#include "xfs_vnodeops.h"
int
-xfs_open(
- xfs_inode_t *ip)
-{
- int mode;
-
- if (XFS_FORCED_SHUTDOWN(ip->i_mount))
- return XFS_ERROR(EIO);
-
- /*
- * If it's a directory with any blocks, read-ahead block 0
- * as we're almost certain to have the next operation be a read there.
- */
- if (S_ISDIR(ip->i_d.di_mode) && ip->i_d.di_nextents > 0) {
- mode = xfs_ilock_map_shared(ip);
- if (ip->i_d.di_nextents > 0)
- (void)xfs_da_reada_buf(NULL, ip, 0, XFS_DATA_FORK);
- xfs_iunlock(ip, mode);
- }
- return 0;
-}
-
-int
xfs_setattr(
struct xfs_inode *ip,
struct iattr *iattr,
- int flags,
- cred_t *credp)
+ int flags)
{
xfs_mount_t *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_ilock(ip, lock_flags);
/* boolean: are we the file owner? */
- file_owner = (current_fsuid(credp) == ip->i_d.di_uid);
+ file_owner = (current_fsuid() == ip->i_d.di_uid);
/*
* Change various properties of a file.
/*
* Change file ownership. Must be the owner or privileged.
- * If the system was configured with the "restricted_chown"
- * option, the owner is not permitted to give away the file,
- * and can change the group id only to a group of which he
- * or she is a member.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
* shall be equal to either the group ID or one of the
* supplementary group IDs of the calling process.
*/
- if (restricted_chown &&
- (iuid != uid || (igid != gid &&
- !in_group_p((gid_t)gid))) &&
+ if ((iuid != uid ||
+ (igid != gid && !in_group_p((gid_t)gid))) &&
!capable(CAP_CHOWN)) {
code = XFS_ERROR(EPERM);
goto error_return;
/*
* Change file ownership. Must be the owner or privileged.
- * If the system was configured with the "restricted_chown"
- * option, the owner is not permitted to give away the file,
- * and can change the group id only to a group of which he
- * or she is a member.
*/
if (mask & (ATTR_UID|ATTR_GID)) {
/*
ip->i_d.di_atime.t_sec = iattr->ia_atime.tv_sec;
ip->i_d.di_atime.t_nsec = iattr->ia_atime.tv_nsec;
ip->i_update_core = 1;
- timeflags &= ~XFS_ICHGTIME_ACC;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
return XFS_ERROR(EIO);
/* capture size updates in I/O completion before writing the inode. */
- error = filemap_fdatawait(VFS_I(ip)->i_mapping);
+ error = xfs_wait_on_pages(ip, 0, -1);
if (error)
return XFS_ERROR(error);
goto error0;
}
/*
+ * transaction commit worked ok so we can drop the extra ticket
+ * reference that we gained in xfs_trans_dup()
+ */
+ xfs_log_ticket_put(tp->t_ticket);
+
+ /*
* Remove the memory for extent descriptions (just bookkeeping).
*/
if (ip->i_df.if_bytes)
xfs_release(
xfs_inode_t *ip)
{
- bhv_vnode_t *vp = VFS_I(ip);
xfs_mount_t *mp = ip->i_mount;
int error;
* be exposed to that problem.
*/
truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
- if (truncated && VN_DIRTY(vp) && ip->i_delayed_blks > 0)
+ if (truncated && VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
xfs_flush_pages(ip, 0, -1, XFS_B_ASYNC, FI_NONE);
}
if (ip->i_d.di_nlink != 0) {
if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
- ((ip->i_size > 0) || (VN_CACHED(vp) > 0 ||
+ ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 ||
ip->i_delayed_blks > 0)) &&
(ip->i_df.if_flags & XFS_IFEXTENTS)) &&
(!(ip->i_d.di_flags &
xfs_inactive(
xfs_inode_t *ip)
{
- bhv_vnode_t *vp = VFS_I(ip);
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
int committed;
* If the inode is already free, then there can be nothing
* to clean up here.
*/
- if (ip->i_d.di_mode == 0 || VN_BAD(vp)) {
+ if (ip->i_d.di_mode == 0 || VN_BAD(VFS_I(ip))) {
ASSERT(ip->i_df.if_real_bytes == 0);
ASSERT(ip->i_df.if_broot_bytes == 0);
return VN_INACTIVE_CACHE;
if (ip->i_d.di_nlink != 0) {
if ((((ip->i_d.di_mode & S_IFMT) == S_IFREG) &&
- ((ip->i_size > 0) || (VN_CACHED(vp) > 0 ||
+ ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 ||
ip->i_delayed_blks > 0)) &&
(ip->i_df.if_flags & XFS_IFEXTENTS) &&
(!(ip->i_d.di_flags &
* Make sure that we have allocated dquot(s) on disk.
