return 0;
}
-STATIC_INLINE int xfs_inode_clean(xfs_inode_t *ip)
-{
- return (((ip->i_itemp == NULL) ||
- !(ip->i_itemp->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
- (ip->i_update_core == 0));
-}
-
STATIC void
xfs_ifree_cluster(
xfs_inode_t *free_ip,
xfs_inode_log_item_t *iip;
xfs_log_item_t *lip;
xfs_perag_t *pag = xfs_get_perag(mp, inum);
- SPLDECL(s);
if (mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp)) {
blks_per_cluster = 1;
iip = (xfs_inode_log_item_t *)lip;
ASSERT(iip->ili_logged == 1);
lip->li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*)) xfs_istale_done;
- AIL_LOCK(mp,s);
+ spin_lock(&mp->m_ail_lock);
iip->ili_flush_lsn = iip->ili_item.li_lsn;
- AIL_UNLOCK(mp, s);
+ spin_unlock(&mp->m_ail_lock);
xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
pre_flushed++;
}
iip->ili_last_fields = iip->ili_format.ilf_fields;
iip->ili_format.ilf_fields = 0;
iip->ili_logged = 1;
- AIL_LOCK(mp,s);
+ spin_lock(&mp->m_ail_lock);
iip->ili_flush_lsn = iip->ili_item.li_lsn;
- AIL_UNLOCK(mp, s);
+ spin_unlock(&mp->m_ail_lock);
xfs_buf_attach_iodone(bp,
(void(*)(xfs_buf_t*,xfs_log_item_t*))
int error;
int delete;
xfs_ino_t first_ino;
+ xfs_dinode_t *dip;
+ xfs_buf_t *ibp;
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(ip->i_transp == tp);
ASSERT(ip->i_d.di_nlink == 0);
ASSERT(ip->i_d.di_nextents == 0);
* by reincarnations of this inode.
*/
ip->i_d.di_gen++;
+
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+ if (error)
+ return error;
+
+ /*
+ * Clear the on-disk di_mode. This is to prevent xfs_bulkstat
+ * from picking up this inode when it is reclaimed (its incore state
+ * initialzed but not flushed to disk yet). The in-core di_mode is
+ * already cleared and a corresponding transaction logged.
+ * The hack here just synchronizes the in-core to on-disk
+ * di_mode value in advance before the actual inode sync to disk.
+ * This is OK because the inode is already unlinked and would never
+ * change its di_mode again for this inode generation.
+ * This is a temporary hack that would require a proper fix
+ * in the future.
+ */
+ dip->di_core.di_mode = 0;
+
if (delete) {
xfs_ifree_cluster(ip, tp, first_ino);
}
fsbno = imap->im_blkno ?
XFS_DADDR_TO_FSB(mp, imap->im_blkno) : NULLFSBLOCK;
error = xfs_dilocate(mp, tp, ino, &fsbno, &len, &off, flags);
- if (error != 0) {
+ if (error)
return error;
- }
+
imap->im_blkno = XFS_FSB_TO_DADDR(mp, fsbno);
imap->im_len = XFS_FSB_TO_BB(mp, len);
imap->im_agblkno = XFS_FSB_TO_AGBNO(mp, fsbno);
imap->im_ioffset = (ushort)off;
imap->im_boffset = (ushort)(off << mp->m_sb.sb_inodelog);
+
+ /*
+ * If the inode number maps to a block outside the bounds
+ * of the file system then return NULL rather than calling
+ * read_buf and panicing when we get an error from the
+ * driver.