*/
error = XFS_QM_DQVOPALLOC(mp, dp,
- current_fsuid(credp), current_fsgid(credp), prid,
+ current_fsuid(), current_fsgid(), prid,
XFS_QMOPT_QUOTALL|XFS_QMOPT_INHERIT, &udqp, &gdqp);
if (error)
goto std_return;
xfs_trans_set_sync(tp);
}
- dp->i_gen++;
-
/*
* Attach the dquot(s) to the inodes and modify them incore.
* These ids of the inode couldn't have changed since the new
}
#ifdef DEBUG
-/*
- * Some counters to see if (and how often) we are hitting some deadlock
- * prevention code paths.
- */
-
-int xfs_rm_locks;
-int xfs_rm_lock_delays;
-int xfs_rm_attempts;
-#endif
-
-/*
- * The following routine will lock the inodes associated with the
- * directory and the named entry in the directory. The locks are
- * acquired in increasing inode number.
- *
- * If the entry is "..", then only the directory is locked. The
- * vnode ref count will still include that from the .. entry in
- * this case.
- *
- * There is a deadlock we need to worry about. If the locked directory is
- * in the AIL, it might be blocking up the log. The next inode we lock
- * could be already locked by another thread waiting for log space (e.g
- * a permanent log reservation with a long running transaction (see
- * xfs_itruncate_finish)). To solve this, we must check if the directory
- * is in the ail and use lock_nowait. If we can't lock, we need to
- * drop the inode lock on the directory and try again. xfs_iunlock will
- * potentially push the tail if we were holding up the log.
- */
-STATIC int
-xfs_lock_dir_and_entry(
- xfs_inode_t *dp,
- xfs_inode_t *ip) /* inode of entry 'name' */
-{
- int attempts;
- xfs_ino_t e_inum;
- xfs_inode_t *ips[2];
- xfs_log_item_t *lp;
-
-#ifdef DEBUG
- xfs_rm_locks++;
-#endif
- attempts = 0;
-
-again:
- xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
-
- e_inum = ip->i_ino;
-
- xfs_itrace_ref(ip);
-
- /*
- * We want to lock in increasing inum. Since we've already
- * acquired the lock on the directory, we may need to release
- * if if the inum of the entry turns out to be less.
- */
- if (e_inum > dp->i_ino) {
- /*
- * We are already in the right order, so just
- * lock on the inode of the entry.
- * We need to use nowait if dp is in the AIL.
- */
-
- lp = (xfs_log_item_t *)dp->i_itemp;
- if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
- if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
- attempts++;
-#ifdef DEBUG
- xfs_rm_attempts++;
-#endif
-
- /*
- * Unlock dp and try again.
- * xfs_iunlock will try to push the tail
- * if the inode is in the AIL.
- */
-
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
- if ((attempts % 5) == 0) {
- delay(1); /* Don't just spin the CPU */
-#ifdef DEBUG
- xfs_rm_lock_delays++;
-#endif
- }
- goto again;
- }
- } else {
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- }
- } else if (e_inum < dp->i_ino) {
- xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
- ips[0] = ip;
- ips[1] = dp;
- xfs_lock_inodes(ips, 2, XFS_ILOCK_EXCL);
- }
- /* else e_inum == dp->i_ino */
- /* This can happen if we're asked to lock /x/..
- * the entry is "..", which is also the parent directory.
- */
-
- return 0;
-}
-
-#ifdef DEBUG
int xfs_locked_n;
int xfs_small_retries;
int xfs_middle_retries;
#endif
}
+/*
+ * xfs_lock_two_inodes() can only be used to lock one type of lock
+ * at a time - the iolock or the ilock, but not both at once. If
+ * we lock both at once, lockdep will report false positives saying
+ * we have violated locking orders.
+ */
+void
+xfs_lock_two_inodes(
+ xfs_inode_t *ip0,
+ xfs_inode_t *ip1,
+ uint lock_mode)
+{
+ xfs_inode_t *temp;
+ int attempts = 0;
+ xfs_log_item_t *lp;
+
+ if (lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL))
+ ASSERT((lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)) == 0);
+ ASSERT(ip0->i_ino != ip1->i_ino);
+
+ if (ip0->i_ino > ip1->i_ino) {
+ temp = ip0;
+ ip0 = ip1;
+ ip1 = temp;
+ }
+
+ again:
+ xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));
+
+ /*
+ * If the first lock we have locked is in the AIL, we must TRY to get
+ * the second lock. If we can't get it, we must release the first one
+ * and try again.