+ */
+ if ((imap->im_blkno + imap->im_len) >
+ XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
+ xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
+ "(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
+ " XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
+ (unsigned long long) imap->im_blkno,
+ (unsigned long long) imap->im_len,
+ XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
+ return EINVAL;
+ }
return 0;
}
xfs_idestroy(
xfs_inode_t *ip)
{
-
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
mrfree(&ip->i_iolock);
freesema(&ip->i_flock);
-#ifdef XFS_VNODE_TRACE
+#ifdef XFS_INODE_TRACE
ktrace_free(ip->i_trace);
#endif
#ifdef XFS_BMAP_TRACE
*/
xfs_mount_t *mp = ip->i_mount;
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
- int s;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
- AIL_LOCK(mp, s);
+ spin_lock(&mp->m_ail_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
- xfs_trans_delete_ail(mp, lip, s);
+ xfs_trans_delete_ail(mp, lip);
else
- AIL_UNLOCK(mp, s);
+ spin_unlock(&mp->m_ail_lock);
}
xfs_inode_item_destroy(ip);
}
xfs_ipin(
xfs_inode_t *ip)
{
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
atomic_inc(&ip->i_pincount);
}
{
ASSERT(atomic_read(&ip->i_pincount) > 0);
- if (atomic_dec_and_lock(&ip->i_pincount, &ip->i_flags_lock)) {
-
- /*
- * If the inode is currently being reclaimed, the link between
- * the bhv_vnode and the xfs_inode will be broken after the
- * XFS_IRECLAIM* flag is set. Hence, if these flags are not
- * set, then we can move forward and mark the linux inode dirty
- * knowing that it is still valid as it won't freed until after
- * the bhv_vnode<->xfs_inode link is broken in xfs_reclaim. The
- * i_flags_lock is used to synchronise the setting of the
- * XFS_IRECLAIM* flags and the breaking of the link, and so we
- * can execute atomically w.r.t to reclaim by holding this lock
- * here.
- *
- * However, we still need to issue the unpin wakeup call as the
- * inode reclaim may be blocked waiting for the inode to become
- * unpinned.
- */
-
- if (!__xfs_iflags_test(ip, XFS_IRECLAIM|XFS_IRECLAIMABLE)) {
- bhv_vnode_t *vp = XFS_ITOV_NULL(ip);
- struct inode *inode = NULL;
-
- BUG_ON(vp == NULL);
- inode = vn_to_inode(vp);
- BUG_ON(inode->i_state & I_CLEAR);
-
- /* make sync come back and flush this inode */
- if (!(inode->i_state & (I_NEW|I_FREEING)))
- mark_inode_dirty_sync(inode);
- }
- spin_unlock(&ip->i_flags_lock);
+ if (atomic_dec_and_test(&ip->i_pincount))
wake_up(&ip->i_ipin_wait);
- }
}
/*
- * This is called to wait for the given inode to be unpinned.
- * It will sleep until this happens. The caller must have the
- * inode locked in at least shared mode so that the buffer cannot
- * be subsequently pinned once someone is waiting for it to be
- * unpinned.
+ * This is called to unpin an inode. It can be directed to wait or to return
+ * immediately without waiting for the inode to be unpinned. The caller must
+ * have the inode locked in at least shared mode so that the buffer cannot be
+ * subsequently pinned once someone is waiting for it to be unpinned.
*/
STATIC void
-xfs_iunpin_wait(
- xfs_inode_t *ip)
+__xfs_iunpin_wait(
+ xfs_inode_t *ip,
+ int wait)
{
- xfs_inode_log_item_t *iip;
- xfs_lsn_t lsn;
-
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE | MR_ACCESS));
+ xfs_inode_log_item_t *iip = ip->i_itemp;
- if (atomic_read(&ip->i_pincount) == 0) {
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+ if (atomic_read(&ip->i_pincount) == 0)
return;
- }
- iip = ip->i_itemp;
- if (iip && iip->ili_last_lsn) {
- lsn = iip->ili_last_lsn;
- } else {
- lsn = (xfs_lsn_t)0;
- }
+ /* Give the log a push to start the unpinning I/O */
+ xfs_log_force(ip->i_mount, (iip && iip->ili_last_lsn) ?