+ */
+ lp = (xfs_log_item_t *)ip0->i_itemp;
+ if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
+ if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
+ xfs_iunlock(ip0, lock_mode);
+ if ((++attempts % 5) == 0)
+ delay(1); /* Don't just spin the CPU */
+ goto again;
+ }
+ } else {
+ xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
+ }
+}
+
int
xfs_remove(
xfs_inode_t *dp,
goto out_trans_cancel;
}
- error = xfs_lock_dir_and_entry(dp, ip);
- if (error)
- goto out_trans_cancel;
+ xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL);
/*
* At this point, we've gotten both the directory and the entry
}
}
- /*
- * Entry must exist since we did a lookup in xfs_lock_dir_and_entry.
- */
XFS_BMAP_INIT(&free_list, &first_block);
error = xfs_dir_removename(tp, dp, name, ip->i_ino,
&first_block, &free_list, resblks);
}
xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- /*
- * Bump the in memory generation count on the parent
- * directory so that other can know that it has changed.
- */
- dp->i_gen++;
- xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
-
if (is_dir) {
/*
* Drop the link from ip's "..".
goto out_bmap_cancel;
/*
- * Drop the link from dp to ip.
+ * Drop the "." link from ip to self.
*/
error = xfs_droplink(tp, ip);
if (error)
} else {
/*
* When removing a non-directory we need to log the parent
- * inode here for the i_gen update. For a directory this is
- * done implicitly by the xfs_droplink call for the ".." entry.
+ * inode here. For a directory this is done implicitly
+ * by the xfs_droplink call for the ".." entry.
*/
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
}
/*
- * Drop the "." link from ip to self.
+ * Drop the link from dp to ip.
*/
error = xfs_droplink(tp, ip);
if (error)
{
xfs_mount_t *mp = tdp->i_mount;
xfs_trans_t *tp;
- xfs_inode_t *ips[2];
int error;
xfs_bmap_free_t free_list;
xfs_fsblock_t first_block;
goto error_return;
}
- if (sip->i_ino < tdp->i_ino) {
- ips[0] = sip;
- ips[1] = tdp;
- } else {
- ips[0] = tdp;
- ips[1] = sip;
- }
-
- xfs_lock_inodes(ips, 2, XFS_ILOCK_EXCL);
+ xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);
/*
* Increment vnode ref counts since xfs_trans_commit &
if (error)
goto abort_return;
xfs_ichgtime(tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- tdp->i_gen++;
xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
error = xfs_bumplink(tp, sip);
* Make sure that we have allocated dquot(s) on disk.
*/
error = XFS_QM_DQVOPALLOC(mp, dp,
- current_fsuid(credp), current_fsgid(credp), prid,
+ current_fsuid(), current_fsgid(), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
if (error)
goto std_return;
}
xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
- /*
- * Bump the in memory version number of the parent directory
- * so that other processes accessing it will recognize that
- * the directory has changed.
- */
- dp->i_gen++;
-
error = xfs_dir_init(tp, cdp, dp);
if (error)
goto error2;
- cdp->i_gen = 1;
error = xfs_bumplink(tp, dp);
if (error)
goto error2;
* Make sure that we have allocated dquot(s) on disk.
*/
error = XFS_QM_DQVOPALLOC(mp, dp,
- current_fsuid(credp), current_fsgid(credp), prid,
+ current_fsuid(), current_fsgid(), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
if (error)
goto std_return;
xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
/*
- * Bump the in memory version number of the parent directory
- * so that other processes accessing it will recognize that
- * the directory has changed.
- */
- dp->i_gen++;
-
- /*
* If this is a synchronous mount, make sure that the
* symlink transaction goes to disk before returning to
* the user.
xfs_reclaim(
xfs_inode_t *ip)
{
- bhv_vnode_t *vp = VFS_I(ip);
xfs_itrace_entry(ip);
- ASSERT(!VN_MAPPED(vp));
+ ASSERT(!VN_MAPPED(VFS_I(ip)));
/* bad inode, get out here ASAP */
- if (VN_BAD(vp)) {
+ if (VN_BAD(VFS_I(ip))) {
xfs_ireclaim(ip);
return 0;
}
if (!ip->i_update_core && (ip->i_itemp == NULL)) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_iflock(ip);
- return xfs_finish_reclaim(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
- } else {
- xfs_mount_t *mp = ip->i_mount;
-
- /* Protect sync and unpin from us */
- XFS_MOUNT_ILOCK(mp);
- spin_lock(&ip->i_flags_lock);
- __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
- vp->i_private = NULL;
- ip->i_vnode = NULL;
- spin_unlock(&ip->i_flags_lock);
- list_add_tail(&ip->i_reclaim, &mp->m_del_inodes);
- XFS_MOUNT_IUNLOCK(mp);
- }
- return 0;
-}
-
-int
-xfs_finish_reclaim(
- xfs_inode_t *ip,
- int locked,
- int sync_mode)
-{
- xfs_perag_t *pag = xfs_get_perag(ip->i_mount, ip->i_ino);
- bhv_vnode_t *vp = VFS_I(ip);
-
- if (vp && VN_BAD(vp))
- goto reclaim;
-
- /* The hash lock here protects a thread in xfs_iget_core from
- * racing with us on linking the inode back with a vnode.