+ iip->ili_last_lsn : 0, XFS_LOG_FORCE);
+ if (wait)
+ wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
+}
- /*
- * Give the log a push so we don't wait here too long.
- */
- xfs_log_force(ip->i_mount, lsn, XFS_LOG_FORCE);
+static inline void
+xfs_iunpin_wait(
+ xfs_inode_t *ip)
+{
+ __xfs_iunpin_wait(ip, 1);
+}
- wait_event(ip->i_ipin_wait, (atomic_read(&ip->i_pincount) == 0));
+static inline void
+xfs_iunpin_nowait(
+ xfs_inode_t *ip)
+{
+ __xfs_iunpin_wait(ip, 0);
}
xfs_fsblock_t start_block;
ifp = XFS_IFORK_PTR(ip, whichfork);
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(ifp->if_bytes > 0);
nrecs = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
* format indicates the current state of the fork.
*/
/*ARGSUSED*/
-STATIC int
+STATIC void
xfs_iflush_fork(
xfs_inode_t *ip,
xfs_dinode_t *dip,
static const short extflag[2] =
{ XFS_ILOG_DEXT, XFS_ILOG_AEXT };
- if (iip == NULL)
- return 0;
+ if (!iip)
+ return;
ifp = XFS_IFORK_PTR(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
* for the attribute fork.
*/
- if (ifp == NULL) {
+ if (!ifp) {
ASSERT(whichfork == XFS_ATTR_FORK);
- return 0;
+ return;
}
cp = XFS_DFORK_PTR(dip, whichfork);
mp = ip->i_mount;
ASSERT(0);
break;
}
+}
+
+STATIC int
+xfs_iflush_cluster(
+ xfs_inode_t *ip,
+ xfs_buf_t *bp)
+{
+ xfs_mount_t *mp = ip->i_mount;
+ xfs_perag_t *pag = xfs_get_perag(mp, ip->i_ino);
+ unsigned long first_index, mask;
+ int ilist_size;
+ xfs_inode_t **ilist;
+ xfs_inode_t *iq;
+ int nr_found;
+ int clcount = 0;
+ int bufwasdelwri;
+ int i;
+
+ ASSERT(pag->pagi_inodeok);
+ ASSERT(pag->pag_ici_init);
+
+ ilist_size = XFS_INODE_CLUSTER_SIZE(mp) * sizeof(xfs_inode_t *);
+ ilist = kmem_alloc(ilist_size, KM_MAYFAIL);
+ if (!ilist)
+ return 0;
+
+ mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
+ first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
+ read_lock(&pag->pag_ici_lock);
+ /* really need a gang lookup range call here */
+ nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)ilist,
+ first_index,
+ XFS_INODE_CLUSTER_SIZE(mp));
+ if (nr_found == 0)
+ goto out_free;
+
+ for (i = 0; i < nr_found; i++) {
+ iq = ilist[i];
+ if (iq == ip)
+ continue;
+ /* if the inode lies outside this cluster, we're done. */
+ if ((XFS_INO_TO_AGINO(mp, iq->i_ino) & mask) != first_index)
+ break;
+ /*
+ * Do an un-protected check to see if the inode is dirty and
+ * is a candidate for flushing. These checks will be repeated
+ * later after the appropriate locks are acquired.
+ */
+ if (xfs_inode_clean(iq) && xfs_ipincount(iq) == 0)
+ continue;
+
+ /*
+ * Try to get locks. If any are unavailable or it is pinned,
+ * then this inode cannot be flushed and is skipped.
+ */
+
+ if (!xfs_ilock_nowait(iq, XFS_ILOCK_SHARED))
+ continue;
+ if (!xfs_iflock_nowait(iq)) {
+ xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ continue;
+ }
+ if (xfs_ipincount(iq)) {
+ xfs_ifunlock(iq);
+ xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ continue;
+ }
+
+ /*
+ * arriving here means that this inode can be flushed. First
+ * re-check that it's dirty before flushing.
+ */
+ if (!xfs_inode_clean(iq)) {
+ int error;
+ error = xfs_iflush_int(iq, bp);
+ if (error) {
+ xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ goto cluster_corrupt_out;
+ }
+ clcount++;
+ } else {
+ xfs_ifunlock(iq);
+ }
+ xfs_iunlock(iq, XFS_ILOCK_SHARED);
+ }
+ if (clcount) {
+ XFS_STATS_INC(xs_icluster_flushcnt);
+ XFS_STATS_ADD(xs_icluster_flushinode, clcount);
+ }
+
+out_free:
+ read_unlock(&pag->pag_ici_lock);
+ kmem_free(ilist, ilist_size);
return 0;
+
+
+cluster_corrupt_out:
+ /*
+ * Corruption detected in the clustering loop. Invalidate the
+ * inode buffer and shut down the filesystem.
+ */
+ read_unlock(&pag->pag_ici_lock);
+ /*
+ * Clean up the buffer. If it was B_DELWRI, just release it --
+ * brelse can handle it with no problems. If not, shut down the
+ * filesystem before releasing the buffer.
+ */
+ bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
+ if (bufwasdelwri)
+ xfs_buf_relse(bp);
+
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+
+ if (!bufwasdelwri) {
+ /*
+ * Just like incore_relse: if we have b_iodone functions,
+ * mark the buffer as an error and call them. Otherwise
+ * mark it as stale and brelse.
+ */
+ if (XFS_BUF_IODONE_FUNC(bp)) {
+ XFS_BUF_CLR_BDSTRAT_FUNC(bp);
+ XFS_BUF_UNDONE(bp);
+ XFS_BUF_STALE(bp);
+ XFS_BUF_SHUT(bp);
+ XFS_BUF_ERROR(bp,EIO);
+ xfs_biodone(bp);
+ } else {
+ XFS_BUF_STALE(bp);
+ xfs_buf_relse(bp);
+ }
+ }
+
+ /*
+ * Unlocks the flush lock
+ */
+ xfs_iflush_abort(iq);
+ kmem_free(ilist, ilist_size);
+ return XFS_ERROR(EFSCORRUPTED);
}
/*
xfs_dinode_t *dip;
xfs_mount_t *mp;
int error;
- /* REFERENCED */
- xfs_inode_t *iq;
- int clcount; /* count of inodes clustered */
- int bufwasdelwri;
- struct hlist_node *entry;
+ int noblock = (flags == XFS_IFLUSH_ASYNC_NOBLOCK);
enum { INT_DELWRI = (1 << 0), INT_ASYNC = (1 << 1) };
XFS_STATS_INC(xs_iflush_count);
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(issemalocked(&(ip->i_flock)));
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
ip->i_d.di_nextents > ip->i_df.if_ext_max);
* If the inode isn't dirty, then just release the inode
* flush lock and do nothing.
*/
- if ((ip->i_update_core == 0) &&
- ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
+ if (xfs_inode_clean(ip)) {
ASSERT((iip != NULL) ?
!(iip->ili_item.li_flags & XFS_LI_IN_AIL) : 1);
xfs_ifunlock(ip);
}
/*
- * We can't flush the inode until it is unpinned, so
- * wait for it. We know noone new can pin it, because
- * we are holding the inode lock shared and you need
- * to hold it exclusively to pin the inode.
+ * We can't flush the inode until it is unpinned, so wait for it if we
+ * are allowed to block. We know noone new can pin it, because we are
+ * holding the inode lock shared and you need to hold it exclusively to
+ * pin the inode.
+ *
+ * If we are not allowed to block, force the log out asynchronously so
+ * that when we come back the inode will be unpinned. If other inodes
+ * in the same cluster are dirty, they will probably write the inode
+ * out for us if they occur after the log force completes.
*/
+ if (noblock && xfs_ipincount(ip)) {
+ xfs_iunpin_nowait(ip);
+ xfs_ifunlock(ip);
+ return EAGAIN;
+ }
xfs_iunpin_wait(ip);
/*
return XFS_ERROR(EIO);
}
- /*
- * Get the buffer containing the on-disk inode.
- */
- error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0);
- if (error) {
- xfs_ifunlock(ip);
- return error;
- }
-
/*
* Decide how buffer will be flushed out. This is done before
* the call to xfs_iflush_int because this field is zeroed by it.
case XFS_IFLUSH_DELWRI_ELSE_SYNC:
flags = 0;
break;
+ case XFS_IFLUSH_ASYNC_NOBLOCK:
case XFS_IFLUSH_ASYNC:
case XFS_IFLUSH_DELWRI_ELSE_ASYNC:
flags = INT_ASYNC;
case XFS_IFLUSH_DELWRI:
flags = INT_DELWRI;
break;
+ case XFS_IFLUSH_ASYNC_NOBLOCK:
case XFS_IFLUSH_ASYNC:
flags = INT_ASYNC;
break;
}
/*
- * First flush out the inode that xfs_iflush was called with.
+ * Get the buffer containing the on-disk inode.
*/
- error = xfs_iflush_int(ip, bp);
- if (error) {
- goto corrupt_out;
+ error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0,
+ noblock ? XFS_BUF_TRYLOCK : XFS_BUF_LOCK);
+ if (error || !bp) {
+ xfs_ifunlock(ip);
+ return error;
}
/*
- * inode clustering:
- * see if other inodes can be gathered into this write
+ * First flush out the inode that xfs_iflush was called with.
*/
- spin_lock(&ip->i_cluster->icl_lock);
- ip->i_cluster->icl_buf = bp;
-
- clcount = 0;
- hlist_for_each_entry(iq, entry, &ip->i_cluster->icl_inodes, i_cnode) {
- if (iq == ip)
- continue;
-
- /*
- * Do an un-protected check to see if the inode is dirty and
- * is a candidate for flushing. These checks will be repeated
- * later after the appropriate locks are acquired.
- */
- iip = iq->i_itemp;
- if ((iq->i_update_core == 0) &&
- ((iip == NULL) ||
- !(iip->ili_format.ilf_fields & XFS_ILOG_ALL)) &&
- xfs_ipincount(iq) == 0) {
- continue;
- }
-
- /*
- * Try to get locks. If any are unavailable,
- * then this inode cannot be flushed and is skipped.
- */
-
- /* get inode locks (just i_lock) */
- if (xfs_ilock_nowait(iq, XFS_ILOCK_SHARED)) {
- /* get inode flush lock */
- if (xfs_iflock_nowait(iq)) {
- /* check if pinned */
- if (xfs_ipincount(iq) == 0) {
- /* arriving here means that
- * this inode can be flushed.
- * first re-check that it's
- * dirty
- */
- iip = iq->i_itemp;
- if ((iq->i_update_core != 0)||
- ((iip != NULL) &&
- (iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
- clcount++;
- error = xfs_iflush_int(iq, bp);
- if (error) {
- xfs_iunlock(iq,
- XFS_ILOCK_SHARED);
- goto cluster_corrupt_out;
- }
- } else {
- xfs_ifunlock(iq);
- }
- } else {
- xfs_ifunlock(iq);
- }
- }
- xfs_iunlock(iq, XFS_ILOCK_SHARED);
- }
- }
- spin_unlock(&ip->i_cluster->icl_lock);
-
- if (clcount) {
- XFS_STATS_INC(xs_icluster_flushcnt);
- XFS_STATS_ADD(xs_icluster_flushinode, clcount);
- }
+ error = xfs_iflush_int(ip, bp);
+ if (error)
+ goto corrupt_out;
/*
- * If the buffer is pinned then push on the log so we won't
+ * If the buffer is pinned then push on the log now so we won't
* get stuck waiting in the write for too long.
*/
- if (XFS_BUF_ISPINNED(bp)){
+ if (XFS_BUF_ISPINNED(bp))
xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
- }
+
+ /*
+ * inode clustering:
+ * see if other inodes can be gathered into this write
+ */
+ error = xfs_iflush_cluster(ip, bp);
+ if (error)
+ goto cluster_corrupt_out;
if (flags & INT_DELWRI) {
xfs_bdwrite(mp, bp);
} else if (flags & INT_ASYNC) {
- xfs_bawrite(mp, bp);
+ error = xfs_bawrite(mp, bp);
} else {
error = xfs_bwrite(mp, bp);
}
corrupt_out:
xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
- xfs_iflush_abort(ip);
- /*
- * Unlocks the flush lock
- */
- return XFS_ERROR(EFSCORRUPTED);
-
cluster_corrupt_out:
- /* Corruption detected in the clustering loop. Invalidate the
- * inode buffer and shut down the filesystem.
- */
- spin_unlock(&ip->i_cluster->icl_lock);
-
- /*
- * Clean up the buffer. If it was B_DELWRI, just release it --
- * brelse can handle it with no problems. If not, shut down the
- * filesystem before releasing the buffer.
- */
- if ((bufwasdelwri= XFS_BUF_ISDELAYWRITE(bp))) {
- xfs_buf_relse(bp);
- }
-
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-
- if(!bufwasdelwri) {
- /*
- * Just like incore_relse: if we have b_iodone functions,
- * mark the buffer as an error and call them. Otherwise
- * mark it as stale and brelse.
- */
- if (XFS_BUF_IODONE_FUNC(bp)) {
- XFS_BUF_CLR_BDSTRAT_FUNC(bp);
- XFS_BUF_UNDONE(bp);
- XFS_BUF_STALE(bp);
- XFS_BUF_SHUT(bp);
- XFS_BUF_ERROR(bp,EIO);
- xfs_biodone(bp);
- } else {
- XFS_BUF_STALE(bp);
- xfs_buf_relse(bp);
- }
- }
-
- xfs_iflush_abort(iq);
/*
* Unlocks the flush lock
*/
+ xfs_iflush_abort(ip);
return XFS_ERROR(EFSCORRUPTED);
}
#ifdef XFS_TRANS_DEBUG
int first;
#endif
- SPLDECL(s);
- ASSERT(ismrlocked(&ip->i_lock, MR_UPDATE|MR_ACCESS));
+ ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
ASSERT(issemalocked(&(ip->i_flock)));
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
ip->i_d.di_nextents > ip->i_df.if_ext_max);
* If the inode isn't dirty, then just release the inode
* flush lock and do nothing.
*/
- if ((ip->i_update_core == 0) &&
- ((iip == NULL) || !(iip->ili_format.ilf_fields & XFS_ILOG_ALL))) {
+ if (xfs_inode_clean(ip)) {
xfs_ifunlock(ip);
return 0;
}
* has been updated, then make the conversion permanent.
*/
ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1 ||
- XFS_SB_VERSION_HASNLINK(&mp->m_sb));
+ xfs_sb_version_hasnlink(&mp->m_sb));
if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
- if (!XFS_SB_VERSION_HASNLINK(&mp->m_sb)) {
+ if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
/*
* Convert it back.
*/
}
}
- if (xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp) == EFSCORRUPTED) {
- goto corrupt_out;
- }
-
- if (XFS_IFORK_Q(ip)) {
- /*
- * The only error from xfs_iflush_fork is on the data fork.
- */
- (void) xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
- }
+ xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK, bp);
+ if (XFS_IFORK_Q(ip))
+ xfs_iflush_fork(ip, dip, iip, XFS_ATTR_FORK, bp);
xfs_inobp_check(mp, bp);
/*
iip->ili_logged = 1;
ASSERT(sizeof(xfs_lsn_t) == 8); /* don't lock if it shrinks */
- AIL_LOCK(mp,s);
+ spin_lock(&mp->m_ail_lock);
iip->ili_flush_lsn = iip->ili_item.li_lsn;
- AIL_UNLOCK(mp, s);
+ spin_unlock(&mp->m_ail_lock);
/*
* Attach the function xfs_iflush_done to the inode's
XFS_MOUNT_IUNLOCK(mp);
}
-/*
- * xfs_iaccess: check accessibility of inode for mode.
- */
-int
-xfs_iaccess(
- xfs_inode_t *ip,
- mode_t mode,
- cred_t *cr)
-{
- int error;
- mode_t orgmode = mode;
- struct inode *inode = vn_to_inode(XFS_ITOV(ip));
-
- if (mode & S_IWUSR) {
- umode_t imode = inode->i_mode;
-
- if (IS_RDONLY(inode) &&
- (S_ISREG(imode) || S_ISDIR(imode) || S_ISLNK(imode)))
- return XFS_ERROR(EROFS);
-
- if (IS_IMMUTABLE(inode))
- return XFS_ERROR(EACCES);
- }
-
- /*
- * If there's an Access Control List it's used instead of
- * the mode bits.
- */
- if ((error = _ACL_XFS_IACCESS(ip, mode, cr)) != -1)
- return error ? XFS_ERROR(error) : 0;
-
- if (current_fsuid(cr) != ip->i_d.di_uid) {
- mode >>= 3;
- if (!in_group_p((gid_t)ip->i_d.di_gid))
- mode >>= 3;
- }
-
- /*
- * If the DACs are ok we don't need any capability check.
- */
- if ((ip->i_d.di_mode & mode) == mode)
- return 0;
- /*
- * Read/write DACs are always overridable.
- * Executable DACs are overridable if at least one exec bit is set.
- */
- if (!(orgmode & S_IXUSR) ||
- (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
- if (capable_cred(cr, CAP_DAC_OVERRIDE))
- return 0;
-
- if ((orgmode == S_IRUSR) ||
- (S_ISDIR(inode->i_mode) && (!(orgmode & S_IWUSR)))) {
- if (capable_cred(cr, CAP_DAC_READ_SEARCH))
- return 0;
-#ifdef NOISE
- cmn_err(CE_NOTE, "Ick: mode=%o, orgmode=%o", mode, orgmode);
-#endif /* NOISE */
- return XFS_ERROR(EACCES);
- }
- return XFS_ERROR(EACCES);
-}
-
-/*
- * xfs_iroundup: round up argument to next power of two
- */
-uint
-xfs_iroundup(
- uint v)
-{
- int i;
- uint m;
-
- if ((v & (v - 1)) == 0)
- return v;
- ASSERT((v & 0x80000000) == 0);
- if ((v & (v + 1)) == 0)
- return v + 1;
- for (i = 0, m = 1; i < 31; i++, m <<= 1) {
- if (v & m)
- continue;
- v |= m;
- if ((v & (v + 1)) == 0)
- return v + 1;
- }
- ASSERT(0);
- return( 0 );
-}
-
#ifdef XFS_ILOCK_TRACE
ktrace_t *xfs_ilock_trace_buf;
return;
}
if (!is_power_of_2(new_size)){
- rnew_size = xfs_iroundup(new_size);
+ rnew_size = roundup_pow_of_two(new_size);
}
if (rnew_size != ifp->if_real_bytes) {
ifp->if_u1.if_extents =
else {
new_size += ifp->if_bytes;
if (!is_power_of_2(new_size)) {
- rnew_size = xfs_iroundup(new_size);
+ rnew_size = roundup_pow_of_two(new_size);
}
xfs_iext_inline_to_direct(ifp, rnew_size);
}
projects / linux-2.6-omap-h63xx.git / blobdiff