- * Once we have the XFS_IRECLAIM flag set it will not touch
- * us.
- */
- write_lock(&pag->pag_ici_lock);
- spin_lock(&ip->i_flags_lock);
- if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
- (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) && vp == NULL)) {
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- if (locked) {
- xfs_ifunlock(ip);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- }
- return 1;
- }
- __xfs_iflags_set(ip, XFS_IRECLAIM);
- spin_unlock(&ip->i_flags_lock);
- write_unlock(&pag->pag_ici_lock);
- xfs_put_perag(ip->i_mount, pag);
-
- /*
- * If the inode is still dirty, then flush it out. If the inode
- * is not in the AIL, then it will be OK to flush it delwri as
- * long as xfs_iflush() does not keep any references to the inode.
- * We leave that decision up to xfs_iflush() since it has the
- * knowledge of whether it's OK to simply do a delwri flush of
- * the inode or whether we need to wait until the inode is
- * pulled from the AIL.
- * We get the flush lock regardless, though, just to make sure
- * we don't free it while it is being flushed.
- */
- if (!locked) {
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- xfs_iflock(ip);
+ xfs_iflags_set(ip, XFS_IRECLAIMABLE);
+ return xfs_reclaim_inode(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
}
-
- /*
- * In the case of a forced shutdown we rely on xfs_iflush() to
- * wait for the inode to be unpinned before returning an error.
- */
- if (xfs_iflush(ip, sync_mode) == 0) {
- /* synchronize with xfs_iflush_done */
- xfs_iflock(ip);
- xfs_ifunlock(ip);
- }
-
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
- reclaim:
- xfs_ireclaim(ip);
- return 0;
-}
-
-int
-xfs_finish_reclaim_all(xfs_mount_t *mp, int noblock)
-{
- int purged;
- xfs_inode_t *ip, *n;
- int done = 0;
-
- while (!done) {
- purged = 0;
- XFS_MOUNT_ILOCK(mp);
- list_for_each_entry_safe(ip, n, &mp->m_del_inodes, i_reclaim) {
- if (noblock) {
- if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL) == 0)
- continue;
- if (xfs_ipincount(ip) ||
- !xfs_iflock_nowait(ip)) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- continue;
- }
- }
- XFS_MOUNT_IUNLOCK(mp);
- if (xfs_finish_reclaim(ip, noblock,
- XFS_IFLUSH_DELWRI_ELSE_ASYNC))
- delay(1);
- purged = 1;
- break;
- }
-
- done = !purged;
- }
-
- XFS_MOUNT_IUNLOCK(mp);
+ xfs_inode_set_reclaim_tag(ip);
return 0;
}
/*
* Zero file bytes between startoff and endoff inclusive.
* The iolock is held exclusive and no blocks are buffered.
+ *
+ * This function is used by xfs_free_file_space() to zero
+ * partial blocks when the range to free is not block aligned.
+ * When unreserving space with boundaries that are not block
+ * aligned we round up the start and round down the end
+ * boundaries and then use this function to zero the parts of
+ * the blocks that got dropped during the rounding.
*/
STATIC int
xfs_zero_remaining_bytes(
int nimap;
int error = 0;
+ /*
+ * Avoid doing I/O beyond eof - it's not necessary
+ * since nothing can read beyond eof. The space will
+ * be zeroed when the file is extended anyway.
+ */
+ if (startoff >= ip->i_size)
+ return 0;
+
+ if (endoff > ip->i_size)
+ endoff = ip->i_size;
+
bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize,
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp);
xfs_off_t len,
int attr_flags)
{
- bhv_vnode_t *vp;
int committed;
int done;
xfs_off_t end_dmi_offset;
xfs_trans_t *tp;
int need_iolock = 1;
- vp = VFS_I(ip);
mp = ip->i_mount;
xfs_itrace_entry(ip);
rounding = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
ioffset = offset & ~(rounding - 1);
- if (VN_CACHED(vp) != 0) {
+ if (VN_CACHED(VFS_I(ip)) != 0) {
xfs_inval_cached_trace(ip, ioffset, -1, ioffset, -1);
error = xfs_flushinval_pages(ip, ioffset, -1, FI_REMAPF_LOCKED);
if (error)
int cmd,
xfs_flock64_t *bf,
xfs_off_t offset,
- cred_t *credp,
int attr_flags)
{
xfs_mount_t *mp = ip->i_mount;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = startoffset;
- error = xfs_setattr(ip, &iattr, attr_flags, credp);
+ error = xfs_setattr(ip, &iattr, attr_flags);
if (error)
return error;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff